阅读说明：本技术 一种基于声纹识别的儿童手表智能报警方法、装置、介质及设备 (Child watch intelligent alarm method, device, medium and equipment based on voiceprint recognition ) 是由 李双卫 于 2021-09-16 设计创作，主要内容包括：本发明公开了一种基于声纹识别的儿童手表智能报警方法、装置、介质及设备,具体包括,根据预置时间通过终端设备获取当前空间环境中的声音信号；读取所述声音信号中第一特征信号和第二特征信号；于所述第一特征信号匹配预置信号的状态下,判断所述第二特征信号是否匹配标准信号；于所述第二特征信号匹配标准信号的状态输出警示信息。该基于声纹识别的儿童手表智能报警方法,儿童在遇到危险情况时,无需接触的情况下即可实现自动报警,及时保证儿童使用者的安全。(The invention discloses a child watch intelligent alarm method, device, medium and equipment based on voiceprint recognition, and the method specifically comprises the steps of acquiring a sound signal in the current space environment through terminal equipment according to preset time; reading a first characteristic signal and a second characteristic signal in the sound signal; judging whether the second characteristic signal is matched with a standard signal or not in the state that the first characteristic signal is matched with a preset signal; and outputting warning information in the state that the second characteristic signal is matched with the standard signal. According to the intelligent alarm method for the child watch based on voiceprint recognition, when a child meets a dangerous condition, automatic alarm can be achieved without contact, and the safety of a child user is guaranteed in time.)

1. An intelligent alarm method of a child watch based on voiceprint recognition is characterized by specifically comprising the following steps of,

acquiring a sound signal in the current space environment through the terminal equipment according to preset time when the terminal equipment works in a preset network environment state;

reading a first characteristic signal and a second characteristic signal in the sound signal;

judging whether the second characteristic signal is matched with a standard signal or not in the state that the first characteristic signal is matched with a preset signal;

and outputting warning information in the state that the second characteristic signal is matched with the standard signal.

2. The intelligent alarm method for the children watch based on the voiceprint recognition as claimed in claim 1, further comprising outputting alarm information in a state that the second characteristic signal does not match the standard signal, and continuously acquiring the sound signal in the current spatial environment.

3. The intelligent alarm method for the children watch based on the voiceprint recognition as claimed in claim 1, wherein when the terminal device works in a predetermined network environment state, the voice signal in the current space environment is obtained through the terminal device according to the preset time, specifically comprising setting a protection time period at the terminal device end, and obtaining the voice signal in the current environment in the protection time period.

4. The children watch intelligent alarm method based on voiceprint recognition according to claim 1, wherein reading the first characteristic signal and the second characteristic signal in the sound signal specifically comprises classifying the acquired sound characteristic signals and recognizing the first characteristic signal and the second characteristic signal in the sound signal.

5. The intelligent alarm method for the child watch based on the voiceprint recognition is characterized in that in the state that the first characteristic signal is matched with the preset signal, whether the second characteristic signal is matched with the standard signal or not is judged, specifically, the identified second characteristic signal is subjected to noise reduction processing through an algorithm, and the extracted second characteristic signal is compared with a threshold value set by the approximation degree of a sensitive vocabulary library arranged in the terminal device.

6. The intelligent alarm method for the child watch based on the voiceprint recognition according to claim 1, wherein alarm information is output in a state that the second characteristic signal matches a standard signal, and specifically comprises that an automatic alarm is started when the degree of approximation between the second characteristic signal and a built-in sensitive vocabulary library is greater than a predetermined threshold value.

7. The intelligent alarm method for the children watch based on the voiceprint recognition is characterized in that the alarm information is output under the condition that the second characteristic signal is not matched with the standard signal, and the sound signal in the current space environment is continuously acquired, specifically, if the similarity of the built-in sensitive vocabulary library is smaller than a preset threshold value, the sound information of the surrounding environment is returned to the terminal equipment end to detect, detect in real time with the built-in sensitive vocabulary library of the terminal equipment, and recognize the alarm information.

