阅读说明：本技术 利用摄像头模块和无线通信设备检测事件的可穿戴设备 (Wearable device for detecting events using camera module and wireless communication device ) 是由 李辉源 于 2020-05-07 设计创作，主要内容包括：本发明描述了一种通过利用可穿戴设备检测对象事件的方法,以及用于执行该方法的管理服务器。可穿戴设备根据本发明的各种实施例之一是穿戴在用户身体上的可穿戴设备,该可穿戴设备可包括：短程通信模块,用于识别用户身体以及位于预定区域内的对象；摄像头模块,用于拍摄可穿戴设备附近的区域,以生成与对象和用户身体的运动中的至少一者相关的图像或视频；控制单元,用于基于由短程通信模块收集的对象信息来确定是否激活摄像头模块；以及通信模块,用于向管理服务器传输由短程通信模块识别的关于对象的信息和由摄像头模块生成的图像或视频,其中短程通信模块可接收由附接到对象的无线通信设备生成的信号,并且控制单元可以通过分析短程通信模块从无线通信设备接收的信号来确定是否满足特定条件,并且基于该确定情况来确定是否激活摄像头模块。(The invention describes a method for detecting an object event by using a wearable device, and a management server for executing the method. Wearable device one of the various embodiments according to the invention is a wearable device worn on the body of a user, which may comprise: a short-range communication module for identifying a user's body and an object located within a predetermined area; a camera module to photograph an area proximate to the wearable device to generate an image or video related to at least one of a subject and a motion of a body of a user; a control unit for determining whether to activate the camera module based on the object information collected by the short-range communication module; and a communication module for transmitting information about the object identified by the short-range communication module and an image or video generated by the camera module to the management server, wherein the short-range communication module may receive a signal generated by a wireless communication device attached to the object, and the control unit may determine whether a specific condition is satisfied by analyzing the signal received by the short-range communication module from the wireless communication device, and determine whether to activate the camera module based on the determination.)

1. A wearable device wearable on a user's body, the wearable device comprising:

a short-range communication module that identifies an object located within a predetermined area from a user's body;

a camera module that takes a photograph of an area near the wearable device and generates an image or video related to movement of the user's body, the object, or both;

a control unit that determines whether to activate the camera module based on the object information collected by the short range communication module; and

a communication module transmitting information about the object identified by the short range communication module and an image or video generated by the camera module to the management server,

wherein the short-range communication module receives a signal generated from a wireless communication device attached to the object, an

The control unit determines whether a specific condition is satisfied by analyzing a signal received by the short-range communication module from the wireless communication device, and determines whether to activate the camera module accordingly.

2. The wearable device according to claim 1, wherein the wearable device is a smart watch or a smart bracelet wearable on a user's wrist, and

the camera module is embedded in a portion of a watchband of the smart watch or a portion of the smart bracelet, and at least a portion of the camera module is exposed through a side surface of the watchband of the smart watch or the smart bracelet.

3. The wearable device of claim 1, wherein the wireless communication device is normally operated in a sleep mode, activated and transmitting a wireless signal when certain conditions are met.

4. The wearable device of claim 1, wherein the wireless communication device continuously transmits wireless signals in an active state and causes the wireless signals transmitted when the particular condition is satisfied to include information about the particular condition being satisfied.

5. The wearable device of claim 1, wherein determining, by the control unit, whether the particular condition is satisfied by analyzing a signal received by the short-range communication module from the wireless communication device is performed based on at least one selected from a signal strength when the short-range communication module identifies the object, a measurement value of an illumination sensor, and a measurement value of a motion sensor.

6. The wearable device according to claim 1, wherein the control unit performs control such that the short-range communication module operates only for any preset period of time.

7. The wearable device of claim 1, wherein in the event that the communication module is unable to access the communication network, the communication module temporarily stores the detected specific behavior information of the user and the image or video generated by the camera module, and transmits the temporarily stored information and image or video to the management server when the communication network is later accessible.

8. The wearable device according to claim 1, wherein the control unit sets a feature value related to a specific object or action from a plurality of reference images or videos, and calculates a capturing probability of the specific object or an occurrence probability of the specific action by extracting the feature value from an image or video generated by the camera module based on the set feature value.

9. A management server that acquires information through communication with a wearable device that can be worn on a user and manages the acquired information, the management server comprising:

a communication unit that receives object information automatically collected by a short-range communication module of a wearable device and receives an image or video generated by the wearable device; and

a motion determination unit that determines whether a preset motion related to the object or the user's body is detected in the image or video using machine learning or artificial intelligence based on the information of the object.

10. The management server according to claim 9, wherein the motion determination unit sets a feature value related to a specific object or motion from a plurality of reference images or videos, and calculates a capturing probability of the specific object or an occurrence probability of the specific motion based on the feature value extracted from the images or videos, when determining whether a preset motion related to the object or the body of the user is detected in the images or videos.

Technical Field

Various embodiments of the present invention relate to a technique for more easily detecting an event of an object by using a wireless communication technique and a camera module included in a wearable device that can be worn by a user.

Background

In daily life, a user unknowingly engages in many physical activities. In particular, such physical activities are accompanied by many events that move a specific object, but it is not easy for the user to remember every event that occurs unconsciously in the user's habit pattern.

