Bank Online Handwritten Signature Authentication Method and Related Devices

Abstract

The present application provides a method and related device for online handwritten signature authentication of banks, which can be applied to the field of cloud computing or the financial field; the target user information and handwritten signature information of the target user are collected through an online device, wherein the handwritten signature information includes signature picture information, timing coordinate information and timing pressure information; according to the target user information, the target handwritten signature information of the target user is obtained, wherein the target handwritten signature information includes target signature picture information, target timing coordinate information and target timing pressure information; according to the signature picture information, timing coordinate information, timing pressure information, target signature picture information, target timing coordinate information and target timing pressure information, the signature similarity of the target user is calculated; if the signature similarity of the target user is greater than a preset similarity threshold, it is determined that the handwritten signature verification of the target user is passed.

Description

Technical Field

[0001] The present invention relates to the technical field of identity authentication, and more specifically to a bank online handwritten signature identity authentication method and related equipment. Background Art

[0002] With the rapid development of paperless office and artificial intelligence technology, handwritten signature verification is widely used in banking and other industries.

[0003] In the prior art, the user's current handwritten signature image is collected and compared with the pre-stored handwritten signature image. However, the accuracy of this comparison method is low, and the existing handwritten signature verification method is performed offline, which takes up a certain amount of counter processing time. Summary of the invention

[0004] In view of this, the present invention provides a bank online handwritten signature identity verification method and related equipment to solve the problems of low accuracy of handwritten signature verification and taking up a certain counter processing time in the prior art.

[0005] The first aspect of the present invention discloses a bank online handwritten signature identity authentication method, the method comprising:

[0006] Collecting target user information and handwritten signature information of a target user through an online device, wherein the handwritten signature information includes signature image information, time sequence coordinate information, and time sequence pressure information;

[0007] According to the target user information, obtaining the target handwritten signature information of the target user, wherein the target handwritten signature information includes target signature picture information, target time sequence coordinate information and target time sequence pressure information;

[0008] Calculating the signature similarity of the target user according to the signature image information, the time sequence coordinate information, the time sequence pressure information, the target signature image information, the target time sequence coordinate information and the target time sequence pressure information;

[0009] If the signature similarity of the target user is greater than a preset similarity threshold, it is determined that the handwritten signature verification of the target user has passed.

[0010] Optionally, calculating the signature similarity of the target user according to the signature image information, the time sequence coordinate information, the time sequence pressure information, the target signature image information, the target time sequence coordinate information and the target time sequence pressure information includes:

[0011] Extracting behavior features from the signature image information, extracting coordinate distribution range features, coordinate change trend features and signature speed features from the time series coordinate information, and extracting pressure distribution range features, pressure change trend features, pen drop angle distribution range features and pen drop angle change trend features from the time series pressure information;

[0012] Extract target behavior features from the target signature image information, extract target coordinate distribution range features, target coordinate change trend features and target signature speed features from the target time series coordinate information, and extract target pressure distribution range features, target pressure change trend features, target pen drop angle distribution range features and target pen drop angle change trend features from the target time series pressure information;

[0013] Calculating the signature image similarity between the signature image and the target signature image according to the behavior feature and the target behavior feature;

[0014] Calculating the time series coordinate similarity according to the coordinate distribution range feature, the coordinate change trend feature, the signature speed feature, the target coordinate distribution range feature, the target coordinate change trend feature and the target signature speed feature;

[0015] Calculate the temporal pressure similarity according to the pressure distribution range feature, the pressure change trend feature, the pen drop angle distribution range feature, the pen drop angle change trend feature, the target pressure distribution range feature, the target pressure change trend feature, the target pen drop angle distribution range feature, and the target pen drop angle change trend feature;

[0016] The signature similarity of the target user is calculated according to the signature image similarity, the temporal coordinate similarity and the temporal pressure similarity.