8. The utility model provides a children's wrist-watch intelligence alarm device based on voiceprint discernment which characterized in that: comprises that

The acquisition unit is used for acquiring a sound signal in the current space environment through the terminal equipment according to preset time when the terminal equipment works in a preset network environment state;

the reading unit is used for reading a first characteristic signal and a second characteristic signal in the sound signal;

the judging unit is used for judging whether the second characteristic signal is matched with a standard signal or not in the state that the first characteristic signal is matched with a preset signal;

and the warning unit is used for outputting warning information in the state that the second characteristic signal is matched with the standard signal.

9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements a child watch smart alarm method based on voiceprint recognition as claimed in any one of claims 1 to 7.

10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the voiceprint recognition based child watch smart alert method as claimed in any one of claims 1 to 7 when executing the computer program.

Technical Field

The invention relates to the technical field of intelligent alarm of child watches, in particular to an intelligent alarm method, device, medium and equipment of a child watch based on voiceprint recognition.

Background

The problem of children is a very hot topic in the world, corresponding measures are made in the safety problem country of children every year, but the problems that children are lost and the like cannot be avoided. With the rise of wearable devices, children's smart watches have also grown up in the market climax. Under the common conditions, the intelligent watch can send an alarm signal and a help-seeking short message only after a watch user presses an SOS help-seeking key when the watch user is in danger, the watch user is determined to be in the condition without pressing the SOS key, and the condition possibly affects the safety of children urgently because a key is out of order, so that a method for automatically alarming without contact is required to be designed.

Disclosure of Invention

Aiming at the defects of the prior art, the invention provides a child watch intelligent alarm method, device, medium and equipment based on voiceprint recognition, and solves the problems that the existing child watch needs manual contact for alarm and the alarm mode is inconvenient to use.

In order to achieve the purpose, the invention is realized by the following technical scheme:

in a first aspect, a child watch intelligent alarm method based on voiceprint recognition specifically includes:

acquiring a sound signal in the current space environment through the terminal equipment according to preset time when the terminal equipment works in a preset network environment state;

reading a first characteristic signal and a second characteristic signal in the sound signal;

judging whether the second characteristic signal is matched with a standard signal or not in the state that the first characteristic signal is matched with a preset signal;

and outputting warning information in the state that the second characteristic signal is matched with the standard signal.

Preferably, the method further comprises outputting warning information in a state that the second characteristic signal does not match the standard signal, and continuously acquiring the sound signal in the current space environment.

Preferably, the obtaining the sound signal in the current spatial environment through the terminal device according to the preset time when the terminal device operates in the predetermined network environment state specifically includes setting a protection time period at the terminal device end, and obtaining the sound signal in the current environment in the protection time period.

Preferably, reading the first characteristic signal and the second characteristic signal in the sound signal specifically includes classifying the acquired sound characteristic signals and identifying the first characteristic signal and the second characteristic signal in the sound signal.

Preferably, in a state where the first feature signal matches a preset signal, determining whether the second feature signal matches a standard signal, specifically including performing noise reduction processing on the identified second feature signal through an algorithm, and comparing the extracted second feature signal with a threshold set by an approximation degree of a built-in sensitive vocabulary library of the terminal device.

Preferably, the warning information is output in a state that the second characteristic signal matches the standard signal, specifically including that if the proximity of the second characteristic signal to the built-in sensitive vocabulary library is greater than a predetermined threshold, an automatic alarm is started.

Preferably, outputting warning information in a state that the second characteristic signal does not match the standard signal, and continuing to acquire the sound signal in the current spatial environment, specifically including returning to the terminal device to detect the sound information of the surrounding environment, detecting with the built-in sensitive vocabulary library of the terminal device in real time, and recognizing the warning information if the proximity of the built-in sensitive vocabulary library is smaller than a predetermined threshold.

In a second aspect, the invention provides a child watch intelligent alarm device based on voiceprint recognition, comprising,

the acquisition unit is used for acquiring a sound signal in the current space environment through the terminal equipment according to preset time when the terminal equipment works in a preset network environment state;

the reading unit is used for reading a first characteristic signal and a second characteristic signal in the sound signal;

the judging unit is used for judging whether the second characteristic signal is matched with a standard signal or not in the state that the first characteristic signal is matched with a preset signal;

and the warning unit is used for outputting warning information in the state that the second characteristic signal is matched with the standard signal.

In a third aspect, the present invention provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a child watch smart alarm method based on voiceprint recognition as described above.

In a fourth aspect, the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the intelligent alarm method for a child watch based on voiceprint recognition in the electronic device.

