A signature verification method, apparatus, device, storage medium, and program product

Abstract

The application provides a signature verification method, device, equipment, storage medium and program product, and relates to the technical field of data processing. The method comprises the following steps: acquiring input data corresponding to a first signature, wherein the input data comprises at least one of pressure data when the first signature is input, three-axis acceleration data of a writing device and writing position data; extracting first features corresponding to the first signature based on the input data; acquiring second features corresponding to a second signature, wherein the second features are used to represent at least one of pressure change, posture change and writing position change when the second signature is input, the second signature is used to verify the first signature, and the second features are extracted based on data when the second signature is written; and generating a verification result based on the first features and the second features, wherein the verification result is used to represent whether the first signature and the second signature are written by the same user. The application can improve the security of the signature.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and specifically to a signature verification method, apparatus, device, storage medium, and program product. Background Technology

[0002] Electronic signatures enable the signing of digital services or contracts and are widely used in the communications field and digital business. In related technologies, a user's electronic signature is pre-stored. During subsequent verification, the pre-stored electronic signature is used to verify the user's input signature to confirm its authenticity. However, these technologies typically verify the electronic signature by comparing its shape with the subsequently input signature. This method is easily copied using high-resolution images or imitated by humans, resulting in relatively low security for signature verification.

[0003] It is evident that the related technologies suffer from low security in signature verification. Summary of the Invention

[0004] This invention provides a signature verification method, apparatus, device, storage medium, and program product to address the problem of low security in signature verification in related technologies.

[0005] To solve the above problems, the present invention is implemented as follows: In a first aspect, embodiments of the present invention provide a signature verification method, including: Obtain input data corresponding to the first signature, wherein the input data includes at least one of the pressure data when inputting the first signature, the three-axis acceleration data of the writing device, and the writing position data; Based on the input data, a first feature corresponding to the first signature is extracted. The first feature is used to characterize at least one of the pressure change, the posture change of the writing device, and the writing position change when the first signature is input. Obtain a second feature corresponding to the second signature. The second feature is used to characterize at least one of the pressure change, the posture change of the writing device, and the writing position change when the second signature is input. The second signature is used to verify the first signature. The second feature is extracted based on the data extracted when writing the second signature. A verification result is generated based on the first feature and the second feature. The verification result is used to characterize whether the first signature and the second signature were written by the same user.

[0006] In a second aspect, embodiments of the present invention provide a signature verification device, comprising: The first acquisition module is used to acquire input data corresponding to the first signature. The input data includes at least one of the pressure data when the first signature is entered, the three-axis acceleration data of the writing device, and the writing position data. The extraction module is used to extract a first feature corresponding to the first signature based on the input data. The first feature is used to characterize at least one of the pressure change when the first signature is input, the posture change of the writing device, and the writing position change. The second acquisition module is used to acquire a second feature corresponding to the second signature. The second feature is used to characterize at least one of the pressure change, the posture change of the writing device, and the writing position change when the second signature is input. The second signature is used to verify the first signature. The second feature is extracted based on the data extracted when writing the second signature. The generation module is used to generate a verification result based on the first feature and the second feature, wherein the verification result is used to characterize whether the first signature and the second signature were written by the same user.

[0007] Thirdly, embodiments of the present invention also provide an electronic device, including a transceiver and a processor. The transceiver is used to acquire input data corresponding to the first signature. The input data includes at least one of the pressure data when the first signature is entered, the three-axis acceleration data of the writing device, and the writing position data. The processor is configured to extract a first feature corresponding to the first signature based on the input data. The first feature is configured to characterize at least one of the pressure change when the first signature is input, the posture change of the writing device, and the writing position change. The transceiver is further configured to acquire a second feature corresponding to the second signature. The second feature is configured to characterize at least one of the pressure change, the posture change of the writing device, and the writing position change when the second signature is input. The second signature is used to verify the first signature. The second feature is extracted based on the data extracted when the second signature is written. The processor is further configured to generate a verification result based on the first feature and the second feature, the verification result being used to characterize whether the first signature and the second signature were written by the same user.

[0008] Fourthly, embodiments of the present invention provide an electronic device, including: a processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, it implements the steps of the signature verification method described in the first aspect.

[0009] Fifthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the signature verification method described in the first aspect.

[0010] In a sixth aspect, the present invention also provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the signature verification method described in the first aspect.

[0011] In this embodiment of the invention, input data corresponding to a first signature is obtained. The input data includes at least one of pressure data when the first signature is input, three-axis acceleration data of the writing device, and writing position data. A first feature corresponding to the first signature is extracted based on the input data. The first feature characterizes at least one of pressure changes, posture changes of the writing device, and writing position changes when the first signature is input. A second feature corresponding to a second signature is obtained. The second feature characterizes at least one of pressure changes, posture changes of the writing device, and writing position changes when the second signature is input. The second signature is used to verify the first signature. The second feature is extracted based on the data when the second signature is written. A verification result is generated based on the first feature and the second feature. The verification result characterizes whether the first signature and the second signature were written by the same user. Thus, by verifying the first signature using the first feature and the second signature using the second feature, the first signature can be verified through at least one of pressure changes, posture changes of the writing device, and writing position changes, thereby improving the security of signature verification. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of a signature verification method provided in an embodiment of the present invention; Figure 2 This is a structural diagram of a signature verification device provided in an embodiment of the present invention; Figure 3 This is a structural diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0014] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0015] Please see Figure 1 , Figure 1 This is a flowchart of a signature verification method provided in an embodiment of the present invention, such as... Figure 1 As shown, it includes the following steps: Step 101: Obtain the input data corresponding to the first signature. The input data includes at least one of the pressure data when inputting the first signature, the three-axis acceleration data of the writing device, and the writing position data.

[0016] The first signature mentioned above is a signature to be verified. After the first signature is written using a writing tool, the first signature is verified using the method of this embodiment of the invention to confirm whether it is a signature written by the user.