[0017] Optionally, calculating the signature image similarity between the signature image and the target signature image according to the behavior feature and the target behavior feature includes:

[0018] inputting the behavior feature and the target behavior feature into a behavior similarity calculation model, so that the behavior similarity calculation model calculates the signature image similarity between the signature image and the target signature image according to the behavior feature and the target behavior feature;

[0019] The behavior similarity calculation model is obtained by training the neural network to be trained using the historical signature image information and the corresponding target signature image information.

[0020] Optionally, calculating the time series coordinate similarity according to the coordinate distribution range feature, the coordinate change trend feature, the signature speed feature, the target coordinate distribution range feature, the target coordinate change trend feature and the target signature speed feature includes:

[0021] Input the coordinate distribution range feature, the coordinate change trend feature, the signature speed feature, the target coordinate distribution range feature, the target coordinate change trend feature and the target signature speed feature into a time series coordinate similarity calculation model;

[0022] Calculate the time series coordinate similarity through the time series coordinate similarity calculation model according to the coordinate distribution range characteristics, the coordinate change trend characteristics, the signature speed characteristics, the target coordinate distribution range characteristics, the target coordinate change trend characteristics and the target signature speed characteristics;

[0023] The time series coordinate similarity calculation model is obtained by training the neural network to be trained using the historical time series coordinate information and its corresponding target time series coordinate information.

[0024] Optionally, calculating the temporal pressure similarity according to the pressure distribution range feature, the pressure change trend feature, the pen drop angle distribution range feature, the pen drop angle change trend feature, the target pressure distribution range feature, the target pressure change trend feature, the target pen drop angle distribution range feature, and the target pen drop angle change trend feature includes:

[0025] Input the pressure distribution range feature, the pressure change trend feature, the pen drop angle distribution range feature, the pen drop angle change trend feature, the target pressure distribution range feature, the target pressure change trend feature, the target pen drop angle distribution range feature and the target pen drop angle change trend feature into a pressure similarity calculation model;

[0026] Calculating the time series pressure similarity through the time series pressure similarity calculation model according to the pressure distribution range feature, the pressure change trend feature, the pen drop angle distribution range feature, the pen drop angle change trend feature, the target pressure distribution range feature, the target pressure change trend feature, the target pen drop angle distribution range feature and the target pen drop angle change trend feature;

[0027] Among them, the time series similarity calculation model is obtained by training the neural network to be trained using the historical time series information and its corresponding target time series information.

[0028] The second aspect of the present invention discloses a bank online handwritten signature identity authentication system, the system comprising:

[0029] A data collection unit, used to collect target user information and handwritten signature information of a target user through an online device, wherein the handwritten signature information includes signature image information, time sequence coordinate information and time sequence pressure information;

[0030] A target handwritten signature information acquisition unit, configured to acquire the target handwritten signature information of the target user according to the target user information, wherein the target handwritten signature information includes target signature image information, target time series coordinate information and target time series pressure information;

[0031] A signature similarity calculation unit, configured to calculate the signature similarity of the target user according to the signature image information, the time series coordinate information, the time series pressure information, the target signature image information, the target time series coordinate information and the target time series pressure information;

[0032] The verification pass determination unit is used to determine that the handwritten signature of the target user has been verified if the signature similarity of the target user is greater than a preset similarity threshold.

[0033] Optionally, the signature similarity calculation unit includes:

[0034] A first feature extraction unit is used to extract behavior features from the signature image information, extract coordinate distribution range features, coordinate change trend features and signature speed features from the time series coordinate information, and extract pressure distribution range features, pressure change trend features, pen drop angle distribution range features and pen drop angle change trend features from the time series pressure information;

[0035] A second feature extraction unit is used to extract target behavior features from the target signature image information, extract target coordinate distribution range features, target coordinate change trend features and target signature speed features from the target time series coordinate information, and extract target pressure distribution range features, target pressure change trend features, target pen drop angle distribution range features and target pen drop angle change trend features from the target time series pressure information;