The invention has the following beneficial effects:

according to the intelligent alarm method for the child watch based on voiceprint recognition, a voice signal in the current space environment is obtained through the terminal equipment according to the set preset time; the acquired sound signals are subjected to noise reduction processing, the approximation degree of the built-in sensitive vocabulary library is compared with a preset threshold value, whether alarm information is sent or not is judged, when the sound characteristic signals and the approximation degree of the built-in sensitive vocabulary library are larger than the preset threshold value, automatic alarm is started, when a child meets a dangerous condition, automatic alarm can be achieved without contact, and safety of a child user is guaranteed in time.

Drawings

Fig. 1 is a flowchart of a child watch intelligent alarm method based on voiceprint recognition according to an embodiment of the present invention;

fig. 2 is a schematic structural diagram of a child watch intelligent alarm device based on voiceprint recognition according to a third embodiment of the present invention;

fig. 3 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.

Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the steps as a sequential process, many of the steps can be performed in parallel, concurrently or simultaneously. In addition, the order of the steps may be rearranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.

Example one

Referring to fig. 1, the present invention provides a technical solution: the intelligent child watch alarm method based on voiceprint recognition specifically comprises the following steps:

s110, acquiring a sound signal in the current space environment through the terminal equipment according to preset time when the terminal equipment works in a preset network environment state;

in the embodiment, a protection time period is set at a terminal equipment end, and a sound signal in the current environment is acquired in the protection time period; the management end can directly carry out network connection through network environment and terminal equipment end, for example, the management end is the keeper end, and terminal equipment is the wrist-watch end, sets up children predetermined protection time quantum, if 7: 00-21: 00, the terminal equipment starts a function of acquiring sound signals of the surrounding environment in the time period;

s120, reading a first characteristic signal (whether calling is available) and a second characteristic signal (voiceprint information) in the sound signal;

in this embodiment, in the time period set for monitoring the child safety, the terminal device classifies the read sound signals of the surrounding environment, identifies the first feature signal (whether to call) and the second feature signal (voiceprint information) in the sound feature signals, identifies the first feature signal (whether to call) if a call related vocabulary occurs in the surrounding environment detected by the terminal device, and performs voiceprint feature extraction on the vocabulary of the occurred related call to identify the second feature signal (voiceprint information).

S130, judging whether the second characteristic signal is matched with a standard signal or not in the state that the first characteristic signal is matched with a preset signal;

in this embodiment, when a call-related vocabulary appears in the surrounding environment detected by the terminal device, under the condition that the first feature signal (whether the call is made) is identified, the identified second feature signal (voiceprint information) is subjected to noise reduction processing by the LMS adaptive filtering algorithm, and the extracted second feature signal is compared with a threshold set in the proximity of a built-in sensitive vocabulary library of the terminal device;

s140, outputting warning information in the state that the second characteristic signal is matched with the standard signal;

in this embodiment, when the proximity of the second characteristic signal received by the terminal device to the built-in sensitive vocabulary library is greater than a set threshold, the automatic alarm is started, and meanwhile, the alarm information is transmitted to the notification chief end.

The invention relates to an LMS adaptive filtering algorithm, in particular to a method for automatically adjusting current filter parameters by using filter parameters obtained at the previous moment so as to adapt to unknown or randomly-changed statistical characteristics of signals and noise, thereby realizing optimal filtering.

The error signal is defined as:

wherein the content of the first and second substances,

e (n) is an error signal;

x_i(n) is an input signal sequence;

d (n) is a desired output signal;

w_iare weight coefficients.

The essence of the LMS algorithm is to find the optimal weight coefficient w_iSo that the error signal e (n) is minimized.

Through a series of deductions, an iterative formula of weight coefficients is obtained:

wherein:

mu is a convergence factor;

is a gradient factor;

using the steepest descent method, the key problem of the LMS algorithm becomes the solution of the convergence factor μ and the gradient factor.

(1) Convergence factor μ

Controlling the rate of convergence, wherein the value range is as follows:

where λ is the maximum eigenvalue of the correlation matrix. As it approaches infinity, the weighted fitness vector converges to the optimal wiener solution.

