IDENTITY IDENTIFICATION METHOD, DEVICE AND COMPUTER-READABLE STORAGE MEDIUM

Abstract

An embodiment of the present application provides an identity recognition method, device and computer-readable storage medium; wherein the method includes: acquiring a first signal sequence; the first signal sequence includes at least two first signals; each of the at least two first signals is related to the motion trajectory of an electronic device; analyzing the first signal sequence, and determining at least two target signals of the first signal sequence according to the analysis results; extracting at least one valid signal from the first signal sequence according to the at least two target signals; obtaining a second signal sequence based on the at least one valid signal; and the second signal sequence is used for identity recognition.

Description

Technical Field

[0001] The present application relates to a security technology, and more particularly to an identity recognition method, device and computer-readable storage medium. Background Art

[0002] Generally speaking, the identity authentication technologies people use include password recognition, fingerprint recognition and face recognition. However, password recognition technology has the defects that the password is too simple and easy to be cracked by others, and too complex and easy to be forgotten by users. Fingerprint recognition technology and face recognition technology involve unique biological features. Once copied and stolen by others, it will cause significant losses to users.

[0003] To this end, relevant technical personnel have proposed a technology that uses the gesture habits of users when using electronic devices to identify the identity of users. Although this authentication method is safer and simpler than the above authentication methods, the relevant technology cannot accurately extract effective gesture signals from the collected gesture signals, resulting in the lack of accuracy of this technology for authenticating user identities based on user gesture habits, which brings inconvenience to users. Summary of the invention

[0004] In order to solve the existing technical problems, the embodiments of the present application provide an identity recognition method, device and computer-readable storage medium, which can at least adaptively determine the valid signals associated with the user's gesture habits and use the valid signals to accurately identify the user's identity.

[0005] The technical solution of the embodiment of the present application is implemented as follows:

[0006] The present application embodiment provides an identity recognition method, which is applied to an electronic device, and the method includes:

[0007] Acquire a first signal sequence; the first signal sequence includes at least two first signals; each of the at least two first signals is related to the motion trajectory of the electronic device;

[0008] analyzing the first signal sequence, and determining at least two target signals of the first signal sequence according to the analysis result;

[0009] According to the at least two target signals, at least one valid signal is extracted from the first signal sequence; based on the at least one valid signal, a second signal sequence is obtained; and the second signal sequence is used for identity recognition.

[0010] In the above solution, analyzing the first signal sequence and determining at least two target signals of the first signal sequence according to the analysis result includes:

[0011] Arrange at least two first signals in ascending order according to the signal values ​​of at least two first signals in the first signal sequence to obtain a first ascending signal sequence; the first ascending signal sequence includes: at least one first signal sorted by signal value;

[0012] For each of the first signals, determining the increasing speed of each of the first signals according to a reference signal corresponding to the first signal in the first ascending signal sequence; the reference signal is an adjacent signal of the first signal;

[0013] Determining, according to the increasing speed of each of the first signals, a first signal satisfying a target condition from the first ascending signal sequence;

[0014] At least two target signals are determined from the first signal sequence according to the signal value of the first signal that meets the target condition.

[0015] In the above solution, the step of determining the first signal satisfying the target condition from the first ascending signal sequence includes:

[0016] Determine a weight of each first signal in the first ascending signal sequence; wherein the weight is a ratio of an increase rate of each first signal to an increase rate of a reference signal corresponding to each first signal;

[0017] Determine at least one first signal having a weight greater than a preset threshold from the first ascending signal sequence as at least one candidate signal;

[0018] A first signal satisfying a target condition is determined from the at least one candidate signal.

[0019] In the above solution, the step of determining the first signal satisfying the target condition from the at least one candidate signal includes:

[0020] Selecting a candidate signal according to the order of the at least one candidate signal in the first ascending signal sequence;

[0021] Determine a first total number and a second total number of the currently selected candidate signals; the first total number is the total number of first signals that are sequentially before the currently selected candidate signal, and the second total number is the total number of first signals that are sequentially before the currently selected candidate signal and have a weight smaller than the weight of the currently selected candidate signal;

[0022] Determining whether a quotient of a second total number of currently selected candidate signals and a first total number is less than or equal to a first value;

[0023] If so, the currently selected candidate signal is determined to be a signal that meets the target condition; if not, return to selecting the candidate signal and repeat the process until the quotient of the second total number of the currently selected candidate signals and the first total number is less than or equal to the first value, and the currently selected candidate signal is determined to be a signal that meets the target condition.

[0024] In the above solution, before arranging at least two first signals in ascending order according to the signal values ​​of at least two first signals in the first signal sequence to obtain a first ascending signal sequence, the method further includes:

[0025] According to a preset second threshold, extract at least two first signals that meet the threshold requirement from the first signal sequence to obtain a third signal sequence;

[0026] Correspondingly, the method of arranging at least two first signals in ascending order according to the signal values ​​of at least two first signals in the first signal sequence to obtain a first ascending signal sequence includes:

[0027] According to the signal values ​​of at least two first signals that meet the threshold requirement in the third signal sequence, the at least two first signals that meet the threshold requirement are arranged in ascending order to obtain a first ascending signal sequence.

[0028] In the above scheme, the at least two target signals include: a first target signal and a second target signal; the first target signal and the second target signal are the demarcation points between invalid signals and valid signals;

[0029] The step of extracting at least one valid signal from the first signal sequence according to the at least two target signals comprises:

[0030] At least one valid signal is extracted from the first signal sequence according to the first target signal and the second target signal.

[0031] In the above solution, before acquiring the first signal sequence, the method further includes:

[0032] Collecting an original signal sequence associated with the motion trajectory of the electronic device, wherein the original signal sequence includes at least two original signals;

[0033] The short-time average amplitude of the original signal sequence is taken to obtain the first signal sequence.

[0034] The present application also provides an identity recognition device, which is applied to an electronic device, and the device includes:

[0035] An acquisition unit, configured to acquire a first signal sequence; the first signal sequence includes at least two first signals; each of the at least two first signals is related to a motion trajectory of the electronic device;

[0036] an analyzing unit, configured to analyze the first signal sequence, and determine at least two target signals of the first signal sequence according to the analysis result;

[0037] The identification unit is used to extract at least one valid signal from the first signal sequence according to the at least two target signals; obtain a second signal sequence based on the at least one valid signal; and the second signal sequence is used for identity identification.

[0038] An embodiment of the present application also provides an identity recognition device, which is applied to an electronic device. The device includes: a processor and a memory for storing a computer program that can be run on the processor, wherein the processor is used to execute the steps of the aforementioned identity recognition method when running the computer program.

[0039] An embodiment of the present application also provides a computer-readable storage medium, which is applied to an electronic device and has a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the aforementioned identity recognition method are implemented.

[0040] The embodiments of the present application provide an identity recognition method, device, and computer-readable storage medium, which can obtain a first signal sequence related to the motion trajectory of an electronic device, analyze the first signal sequence, determine at least two target signals in the first signal sequence based on the analysis results, extract at least one valid signal from the first signal sequence based on the at least two target signals, and obtain a second signal sequence for identity recognition. In the aforementioned scheme, the embodiments of the present application analyze the first signal sequence related to the motion trajectory of the electronic device, and can adaptively determine at least two target signals from the first signal sequence according to the analysis results and the actual motion trajectory of the electronic device. In this way, the embodiments of the present application extract at least one valid signal from the first signal sequence based on at least two target signals, and obtain the second signal sequence for identity recognition based on at least one valid signal, which can improve the flexibility and accuracy of obtaining the second signal sequence, thereby effectively improving the flexibility and accuracy of user identity recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0042] Figure 1 Schematic diagram of the process of the identity recognition method provided in the embodiment of the present application Figure 1 ;

[0043] Figure 2 Schematic diagram of the process of the identity recognition method provided in the embodiment of the present application Figure 2 ;

[0044] Figure 3 Schematic diagram of the process of the identity recognition method provided in the embodiment of the present application Figure 3 ;

[0045] Figure 4a , Figure 4b , Figure 4c and Figure 4d They are the original signal sequences corresponding to the hand gestures of letters a, b, c and d;

[0046] Figure 5a , Figure 5b , Figure 5c and Figure 5d are the first signal sequences corresponding to the hand gestures of letters a, b, c and d respectively;

[0047] Figure 6a , Figure 6b , Figure 6c and Figure 6d are the third signal sequences corresponding to the hand gestures of letters a, b, c and d respectively;

[0048] Figure 7a , Figure 7b , Figure 7c and Figure 7d are the first ascending signal sequences corresponding to the gesture actions of letters a, b, c and d respectively;

[0049] Figure 8a , Figure 8b , Figure 8c and Figure 8d are the weight sequences corresponding to the gesture actions of letters a, b, c and d respectively;

[0050] Figure 9a , Figure 9b , Fig.9c and Figure 9d are second signal sequences corresponding to the hand gestures of letters a, b, c and d respectively;

[0051] Fig.10 Flow chart 4 of the identity recognition method provided in the embodiment of the present application;

[0052] Fig.11 Flow chart 5 of the identity recognition method provided in the embodiment of the present application;

[0053] Fig.12 A schematic diagram of the structure of the identity recognition device provided in the embodiment of the present application Figure 1 ;

[0054] Fig.13 A schematic diagram of the structure of the identity recognition device provided in the embodiment of the present application Figure 2 . DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. In the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other arbitrarily.

