WO2018152724A1

WO2018152724A1 - Identity recognition method, device and system

Info

Publication number: WO2018152724A1
Application number: PCT/CN2017/074537
Authority: WO
Inventors: 李景振; 聂泽东; 刘宇航
Original assignee: 深圳先进技术研究院
Priority date: 2017-02-23
Filing date: 2017-02-23
Publication date: 2018-08-30

Abstract

An identity recognition method, device and system. The method comprises: sending an activation signal to a contacting human body position, so that the activation signal can be transmitted to an excitation signal generation component by means of the human body; receiving a returned identity authentication signal from the contacting human body position, wherein the distance between the excitation signal generation component and the set human body position is shorter than or equal to a distance threshold, the excitation signal generation component generates a standard excitation signal after being activated by the activation signal, and the identity authentication signal is generated after the standard excitation signal passes through the set human body position; extracting biological feature information associated with the set human body position from the identity authentication signal; and performing identity recognition on the human body according to the extracted biological feature information.

Description

Identification method, device and system

Technical field

The present disclosure relates to signal processing techniques, for example, to an identification method, apparatus, and system.

Background technique

With the development of society, identity technology has also achieved rapid development. It has been widely used to identify individual identities using biometric authentication techniques such as fingerprint recognition, speech recognition, iris recognition, and the like.

In the process of implementing the present disclosure, the inventor has found the following technical problems: the technology for realizing identity recognition through biometric authentication technology has certain hidden dangers, for example, iris recognition calculation is complicated and inconvenient to operate; fingerprint recognition and speech recognition are not good in confidentiality, and easy It is imitated and misappropriated, which makes people face financial and other losses, is not safe enough, and can not be identified because of interference, such as fingerprint wear and water, it is difficult to identify.

Summary of the invention

The present disclosure provides an identification method, apparatus, and system that can perform identification quickly, safely, and efficiently.

An identification method, applied to the identification device, may include: transmitting an activation signal to a human body part in contact with the identification device, so that the activation signal is transmitted to the excitation signal generating component through the human body, wherein And a distance between the excitation signal generating component and the set body part is less than or equal to a distance threshold, and the excitation signal generating component generates a standard excitation signal after being activated by the activation signal, and the standard excitation signal is generated after the setting of the human body part The authentication signal.

Receiving, by the contacted human body part, an identity verification signal returned by the human body, extracting, in the identity verification signal, biometric information associated with the set body part, according to the extracted biometric information, The human body is identified.

An identification device is applied to the identity recognition device, and may include: an activation module, a receiving module, an extraction module, and an identification module.

An activation module configured to transmit an activation signal to a body part in contact with the identification device to transmit the activation signal to the excitation signal generating component through the human body, wherein the excitation signal generating component and the setting body component The distance between the distances is less than or equal to the distance threshold, and the excitation signal generating unit After the activation signal is activated, a standard excitation signal is generated, and the standard excitation signal generates the identity verification signal after the setting of the body part.

The receiving module is connected to the activation module and configured to receive an identity verification signal returned by the human body through the body parts that are in contact with each other.

And an extraction module, connected to the receiving module, configured to extract, in the identity verification signal, biometric information associated with the set body part.

The identification module is connected to the extraction module and configured to identify the human body according to the extracted biometric information.

An identification system may include: an excitation signal generating component and an identification device, wherein the excitation signal generating component is wearable on a human body to be recognized, and a distance between the body part and the set body part is less than or equal to a distance threshold.

The identity recognition device is configured to send an activation signal to a human body part in contact with the identification device; receive an identity verification signal returned by the human body through a human body part in contact with the identity recognition device; and extract and And setting biometric information associated with the human body part; and identifying the human body according to the extracted biometric information.

The excitation signal generating component is configured to generate a standard excitation signal according to the received activation signal, and send the standard excitation signal to the identity recognition device via the set body part, wherein the standard excitation signal The identity verification signal is generated after the body part is set.

An electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor.

The memory stores instructions executable by the one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform any of the above identification methods.

A non-transitory computer readable storage medium, wherein the non-transitory computer readable storage medium stores computer instructions for causing the computer to perform any one of the above described identification methods.

A computer program product comprising a computing program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions that, when executed by a computer, cause the computer to perform any of the Identification method.

In this embodiment, the human body is used as a medium for human body communication, and the standard excitation signal is used to identify the identity information generated by setting the human body part and carrying the biometric information of the part. The low power consumption, high data rate, low human damage and high confidentiality of the human body's transmitted signals make identification easy, safe and effective. The identification signal generated by the human body part is not easy to be imitated and used, which can enhance the confidentiality and security of the identity recognition.

DRAWINGS

FIG. 1 is a flowchart of an identity recognition method according to Embodiment 1.

FIG. 2 is a flowchart of an identity recognition method according to Embodiment 2.