Sometimes, the physical activity of the user accompanying such movement of the object is determined as an important event in a plurality of fields. For example, in the field of healthcare and the like, when, what, how much a user takes a medicine may be an important factor. For certain diseases, not missing a medication can be a very important treatment problem.

The problem is that users often do not realize this in daily life when these important events are omitted. Even if late acknowledgements are missed, the loss or risk due to failure to fulfill the matters on time cannot be traced.

Recently, a technique of analyzing the user's activities using a camera has been provided, but a fixedly installed camera is used in most cases and it is difficult to apply the technique to daily life.

Disclosure of Invention

Technical problem

Various embodiments of the present disclosure are directed to determining whether a predetermined event occurs by relatively simply recognizing a specific object in daily life through a wearable device and its configuration, and providing various services by recording the time when the event occurs.

The technical problems to be solved by the present disclosure are not limited to the above technical problems, and other technical problems not mentioned will be more apparent to those skilled in the art from the following description.

Technical scheme

According to one of the various embodiments of the present disclosure, there is provided a wearable device wearable on a body of a user, the wearable device comprising: a short-range communication module identifying an object located within a predetermined area from a body of a user; a camera module that takes a photograph of an area near the wearable device and generates an image or video related to movement of the user's body, object, or both; a control unit determining whether to activate the camera module based on the object information collected by the short range communication module; and a communication module transmitting information about the object recognized by the short-range communication module and an image or video generated by the camera module to the management server, wherein the short-range communication module receives the generated signal from the wireless communication device attached at the object, and the control unit determines whether a specific condition is satisfied by analyzing the signal received by the short-range communication module from the wireless communication device, and determines whether to activate the camera module accordingly.

The wearable device may be a smart watch or a smart bracelet wearable on a wrist of a user, the camera module may be embedded in a portion of a watchband of the smart watch or a portion of the smart bracelet, and at least a portion of the camera module may be exposed through a side surface of the watchband of the smart watch or the smart watchband.

Wireless communication devices may typically operate in a sleep mode and may be activated and may transmit wireless signals when certain conditions are met.

The wireless communication device may continuously transmit the wireless signal in the active state, and may cause the wireless signal transmitted when the specific condition is satisfied to include information on the satisfaction of the specific condition.

The control unit determining whether the specific condition is satisfied by analyzing the signal received by the short-range communication module from the wireless communication device may be performed based on at least one selected from the group consisting of a signal strength when the short-range communication module identifies the object, a measurement value of the illuminance sensor, and a measurement value of the motion sensor.

The control unit may perform control such that the short-range communication module operates only for any preset time period.

In a case where the communication module cannot access the communication network, the communication module may temporarily store the detected wireless signal information and the image or video generated by the camera module, and transmit the temporarily stored information and the image or video to the management server when the communication network can be accessed later.

The control unit may set a feature value related to a specific object or motion from a plurality of reference images or videos, and may calculate a capturing probability of the specific object or an occurrence probability of the specific motion through feature values extracted from images or videos generated by the camera module based on the set feature value.

According to one of various embodiments of the present disclosure, there is provided a management server for acquiring information through communication with a wearable device wearable on a body of a user and managing the acquired information, the management server including: a communication unit to receive information on an object automatically collected by a short-range communication module of a wearable device and to receive an image or video generated by the wearable device; and an action determination unit that determines whether a preset action related to the object or the body of the user is detected in the image or video using machine learning or artificial intelligence based on information on the object.

In determining whether a preset motion related to the object or the body of the user is detected in the image or video, the motion determination unit of the management server may set a feature value related to the specific object or motion from a plurality of reference images or videos, and may calculate a capturing probability of the specific object or an occurrence probability of the specific motion based on the feature value extracted from the image or video.

Advantageous effects

According to the embodiments of the present disclosure, since the wearable device records whether and when a specific event occurs, a more effective guidance system for detecting that a user such as healthcare is easily missed an event in the daily field may be provided, and a system capable of data analysis by learning a user pattern may be implemented.

The effects that can be obtained from the present disclosure are not limited to the above effects. Further, other effects not described herein will be more apparent to those skilled in the art from the following description.

Drawings

FIG. 1 is a schematic diagram illustrating an event detection system according to one embodiment of the present disclosure;

fig. 2 is a block diagram illustrating a wearable device according to one embodiment of the present disclosure;

FIG. 3 is a block diagram illustrating a management server according to one embodiment of the present disclosure;

fig. 4 is an operational flow diagram illustrating detection of an object and generation of an image or video by a wearable device according to one embodiment of the present disclosure;

fig. 5 is an operational flow diagram illustrating a management server managing information received from a wearable device and ultimately determining whether a particular event has occurred, according to one embodiment of the present disclosure;

fig. 6 is an operational flow diagram illustrating detection of an event of an object by a wearable device according to another embodiment of the present disclosure;

fig. 7 is an operational flow diagram illustrating detection of an event of an object by a wearable device according to another embodiment of the present disclosure;

fig. 8 is a diagram showing a structure of a wearable device according to one embodiment of the present disclosure;

fig. 9-11 illustrate a wearable device provided in the form of a smart watch in accordance with one embodiment of the present disclosure.