[0056] In the related art, in order to utilize the user's gesture habits when using electronic devices to identify the user's identity, the user is required to hold the electronic device and make gestures, so that the electronic device generates a certain motion trajectory. The acceleration sensor in the electronic device collects the acceleration obtained by the electronic device at a certain frequency based on the certain motion trajectory to obtain multiple acceleration signals. In order to identify when the user's gesture action starts and ends, the related art generally implements it through two schemes: one is to set a start button and an end button on the electronic device, and determine the start and end of the gesture action by the user triggering the button; the other is to determine a fixed threshold through a large number of experiments, and based on the fixed threshold and the signal values ​​of the multiple acceleration signals collected, the acceleration signal associated with the gesture action is intercepted to determine the start and end of the gesture action.

[0057] Compared with the solution of identifying when the user's gesture action starts and ends in the related art, the present application can at least analyze the characteristics of the collected multiple acceleration signals, adaptively determine the effective signal associated with the user's gesture habits, and use the effective signal to accurately identify the user's identity. The specific implementation of the above solution is shown in the following embodiments.

[0058] Those skilled in the art should know that the electronic devices involved in the following embodiments of the present application can be any electronic devices, such as: industrial control computers, personal computers and other types of computers, all-in-one computers, laptops, tablet computers, mobile phones, e-readers, etc., and can also be wearable devices such as smart glasses, smart watches, smart shoes, etc. The preferred electronic device in the embodiments of the present application is a mobile phone.

[0059] Embodiment 1

[0060] like Figure 1 The figure shows the process flow of the identity recognition method provided in this embodiment. Figure 1 The method includes S101 to S103; the execution subject of S101 to S103 is an electronic device, wherein:

[0061] (Step) S101: Acquire a first signal sequence; the first signal sequence includes at least two first signals; each of the at least two first signals is related to a motion trajectory of the electronic device;

[0062] In the embodiment of the present application, before the electronic device acquires the first signal sequence, the method further includes:

[0063] Collecting an original signal sequence associated with the motion trajectory of the electronic device, wherein the original signal sequence includes at least two original signals;

[0064] The short-time average amplitude of the original signal sequence is taken to obtain the first signal sequence.

[0065] It can be understood that the electronic device recognizes the identity of the user based on the user's gesture habits, which requires the user to hold the electronic device and make gestures so that the electronic device can recognize the user's gesture habits; the electronic device can generate a certain motion trajectory in the air based on the user's gestures, and in the process of the electronic device generating a certain motion trajectory, the electronic device can generate motion physical quantities such as displacement, velocity and acceleration. Based on this, the electronic device can use the built-in sensor to collect displacement, velocity or acceleration according to the preset collection frequency to obtain a displacement signal sequence, a velocity signal sequence or an acceleration signal sequence.

[0066] Considering that the data sensitivity of acceleration in the aforementioned motion quantity is low and easier to process, the original signal sequence collected by the electronic device in the embodiment of the present application is preferably an acceleration signal sequence, and the electronic device can collect the acceleration signal through an acceleration sensor. In the embodiment of the present application, the acceleration sensor is preferably a linear acceleration sensor to avoid the influence of gravity acceleration on the collected acceleration, thereby simplifying the signal processing process of the original signal sequence. In addition, the acquisition frequency of the electronic device can be 10 Hz, 50 Hz or 100 Hz; in order to take into account the accuracy and efficiency of signal processing, the acquisition frequency in the embodiment of the present application is preferably 50 Hz, that is, the acquisition frequency of the electronic device in SENSOR_DELAY_GAME mode.

[0067] In the embodiment of the present application, since at least two original signals are vector signals, it is not convenient for the electronic device to identify valid signals, and the electronic device performs signal processing on the original signal sequence, which can be specifically achieved through two signal processing methods: first, the short-time average amplitude of the original signal sequence is calculated, and at least two first signals are obtained according to the short-time average amplitude, and the first signal sequence is determined; second, the short-time energy amplitude of the original signal sequence is calculated, and at least two first signals are obtained according to the short-time energy amplitude, and the first signal sequence is determined. Please refer to the subsequent description for the specific calculation method, which will not be repeated here. Considering that the short-time average amplitude carries less energy information than the short-time energy amplitude, has lower data sensitivity, can more truly reflect the dynamic change trend of gesture actions, can also prevent fixed-point overflow and reduce data processing volume, and improve data processing efficiency, the signal processing of the original signal sequence in the present application is preferably the first signal processing method.

[0068] Thus, the electronic device can obtain a first signal sequence, and each of the at least two first signals in the first signal sequence is a signal related to the motion trajectory of the electronic device. In addition, the first signal sequence obtained by the electronic device in the present application has a lower data sensitivity, making the data more stable, which is conducive to obtaining an effective signal that can characterize the user's gesture habits based on the first signal sequence.

[0069] S102: Analyze the first signal sequence, and determine at least two target signals of the first signal sequence according to the analysis result;

[0070] In the embodiment of the present application, the analysis of the first signal sequence is specifically an analysis of the signal values ​​of at least two first signals in the first signal sequence;

[0071] In the embodiment of the present application, the first signal sequence includes a valid signal that can represent the gesture habits of the user, and also includes an invalid signal;

[0072] According to actual applications, an invalid signal is a signal generated before the user starts to make gestures while holding the electronic device, and is related to the jitter and / or transition movement generated when the user holds the electronic device. Therefore, in the first signal sequence, the distribution of invalid signals and valid signals is: invalid signal area -> valid signal area -> invalid signal area. Based on this, in order to determine the valid signal in the first signal sequence, the present application analyzes the first signal sequence and determines at least two target signals in the first signal sequence, and the at least two target signals are the first signal at the boundary between the invalid signal area and the valid signal area.

[0073] S103: extracting at least one valid signal from the first signal sequence according to the at least two target signals; obtaining a second signal sequence based on the at least one valid signal; the second signal sequence is used for identity recognition;

[0074] It can be understood that the at least two target signals represent at least two boundary positions between valid signals and invalid signals. Therefore, the present application can extract at least one valid signal in the first signal sequence based on the at least two target signals, and obtain a second signal sequence that can be used to identify the user based on the at least one valid signal.

[0075] In the embodiment of the present application, since the acquired first signal sequence is related to the motion trajectory generated by the electronic device when the user holds the electronic device and makes gestures, the present application determines at least two target signals in the first signal sequence by analyzing the characteristics of the first signal sequence, and can accurately identify the boundary position of the valid signal and the invalid signal in the first signal sequence based on the at least two target signals, thereby accurately extracting the valid signal that can characterize the user's gesture habits. Therefore, the user's identity can be identified using the valid signal in the present application, which can improve the accuracy of the identity recognition result.

[0076] It should be noted here that, according to actual applications, since the user holds the electronic device and makes gestures, jitters will occur before the user holds the electronic device and makes gestures. In addition, the user holds the electronic device and makes transition movements when preparing to make gestures. Therefore, the first signal sequence acquired by the electronic device includes not only valid signals related to the user's gestures, but also invalid signals related to the user. Among them, the invalid signal includes a first invalid signal and a second invalid signal; wherein the first invalid signal is related to the jitters generated before the user holds the electronic device and makes gestures, and the second invalid signal is related to the transition movements made when the user holds the electronic device and prepares to make gestures.