[0017] The above input data includes at least one of the following: pressure data when inputting the first signature, three-axis acceleration data of the writing device, and writing position data. The pressure data is the pressure applied to the planar area of ​​the signature when writing the first signature, the three-axis acceleration data is the acceleration of the writing device in different directions when writing the first signature, and the writing position data is the position of the writing device in the planar area of ​​the signature at different times.

[0018] The pressure data when inputting the first signature can be represented as a continuous pressure value P(t), and the triaxial acceleration data of the writing device can be represented as... The writing position data can be represented as (x(t), y(t)).

[0019] It should be understood that when a user writes a signature, the pressure data, the three-axis acceleration data of the writing device, and the writing position data can reflect the user's writing habits. Different users have different pressure data, three-axis acceleration data of the writing device, and writing position data when writing a signature, which can be used to verify the first signature through the input data of the first signature.

[0020] It should be noted that obtaining the input data corresponding to the first signature can be achieved by placing sensors in the writing area where the first signature is written to collect pressure data and writing position data, such as using a pressure-sensitive screen or active stylus with a high sampling rate (≥200 Hz) to collect the continuous pressure value P(t) of the pen tip during writing contact; or by placing sensors on the writing device to collect triaxial acceleration data.

[0021] Step 102: Extract the first feature corresponding to the first signature based on the input data. The first feature is used to characterize at least one of the pressure change, the posture change of the writing device, and the writing position change when the first signature is input.

[0022] The first feature mentioned above is a feature extracted based on at least one of pressure data, triaxial acceleration data of the writing device, and writing position data, so that the first feature can characterize at least one of the pressure change, posture change of the writing device, and writing position change when the first signature is input.

[0023] Specifically, when the input data includes pressure data, the first feature can characterize the pressure change when the first signature is entered; when the input data includes the three-axis acceleration data of the writing device, the first feature can characterize the posture change of the writing device; and when the input data includes writing position data, the first feature can characterize the writing position change.

[0024] In some implementations, extracting the first feature corresponding to the first signature based on the input data can be achieved by extracting features of the input data through a preset algorithm; or by inputting the input data into a feature extraction model and extracting the first feature corresponding to the input data through the feature extraction model.

[0025] In some implementations, when the input data is pressure data, triaxial acceleration data of the writing device, or writing position data, the first feature is a feature obtained by extracting the pressure data, triaxial acceleration data of the writing device, or writing position data. When the input data includes at least two of the following: pressure data, triaxial acceleration data of the writing device, and writing position data, the features obtained by extracting the pressure data, triaxial acceleration data of the writing device, or writing position data can be extracted separately first, and then the extracted features can be weighted, fused, or spliced ​​to obtain the first feature corresponding to the input data.

[0026] Step 103: Obtain the second feature corresponding to the second signature. The second feature is used to characterize at least one of the pressure change, the posture change of the writing device, and the writing position change when the second signature is input. The second signature is used to verify the first signature. The second feature is extracted based on the data extracted when writing the second signature.

[0027] The second signature mentioned above is a signature used to verify the first signature. The second signature can be a signature that is pre-entered. When the user enters the second signature, the input data corresponding to the second signature is also collected. Then, the second feature corresponding to the second signature is obtained by adjusting and extracting the input data corresponding to the second signature.

[0028] It should be noted that the extraction method of the first feature is the same as that of the second feature. That is, the features corresponding to the first signature (first feature) and the features corresponding to the second signature (second feature) are extracted in the same way. This allows us to determine whether the first signature and the second signature are from the same user, thereby verifying the first signature.

[0029] Step 104: Generate a verification result based on the first feature and the second feature. The verification result is used to characterize whether the first signature and the second signature were written by the same user.

[0030] In this embodiment of the invention, input data corresponding to a first signature is obtained. The input data includes at least one of pressure data when the first signature is input, three-axis acceleration data of the writing device, and writing position data. A first feature corresponding to the first signature is extracted based on the input data. The first feature characterizes at least one of pressure changes, posture changes of the writing device, and writing position changes when the first signature is input. A second feature corresponding to a second signature is obtained. The second feature characterizes at least one of pressure changes, posture changes of the writing device, and writing position changes when the second signature is input. The second signature is used to verify the first signature. The second feature is extracted based on the data when the second signature is written. A verification result is generated based on the first feature and the second feature. The verification result characterizes whether the first signature and the second signature were written by the same user. Thus, by verifying the first signature using the first feature and the second signature using the second feature, the first signature can be verified through at least one of pressure changes, posture changes of the writing device, and writing position changes, thereby improving the security of signature verification.

[0031] Furthermore, the features corresponding to the extracted pressure data, the three-axis acceleration data of the writing device, and the writing position data are explained respectively, so that the first feature can be obtained through the features corresponding to the pressure data, the three-axis acceleration data of the writing device, and the writing position data.

[0032] In one embodiment, the input data includes the pressure data, and the step of extracting the first feature corresponding to the first signature based on the input data includes: The pressure data includes multiple pressures, which are pressure values ​​at multiple times. The first-order difference for each time moment is calculated based on the normalized pressures. The first-order difference is the difference between the pressure at the corresponding time moment and the pressure at the previous time moment. Based on the normalized multiple pressures, calculate the first pressure and the second pressure of each stroke in the multiple strokes included in the first signature. The first pressure is the pressure at the start position of the corresponding stroke, and the second pressure is the pressure at the end position of the corresponding stroke. A binary code is generated based on the first difference corresponding to the plurality of strokes, wherein the first difference is the difference between the first pressure and the second pressure of the corresponding stroke; The first feature corresponding to the first signature is generated based on the first-order difference corresponding to the multiple time points and the binary encoding.

[0033] The aforementioned multiple pressures specifically refer to the pressure values ​​collected at multiple times. By calculating the first-order difference corresponding to each time point based on the pressure values ​​at multiple times, a binary code is generated. This allows the pressure changes to be determined through the first-order difference, and the pressure differences between different strokes to be determined through the binary code.