FIG. 3 is a flowchart of an identity recognition method according to Embodiment 3.

FIG. 4 is a schematic diagram of a QRS wave extracted by applying the method provided in the third embodiment.

FIG. 5 is a flowchart of an identification method provided in Embodiment 4.

FIG. 6 is a schematic structural diagram of an identity recognition apparatus according to Embodiment 5.

FIG. 7 is a schematic structural diagram of an identity recognition system according to Embodiment 6.

FIG. 8 is a schematic diagram showing the hardware structure of an electronic device according to Embodiment 8 of the present invention.

detailed description

The invention will now be described in conjunction with the drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the disclosure and are not intended to be limiting. In addition, it should be noted that, for the convenience of description, only some but not all of the structures related to the present disclosure are shown in the drawings. The features of the following embodiments and embodiments may be combined with each other without conflict.

Embodiment 1

1 is a flowchart of an identity recognition method according to the first embodiment. The embodiment is applicable to the case where the human body is used as a transmission medium to collect biometric information of a human body part, and the biometric information is used for identity recognition. . The method can be performed by an identification device, which can be implemented by software and/or hardware, which can be integrated in any identification device that provides signal transmission, reception and processing, for example, the device is integrated with a processor In the signal processing device. The method can include S110-S140.

In S110, the identification device transmits an activation signal to the contacted human body part to transmit the activation signal to the excitation signal generating part through the human body.

The human body can be used not only as a receptor for sharing information, but also as a carrier for information transmission. Human body communication refers to the use of the human body as a transmission medium for wireless communication, and information transmission in the human body through capacitive coupling or alternating current coupling. Since the human body communication does not require an antenna design, the transceiver of the human body communication can be made smaller than the ordinary transceiver, and can also be integrated into a person's personal belongings or close-up items, such as To integrate the human body communication transceiver on clothes or watches, and the like. The human body communication transceiver can effectively reduce the influence of external electromagnetic noise on information transmission, has the advantages of low power consumption, high data rate and low human body damage, and can also remove the wire connection when the devices are connected to each other, and can efficiently and conveniently transmit information. In this embodiment, the transceiver can be an excitation signal generating component.

In order to realize identification of the human body, the excitation signal generating component is disposed at a body to be verified close to a set body part (for example, a heart, a wrist or an ankle, etc.). The excitation signal generating component can be activated by an activation signal transmitted by the human body to generate a standard excitation signal. The standard excitation signal is excited by the set body part to generate a signal carrying the biometric information of the set body part (hereinafter referred to as an authentication signal). The identity identification device can identify the human body to be verified by obtaining the above authentication signal.

Optionally, the excitation signal generating component is wearable on the human body to be identified, and the distance between the human body component and the set human body component is less than or equal to a distance threshold, and the distance threshold may be 2 m.

Optionally, the identification device may include a processor and an excitation source, wherein the excitation source is configured to send an excitation signal to a body part (eg, a finger or a palm) that is in contact with the excitation source, and receive the transmission through the human body. Authentication signal. The processor can receive an identity verification signal sent by the excitation source to determine the identity of the human body to be verified.

In this embodiment, in order to send an activation signal to the excitation signal generating component, one or more parts of the human body to be verified are required to contact an excitation source, and the excitation source may send an activation signal to the human body, the activation signal using the human body as a transmission medium. When the activation signal is received, the activation signal is activated by the activation signal generated by the excitation signal generating means disposed close to the body part.

Optionally, the set body part may be a heart. Everyone has different beats due to the heart, and the beat information of the heart is easy to collect. When the heart is used as a body part, the identity of the human body to be verified can be easily and accurately identified.

In S120, the identity recognition device receives an identity verification signal returned by the human body through the body parts that are in contact with each other.

The excitation signal generating component is activated by the activation signal to generate a standard excitation signal, and the standard excitation signal generates an identity verification signal after being stimulated by the body part. Due to the influence of the biometric characteristics of the human body part (for example, heart beat), the characteristics such as the amplitude and frequency of the authentication signal change compared to the standard excitation signal. The authentication signal is transmitted to the excitation source in contact with the human body part by using the human body as a transmission medium, and the excitation source can not only transmit the activation signal but also receive the identity verification signal.

Biometric authentication technology is a technology that realizes human identity recognition by extracting human biological characteristics. Biometrics for biometric authentication techniques can include hand shapes, fingerprints, face shapes, irises, sounds, and the like. These biometrics have the risk of being easily copied and counterfeited. In this embodiment, the identification device and the excitation signal generating component acquire the biological characteristics of the heartbeat of the human body. Because the biological characteristics of the heartbeat corresponding to each human body are different, and it is not easy to forge, it can overcome the defects that the biological features such as fingerprints and sounds are easy to be counterfeited. Therefore, the biometric characteristics of the heartbeat in this embodiment are more reliable and more reliable. Safety. In the embodiment, the identity verification signal may include information of heartbeat, so that the identity verification signal is used to perform identification of the human body to be verified is reliable and secure.

