A user identification method, apparatus and device

Abstract

This invention discloses a user identification method, apparatus, and device. The method includes: obtaining static gesture data of a user; performing absolute value processing on the static gesture data to obtain an absolute value sequence; obtaining the number of signal points belonging to valid static gesture clusters in the absolute value sequence; and identifying the user based on the number of signal points belonging to valid static gesture clusters. Through the above method, this invention achieves accurate and efficient user identification.

Description

Technical Field

[0001] This invention relates to the field of security technology, and specifically to a user identification method, apparatus, and device. Background Technology

[0002] Currently, mainstream identity verification technologies mainly include passwords, fingerprint recognition, and facial recognition. These technologies have been applied to various aspects of life. However, once personal biometric information such as faces, fingerprints, and irises is stolen, it can cause irreparable damage to the user's personal safety, leading to considerable concerns among users about the security of using personal biometric information for identity verification. Static user gestures have advantages such as being easy to collect and difficult to imitate. Based on the differences in the amplitude of physiological tremors among different users, user identity can be verified.

[0003] Traditional biometric authentication suffers from problems such as susceptibility to external environmental influences, low security, and difficulty in being accepted by users. For example, dynamic gestures are easily imitated during operation, making them unsecured as an authentication method. Feature extraction is computationally complex, and dynamic time warping requires a certain length of feature sequence. Excessive sequence differences can lead to inaccurate similarity matching results after calibration. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention are proposed to provide a user identification method, apparatus, and device that overcomes or at least partially solves the above problems.

[0005] According to one aspect of the present invention, a user identification method is provided, comprising:

[0006] Obtain the user's static gesture data;

[0007] The static gesture data is processed by absolute value analysis to obtain an absolute value sequence;

[0008] Obtain the number of signal points belonging to valid static gesture clusters in the absolute value sequence;

[0009] The user is identified based on the number of signal points belonging to the effective static gesture cluster.

[0010] According to another aspect of the present invention, a user identification device is provided, comprising:

[0011] The acquisition module is used to obtain the user's static gesture data;

[0012] The processing module is used to perform absolute value processing on the static gesture data to obtain an absolute value sequence; and to obtain the number of signal points belonging to the effective static gesture cluster in the absolute value sequence.

[0013] The recognition module is used to identify the user based on the number of signal points belonging to the valid static gesture cluster.

[0014] According to another aspect of the present invention, a computing device is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus;

[0015] The memory is used to store at least one executable instruction, which causes the processor to perform the operation corresponding to the user identification method described above.

[0016] According to another aspect of the present invention, a computer storage medium is provided, the storage medium storing at least one executable instruction that causes a processor to perform an operation corresponding to the user identification method described above.

[0017] According to the solution provided in the above embodiments of the present invention, by obtaining the user's static gesture data; performing absolute value processing on the static gesture data to obtain an absolute value sequence; obtaining the number of signal points belonging to the effective static gesture cluster in the absolute value sequence; and identifying the user based on the number of signal points belonging to the effective static gesture cluster, automatic clustering of static gesture signals can be achieved, thereby solving the problem of low efficiency in traditional biometric identity authentication and achieving the beneficial effect of accurate and efficient identification of user identity.

[0018] The above description is merely an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of the present invention more obvious and understandable, specific implementation methods of the embodiments of the present invention are described below. Attached Figure Description

[0019] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0020] Figure 1 A flowchart of the user identification method provided in an embodiment of the present invention is shown;

[0021] Figure 2 This illustrates the use of DIST in the user identification method provided by an embodiment of the present invention. N×i A schematic diagram of the KNN distribution is obtained by arranging each column in ascending order.

[0022] Figure 3This diagram illustrates the smoothed k-dist(m) curve in the user identification method provided by an embodiment of the present invention.

[0023] Figure 4 This diagram illustrates the probability distribution of the smoothed k-dist(m) curve in the user identification method provided by an embodiment of the present invention.

[0024] Figure 5 This diagram illustrates the piecewise difference of the smoothed k-dist(m) curve in the user identification method provided by an embodiment of the present invention.

[0025] Figure 6 This diagram illustrates the sequence distribution of the number of differences corresponding to each position point in the piecewise difference sequence of the smooth k-dist(m) curve in the user identification method provided by an embodiment of the present invention.

[0026] Figure 7 This diagram illustrates the distribution of the number of differences in the user identification method provided in this embodiment of the invention.