Detailed Description

The terminology used herein is for the purpose of describing embodiments and is not intended to be limiting of the disclosure. In this specification, the singular forms include the plural forms unless specifically mentioned. The terms "comprises" and/or "comprising," as used herein, specify the presence of stated elements, but do not preclude the presence or addition of one or more other elements. In the drawings, like numbering represents like elements. The term "and/or" includes all combinations of one or more of the associated listed elements. It will be further understood that the terms first, second, etc. may be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish one element from another. For example, a first element discussed below could be termed a second element without departing from the technical scope of the present disclosure.

The term "event" as referred to in this document may refer to an action of positioning or moving an object in a specific area, the object being related to the body of the user. For example, an event may include, but is not limited to, the act of taking a drug or eating.

FIG. 1 is a schematic diagram illustrating an event detection system 10 according to one embodiment of the present disclosure. The event detection system 10 causes the wearable device 200 to perform a function of recognizing a signal transmitted from the wireless communication device 100 attached at a subject, detects whether a predetermined valid event occurs while the subject is photographed, and records time information.

According to one embodiment, the event detection system 10 may include a wireless communication device 100, a wearable device 200, a management server 300, and a user terminal 400.

The wireless communication device 100 is attached at or in an area near the object and recognized by the wearable device 200, thereby ensuring that the wearable device 200 recognizes the object. For example, the wireless communication device 100 may include a cellular communication module, a short-range wireless communication module, and a Global Navigation Satellite System (GNSS) communication module. Examples of the short-range wireless communication module include a beacon, bluetooth, WiFi Direct (Wi-Fi Direct), ZigBee, Radio Frequency (RF) module, and Near Field Communication (NFC), but are not limited thereto.

According to one embodiment, the wireless communication device 100 may transmit a wireless signal (e.g., a bluetooth signal) and may transmit the signal only in certain situations, such that the power consumption of the battery of the wireless communication device is reduced.

According to various embodiments, the wireless communication device 100 may operate in a sleep mode and may be activated and may transmit wireless signals when certain conditions are met. In this case, the specific condition may be a condition that at least one of the measurement value of the illuminance sensor or the measurement value of the motion sensor reaches a specific value, or a condition that a rate of change or a calculated value of each measurement value reaches a specific value. Therefore, the battery power can be prevented from being unnecessarily consumed.

According to another embodiment, the wireless communication device 100 may transmit a wireless signal in real time, and when an event satisfying a specific condition occurs, the wireless communication device 100 may transmit a wireless signal including information indicating that the specific condition is satisfied. Also in this case, the specific condition may be related to at least one of the measurement value of the illuminance sensor or the measurement value of the motion sensor. As described above, in the case where the wireless communication apparatus 100 does not operate in the sleep mode but operates all the time and transmits a wireless signal in real time, the time required for the wireless communication apparatus 100 to be activated from the sleep mode when a specific condition occurs is not required any more. Since the wireless communication device 100 always communicates with the wearable device 200 in a wireless manner, the time taken for the camera module of the wearable device 200 to react when a specific situation occurs can be reduced.

The wireless communication device 100 may include at least one of various sensor modules, such as various GPS sensors, gesture sensors, gyroscope sensors, 9-axis sensors, illuminance sensors, and motion sensors. For example, the wireless communication device 100 may include at least one selected from the group of a beacon, a short-range wireless communication device, and a long-range wireless communication device. One method of operation of the wireless communication device 100 is to utilize a 9-axis sensor to detect movement of an object to which the wireless communication device 100 is attached and generate a wireless signal accordingly. The 9-axis sensor according to one embodiment may be composed of an acceleration sensor for three axes, a gyro sensor for three axes, and a geomagnetic sensor for three axes, and the motion of an object to which the sensor is attached may be measured accordingly. The wireless communication device 100 is attached to an object, detects movement of the object by the above-described sensor, and generates a wireless communication device signal only when a specific condition is satisfied. As described above, when a certain condition occurs, the wireless communication apparatus 100 is activated from the sleep state and transmits a wireless signal. Alternatively, the wireless communication device 100, which has transmitted the wireless signal in real time, transmits a wireless signal additionally including information indicating that a specific condition has occurred.

In one embodiment of the present disclosure, when the wireless signal is recognized by the short-range communication module of the wearable device 200, the wearable device 200 can determine whether to activate the camera module based on the wireless signal information collected by the wireless communication device 100. Specifically, when the wearable device 200 receives wireless signal information indicating that a specific condition has occurred, the camera module may be activated.

The wearable device 200 may be an electronic device that is wearable on at least a portion of a user's body (e.g., a wrist), and may be implemented as, for example, a smart watch, smart glasses, or a smart helmet, but is not limited thereto. In one embodiment of the present disclosure, the wearable device 200 recognizes an object through the short range communication module, the camera module, or the sensor module, photographs an area adjacent to the wearable device 200, and transmits the result of the photographing to the management server 300. The detailed configuration of the wearable device 200 will be described later with reference to fig. 2.