[0036] a signature picture similarity calculation unit, used to calculate the signature picture similarity between the signature picture and the target signature picture according to the behavior feature and the target behavior feature;

[0037] A time series coordinate similarity calculation unit, used to calculate the time series coordinate similarity according to the coordinate distribution range feature, the coordinate change trend feature, the signature speed feature, the target coordinate distribution range feature, the target coordinate change trend feature and the target signature speed feature;

[0038] a time series pressure similarity calculation unit, configured to calculate the time series pressure similarity according to the pressure distribution range feature, the pressure change trend feature, the pen drop angle distribution range feature, the pen drop angle change trend feature, the target pressure distribution range feature, the target pressure change trend feature, the target pen drop angle distribution range feature, and the target pen drop angle change trend feature;

[0039] The signature similarity calculation subunit is used to calculate the signature similarity of the target user according to the signature image similarity, the time series coordinate similarity and the time series pressure similarity.

[0040] Optionally, the signature image similarity calculation unit includes:

[0041] a signature picture similarity calculation subunit, configured to input the behavior feature and the target behavior feature into a behavior similarity calculation model, so that the behavior similarity calculation model calculates the signature picture similarity between the signature picture and the target signature picture according to the behavior feature and the target behavior feature;

[0042] The behavior similarity calculation model is obtained by training the neural network to be trained using the historical signature image information and the corresponding target signature image information.

[0043] The third aspect of the present invention discloses an electronic device, characterized in that the electronic device includes a processor and a memory, the memory is used to store program code and data for bank online handwritten signature identity authentication, and the processor is used to call the program instructions in the memory to execute a bank online handwritten signature identity authentication method as disclosed in the first aspect of the present invention.

[0044] The fourth aspect of the present invention discloses a storage medium, which includes a storage program, wherein when the program is running, the device where the storage medium is located is controlled to execute a bank online handwritten signature identity authentication method disclosed in the first aspect of the present invention.

[0045] The present invention provides a bank online handwritten signature identity authentication method and related equipment, which collects target user information and handwritten signature information of a target user through an online device, wherein the handwritten signature information includes signature picture information, time sequence coordinate information and time sequence pressure information; obtains target handwritten signature information of the target user according to the target user information, wherein the target handwritten signature information includes target signature picture information, target time sequence coordinate information and target time sequence pressure information; calculates the signature similarity of the target user according to the signature picture information, the time sequence coordinate information, the time sequence pressure information, the target signature picture information, the target time sequence coordinate information and the target time sequence pressure information; and determines that the handwritten signature verification of the target user is passed if the signature similarity of the target user is greater than a preset similarity threshold. The technical solution provided by the present invention calculates the signature similarity of the target user based on the signature image information, the time series coordinate information, the time series pressure information, the target signature image information, the target time series coordinate information and the target time series pressure information, instead of just comparing the collected handwritten signature image with the pre-stored handwritten signature image as in the prior art. This not only improves the accuracy of signature comparison, but the present invention also collects the user's handwritten signature information online, thereby reducing the counter processing time. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0047] Figure 1 A schematic diagram of a flow chart of a bank online handwritten signature identity authentication method provided by an embodiment of the present invention;

[0048] Figure 2 A schematic diagram of the structure of a bank online handwritten signature identity authentication system provided by an embodiment of the present invention;

[0049] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] In this application, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0052] It should be noted that the bank online handwritten signature identity authentication method provided by the present invention can be used in the field of cloud computing, big data, data processing technology or finance. The above is only an example and does not limit the application field of the bank online handwritten signature identity authentication provided by the present invention.

[0053] See also Figure 1 , shows a schematic diagram of a flow chart of a bank online handwritten signature identity authentication method provided by an embodiment of the present invention, and the bank online handwritten signature identity authentication method specifically includes the following steps:

[0054] S101: collecting target user information and handwritten signature information of a target user through an online device, wherein the handwritten signature information includes signature image information, time sequence coordinate information, and time sequence pressure information.