[0027] Figure 8 This diagram illustrates the ratio of the front and rear segments of the difference quantity merging distribution weight in the user identification method provided by an embodiment of the present invention.

[0028] Figure 9 This diagram illustrates the difference between the preceding and following segments of the weighted distribution of the difference quantity in the user identification method provided by an embodiment of the present invention.

[0029] Figure 10 This diagram illustrates the calculation of the weights for the distribution of the number of lookup differences in the user identification method provided by an embodiment of the present invention.

[0030] Figure 11 This diagram illustrates the critical segmentation of the k-dist(m) curve segmentation difference in the user identification method provided by an embodiment of the present invention.

[0031] Figure 12 This diagram illustrates the critical point of the smoothed k-dist(m) curve in the user identification method provided by an embodiment of the present invention.

[0032] Figure 13 A flowchart of a specific user identification method provided by an embodiment of the present invention is shown;

[0033] Figure 14 A schematic diagram of the structure of the user identification device provided in an embodiment of the present invention is shown;

[0034] Figure 15 A schematic diagram of the structure of a computing device provided in an embodiment of the present invention is shown. Detailed Implementation

[0035] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this invention will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.

[0036] Figure 1 A flowchart of a user identification method provided by an embodiment of the present invention is shown. Figure 1 As shown, the method includes the following steps:

[0037] Step 11: Obtain the user's static gesture data; the static gesture data here may be the user's physiological tremor signal.

[0038] Step 12: Perform absolute value processing on the static gesture data to obtain an absolute value sequence;

[0039] Step 13: Obtain the number of signal points belonging to the effective static gesture cluster in the absolute value sequence;

[0040] Step 14: Identify the user based on the number of signal points belonging to the valid static gesture cluster.

[0041] In this embodiment, by obtaining the user's static gesture data; performing absolute value processing on the static gesture data to obtain an absolute value sequence; obtaining the number of signal points belonging to valid static gesture clusters in the absolute value sequence; and identifying the user based on the number of signal points belonging to valid static gesture clusters, automatic clustering of tremor gesture signals can be achieved. This allows the user's static gesture data to be compared with valid gesture cluster templates, thereby solving the problems of low security and difficulty in being accepted by users in traditional biometric identity authentication, and achieving the beneficial effect of accurate and efficient identification of user identity.

[0042] In an optional embodiment of the present invention, step 11 is specifically implemented by collecting the user's static gesture data through gesture collection software and corresponding devices. First, the user needs to maintain a relatively static posture with the device, and then click the "Start Collection" button on the device. After that, the device starts collecting the user's gestures. When the preset collection time is reached, the device will display "Collection Ended", at which point the collection operation ends and the user's static gesture data is obtained.

[0043] During the process of collecting a user's gestures, the upper limbs need to exhibit muscle tremors, the elbows should not be supported by the body, and the arms need to relax after each signal collection before the next collection. This can prevent upper limb fatigue caused by continuous collection, which could lead to unreliable templates.

[0044] During the process of the device collecting user gestures, it is necessary to collect physiological tremor signals through a built-in linear accelerometer sensor, as this can eliminate the influence of gravitational acceleration. The optimal sampling frequency for the built-in linear accelerometer sensor is set to 50Hz. This is because each static gesture capture lasts approximately 10 seconds, and static gestures can reflect the user's inherent physiological tremor information. If other operations introduce noise near the start and end points of the gesture sequence, the amplitude fluctuation will be relatively large. Therefore, this setting ensures a relatively stable effective signal amplitude.

[0045] In another optional embodiment of the present invention, step 12 may include:

[0046] Step 121: Perform absolute value processing on the data points of the three-axis acceleration position i in the sequence of static gesture data to obtain the absolute value sequence L. self ={l1,l2,l3,...l N The absolute value sequence has a length of N, where N is a positive integer.

[0047] In this embodiment, since the differences in static gestures among different users mainly lie in the differences in the amplitude of signal jitter in various directions, in order to ensure that the data points are in the same quadrant in space during data analysis, it is necessary to perform absolute value processing on the data points of the three-axis acceleration position i in the sequence of static gesture data, i.e., formula: l i =(|x i |,|y i |,|z i |), where l i Let |x| represent the i-th data point. i | represents the absolute value of the data point at position i on the x-axis, |y i | represents the absolute value of the data point at position i on the y-axis, |z i | represents the absolute value of the data point at position i on the z-axis. Then, calculate l sequentially. i The absolute value sequence L is obtained. self ={l1,l2,l3,...l N}, where the length of the data points is N, 1≤i≤N.