According to one embodiment of the present disclosure, the wearable device 200 may be provided as a smart watch wearable on a user's wrist. In this case, the camera module or the sensor module included in the wearable device 200 may be located on a band connected to the case of the smart watch. For example, in the case where the case of a smart watch is to be positioned on the wrist portion connected to the back of the hand, a camera module or sensor module may be provided on the wrist portion located connected to the palm of the hand. With such a configuration, the wearable device 200 can detect or photograph an action or event performed on the palm side of the user's hand by the camera module or the sensor module, and can detect or photograph an object located near the palm of the user's hand or held by the user's hand.

The camera module included in the wearable device 200 may be formed in an integrated manner in a wristband of the smart watch. The detailed configuration thereof will be described later.

The management server 300 is connected to the user's wearable device 200 through a network, receives information collected by the wearable device 200, and determines whether a specific event has occurred by analyzing the received information. Further, the management server 300 may provide the collected or processed information to the user terminal 400 through a network. The management server 300 may include information on hardware, for example, a control unit having at least one processor, a communication module, and a storage unit (for example, a memory), or information on software for algorithm operation.

The user terminal 400 is connected to the wearable device 200 and performs functions such as creating an initial setting value of the wearable device 200 and changing the setting value. Such operation may be implemented according to a manipulation performed by a user on the user terminal 400. The user may access the management server 300 through the user terminal 400, may recognize information transmitted from the wearable device 200 managed by the user to the management server 300, and may also recognize information processed by the management server 300 using the information transmitted thereto.

Examples of the user terminal 400 include all types of handheld wireless communication devices, such as mobile phones, smart phones, Personal Digital Assistants (PDAs), Portable Multimedia Players (PMPs), and tablet computers capable of connecting to a web server through a network according to one embodiment of the present disclosure. The user terminal 400 may be one of digital devices such as a personal computer (e.g., a desktop computer and a notebook computer), a workstation, a Personal Digital Assistant (PDA), and a web tablet, which has a storage device and is equipped with microprocessor capabilities for computing.

The external server may be a device or a program that transmits and receives information (for example, identification information of a wireless signal, and image information of an object corresponding to the wireless signal) required by the management server 300 through a network.

Fig. 2 is a block diagram illustrating a wearable device 200 according to one embodiment of the present disclosure. The wearable device 200 may include a communication module 210, a control unit 220, a wireless signal receiving unit 221, an object recognition unit 223, an event detection unit 225, a storage unit 230, and a camera module 240.

The communication module 210 of the wearable device 200 performs a function of receiving a wireless signal generated from the wireless communication device 100, and a function of transmitting and receiving information required for the operation of the wearable device 200 by communicating with the management server 300, the user terminal 400, or an external server. The communication module 210 may be implemented as a short-range communication module, such as bluetooth, ZigBee, infrared communication module, NFC, RF module, two-dimensional code module, or Wi-Fi module, or may be implemented in a long-range form, such as a network communication module and a base station communication module.

The control unit 220 may perform data processing functions that control the overall operation, such as controlling power to the wearable device 200, controlling signal flow between internal components of the wearable device 200, and processing data. The control unit 220 may comprise at least one processor or microprocessor MCU.

The control unit 220 may determine whether to activate the camera module 240 and may control the operation of the camera module 240 accordingly. Further, the control unit 220 may control the operation of the short range communication module. According to one embodiment, the control unit 220 may perform control such that the short-range communication module operates only for any preset time period.

According to one embodiment, the control unit 220 may be implemented in a form including all functions of the management server 300 described later. In this case, the control unit 220 of the wearable device 200 itself performs the function of the management server 300, and thus can operate without the management server 300.

The wireless signal receiving unit 221 may collect signals generated from the wireless communication device 100 attached at an object. The wireless signal collection method of the wireless signal receiving unit 221 may be similar to the communication method of the communication module 210 described above. In addition, at least some components of the wireless signal receiving unit 221 may be included in the communication module 210.

The storage unit 230 may store therein data received or generated from the control unit 220, the wireless communication device 100, the wearable device 200, the management server 300, the user terminal 400, or other elements of the event detection system 10. Examples of the storage unit 230 may include a memory, a cache, and a buffer, and the storage unit 230 may be composed of software, firmware, hardware, or a combination of at least two thereof.

The camera module 240 captures an area near the wearable device 200 and generates images or video related to the user's body or object or both movements. The camera module 240 may include a 2D or 3D camera device, and may include a driving means (e.g., an actuator) for rotating or moving a lens of the camera.

According to one embodiment, the camera module 240 is activated when the wearable device 200 recognizes an object through the communication module 210, or the camera module 240 is activated when a specific behavior of the user is detected through the sensor module of the wearable device 200, or the camera module 240 is activated when information acquired from a signal received from the wireless communication device 100 indicates that a specific condition is specifically satisfied. However, it is not limited thereto, and the camera module 240 may be activated by other specific conditions (e.g., the user selects the activation function). In the process of the wearable device 200 detecting a particular behavior of the user, the wearable device 200 may detect the signal strength when the short-range communication module identifies an object. Taking the case where the wearable device 200 identifies an object using a signal generated by the wireless communication device 100 as an example, the signal strength may vary according to the distance between the wearable device 200 and the wireless communication device 100, so that the distance between the wearable device 200 and the object may be calculated based on the signal strength. The signal strength may be calculated by a received signal strength indicator RSSI.