In the identification device, the processor integrated with the excitation source, after receiving the identity verification signal, extracts, analyzes and discriminates the identity verification signal through a signal processing algorithm, thereby identifying the identity of the human body to be verified.

In S130, in the identity verification signal, the identity recognition device extracts biometric information associated with the set body part.

The authentication signal can be a signal of a certain length of time, and not every time the signal contains useful information, so it is necessary to extract the biometric information of the human body part. When the heart is used as the body part, the authentication signal is similar to the electrocardiogram. This biometric information can be a QRS wave, and each person's QRS wave is different. 4 is a schematic diagram of a QRS wave extracted by the identity recognition method in the embodiment. As shown in FIG. 4, in the QRS wave, the R peak point is the point with the largest amplitude in the identity verification signal, and the left side of the R peak point is The minimum extreme point of the neighbor is Q point, the smallest extreme point adjacent to the right side of the R peak point is the S point, and the signal from the Q point to the S point is the QRS wave.

Usually, the heart consists of four chambers, the left and right atrium and the left and right ventricles. The left and right ventricles pump blood out of the aorta and its branches through the body's capillaries, and the left and right atriums recover the blood flowing into the veins and pump the blood into the corresponding ventricles. The cardiomyocytes in the heart are semi-permeable membranes. Under the resting state, a certain number of positively charged cations are arranged outside the membrane. The same number of negatively charged anions are arranged in the membrane, and the extra-membrane potential is higher than the membrane, which is called polarization state. . At rest, the cardiomyocytes in each part of the heart are in a polarized state, and there is no potential difference. The potential curve recorded by the current recorder is straight, which is the equipotential line of the surface electrocardiogram. When the cardiomyocytes are stimulated by a certain intensity, the permeability of the cell membrane changes, and a large amount of cations flow into the membrane in a short time, so that the potential inside the membrane changes from negative to negative. This process is called depolarization. The process of ventricular depolarization is faster, producing a higher frequency ECG waveform, such as ventricular depolarization can generate QRS complexes.

The QRS wave is the largest amplitude group in the ECG and can reflect the whole process of ventricular depolarization. In the QRS wave, a Q wave with a small amplitude and a downward direction is first presented, and then an R wave having a large amplitude and a direction upward is presented, and then an S wave having a small amplitude and a downward direction is presented.

In S140, the identity recognition device identifies the human body according to the extracted biometric information.

In this embodiment, the identity recognition device may identify the human body according to digital features of the biometric information, such as a maximum value, a minimum value, or an average value.

Although each person's biometric information is different, even if the biometric information is quantized into one waveform, there are certain limitations in using the waveform for identification. If the above waveform information can be converted into an identity code similar to the ID number by using a certain algorithm, and then the identified identity code is compared with the pre-stored identity code in the library, the identification can be made more convenient.

In this embodiment, the human body is used as the medium for human body communication, and the identification signal generated by setting the human body part by using the standard excitation signal carries the identity verification signal of the biometric information of the human body part for identification. The low power consumption, high data rate, low human damage and high confidentiality of the human body transmit signals make identification easy, safe and effective. The identification signal generated by the human body part is not easy to be imitated and used, which can enhance the confidentiality and security of the identity recognition.

Embodiment 2

2 is a flowchart of an identity identification method according to the second embodiment. The second embodiment is based on the foregoing embodiment. In the identity verification signal, extracting biometric information associated with the set body part includes: Extracting at least one R peak point in the authentication signal by using a wavelet transform algorithm, and extracting a QRS wave as the biometric information in the identity verification signal according to the location of the R peak point.

The identity recognition method provided in this embodiment includes S201-S205.

In S201, the identification device transmits an activation signal to the contacted human body part, so that the activation signal is transmitted through the human body to the excitation signal generating part disposed in contact with the set body part.

The excitation signal generating component generates a standard excitation signal after being activated by the activation signal, and the standard excitation signal generates the identity verification signal after the setting of the body part.

In S202, an identity verification signal returned by the human body is received by the human body part in contact with the identity recognition device.

In S203, using the wavelet transform algorithm, the identity recognition device extracts at least one R peak point in the identity verification signal.

For the waveform of the identification signal, when the human body part is set as the heart, after several experiments, the QRS wave is relatively stable and is basically not affected by the heart rate change. Therefore, the QRS wave is used as the present embodiment. Biometric information, accurate extraction of QRS waveforms for fast identification important. The R peak point is a feature point, and determining the R peak point is the basis for extracting biometric information. The R peak point is the point with the largest amplitude in the authentication signal, the minimum extreme point adjacent to the left side of the R peak point is Q point, and the smallest extreme point adjacent to the right side of the R peak point is the S point, from the Q point to The signal at point S is the QRS wave.