[0048] In another optional embodiment of the present invention, step 13 may include:

[0049] Step 131: Obtain the k-dist(m) sequence based on the absolute value sequence;

[0050] Step 132: Obtain the first parameter Eps based on the k-dist(m) sequence;

[0051] Step 133: Obtain the second parameter MinPts based on the first parameter Eps;

[0052] Step 134: Perform cluster analysis on the first parameter Eps and the second parameter MinPts to obtain effective static gesture clusters and noise jitter clusters. The effective static gesture clusters are C gesture The noise jitter cluster is C noise ;

[0053] Step 135: Using the effective static gesture cluster as the user gesture authentication template, determine whether each data point in the absolute value sequence belongs to the effective static gesture cluster or the noise jitter cluster;

[0054] Step 136: Obtain the number of signal points clustered into the effective static gesture cluster.

[0055] In this embodiment, steps 135-136 use the effective static gesture cluster C gesture As a user gesture authentication template, other tremor signals L to be authenticated in the absolute value sequence will be used. test ={l1,l2,l3,...l n}, and calculate the gesture cluster C to which each spatial gesture signal belongs according to the Eps and MinPts parameters. gesture Or noise jitter cluster C noise Finally, the data is clustered into the effective static gesture cluster C. gesture The number of signal points.

[0056] In another optional embodiment of the present invention, step 132 may include:

[0057] Step 1321: Obtain the distance distribution matrix (DIST) of the data points in the absolute value sequence. N×N In this context, the distance between data points in the absolute value sequence is represented as the distance between various data points in space.

[0058] Specifically, there are differences between the amplitudes of valid gesture data and noise data, as well as the amplitudes of valid static gestures from different users. These differences manifest as differences in spatial distance. Therefore, it is necessary to calculate the distances between various data points in space to obtain the distance distribution matrix between spatial data points, i.e., the distance distribution matrix DIST of the data points in the absolute value sequence. N×N .

[0059] Specifically, through the formula DIST N×N = {dist(i,j)}|1≤i≤N,1≤j≤N, to obtain the distance distribution matrix DIST of the data points in the absolute value sequence. N×N Where dist(i,j) is the Euclidean distance between data points at positions i and j in space, and N is the number of data points.

[0060] Step 1322, for the DIST N×N Sort DIST in ascending order by row. N×i Arrange each column in ascending order to obtain the KNN distribution using the nearest neighbor algorithm;

[0061] Specifically, such as Figure 2 As shown, the KNN nearest neighbor algorithm does not require training, and its classification accuracy is high when the class label boundaries are relatively neat.

[0062] Step 1323: Based on the KNN distribution, smooth the k-dist (k=m) curve to obtain a smoothed k-dist (m) sequence, where m is an integer less than or equal to N;

[0063] Specifically, such as Figure 3 As shown, for the absolute value sequence of static gesture data, the middle part of the data is relatively stable and can reflect the k-dist distribution of other positions. Therefore, the sequence at position m can be selected for analysis, i.e., k-dist (k = m). Furthermore, smoothing the k-dist (k = m) curve can prevent some noise from affecting the data analysis. Preferably, the k-dist at the middle position of the sequence is selected for analysis. The sequence length is N, and the k-dist (k = m) curve at position N / 2 = m is selected. If m is not an integer, it is calculated by rounding to the nearest integer.

[0064] Secondly, smooth the k-dist (k=m) by averaging every three points, i.e., using the formula... We obtain a smooth k-dist(m) sequence, where N represents the number of k-dist (k = m) segments, and dist... j This represents the k-dist value at position k-dist (k = m), and interval represents the window length for averaging, interval = 3.

[0065] Step 1324: Obtain the smoothed k-dist(m) segmented difference sequence of the smoothed k-dist(m) sequence;

[0066] Specifically, such as Figure 4 and Figure 5 As shown, firstly, the probability distribution of the k-dist (k=m) data points is statistically analyzed. The k-dist distance interval is set to 0.01. Then, by dividing the maximum k-dist (m) distance by the k-dist (m) distance interval, the following is obtained: Figure 4 The diagram shows a smooth k-dist(m) probability distribution.

