阅读说明：本技术 一种房颤信号的分类方法、装置、终端以及存储介质 (Atrial fibrillation signal classification method, device, terminal and storage medium ) 是由 刘陆洋 郭光明 陈茂林 李露平 于 2019-11-22 设计创作，主要内容包括：本申请适用于生命特征识别技术领域,提供了一种房颤信号的分类方法、装置、终端以及存储介质,该方法包括：获取多个用户的房颤信号；对多个所述房颤信号进行聚类操作,得到至少一个房颤聚类组；分别识别各个所述房颤聚类组对应的房颤类型。本申请提供的技术方案通过聚类的方式获取到与该用户存在相同或相似的房颤信号的其他用户划分至同一组别内,并为不同的组别进行类型识别,实现了精准化的房颤分类和相对风险定级,提高了房颤分类的准确性以及用户的使用体验,方便和指引健康领域从业人员和用户确定身体健康状况和定位相对风险等级。(The application is suitable for the technical field of vital sign recognition, and provides a classification method, a device, a terminal and a storage medium for atrial fibrillation signals, wherein the method comprises the following steps: acquiring atrial fibrillation signals of a plurality of users; clustering a plurality of atrial fibrillation signals to obtain at least one atrial fibrillation cluster group; and respectively identifying the type of the atrial fibrillation corresponding to each atrial fibrillation cluster group. According to the technical scheme, other users who have the same or similar atrial fibrillation signals with the user are obtained through a clustering mode and are divided into the same group, type identification is carried out on different groups, accurate atrial fibrillation classification and relative risk grading are achieved, the accuracy of atrial fibrillation classification and the use experience of the user are improved, and health field practitioners and the user can be conveniently guided to determine the body health condition and position the relative risk grade.)

1. A method for classifying atrial fibrillation signals, comprising:

acquiring atrial fibrillation signals of a plurality of users;

clustering a plurality of atrial fibrillation signals to obtain at least one atrial fibrillation cluster group;

and respectively identifying the type of the atrial fibrillation corresponding to each atrial fibrillation cluster group.

2. The method of classifying according to claim 1, wherein said clustering a plurality of said atrial fibrillation signals to obtain at least one atrial fibrillation cluster group comprises:

establishing an atrial fibrillation time sequence of the user based on the atrial fibrillation signals;

according to the atrial fibrillation time sequence, respectively calculating the atrial fibrillation similarity among the users;

and dividing a plurality of atrial fibrillation signals corresponding to the users with the similarity larger than a preset similarity threshold into the same atrial fibrillation clustering group.

3. The classification method according to claim 2, wherein the calculating of the atrial fibrillation similarity between the users according to the atrial fibrillation time sequence comprises:

calculating a distance value between the atrial fibrillation time sequence of the user and the atrial fibrillation time sequence of each user through a dynamic time warping algorithm, and constructing a distance feature vector related to the user;

the dividing the atrial fibrillation signals corresponding to the plurality of users with the similarity greater than a preset similarity threshold into the same atrial fibrillation clustering group comprises:

generating an N-dimensional distance feature matrix according to the distance feature vectors of the N users; the N is the total number of all the users;

projecting the N-dimensional distance characteristic matrix to a K-dimensional clustering matrix through a principal component analysis algorithm; k is the group number of the atrial fibrillation cluster group;

and dividing the atrial fibrillation signals of all the users into K atrial fibrillation clustering groups according to the K-dimensional clustering matrix.

4. The classification method according to claim 2, wherein the calculating of the atrial fibrillation similarity between the users according to the atrial fibrillation time sequence comprises:

identifying the number of elements contained in each atrial fibrillation time sequence;

and if the difference value between the element numbers corresponding to any two users is smaller than a preset window threshold value, calculating the atrial fibrillation similarity between the two users.

5. The classification method according to claim 2, wherein the establishing of the atrial fibrillation time sequence of the user based on the atrial fibrillation signals comprises:

acquiring the acquisition date corresponding to each acquisition point in the atrial fibrillation signal;

if the acquisition date between any two adjacent acquisition points is not continuous, adding a compensation acquisition point with the missing date between the two acquisition points on the atrial fibrillation signal through a preset missing compensation algorithm to obtain a date continuous signal;

and outputting the atrial fibrillation time sequence according to the date continuous signal.

6. The classification method according to any one of claims 1 to 5, wherein the obtaining atrial fibrillation signals of a plurality of users comprises:

acquiring a heart rhythm signal of the user;

if the heart rhythm signal meets a preset atrial fibrillation judgment condition, configuring a collection point of a collection date corresponding to the heart rhythm signal as a first bit value;

if the heart rhythm signal does not meet the atrial fibrillation judgment condition, configuring the acquisition point of the acquisition date corresponding to the heart rhythm signal as a second bit value;

and generating the atrial fibrillation signals according to the acquisition points corresponding to all the acquisition dates.

7. The method according to any one of claims 1 to 5, further comprising, after said respectively identifying the type of atrial fibrillation corresponding to each of said groups of atrial fibrillation classes:

acquiring reminding information associated with the atrial fibrillation type;

and outputting the reminding information.

8. The method according to any one of claims 1 to 5, further comprising, after said respectively identifying the type of atrial fibrillation corresponding to each of said groups of atrial fibrillation classes:

determining a characteristic signal corresponding to each atrial fibrillation group according to the atrial fibrillation signals contained in each atrial fibrillation group;

and if a new atrial fibrillation signal of a new user is received, identifying the type of the atrial fibrillation corresponding to the new user according to the characteristic signal of each atrial fibrillation cluster group and the new atrial fibrillation signal.

9. The method of claim 8, wherein if a new atrial fibrillation signal is received from a new user, identifying the type of atrial fibrillation corresponding to the new user according to the feature signal of each group of atrial fibrillation classes and the new atrial fibrillation signal comprises:

generating an atrial fibrillation classification model through each characteristic signal;

and leading the newly added atrial fibrillation signals into the atrial fibrillation classification model, and determining the type of the atrial fibrillation corresponding to the newly added user.

10. An apparatus for classifying atrial fibrillation signals, comprising:

the atrial fibrillation signal acquisition unit is used for acquiring atrial fibrillation signals of a plurality of users;

the atrial fibrillation clustering execution unit is used for clustering a plurality of atrial fibrillation signals to obtain at least one atrial fibrillation cluster group;

and the atrial fibrillation type identification unit is used for respectively identifying the type of the atrial fibrillation corresponding to each atrial fibrillation cluster group.

11. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 9 when executing the computer program.

12. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 9.

Technical Field

The application belongs to the technical field of vital sign recognition, and particularly relates to a classification method, a classification device, a classification terminal and a storage medium for atrial fibrillation signals.

Background

Atrial fibrillation, abbreviated as atrial fibrillation, is the most common persistent chronic cardiac arrhythmia, often resulting from chaotic atrial activity and irregular atrial compression. With the continuous improvement of the health attention of people and the gradual increase of the incidence of atrial fibrillation, how to accurately determine the type of atrial fibrillation of a patient and the severity of the atrial fibrillation behavior of the patient determined by the type of atrial fibrillation is very important for the patient to make a treatment scheme and adjust the treatment behaviors such as daily work and rest. The existing atrial fibrillation identification technology judges whether the atrial fibrillation condition exists in a user or not by collecting a heart rhythm signal of the user, but cannot determine the atrial fibrillation type of the user under the condition of the atrial fibrillation, cannot classify the atrial fibrillation according to different users, and carries out grading on the severity.

Content of application

The embodiment of the application provides a classification method, a device, a terminal and a storage medium for atrial fibrillation signals, can solve the existing atrial fibrillation identification technology, can only identify whether the atrial fibrillation condition exists or not, cannot determine the type of atrial fibrillation of the user, cannot give fine atrial fibrillation classification to different users, and solves the problem that the accuracy of atrial fibrillation detection is low.

In a first aspect, an embodiment of the present application provides a method for classifying atrial fibrillation signals, including:

acquiring atrial fibrillation signals of a plurality of users;

clustering a plurality of atrial fibrillation signals to obtain at least one atrial fibrillation cluster group;

and respectively identifying the type of the atrial fibrillation corresponding to each atrial fibrillation cluster group.

In a possible implementation manner of the first aspect, the clustering a plurality of atrial fibrillation signals to obtain at least one atrial fibrillation cluster group includes:

establishing an atrial fibrillation time sequence of the user based on the atrial fibrillation signals;

according to the atrial fibrillation time sequence, respectively calculating the atrial fibrillation similarity among the users;

and dividing a plurality of atrial fibrillation signals corresponding to the users with the similarity larger than a preset similarity threshold into the same atrial fibrillation clustering group.

In a possible implementation manner of the first aspect, the calculating atrial fibrillation similarities among the users according to the atrial fibrillation time series includes:

calculating a distance value between the atrial fibrillation time sequence of the user and the atrial fibrillation time sequence of each user through a dynamic time warping algorithm, and constructing a distance feature vector related to the user;

the dividing the atrial fibrillation signals corresponding to the plurality of users with the similarity greater than a preset similarity threshold into the same atrial fibrillation clustering group comprises:

generating an N-dimensional distance feature matrix according to the distance feature vectors of the N users; the N is the total number of all the users;

projecting the N-dimensional distance characteristic matrix to a K-dimensional clustering matrix through a principal component analysis algorithm; k is the group number of the atrial fibrillation cluster group;

and dividing the atrial fibrillation signals of all the users into K atrial fibrillation clustering groups according to the K-dimensional clustering matrix.

In a possible implementation manner of the first aspect, the calculating atrial fibrillation similarities among the users according to the atrial fibrillation time series includes:

identifying the number of elements contained in each atrial fibrillation time sequence;

and if the difference value between the element numbers corresponding to any two users is smaller than a preset window threshold value, calculating the atrial fibrillation similarity between the two users.