Wavelet transform inherits and develops the idea of localization of short-time Fourier transform. It can also overcome the shortcomings of window size and frequency variation. It can provide a “time-frequency” window with frequency change, which can be used as a tool for signal time-frequency analysis and processing. . The characteristics of the wavelet transform include features that can fully highlight some aspects of the problem by transform. The wavelet transform can refer to a local transform in time and frequency domain, which can localize the time (space) frequency, and thus can effectively Extract information from the signal. Through the telescopic translation operation, the signal (function) is gradually multi-scale refined, which can realize time subdivision at high frequency and frequency subdivision at low frequency, which can automatically adapt to the requirements of time-frequency signal analysis, so that it can focus on any detail of the signal. The above characteristics of the wavelet transform make the wavelet transform suitable for signal extraction.

In this embodiment, in order to effectively extract the R peak point, the quadratic spline wavelet is used to decompose the identity verification signal according to the porous algorithm, and the quadratic spline wavelet is used as the orthogonal symmetric wavelet with non-compact support. The advantages of smoothness, good frequency characteristics, strong resolving power and linear phase characteristics can effectively extract information. When the filter of the quadratic spline wavelet is used to extract the R peak point, the low-pass filter coefficients h ₀ , h ₁ and h ₂ of the wavelet transform and the wavelet transform high-pass filter coefficients g ₀ , g ₁ and g ₂ are taken. The values can be as shown in Table 1.

Table 1 Filter coefficients of wavelet transform

The extraction of the R peak point may include the following steps.

(1) Perform a quadratic spline wavelet 5-scale decomposition on the authentication signal according to the porous algorithm.

(2) Taking the 2s signal data as a segment, the wavelet decomposition on the 4 scale decomposes the high-frequency coefficients, and calculates the wavelet decomposition positive and negative mode extreme points.

(3) A variable threshold is set, and a modal value pair that satisfies the threshold is detected in each segment. The choice of the variable threshold is related to the positive value of the positive value A ₁ (i-1) and the mean value of the negative value A ₂ (i-1) in the first 2 s data. It is assumed that the maximum positive value of the segment is M and the minimum negative value is N. , the positive and negative thresholds A ₁ (i) and A ₂ (i) are:

(4) Perform time-shift correction on each detected extreme value point of the mode, and find the maximum point in the identity verification signal as the R peak point according to the position of the corrected pair of mode values.

(5) Eliminate excess R peaks. In most cases, there is only a single R peak in the QRS wave, but when the QRS wave appears as a complex wave, that is, when there are multiple R peaks in a single QRS wave, the R peak with a smaller amplitude is eliminated, and the selection has the largest The R peak of the amplitude.

In S204, according to the location of the R peak point, the identity recognition device extracts a QRS wave as the biometric information in the identity verification signal.

Each R peak point corresponds to a QRS wave, and data from the R peak point is taken as a raw QRS wave. Because each heartbeat is different, the biometric information of the individual can be obtained by averaging multiple original QRS waves.

In S205, the identity recognition device identifies the human body according to the extracted biometric information.

In this embodiment, the wavelet transform algorithm is used to extract at least one R peak point in the identity verification signal, and the multi-resolution characteristics of the wavelet transform can accurately extract the R peak point, which is beneficial to extract the biometric information.

Embodiment 3

3 is a flow chart of an identification method provided in the third embodiment, and FIG. 4 is a schematic diagram of a QRS wave provided in the third embodiment. Embodiment 3 is based on the foregoing embodiment, according to the location of the at least one R peak point, extracting a QRS wave as the biometric information in the identity verification signal, as shown in FIG. 4, in the identity verification The signal is based on the at least one R peak point as a base point, and the data of the first time period is extracted from the R peak point to the left, and the data of the second time period is extracted from the R peak point to the right, as the original QRS wave, at least one The original QRS wave is superimposed and averaged to obtain an average QRS wave, and each of the original QRS wave is correlated with the average QRS wave, and the original QRS wave whose correlation exceeds the set correlation threshold is superimposed and averaged to obtain a biological The QRS wave of the feature information.

The identity recognition method provided in this embodiment may include S301-S308.

In S301, the identification device transmits an activation signal to the contacted human body part, so that the activation signal is transmitted through the human body to an excitation signal generating component disposed in contact with the set body part, wherein the excitation signal generating component After the activation signal is activated, a standard excitation signal is generated, and the standard excitation signal generates the identity verification signal after the setting of the body part.

In S302, the identity recognition device receives an identity verification signal returned by the human body through the body parts that are in contact with each other.

In S303, at least one R peak point in the identity verification signal is extracted using a wavelet transform algorithm.