[0077] It can be determined that the distribution of the first invalid signal, the second invalid signal and the valid signal in the first signal sequence is: first invalid signal area -> second invalid signal area -> valid signal area -> second invalid signal area -> first invalid signal area. Figure 5a As shown, it is a first signal sequence acquired by the electronic device when the motion trajectory generated by the electronic device is letter a, wherein the first invalid signal area A1, the second invalid signal area A2 and the valid signal area A3 are marked.

[0078] Generally, the signal value of the first invalid signal is close to 0, and is significantly different from the signal value of the second invalid signal. The signal value of the second invalid signal is significantly different from the signal value of the valid signal.

[0079] Based on this, in order to extract a valid signal from a first signal sequence, the present application can be implemented through two extraction schemes: the first is to determine only the boundary position between the second invalid signal and the valid signal (the first target signal and the second target signal) based on the signal values ​​of at least two first signals in the first signal sequence, and extract the valid signal from the first signal sequence according to the boundary position; the second is to determine the boundary position between the first invalid signal and the second invalid signal (the third target signal and the fourth target signal) from the first signal sequence, first filter out the first invalid signal, and determine the boundary position between the second invalid signal and the valid signal from the remaining signal to extract the valid signal from the remaining signal.

[0080] The first extraction scheme is embodied in Example 2, and the second extraction scheme is embodied in Example 3.

[0081] Embodiment 2

[0082] In the embodiment of the present application, a first extraction scheme is adopted to extract the valid signal in the first signal sequence.

[0083] like Figure 2 The following is a flow chart of the identity recognition method provided in the embodiment of the present application. Figure 2 ; The method comprises:

[0084] (Step) S201: Acquire a first signal sequence; the first signal sequence includes at least two first signals; each of the at least two first signals is related to a motion trajectory of the electronic device;

[0085] In the embodiment of the present application, before the electronic device acquires the first signal sequence, the method further includes:

[0086] S200: Collect an original signal sequence associated with a motion trajectory of the electronic device, wherein the original signal sequence includes at least two original signals; and take a short-time average amplitude of the original signal sequence to obtain the first signal sequence.

[0087] In a preferred embodiment, the original signal sequence collected by the electronic device is an acceleration signal sequence; specifically, in the process of the electronic device generating a motion trajectory, the electronic device collects the acceleration generated by the electronic device through a built-in linear acceleration sensor according to a preset collection frequency to obtain at least two acceleration signals, and the at least two acceleration signals constitute the acceleration signal sequence.

[0088] In a preferred embodiment, the preset acquisition frequency is 50 Hz when the electronic device is in SENSOR_DELAY_GAME mode.

[0089] For example, in the image representation, when the user holds the electronic device and makes a gesture, and the movement trajectory of the electronic device is the letter "a", the collected acceleration signal sequence is as follows: Figure 4a As shown; when the motion trajectory of the electronic device is the letter "b", the collected acceleration signal sequence is as follows Figure 4b As shown; when the motion trajectory of the electronic device is the letter "c", the collected acceleration signal sequence is as follows Figure 4c As shown; when the motion trajectory of the electronic device is the letter "d", the collected acceleration signal sequence is as follows Figure 4d shown.

[0090] Since at least two original signals in the original signal sequence are physically vectors, it is not convenient for the electronic device to directly identify the valid signal, and the electronic device needs to perform signal processing on the original signal sequence to obtain a first signal sequence that can identify valid data. The signal processing method for the original signal sequence includes a first signal processing method and a second signal processing method.

[0091] Among them, the first signal processing method is: calculating the short-time average amplitude of the original signal sequence;

[0092] Here, how to calculate the short-time average amplitude of the original signal sequence is introduced. For the convenience of explanation, it is assumed that the original signal sequence is X(m), m represents the number of original signals in the original signal sequence, and in the order of acquisition, the original signals in X(m) are x(1), x(2), ..., x(m) in sequence. The present application processes the aforementioned multiple original signals through a short-time average amplitude window function, and the formula of the short-time average amplitude window function is defined as: Where N is the window length, x(m) represents the signal value of the mth original signal, and E n Represents the nth short-time average amplitude, where n is a positive integer; wherein N is generally set to an odd number, preferably 3, to facilitate subsequent data processing.

[0093] The implementation principle of the above formula 1 is: the nth E n The value of the original signal x [m-n-(N-1)] With the original signal x n The sum of the absolute values ​​of all original signal values ​​between (including the two original signals); wherein, the signal values ​​of the original signals that do not exist (the subscript of x is less than 0, equal to 0 or greater than m) involved in the summation process are all 0; wherein, the number of original signals that exist in the summation process is equal to the window length.

[0094] Obviously, according to Formula 1, the number of short-time average amplitudes calculated is the same as the number of original signals in the original signal sequence, and the nth short-time average amplitude corresponds to the nth original signal. Thus, the electronic device obtains at least two first signals based on the at least two short-time average amplitudes calculated and the acquisition time interval, and the at least two first signals constitute a first signal sequence.

[0095] Among them, the second signal processing method is: calculating the short-time energy amplitude of the original signal sequence;

[0096] Here, we briefly introduce how to calculate the short-time energy amplitude of the original signal sequence. The principle of calculating the short-time energy amplitude is similar to the principle of calculating the short-time average amplitude mentioned above. The only difference is that the nth short-time energy amplitude is the original signal x [m-n-(N-1)] With the original signal x n The sum of the squares of all original signal values ​​between (including these two original signals).

[0097] In the embodiment of the present application, the signal processing method for the original signal sequence is preferably the first signal processing method. This is because: compared with the short-time energy amplitude, the data sensitivity of the short-time average amplitude is lower and the data stability is higher, which is conducive to obtaining the first signal sequence with higher data processing value.

[0098] In the embodiment of the present application, by converting the original signal sequence into a first signal sequence with data processing value, an accurate valid signal can be extracted based on the first signal sequence, and a more accurate second signal sequence that can be used to identify the user's identity can be obtained based on the accurate valid signal.

[0099] S202: Arrange at least two first signals in ascending order according to signal values ​​of at least two first signals in the first signal sequence to obtain a first ascending signal sequence; the first ascending signal sequence includes: at least one first signal sorted by signal value;

[0100] Considering that the signal values ​​of the invalid signals (the first invalid signal and the second invalid signal) are significantly different from the signal values ​​of the valid signals, the electronic device arranges at least two first signals in the first signal sequence in ascending order to obtain a first ascending signal sequence.

[0101] Therefore, the electronic device can distinguish most of the invalid signals from most of the valid signals according to the arrangement order by arranging at least two first signal sequences in ascending order, which is conducive to accurately extracting valid signals from the first signal sequences.

[0102] S203: for each of the first signals, determine the increasing speed of each of the first signals according to a reference signal corresponding to the first signal in the first ascending signal sequence; the reference signal is an adjacent signal of the first signal;

[0103] For ease of calculation, it is assumed that adjacent first signals in the first ascending signal sequence have the same time interval, which is the acquisition time interval; specifically, the increasing rate of the first signal of the electronic device is equal to: (the difference between the signal value of the first signal and the signal value of the reference signal) divided by the acquisition time interval; wherein the reference signal is preferably a signal that is arranged before each of the first signals and adjacent to each of the first signals.

[0104] Therefore, the embodiment of the present application can highlight the signal value difference between each first signal and the reference signal by calculating the growth rate of each first signal, which is helpful to determine the signal value that separates the invalid signal and the valid signal.

[0105] S204: determining, according to the increasing speed of each of the first signals, a first signal satisfying a target condition from the first ascending signal sequence;

[0106] Specifically, S204 can be implemented through steps A1 to A3:

[0107] A1: Determine a weight corresponding to each first signal in the first ascending signal sequence; wherein the weight is a ratio of an increase rate of each first signal to an increase rate of a reference signal corresponding to each first signal;

[0108] A2: determining at least one first signal having a weight greater than a preset threshold from the first ascending signal sequence as at least one candidate signal;

[0109] A3: Determine a first signal that meets the target condition from the at least one candidate signal.