[0067] from Figure 4It can be seen that the k-dist(m) data points are mainly distributed in densely spaced areas, and k-dist(m) shows a uniform distribution in the flat sections of the curve, while a few k-dist(m) data points are distributed in larger areas, and k-dist(m) shows a non-uniform distribution in the steep sections of the curve.

[0068] Secondly, based on from Figure 4 The characteristics of amplitude differences between smooth and steep segments of the k-dist(m) data observed are used to obtain a smoothed k-dist(m) segmented difference sequence through piecewise first-order differencing. Piecewise first-order differencing can reduce irregular fluctuations between stable segments, making the fluctuation curve smoother. The difference calculation method for each segment is: DIFF i =|d i -d i-1 |+|d i+1 -d i |,i=1,...,L,where,d i Let i represent the value at position i of k-dist(m), and L represent the number of segments.

[0069] Step 1325: Determine the critical point position P of the smoothed k-dist(m) sequence based on the critical point position of the difference in the smoothed k-dist(m) segmented difference sequence;

[0070] Step 1326: Based on the critical point position P of the smoothed k-dist(m) sequence, find the k-dist value at the corresponding position of the k-dist(m) sequence, and use it as the first parameter Eps.

[0071] Specifically, such as Figures 6-12 As shown, the first step involves searching for tempValue, temPos, and mumLeft in left-to-right order. tempValue and temPos represent the maximum difference value and the position of the maximum difference value at position i and its left, respectively. mumLeft... i This represents the number of differences to the left of tempValue that are less than tempPos at position i.

[0072] The second step is to initialize temPos to 1 and tempValue to diff1, then use the formula... The temPos of each location point i can be obtained.

[0073] The third step is to use the formula. Calculate the corresponding mumLeft based on tempValue and temPos at position i. iThe value is used to obtain the quantity distribution sequence NL, where NL = {numLeft1, ..., numLeft}. L}

[0074] Fourth step: Based on the quantity distribution sequence NL, merge consecutive mumLefts with the same quantity from left to right. i This yields the merged item sequence M. like Figure 7 As shown, the merged item sequence M reveals the result of the quantity merging distribution. Here, H is the length of the merged item sequence M, m... H Let Num be the number of consecutive identical mumLefts merged in the H-th merge item, where Num = {num1, ... num2} H} is the mumLeft value for each merged item.

[0075] The fifth step is to analyze the differences and ratios between the points before and after the quantity distribution, based on the quantity distribution distribution shown by the merged item sequence M, to obtain the critical point of quantity distribution difference. For example... Figure 8 and Figure 9 As shown, the signal points are unstable within the steep segment, and the signal amplitude varies greatly. This is characterized by a large difference in the ratio of adjacent signal differences in the search distribution sequence, and the difference values ​​are relatively low. In contrast, the data in the stable segment is stable, and the signal points distributed in the same difference interval are relatively concentrated, characterized by large differences between adjacent signals and a low difference ratio.

[0076] Step 6, as follows Figure 10 As shown, through the formula Calculate the weights of each location in the quantity merge distribution. The maximum value of the weight is recorded as the critical point position, denoted as P1. The formula... Based on the characteristic that the difference ratio and numerical difference between adjacent data at the critical positions of the stationary and steep segments of the quantity merged distribution sequence are relatively large, the weight is calculated by combining two indicators. The formula can solve the problem that a single indicator cannot directly distinguish the critical region of quantity distribution.

[0077] Step 7: Based on the critical point position P1, obtain the critical point position P2 of the quantity merging distribution. Since the position i of the quantity distribution weight corresponds to the position i of the merging distribution point, P2 = P1.

[0078] Step 8, using the formula The critical position P3 of the distribution of the number of searches on the left and right is obtained.

[0079] Step nine: Determine the critical position P3 of the left and right search quantity distribution as the critical point position P of the smooth k-dist(m) sequence. For example... Figure 11 and Figure 12As shown, since the positions i(P1), i(P2), and i(P3) of the smoothed k-dist(m) segmented difference sequence, as well as the positions i(P3) of the left and right search quantity distribution, are consistent, P = P3 can be directly determined.

[0080] At this point, the critical position P of the smooth k-dist(m) sequence can be adaptively calculated, and the k-dist value corresponding to the position of k-dist(m) can be found based on the critical position P, denoted as Eps.

[0081] In another optional embodiment of the present invention, step 133 may include:

[0082] Step 1331: Calculate the mathematical expectation of the data objects in the neighborhood of the position corresponding to the first parameter Eps, and use the mathematical expectation as the second parameter MinPts of the k-dist(m) sequence.