In a possible implementation manner of the first aspect, the establishing a time series of atrial fibrillation of the user based on the atrial fibrillation signal includes:

acquiring the acquisition date corresponding to each acquisition point in the atrial fibrillation signal;

if the acquisition date between any two adjacent acquisition points is not continuous, adding a compensation acquisition point with the missing date between the two acquisition points on the atrial fibrillation signal through a preset missing compensation algorithm to obtain a date continuous signal;

and outputting the atrial fibrillation time sequence according to the date continuous signal.

In a possible implementation manner of the first aspect, the acquiring atrial fibrillation signals of multiple users includes:

acquiring a heart rhythm signal of the user;

if the heart rhythm signal meets a preset atrial fibrillation judgment condition, configuring a collection point of a collection date corresponding to the heart rhythm signal as a first bit value;

if the heart rhythm signal does not meet the atrial fibrillation judgment condition, configuring the acquisition point of the acquisition date corresponding to the heart rhythm signal as a second bit value;

and generating the atrial fibrillation signals according to the acquisition points corresponding to all the acquisition dates.

In a possible implementation manner of the first aspect, after the respectively identifying the types of atrial fibrillation corresponding to the respective groups of atrial fibrillation clusters, the method further includes:

acquiring reminding information associated with the atrial fibrillation type;

and outputting the reminding information.

In a possible implementation manner of the first aspect, after the respectively identifying the types of atrial fibrillation corresponding to the respective groups of atrial fibrillation clusters, the method further includes:

determining a characteristic signal corresponding to each atrial fibrillation group according to the atrial fibrillation signals contained in each atrial fibrillation group;

and if a new atrial fibrillation signal of a new user is received, identifying the type of the atrial fibrillation corresponding to the new user according to the characteristic signal of each atrial fibrillation cluster group and the new atrial fibrillation signal.

In a possible implementation manner of the first aspect, if a new atrial fibrillation signal of a new user is received, identifying the type of atrial fibrillation corresponding to the new user according to the feature signal of each atrial fibrillation cluster group and the new atrial fibrillation signal includes:

generating an atrial fibrillation classification model through each characteristic signal;

and leading the newly added atrial fibrillation signals into the atrial fibrillation classification model, and determining the type of the atrial fibrillation corresponding to the newly added user.

In a second aspect, an embodiment of the present application provides an apparatus for classifying atrial fibrillation signals, including:

the atrial fibrillation signal acquisition unit is used for acquiring atrial fibrillation signals of a plurality of users;

the atrial fibrillation clustering execution unit is used for clustering a plurality of atrial fibrillation signals to obtain at least one atrial fibrillation cluster group;

and the atrial fibrillation type identification unit is used for respectively identifying the type of the atrial fibrillation corresponding to each atrial fibrillation cluster group.

In a third aspect, an embodiment of the present application provides a terminal device, a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the method for classifying atrial fibrillation signals according to any one of the first aspect when executing the computer program.

In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program, where the computer program is executed by a processor to implement the method for classifying atrial fibrillation signals according to any one of the first aspect.

In a fifth aspect, the present application provides a computer program product, which when run on a terminal device, causes the terminal device to execute the method for classifying atrial fibrillation signals according to any one of the above first aspects.

It is understood that the beneficial effects of the second aspect to the fifth aspect can be referred to the related description of the first aspect, and are not described herein again.

Compared with the prior art, the embodiment of the application has the advantages that:

this application embodiment is through the atrial fibrillation signal that acquires a plurality of users to clustering operation is carried out to a plurality of atrial fibrillation signals, the user that will have the same or similar atrial fibrillation phenomenon divides to same atrial fibrillation cluster group, and discerns the type of atrial fibrillation that each atrial fibrillation cluster group corresponds, has realized the classification to the atrial fibrillation signal. Compared with the existing atrial fibrillation identification technology, the method and the device have the advantages that whether atrial fibrillation exists in the user is not determined singly, other users who have the same or similar atrial fibrillation signals with the user can be obtained in a clustering mode and are divided into the same group, type identification is carried out on different groups, accurate atrial fibrillation classification is achieved, the physical condition of the user can be determined conveniently, and the accuracy of atrial fibrillation classification and the use experience of the user are improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.

Fig. 1 is a block diagram of a partial structure of a mobile phone provided in an embodiment of the present application;

FIG. 2 is a block diagram of a classification system for atrial fibrillation signals according to an embodiment of the present application;

FIG. 3 is a block diagram of a classification system for atrial fibrillation signals according to another embodiment of the present application;

fig. 4 is a flowchart of an implementation of a method for classifying atrial fibrillation signals according to a first embodiment of the present application;

FIG. 5 is a schematic diagram of a waveform of an atrial fibrillation signal provided by an embodiment of the present application;

FIG. 6 is a waveform diagram of atrial fibrillation signals for two users according to an embodiment of the present application;

FIG. 7 is a schematic diagram illustrating classification of atrial fibrillation signals according to an embodiment of the present application;

fig. 8 is a flowchart illustrating a detailed implementation of a method S402 for classifying atrial fibrillation signals according to a second embodiment of the present application;

fig. 9 is a flowchart of a detailed implementation of the methods S4022 and S4023 for classifying atrial fibrillation signals according to the third embodiment of the present application;

FIG. 10 is a schematic diagram illustrating a generation of an N-dimensional distance feature matrix according to an embodiment of the present application;

FIG. 11 is a schematic diagram of clustering of atrial fibrillation signals provided by an embodiment of the present application;

fig. 12 is a flowchart of a detailed implementation of a method S4022 for classifying atrial fibrillation signals according to a fourth embodiment of the present application;

fig. 13 is a flowchart of a detailed implementation of a method S4021 for classifying atrial fibrillation signals according to a fifth embodiment of the present application;

fig. 14 is a flowchart illustrating a detailed implementation of a method S401 for classifying atrial fibrillation signals according to a sixth embodiment of the present application;

fig. 15 is a flowchart illustrating a detailed implementation of a method for classifying atrial fibrillation signals according to a seventh embodiment of the present application;

FIG. 16 is a schematic diagram of a reminder message provided in accordance with an embodiment of the present application;

fig. 17 is a flowchart illustrating a detailed implementation of a method for classifying atrial fibrillation signals according to an eighth embodiment of the present application;

fig. 18 is a flowchart illustrating an implementation of a method for classifying atrial fibrillation signals S1702 according to a ninth embodiment of the present application;

fig. 19 is a block diagram illustrating an apparatus for classifying atrial fibrillation signals according to an embodiment of the present application;

fig. 20 is a schematic diagram of a terminal device according to another embodiment of the present application.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

It should also be understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

As used in this specification and the appended claims, the term "if" may be interpreted contextually as "when", "upon" or "in response to" determining "or" in response to detecting ". Similarly, the phrase "if it is determined" or "if a [ described condition or event ] is detected" may be interpreted contextually to mean "upon determining" or "in response to determining" or "upon detecting [ described condition or event ]" or "in response to detecting [ described condition or event ]".

Furthermore, in the description of the present application and the appended claims, the terms "first," "second," "third," and the like are used for distinguishing between descriptions and not necessarily for describing or implying relative importance.

Reference throughout this specification to "one embodiment" or "some embodiments," or the like, means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," or the like, in various places throughout this specification are not necessarily all referring to the same embodiment, but rather "one or more but not all embodiments" unless specifically stated otherwise. The terms "comprising," "including," "having," and variations thereof mean "including, but not limited to," unless expressly specified otherwise.

The classification method for atrial fibrillation signals provided by the embodiment of the application can be applied to mobile phones, tablet computers, wearable devices, vehicle-mounted devices, Augmented Reality (AR)/Virtual Reality (VR) devices, notebook computers, ultra-mobile personal computers (UMPCs), netbooks, Personal Digital Assistants (PDAs) and other terminal devices, and can also be applied to databases, servers and service response systems based on terminal artificial intelligence.

For example, the terminal device may be a Station (ST) in a WLAN, and may be a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with Wireless communication capability, a computing device or other processing device connected to a Wireless modem, a computer, a laptop, a handheld communication device, a handheld computing device, and/or other devices for communicating on a Wireless system, and a next generation communication system, such as a Mobile terminal in a 5G Network or a Mobile terminal in a future evolved Public Land Mobile Network (PLMN) Network, and so on.

By way of example and not limitation, when the terminal device is a wearable device, the wearable device may also be a generic term for intelligently designing daily wearing by applying wearable technology, developing wearable devices, such as glasses, gloves, watches, clothing, shoes, and the like. The wearable device is worn directly on the body, or is a portable device integrated into the clothing or accessories of the user, and collects atrial fibrillation signals of the user by being attached to the user. The wearable device is not only a hardware device, but also realizes powerful functions through software support, data interaction and cloud interaction. The generalized wearable intelligent device has the advantages that the generalized wearable intelligent device is complete in function and large in size, can realize complete or partial functions without depending on a smart phone, such as a smart watch or smart glasses, and only is concentrated on a certain application function, and needs to be matched with other devices such as the smart phone for use, such as various smart bracelets for monitoring physical signs, smart jewelry and the like.

Take the terminal device as a mobile phone as an example. Fig. 1 is a block diagram illustrating a partial structure of a mobile phone according to an embodiment of the present disclosure. Referring to fig. 1, the cellular phone includes: radio Frequency (RF) circuit 110, memory 120, input unit 130, display unit 140, sensor 150, audio circuit 160, near field communication module 170, processor 180, and power supply 190. Those skilled in the art will appreciate that the handset configuration shown in fig. 1 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.