[0034] Specifically, the multiple pressures are first normalized to eliminate absolute differences between the devices collecting the pressure. In some implementations, the normalization of multiple pressures can be achieved using the following formula: ; In the formula, P norm P(t) represents the normalized pressure value at time t, and P(t) represents the unnormalized pressure value at time t. max P is the highest pressure value among multiple pressures. min It is the smallest pressure value among multiple pressures.

[0035] In some implementations, the normalized pressure can also be low-pass filtered. A low-pass filter (such as a Butterworth filter) can be used to remove high-frequency noise caused by equipment noise or involuntary muscle tremors, while retaining the main pressure profile that represents writing habits, thereby improving the accuracy of the normalized pressure.

[0036] Furthermore, after normalizing multiple pressures, the first-order difference corresponding to each time step is calculated based on the normalized multiple pressures, so that the pressure changes over time can be characterized by the first-order difference.

[0037] Specifically, the first difference at each time step can be calculated using the following formula: ; In the formula, Let be the first-order difference at time t.

[0038] Meanwhile, after normalizing multiple pressures, the first pressure and second pressure of each stroke in the multiple strokes included in the first signature are calculated based on the normalized multiple pressures, and a binary code is generated by the first pressure and the second pressure.

[0039] The first pressure is the pressure at the starting position of the corresponding stroke. The starting position can be the first 20% of the corresponding stroke. That is, the first pressure is obtained by averaging the pressure of the first 20% of the corresponding stroke. The second pressure is the pressure applied at the end of the corresponding stroke. The end point can be the last 20% of the stroke. The second pressure is obtained by averaging the pressure applied to the last 20% of the stroke. .

[0040] Furthermore, after calculating the first and second pressures for each stroke, the first difference for each stroke is calculated and then passed through a preset difference threshold. Determine the binary value corresponding to each stroke. For example, When, the binary value corresponding to the stroke is determined to be 1; and When a stroke is entered, its corresponding binary value is set to 0. Thus, by using the binary values ​​corresponding to multiple strokes, a binary code for the signature can be obtained. This binary code can then be used to determine the input pressure of each stroke when the user enters the signature.

[0041] In this embodiment of the invention, the pressure data, including multiple pressures, is normalized, where the multiple pressures are pressure values ​​at multiple time points. Based on the normalized pressures, a first-order difference is calculated for each time point, where the first-order difference is the difference between the pressure at the corresponding time point and the pressure at the previous time point. Based on the normalized pressures, a first pressure and a second pressure are calculated for each stroke in the multiple strokes included in the first signature, where the first pressure is the pressure at the start position of the corresponding stroke, and the second pressure is the pressure at the end position of the corresponding stroke. A binary code is generated based on the first difference corresponding to the multiple strokes, where the first difference is the difference between the first pressure and the second pressure of the corresponding stroke. A first feature corresponding to the first signature is generated based on the first-order difference and the binary code. Thus, by generating the first feature through the first-order difference and the binary code, the pressure variation and the pressure differences between different strokes can be determined using the first feature, facilitating subsequent verification of the first signature using the first feature.

[0042] In one embodiment, the method further includes: Determine multiple peak pressures among the plurality of pressures, each peak pressure being greater than its adjacent pressure; Calculate the pressure change corresponding to each peak pressure, where the change is the change between the corresponding peak pressure and the previous peak pressure. The permutation entropy is calculated based on the pressure changes corresponding to the multiple peak pressures, and the permutation entropy is used to characterize the changes of the multiple peak pressures. The step of generating the first feature corresponding to the first signature based on the first-order difference corresponding to the plurality of time points and the binary encoding includes: The first feature corresponding to the first signature is generated based on the first-order difference corresponding to the multiple time points, the binary encoding, and the permutation entropy.

[0043] The aforementioned permutation entropy is used to characterize the changes in multiple peak pressures. By calculating the permutation entropy, the pressure changes can be further quantified.

[0044] Specifically, determine multiple peak pressures. Calculate the pressure change corresponding to each peak pressure. ,in The permutation entropy is calculated by measuring the pressure changes corresponding to multiple peak pressures. Specifically, it can be: , H is a permutation and combination of pressure changes corresponding to multiple peak pressures. pe The permutation entropy is calculated, and the permutation entropy can be combined with the first-order difference and binary encoding corresponding to multiple time steps to generate the first feature.

[0045] In some implementations, the first feature corresponding to the first signature is generated based on the first-order difference, binary encoding, and permutation entropy corresponding to multiple time points. This can be achieved by constructing a feature vector V corresponding to the pressure data based on the binary encoding, permutation entropy, autocorrelation coefficient, and the first-order difference corresponding to multiple time points. p And a fixed-length binary hash value H is generated using a collision-resistant hashing algorithm. p As the first feature.

[0046] In this embodiment of the invention, multiple peak pressures are determined from the plurality of pressures, each peak pressure being greater than its adjacent pressure; the pressure change corresponding to each peak pressure is calculated, the change being the change between the corresponding peak pressure and the previous peak pressure; an arrangement entropy is calculated based on the pressure changes corresponding to the plurality of peak pressures, the arrangement entropy being used to characterize the changes in the plurality of peak pressures; a first feature corresponding to the first signature is generated based on the first-order difference corresponding to the plurality of time points, the binary encoding, and the arrangement entropy. Thus, by generating the first feature through the first-order difference value, binary encoding, and arrangement entropy, the pressure changes and pressure differences between different strokes can be determined through the first feature, facilitating subsequent verification of the first signature using the first feature.

[0047] In one embodiment, the input data includes the triaxial acceleration data, and the step of extracting the first feature corresponding to the first signature based on the input data includes: The triaxial acceleration is filtered, and the filtered triaxial acceleration is within a set frequency range. The filtered triaxial acceleration includes x-axis acceleration, y-axis acceleration and z-axis acceleration at multiple moments. Based on the filtered triaxial accelerations, the planar acceleration and z-axis acceleration corresponding to each moment are determined, wherein the planar acceleration is the sum of the x-axis acceleration and y-axis acceleration at the corresponding moment; Calculate the phase difference at each moment, where the phase difference is the difference between the plane phase and the vertical phase at the corresponding moment, the plane phase is calculated from the plane acceleration at the corresponding moment, and the vertical phase is calculated from the z-axis acceleration at the corresponding moment; Calculate the mean, standard deviation, and probability distribution shape parameter of the phase difference at the multiple time points, wherein the probability distribution shape parameter is used to characterize the shape of the curve corresponding to the multiple time points; The first feature corresponding to the first signature is generated based on the mean, standard deviation, and probability distribution shape parameters of the phase difference at the multiple time points.