To this end, although not shown in fig. 2, the wearable device 200 may further include a sensor module capable of recognizing a specific behavior of the user as described above. The sensor module may include at least one sensor capable of measuring a physical quantity or detecting an operation state of the wearable device 200, and converting the measured or detected information into an electrical signal. The sensor module may include, for example, a sensor selected from the group consisting of a GPS sensor, a gesture sensor, a gyroscope sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a proximity sensor, a biometric sensor (e.g., an iris sensor, a fingerprint sensor), an infrared sensor, an ultraviolet sensor, a 9-axis sensor, and an illuminance sensor.

In fig. 2 described above, the main body performing various roles in the wearable device 200 is denoted by the word "unit" or "module", but various parts may be sub-program modules running in the wearable device 200 or components of the functional classification of the control unit 220. These program modules are a concept including, but not limited to, routines, subroutines, programs, objects, components, and data structures that perform corresponding operations or implement particular abstract data types.

Fig. 3 is a block diagram illustrating a management server 300 according to one embodiment of the present disclosure. The management server 300 may include a communication unit 310, a control unit 320, an action determination unit 330, an event occurrence determination unit 340, and a storage unit 350.

The communication unit 310 of the management server 300 performs a function of transmitting and receiving information required for the operation of the management server 300 by communicating with the wearable device 200, the user terminal 400, or an external server.

The communication unit 310 may receive information on the object collected by the wearable device 200 from the wearable device 200 through the short-range communication module, and receive an image or video generated by the camera module 240.

Further, the communication unit 310 may transmit information about whether the event occurs, which is determined by the event occurrence determination unit 340, to the user terminal 400.

According to one embodiment of the present disclosure, the communication unit 310 may control the operation of the wearable device 200 by managing real-time communication between the server 300 and the wearable device 200.

The control unit 320 may perform data processing functions that control the overall operation, such as controlling power supply to the management server 300, controlling signal flow between internal components of the wearable device 200, and processing data. The control unit 320 may include at least one processor or MCU.

The motion determination unit 330 may determine whether a preset motion is detected based on the object information and the image or video received by the communication unit 310. Specifically, the action determination unit 330 may determine whether a preset action related to the object or the body of the user is detected based on the object information, and may make such determination based on machine learning or artificial intelligence.

The motion determination unit 330 may extract a feature value related to a preset object or motion in an image or video received from the wearable device 200, and may perform extraction of the feature value for a plurality of objects or motions.

The motion determination unit 330 may set a feature value for a specific object or motion from a plurality of images or videos provided in advance, and may extract a feature value from the image or video received from the wearable device 200 based on this. Thereafter, the motion determination unit 330 may calculate a capture probability of a specific object or an occurrence probability of a specific motion based on the extracted feature values.

According to one embodiment of the present disclosure, preset actions related to a specific subject or a user's body may be differently set for respective subjects. For example, when the first object is recognized, the first motion and the second motion may be preset motions related to the body of the user. When the second object is recognized, the third motion and the fourth motion may be preset motions related to the body of the user.

According to one embodiment of the present disclosure, in the present disclosure, the object identified by the wireless signal may be an object related to a medicine, and the preset action may be a case related to the medicine or a medicine taking behavior. For example, the object identified by the signal generated from the wireless communication device 100 may be a container containing a drug. In this case, the preset action may include exposure of the medicine, opening of the container, holding of the medicine in the user's hand, and access of the medicine to the user's mouth.

The event occurrence determination unit 340 may perform a function of determining whether a specific event has occurred. When determining whether a specific event has occurred based on the probability calculated using the feature values, the event occurrence determination unit 340 may determine whether the specific event has occurred by synthesizing weights set for the respective preset actions detected by the action determination unit 330.

For example, when the action determination unit 330 determines that the first action, the second action, and the third action, which are preset actions for the identified specific object, are detected, the event occurrence determination unit 340 determines whether a specific event occurs by performing final calculation by applying weight values preset to the first action, the second action, and the third action, respectively.

The storage unit 350 may store therein data received or generated from the control unit 320, the wearable device 200, the user terminal 400, or other elements of the event detection system 10. Examples of the storage unit 350 may include a memory, a cache, and a buffer, and the storage unit 230 may be composed of software, firmware, hardware, or a combination of at least two thereof.

The storage unit 350 may store therein data related to machine learning or artificial intelligence used by the action determination unit 330, and may also store therein data related to whether a specific event has occurred, wherein the data is generated by the event occurrence determination unit 340. In addition, the storage unit 350 stores therein information about the wearable devices 200 and the user terminals 400, and may store therein information about which user terminal 400 a specific wearable device 200 is associated with.

According to one embodiment, the storage unit 350 is not a storage unit embedded in the management server 300, but may be replaced with an online server (e.g., a cloud server). In this case, the management server 300 may store various types of information on the online server for use.

Hereinafter, referring to fig. 4 and 5, when the wearable device 200 detects an object through the camera module and generates an image or video through the same configuration in fig. 1 and 2, it is determined whether an event occurs by receiving information from the management server 300. At least some of the steps shown in fig. 4 and 5 may be omitted or their order may be changed.