[0055] In the specific process of executing step S101, the handwritten signature information signed by the user on the online device and the target user information of the target user are collected through the preset online device.

[0056] It should be noted that the pre-set online device is composed of pre-set standard hardware and software.

[0057] In an embodiment of the present application, the handwritten signature information includes signature image information, time sequence coordinate information and time sequence pressure information.

[0058] It should be noted that the timing coordinate information includes multiple signature times t sorted by time, and the x-coordinate and y-coordinate at each signature time t; the timing pressure information includes multiple signature times t sorted by time, and the pressure p and pen-falling angle at each signature time t.

[0059] S102: Acquire target handwritten signature information of the target user according to the target user information, wherein the target handwritten signature information includes target signature image information, target time series coordinate information, and target time series pressure information.

[0060] In an embodiment of the present application, for each user who comes to the bank to handle business, the user's handwritten signature information and the user's user information can be collected in advance, and the user's handwritten signature information and user information can be bound and stored in a database.

[0061] In the specific process of executing step S102, after the target user information of the target user is collected, the corresponding handwritten signature information of the target user can be obtained from the database according to the target user information (for easy distinction, the handwritten signature information of the target user is referred to as target handwritten signature information).

[0062] S103: Calculate the signature similarity of the target user according to the signature image information, the time sequence coordinate information, the time sequence pressure information, the target signature image information, the target time sequence coordinate information and the target time sequence pressure information.

[0063] In the specific process of executing step S103, after obtaining the handwritten signature information of the target user and the corresponding target handwritten signature information, behavioral features can be extracted from the signature image information in the handwritten signature information of the target user, coordinate distribution range features, coordinate change trend features and signature speed features can be extracted from the time series coordinate information, and pressure distribution range features, pressure change trend features, pen-falling angle distribution range features and pen-falling angle change trend features can be extracted from the time series pressure information.

[0064] Target behavior features are extracted from the target signature image information of the corresponding target handwritten signature information; target coordinate distribution range features, target coordinate change trend features and target signature speed features are extracted from the target time series coordinate information; target pressure distribution range features, target pressure change trend features, target pen-falling angle distribution range features and target pen-falling angle change trend features are extracted from the target time series pressure information.

[0065] According to the behavior characteristics and the target behavior characteristics, the signature image similarity between the signature image and the target signature image is calculated; according to the coordinate distribution range characteristics, the coordinate change trend characteristics, the signature speed characteristics, the target coordinate distribution range characteristics, the target coordinate change trend characteristics and the target signature speed characteristics, the time series coordinate similarity is calculated; according to the pressure distribution range characteristics, the pressure change trend characteristics, the pen-falling angle distribution range characteristics, the pen-falling angle change trend characteristics, the target pressure distribution range characteristics, the target pressure change trend characteristics, the target pen-falling angle distribution range characteristics and the target pen-falling angle change trend characteristics, the time series pressure similarity is calculated; according to the signature image similarity, the time series coordinate similarity and the time series pressure similarity, the signature similarity of the target user is calculated.

[0066] Optionally, the neural network to be trained may be pre-trained using historical signature image information and the corresponding target signature image information to obtain a behavior similarity calculation model; the behavior characteristics and the target behavior characteristics are input into the behavior similarity calculation model so that the behavior similarity calculation model calculates the signature image similarity between the signature image and the target signature image based on the behavior characteristics and the target behavior characteristics.

[0067] Optionally, the neural network to be trained is pre-trained using historical time series coordinate information and its corresponding target time series coordinate information to obtain a time series coordinate similarity calculation model; the coordinate distribution range characteristics, coordinate change trend characteristics, signature speed characteristics, target coordinate distribution range characteristics, target coordinate change trend characteristics and target signature speed characteristics are input into the time series coordinate similarity calculation model; the time series coordinate similarity is calculated through the time series coordinate similarity calculation model based on the coordinate distribution range characteristics, coordinate change trend characteristics, signature speed characteristics, target coordinate distribution range characteristics, target coordinate change trend characteristics and target signature speed characteristics.