[0110] In the above A1 to A3, the electronic device calculates the ratio of the growth rate of each first signal to the growth rate of the respective reference signal, and uses each ratio as the weight of the first signal corresponding to each signal. Based on the comparison between the weight of the first signal and the preset threshold, it can determine which first signal has a more obvious growth in signal value relative to its reference signal. Furthermore, the electronic device uses the first signal with a more obvious signal value growth as a candidate signal to obtain at least one candidate signal; among the at least one candidate signal, there is a candidate signal whose signal value can be used as the first threshold for demarcating invalid signals from valid signals.

[0111] According to practical applications, the preset threshold in the embodiment of the present application is preferably 1. When the preset threshold is 1, the electronic device is advantageously able to obtain at least one more accurate candidate signal.

[0112] Further, determining the first signal satisfying the target condition from the at least one candidate signal includes:

[0113] Selecting a candidate signal according to the order of the at least one candidate signal in the first ascending signal sequence;

[0114] Determine a first total number and a second total number of the currently selected candidate signals; the first total number is the total number of first signals that are sequentially before the currently selected candidate signal, and the second total number is the total number of first signals that are sequentially before the currently selected candidate signal and have a weight smaller than the weight of the currently selected candidate signal;

[0115] Determining whether a quotient of a second total number of currently selected candidate signals and a first total number is less than or equal to a first value;

[0116] If so, the currently selected candidate signal is determined to be a signal that meets the target condition; if not, return to selecting the candidate signal and repeat the process until the quotient of the second total number of the currently selected candidate signals and the first total number is less than or equal to the first value, and the currently selected candidate signal is determined to be a signal that meets the target condition.

[0117] Specifically, A3 can be achieved through steps A31 to A32:

[0118] A31: determining, according to the order of the at least one candidate signal in the first ascending signal sequence, a first total number and a second total number corresponding to the first candidate signal that is in the first order; the first total number is the total number of first signals that are in the order before the first candidate signal, and the second total number is the total number of first signals that are in the order before the first candidate signal and have a weight smaller than the weight of the first candidate signal;

[0119] A32: Determine whether the quotient of the second total and the first total is less than or equal to the first value. If the judgment is yes, determine that the first candidate signal is a signal that meets the target condition; otherwise, perform corresponding processing on the candidate signal that is next in sequence to the first candidate signal (i.e., determine the first total and the second total of the next candidate signal, and determine whether the quotient of the second total and the first total is less than or equal to the first value) until a signal that meets the target condition is determined.

[0120] That is, the signal that meets the target condition can be: a first candidate signal whose quotient of the second total and the first total is less than or equal to the first value; wherein the first total is the total number of first signals that are sequentially before the corresponding first candidate signal, and the second total is the total number of first signals that are sequentially before the first candidate signal and whose weight is smaller than the weight of the first candidate signal.

[0121] The purpose of A31-A32 is to determine whether each candidate signal is a valid signal or an invalid signal in turn according to the order of the at least one candidate signal in the first ascending signal sequence.

[0122] According to the above scheme, the electronic device arranges at least two first signals in the first signal series in ascending order to obtain a first ascending signal sequence, and can distinguish the vast majority of invalid signals from the vast majority of valid signals according to the order of arrangement; that is, based on the actual phenomenon that the signal value of the invalid signal is significantly smaller than the signal value of the valid signal, the electronic device sorts at least two first signals according to size and divides them into a first area with a smaller signal value and a second area with a larger signal value; wherein, the vast majority of the first signals in the first area are invalid signals, and there are also very few valid signals with smaller signal values; the vast majority of the first signals in the second area are valid signals, and there are also very few invalid signals with larger signal values. In the embodiment of the present application, the very few valid signals with smaller signal values ​​in the first area are regarded as individual abnormal signals.

[0123] Considering the existence of individual abnormal signals, the electronic device needs to determine in sequence according to the order of at least one candidate signal in the first ascending sequence whether the signal value of the candidate signal can be used as the signal value that demarcates an invalid signal from a valid signal.

[0124] Specifically, the electronic device determines, in order of the candidate signals in the first ascending sequence, whether there is a first signal with a certain proportion of weight greater than that of the candidate signal before the candidate signal. If there is, it means that there is an individual abnormal signal before the candidate signal, and the signal value of the candidate signal can be used as the first threshold for dividing invalid signals from valid signals; if not, it means that there is no individual abnormal signal before the candidate signal, and the signal value of the candidate signal cannot be used as the first threshold for dividing invalid signals from valid signals, and it is necessary to continue to judge the candidate signal that is next in order to the candidate signal.

[0125] Obviously, there will be no individual abnormal signal before the candidate signal with the first order. Therefore, the electronic device can start the above-mentioned judgment process from the first candidate signal with the second order.

[0126] S205: Determine a first target signal and a second target signal from the first signal sequence according to the first signal that meets the target condition;

[0127] Through the above scheme, the embodiment of the present application can adaptively determine the signal value of the first signal that meets the target condition as the first threshold based on the signal values ​​of at least two first signals in the first signal sequence, and determine the first target signal and the second target signal from the first signal sequence according to the first threshold, so that the extraction of effective signals is more flexible and accurate.

[0128] The above S203 to S205 are solutions for determining the first signal that meets the target condition directly based on the signal values ​​of multiple first signals in the first ascending signal sequence. In addition, in order to prevent the weights of individual first signals in the first ascending signal sequence from being too sensitive, which is not conducive to accurately determining the first threshold, in an optional embodiment (grouping), the electronic device does not execute the solution for determining the first threshold in S203 to S205, but executes C1 to C8 to determine the first threshold. The following are the execution steps of C1 to C8:

[0129] C1. Based on the order of the multiple first signals in the first ascending signal sequence, and according to the grouping rule of nine first signals in each group, the multiple first signals in the first ascending signal sequence are grouped in sequence to obtain multiple first groups in a certain order;

[0130] C2. For the nine first signals in each group, according to the order of the nine first signals, the nine first signals are divided into a front point part, a middle point part and a rear point part, with three first signals as one part; wherein the front point part includes the three first signals in the front sequence, the middle point part includes the three first signals in the middle sequence, and the rear point part includes the three first signals in the rear sequence;

[0131] C3, calculating the average value P1 of the first signal of the front point part, the average value P2 of the first signal of the middle point part and the average value P3 of the first signal of the rear point part in each group;

[0132] C4. Calculate the group weight corresponding to each group; wherein, for each group, the group weight = (P2 squared) divided by (P1 multiplied by P3);

[0133] C5. Determine at least one first group whose group weight is greater than a preset threshold as at least one candidate group; wherein the preset threshold may be 1;

[0134] C6. Determine, according to the order of the at least one candidate group in the plurality of groups, a third total number and a fourth total number corresponding to the first candidate group that is in the first order; the third total number is the total number of first groups that are in the order before the first candidate group, and the fourth total number is the total number of first signals that are in the order before the first candidate signal and whose group weight is smaller than the group weight of the first candidate signal;

[0135] C7, determining whether the quotient of the fourth total and the third total is less than or equal to the first value, and if so, determining that the first candidate group is the group that meets the target condition; otherwise, performing corresponding processing on the candidate group that is next in order to the first candidate group until a group that meets the target condition is determined; wherein the first value may be 0.85;

[0136] C8. Determine a first target signal and a second target signal from the first signal sequence according to P2 (first threshold) of the first group that meets the target condition.

[0137] In the above C3-C4, the group weight can be calculated by formula 2: in, a sum of first signals representing the preceding part of the first group; A sum of first signals representing a midpoint portion of the first group; The sum of the first signals of the last point part of the first group; k represents the group weight;

[0138] In the above C1 to C8, the present application groups multiple first signals in the first ascending signal sequence to calculate the group weight of each group using the signal values ​​of the nine first signals in each group, which can reduce the sensitivity of data processing, improve the stability of data processing, and facilitate accurate determination of the first threshold, and further facilitate determination of the first target signal and the second target signal from at least two first signals in the first signal sequence according to the first threshold.

[0139] S206: Extract at least one valid signal from the first signal sequence according to the first target signal and the second target signal.