Fig. 4 is a flow diagram illustrating the operation of detecting an object and generating an image or video by the wearable device 200 according to one embodiment of the present disclosure.

When the user approaches the object, the wearable device 200 receives a wireless signal generated from the wireless communication device 100 at step S410. The wireless signals received by the wearable device 200 may include information about a particular condition (e.g., measurements of an illumination sensor and measurements of a motion sensor).

Thereafter, the control unit 220 of the wearable device 200 may determine whether to activate the camera module 240 based on information included in the received wireless signal at step S420. For example, the control unit 220 may determine whether to activate the camera module 240 based on the time at which the wireless signal generated from the wireless communication device 100 is collected, the measurement value of the illuminance sensor, the measurement value of the motion sensor, and the RSSI value.

When the control unit 220 determines not to activate the camera module 240, the wearable device 200 returns to a state of performing wireless signal recognition or specific behavior detection.

In contrast, in step S430, when the control unit 220 determines to activate the camera module 240, the control unit 220 activates the camera module 240, thereby generating an image or video by shooting.

Thereafter, the control unit 220 may determine whether a predetermined time has elapsed at step S440. In step S450, when the predetermined time has elapsed, the control unit 220 performs control such that the camera module 240 enters an inactive state. According to one embodiment of the present disclosure, the predetermined time may be measured from the time the camera module 240 is activated. In the case where the camera module 240 is activated, when the wearable device 200 additionally recognizes a wireless signal or detects a specific behavior of the user, the measured time is reset and the time during which the camera module 240 is activated is extended.

In step S460, after the camera module 240 is inactivated, the wearable device 200 may transmit an image or video generated by the camera module 240 to the management server 300. Further, in the process of transmitting the image or video generated by the camera module 240 to the management server 300, the wearable device 200 may also transmit information (e.g., a measurement value of an illuminance sensor, a measurement value of a motion sensor, an RSSI value, etc.) on the condition that the generated image or video is transmitted to the management server 300.

According to one embodiment of the present disclosure, in a case where the wearable device 200 cannot access the communication network, the collected information about the object, the detected wireless signal information (specific condition satisfaction information and sensor information), and the image or video generated by the camera module 240 may be temporarily stored in the storage unit 230 of the wearable device 200. When the wearable device 200 is later connected to a wireless communication network, various types of data listed above are transmitted to the management server 300.

Fig. 5 is a flowchart illustrating an operation in which the management server 300 manages information received from the wearable device 200 and finally determines whether a specific event occurs according to one embodiment of the present disclosure. Like the contents of the figures, at least some of the steps shown in fig. 5 may be omitted or their order may be changed.

When the wearable device 200 transmits the object information, the specific behavior of the user, and the image or video generated in association therewith at step S460 of fig. 4, the management server 300 receives the object information, the specific behavior of the user, and the image or video at step S510.

Thereafter, the management server 300 may extract a feature value related to a preset object or action from the received image or video at step S520. The extraction of the feature values may be performed for a plurality of objects or actions, and the management server 300 may perform the extraction of the feature values on the objects or actions based on an artificial intelligence technique. According to one embodiment, as the management server 300 performs data analysis based on the deep learning technique, the extraction of feature values in data may be automatically performed, and the capability related to the feature value extraction is continuously improved.

In step S530, the management server 300 may calculate an occurrence probability of a specific action or a capture probability of a specific object by synthesizing feature values derived as a result of step S520. When it is determined based thereon that a specific action has occurred or a specific object has been captured, the management server 300 thus determines whether a specific event has occurred at step S540. In step S560, when the management server 300 determines that a specific event has occurred, the management server 300 transmits information about the occurred event to the user terminal 400.

Hereinafter, the operation of the management server 300 to detect an event of an object, which is described in detail with reference to fig. 6 and 7, is performed by the configuration as shown in fig. 1 and 2. In the embodiment described with reference to fig. 6 and 7, the detection and determination of actions and events performed by the management server 300 is described, but in another embodiment of the present disclosure, the detection and determination of actions and events may be performed by the wearable device 200 instead of the management server 300.

At least some of the steps shown in fig. 6 and 7 may be omitted or their order may be changed.

Fig. 6 is a flowchart illustrating the operation of detecting an event of an object by the management server 300 according to one embodiment of the present disclosure.

When the user approaches the object, the wearable device 200 recognizes the wireless signal and collects a video image of the object through the camera module 240 of the wearable device 200 at step S610. Step S610 may be performed by the wearable device 200 instead of the management server 300.

For example, when the wireless communication device 100 is attached to a specific pharmaceutical wrapper and the user holds the pharmaceutical wrapper and the wearable device 200 is worn on the wrist of the user, a signal is generated from the wireless communication device 100 attached to the pharmaceutical wrapper according to the movement of the pharmaceutical wrapper and the communication module of the wearable device 200 scans the wireless signal, thereby identifying the subject "pharmaceutical". Accordingly, the camera module 240 of the wearable device 200 may be activated and collect a video image of the surroundings. The video images captured by the camera module 240 of the wearable device 200 may include video of drug exposure, drug container opening, a situation where the user holds the drug in his hand, and a situation where the drug is close to the user's mouth. The camera module 240 of the wearable device 200 can capture a plurality of video images, and can perform capturing of the video images at any time interval during a predetermined time.