[0083] In this embodiment, through the formula The expected value of the data objects in the neighborhood of the position corresponding to the first parameter Eps can be calculated, where p i This represents the number of data points in the Eps neighborhood of point i. When calculating the expected value of data objects, the number of objects in the neighborhood of each point is calculated sequentially based on the statistical distribution characteristics of the data points in the neighborhood of each point. This allows for the adaptive calculation of the optimal global parameters Eps and MinPts.

[0084] In another optional embodiment of the invention, step 14 may include:

[0085] Step 141: Obtain the ratio of the number of signal points belonging to the effective static gesture cluster to the length of the absolute value sequence;

[0086] Step 142: Based on the ratio and a preset threshold, determine whether the user is the target user.

[0087] In this embodiment, when collecting the user's static gesture sequence L, the absolute value sequence L = {l1, l2, l3, ... l1} is first calculated. N The absolute value sequence L = {l1, l2, l3, ... l} N The length is N, and then signal points l1 to l are extracted sequentially. N Then, based on the Eps and MinPts parameters, the signal points l1 to l2 are calculated respectively. N The category is then determined, and the effective static gesture cluster C is counted. gesture The number of signal points is determined, and finally, the cluster C belonging to the effective static gestures is grouped together. gesture The ratio r of the number of signal points to the length N of the absolute value sequence selfThe identity of the user to be authenticated is determined by comparing it with a preset threshold. The preset threshold is the authentication threshold ρ.

[0088] In another optional embodiment of the present invention, step 142 may include:

[0089] Step 1421: If the ratio is greater than or equal to a preset threshold, then the user is determined to be the target user;

[0090] Step 1422: If the ratio is less than the preset threshold, then the user is determined to be a non-target user.

[0091] In this embodiment, if the ratio r self If the ratio r is greater than or equal to ρ, then the user is determined to be the target user; if the ratio r is greater than or equal to ρ, then the user is determined to be the target user. self If <ρ, then the user is determined to be a non-target user.

[0092] The following is combined Figure 13 Explain the implementation process of the above method:

[0093] like Figure 13 As shown, the above embodiments of the present invention are mainly based on the personalized differences in the user's physiological tremor signals, referred to as static gestures, to achieve user identity authentication.

[0094] The main steps of the method include:

[0095] Signal acquisition: Acquiring static gesture data from users;

[0096] Signal processing: The collected static gesture data of users is processed to remove the signal timing features. Then, the three-axis absolute amplitude points of the jitter signal after removing the signal timing features are placed in the same quadrant in space. The adaptive DBSCAN density clustering method is used to cluster the valid gestures and jitter noise. Finally, the cluster of valid user gestures is used as the reference template.

[0097] Signal classification and authentication: The cluster categories of signals to be authenticated are analyzed in turn, and the authentication threshold is calculated based on the statistical results to determine the user's identity.

[0098] In the above embodiments of the present invention, effective gesture clusters and jitter noise clusters are clustered. Using the effective gesture clusters as a reference template, the clustering categories of the signals to be authenticated are analyzed in sequence. Based on the statistical results, the authentication threshold is calculated to determine the user's identity, thereby realizing automatic clustering of user tremor gesture signals. Based on the effective gesture cluster template, accurate and efficient identification of user identity is achieved, reducing the computational complexity of extracting various features and shape calibration matching.

[0099] Figure 14 A schematic diagram of the structure of a user identification device 140 provided in an embodiment of the present invention is shown. Figure 14 As shown, the device includes:

[0100] The acquisition module 141 is used to obtain the user's static gesture data;

[0101] Processing module 142 is used to perform absolute value processing on the static gesture data to obtain an absolute value sequence; and to obtain the number of signal points belonging to the effective static gesture cluster in the absolute value sequence.

[0102] The recognition module 143 is used to identify the user based on the number of signal points belonging to the effective static gesture cluster.

[0103] Optionally, the processing module 142 is further configured to perform absolute value processing on the data points of the triaxial acceleration position i in the sequence of static gesture data to obtain an absolute value sequence L. self ={l1,l2,l3,...l N The absolute value sequence has a length of N, where N is a positive integer.