In S304, data of the first time period and data of the second time period are extracted as the base point of each R peak point in the identity verification signal, respectively, as the original QRS wave corresponding to each R peak point.

4 is a schematic diagram of a QRS wave extracted by applying the method provided in the third embodiment, where the R peak point is the point with the largest amplitude in the identity verification signal, and the minimum extreme point immediately adjacent to the left side of the R peak point is the Q point. The minimum extreme point immediately to the right of the R peak point is the S point, and the signal from the Q point to the S point is the QRS wave.

Under normal conditions, the QRS wave width is less than 120ms, with Q points being either or not, and S points may be more than one. Therefore, on the basis of repeated experimental argumentation, an optional extraction method is to extract the data of about 60 ms forward based on the R point, and extract the data of about 100 ms backward as the original QRS wave. That is, the first time period is set to be about 60 ms, and the second time period is set to be about 100 ms. In the present embodiment, a plurality of original QRS waves are extracted by the above method.

In S305, a plurality of the original QRS waves are superimposed and averaged to obtain an average QRS wave.

In order to eliminate the influence of various interference factors and abnormal QRS waves, the selected plurality of original QRS waves are superimposed and averaged to obtain an average QRS wave. The superimposed average may refer to an average of points of corresponding positions in a plurality of original QRS waves.

In S306, correlation analysis is performed between each original QRS wave and the average QRS wave.

Then, each original QRS wave is correlated with the average QRS wave. For example, the threshold θ=0.95 can be set to remove the original QRS wave whose correlation is less than the threshold. The threshold value can also be set to other suitable values as needed.

In S307, the original QRS waves whose correlation exceeds the set correlation threshold are superimposed and averaged to obtain a target QRS wave as biometric information.

Finally, the original QRS wave whose correlation exceeds the threshold is superimposed and averaged to obtain the target QRS wave used as the biometric information, so that the obtained target QRS wave is reliable.

In S308, the human body is identified according to the extracted biometric information.

In this embodiment, the original QRS waves whose correlation exceeds the set correlation threshold are superimposed and averaged to obtain the target QRS wave as the biometric information, and the abnormal data in the identity verification signal can be excluded, and the reliable biometric information is obtained.

Embodiment 4

FIG. 5 is a flowchart of an identity recognition method according to Embodiment 4, and Embodiment 4 is implemented by the foregoing. For example, the identifying the human body according to the extracted biometric information includes: inputting the biometric information into a pre-trained identity recognition model, and acquiring an identity code output by the identity recognition model; The identity recognition model pre-stores a legal identity code corresponding to the biometric information of the legal user, and identifies the human body according to the identity code output by the identity recognition model.

The identity recognition method provided in this embodiment may include S401-S405.

In S401, the identification device transmits an activation signal to the contacting human body part, so that the activation signal is transmitted through the human body to the excitation signal generating part disposed close to the set body part.

In S402, an identity verification signal returned by the human body is received by the body parts that are in contact with each other.

In S403, biometric information associated with the set body part is extracted in the identity verification signal.

In S404, the biometric information is input into a pre-trained identity recognition model, and an identity code output by the identity recognition model is obtained. The legal identity code corresponding to the biometric information of the legal user is pre-stored.

The biometric information is input into a pre-trained identification model, and the identity model outputs an identity code. Each user's identity code is unique and will be pre-stored for comparison with the identity model output identity code.

Optionally, the identity recognition model may be a back propagation neural network model.

The neural network method is a widely used method. Among many neural network algorithms, the back propagation neural network is a multi-layer feedforward network trained by the error inverse propagation algorithm, also called BP neural network. BP neural networks can learn and store a large number of input-output mode mapping relationships without the need to reveal mathematical equations describing such mapping relationships in advance.

The BP neural network algorithm is used for identification. Illustratively, the calculation can employ a three-layer neural network, namely an input layer, an intermediate layer, and an output layer. In the network, signals are transmitted from the input to the output in one direction, and the neurons in the same layer do not pass signals to each other. Each neuron is connected to all neurons in an adjacent layer. The output value of a layer of neurons is transmitted to the neurons of the next layer by the enhancement or inhibition of the connection weight coefficient. In addition to the input layer, the input to each neuron is the weighted sum of the output values of all neurons in the previous layer. In this embodiment, the number of nodes in the three-layer neural network is different. Illustratively, the number of nodes in the input layer neural network is seven, and the number of nodes in the intermediate layer neural network is ten, and the output layer The number of nodes in the neural network is two.

BP network qth layer output

Can be obtained by:

Where s _i represents the output of the hidden node,

Indicates the output of the hidden node corresponding to the qth layer,

a connection weight coefficient indicating the input of the jth node of the q-1 layer to the input of the i th node of the qth layer,

Indicates the action threshold for each neuron node on the qth layer, n indicates the number of nodes, and n _q-1 indicates the number of nodes on the q-1th layer.