When a plurality of video images are generated by the camera module 240 of the wearable device 200 as described above, the management server 300 receives and collects the video images from the wearable device 200 in step S620.

Next, in step S630, the management server 300 may identify content (e.g., an image of a medicine) corresponding to a scan target (e.g., a medicine) through the local storage unit 350 or the online cloud server, may compare the identified content with an image captured by photographing or filming through an artificial intelligence technique, and may determine whether a probability that a collected video image is related to a specific behavior, such as a medicine taking behavior, or to a container including a specific medicine is equal to or greater than a reference value.

According to one embodiment, the determination operation of step S630 may be performed by using a first determination algorithm of an image similarity determination technique. For example, the control unit 320 may divide areas such as color and texture of a video collected by shooting and a video identified by scanning, and may determine image similarity through a matching operation based on position information and a color table or object similarity. Examples of the first determination algorithm may include various image similarity determination techniques, and are not limited to a specific technique. In addition, the first determination algorithm may apply artificial intelligence techniques. That is, the management server 300 may perform image similarity determination using an artificial intelligence technique, and thus, the first determination algorithm may be derived and developed through deep learning such as machine learning.

Further, the method of determining a match may determine whether a similarity value derived by the similarity operation is equal to or greater than a predetermined threshold value. The similarity value may be derived in an image similarity determination process. In step S640, when the similarity value is equal to or greater than the predetermined threshold value, the control unit 320 determines that the acquired image matches the image identified according to the reception of the wireless signal, and records time information at this time as first time information. Such image matching may be performed by analysis of a plurality of images resulting from the photographing. The control unit 320 may calculate the probability that a specific event has occurred through a plurality of video images. The first time information of step S640 may be time information of determining whether a specific object is an object for monitoring occurrence of an event.

For the image matching based on the similarity determination by the management server 300 of the present disclosure, the comprehensive analysis and matching may be performed by an artificial intelligence technique, instead of performing a one-to-one form matching for a specific event or image. For example, in determining that the object is a medicine bottle, the management server 300 captures a common point of a plurality of reference images for the object as the medicine bottle, sets a feature value, and calculates a similarity of a relationship that an image acquired by the wearable device 200 has with the feature value, thereby performing similarity determination.

According to one embodiment, the first time information may be used, for example, as metadata for data analysis of event occurrence and may be used as information for analyzing a user pattern. As one non-limiting example, when a time difference between the first time information and second time information, which will be described later, is equal to or greater than a predetermined value, the second time information is determined to be error data according to circumstances. This is because, for example, when the user touches a medicine, but when it is recognized that the medicine is taken into the mouth after several hours, it may be wrong to determine that the recognized medicine is taken. However, the recording of the first time information may be omitted.

Further, the control unit 320 may calculate a similarity value as probability information of the first determination algorithm. The probability information of the first determination algorithm can be used to ensure reliability of the accumulated data by determining valid events by probability, which will be described later.

Meanwhile, when the matching at step S630 is not satisfied, the operation of fig. 3 is ended, or waits in an idle state to recognize a signal generated from the wireless communication device attached at the new object.

Next, in step S650, the control unit 320 may additionally collect a video of the object and may determine whether the collected video satisfies an event condition. According to one embodiment, the event condition may be a condition for recognizing whether a preset motion related to the body of the user with respect to the object is detected. For example, the control unit 320 may identify whether a drug taken out by the user enters a mouth that is a part of the user's body. The recognition run may be derived by applying a second determination algorithm based on machine learning or algorithms. For example, the control unit 320 may apply an image analysis technique using a known artificial intelligence technique, and may compare feature values extracted from the acquired image with feature values extracted from other images, thereby calculating the probability that the "taking medicine" action has been performed. The latter image may be an image that is a reference for image analysis, and may be composed of a management image or a non-management image.

Both the first determination algorithm and the second determination algorithm using artificial intelligence may have an improved accuracy and speed of determination with accumulation of images and corresponding updating of the determination results.

When the collected video satisfies the event condition, the control unit 320 records the time of collecting the video as the second time information at step S660. For example, the control unit 320 may record the time when the medicine enters the user's mouth or the time within a predetermined error range thereof as the second time information. The second time information may be determined immediately using the time when the event of the object occurs or after determining whether a specific condition is satisfied and identifying a valid event. The valid event may refer to an event arbitrarily selected by a user among events occurring at an object to record time information.

Further, the control unit 320 may derive the preset motion related to the body of the user detected by the second determination algorithm as a numerical value, and may calculate the resultant value as probability information of the second determination algorithm. Similar to the probability information of the first determination algorithm described above, the probability information of the second determination algorithm may also be used to probabilistically determine whether an event occurring at the object is a valid event.