[0140] In the embodiment of the present application, according to the adaptively determined first threshold, the electronic device can determine the first target signal and the second target signal from the first signal sequence; according to the order of at least one first signal in the first signal series, the first target signal is the first signal whose signal value is equal to the first threshold, and the second target signal is the first signal whose last signal value is equal to the first threshold;

[0141] The electronic device extracts the first signal between the first target signal and the second target signal to obtain at least one valid signal in the first signal sequence.

[0142] In an embodiment of the present application, the electronic device obtains a first signal sequence with data processing value by performing signal processing on the collected original signal sequence; by considering the obvious difference in signal value between invalid signals and valid signals, at least two first signals in the first signal sequence are arranged in ascending order according to the size of the signal value to obtain a first ascending signal sequence, and most of the invalid signals and most of the valid data in the at least two first signals can be distinguished by region; by comparing the increasing rates of two adjacent first signals in the first ascending signal sequence, at least one first signal with an obvious signal value increase can be determined as a candidate signal, so as to determine a first threshold for demarcating invalid signals and valid signals from the signal value of at least one candidate signal; by considering that there are individual difference points in the first ascending signal sequence and the region with lower signal values, it is accurately determined which candidate signal's signal value can be used as the first threshold; by selecting the first target signal and the second target signal from the first signal sequence according to the first threshold, a valid signal can be extracted from the first signal sequence based on the first target signal and the second target signal. Therefore, the embodiment of the present application can adaptively detect invalid signals through the aforementioned technical solution, adaptively determine the first threshold for distinguishing invalid signals from valid signals, and then accurately and efficiently extract at least one valid signal from the first signal sequence based on the first threshold, obtain the second signal sequence based on the at least one valid signal, and use the second signal sequence to identify the user's identity, thereby improving the accuracy and efficiency of identity recognition.

[0143] Embodiment 3

[0144] In the embodiment of the present application, the second extraction scheme is adopted to extract the valid signal in the first signal sequence.

[0145] like Figure 3 The following is a flow chart of the identity recognition method provided in the embodiment of the present application. Figure 3 ; The method comprises:

[0146] (Step) S301: Acquire a first signal sequence; the first signal sequence includes at least two first signals; each of the at least two first signals is related to a motion trajectory of the electronic device;

[0147] In the embodiment of the present application, before the electronic device acquires the first signal sequence, the method further includes:

[0148] S300: Collect an original signal sequence associated with the motion trajectory of the electronic device, wherein the original signal sequence includes at least two original signals; and take a short-time average amplitude of the original signal sequence to obtain the first signal sequence.

[0149] For the detailed description of S300, please refer to the detailed description of S200 mentioned above, which will not be elaborated here.

[0150] For other detailed descriptions of S301, please refer to the aforementioned detailed descriptions of S201, which will not be elaborated here.

[0151] From the image's perspective:

[0152] For the original signal sequence involved in the embodiments of the present application, for example, when the gesture action is "a", the original signal sequence is as follows: Figure 4a As shown; when the gesture action is "b", the original signal sequence is as follows Figure 4b As shown; when the gesture action is "c", the original signal sequence is as follows Figure 4c As shown; when the gesture action is "d", the original signal sequence is as follows Figure 4d shown.

[0153] For the first signal sequence involved in the embodiment of the present application, for example, when the gesture action is "a", the first signal sequence is as follows: Figure 5a As shown; when the gesture action is "b", the first signal sequence is as follows Figure 5b As shown; in the case where the gesture action is "c", the first signal sequence is as follows Figure 5c As shown; when the gesture action is "d", the first signal sequence is as follows Figure 5d shown.

[0154] S302: extracting at least two first signals that meet the threshold requirement from the first signal sequence according to a preset second threshold, to obtain a third signal sequence;

[0155] S303: Arrange at least two first signals meeting the threshold requirement in ascending order according to signal values ​​of at least two first signals meeting the threshold requirement in the third signal sequence to obtain a first ascending signal sequence;

[0156] The embodiment of the present application takes into account that: the signal value of the first invalid signal is close to 0, which is significantly different from the signal value of the second invalid signal, and the signal value of the second invalid signal is significantly different from the signal value of the valid signal.

[0157] Based on this, in the embodiment of the present application, the electronic device uses a preset second threshold as a demarcation value for distinguishing the first invalid signal from the second invalid signal, and determines the third target signal and the fourth target signal from the first signal sequence according to the preset second threshold. Wherein, according to the order of at least two first signals in the first signal sequence, the third target signal is the first signal whose first signal value is equal to the second threshold, and the fourth target signal is the first signal whose last signal value is equal to the second threshold.

[0158] Next, the electronic device extracts the first signal between the third target signal and the fourth target signal (including the third target signal and the fourth target signal) as the first signal that meets the threshold requirement, obtains a third signal sequence, and extracts a valid signal from at least two first signals of the third signal sequence; wherein, at least two first signals of the third signal sequence include a second invalid signal and a valid signal.

[0159] From the perspective of image expression, for example, when the gesture action is "a", the third signal sequence is as follows: Figure 6a As shown; when the gesture action is "b", the third signal sequence is as follows Figure 6b As shown; in the case where the gesture action is "c", the third signal sequence is as follows Figure 6c As shown; when the gesture action is "d", the third signal sequence is as follows Figure 6d shown.

[0160] It can be understood that the purpose of the above scheme is to first filter out the first invalid signal in the first signal sequence to obtain the third signal sequence, and then extract the valid signal from the third signal sequence. This scheme of first filtering out the first invalid signal and then extracting the valid signal from at least two first signals from which the first invalid signal is filtered out is equivalent to a scheme of filtering out the first invalid signal and the second invalid signal in the first signal sequence one by one, which can improve the extraction accuracy of the valid signal and avoid the error in extracting the valid signal caused by filtering out the first invalid signal and the second invalid signal at the same time.

[0161] S304: for each of the first signals, determine the increasing speed of each of the first signals according to a reference signal corresponding to the first signal in the first ascending signal sequence, wherein the reference signal represents an adjacent signal of the first signal;

[0162] For the detailed description of S304, please refer to the detailed description of S203 mentioned above, which will not be elaborated here.

[0163] For the first ascending signal sequence involved in the embodiment of the present application, for example, when the gesture action is "a", the first ascending signal sequence is as follows: Figure 7a As shown; when the gesture action is "b", the first ascending signal sequence is as follows Figure 7b As shown; in the case where the gesture action is "c", the first ascending signal sequence is as follows Figure 7c As shown; when the gesture action is "d", the first ascending signal sequence is as follows Figure 7d shown.

[0164] S305: determining a first signal that meets a target condition from the first ascending signal sequence according to the increasing speed of each of the first signals;

[0165] Specifically, S305 can be implemented through steps A1 to A3:

[0166] A1: Determine a weight corresponding to each first signal in the first ascending signal sequence; wherein the weight is a ratio of an increase rate of each first signal to an increase rate of a reference signal corresponding to each first signal;

[0167] A2: determining at least one first signal having a weight greater than a preset threshold from the first ascending signal sequence as at least one candidate signal;

[0168] A3: Determine a first signal that meets the target condition from the at least one candidate signal.

[0169] Further, A3 can be implemented through steps A31 to A32:

[0170] A31: determining, according to the order of the at least one candidate signal in the first ascending signal sequence, a first total number and a second total number corresponding to the first candidate signal that is second in order; the first total number is the total number of first signals that are before the first candidate signal, and the second total number is the total number of first signals that are before the first candidate signal and have a weight smaller than the weight of the first candidate signal;

[0171] A32: Determine whether the quotient of the second total and the first total is less than or equal to a first value. If it is, determine that the first candidate signal is a signal that meets the target condition; otherwise, perform corresponding processing on the candidate signal that is next in sequence to the first candidate signal until a signal that meets the target condition is determined.

[0172] For other detailed descriptions of S305, please refer to the detailed descriptions of S204 mentioned above, which will not be elaborated here.

[0173] S306: Determine at least two target signals from the first signal sequence according to the signal value of the first signal that meets the target condition; the at least two target signals include: a first target signal and a second target signal;

[0174] For the detailed description of S306, please refer to the detailed description of S205 mentioned above, which will not be elaborated here.