[0048] The aforementioned triaxial acceleration is used to characterize the acceleration changes of the writing device in different directions, and the positional changes of the writing device can be determined by the acceleration in different directions.

[0049] In this process, the triaxial acceleration can be preprocessed before filtering. In some implementations, the preprocessing may include filtering out the gravitational acceleration component and the device's stationary offset, and may involve applying a Kalman filter or a complementary filter to the triaxial acceleration.

[0050] The aforementioned filtering of the triaxial acceleration preserves the triaxial acceleration within a set frequency range. The filtered triaxial acceleration can characterize the hand tremors experienced by the user when using the writing device. The set frequency range is 5-15Hz; that is, by applying a 5-15Hz bandpass filter to the triaxial acceleration data, the triaxial acceleration characteristic of hand tremors is extracted. , Let x be the acceleration along the x-axis. The acceleration along the y-axis, This refers to the z-axis acceleration. In some implementations, the dominant frequency of the micro-judder along each axis can be obtained using a Fast Fourier Transform. To calculate the correlation coefficient of the in-plane micro-flutter amplitude.

[0051] After filtering the triaxial acceleration, the planar acceleration is calculated first, which can be expressed as: ; in the formula for , for And z-axis acceleration .

[0052] Furthermore, to calculate the phase difference at each moment, one can first perform Hilbert transforms on the planar acceleration and z-axis acceleration respectively to obtain analytic signals, calculate the planar phase and vertical phase using the analytic signals, and then calculate the phase difference.

[0053] The analytical signals obtained by performing Hilbert transforms on the planar acceleration and the z-axis acceleration can be expressed as follows: ; ; In the formula, XY(t) is the analytical signal of the plane acceleration, Z(t) is the interpreted signal of the z-axis acceleration, H[] is the frequency response function of the Hilbert transformer, and j is the coefficient.

[0054] The planar phase and vertical phase can be calculated using the following formulas: ; ; In the formula, For planar phase, It is the vertical phase.

[0055] The phase difference at each moment can be calculated using the following formula: ; In the formula, Let be the phase difference at time t.

[0056] After calculating the phase difference at each time step, the average of the phase differences across multiple time steps is calculated. Standard deviation The first feature corresponding to the first signature is generated based on the mean, standard deviation, and probability distribution shape parameters of the phase difference at multiple time points, thereby obtaining the feature V corresponding to the three-dimensional acceleration. a .

[0057] Furthermore, the first feature corresponding to the first signature can be generated based on the mean, standard deviation, probability distribution shape parameters, and main frequency of micro-judder of each axis at multiple time points.

[0058] In this embodiment of the invention, the triaxial acceleration is filtered, and the filtered triaxial acceleration is within a set frequency range. The filtered triaxial acceleration includes x-axis acceleration, y-axis acceleration, and z-axis acceleration at multiple moments. Based on the filtered triaxial acceleration, the planar acceleration and z-axis acceleration corresponding to each moment are determined, and the planar acceleration is the sum of the x-axis acceleration and y-axis acceleration at the corresponding moment. The phase difference at each moment is calculated, and the phase difference is the difference between the planar phase and the vertical phase at the corresponding moment. The planar phase is calculated from the planar acceleration at the corresponding moment, and the vertical phase is calculated from the z-axis acceleration at the corresponding moment. The mean, standard deviation, and probability distribution shape parameter of the phase difference at multiple moments are calculated, and the probability distribution shape parameter is used to characterize the shape of the curve corresponding to the multiple moments. Based on the mean, standard deviation, and probability distribution shape parameter of the phase difference at multiple moments, a first feature corresponding to the first signature is generated. In this way, the mean, standard deviation and probability distribution shape parameters of the phase difference at multiple moments generate the first feature corresponding to the first signature, so that the first feature can characterize the pose change of the writing device from aspects such as the mean, standard deviation and probability distribution shape parameters of the phase difference.

[0059] In one embodiment, the input data includes writing position data, and the step of extracting the first feature corresponding to the first signature based on the input data includes: Based on the position data at multiple moments included in the writing position data, the instantaneous velocity and instantaneous acceleration at each moment are calculated respectively; The abrupt change moment is determined based on the instantaneous acceleration at the multiple moments, and the difference between the standard deviation of the acceleration corresponding to the abrupt change moment and the instantaneous acceleration at the multiple moments is greater than a set deviation threshold. Based on the instantaneous velocity at the multiple moments, a velocity density distribution function is generated for the signature region where the first signature is located. The velocity density distribution function is used to characterize the velocity change of the first signature in the signature region. A topology map is generated based on the velocity density distribution function. The topology map is used to characterize the changes in different regions of the two-dimensional terrain when the velocity density distribution function is used as the two-dimensional terrain. The first feature corresponding to the first signature is generated based on the topology map, the instantaneous acceleration at the mutation time point, and the location data of the mutation time point.

[0060] The instantaneous velocity and instantaneous acceleration mentioned above refer to the velocity and acceleration of the writing device within the signature area. It should be noted that instantaneous acceleration differs from three-axis acceleration. Instantaneous acceleration refers to the acceleration of the writing device within the signature area, i.e., the acceleration of the contact point, and is used to determine the positional changes within the signature pattern. Three-axis acceleration, on the other hand, refers to the acceleration of the writing device as a whole in different directions, and is used to determine the pose changes of the writing device.

[0061] The instantaneous velocity and instantaneous acceleration can be calculated using the following formulas: ; ; In the formula, v t Let a be the instantaneous velocity. t For instantaneous acceleration, and The difference between two location data points. This represents the time difference between two location data points.