Next, in step S670, the control unit 320 may finally determine a valid event based on the probability information. Specifically, when the sum of the probability information of the first determination algorithm and the probability information of the second determination algorithm is equal to or greater than a predetermined value, the control unit 320 may determine that a valid event has occurred, and may determine the second time information using the time at which the valid event occurred. For example, the control unit 320 converts whether the object is a detection target object (e.g., a medicine) into a numerical value, converts whether a predetermined event (e.g., behavior close to the mouth) occurs at the object into a numerical value, and determines the event as a valid event when the sum of the numerical values is equal to or greater than a predetermined value.

In this case, the control unit 320 may assign a higher weight to the probability information of the second determination algorithm than to the determination information of the first determination algorithm. This is because what motion of an object occurs may actually be a more important factor than whether there is an object under the event occurrence condition, and the process of identifying an object may involve the identification process of whether the event condition is satisfied. However, step S670 may be omitted, and thus the second time information may be simply determined using the time at which the valid event occurs.

Fig. 7 is a flowchart illustrating an operation of detecting an event of an object by the management server 300 according to another embodiment of the present disclosure. The same contents as those of fig. 6 in fig. 7 are omitted or simplified. Similar to that of fig. 6, at least some of the steps shown in fig. 7 may be omitted or the order thereof may be changed.

In fig. 7, the camera module 240 of the wearable device 200 is activated if a specific behavior of the user is recognized, instead of in step S610 of fig. 6 according to some embodiments as described above. For this, the control unit 320 of the management server 300 may detect a specific behavior of the user through the sensor module, the camera module 240, or the communication module 210 of the wearable device 200 at step S710. The specific behavior of the user includes a unique movement of the user's body. For example, when the user eats, an action of bringing food into the mouth with the hand wearing the wearable device 200 is detected. In this case, the control unit 320 of the management server 300 may be configured to recognize a specific behavior when a sensor value corresponding to a predetermined value for recognizing the specific behavior of the user is collected through the sensor module, or when the collected sensor value is analyzed and the result of the analysis corresponds to a specific pattern, without imposing limitations.

When the specific behavior of the user is detected as described above, the control unit 320 of the management server 300 activates the camera module 240 of the wearable device 200 to capture a video image and receives the video image from the wearable device 200 at step S720. Thereafter, the management server 300 may perform a probability value determination operation related to a specific behavior or object at step S730, may perform an event condition satisfaction operation at step S740, and may record time information at step S750, as same as or similar to that of fig. 6. Similar to fig. 6, the functions of dividing the time information into the first time and the second time information and determining the valid event based on the probability information may be omitted in fig. 7. Alternatively, the contents described with reference to fig. 6 may be performed in the same manner.

The steps described as being performed by the management server 300 with reference to fig. 6 and 7 may be performed by the wearable device 200. In this case, the wearable device 200 may implement the functions of the management server 300 by itself, including all the above-described functions of the management server 300.

Through the embodiments described above with reference to fig. 1 to 7, since the wearable device 200 records whether and when a specific event has occurred, a more effective guidance system for detecting user events that are easily missed in fields such as healthcare may be provided, and a system capable of performing data analysis by learning user patterns may be implemented.

Fig. 8 is a diagram illustrating a structure of a wearable device 200 according to one embodiment of the present disclosure.

Referring to fig. 8 (a), the wearable device 200 may be provided as a smart watch wearable on a user's wrist. The camera module 240 included in the wearable device 200 may be included in a watchband of the smart watch in an integrated manner.

In the case where the camera module 240 is included in the wristband of the smart watch, a lens portion of the camera module 240 that needs to be exposed to the outside of the wristband may be located on a side surface of the wristband. Since the lens portion of the camera module 240 is exposed on the side surface of the watchband of the smart watch, the area photographed by the camera module 240 is disposed in the palm side direction when the user wears the smart watch.

Referring to fig. 8 (b), the wearable device 200 may be provided as a smart watch wearable on a user's wrist. The camera module 240 included in the wearable device 200 may be included in a specific case formed to be close to a band of a smart watch. Even in this case, the position of the camera module 240 may be determined such that the area photographed by the camera module 240 is set in the palm side direction when the user wears the smart watch.

Fig. 9 to 11 illustrate a case where the wearable device 200 according to one embodiment of the present disclosure is provided in the form of a smart watch.

Referring to fig. 9 to 11, the camera module 240 in the smart watch may be formed to be included in a band of the smart watch.

Fig. 9 (a) and (b) show a perspective view and a front view of the smart watch, respectively. Fig. 10 (a), (b), and (c) show a rear view, a top view, and a bottom view, respectively, of the smart watch. Fig. 11 (a) and (b) show a left side view and a right side view of the smart watch, respectively.

The wearable device 200 disclosed in the present disclosure may be provided in the form of a smart watch as shown in the figure, or may be provided in the form of a smart bracelet including a camera module.

The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by hardware, or in a combination of the two. A software module may reside in Random Access Memory (RAM), read-only memory (ROM), Erasable Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), flash memory, a hard disk, a removable disk, a CD-ROM, or any other type of computer-readable recording medium known in the art to which this disclosure pertains.

Although the embodiments of the present disclosure have been described with reference to the accompanying drawings, those skilled in the art will appreciate that the present disclosure may be embodied in other specific forms without changing the technical idea or essential features of the present disclosure. The present disclosure is directed to. It is therefore to be understood that the above embodiments are illustrative in all respects and not restrictive.