The BP network is a reverse error propagation network. Its training is realized by the error signal propagating from the output layer to the input layer and adjusting the connection weight coefficients between the layers along the way. Given a set of sample data, calculate the actual output of each layer

Let the ideal output of the sample be d _pi , then adjust each connection weight coefficient by the following formula:

After the evolution of the split and split, you can get:

According to the above formula, each connection coefficient can be obtained as:

Where δ represents the adjustment parameter of the connection weight coefficient, q represents the common q layer of the BP network, Q represents the superposition operation of the q layer of the BP network, n _q+1 represents the number of nodes of the q+1th layer, and μ represents the learning rate coefficient of the algorithm. , α represents a momentum factor, 0 < α < 1.

For example, the BP network has three layers, q=3,

Indicates the adjustment parameter between the pth node of the 3rd layer (the topmost layer) and the kth node of the 1st layer (the lowermost layer).

The BP neural network algorithm is simple and accurate, and can accurately identify the identity.

In S405, the human body is identified according to the identity code output by the identity recognition model.

The identity code output by the identity model is compared with the pre-stored identity code, and a unique corresponding pre-stored identity code can be found to determine the identity of the user. Finding the corresponding identity based on the identity code without having to match the biometric information not only increases the operability of the experiment but also saves a lot of computation.

In this embodiment, the biometric information is input into a pre-trained identity recognition model by pre-storing the legal identity code corresponding to the biometric information of the legal user, and the identity code output by the identity recognition model is obtained, according to the identity. The identity code output by the recognition model identifies the human body, and the identity recognition model and identity coding can be used for simple and accurate identification.

Embodiment 5

FIG. 6 is a schematic structural diagram of an identity recognition apparatus according to Embodiment 5, which may be used to perform any one of the foregoing embodiments. The apparatus may include an activation module 501, a receiving module 502, an extraction module 503, and an identification module 504.

The activation module 501 is configured to send an activation signal to the contacted human body position, so that the activation signal is transmitted through the human body to an excitation signal generating component disposed adjacent to the set body part, wherein the excitation signal generating component and the setting body The distance between the parts is less than or equal to the distance threshold.

The receiving module 502 is connected to the activation module 501, and is configured to receive an identity verification signal returned by the human body through the contacted human body position, wherein the excitation signal generating component generates a standard after being activated by the activation signal And an excitation signal, wherein the standard excitation signal generates the identity verification signal after the setting of the body part.

The extraction module 503 is connected to the receiving module 502 and configured to extract biometric information associated with the set body part in the identity verification signal.

The identification module 504 is connected to the extraction module 503 and configured to identify the human body according to the extracted biometric information.

In this embodiment, the human body is used as a medium for human body communication, and the standard excitation signal is used to identify the identity information generated by setting the human body part and carrying the biometric information of the part. The low power consumption, high data rate, low human damage and high confidentiality of the human body's transmitted signals make identification easy, safe and effective. The identification signal generated by the human body part is not easy to be imitated and misappropriated, which further enhances the confidentiality and security of the identification.

Optionally, the set body part is a heart.

Optionally, the extraction module 503 includes an R peak point extraction unit and a biometric extraction unit.

An R peak point extracting unit configured to extract, by using a wavelet transform algorithm, to the identity verification signal One less R peak point.

The biometric extracting unit is connected to the R peak point extracting unit and configured to extract a QRS wave as the biometric information in the identity verification signal according to the location of the R peak point.

Optionally, the biometric extraction unit includes an original waveform extraction subunit, a first average subunit, a correlation analysis subunit, and a second average subunit.

The original waveform extraction subunit is configured to extract data of the first time period forward by using each R peak point as a base point in the identity verification signal, and extract data of the second time period backward as each R peak point Corresponding to the original QRS wave.

A first average subunit, coupled to the original waveform extraction subunit, is configured to superimpose and average at least one of the original QRS waves to obtain an average QRS wave.

A correlation analysis subunit, coupled to the first average subunit, is configured to correlate each of the original QRS waves with an average QRS wave.

The second average subunit is connected to the correlation analysis subunit, and is configured to superimpose and average the original QRS waves whose correlation exceeds the set correlation threshold to obtain the QRS wave as biometric information.

In this embodiment, the original QRS waves whose correlation exceeds the set correlation threshold are superimposed and averaged to obtain the QRS wave as biometric information, and the abnormal data in the identity verification signal can be excluded, and reliable biometric information is obtained.

Optionally, the identification module 504 includes an identity code acquisition unit and an identity recognition unit.

An identity code obtaining unit is configured to input the biometric information into a pre-trained identity recognition model, and obtain an identity code output by the identity recognition model; wherein, the legal identity code corresponding to the biometric information of the legal user is pre-stored .