The following describes each component of the mobile phone in detail with reference to fig. 1:

the RF circuit 110 may be used for receiving and transmitting signals during information transmission and reception or during a call, and in particular, receives downlink information of a base station and then processes the received downlink information to the processor 180; in addition, the data for designing uplink is transmitted to the base station. Typically, the RF circuitry includes, but is not limited to, an antenna, at least one Amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like. In addition, the RF circuitry 110 may also communicate with networks and other devices via wireless communications. The wireless communication may use any communication standard or protocol, including but not limited to Global System for Mobile communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE)), e-mail, Short Messaging Service (SMS), etc., and the RF circuit 110 receives atrial fibrillation signals of the user fed back from other terminals.

The memory 120 may be used to store software programs and modules, and the processor 180 executes various functional applications and data processing of the mobile phone by operating the software programs and modules stored in the memory 120, for example, storing the received atrial fibrillation signals in the memory 120. The memory 120 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. Further, the memory 120 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.

The input unit 130 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the cellular phone 100. Specifically, the input unit 130 may include a touch panel 131 and other input devices 132. The touch panel 131, also referred to as a touch screen, may collect touch operations of a user on or near the touch panel 131 (e.g., operations of the user on or near the touch panel 131 using any suitable object or accessory such as a finger or a stylus pen), and drive the corresponding connection device according to a preset program.

The display unit 140 may be used to display information input by the user or information provided to the user and various menus of the mobile phone, such as an atrial fibrillation signal received by the user and a recognition result output after the category of the atrial fibrillation signal is determined. The Display unit 140 may include a Display panel 141, and optionally, the Display panel 141 may be configured in the form of a Liquid Crystal Display (LCD), an Organic Light-Emitting Diode (OLED), or the like. Further, the touch panel 131 can cover the display panel 141, and when the touch panel 131 detects a touch operation on or near the touch panel 131, the touch operation is transmitted to the processor 180 to determine the type of the touch event, and then the processor 180 provides a corresponding visual output on the display panel 141 according to the type of the touch event. Although the touch panel 131 and the display panel 141 are shown as two separate components in fig. 1 to implement the input and output functions of the mobile phone, in some embodiments, the touch panel 131 and the display panel 141 may be integrated to implement the input and output functions of the mobile phone.

The handset 100 may also include at least one sensor 150, such as a light sensor, motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor that adjusts the brightness of the display panel 141 according to the brightness of ambient light, and a proximity sensor that turns off the display panel 141 and/or the backlight when the mobile phone is moved to the ear. As one of the motion sensors, the accelerometer sensor can detect the magnitude of acceleration in each direction (generally, three axes), can detect the magnitude and direction of gravity when stationary, and can be used for applications of recognizing the posture of a mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer and tapping), and the like; as for other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which can be configured on the mobile phone, further description is omitted here. Further, if the terminal device can be used for collecting atrial fibrillation signals of the user, the terminal device can be further provided with an electrocardio sensor, the electrocardio sensor is used for obtaining the electrocardio signals of the user, and the electrocardio signals are converted into the atrial fibrillation signals.

Audio circuitry 160, speaker 161, and microphone 162 may provide an audio interface between the user and the handset. The audio circuit 160 may transmit the electrical signal converted from the received audio data to the speaker 161, and convert the electrical signal into a sound signal for output by the speaker 161; on the other hand, the microphone 162 converts the collected sound signal into an electrical signal, which is received by the audio circuit 160 and converted into audio data, which is then processed by the audio data output processor 180 and then transmitted to, for example, another cellular phone via the RF circuit 110, or the audio data is output to the memory 120 for further processing. For example, the terminal device may play the classification result of the atrial fibrillation signal through the audio circuit 160, and notify the user by means of a voice signal.

The terminal device may receive atrial fibrillation signals sent by other devices through the near field communication module 170, for example, the near field communication module 170 is integrated with a bluetooth communication module, establishes communication connection with the wearable device through the bluetooth communication module, and receives atrial fibrillation signals fed back by the wearable device. Although fig. 1 shows the near field communication module 170, it is understood that it does not belong to the essential constitution of the cellular phone 100, and may be omitted entirely as needed within the scope not changing the essence of the application.

The processor 180 is a control center of the mobile phone, connects various parts of the entire mobile phone by using various interfaces and lines, and performs various functions of the mobile phone and processes data by operating or executing software programs and/or modules stored in the memory 120 and calling data stored in the memory 120, thereby integrally monitoring the mobile phone. Alternatively, processor 180 may include one or more processing units; preferably, the processor 180 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 180.

The handset 100 also includes a power supply 190 (e.g., a battery) for powering the various components, which may preferably be logically connected to the processor 180 via a power management system, such that the power management system may be used to manage charging, discharging, and power consumption.

Fig. 2 is a block diagram illustrating a classification system for atrial fibrillation signals according to an embodiment of the present application. Referring to fig. 2, the classification system of atrial fibrillation signals includes a mobile terminal 210, a wearable device 220 and a remote communication terminal 230. The mobile terminal 210 and the wearable device 220 may establish a communication connection through a near field communication manner, and the remote communication terminal 230 and the mobile terminal 210 may communicate through a wired and/or wireless network.

The classification device for atrial fibrillation signals provided by the present application is specifically a mobile terminal 210 used by a user. The mobile terminal 210 can receive atrial fibrillation signals sent by other devices, for example, the mobile terminal can establish communication connection with the wearable device 220 through near field communication modes such as a bluetooth communication mode or a WIFI communication mode, receive atrial fibrillation signals sent by the wearable device 220, can also establish communication with other far-end communication terminals 230 through remote communication modes such as a wired communication mode or a wireless communication mode, receive atrial fibrillation signals sent by the far-end communication terminals 230, perform clustering operation on the atrial fibrillation signals by receiving the atrial fibrillation signals of a plurality of different users, and perform subsequent classification and identification.

Wearable device 220 is specifically configured to collect a biometric signal of a user, where the biometric signal may be an originally collected electrocardiographic signal or an atrial fibrillation signal generated by processing with an atrial fibrillation recognition algorithm. If the acquired electrocardiosignals are electrocardiosignals, the original electrocardiosignals can be sent to the mobile terminal 210, atrial fibrillation is identified through the electrocardiosignals by the mobile terminal 210, and the electrocardiosignals are converted into atrial fibrillation signals; after the electrocardiosignals are converted into atrial fibrillation signals by a processing module arranged in the wearable device 220, the atrial fibrillation signals are sent to the mobile terminal 210.

The remote communication terminal 230 may be a user terminal located at a remote end, or may be the wearable device 220, and is configured to acquire atrial fibrillation signals of other users and send the atrial fibrillation signals to the mobile terminal 210 through a communication link with the mobile terminal 210. Of course, remote communication terminal 230 may receive atrial fibrillation signals transmitted by mobile terminal 210.

Fig. 3 shows a block diagram of a classification system for atrial fibrillation signals according to another embodiment of the present application. Referring to fig. 3, the classification system of atrial fibrillation signals includes a server 310, a terminal device 320, and a wearable device 330. Wherein the server 310 and the terminal device 320 and the wearable device 330 may communicate over a wired and/or wireless network.

The server 310 may receive atrial fibrillation signals sent by other devices, that is, the server belongs to a cloud device, for example, the server receives atrial fibrillation signals fed back by the terminal device 320 and the wearable device 330. Optionally, other devices may be installed with a client program matching server 310, and package the acquired atrial fibrillation signals through the client program and send the packaged atrial fibrillation signals to server 310, and then server 310 may cluster a plurality of atrial fibrillation signals after receiving the atrial fibrillation signals fed back by other devices, and identify the type corresponding to each atrial fibrillation signal.

The mobile terminal 320 may be a terminal device used by a user, an electrocardiogram sensor may be built in the mobile terminal 320, the electrocardiogram sensor acquires an electrocardiogram signal of the user, and generates a corresponding atrial fibrillation signal based on the electrocardiogram signal, and then sends the atrial fibrillation signal to the server 310 through a client installed locally. The mobile terminal 320 may further be configured with a communication module, such as a bluetooth communication module or a WIFI communication module, and receive atrial fibrillation signals fed back by the wearable device used by the user through the communication module, and send the atrial fibrillation signals to the server 310 through a client program installed locally.

The wearable device 330 may be an intelligent wearable device, may be equipped with a client program matched with the server 310, and after acquiring atrial fibrillation signals or cardiac electrical signals of the user, sends the acquired signals to the server 310 through the client program.

In the embodiment of the present application, the main execution subject of the procedure is a classification device of atrial fibrillation signals. By way of example and not limitation, the classification device of atrial fibrillation signals may specifically be a cloud server, and performs clustering operation on the atrial fibrillation signals by receiving atrial fibrillation signals of different users to determine types of atrial fibrillation in different groups of atrial fibrillation clusters. Fig. 1 shows a flowchart of an implementation of a classification method for atrial fibrillation signals according to a first embodiment of the present application, which is detailed as follows:

in S401, atrial fibrillation signals of a plurality of users are acquired.

In this embodiment, the atrial fibrillation signal may be an electrocardiographic signal obtained by a wearable device or an electrocardiographic acquisition device, and the wearable device and the electrocardiographic acquisition device may be configured with an Electrocardiograph (ECG) sensor or a photoplethysmography (PPG) sensor, for example, and may be used to obtain an electrocardiographic signal of a wearing user or a detected user. The wearable device can be a bracelet, a watch or other devices capable of being in contact with the skin of a user, obtains the heart rhythm value of the worn user by detecting the vasodilatation condition of the contact area, and generates the electrocardiosignal of the user based on the heart rhythm value corresponding to each acquisition moment. Under the circumstance, the wearable device or the electrocardio acquisition device directly sends the acquired original electrocardio data to the classification device of the atrial fibrillation signal, judges whether atrial fibrillation exists in the user or not after the classification device receives the electrocardio data, and classifies the atrial fibrillation of the user under the condition that the atrial fibrillation exists. In particular, the atrial fibrillation signal may be a PPG signal of the pulse of the user over a period of time, including the PPG signal during at least one episode of atrial fibrillation in the user.