[0062] Furthermore, determining the abrupt change point based on instantaneous acceleration at multiple moments can be expressed as: , Let be the standard deviation of the instantaneous acceleration at multiple moments. To preset the basic threshold, To set a deviation threshold, after determining the mutation time point, its position (x) is recorded. i ,y i ) and intensity .

[0063] The velocity density distribution function for generating the signature region containing the first signature based on instantaneous velocities at multiple moments can be expressed as an instantaneous velocity v. t Using kernel density estimation as the weight, a continuous velocity density distribution function is generated over the signature region. And calculate its gradient field. .

[0064] Furthermore, a topological graph is generated based on the velocity density distribution function, that is, using the velocity density distribution function... For two-dimensional terrain, a continuous cohomology algorithm is applied to track the terrain at different water levels. The topological changes under the terrain are analyzed to generate a topological map describing the birth and death times of topological features. The birth time is the moment when a certain topological feature appears in a region of the terrain, and the death time is the moment when the topological feature is merged or covered by water level.

[0065] The above-mentioned generation of the first feature corresponding to the first signature based on the topology graph, the instantaneous acceleration at the mutation moment, and the location data at the mutation moment can be achieved by extracting topological invariants, including the maximum persistence length, the average persistence length, and the feature quantity distribution, from the topology graph, and then combining them with the instantaneous acceleration at the mutation moment and the location data at the mutation moment to extract the feature corresponding to the location data.

[0066] In this embodiment of the invention, based on the position data at multiple moments included in the writing position data, the instantaneous velocity and instantaneous acceleration at each moment are calculated respectively; abrupt change moment points are determined based on the instantaneous acceleration at the multiple moments, wherein the difference between the acceleration corresponding to the abrupt change moment point and the standard deviation of the instantaneous acceleration at the multiple moments is greater than a set deviation threshold; a velocity density distribution function is generated for the signature region where the first signature is located based on the instantaneous velocity at the multiple moments, and the velocity density distribution function is used to characterize the velocity change of the first signature in the signature region; a topology map is generated based on the velocity density distribution function, and the topology map is used to characterize the changes in different regions of the two-dimensional terrain when the velocity density distribution function is a two-dimensional terrain; a first feature corresponding to the first signature is generated based on the topology map, the instantaneous acceleration at the abrupt change moment point, and the position data at the abrupt change moment point. Thus, by generating the first feature corresponding to the first signature through the topology map, the instantaneous acceleration at the abrupt change moment point, and the position data at the abrupt change moment point, the first feature can characterize the positional changes in the first signature.

[0067] In one embodiment, generating a verification result based on the first feature and the second feature includes: Calculate the similarity between the first feature and the second feature; The verification result is generated based on the similarity. The step of generating the verification result based on the similarity includes at least one of the following: If the similarity is greater than or equal to a first set similarity threshold, a verification result is generated to characterize that the verification has passed. If the similarity is less than the first set similarity threshold and the similarity is greater than or equal to the second set similarity threshold, a verification result is generated to characterize the verification to be confirmed, wherein the second set similarity threshold is less than the first set similarity threshold. If the similarity is less than the second set similarity threshold, a verification result is generated to characterize the verification failure.

[0068] The first and second set similarity thresholds are used to verify the first signature. The second set similarity threshold is less than the first set similarity threshold, so that data can be verified by the two set similarity thresholds.

[0069] Specifically, when the similarity is less than a first set similarity threshold and the similarity is greater than or equal to a second set similarity threshold, a verification result is generated to represent the verification to be confirmed, so that the user can confirm again, thereby improving the accuracy of the verification.

[0070] In this embodiment of the invention, when the similarity is greater than or equal to a first preset similarity threshold, a verification result is generated to indicate that the verification has passed; when the similarity is less than the first preset similarity threshold and the similarity is greater than or equal to a second preset similarity threshold, a verification result is generated to indicate that the verification is pending confirmation, where the second preset similarity threshold is less than the first preset similarity threshold; when the similarity is less than the second preset similarity threshold, a verification result is generated to indicate that the verification has failed. Thus, by generating verification results using two preset similarity thresholds, the accuracy of the verification is improved.

[0071] In some implementations, a third set similarity threshold can be introduced. When the feature matching degree is higher than the third set similarity threshold but the verification is successful, a model update mechanism is triggered to smoothly and adaptively update the second feature of the second signature using the current data. The third set similarity threshold is lower than the first set similarity threshold.

[0072] In some implementations, during the verification phase, a grid background that has undergone random nonlinear transformation can be presented to the user; the signature written by the user under this deformed background and its corresponding dynamic features can be collected; during subsequent verification, the collected features are compared with a second feature based on the same deformation rule to verify the signature.

[0073] Please see Figure 2 , Figure 2 This is a structural diagram of a signature verification device provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the signature verification device 200 includes: The first acquisition module 201 is used to acquire input data corresponding to the first signature. The input data includes at least one of the pressure data when the first signature is entered, the three-axis acceleration data of the writing device, and the writing position data. Extraction module 202 is used to extract a first feature corresponding to the first signature based on the input data. The first feature is used to characterize at least one of the pressure change when the first signature is input, the posture change of the writing device, and the writing position change. The second acquisition module 203 is used to acquire a second feature corresponding to the second signature. The second feature is used to characterize at least one of the pressure change, the posture change of the writing device, and the writing position change when the second signature is input. The second signature is used to verify the first signature. The second feature is extracted based on the data extracted when writing the second signature. The generation module 204 is used to generate a verification result based on the first feature and the second feature, wherein the verification result is used to characterize whether the first signature and the second signature were written by the same user.