The identity identification unit is connected to the identity code acquisition unit and configured to identify the human body according to the identity code output by the identity recognition model.

The identity recognition apparatus provided in this embodiment may be used to perform the identity recognition method provided by any of the foregoing embodiments, and has the corresponding functions and beneficial effects of performing the method.

Embodiment 6

FIG. 7 is a schematic structural diagram of an identity recognition system according to Embodiment 6. The identification system may include an excitation signal generating component 601 and an identification device 602, the excitation signal generating component 601 being worn on a position of the human body 603 to be verified close to the set body part, between the excitation signal generating component and the setting body part The distance is less than or equal to the distance threshold.

The identity recognition device 602 is configured to send an activation signal to the contacted human body part; receive an identity verification signal returned by the human body through the contacted human body part; and extract and describe the identity verification signal Setting biometric information associated with the human body part; and identifying the human body according to the extracted biometric information.

The excitation signal generating component 601 is configured to generate a standard excitation signal according to the received activation signal, and send the standard excitation signal to the identity recognition device via the set body part, wherein the standard excitation The identity verification signal is generated after the signal passes the set body part.

Optionally, as shown in FIG. 7, the identification device 602 may include an excitation source 6021 and a processor 6022, wherein the excitation source 6021 is in contact with one or more parts of the human body 603 to be verified, and is in contact with the human body part. Send an activation signal and receive an authentication signal returned by the human body. The processor receives the identity verification signal sent by the excitation source, and extracts the biometric information in the identity verification signal for identification of the human body to be authenticated. The excitation signal generating part 601 is disposed at a position close to the human heart 6031 to be verified, and the distance between the excitation signal generating part and the set body part is usually less than or equal to the distance threshold. Further, the excitation signal generating part 601 may be disposed at a portion such as a wrist or an ankle of the human body 603 to be verified.

The identity recognition system provided in this embodiment may be used to perform the identity recognition method provided by any of the foregoing embodiments, and has the corresponding functions and beneficial effects of performing the method.

Example 7

The seventh embodiment further provides a non-transitory computer readable storage medium, wherein the non-transitory computer readable storage medium stores computer executable instructions, which can be provided by any of the above embodiments Identification method.

Example eight

FIG. 8 is a schematic diagram showing the hardware structure of an electronic device according to the eighth embodiment. As shown in FIG. 8, the electronic device includes: one or more processors 710. One processor 710 is taken as an example in FIG. 8; .

The electronic device may further include an input device 730 and an output device 740.

The processor 710, the memory 720, the input device 730, and the output device 740 in the electronic device may be connected by a bus or other means, as exemplified by a bus connection in FIG.

The memory 720, as a non-transitory computer readable storage medium, can be used to store software programs, computer executable programs, and modules, such as programs, instructions, and modules corresponding to the identification methods in any embodiment (eg, FIG. 6 The activation module 501, the receiving module 502, the extraction module 503, and the identification module 504) are shown. The processor 710 executes the function application and the data processing by executing software programs, instructions, and modules stored in the memory 720, that is, implementing the identity recognition method of the above method embodiment.

The memory 720 may include a storage program area and an storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store data created according to usage of the electronic device, and the like. Moreover, memory 720 can include high speed random access memory, and can 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 embodiments, memory 720 can optionally include memory remotely located relative to processor 710, which can be connected to the electronic device over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

Input device 730 can be configured to receive input digital or character information and to generate key signal inputs related to user settings and function controls of the electronic device. The output device 740 can include a display device such as a display screen.

The electronic device of the present embodiment may further include a communication device 750 that transmits and/or receives information over a communication network.

Finally, it should be understood that those skilled in the art can understand that all or part of the process of implementing the above embodiment method can be completed by executing related hardware by a computer program, and the program can be stored in a non-transitory computer. In reading a storage medium, the program, when executed, may include a flow of an embodiment of the method described above, wherein the computer readable storage medium may be a magnetic disk, an optical disk, a read only memory (ROM), or a random access memory. (RAM), etc.

Industrial applicability

The present disclosure provides an identification method, device and system for identity verification by human body transmission Signals are used for identification, making identification easy and secure, and enhancing the confidentiality and security of identity.