[0068] Optionally, the neural network to be trained is pre-trained using historical time series information and its corresponding target time series information to obtain a time series similarity calculation model; the pressure distribution range characteristics, pressure change trend characteristics, pen drop angle distribution range characteristics, pen drop angle change trend characteristics, target pressure distribution range characteristics, target pressure change trend characteristics, target pen drop angle distribution range characteristics and target pen drop angle change trend characteristics are input into the pressure similarity calculation model; the time series pressure similarity calculation model is used to calculate the time series pressure similarity based on the pressure distribution range characteristics, pressure change trend characteristics, pen drop angle distribution range characteristics, pen drop angle change trend characteristics, target pressure distribution range characteristics, target pressure change trend characteristics, target pen drop angle distribution range characteristics and target pen drop angle change trend characteristics.

[0069] In the embodiment of the present application, the historical handwritten signature information of the historical user and the corresponding target handwritten signature information can be obtained in advance. The historical handwritten signature information includes historical signature image information, historical time sequence coordinate information and historical time sequence pressure information; the target handwritten signature information includes target signature image information, target time sequence coordinate information and target time sequence pressure information.

[0070] The historical behavior features are extracted from the historical signature image information, and the historical target behavior features are extracted from the target signature image information. The historical behavior features and the target behavior features are input into the neural network to be trained, and the historical signature image similarity is calculated by the neural network to be trained using the historical behavior features and the target behavior features, and the corresponding loss function is constructed using the historical signature image similarity and the historical target signature image similarity corresponding thereto, so as to adjust the parameters of the neural network to be trained using the loss function until the neural network to be trained reaches convergence, and a behavior similarity calculation model is obtained.

[0071] The historical coordinate distribution range feature, the historical coordinate change trend feature and the historical signature speed feature are extracted from the historical time series coordinate information, and the target coordinate distribution range feature, the target coordinate change trend feature and the target signature speed feature are extracted from the target time series coordinate information. The historical coordinate distribution range feature, the historical coordinate change trend feature, the historical signature speed feature, the target coordinate distribution range feature, the target coordinate change trend feature and the target signature speed feature are input into the neural network to be trained, and the historical time series coordinate similarity is calculated by the neural network to be trained using the historical coordinate distribution range feature, the historical coordinate change trend feature, the historical signature speed feature, the target coordinate distribution range feature, the target coordinate change trend feature and the target signature speed feature, and the corresponding loss function is constructed using the historical time series coordinate similarity and the corresponding historical target time series coordinate similarity, so as to use the loss function to adjust the parameters of the neural network to be trained until the neural network to be trained reaches convergence, and a behavior time series coordinate similarity calculation model is obtained.

[0072] The historical pressure distribution range characteristics, historical pressure change trend characteristics, historical pen-falling angle distribution range characteristics and historical pen-falling angle change trend characteristics are extracted from the historical time-series pressure information; the target pressure distribution range characteristics, target pressure change trend characteristics, target pen-falling angle distribution range characteristics and target pen-falling angle change trend characteristics are extracted from the target time-series pressure information. The historical pressure distribution range characteristics, historical pressure change trend characteristics, historical pen-falling angle distribution range characteristics, historical pen-falling angle change trend characteristics, target pressure distribution range characteristics, target pressure change trend characteristics, target pen-falling angle distribution range characteristics and target pen-falling angle change trend characteristics extracted from the historical time series pressure information are input into the neural network to be trained, and the historical time series pressure similarity is calculated by the neural network to be trained using the historical pressure distribution range characteristics, historical pressure change trend characteristics, historical pen-falling angle distribution range characteristics, historical pen-falling angle change trend characteristics, target pressure distribution range characteristics, target pressure change trend characteristics, target pen-falling angle distribution range characteristics and target pen-falling angle change trend characteristics extracted from the historical time series pressure information, and a corresponding loss function is constructed using the historical time series pressure similarity and the corresponding historical target time series pressure similarity, so as to use the loss function to adjust the parameters of the neural network to be trained until the neural network to be trained converges, and a behavior time series pressure similarity calculation model is obtained.