Optionally, the atrial fibrillation signal may also be an atrial fibrillation signal with a day as a granularity, the wearable device or the electrocardiograph acquisition device may acquire an electrocardiograph signal of the user at a preset time interval, and determine whether a heart rate value of the user is greater than a preset atrial fibrillation trigger threshold, and if it is detected that a current heart rate value is greater than the preset atrial fibrillation trigger threshold, record a duration time during which the heart rate value is greater than the atrial fibrillation trigger threshold; if the duration is larger than a preset duration threshold, identifying that atrial fibrillation exists in the user in the current collection date, generating atrial fibrillation signals based on time granularity according to whether atrial fibrillation exists in each collection date, and sending the atrial fibrillation signals to a classification device so as to identify the type of the atrial fibrillation signals of the user.

Fig. 5 shows a waveform diagram of an atrial fibrillation signal provided by an embodiment of the present application. Referring to fig. 5, fig. 5 contains an electrocardiogram obtained by acquiring the heart rate value of the user at a plurality of acquisition moments, wherein the atrial fibrillation trigger threshold is 300, that is, when the heart rate value of the user appears more than 300 times per minute, it is determined that atrial fibrillation behavior currently exists in the user. As can be seen from the waveform diagram of the heart rate value and the time in fig. 5, when the user has atrial fibrillation behaviors in four days of 8 days, 9 days, 11 days and 12 days, the four days are marked as atrial fibrillation trigger days, so as to generate an atrial fibrillation waveform diagram, and the acquisition device can use any one of the waveform diagram of the heart rate value and the time in fig. 5 or the atrial fibrillation waveform diagram as an atrial fibrillation signal and send the atrial fibrillation signal to the classification device.

In a possible implementation mode, this wearable equipment or electrocardio collection equipment can be provided with the memory cell, the two above-mentioned equipment will gather user's atrial fibrillation signal and store in the memory cell, when detecting the atrial fibrillation signal that the memory in the memory cell satisfies preset upload threshold value, for example, the data bulk of this atrial fibrillation signal is greater than preset data bulk threshold value, or when the recording day number of this atrial fibrillation signal reachs preset day number threshold value again, can encapsulate the atrial fibrillation signal that has stored, and send the sorter for atrial fibrillation signal.

In a possible implementation manner, after receiving atrial fibrillation signals fed back by other devices, the classification device of the atrial fibrillation signals can detect monitoring duration corresponding to the atrial fibrillation signals, and if the monitoring duration is greater than or equal to preset effective duration, identify the atrial fibrillation signals as effective signals and perform subsequent clustering operation on the atrial fibrillation signals; on the contrary, if the monitoring duration of the atrial fibrillation signal is less than the effective duration, the atrial fibrillation signal is identified as an undetermined signal, the wearable equipment or the electrocardiogram device corresponding to the user continues to wait for the atrial fibrillation signals of the subsequent date to be fed back until the monitoring duration of all the atrial fibrillation signals of the user is greater than the effective duration, all the atrial fibrillation signals corresponding to the user are spliced according to the time sequence to obtain a total atrial fibrillation signal, and the subsequent related operations of S402 and S403 are executed.

In this embodiment, the sorter of the atrial fibrillation signal can receive other equipment or acquire user's atrial fibrillation signal through built-in sensor, if through other equipment, for example wearable equipment or electrocardio collection equipment etc. acquire user's atrial fibrillation signal, then can be for the above-mentioned different collection equipment configuration corresponding atrial fibrillation signal feedback cycle, collection equipment can be according to this feedback cycle, regularly sends user's atrial fibrillation signal to the sorter of atrial fibrillation signal to for the corresponding user number of this user mark, in order to distinguish different user's atrial fibrillation signal. Optionally, if the collecting device is configured with a client program corresponding to the classifying device, when the user starts the client program, the atrial fibrillation signal collected between the time when the atrial fibrillation signal is fed back last time and the current starting time may be packaged by the client program, and the atrial fibrillation signal between the two times is sent to the classifying device of the atrial fibrillation signal.

Optionally, in this embodiment, the classification device for atrial fibrillation signals may be configured with a classification triggering population, and since the atrial fibrillation signals of the user are automatically labeled and classified through the clustering operation, the accuracy of the classification operation can be ensured only when the number of samples is greater than a preset population threshold. Based on this, the classifying means may be configured with the above-mentioned number of classified triggers, and perform the operation of S402 only when it is detected that the number of users currently feeding back atrial fibrillation signals is greater than the number of classified triggers. Preferably, after each clustering and classifying operation is performed, the number threshold can be configured according to a preset adjustment step length, so that after an atrial fibrillation signal of a new user is received, the type of atrial fibrillation can be determined again and the corresponding atrial fibrillation clustering group can be obtained through division.

For example, the initial classification trigger number is 3000. After the classification device of the atrial fibrillation signals receives the atrial fibrillation signals uploaded by 3000 different users, clustering operation of the atrial fibrillation signals can be performed once, and corresponding atrial fibrillation types are marked for different atrial fibrillation clustering groups. The step length of adjustment is 300, and the sorter of the atrial fibrillation signal receives the atrial fibrillation signal of newly-increased 300 users again, and total amount that is total atrial fibrillation signal increases to 3300 when, then carry out the clustering operation of an atrial fibrillation signal again, analogize with this, carry out once clustering operation back every time, all improve 300 to categorised trigger population to can regularly carry out the clustering operation, with the accuracy of improving classification, avoid appearing new atrial fibrillation type and unable discernment, or because of the sample is less and neglect the condition emergence of some atrial fibrillation types.

In S402, a clustering operation is performed on a plurality of atrial fibrillation signals to obtain at least one atrial fibrillation cluster group.

In this embodiment, classification device of atrial fibrillation signal can carry out cluster processing to all atrial fibrillation signals after receiving the atrial fibrillation signal that comes from a plurality of different users, divides the same or similar atrial fibrillation signal of signal waveform into same atrial fibrillation cluster group, and the similarity is greater than preset similarity threshold value between the signal of two arbitrary atrial fibrillation signals that belong to same atrial fibrillation cluster group promptly.

In a possible implementation manner, the clustering operation on the atrial fibrillation signal may specifically be: and drawing any two atrial fibrillation signals on a preset coordinate system, calculating the sum of the areas of the intersection areas of the two signal waveforms, and determining the similarity between the two signal waveforms based on the sum of the areas. Specifically, if the numerical value of the area sum is larger, the similarity between two atrial fibrillation signals is smaller; conversely, if the numerical value of the area sum is smaller, the similarity between two atrial fibrillation signals is larger. Fig. 6 shows waveforms of atrial fibrillation signals of two users provided by an embodiment of the present application. Referring to fig. 6, the classification apparatus may generate atrial fibrillation signals of two users, i.e., user a and user B, on the same coordinate system, identify an intersection area between the two signals, calculate an intersection area of the intersection area, and determine a similarity between the two atrial fibrillation signals based on the intersection area. The classification device can divide two atrial fibrillation signals with the similarity larger than a preset similarity threshold into the same atrial fibrillation clustering group.

In a possible implementation mode, the classification device of the atrial fibrillation signals can be configured with a detection window, the detection window is configured with signal length, if the signal length of the atrial fibrillation signals fed back by any user is greater than the detection window, the splitting device can randomly intercept preset signal segments from the atrial fibrillation signals through the detection window, and perform clustering operation on the signal segments intercepted and obtained by the users, so that the calculation amount of the clustering operation can be reduced. For example, the detection window may be 30 days, and if the signal length of the atrial fibrillation signal fed back by a certain user is 100 days, the classification device may intercept a signal segment with the signal length of 30 days from the atrial fibrillation signal through the detection window, and perform similarity calculation on the signal segment and the atrial fibrillation signals or signal segments of other users. It should be noted that, if the signal length of an atrial fibrillation signal of a certain user is smaller than the window size of the detection window, no intercepting operation is needed, in this case, if the similarity between two atrial fibrillation signals is calculated in the intersection area manner, the atrial fibrillation signal with a shorter signal length may be slid on the waveform of another atrial fibrillation signal with a longer signal length, the intersection area corresponding to each time in the sliding process is calculated, the intersection area with the smallest value is selected as the feature area, and the similarity between the two atrial fibrillation signals is calculated based on the feature area.

Because the classification means of current atrial fibrillation type mainly is based on carrying out simple classification in medical science, specifically divide into initial atrial fibrillation, paroxysmal atrial fibrillation, continuation atrial fibrillation, permanent atrial fibrillation four according to the duration of the behavior of atrial fibrillation, and also only limited approximate scope in the classification based on duration, the duration that normal condition lasts after the behavior of atrial fibrillation stops does not define, it is thus visible, current classification mode precision of type of atrial fibrillation is lower. Illustratively, table 1 shows the classification rules for one atrial fibrillation type in the prior art.

TABLE 1

In the embodiment, clustering operation is performed on the acquired atrial fibrillation signals of a plurality of users, so that the collected atrial fibrillation signals can be divided into a plurality of different atrial fibrillation cluster groups, and the type of the atrial fibrillation which is not determined in the current classification means can be identified. For example, the existing classification method divides the atrial fibrillation signals into the four types, and after clustering operation, the number of the obtained atrial fibrillation cluster groups is 9, that is, there are 9 types in the atrial fibrillation signals, so that the atrial fibrillation types which are not identified in the prior art can be made up, and the purpose of automatically labeling the atrial fibrillation types is achieved.

In S403, the type of atrial fibrillation corresponding to each atrial fibrillation cluster group is identified.