Claims

An identification method applied to an identification device includes:

Transmitting an activation signal to a body part in contact with the identification device to transmit the activation signal to the excitation signal generating part through the human body, wherein a distance between the excitation signal generating part and the set body part is less than a distance a threshold value, the excitation signal generating component generates a standard excitation signal after being activated by the activation signal, and the standard excitation signal generates the identity verification signal after the setting of the body part;

Receiving an identity verification signal returned by the human body through the body parts that are in contact with each other;

Extracting, in the authentication signal, biometric information associated with the set body part;

And identifying the human body according to the extracted biometric information.
The method of claim 1 wherein said setting the body part is a heart.
The method according to claim 1 or 2, wherein in the identity verification signal, extracting biometric information associated with the set body part comprises:

Extracting a plurality of R peak points in the authentication signal using a wavelet transform algorithm;

A QRS wave corresponding to each R peak point is extracted as the biometric information in the authentication signal according to the location of each R peak point.
The method according to claim 3, wherein the QRS wave corresponding to each R peak point is extracted as the biometric information in the identity verification signal according to the location of each R peak point, including:

Determining data of the first time period and data of the second time period as the original QRS wave corresponding to each R peak point in the authentication signal with each R peak point as a base point;

A plurality of original QRS waves are superimposed and averaged to obtain an average QRS wave;

Correlate each original QRS wave to the average QRS wave;

The original QRS waves whose correlation exceeds the set correlation threshold are superimposed and averaged to obtain a target QRS wave as biometric information.
The method according to claim 1, wherein the identifying the human body based on the extracted biometric information comprises:

Inputting the biometric information into a pre-trained identity recognition model, and acquiring an identity code output by the identity recognition model; wherein the identity recognition model pre-stores a legal identity code corresponding to the biometric information of the legal user;

The human body is identified according to an identity code output by the identity recognition model.
The method of claim 5, wherein the identity recognition model is a back propagation nerve Network model.
An identification device for use in an identification device includes:

An activation module configured to send an activation signal to a body part in contact with the identification device to transmit the activation signal to the excitation signal generating component through the human body, wherein the excitation signal generating component and the set body part are The distance is less than the distance threshold, and the excitation signal generating component generates a standard excitation signal after being activated by the activation signal, and the standard excitation signal generates the identity verification signal after the setting of the body part;

a receiving module, connected to the activation module, configured to receive an identity verification signal returned by the human body through a human body part in contact with the identity recognition device;

An extraction module, coupled to the receiving module, configured to extract, in the identity verification signal, biometric information associated with the set body part;

The identification module is connected to the extraction module and configured to identify the human body according to the extracted biometric information.
The device according to claim 7, wherein said set body part is a heart.
The apparatus according to claim 7 or 8, wherein the extraction module comprises:

An R peak point extracting unit configured to extract a plurality of R peak points in the identity verification signal by using a wavelet transform algorithm;

a biometric extracting unit connected to the R peak point extracting unit, configured to extract a QRS wave corresponding to each R peak point as the biometric information in the identity verification signal according to a location of each R peak point .
The device according to claim 9, wherein the biometric extraction unit comprises:

The original waveform extraction subunit is configured to extract data of the first time period and data of the second time period as the base point of each R peak point in the identity verification signal, as the original corresponding to each R peak point QRS wave;

a first average subunit, connected to the original waveform extraction subunit, configured to superimpose and average a plurality of original QRS waves to obtain an average QRS wave;

a correlation analysis subunit, coupled to the first average subunit, configured to correlate each original QRS wave with an average QRS wave;

The second average subunit is connected to the correlation analysis subunit, and is configured to superimpose and average the original QRS waves whose correlation exceeds the set correlation threshold to obtain a target QRS wave as biometric information.
The apparatus of claim 7, wherein the identification module comprises:

An identity code obtaining unit is configured to input the biometric information into a pre-trained identity recognition model, and obtain an identity code output by the identity recognition model; wherein the identity recognition model pre-stores biometric information corresponding to the legal user Legal identity code;

The identity identification unit is connected to the identity code acquisition unit and configured to identify the human body according to the identity code output by the identity recognition model.
The apparatus of claim 11 wherein said identity recognition model is a backpropagation neural network model.
An identification system includes: an excitation signal generating component and an identification device, wherein the excitation signal generating component is worn on the human body to be recognized, and the distance between the human body component and the set human body component is less than a distance threshold;

The identity recognition device is configured to send an activation signal to a human body part in contact with the identification device; receive an identity verification signal returned by the human body through a human body part in contact with the identity recognition device; and extract and Setting biometric information associated with a human body part; and identifying the human body according to the extracted biometric information;

The excitation signal generating component is configured to generate a standard excitation signal according to the received activation signal, and send the standard excitation signal to the identity recognition device via the set body part, wherein the standard excitation signal The identity verification signal is generated after the body part is set.
An electronic device comprising:

At least one processor; and,

a memory communicatively coupled to the at least one processor; wherein

The memory stores instructions executable by the one processor, the instructions being executed by the at least one processor to enable the at least one processor to implement the identity of any of claims 1-6 recognition methods.
A non-transitory computer readable storage medium, wherein the non-transitory computer readable storage medium stores computer instructions for causing the computer to perform the identity of any of claims 1-6 recognition methods.
A computer program product comprising a computing program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions that, when executed by a computer, cause the computer to perform claims 1-6 The identification method of any of the above.