[0073] S104: Determine whether the target user's signature similarity is greater than a preset similarity threshold; if the target user's signature similarity is greater than the preset similarity threshold, execute step S105; if the target user's signature similarity is not greater than the preset similarity threshold, execute step S106.

[0074] In the specific execution process of step S104, a preset similarity threshold is pre-set. After calculating the signature similarity between the target user's current handwritten signature information and the target handwritten signature information, it can be determined whether the target user's handwritten signature verification passes based on the signature similarity and the preset similarity threshold.

[0075] Specifically, it is determined whether the signature similarity is greater than a preset similarity threshold. If so, it can be determined that the target user's handwritten signature verification has passed, that is, the target user's identity verification has passed. If not, it can be determined that the target user's handwritten signature verification has failed, that is, the target user's identity verification has failed.

[0076] In the embodiment of the present application, when it is determined that the identity authentication of the target user fails, corresponding alarm information can also be output.

[0077] S105: Determine whether the handwritten signature of the target user has been verified.

[0078] S106: Determine whether the handwritten signature verification of the target user is easy to pass.

[0079] The present invention provides a bank online handwritten signature identity authentication method, which collects target user information and handwritten signature information of a target user through an online device, wherein the handwritten signature information includes signature picture information, time sequence coordinate information and time sequence pressure information; obtains target handwritten signature information of the target user according to the target user information, wherein the target handwritten signature information includes target signature picture information, target time sequence coordinate information and target time sequence pressure information; calculates the signature similarity of the target user according to the signature picture information, time sequence coordinate information, time sequence pressure information, target signature picture information, target time sequence coordinate information and target time sequence pressure information; and determines that the handwritten signature verification of the target user is passed if the signature similarity of the target user is greater than a preset similarity threshold. The technical solution provided by the present invention calculates the signature similarity of the target user based on signature image information, temporal coordinate information, temporal pressure information, target signature image information, target temporal coordinate information and target temporal pressure information, instead of simply comparing the collected handwritten signature image with the pre-stored handwritten signature image as in the prior art. This not only improves the accuracy of signature comparison, but the present invention also collects the user's handwritten signature information online, thereby reducing the counter processing time.

[0080] Corresponding to the bank online handwritten signature identity authentication method disclosed in the above embodiment of the present invention, the embodiment of the present invention also provides a bank online handwritten signature identity authentication system, such as Figure 2 As shown, the system includes:

[0081] The data collection unit 21 is used to collect the target user information and handwritten signature information of the target user through the online device, wherein the handwritten signature information includes signature image information, time series coordinate information and time series pressure information;

[0082] The target handwritten signature information acquisition unit 22 is used to acquire the target handwritten signature information of the target user according to the target user information, wherein the target handwritten signature information includes the target signature image information, the target time sequence coordinate information and the target time sequence pressure information;

[0083] The signature similarity calculation unit 23 is used to calculate the signature similarity of the target user according to the signature image information, the time sequence coordinate information, the time sequence pressure information, the target signature image information, the target time sequence coordinate information and the target time sequence pressure information;

[0084] The verification pass determination unit 24 is used to determine that the handwritten signature of the target user has been verified if the signature similarity of the target user is greater than a preset similarity threshold.

[0085] The specific principles and execution processes of each unit in the bank online handwritten signature identity authentication system disclosed in the above embodiment of the present invention are similar to those in the above embodiment of the present invention. Figure 1 The public bank online handwritten signature identity authentication method is the same, and can refer to the above embodiment of the present invention. Figure 1 The corresponding parts of the public bank's online handwritten signature identity authentication method will not be repeated here.