In this embodiment, classification apparatus of atrial fibrillation signal has confirmed that a plurality of atrial fibrillation signals can divide the atrial fibrillation cluster group that obtains after, can gather the signal characteristic of the signal for the corresponding atrial fibrillation type of group mark for each atrial fibrillation according to the signal characteristic of the atrial fibrillation signal that each atrial fibrillation cluster group contains to all the atrial fibrillation signals of this atrial fibrillation cluster group all discern the type of atrial fibrillation that this atrial fibrillation cluster group corresponds.

Optionally, the sorter of the atrial fibrillation signal can mark the corresponding dimension grade for the dimension of different atrial fibrillation to make up according to the dimension grade of each atrial fibrillation dimension, obtain the type of atrial fibrillation, for example, this dimension of atrial fibrillation can be for the duration of atrial fibrillation, the intensity of atrial fibrillation and/or the interval duration of atrial fibrillation. Specifically, sorter can extract the representative characteristic signal in each group of the atrial fibrillation, and discern the length of duration and the intensity of the atrial fibrillation of this characteristic signal, according to the characteristic signal that all groups of the group of the atrial fibrillation correspond, based on the difference between the length of duration of the atrial fibrillation, divide into a plurality of lengths of duration grades, and based on the difference between the intensity of the atrial fibrillation, divide into a plurality of intensity grades, according to length of duration grade and intensity grade, for the type of the atrial fibrillation that the group mark of the atrial fibrillation of difference corresponds. If the atrial fibrillation duration of any two atrial fibrillation cluster groups is the same, the atrial fibrillation cluster groups can be distinguished through the difference of the intensity levels of the atrial fibrillation; if the intensity levels of any two groups of atrial fibrillation clusters are the same, the groups can be distinguished by the difference of the duration of atrial fibrillation.

For example, the duration of atrial fibrillation can be divided into three different levels of permanence, persistence and paroxysmal, and the duration of atrial fibrillation can be divided into one level of atrial fibrillation, two levels of atrial fibrillation and three levels of atrial fibrillation according to the intensity of atrial fibrillation. The sorter that the room quivered the signal is when detecting that two rooms quiver the duration of gathering group is the same, then can quiver the difference of gathering group according to the room for distinguish two different rooms, for example paroxysmal room quivers one-level and paroxysmal room quiver the second grade. If the atrial fibrillation intensity of the two atrial fibrillation signals is the same, the two atrial fibrillation signals can be distinguished according to the duration of the atrial fibrillation, such as one level of permanent atrial fibrillation and one level of paroxysmal atrial fibrillation. The specific number of the dimensions to be divided and the grade number of each dimension can be determined according to the group groups obtained by clustering and the different characteristics of the atrial fibrillation signals of each group.

For example, fig. 7 shows a schematic diagram of classification of atrial fibrillation signals provided by an embodiment of the present application. Referring to fig. 7, the classification apparatus for atrial fibrillation signals can classify types of atrial fibrillation according to two dimensions of duration of atrial fibrillation and interval time between every two atrial fibrillation activities (i.e. average duration of non-atrial fibrillation dates after normal recovery), which are respectively: permanent atrial fibrillation, persistent atrial fibrillation, paroxysmal atrial fibrillation with one level, paroxysmal atrial fibrillation with two levels, paroxysmal atrial fibrillation with three levels and paroxysmal atrial fibrillation with four levels. Wherein, the permanent atrial fibrillation is characterized in that: the duration of atrial fibrillation is longer than 100 days; persistent atrial fibrillation is characterized by: the duration of atrial fibrillation is longer than 7 days, and is approximately concentrated on about 25 days; the behavior of paroxysmal atrial fibrillation is as follows: the duration of atrial fibrillation is less than 7 days, the duration is divided into the following first level to the fourth level according to the duration of a normal state, and the severity is increased in sequence.

Above can see that, the classification method of atrial fibrillation signals provided by the embodiment of the application divides users with the same or similar atrial fibrillation phenomenon into the same atrial fibrillation cluster group by acquiring atrial fibrillation signals of a plurality of users and clustering the plurality of atrial fibrillation signals, and identifies the type of atrial fibrillation corresponding to each atrial fibrillation cluster group, thereby realizing classification of the atrial fibrillation signals. Compared with the existing atrial fibrillation identification technology, the method and the device have the advantages that whether atrial fibrillation exists in the user is not determined singly, other users who have the same or similar atrial fibrillation signals with the user can be obtained in a clustering mode and are divided into the same group, type identification is carried out on different groups, accurate atrial fibrillation classification is achieved, the physical condition of the user can be determined conveniently, and the accuracy of atrial fibrillation classification and the use experience of the user are improved.

Fig. 8 shows a flowchart of a specific implementation of a classification method S402 for atrial fibrillation signals according to the second embodiment of the present application. Referring to fig. 8, with respect to the embodiment shown in fig. 4, in the method for classifying atrial fibrillation signals provided in this embodiment, S402 includes: s4021 to S4023 are specifically described as follows:

in S4021, an atrial fibrillation time sequence of the user is established based on the atrial fibrillation signal.

In this embodiment, the classification device of the atrial fibrillation signals can preprocess the atrial fibrillation signals according to preset time granularity, so that the atrial fibrillation signals fed back by different users can be unified to the same dimension, and subsequent similarity calculation is facilitated. Because the collecting devices used by different users have differences or different collecting configurations of different collecting devices, the unit or collecting interval of the acquired atrial fibrillation signals has differences, in this case, if similarity calculation is directly performed on two signals, the situation of abnormal calculation may be caused, and when the similarity of two continuous signals is calculated, because the number of coordinate points is more, the calculation amount of the similarity can be increased, so that the atrial fibrillation signals can be discretized, and the atrial fibrillation time sequence related to the users can be obtained.

In this embodiment, the classification apparatus for atrial fibrillation signals can configure a feature value extraction algorithm, and assigns values to each element according to a signal segment corresponding to each element in an atrial fibrillation time sequence on the atrial fibrillation signals, so as to generate an atrial fibrillation time sequence with continuity and the same time dimension. Alternatively, the feature value extraction algorithm may be a mean value calculation algorithm, which calculates a signal segment corresponding to each element on the atrial fibrillation signal, calculates a mean value of the signal segment, and identifies the mean value as a bit value of the element.

It should be noted that the time granularity in the classification apparatus for atrial fibrillation signals may be day level, hour level, week level, or the like, and the setting of the specific granularity may be configured by default values of the system, or may be configured according to atrial fibrillation signals fed back by all users. For example, if the atrial fibrillation signals fed back by all users are atrial fibrillation signals acquired by taking a year as a monitoring period, because the time span is large, a month can be selected as the time granularity, the atrial fibrillation signals obtained by monitoring the users for multiple years are divided into an atrial fibrillation time sequence taking the month as a unit, and each element in the atrial fibrillation time sequence represents the atrial fibrillation characteristic value of the user in a certain month; if the atrial fibrillation signals fed back by all users are atrial fibrillation signals acquired by taking days as a monitoring period, and the maximum duration of the atrial fibrillation signals is 2 days, hours can be selected as time at the moment due to the short time span, and the atrial fibrillation value corresponding to each atrial fibrillation signal in each hour is extracted, so that an atrial fibrillation time sequence taking time as a unit is obtained.

In S4022, atrial fibrillation similarity between the users is calculated according to the atrial fibrillation time series.

In this embodiment, the classification apparatus for atrial fibrillation signals preprocesses each atrial fibrillation signal, and after obtaining the atrial fibrillation time sequences, can select the atrial fibrillation time sequences of any two users, performs similarity calculation through the two atrial fibrillation time sequences, and takes the similarity between the two atrial fibrillation time sequences as the similarity between the two users. When two users belong to the same atrial fibrillation type, the acquired atrial fibrillation waveforms are more similar, so that the similarity between atrial fibrillation time sequences obtained by atrial fibrillation signal conversion is higher, and whether the two users belong to the same atrial fibrillation type or not can be determined according to the similarity between the atrial fibrillation time sequences, so that the users can be grouped.

Alternatively, the method for calculating the atrial fibrillation similarity according to the atrial fibrillation time sequence may be as follows: aligning the two atrial fibrillation time sequences, calculating the difference value between the aligned elements, superposing the absolute values of the differences of all corresponding position elements, and determining the similarity between the two atrial fibrillation time sequences according to the superposed values. If the numerical value of the superposition value is larger, the similarity between the corresponding atrial fibrillation time sequences is lower; conversely, if the value of the superimposed value is smaller, the similarity of the corresponding atrial fibrillation time series is higher.

In a possible implementation manner, the above-mentioned manner for aligning the two atrial fibrillation time sequences may be: the classification device takes one atrial fibrillation time sequence with longer sequence length as a reference sequence, slides another atrial fibrillation time sequence with shorter sequence length on the reference sequence, calculates the superposition values at each sliding moment, identifies the sliding moment corresponding to the minimum superposition value as an alignment moment, and calculates the similarity between two users according to the superposition values at the alignment moment.

In S4023, dividing the atrial fibrillation signals corresponding to the users whose similarities are greater than the preset similarity threshold into the same atrial fibrillation cluster group.

In this embodiment, after calculating the similarity between each atrial fibrillation time sequence, the classification apparatus for atrial fibrillation signals can identify a plurality of atrial fibrillation signals with the similarity greater than the preset similarity threshold as associated signals, and classify the atrial fibrillation signals with the association relationship to the same atrial fibrillation cluster group, i.e., the similarity between any two atrial fibrillation signals in the same atrial fibrillation cluster group is greater than the preset similarity threshold.

In the embodiment of the application, atrial fibrillation time sequences are obtained by preprocessing atrial fibrillation signals, and the similarity between every two atrial fibrillation time sequences is calculated, so that the purpose of classifying the atrial fibrillation signals of all users is realized, and the accuracy of similarity calculation of the atrial fibrillation signals is improved.