[0175] The above S304 to S306 are solutions for determining the first signal that meets the target condition directly based on the signal values ​​of multiple first signals in the first ascending signal sequence. In addition, in order to prevent the weights of individual first signals in the first ascending signal sequence from being too sensitive and not conducive to accurately determining the first threshold, in an optional embodiment (grouping), the electronic device does not execute the solution for determining the first threshold in S304 to S306, but executes C1 to C8 to determine the first threshold.

[0176] S307: Extracting at least one valid signal from the first signal sequence according to the first target signal and the second target signal;

[0177] For the detailed description of S307, please refer to the detailed description of S206 mentioned above, which will not be elaborated here.

[0178] In an embodiment of the present application, the electronic device obtains a first signal sequence with data processing value by performing signal processing on the collected original signal sequence; by considering the obvious difference in signal value between the first invalid signal and the second invalid signal, and the obvious difference in signal value between the valid signal, at least two first signals in the first signal sequence are arranged in ascending order according to the size of the signal value to obtain a first ascending signal sequence, and most of the invalid signals and most of the valid data in the at least two first signals can be distinguished by region; by comparing the growth rates of two adjacent first signals in the first ascending signal sequence, at least one first signal with an obvious signal value growth can be determined as a candidate signal, so as to determine a first threshold for demarcating invalid signals and valid signals from the signal value of at least one candidate signal; by considering the presence of individual difference points in the region with lower signal values ​​in the first ascending signal sequence, it is accurately determined which candidate signal's signal value can be used as the first threshold; by selecting the first target signal and the second target signal from the first signal sequence according to the first threshold, a valid signal can be extracted from the first signal sequence based on the first target signal and the second target signal. Therefore, the embodiment of the present application can adaptively determine the first threshold through the aforementioned technical solution, and then accurately and efficiently extract at least one valid signal from the first signal sequence based on the first threshold, and obtain a second signal sequence for identifying the user's identity based on the at least one valid signal, thereby improving the accuracy and efficiency of identity recognition.

[0179] Compared with the second embodiment, in the third embodiment, since the first invalid signal in the first signal sequence is first filtered out, and at least one valid signal is extracted from the multiple first signals from which the first invalid signal is filtered out, the error caused by the first invalid signal to the process of extracting the valid signal can be avoided, and the computational overhead of subsequent data processing can be reduced. In practical applications, the technical solution in the third embodiment is preferably selected to obtain the second signal sequence for identifying the user. In addition, in application scenarios where the signal value of the first invalid signal is closer to the signal value of the second invalid signal, for example, when the user suffers from hand tremors, the technical solution of the second embodiment can improve the efficiency of data processing.

[0180] Embodiment 4

[0181] Based on the description of the foregoing technical solution, it can be known that the difference between Example 3 and Example 2 lies in that: before arranging at least two first signals in ascending order according to the signal values ​​of at least two first signals in the first signal sequence to obtain a first ascending signal sequence, at least two first signals that meet the threshold requirement are extracted from the first signal sequence according to a preset second threshold to obtain a third signal sequence; correspondingly, the first ascending signal sequence in Example 3 is a signal sequence obtained by arranging multiple first signals in the third signal sequence in ascending order.

[0182] That is to say, the processes performed in other aspects of Example 2 and Example 3 are the same. Therefore, the embodiment of this application elaborates on the identity recognition method proposed in this application, and by elaborating on the technical solution of Example 3, the specific implementation process of Example 2 can also be reflected, that is, the specific implementation process of the identity recognition method in this application can be explained.

[0183] Based on this, the embodiments of the present application are combined Fig.10 , the technical solution in Example 3 is described in detail. Fig.10 As shown, it is a flowchart diagram 4 of the identity recognition method provided in the embodiment of the present application, and the method can be divided into four parts:

[0184] Part 1: When a user holds an electronic device and makes a gesture, the electronic device uses a built-in linear acceleration sensor to collect acceleration signals generated when the electronic device generates a certain motion trajectory according to the collection frequency (50Hz) in the SENSOR_DELAY_GAME mode, and obtains an acceleration signal sequence based on the collected multiple acceleration signals;

[0185] Taking the X-axis as the time axis, when the motion trajectory generated by the electronic device is the letter a, the collected acceleration signal sequence is as follows: Figure 4a As shown; when the motion trajectory of the electronic device is the letter "b", the collected acceleration signal sequence is as follows Figure 4b As shown; when the motion trajectory of the electronic device is the letter "c", the collected acceleration signal sequence is as follows Figure 4c As shown; when the motion trajectory of the electronic device is the letter "d", the collected acceleration signal sequence is as follows Figure 4d shown.

[0186] For specific electronic equipment execution process, please refer to Fig.10 S1000~S1001 in:

[0187] S1000, start (sensing a user holding an electronic device and performing a gesture);

[0188] S1001, collecting acceleration signal sequences at a collection frequency of 50 Hz through a built-in linear acceleration sensor;

[0189] Part 2: Calculate the short-time average amplitude of the acceleration signal sequence;

[0190] The electronic device uses a short-time average amplitude window function to select a rectangular window to process the acceleration signal sequence; wherein the formula for selecting a rectangular window by the short-time average amplitude window function is defined as: Where N is the window length, x(m) represents the signal value of the mth original signal, and E n represents the nth short-time average amplitude, where n is a positive integer. For the specific principle of selecting the rectangular window as the short-time average amplitude window function, please refer to the above description and will not be elaborated here.

[0191] For specific electronic equipment execution process, please refer to Fig.10 S1002 in:

[0192] S1002, calculating the short-time average amplitude of the acceleration signal sequence to obtain a first signal sequence;

[0193] Taking the X axis as the time axis, when the motion trajectory generated by the electronic device is letter a, the first signal sequence is as follows: Figure 5a As shown; when the motion trajectory of the electronic device is the letter "b", the first signal sequence is as follows Figure 5b As shown; when the motion trajectory of the electronic device is the letter "c", the first signal sequence is as follows Figure 5c As shown; when the motion trajectory of the electronic device is the letter "d", the first signal sequence is as follows Figure 5d shown.

[0194] Part three, filtering out the static segment jitter signal (first invalid signal) in the first signal sequence;

[0195] In the embodiment of the present application, the first signal sequence includes a part related to the gesture action (gesture segment signal) and a part unrelated to the gesture action (non-gesture segment signal); wherein the non-gesture segment signal includes a normal jitter signal close to zero and a transition segment non-gesture signal with a larger fluctuation than the normal jitter signal; the former is mainly introduced because the user's holding state does not return to a stable state before and after the gesture action starts, and the latter is mainly introduced due to the inevitable preparatory action made by the user before the gesture action starts.

[0196] Obviously, in the first signal sequence, the non-gesture segment part is introduced before the start and after the end of the gesture segment part; among them, the non-gesture segment part before the start of the gesture segment part first introduces the normal jitter signal, and the non-gesture segment part after the end of the gesture segment first introduces the transition segment non-gesture signal.

[0197] Considering that the normal jitter signal is close to zero value and easy to filter out, it can be filtered out by setting a simple low threshold value T1 (second threshold value). According to the experimental results, the normal jitter signal value range is between 0 and 0.5. T1 is set to 0.5. According to the time axis of the first signal sequence, the first signal with a signal value equal to 0.5 in the first signal sequence is determined to be position M1, and the last signal with a signal value equal to 0.5 is determined to be position M2. The non-gesture signal and the first signal in the transition section between M1 and M2 in the first signal sequence are extracted to obtain the third signal sequence.

[0198] For specific electronic equipment execution process, please refer to Fig.10 S1003 in:

[0199] S1003. Obtain a preset second threshold, traverse the first signal sequence along the time axis of the first signal sequence, determine the first signal in the first signal sequence that is equal to the second threshold, and the last signal that is equal to the second threshold, extract the signal between the two signals in the first signal sequence, and obtain a third signal sequence.

[0200] Taking the X axis as the time axis, when the motion trajectory generated by the electronic device is letter a, the third signal sequence is as follows: Figure 6a As shown; when the motion trajectory of the electronic device is the letter "b", the third signal sequence is as follows Figure 6b As shown; when the motion trajectory of the electronic device is the letter "c", the third signal sequence is as follows Figure 6c As shown; when the motion trajectory of the electronic device is the letter "d", the third signal sequence is as follows Figure 6d shown.