[0074] In one embodiment, the input data includes the pressure data, and the extraction module 202 includes: The processing submodule is used to normalize the multiple pressures included in the pressure data, wherein the multiple pressures are pressure values ​​at multiple times. The first calculation submodule is used to calculate the first-order difference corresponding to each time moment based on multiple pressures after normalization processing. The first-order difference is the difference between the pressure at the corresponding time moment and the pressure at the previous time moment. The second calculation submodule is used to calculate the first pressure and the second pressure of each stroke in the multiple strokes included in the first signature based on the multiple pressures after normalization processing. The first pressure is the pressure at the start position of the corresponding stroke, and the second pressure is the pressure at the end position of the corresponding stroke. The first generation submodule is used to generate a binary code based on the first difference corresponding to the plurality of strokes, wherein the first difference is the difference between the first pressure and the second pressure of the corresponding stroke; The second generation submodule is used to generate the first feature corresponding to the first signature based on the first-order difference corresponding to the plurality of time points and the binary encoding.

[0075] In one embodiment, the signature verification device 200 further includes: The first determining submodule is used to determine multiple peak pressures among the multiple pressures, each peak pressure being greater than the adjacent pressure; The third calculation submodule is used to calculate the pressure change corresponding to each peak pressure, wherein the change is the change between the corresponding peak pressure and the previous peak pressure. The fourth calculation submodule is used to calculate the permutation entropy based on the pressure changes corresponding to the multiple peak pressures, and the permutation entropy is used to characterize the changes of the multiple peak pressures. The second generation submodule includes: The generation unit is used to generate a first feature corresponding to the first signature based on the first-order difference corresponding to the plurality of time points, the binary encoding, and the permutation entropy.

[0076] In one embodiment, the input data includes the triaxial acceleration data, and the extraction module 202 includes: The filtering submodule is used to filter the triaxial acceleration. The filtered triaxial acceleration is within a set frequency range. The filtered triaxial acceleration includes x-axis acceleration, y-axis acceleration and z-axis acceleration at multiple moments. The second determining submodule is used to determine the planar acceleration and the z-axis acceleration corresponding to each moment based on the filtered triaxial acceleration, wherein the planar acceleration is the sum of the x-axis acceleration and the y-axis acceleration at the corresponding moment; The fifth calculation submodule is used to calculate the phase difference at each moment, wherein the phase difference is the difference between the plane phase and the vertical phase at the corresponding moment, the plane phase is calculated from the plane acceleration at the corresponding moment, and the vertical phase is calculated from the z-axis acceleration at the corresponding moment; The sixth calculation submodule is used to calculate the mean, standard deviation and probability distribution shape parameter of the phase difference at the multiple time points, wherein the probability distribution shape parameter is used to characterize the shape of the curve corresponding to the multiple time points; The third generation submodule is used to generate the first feature corresponding to the first signature based on the mean, standard deviation and probability distribution shape parameters of the phase difference at the multiple times.

[0077] In one embodiment, the input data includes writing position data, and the extraction module 202 includes: The seventh calculation submodule is used to calculate the instantaneous velocity and instantaneous acceleration at each moment based on the position data at multiple moments included in the writing position data; The third determining submodule is used to determine the abrupt change time point based on the instantaneous acceleration at the plurality of times, wherein the difference between the acceleration corresponding to the abrupt change time point and the standard deviation of the instantaneous acceleration at the plurality of times is greater than a set deviation threshold. The fourth generation submodule is used to generate a velocity density distribution function of the signature region where the first signature is located based on the instantaneous velocity at the multiple moments. The velocity density distribution function is used to characterize the velocity change of the first signature in the signature region. The fifth generation submodule is used to generate a topology map based on the velocity density distribution function. The topology map is used to characterize the changes in different regions of the two-dimensional terrain when the velocity density distribution function is used as the two-dimensional terrain. The sixth generation submodule is used to generate a first feature corresponding to the first signature based on the topology map, the instantaneous acceleration at the mutation time point, and the location data of the mutation time point.

[0078] In one embodiment, the generation module 204 includes: The eighth calculation submodule is used to calculate the similarity between the first feature and the second feature; The seventh generation submodule is used to generate the verification result based on the similarity. The step of generating the verification result based on the similarity includes at least one of the following: If the similarity is greater than or equal to a first set similarity threshold, a verification result is generated to characterize that the verification has passed. If the similarity is less than the first set similarity threshold and the similarity is greater than or equal to the second set similarity threshold, a verification result is generated to characterize the verification to be confirmed, wherein the second set similarity threshold is less than the first set similarity threshold. If the similarity is less than the second set similarity threshold, a verification result is generated to characterize the verification failure.

[0079] The business processing apparatus provided in this embodiment of the invention can implement each process of each embodiment of the above-described business processing method. The technical features are one-to-one and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0080] It should be noted that the signature verification device in the embodiments of the present invention can be a device, or it can be a component, integrated circuit, or chip in an electronic device.

[0081] This invention also provides an electronic device, including: a processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the above-described functionality. Figure 1 The various processes of the signature verification method embodiment shown herein can achieve the same technical effect, and will not be described again here to avoid repetition.

[0082] For details, see Figure 3 As shown, this embodiment of the invention also provides an electronic device, including a bus 301, a transceiver 302, an antenna 303, a bus interface 304, a processor 305, and a memory 306.

[0083] The transceiver 302 is used to acquire input data corresponding to the first signature. The input data includes at least one of the pressure data when the first signature is entered, the three-axis acceleration data of the writing device, and the writing position data. The processor 305 is configured to extract a first feature corresponding to the first signature based on the input data. The first feature is configured to characterize at least one of the pressure change when the first signature is input, the posture change of the writing device, and the writing position change. The transceiver 302 is further configured to acquire a second feature corresponding to the second signature. The second feature is configured to characterize at least one of the pressure change, the posture change of the writing device, and the writing position change when the second signature is input. The second signature is used to verify the first signature. The second feature is obtained based on the data extracted when the second signature is written. The processor 305 is further configured to generate a verification result based on the first feature and the second feature, the verification result being used to characterize whether the first signature and the second signature were written by the same user.