Fig. 9 shows a flowchart of specific implementation of methods S4022 and S4023 for classifying atrial fibrillation signals according to a third embodiment of the present application. Referring to fig. 9, with respect to the embodiment shown in fig. 8, in the method for classifying atrial fibrillation signals provided in this embodiment, S4022 includes: s901 and S4023 include: s902 to S904 are specifically described as follows:

further, the calculating the atrial fibrillation similarity between the users according to the atrial fibrillation time sequence includes:

in S901, distance values between the atrial fibrillation time series of the user and the atrial fibrillation time series of each user are calculated through a dynamic time warping algorithm, and distance feature vectors with respect to the users are constructed.

In this embodiment, the classification apparatus for atrial fibrillation signals may obtain the similarity through a dynamic time warping algorithm when calculating the similarity between two atrial fibrillation time sequences, and the specific implementation process includes: generating corresponding coordinate grids according to the number of elements contained in the two atrial fibrillation time sequences, taking the difference value between the elements corresponding to the intersection points of each coordinate grid as an element distance value corresponding to the coordinate grid, superposing the element distance values corresponding to the passing grid intersection points when calculating the total distance of the path to obtain the total distance value corresponding to the path, selecting the path with the minimum total distance value as a characteristic path between the two atrial fibrillation time sequences, and taking the distance value corresponding to the characteristic path as the distance value between the two atrial fibrillation time sequences.

For example, if the user a is a first atrial fibrillation time sequence including M elements and the user B is a second atrial fibrillation time sequence including N elements, an M × N coordinate grid may be generated, and the coordinate distance value of the coordinate (M, N) is the distance value between the mth element in the first atrial fibrillation time sequence and the nth element in the second atrial fibrillation time sequence, and of all paths to the target point (M, N), one path with the smallest total distance value is calculated as the feature path, and the total distance value corresponding to the feature path is used as the distance value between the two atrial fibrillation time sequences.

In this embodiment, the classification means of atrial fibrillation signals calculates distance values between a time series of atrial fibrillation corresponding to a user and time series of atrial fibrillation of all users, thereby generating distance feature vectors regarding the distance values between the user and the time series of atrial fibrillation of all users. For example, if the classification device receives atrial fibrillation signals fed back by N users, the classification device calculates the distance value between the atrial fibrillation time sequence of the ith user of the N users and the atrial fibrillation time sequence of the N users, so as to obtain an N-dimensional distance feature vector, that is, when calculating the distance value, the ith user needs to calculate the distance value from the ith user, but the distance value from the ith user is inevitably 0 because the two atrial fibrillation time sequences are the same.

For example, fig. 10 shows a schematic diagram of generating an N-dimensional distance feature matrix according to an embodiment of the present application. Referring to fig. 10, the classification apparatus for atrial fibrillation signals receives the atrial fibrillation signals fed back by N users, and generates corresponding atrial fibrillation time sequences according to the individual atrial fibrillation signals. Because the detection duration of the atrial fibrillation signals fed back by each user is different, the length of the generated atrial fibrillation time sequences is different, after the distance values among the atrial fibrillation time sequences are calculated, each user needs to perform the calculation of N distance values, and therefore the atrial fibrillation time sequences with different lengths of each user can be converted into the distance feature vectors with the same length.

The dividing the atrial fibrillation signals corresponding to the plurality of users with the similarity greater than a preset similarity threshold into the same atrial fibrillation clustering group comprises:

in S902, an N-dimensional distance feature matrix is generated according to the distance feature vectors of the N users; and N is the total number of all the users.

In this embodiment, after obtaining the distance eigenvectors corresponding to the N users, the classification device for atrial fibrillation can combine the N distance eigenvectors according to the user numbers of the N users, thereby forming an N-distance eigenvector matrix. It should be noted that, the classification apparatus for atrial fibrillation signals receives atrial fibrillation signals sent by N users, and therefore, when distance feature vectors are calculated, distance values between an atrial fibrillation time sequence of each user and atrial fibrillation time sequences of all N users need to be calculated respectively, so that a distance feature vector including N elements is constructed and obtained, and the distance feature vectors corresponding to N users are combined, so that an N-dimensional distance feature matrix, that is, a matrix with a size of N × N, may be formed.

In S903, projecting the N-dimensional distance characteristic matrix to a K-dimensional clustering matrix through a principal component analysis algorithm; and K is the group number of the atrial fibrillation cluster group.

In this embodiment, the classification apparatus for atrial fibrillation signals may employ a principal component analysis algorithm to project an N-distance eigenvector into a K-dimensional clustering matrix, where the specific projection manner specifically is: calculating a distance feature mean value according to the distance feature vectors of the N users, and performing mean value removing operation on the N-dimensional distance matrix based on the distance feature mean value, namely subtracting the respective distance mean value from each element in the distance feature vector of each user, and then calculating a covariance matrix of the matrix after the processing operation; computing eigenvalues and eigenvectors of a covariance matrix through a parity decomposition (SVD); sorting the eigenvalues from big to small, and selecting the largest K of the eigenvalues; then, the corresponding K eigenvectors are respectively used as column vectors to form an eigenvector matrix, so that the process of projecting the N-dimensional vector to the K-dimensional vector is completed, and a new vector space is constructed.

In S904, the atrial fibrillation signals of all the users are divided into K groups of the atrial fibrillation clusters according to the K-dimensional clustering matrix.

In this embodiment, after the classification device for atrial fibrillation signals obtains the K-dimensional clustering matrix, the user numbers corresponding to the dimensions can be determined according to the elements contained in each dimension, and since each dimension corresponds to one user number in the N-dimensional distance feature matrix, after N is projected to the K-dimensional clustering matrix as the distance feature matrix, the user numbers corresponding to the K-dimensional clustering matrix can still be determined based on the projection relationship between the N and the N, so that the clustering dimension of each user can be determined, the atrial fibrillation group to which the user belongs can be determined based on the clustering dimension, and all atrial fibrillation signals can be divided into a plurality of different types according to the atrial fibrillation group of each user, and one atrial fibrillation type corresponding to each atrial fibrillation distance group.

For example, fig. 11 shows a clustering diagram of atrial fibrillation signals provided by an embodiment of the present application. Referring to fig. 11, the classification device of atrial fibrillation signals divides the atrial fibrillation signals of all users into 6 atrial fibrillation cluster groups, and draws all the atrial fibrillation signals belonging to the same atrial fibrillation cluster group on the same coordinate axis for display, and the waveforms of all the atrial fibrillation signals belonging to the same atrial fibrillation cluster group are similar or close, so that the classification effect of atrial fibrillation through the method is better, and the classification accuracy is higher.

In the embodiment of the application, by adjusting the atrial fibrillation time sequences with different lengths to the distance feature vectors with fixed lengths and performing clustering operation on all the distance feature vectors, the accuracy of the clustering operation can be improved, and the distance values between the sequences with different lengths are calculated through a dynamic time warping algorithm, so that the accuracy of the distance values can be improved, and the accuracy of the classification operation is further improved.

Fig. 12 shows a flowchart of a specific implementation of a method S4022 for classifying atrial fibrillation signals according to a fourth embodiment of the present application. Referring to fig. 12, with respect to the embodiment shown in fig. 8, in the method for classifying atrial fibrillation signals provided in this embodiment, S4022 further includes: s1201 to S1202 are specifically described as follows:

further, the calculating the atrial fibrillation similarity between the users according to the atrial fibrillation time sequence includes:

in S1201, the number of elements included in each of the atrial fibrillation time series is identified.

In this embodiment, when calculating the similarity between any two users of atrial fibrillation, the classification apparatus for atrial fibrillation may calculate the similarity between two users with smaller sequence length difference, and may not calculate the similarity between two users with larger sequence length difference, thereby reducing a large amount of unnecessary calculations and improving the response speed of clustering operations. Based on this, before calculating the atrial fibrillation similarity of two users, the classification device of atrial fibrillation signals can count the number of elements respectively contained in two atrial fibrillation time sequences, and the sequence length of each atrial fibrillation time sequence can be determined by counting the number of elements of each atrial fibrillation time sequence.

In this embodiment, the classification apparatus for atrial fibrillation signals may calculate a difference between the numbers of elements in the two atrial fibrillation time sequences, and if the difference between the numbers of the two elements is greater than or equal to a preset window threshold, identify that the length difference between the two atrial fibrillation time sequences is large, and may set the similarity between the two elements to a preset default value without performing similarity calculation.

In S1202, if a difference between the numbers of elements corresponding to any two users is smaller than a preset window threshold, the atrial fibrillation similarity between the two users is calculated.

In this embodiment, the classification apparatus of atrial fibrillation signals may perform the similarity calculation operation when the difference between the numbers of the elements in the atrial fibrillation time sequences of the two users is smaller than the preset window threshold.

In the embodiment of the application, when the atrial fibrillation similarity is calculated, the difference between the number of elements between two atrial fibrillation time sequences is determined, so that the large similarity operation of the length difference of the atrial fibrillation time sequences can be filtered, the efficiency of calculating the atrial fibrillation similarity can be improved, and the clustering response speed is improved.

Fig. 13 shows a flowchart of a specific implementation of a method S4021 for classifying atrial fibrillation signals according to a fifth embodiment of the present application. Referring to fig. 13, with respect to the embodiment shown in fig. 8, in the method for classifying atrial fibrillation signals provided in this embodiment, S4021 includes: s1301 to S1303 are specifically detailed as follows:

further, said establishing a time series of atrial fibrillation for said user based on said atrial fibrillation signal comprises:

in S1301, acquiring a collection date corresponding to each collection point in the atrial fibrillation signal.