[0201] Part 4: filtering out the transition segment non-gesture signal (second invalid signal) in the third signal sequence;

[0202] Since the transition section non-gesture signals and gesture section signals are distributed in different signal value intervals, the electronic device arranges the signals in the third signal sequence in ascending order to obtain a first ascending signal sequence, and can distinguish most of the transition section non-gesture signals and most of the gesture section signals in the first ascending signal sequence, which are distributed in the front low signal value area and the rear high signal value area, respectively.

[0203] Taking the X axis as the time axis, when the motion trajectory generated by the electronic device is letter a, the first ascending signal sequence is as follows: Figure 7a As shown; when the motion trajectory of the electronic device is the letter "b", the first ascending signal sequence is as follows Figure 7b As shown; when the motion trajectory of the electronic device is the letter "c", the first ascending signal sequence is as follows Figure 7c As shown; when the motion trajectory of the electronic device is the letter "d", the first ascending signal sequence is as follows Figure 7d shown.

[0204] For specific electronic equipment execution process, please refer to Fig.10 S1004 in:

[0205] S1004: Arrange the multiple first signals in the first signal sequence in ascending order according to signal values ​​to obtain a first ascending signal sequence.

[0206] Obviously, in the case of different motion trajectories of the electronic device, the boundary between the low signal value area and the high signal value area can be intuitively seen in the diagram of the first ascending signal sequence, and the signal value of the signal sequence changes significantly. Therefore, the embodiment of the present application analyzes the signal value difference of multiple first signals in the first ascending signal sequence to detect the critical inflection point (demarcation signal value) between the transition section non-gesture signal and the gesture segment signal, and then determines which first signal in the third signal sequence the gesture segment signal starts and ends based on the demarcation value.

[0207] In the scheme for detecting critical inflection points, in order to prevent individual difference signals (signal values ​​that differ greatly from those of adjacent signals) from being too sensitive and affecting the detection results, the specific electronic device execution process is S1005:

[0208] S1005, analyzing the first ascending signal sequence to determine a first signal in the first ascending signal sequence that meets a target condition;

[0209] S1006, determining a first threshold according to the first signal that meets the target condition;

[0210] The specific implementation of S1005~S1006 is as follows Fig.11 The execution flow shown is as follows Figure 2 , including S1100~S1111:

[0211] S1100, start;

[0212] S1101, based on the order of the plurality of first signals in the first ascending signal sequence, and in accordance with a grouping rule of nine first signals per group, the plurality of first signals in the first ascending signal sequence are grouped in sequence to obtain a plurality of first groups having a certain order;

[0213] S1102. For the nine first signals in each group, according to the order of the nine first signals, divide the nine first signals into a front point part, a middle point part and a rear point part, with three first signals as one part; wherein the front point part includes the three first signals in the front sequence, the middle point part includes the three first signals in the middle sequence, and the rear point part includes the three first signals in the rear sequence;

[0214] S1103, calculating the average value P1 of the first signal of the front point part, the average value P2 of the first signal of the middle point part, and the average value P3 of the first signal of the rear point part in each group;

[0215] S1104, calculating the group weight corresponding to each group; wherein, for each group, the group weight = (P2 squared) divided by (P1 multiplied by P3);

[0216] S1105, determining at least one first group whose group weight is greater than 1 as at least one candidate group; wherein the preset threshold may be 1;

[0217] S1106. Determine, according to the order of the at least one candidate group in the multiple groups, a candidate group with the first order as a first candidate group;

[0218] S1107, determining a third total number and a fourth total number corresponding to the first candidate group; the third total number is the total number of first groups that are sequentially before the first candidate group, and the fourth total number is the total number of first signals that are sequentially before the first candidate signal and whose group weight is smaller than the group weight of the first candidate signal;

[0219] S1108, determine whether the quotient of the fourth total and the third total is less than or equal to 0.85; if so, go to S1109; otherwise, go to S1110;

[0220] S1109, determining that the first candidate group is a group that meets the target condition;

[0221] S1110, taking the candidate group that is next in order to the first candidate group as the first candidate group;

[0222] S1111. Determine P2 of the first group that meets the target condition as a first threshold.

[0223] Among them, P2 of the first group that meets the target condition is the dividing value (first threshold) between the non-gesture signal and the gesture segment signal in the transition segment, and the first signal ranked second in the midpoint part of the first group that meets the target condition is the inflection point in the first ascending signal sequence.

[0224] The group weight can be calculated by formula 2: in, a sum of first signals representing the preceding part of the first group; A sum of first signals representing a midpoint portion of the first group; The sum of the first signals of the last point part of the first group; k represents the group weight;

[0225] Taking the X-axis as the time axis, when the motion trajectory generated by the electronic device is letter a, the weight sequence is as follows Figure 8a As shown; when the motion trajectory of the electronic device is the letter "b", the weight sequence is as follows Figure 8b As shown; when the motion trajectory of the electronic device is the letter "c", the weight sequence is as follows Figure 8c As shown; when the motion trajectory of the electronic device is the letter "d", the weight sequence is as follows Figure 8d shown.

[0226] Obviously, in the case of different motion trajectories of electronic devices, the boundary between the low signal value area and the high signal value area can be intuitively seen in the diagram of the weight sequence. The weight changes significantly, and the probability that the weight on the right side of the critical point is greater than the weight on the left side is high, while the difference between the weights on the left side of the critical point is not obvious.

[0227] According to S1100~S1111 Figure 6a , Figure 6b , Figure 6c and Figure 6d The experimental results of each gesture obtained by processing the first ascending signal sequence in are shown in Table 1:

[0228] Table 1 First threshold calculation table

[0229]

[0230]

[0231] Obviously, none of the candidate groups listed in Table 1 meets the target condition, and it is necessary to perform corresponding processing on the candidate groups next to each candidate group shown in the table until a group meeting the target condition is determined.

[0232] Next, the electronic device executes S1007:

[0233] S1007. According to the first threshold, traverse the third signal sequence, determine the first first signal equal to the first threshold and the last first signal equal to the first threshold from the third signal sequence, extract the signal between the two first signals in the first signal sequence, and obtain a second signal sequence;

[0234] S1008: Use the second signal sequence for user identification.

[0235] In the embodiment of the present application, a detailed description is given of how the electronic device collects the original signal sequence, how the original signal sequence is converted into the first signal sequence, how at least one valid signal is extracted from the first signal sequence, and how the second signal sequence is obtained based on at least one valid data. By designing the aforementioned process, the embodiment of the present application improves the flexibility, accuracy and efficiency of extracting valid data from many aspects, so as to improve the flexibility, accuracy and efficiency of identifying the user's identity using the second signal sequence.

[0236] Embodiment 5

[0237] like Fig.12 FIG. 1 is a schematic diagram of the structure of the identity recognition device provided in the embodiment of the present application. Figure 1 The identity recognition device is applied to an electronic device, wherein the device comprises:

[0238] An acquisition unit 121 is configured to acquire a first signal sequence; the first signal sequence includes at least two first signals; each of the at least two first signals is related to a motion trajectory of the electronic device;

[0239] An analyzing unit 122, configured to analyze the first signal sequence, and determine at least two target signals of the first signal sequence according to the analysis result;

[0240] The identification unit 123 is used to extract at least one valid signal from the first signal sequence according to the at least two target signals; obtain a second signal sequence based on the at least one valid signal; and the second signal sequence is used for identity identification.

[0241] In the above solution, the analysis unit 122 is further used for:

[0242] Arrange at least two first signals in ascending order according to the signal values ​​of at least two first signals in the first signal sequence to obtain a first ascending signal sequence; the first ascending signal sequence includes: at least one first signal sorted by signal value;

[0243] For each of the first signals, determining the increasing speed of each of the first signals according to a reference signal corresponding to the first signal in the first ascending signal sequence; the reference signal is an adjacent signal of the first signal;

[0244] Determining, according to the increasing speed of each of the first signals, a first signal satisfying a target condition from the first ascending signal sequence;

[0245] At least two target signals are determined from the first signal sequence according to the signal value of the first signal that meets the target condition.