[0084] In one embodiment, the input data includes the pressure data, and the step of extracting the first feature corresponding to the first signature based on the input data includes: The pressure data includes multiple pressures, which are pressure values ​​at multiple times. The first-order difference for each time moment is calculated based on the normalized pressures. The first-order difference is the difference between the pressure at the corresponding time moment and the pressure at the previous time moment. Based on the normalized multiple pressures, calculate the first pressure and the second pressure of each stroke in the multiple strokes included in the first signature. The first pressure is the pressure at the start position of the corresponding stroke, and the second pressure is the pressure at the end position of the corresponding stroke. A binary code is generated based on the first difference corresponding to the plurality of strokes, wherein the first difference is the difference between the first pressure and the second pressure of the corresponding stroke; The first feature corresponding to the first signature is generated based on the first-order difference corresponding to the multiple time points and the binary encoding.

[0085] In one embodiment, the processor 305 is further configured to determine a plurality of peak pressures among the plurality of pressures, each peak pressure being greater than the adjacent pressure; The processor 305 is further configured to calculate the pressure change corresponding to each peak pressure, wherein the change is the change between the corresponding peak pressure and the previous peak pressure. The processor 305 is further configured to calculate the arrangement entropy based on the pressure change corresponding to the plurality of peak pressures, wherein the arrangement entropy is used to characterize the change of the plurality of peak pressures. The step of generating the first feature corresponding to the first signature based on the first-order difference corresponding to the plurality of time points and the binary encoding includes: The first feature corresponding to the first signature is generated based on the first-order difference corresponding to the multiple time points, the binary encoding, and the permutation entropy.

[0086] In one embodiment, the input data includes the triaxial acceleration data, and the step of extracting the first feature corresponding to the first signature based on the input data includes: The triaxial acceleration is filtered, and the filtered triaxial acceleration is within a set frequency range. The filtered triaxial acceleration includes x-axis acceleration, y-axis acceleration and z-axis acceleration at multiple moments. Based on the filtered triaxial accelerations, the planar acceleration and z-axis acceleration corresponding to each moment are determined, wherein the planar acceleration is the sum of the x-axis acceleration and y-axis acceleration at the corresponding moment; Calculate the phase difference at each moment, where the phase difference is the difference between the plane phase and the vertical phase at the corresponding moment, the plane phase is calculated from the plane acceleration at the corresponding moment, and the vertical phase is calculated from the z-axis acceleration at the corresponding moment; Calculate the mean, standard deviation, and probability distribution shape parameter of the phase difference at the multiple time points, wherein the probability distribution shape parameter is used to characterize the shape of the curve corresponding to the multiple time points; The first feature corresponding to the first signature is generated based on the mean, standard deviation, and probability distribution shape parameters of the phase difference at the multiple time points.

[0087] In one embodiment, the input data includes writing position data, and the step of extracting the first feature corresponding to the first signature based on the input data includes: Based on the position data at multiple moments included in the writing position data, the instantaneous velocity and instantaneous acceleration at each moment are calculated respectively; The abrupt change moment is determined based on the instantaneous acceleration at the multiple moments, and the difference between the standard deviation of the acceleration corresponding to the abrupt change moment and the instantaneous acceleration at the multiple moments is greater than a set deviation threshold. Based on the instantaneous velocity at the multiple moments, a velocity density distribution function is generated for the signature region where the first signature is located. The velocity density distribution function is used to characterize the velocity change of the first signature in the signature region. A topology map is generated based on the velocity density distribution function. The topology map is used to characterize the changes in different regions of the two-dimensional terrain when the velocity density distribution function is used as the two-dimensional terrain. The first feature corresponding to the first signature is generated based on the topology map, the instantaneous acceleration at the mutation time point, and the location data of the mutation time point.

[0088] In one embodiment, generating a verification result based on the first feature and the second feature includes: Calculate the similarity between the first feature and the second feature; The verification result is generated based on the similarity. The step of generating the verification result based on the similarity includes at least one of the following: If the similarity is greater than or equal to a first set similarity threshold, a verification result is generated to characterize that the verification has passed. If the similarity is less than the first set similarity threshold and the similarity is greater than or equal to the second set similarity threshold, a verification result is generated to characterize the verification to be confirmed, wherein the second set similarity threshold is less than the first set similarity threshold. If the similarity is less than the second set similarity threshold, a verification result is generated to characterize the verification failure.

[0089] exist Figure 3 In this context, a bus architecture (represented by bus 301) is used. Bus 301 can include any number of interconnected buses and bridges, linking various circuits including one or more processors represented by processor 305 and memory represented by memory 306. Bus 301 can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 304 provides an interface between bus 301 and transceiver 302. Transceiver 302 can be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by processor 305 is transmitted over a wireless medium via antenna 303, which further receives data and transmits it to processor 305.

[0090] Processor 305 manages bus 301 and general processing, and also provides various functions, including timing, peripheral interface, voltage regulation, power management, and other control functions. Memory 306 can be used to store data used by processor 305 during operation.

[0091] Optionally, the processor 305 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a graphics processing unit (GPU).

[0092] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the above-described functions. Figure 1 The various processes corresponding to the signature verification method embodiments achieve the same technical effect, and will not be described again here to avoid repetition. The computer-readable storage medium mentioned includes, for example, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0093] The present invention also provides a computer program product, including computer instructions that, when executed by a processor, implement the above-described... Figure 1 The various processes corresponding to the signature verification method embodiments can achieve the same technical effect, and will not be described again here to avoid repetition.

[0094] In the embodiments of this invention, the terms "first," "second," etc., are used to distinguish similar object parameters and are not necessarily used to describe a specific order or sequence. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or devices. Additionally, the use of "and / or" in this application indicates at least one of the connected object parameters, such as A and / or B and / or C, representing seven possibilities: A alone, B alone, C alone, both A and B present, both B and C present, both A and C present, and A, B, and C present.

[0095] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0096] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, etc.) to execute the methods of the various embodiments of this application.