In this embodiment, when acquiring atrial fibrillation signals of a user, the acquisition device records acquisition time corresponding to each acquisition point, where the acquisition time includes acquisition time and acquisition date. After the classification device of the atrial fibrillation signals receives the atrial fibrillation signals, each acquisition point can be marked on a preset time coordinate system according to the acquisition time associated with each acquisition point, and the acquisition date corresponding to each acquisition point is determined.

In S1302, if the acquisition date between any two adjacent acquisition points is not continuous, adding a compensation acquisition point with a missing date between the two acquisition points to the atrial fibrillation signal through a preset missing compensation algorithm to obtain a date continuous signal.

In this embodiment, classification device of atrial fibrillation signal can judge whether the collection date between each adjacent collection point is continuous, if the collection date between two arbitrary adjacent collection points is discontinuous, then can the user during the monitoring, take off the wearable equipment that is used for gathering the atrial fibrillation signal etc. and do not gather the atrial fibrillation signal, consequently have partial date and lack the atrial fibrillation signal. Based on the method, the classification device of the atrial fibrillation signals can determine the compensation acquisition points corresponding to the missing dates through the missing compensation algorithm.

Optionally, the acquiring device of atrial fibrillation signals can determine the compensation acquiring points corresponding to the missing dates through a linear fitting algorithm. The collecting device of the atrial fibrillation signals can output the function corresponding to the user according to the collected collecting points of the collecting date and configure the maximum index value of the fitted function, so that the overfitting condition is avoided in the function fitting process.

In S1303, the atrial fibrillation time series is output according to the date continuation signal.

In this embodiment, by filling the compensation acquisition points in the missing date, atrial fibrillation signals having corresponding acquisition points on each acquisition date can be obtained, that is, the atrial fibrillation signals are continuous based on the acquisition date, and according to the continuous signals on the date, an atrial fibrillation time sequence of the user is output, and the specific manner of outputting the atrial fibrillation time sequence may be described in S4021, and is not described herein again.

In the embodiment of the application, the missing date is identified, and the compensation acquisition points are added to obtain the date continuous signals, so that the atrial fibrillation time sequence is generated, the continuity of each element in the atrial fibrillation time sequence in terms of date is improved, and the accuracy of subsequent atrial fibrillation classification can be improved.

Fig. 14 shows a flowchart of a specific implementation of a classification method S401 for atrial fibrillation signals according to a sixth embodiment of the present application. Referring to fig. 14, with respect to any one of the embodiments shown in fig. 4, fig. 8, fig. 9, fig. 12, and fig. 13, the method S401 for classifying atrial fibrillation signals according to this embodiment includes: s4011 to S4014 are described in detail as follows:

further, the acquiring atrial fibrillation signals of a plurality of users comprises: :

in S4011, a heart rhythm signal of the user is acquired.

In this embodiment, the acquisition device, such as a wearable device and an electrocardiograph acquisition device, may send the acquired heart rhythm signal to a classification device of atrial fibrillation signals, and convert the heart rhythm signal into an atrial fibrillation signal through the classification device. It should be noted that the atrial fibrillation signal may obtain the heart rhythm values corresponding to the preset time nodes in a preset acquisition period, and sequentially connect the heart rhythm values corresponding to the time nodes, so as to obtain the heart rhythm signal of the user.

In this embodiment, the classification device for collecting atrial fibrillation may be configured with atrial fibrillation determination conditions, and if it is detected that the cardiac rhythm signal fed back on the current collection date meets the atrial fibrillation determination conditions, the operation of S4012 is performed; on the contrary, if there is no acquisition point satisfying the atrial fibrillation determination condition in the cardiac rhythm signal fed back by the current acquisition date, the operation of S4013 is performed.

Optionally, the classification device for collecting atrial fibrillation may be provided with an atrial fibrillation heart rate threshold and a duration threshold, if a signal segment exceeding the atrial fibrillation heart rate threshold is detected in a heart rhythm signal, the duration of the signal segment exceeding the atrial fibrillation heart rate threshold is detected, and if the duration is greater than the duration threshold, the condition for determining atrial fibrillation is identified to be satisfied; otherwise, if the signal section of the heart rhythm signal exceeding the atrial fibrillation does not exist, or the duration of the signal section exceeding the atrial fibrillation heart rhythm threshold is smaller than or equal to the duration threshold, identifying that the atrial fibrillation judgment condition is not met.

In S4012, if the cardiac rhythm signal satisfies a preset atrial fibrillation determination condition, configuring an acquisition point of an acquisition date corresponding to the cardiac rhythm signal as a first bit value.

In this embodiment, when detecting that the cardiac rhythm signal fed back by a certain collection date satisfies the atrial fibrillation determination condition, the classification apparatus for atrial fibrillation signals configures a corresponding collection point for the collection date, and configures a bit value of the collection point as a first bit value, for example, 1, that is, on the collection date, the atrial fibrillation behavior exists in the user.

In S4013, if the cardiac rhythm signal does not satisfy the atrial fibrillation determination condition, configuring the collection point of the collection date corresponding to the cardiac rhythm signal as a second bit value.

In this embodiment, when detecting that the cardiac rhythm signal fed back by a certain collection date does not satisfy the atrial fibrillation determination condition, the classification apparatus for atrial fibrillation signals configures a corresponding collection point for the collection date, and configures a bit value of the collection point as a second bit value, for example, 0, that is, on the collection date, there is no atrial fibrillation behavior for the user.

In S4014, the atrial fibrillation signal is generated according to the acquisition points corresponding to all the acquisition dates.

In this embodiment, the classification device for atrial fibrillation signals marks each acquisition point on a preset coordinate system according to the bit value of the acquisition point corresponding to each acquisition date to obtain atrial fibrillation signals.

In this application embodiment, through carrying out the normalization to the atrial fibrillation signal, whether there is the atrial fibrillation action to be used for configuring each bit value that the collection date corresponds through judging every collection date to can construct the atrial fibrillation signal that uses the day as the granularity, when realizing the normalization, can unify the dimension of atrial fibrillation signal, the accuracy of the follow-up clustering operation of being convenient for.

Fig. 15 is a flowchart illustrating a specific implementation of a classification method for atrial fibrillation signals according to a seventh embodiment of the present application. Referring to fig. 12, in comparison with any one of the embodiments shown in fig. 4, fig. 8, fig. 9, fig. 12, and fig. 13, the method for classifying atrial fibrillation signals according to this embodiment further includes: s1501 to S1502 are detailed as follows:

further, after the respective identification of the type of atrial fibrillation corresponding to each group of groups of atrial fibrillation clusters, the method further includes:

in S1501, the reminding information associated with the atrial fibrillation type is acquired.

In this embodiment, after determining the type of atrial fibrillation corresponding to each user, the classification apparatus for atrial fibrillation signals may obtain the reminding information associated with each type of atrial fibrillation from the database. The reminder information includes but is not limited to: behavior advice information, medical advice information, disease state introduction information, and the like.

In S1502, the reminder information is output.

In this embodiment, the classification device for atrial fibrillation signals may obtain a communication address of a user terminal associated with a user, and send the prompting information of the type of atrial fibrillation to which the user belongs to the user terminal through the communication address, so that the user can view and obtain the prompting information through the user terminal.

Optionally, the classification device of atrial fibrillation signals can also add a waveform diagram of the atrial fibrillation signals to the reminding information and mark the category name of the type of atrial fibrillation signals so that the user can determine the type of atrial fibrillation to which the user belongs.

For example, fig. 16 is a schematic diagram illustrating a reminder message provided in an embodiment of the present application. Referring to fig. 16, the classification apparatus of atrial fibrillation signals may display the type of atrial fibrillation and a waveform diagram of atrial fibrillation signals of the user on a first page and display a reminder corresponding to the type of atrial fibrillation on a second page.

In the embodiment of the application, the reminding information associated with the type of the atrial fibrillation of the user is acquired, and the reminding information is output to the user, so that the user can conveniently determine the relevant information of the type of the atrial fibrillation and make a corresponding treatment strategy.

Fig. 17 is a flowchart illustrating a specific implementation of a classification method for atrial fibrillation signals according to an eighth embodiment of the present application. Referring to fig. 17, in comparison with any one of the embodiments shown in fig. 4, fig. 8, fig. 9, fig. 12, and fig. 13, the method for classifying atrial fibrillation signals according to this embodiment further includes: s1701 to S1702 are specifically described as follows:

further, after the respective identification of the type of atrial fibrillation corresponding to each group of groups of atrial fibrillation clusters, the method further includes:

in S1701, a feature signal corresponding to each atrial fibrillation group is determined according to the atrial fibrillation signals included in each atrial fibrillation group.

In this embodiment, the classification device of atrial fibrillation signals performs clustering operation on all atrial fibrillation signals to obtain a plurality of atrial fibrillation cluster groups, and then determines the characteristic signals corresponding to each atrial fibrillation cluster group in a big data analysis manner. Specifically, each atrial fibrillation cluster group comprises a plurality of atrial fibrillation signals, the classification device can extract common features according to the atrial fibrillation signals, draw standard signals based on all the common features, and identify the drawn standard signals as the feature signals of the atrial fibrillation cluster group. The similarity between the characteristic signal and each atrial fibrillation signal of the cluster group is larger than a similarity threshold.

In S1702, if a new atrial fibrillation signal of a new user is received, identifying the type of atrial fibrillation corresponding to the new user according to the feature signal of each atrial fibrillation cluster group and the new atrial fibrillation signal.

In this embodiment, classification apparatus of atrial fibrillation signal is after carrying out a clustering operation, if receive newly-increased atrial fibrillation signal that newly-increased user fed back, then can discern this newly-increased user's type of atrial fibrillation, at this moment, need not all atrial fibrillation signal execution clustering operations of rethread, owing to confirmed the type of atrial fibrillation that exists, then can this newly-increased atrial fibrillation signal belonged type of quivering group to with the type of quivering type discernment of this atrial fibrillation type group correspondence for newly-increased user's type of quivering.