(2) Gradient factor

The gradient factor expression is obtained by approximate calculation:

wherein the content of the first and second substances,

a is an adjustment coefficient;

e (k) is an error signal at time k;

x (k) is an input signal sequence at the time k;

the weight coefficients are therefore ultimately expressed as:

w (k +1) ═ W (k) + a μ e (k) x (k),0.8 < a < 2.2, typically a ═ 1;

wherein the content of the first and second substances,

a is an adjustment coefficient;

mu is a convergence factor;

e (k) is an error signal at time k;

x (k) is an input signal sequence at the time k;

when a is 1, the accuracy of extracting the second characteristic signal (voiceprint information) can be increased, the response time of reading and identifying the second characteristic signal (voiceprint information) is shortened, and the sensitivity of the terminal device to alarm response is improved.

1.3. Algorithm implementation step

S110, settingInitial value of fixed filter w (k):

s120, calculating an estimation value actually output by the filter: y (k) ═ W^T(k)X(k)；

Wherein the content of the first and second substances,

x (k) is the input signal sequence at time k.

S130, calculating an estimation error: e (k) ═ d (k) -y (k);

wherein the content of the first and second substances,

d (k) is the desired output signal at time k;

y (k) is an estimated value for calculating the actual output of the filter;

e (k) is an error signal at time k;

s140, updating the filter coefficient at the moment k + 1: w (k +1) ═ W (k) + μ e (k) x (k);

wherein the content of the first and second substances,

mu is a convergence factor;

e (k) is an error signal at time k

X (k) is the input signal sequence at time k.

k becomes k +1, and steps S120, S130, and S140 are repeated.

In this embodiment, the method further includes outputting warning information in a state that the second characteristic signal does not match the standard signal, and continuing to acquire the sound signal in the current spatial environment, and specifically includes returning to the terminal device to detect sound information of the surrounding environment if the proximity of the second characteristic signal (voiceprint information) identified by the terminal device compared with a sensitive vocabulary library built in the terminal device is smaller than a predetermined threshold, detecting the sound information in real time with the sensitive vocabulary library built in the terminal device, and identifying warning information.

In this embodiment, terminal equipment sends alarm information to and receives alarm platform and simultaneously notifies the management end, specifically includes, for example, the management end is the keeper end, and terminal equipment is the wrist-watch end, and after wrist-watch end discernment alarm information, the wrist-watch end is direct to be connected and send alarm information with receiving alarm platform, and the head of a family end receives alarm information in step.

The invention relates to a child watch intelligent alarm method based on voiceprint recognition, wherein a terminal device is connected with a management end through a network, for example, the management end is a household end, the terminal device is a watch end, a corresponding protection time period is set at the watch end, an acquisition unit acquires a sound signal in the current space environment, a reading unit reads a first characteristic signal and a second characteristic signal in the sound signal, a judgment unit judges whether the second characteristic signal is matched with a standard signal, when the second characteristic signal is matched with the standard signal, if the similarity between the second characteristic signal received by the watch end and a built-in sensitive vocabulary library is greater than a set threshold value, an automatic alarm is started, and meanwhile, an alarm message is transmitted to a household end, otherwise, the peripheral environment signal is continuously monitored and acquired, and the automatic alarm can be realized without contact when a child encounters a dangerous condition, the method comprises the steps of detecting sound information of the surrounding environment at the collected watch end, carrying out noise reduction processing, comparing preset voiceprint information characteristics and environment voice information characteristics, carrying out real-time detection with a built-in sensitive vocabulary library of the watch, identifying alarm information, and timely guaranteeing the safety of a child user.

Example two

Fig. 2 is a schematic structural diagram of a child watch intelligent alarm device based on voiceprint recognition, which is provided by an embodiment of the present invention, and specifically includes:

the acquisition unit 210 is configured to acquire a sound signal in a current spatial environment through the terminal device according to a preset time when the terminal device operates in a predetermined network environment state;

a reading unit 220, configured to read a first characteristic signal and a second characteristic signal in the sound signal;

a judging unit 230, configured to judge whether the second characteristic signal matches a standard signal in a state where the first characteristic signal matches a preset signal;

the warning unit 240 is configured to output warning information in a state where the second characteristic signal matches the standard signal.