[0104] Optionally, the processing module 142 is further configured to obtain a k-dist(m) sequence based on the absolute value sequence;

[0105] Based on the k-dist(m) sequence, the first parameter Eps is obtained;

[0106] Based on the first parameter Eps, the second parameter MinPts is obtained;

[0107] Cluster analysis was performed on the first parameter Eps and the second parameter MinPts to obtain effective static gesture clusters and noise jitter clusters;

[0108] Using the effective static gesture cluster as a user gesture authentication template, determine whether each data point in the absolute value sequence belongs to the effective static gesture cluster or the noise jitter cluster;

[0109] Obtain the number of signal points clustered into the effective static gesture cluster.

[0110] Optionally, the processing module 142 is further configured to obtain the distance distribution matrix (DIST) of the data points in the absolute value sequence. N×N ;

[0111] For the DIST N×N Sort DIST in ascending order by row. N×i Arrange each column in ascending order to obtain the KNN distribution using the nearest neighbor algorithm;

[0112] Based on the KNN distribution, the k-dist (k=m) curve is smoothed to obtain a smoothed k-dist (m) sequence, where m is an integer less than or equal to N;

[0113] Obtain the smoothed k-dist(m) segmented difference sequence of the smoothed k-dist(m) sequence;

[0114] The critical point position P of the smooth k-dist(m) sequence is determined based on the critical point position of the difference critical point of the smooth k-dist(m) segmented difference sequence;

[0115] Based on the critical point position P of the smoothed k-dist(m) sequence, find the k-dist value at the corresponding position in the k-dist(m) sequence, and use it as the first parameter Eps.

[0116] Optionally, the processing module 142 is further configured to calculate the mathematical expectation of the data objects in the neighborhood of the position corresponding to the first parameter Eps, and use the mathematical expectation as the second parameter MinPts of the k-dist(m) sequence.

[0117] Optionally, the recognition module 143 is further configured to obtain the ratio of the number of signal points belonging to the valid static gesture cluster to the length of the absolute value sequence;

[0118] Based on the ratio and a preset threshold, it is determined whether the user is the target user.

[0119] Optionally, the identification module 143 is further configured to determine the user as the target user if the ratio is greater than or equal to a preset threshold.

[0120] If the ratio is less than the preset threshold, the user is determined to be a non-target user.

[0121] It should be noted that this embodiment is a device embodiment corresponding to the above method embodiment. All implementation methods in the above method embodiment are applicable to this device embodiment and can achieve the same technical effect.

[0122] This invention provides a non-volatile computer storage medium storing at least one executable instruction that can execute the user identification method in any of the above method embodiments.

[0123] Figure 15 The diagram shows a structural schematic of a computing device provided in an embodiment of the present invention. The specific embodiments of the present invention do not limit the specific implementation of the computing device.

[0124] like Figure 15 As shown, the computing device may include a processor, a communications interface, memory, and a communications bus.

[0125] The processor, communication interface, and memory communicate with each other via a communication bus. The communication interface is used to communicate with other network elements, such as clients or other servers. The processor executes programs, specifically the steps described in the user identification method embodiment for computing devices.

[0126] Specifically, the program may include program code, which includes computer operation instructions.

[0127] The processor may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The computing device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0128] Memory is used to store programs. Memory may include high-speed RAM, and may also include non-volatile memory, such as at least one disk drive.

[0129] Specifically, the program can be used to cause the processor to execute the user identification method in any of the above method embodiments. The specific implementation of each step in the program can be found in the corresponding descriptions of the steps and units in the above user identification method embodiments, and will not be repeated here. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the devices and modules described above can be referred to the corresponding process descriptions in the foregoing method embodiments, and will not be repeated here.

[0130] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, the embodiments of the present invention are not directed to any particular programming language. It should be understood that the embodiments of the present invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the embodiments of the present invention.