[0097] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A signature verification method, characterized in that, include: Obtain input data corresponding to the first signature, wherein the input data includes at least one of the pressure data when inputting the first signature, the three-axis acceleration data of the writing device, and the writing position data; Based on the input data, a first feature corresponding to the first signature is extracted. The first feature is used to characterize at least one of the pressure change, the posture change of the writing device, and the writing position change when the first signature is input. Obtain a second feature corresponding to the second signature. The second feature is used to characterize at least one of the pressure change, the posture change of the writing device, and the writing position change when the second signature is input. The second signature is used to verify the first signature. The second feature is extracted based on the data extracted when writing the second signature. A verification result is generated based on the first feature and the second feature. The verification result is used to characterize whether the first signature and the second signature were written by the same user.

2. The method as described in claim 1, characterized in that, The input data includes the pressure data, and the step of extracting the first feature corresponding to the first signature based on the input data includes: The pressure data includes multiple pressures, which are pressure values ​​at multiple times. The first-order difference for each time moment is calculated based on the normalized pressures. The first-order difference is the difference between the pressure at the corresponding time moment and the pressure at the previous time moment. Based on the normalized multiple pressures, calculate the first pressure and the second pressure of each stroke in the multiple strokes included in the first signature. The first pressure is the pressure at the start position of the corresponding stroke, and the second pressure is the pressure at the end position of the corresponding stroke. A binary code is generated based on the first difference corresponding to the plurality of strokes, wherein the first difference is the difference between the first pressure and the second pressure of the corresponding stroke; The first feature corresponding to the first signature is generated based on the first-order difference corresponding to the multiple time points and the binary encoding.

3. The method as described in claim 2, characterized in that, The method further includes: Determine multiple peak pressures among the plurality of pressures, each peak pressure being greater than its adjacent pressure; Calculate the pressure change corresponding to each peak pressure, where the change is the change between the corresponding peak pressure and the previous peak pressure. The permutation entropy is calculated based on the pressure changes corresponding to the multiple peak pressures, and the permutation entropy is used to characterize the changes of the multiple peak pressures. The step of generating the first feature corresponding to the first signature based on the first-order difference corresponding to the plurality of time points and the binary encoding includes: The first feature corresponding to the first signature is generated based on the first-order difference corresponding to the multiple time points, the binary encoding, and the permutation entropy.

4. The method according to any one of claims 1 to 3, characterized in that, The input data includes the triaxial acceleration data, and the step of extracting the first feature corresponding to the first signature based on the input data includes: The triaxial acceleration is filtered, and the filtered triaxial acceleration is within a set frequency range. The filtered triaxial acceleration includes x-axis acceleration, y-axis acceleration and z-axis acceleration at multiple moments. Based on the filtered triaxial accelerations, the planar acceleration and z-axis acceleration corresponding to each moment are determined, wherein the planar acceleration is the sum of the x-axis acceleration and y-axis acceleration at the corresponding moment; Calculate the phase difference at each moment, where the phase difference is the difference between the plane phase and the vertical phase at the corresponding moment, the plane phase is calculated from the plane acceleration at the corresponding moment, and the vertical phase is calculated from the z-axis acceleration at the corresponding moment; Calculate the mean, standard deviation, and probability distribution shape parameter of the phase difference at the multiple time points, wherein the probability distribution shape parameter is used to characterize the shape of the curve corresponding to the multiple time points; The first feature corresponding to the first signature is generated based on the mean, standard deviation, and probability distribution shape parameters of the phase difference at the multiple time points.

5. The method according to any one of claims 1 to 3, characterized in that, The input data includes writing position data, and the step of extracting the first feature corresponding to the first signature based on the input data includes: Based on the position data at multiple moments included in the writing position data, the instantaneous velocity and instantaneous acceleration at each moment are calculated respectively; The abrupt change moment is determined based on the instantaneous acceleration at the multiple moments, and the difference between the standard deviation of the acceleration corresponding to the abrupt change moment and the instantaneous acceleration at the multiple moments is greater than a set deviation threshold. Based on the instantaneous velocity at the multiple moments, a velocity density distribution function is generated for the signature region where the first signature is located. The velocity density distribution function is used to characterize the velocity change of the first signature in the signature region. A topology map is generated based on the velocity density distribution function. The topology map is used to characterize the changes in different regions of the two-dimensional terrain when the velocity density distribution function is used as the two-dimensional terrain. The first feature corresponding to the first signature is generated based on the topology map, the instantaneous acceleration at the mutation time point, and the location data of the mutation time point.

6. The method according to any one of claims 1 to 3, characterized in that, The generation of verification results based on the first feature and the second feature includes: Calculate the similarity between the first feature and the second feature; The verification result is generated based on the similarity. The step of generating the verification result based on the similarity includes at least one of the following: If the similarity is greater than or equal to a first set similarity threshold, a verification result is generated to characterize that the verification has passed. If the similarity is less than the first set similarity threshold and the similarity is greater than or equal to the second set similarity threshold, a verification result is generated to characterize the verification to be confirmed, wherein the second set similarity threshold is less than the first set similarity threshold. If the similarity is less than the second set similarity threshold, a verification result is generated to characterize the verification failure.

7. A signature verification device, characterized in that, include: The first acquisition module is used to acquire input data corresponding to the first signature. The input data includes at least one of the pressure data when the first signature is entered, the three-axis acceleration data of the writing device, and the writing position data. The extraction module is used to extract a first feature corresponding to the first signature based on the input data. The first feature is used to characterize at least one of the pressure change when the first signature is input, the posture change of the writing device, and the writing position change. The second acquisition module is used to acquire a second feature corresponding to the second signature. The second feature is used to characterize at least one of the pressure change, the posture change of the writing device, and the writing position change when the second signature is input. The second signature is used to verify the first signature. The second feature is extracted based on the data extracted when writing the second signature. The generation module is used to generate a verification result based on the first feature and the second feature, wherein the verification result is used to characterize whether the first signature and the second signature were written by the same user.

8. An electronic device, characterized in that, include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the steps of the signature verification method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the signature verification method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, It includes computer instructions that, when executed by a processor, implement the steps of the signature verification method as described in any one of claims 1 to 6.

Images