Optionally, in this embodiment, the classification device for atrial fibrillation signals may calculate matching degrees between the newly added atrial fibrillation signal and each of the feature signals, and select the atrial fibrillation type corresponding to the feature signal with the highest matching degree as the atrial fibrillation type of the newly added user.

Optionally, the classification device of atrial fibrillation signals may calculate a distance value between a newly added atrial fibrillation signal and the feature signal through a DTW algorithm, and select an atrial fibrillation type corresponding to the feature signal with the smallest distance value as the atrial fibrillation type of the newly added user.

In the embodiment of the application, the characteristic signal of the atrial fibrillation cluster group is matched with the newly added atrial fibrillation signal of the newly added user, so that the type of the atrial fibrillation of the newly added user can be identified, and the purposes of automatic labeling and classification of the newly added user are achieved.

Fig. 18 is a flowchart illustrating a detailed implementation of a method S1702 for classifying atrial fibrillation signals according to a ninth embodiment of the present application. Referring to fig. 18, in comparison with the embodiment shown in fig. 17, the method for classifying atrial fibrillation signals provided in this embodiment further includes: s1801 to S1802 are specifically described as follows:

further, if a new atrial fibrillation signal of a new user is received, identifying the type of atrial fibrillation corresponding to the new user according to the characteristic signal of each atrial fibrillation cluster group and the new atrial fibrillation signal, including:

in S1801, an atrial fibrillation classification model is generated from each of the feature signals.

In this embodiment, the classification device for atrial fibrillation signals may generate a classification model, which may be an SVM model, an LR model, and/or a GBDT model, according to the plurality of feature signals.

In S1802, the newly added atrial fibrillation signal is imported into the atrial fibrillation classification model, and the type of atrial fibrillation corresponding to the newly added user is determined.

In this embodiment, the classification device of atrial fibrillation signals introduces new atrial fibrillation signals into the classification model, calculates the probability value of each atrial fibrillation type, and selects an atrial fibrillation type with the highest probability value as the atrial fibrillation type of the new user.

In the embodiment of the application, the atrial fibrillation classification model is created through the characteristic signals of the atrial fibrillation cluster group, so that the type of atrial fibrillation of a newly added user can be identified, and the purposes of automatic labeling and classification of the newly added user are achieved.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

Fig. 19 shows a block diagram of the classification apparatus of atrial fibrillation signals provided in the embodiment of the present application, corresponding to the classification method of atrial fibrillation signals described in the above embodiment, and only the relevant portions to the embodiment of the present application are shown for convenience of description.

Referring to fig. 19, the apparatus for classifying atrial fibrillation signals includes:

an atrial fibrillation signal acquiring unit 191 for acquiring atrial fibrillation signals of a plurality of users;

an atrial fibrillation cluster executing unit 192, configured to perform a cluster operation on multiple atrial fibrillation signals to obtain at least one atrial fibrillation cluster group;

and an atrial fibrillation type identifying unit 193 configured to identify an atrial fibrillation type corresponding to each atrial fibrillation cluster group.

Optionally, the atrial fibrillation cluster performing unit 192 includes:

an atrial fibrillation time sequence establishing unit, configured to establish an atrial fibrillation time sequence of the user based on the atrial fibrillation signal;

the atrial fibrillation similarity calculation unit is used for respectively calculating the atrial fibrillation similarity among the users according to the atrial fibrillation time sequence;

and the atrial fibrillation cluster group dividing unit is used for dividing a plurality of atrial fibrillation signals corresponding to the users, the similarity of which is greater than a preset similarity threshold value, into the same atrial fibrillation cluster group.

Optionally, the atrial fibrillation similarity calculation unit includes:

a distance feature vector construction unit, configured to calculate, by using a dynamic time warping algorithm, a distance value between the atrial fibrillation time series of the user and the atrial fibrillation time series of each user, and construct a distance feature vector for the user;

the clustering and dividing unit of atrial fibrillation comprises:

a distance feature matrix generating unit, for generating an N-dimensional distance feature matrix according to the distance feature vectors of the N users; the N is the total number of all the users;

the clustering matrix projection unit is used for projecting the N-dimensional distance characteristic matrix to the K-dimensional clustering matrix through a principal component analysis algorithm; k is the group number of the atrial fibrillation cluster group;

and the clustering matrix dividing unit is used for dividing the atrial fibrillation signals of all the users into K atrial fibrillation clustering groups according to the K-dimensional clustering matrix.

Optionally, the atrial fibrillation similarity calculation unit includes:

the element number identification unit is used for identifying the number of elements contained in each atrial fibrillation time sequence;

and the similarity calculation triggering unit is used for calculating the atrial fibrillation similarity between the two users if the difference value between the element numbers corresponding to any two users is smaller than a preset window threshold value.

Optionally, the atrial fibrillation time sequence creating unit includes:

the acquisition date acquisition unit is used for acquiring the acquisition date corresponding to each acquisition point in the atrial fibrillation signal;

the compensation acquisition point adding unit is used for adding compensation acquisition points with missing dates between any two adjacent acquisition points on the atrial fibrillation signal through a preset missing compensation algorithm to obtain a continuous date signal if the acquisition dates between any two adjacent acquisition points are discontinuous;

and the date continuous signal conversion unit is used for outputting the atrial fibrillation time sequence according to the date continuous signal.

Optionally, the atrial fibrillation signal acquiring unit 191 includes:

a heart rate signal acquisition unit for acquiring a heart rate signal of the user;

the first bit value configuration unit is used for configuring a collection point of a collection date corresponding to the heart rhythm signal as a first bit value if the heart rhythm signal meets a preset atrial fibrillation judgment condition;

a second bit value configuration unit, configured to configure the acquisition point of the acquisition date corresponding to the heart rhythm signal as a second bit value if the heart rhythm signal does not satisfy the atrial fibrillation determination condition;

and the atrial fibrillation signal generating unit is used for generating the atrial fibrillation signals according to all the acquisition points corresponding to the acquisition dates.

Optionally, the apparatus for classifying atrial fibrillation signals further comprises:

the reminding information acquisition unit is used for acquiring reminding information related to the atrial fibrillation type;

and the reminding information output unit is used for outputting the reminding information.

Optionally, the apparatus for classifying atrial fibrillation signals further comprises:

the characteristic signal determining unit is used for determining a characteristic signal corresponding to each atrial fibrillation group according to the atrial fibrillation signals contained in each atrial fibrillation group;

and the newly added user identification unit is used for identifying the atrial fibrillation type corresponding to the newly added user according to the characteristic signal of each atrial fibrillation cluster group and the newly added atrial fibrillation signal if the newly added atrial fibrillation signal of the newly added user is received.

Optionally, the newly added subscriber identification unit includes:

the atrial fibrillation classification model generation unit is used for generating an atrial fibrillation classification model through each characteristic signal;

and the atrial fibrillation classification model importing unit is used for importing the newly-added atrial fibrillation signals into the atrial fibrillation classification model and determining the type of the atrial fibrillation corresponding to the newly-added user.

Therefore, the classification device for atrial fibrillation signals provided by the embodiment of the application can also acquire other users with the same or similar atrial fibrillation signals of the user through clustering and divide the same group, and perform type identification for different groups, so that accurate atrial fibrillation classification is realized, the physical condition of the user can be conveniently determined, and the accuracy of the classification of atrial fibrillation and the use experience of the user are improved.

Fig. 20 is a schematic structural diagram of a terminal device according to an embodiment of the present application. As shown in fig. 20, the terminal device 20 of this embodiment includes: at least one processor 200 (only one shown in fig. 20), a memory 201, and a computer program 202 stored in the memory 201 and executable on the at least one processor 200, the processor 200 implementing the steps in any of the various embodiments of the method for classifying atrial fibrillation signals described above when the computer program 202 is executed by the processor 200.

The terminal device 20 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor 200, a memory 201. Those skilled in the art will appreciate that fig. 20 is merely an example of the terminal device 20, and does not constitute a limitation of the terminal device 20, and may include more or less components than those shown, or combine some components, or different components, such as an input-output device, a network access device, and the like.

The Processor 200 may be a Central Processing Unit (CPU), and the Processor 200 may be other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The storage 201 may be an internal storage unit of the terminal device 20 in some embodiments, for example, a hard disk or a memory of the terminal device 20. The memory 201 may also be an external storage device of the apparatus/terminal device 20 in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, provided on the terminal device 20. Further, the memory 201 may also include both an internal storage unit and an external storage device of the terminal device 20. The memory 201 is used for storing an operating system, an application program, a BootLoader (BootLoader), data, and other programs, such as program codes of the computer program. The memory 201 may also be used to temporarily store data that has been output or is to be output.

It should be noted that, for the information interaction, execution process, and other contents between the above-mentioned devices/units, the specific functions and technical effects thereof are based on the same concept as those of the embodiment of the method of the present application, and specific reference may be made to the part of the embodiment of the method, which is not described herein again.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

An embodiment of the present application further provides a network device, where the network device includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, the processor implementing the steps of any of the various method embodiments described above when executing the computer program.

The embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program implements the steps in the above-mentioned method embodiments.

The embodiments of the present application provide a computer program product, which when running on a mobile terminal, enables the mobile terminal to implement the steps in the above method embodiments when executed.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium and can implement the steps of the embodiments of the methods described above when the computer program is executed by a processor. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code to a photographing apparatus/terminal apparatus, a recording medium, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium. Such as a usb-disk, a removable hard disk, a magnetic or optical disk, etc. In certain jurisdictions, computer-readable media may not be an electrical carrier signal or a telecommunications signal in accordance with legislative and patent practice.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the embodiments provided in the present application, it should be understood that the disclosed apparatus/network device and method may be implemented in other ways. For example, the above-described apparatus/network device embodiments are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implementing, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.