[0131] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0132] Similarly, it should be understood that, in order to streamline the embodiments of the invention and aid in understanding one or more of the various inventive aspects, features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the above description of exemplary embodiments of the invention. However, this disclosure should not be construed as reflecting an intention that the claimed embodiments of the invention require more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0133] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0134] Furthermore, those skilled in the art will understand that although some embodiments herein include certain features included in other embodiments but not others, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0135] The various component embodiments of the present invention can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components according to the embodiments of the present invention. The embodiments of the present invention can also be implemented as device or apparatus programs (e.g., computer programs and computer program products) for performing part or all of the methods described herein. Such programs implementing the embodiments of the present invention can be stored on a computer-readable medium, or can be in the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0136] It should be noted that the above embodiments are illustrative of the present invention and not restrictive of the invention, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. Embodiments of the present invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A user identification method, characterized in that, The method includes: Obtain the user's static gesture data; The static gesture data is processed by absolute value analysis to obtain an absolute value sequence; The number of signal points belonging to the effective static gesture cluster in the absolute value sequence is obtained; wherein, a k-dist(m) sequence is obtained based on the absolute value sequence; a first parameter Eps is obtained based on the k-dist(m) sequence; a second parameter MinPts is obtained based on the first parameter Eps; cluster analysis is performed on the first parameter Eps and the second parameter MinPts to obtain the effective static gesture cluster and the noise jitter cluster; using the effective static gesture cluster as the user gesture authentication template, it is determined whether each data point in the absolute value sequence belongs to the effective static gesture cluster or the noise jitter cluster; the number of signal points clustered into the effective static gesture cluster is obtained; The user is identified based on the number of signal points belonging to the effective static gesture cluster; wherein, the ratio of the number of signal points belonging to the effective static gesture cluster to the length of the absolute value sequence is obtained; based on the ratio and a preset threshold, it is determined whether the user is the target user.

2. The user identification method according to claim 1, characterized in that, The static gesture data is subjected to absolute value processing to obtain an absolute value sequence, including: The absolute value of the data points at the triaxial acceleration position i in the sequence of static gesture data is processed to obtain the absolute value sequence L. self ={l1,l2,l3,...l N The absolute value sequence has a length of N, where N is a positive integer.

3. The user identification method according to claim 1, characterized in that, Based on the k-dist(m) sequence, the first parameter Eps is obtained, including: Obtain the distance distribution matrix (DIST) of the data points in the absolute value sequence. N×N ; For the DIST N×N Sort the data in ascending order, for each row in the DIST. N×i Arrange each column in ascending order to obtain the KNN distribution using the nearest neighbor algorithm; Based on the KNN distribution, the k-dist (k=m) curve is smoothed to obtain a smoothed k-dist (m) sequence, where m is an integer less than or equal to N; Obtain the smoothed k-dist(m) segmented difference sequence of the smoothed k-dist(m) sequence; The critical point position P of the smooth k-dist(m) sequence is determined based on the critical point position of the difference critical point of the smooth k-dist(m) segmented difference sequence; Based on the critical point position P of the smoothed k-dist(m) sequence, find the k-dist value at the corresponding position in the k-dist(m) sequence, and use it as the first parameter Eps.

4. The user identification method according to claim 1, characterized in that, Based on the first parameter Eps, the second parameter MinPts is obtained, including: Calculate the mathematical expectation of the data objects in the neighborhood of the position corresponding to the first parameter Eps, and use the mathematical expectation as the second parameter MinPts of the k-dist(m) sequence.

5. The user identification method according to claim 1, characterized in that, Based on the ratio and a preset threshold, it is determined whether the user is a target user, including: If the ratio is greater than or equal to a preset threshold, then the user is determined to be the target user; If the ratio is less than the preset threshold, the user is determined to be a non-target user.

6. A user identification device, characterized in that, include: The acquisition module is used to obtain the user's static gesture data; The processing module is used to perform absolute value processing on the static gesture data to obtain an absolute value sequence; The number of signal points belonging to the effective static gesture cluster in the absolute value sequence is obtained; wherein, a k-dist(m) sequence is obtained based on the absolute value sequence; a first parameter Eps is obtained based on the k-dist(m) sequence; a second parameter MinPts is obtained based on the first parameter Eps; cluster analysis is performed on the first parameter Eps and the second parameter MinPts to obtain the effective static gesture cluster and the noise jitter cluster; using the effective static gesture cluster as the user gesture authentication template, it is determined whether each data point in the absolute value sequence belongs to the effective static gesture cluster or the noise jitter cluster; the number of signal points clustered into the effective static gesture cluster is obtained; The identification module is used to identify the user based on the number of signal points belonging to the effective static gesture cluster; wherein, the ratio of the number of signal points belonging to the effective static gesture cluster to the length of the absolute value sequence is obtained; and based on the ratio and a preset threshold, it is determined whether the user is the target user.

7. A computing device, comprising: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction that causes the processor to perform the operation corresponding to the user identification method as described in any one of claims 1-5.

8. A computer storage medium storing at least one executable instruction that causes a processor to perform an operation corresponding to the user identification method as described in any one of claims 1-5.

Images