[0246] In the above solution, the analysis unit 122 is further used for:

[0247] Determine a weight of each first signal in the first ascending signal sequence; wherein the weight is a ratio of an increase rate of each first signal to an increase rate of a reference signal corresponding to each first signal;

[0248] Determine at least one first signal having a weight greater than a preset threshold from the first ascending signal sequence as at least one candidate signal;

[0249] A first signal satisfying a target condition is determined from the at least one candidate signal.

[0250] In the above solution, the analysis unit 122 is further used for:

[0251] Selecting a candidate signal according to the order of the at least one candidate signal in the first ascending signal sequence;

[0252] Determine a first total number and a second total number of the currently selected candidate signals; the first total number is the total number of first signals that are sequentially before the currently selected candidate signal, and the second total number is the total number of first signals that are sequentially before the currently selected candidate signal and have a weight smaller than the weight of the currently selected candidate signal;

[0253] Determining whether a quotient of a second total number of currently selected candidate signals and a first total number is less than or equal to a first value;

[0254] If so, the currently selected candidate signal is determined to be a signal that meets the target condition; if not, return to selecting the candidate signal and repeat the process until the quotient of the second total number of the currently selected candidate signals and the first total number is less than or equal to the first value, and the currently selected candidate signal is determined to be a signal that meets the target condition.

[0255] In the above solution, the analysis unit 122 is further used for:

[0256] According to a preset second threshold, extract at least two first signals that meet the threshold requirement from the first signal sequence to obtain a third signal sequence;

[0257] Correspondingly, the method of arranging at least two first signals in ascending order according to the signal values ​​of at least two first signals in the first signal sequence to obtain a first ascending signal sequence includes:

[0258] According to the signal values ​​of at least two first signals that meet the threshold requirement in the third signal sequence, the at least two first signals that meet the threshold requirement are arranged in ascending order to obtain a first ascending signal sequence.

[0259] In the above scheme, the at least two target signals include: a first target signal and a second target signal; the first target signal and the second target signal are the demarcation points between invalid signals and valid signals;

[0260] The identification unit 123 is further used for:

[0261] At least one valid signal is extracted from the first signal sequence according to the first target signal and the second target signal.

[0262] In the embodiment of the present application, the aforementioned identity recognition method is applied to an identity recognition device, and the identity recognition device is applied to an electronic device, so that the electronic device can effectively and efficiently recognize the identity of the user.

[0263] Embodiment 6

[0264] like Fig.13 FIG. 1 is a schematic diagram of the structure of the identity recognition device provided in the embodiment of the present application. Figure 2 ; Wherein, the device includes: a processor 131 and a memory 132 for storing a computer program that can be run on the processor, wherein the processor is used to execute the steps of the aforementioned identity recognition method when running the computer program.

[0265] It can be understood that the memory 132 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disk, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), and direct RAM bus random access memory (DRRAM, Direct Rambus Random Access Memory).The memory 132 described in the embodiments of the present application is intended to include, but is not limited to, these and any other suitable types of memory.

[0266] The method disclosed in the above embodiment of the present application can be applied to the processor 131, or implemented by the processor 131. The processor 131 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor 131 or an instruction in the form of software. The above processor 131 may be a general-purpose processor, a DSP, or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 131 can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present invention. A general-purpose processor may be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiment of the present application, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in the memory 132, and the processor 131 reads the information in the memory 132 and completes the steps of the above method in combination with its hardware.

[0267] Embodiment 7

[0268] An embodiment of the present application also provides a computer-readable storage medium, which is applied to an electronic device and stores a computer program thereon. When the computer program is executed by a processor, the steps of the aforementioned identity recognition method are implemented.

Claims

1. An identity recognition method, characterized in that: Applied to electronic equipment, the method comprises: Acquire a first signal sequence; the first signal sequence includes at least two first signals; each of the at least two first signals is related to the motion trajectory of the electronic device; analyzing the first signal sequence, and determining at least two target signals of the first signal sequence according to the analysis result; According to the at least two target signals, at least one valid signal is extracted from the first signal sequence; based on the at least one valid signal, a second signal sequence is obtained; the second signal sequence is used for identity recognition; The at least two target signals include: a first target signal and a second target signal; the first target signal and the second target signal are demarcation points between invalid signals and valid signals; The step of extracting at least one valid signal from the first signal sequence according to the at least two target signals comprises: At least one valid signal is extracted from the first signal sequence according to the first target signal and the second target signal.

2. The method according to claim 1, characterized in that The analyzing the first signal sequence and determining at least two target signals of the first signal sequence according to the analysis result includes: Arrange at least two first signals in ascending order according to the signal values ​​of at least two first signals in the first signal sequence to obtain a first ascending signal sequence; the first ascending signal sequence includes: at least one first signal sorted by signal value; For each of the first signals, determining the increasing speed of each of the first signals according to a reference signal corresponding to the first signal in the first ascending signal sequence; the reference signal is an adjacent signal of the first signal; Determining, according to the increasing speed of each of the first signals, a first signal satisfying a target condition from the first ascending signal sequence; At least two target signals are determined from the first signal sequence according to the signal value of the first signal that meets the target condition.

3. The method according to claim 2, characterized in that The determining a first signal satisfying a target condition from the first ascending signal sequence comprises: Determine a weight of each first signal in the first ascending signal sequence; wherein the weight is a ratio of an increase rate of each first signal to an increase rate of a reference signal corresponding to each first signal; Determine at least one first signal having a weight greater than a preset threshold from the first ascending signal sequence as at least one candidate signal; A first signal satisfying a target condition is determined from the at least one candidate signal.

4. The method according to claim 3, characterized in that The determining a first signal satisfying a target condition from the at least one candidate signal comprises: Selecting a candidate signal according to the order of the at least one candidate signal in the first ascending signal sequence; Determine a first total number and a second total number of the currently selected candidate signals; the first total number is the total number of first signals that are sequentially before the currently selected candidate signal, and the second total number is the total number of first signals that are sequentially before the currently selected candidate signal and have a weight smaller than the weight of the currently selected candidate signal; Determining whether a quotient of a second total number of currently selected candidate signals and a first total number is less than or equal to a first value; If so, the currently selected candidate signal is determined to be a signal that meets the target condition; if not, return to selecting the candidate signal and repeat the process until the quotient of the second total number of the currently selected candidate signals and the first total number is less than or equal to the first value, and the currently selected candidate signal is determined to be a signal that meets the target condition.

5. The method according to claim 2, characterized in that: Before arranging at least two first signals in ascending order according to signal values ​​of at least two first signals in the first signal sequence to obtain a first ascending signal sequence, the method further includes: According to a preset second threshold, extract at least two first signals that meet the threshold requirement from the first signal sequence to obtain a third signal sequence; Correspondingly, the method of arranging at least two first signals in ascending order according to the signal values ​​of at least two first signals in the first signal sequence to obtain a first ascending signal sequence includes: According to the signal values ​​of at least two first signals that meet the threshold requirement in the third signal sequence, the at least two first signals that meet the threshold requirement are arranged in ascending order to obtain a first ascending signal sequence.

6. The method according to claim 1, characterized in that Before acquiring the first signal sequence, the method further includes: Collecting an original signal sequence associated with the motion trajectory of the electronic device, wherein the original signal sequence includes at least two original signals; The short-time average amplitude of the original signal sequence is taken to obtain the first signal sequence.

7. An identity recognition device, applied to electronic equipment, characterized in that: The device comprises: An acquisition unit, configured to acquire a first signal sequence; the first signal sequence includes at least two first signals; each of the at least two first signals is related to a motion trajectory of the electronic device; an analyzing unit, configured to analyze the first signal sequence, and determine at least two target signals of the first signal sequence according to the analysis result; an identification unit, configured to extract at least one valid signal from the first signal sequence according to the at least two target signals; obtain a second signal sequence based on the at least one valid signal; the second signal sequence is used for identity identification; the at least two target signals include: a first target signal and a second target signal; the first target signal and the second target signal are the demarcation points between invalid signals and valid signals; The identification unit is specifically used for: At least one valid signal is extracted from the first signal sequence according to the first target signal and the second target signal.

8. An identity recognition device, applied to an electronic device, characterized in that: The device comprises: a processor and a memory for storing a computer program that can be run on the processor, wherein the processor is configured to execute the steps of the method according to any one of claims 1 to 6 when running the computer program.

9. A computer-readable storage medium, applied to an electronic device, having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images