The working principle of the embodiment of the invention is that the child watch intelligent alarm device based on voiceprint recognition is implemented, for example, the management terminal is a household terminal, the terminal device is a watch terminal, a corresponding protection time period is set at the watch terminal, the acquisition unit 210 simultaneously acquires a sound signal in the current space environment, the reading unit 220 reads a first characteristic signal and a second characteristic signal in the sound signal, the judgment unit 230 judges whether the second characteristic signal matches a standard signal, when the proximity of the second characteristic signal received at the watch terminal and a built-in sensitive vocabulary library is greater than a set threshold value, the alarm unit 240 starts automatic alarm and simultaneously transmits alarm information to the household terminal, otherwise, the alarm information is continuously monitored and acquired, when the child meets a dangerous condition, the automatic alarm can be realized without contact, the noise reduction processing is performed on the sound information of the acquired by the watch terminal detecting the surrounding environment, and comparing preset voiceprint information characteristics with environment voice information characteristics, detecting the voiceprint information characteristics with a built-in sensitive vocabulary library of the watch in real time, and identifying alarm information to ensure the safety of the child user in time.

EXAMPLE III

Embodiments of the present application also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform:

acquiring a sound signal in the current space environment through the terminal equipment according to preset time when the terminal equipment works in a preset network environment state;

reading a first characteristic signal and a second characteristic signal in the sound signal;

judging whether the second characteristic signal is matched with a standard signal or not in the state that the first characteristic signal is matched with a preset signal;

and outputting warning information in the state that the second characteristic signal is matched with the standard signal.

Storage medium-any of various types of memory devices or storage devices. The term "storage medium" is intended to include: mounting media such as CD-ROM, floppy disk, or tape devices; computer system memory or random access memory such as DRAM, DDR RAM, SRAM, EDO RAM, Lanbas (Rambus) RAM, etc.; non-volatile memory such as flash memory, magnetic media (e.g., hard disk or optical storage); registers or other similar types of memory elements, etc. The storage medium may also include other types of memory or combinations thereof. In addition, the storage medium may be located in the computer system in which the program is executed, or may be located in a different second computer system connected to the computer system through a network (such as the internet). The second computer system may provide the program instructions to the computer for execution. The term "storage medium" may include two or more storage media that may reside in different locations, such as in different computer systems that are connected by a network. The storage medium may store program instructions (e.g., embodied as a computer program) that are executable by one or more processors.

Of course, the storage medium provided in the embodiments of the present application contains computer-executable instructions, and the computer-executable instructions are not limited to the above-mentioned child watch intelligent alarm method based on voiceprint recognition, and may also perform related operations in the child watch intelligent alarm method based on voiceprint recognition provided in any embodiments of the present application.

Example four

The embodiment of the application provides an electronic device, and the child watch intelligent alarm device based on voiceprint recognition provided by the embodiment of the application can be integrated in the electronic device. Fig. 3 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present application. As shown in fig. 3, the present embodiment provides an electronic device 400, which includes: one or more processors 420; storage 410 to store one or more programs that, when executed by the one or more processors 420, cause the one or more processors 420 to implement:

acquiring a sound signal in the current space environment through the terminal equipment according to preset time when the terminal equipment works in a preset network environment state;

reading a first characteristic signal and a second characteristic signal in the sound signal;

judging whether the second characteristic signal is matched with a standard signal or not in the state that the first characteristic signal is matched with a preset signal;

and outputting warning information in the state that the second characteristic signal is matched with the standard signal.

As shown in fig. 3, the electronic device 400 includes a processor 420, a storage device 410, an input device 430, and an output device 440; the number of the processors 420 in the electronic device may be one or more, and one processor 420 is taken as an example in fig. 3; the processor 420, the storage device 410, the input device 430, and the output device 440 in the electronic apparatus may be connected by a bus or other means, and are exemplified by a bus 450 in fig. 3.

The storage device 410 is a computer-readable storage medium, and can be used to store software programs, computer-executable programs, and module units, such as program instructions corresponding to the intelligent alarm method for a child watch based on voiceprint recognition in the embodiment of the present application.

The storage device 410 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 for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the storage 410 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 non-volatile solid state storage device. In some examples, storage 410 may further include memory located remotely from processor 420, which may be connected via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The input means 430 may be used to receive input numbers, character information, or voice information, and to generate key signal inputs related to user settings and function control of the electronic device. The output device 440 may include a display screen, speakers, etc.

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.

Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.