[0086] The present invention provides a bank online handwritten signature identity authentication system, which collects target user information and handwritten signature information of a target user through an online device, wherein the handwritten signature information includes signature picture information, time sequence coordinate information and time sequence pressure information; obtains target handwritten signature information of the target user according to the target user information, wherein the target handwritten signature information includes target signature picture information, target time sequence coordinate information and target time sequence pressure information; calculates the signature similarity of the target user according to the signature picture information, time sequence coordinate information, time sequence pressure information, target signature picture information, target time sequence coordinate information and target time sequence pressure information; and determines that the handwritten signature verification of the target user is passed if the signature similarity of the target user is greater than a preset similarity threshold. The technical solution provided by the present invention calculates the signature similarity of the target user based on signature image information, temporal coordinate information, temporal pressure information, target signature image information, target temporal coordinate information and target temporal pressure information, instead of simply comparing the collected handwritten signature image with the pre-stored handwritten signature image as in the prior art. This not only improves the accuracy of signature comparison, but the present invention also collects the user's handwritten signature information online, thereby reducing the counter processing time.

[0087] Optionally, the signature similarity calculation unit includes:

[0088] A first feature extraction unit is used to extract behavior features from signature image information, extract coordinate distribution range features, coordinate change trend features and signature speed features from time series coordinate information, and extract pressure distribution range features, pressure change trend features, pen drop angle distribution range features and pen drop angle change trend features from time series pressure information;

[0089] A second feature extraction unit is used to extract target behavior features from the target signature image information, extract target coordinate distribution range features, target coordinate change trend features and target signature speed features from the target time series coordinate information, and extract target pressure distribution range features, target pressure change trend features, target pen drop angle distribution range features and target pen drop angle change trend features from the target time series pressure information;

[0090] A signature image similarity calculation unit, used to calculate the signature image similarity between the signature image and the target signature image according to the behavior characteristics and the target behavior characteristics;

[0091] A time series coordinate similarity calculation unit, used to calculate the time series coordinate similarity according to the coordinate distribution range characteristics, coordinate change trend characteristics, signature speed characteristics, target coordinate distribution range characteristics, target coordinate change trend characteristics and target signature speed characteristics;

[0092] A time series pressure similarity calculation unit, used to calculate the time series pressure similarity according to the pressure distribution range characteristics, the pressure change trend characteristics, the pen drop angle distribution range characteristics, the pen drop angle change trend characteristics, the target pressure distribution range characteristics, the target pressure change trend characteristics, the target pen drop angle distribution range characteristics and the target pen drop angle change trend characteristics;

[0093] The signature similarity calculation subunit is used to calculate the signature similarity of the target user according to the signature image similarity, the time series coordinate similarity and the time series pressure similarity.

[0094] Optionally, the signature image similarity calculation unit includes:

[0095] The signature image similarity calculation subunit is used to input the behavior characteristics and the target behavior characteristics into the behavior similarity calculation model, so that the behavior similarity calculation model calculates the signature image similarity between the signature image and the target signature image according to the behavior characteristics and the target behavior characteristics;

[0096] Among them, the behavior similarity calculation model is obtained by training the neural network to be trained using the historical signature image information and the corresponding target signature image information.

[0097] Optionally, the time series coordinate similarity calculation unit includes:

[0098] A first input unit is used to input the coordinate distribution range feature, the coordinate change trend feature, the signature speed feature, the target coordinate distribution range feature, the target coordinate change trend feature and the target signature speed feature into the time series coordinate similarity calculation model;

[0099] A time series coordinate similarity calculation subunit, used to calculate the time series coordinate similarity according to the coordinate distribution range characteristics, coordinate change trend characteristics, signature speed characteristics, target coordinate distribution range characteristics, target coordinate change trend characteristics and target signature speed characteristics through a time series coordinate similarity calculation model;

[0100] Among them, the time series coordinate similarity calculation model is obtained by training the neural network to be trained using the historical time series coordinate information and its corresponding target time series coordinate information.

[0101] Optionally, a time series pressure similarity calculation unit includes:

[0102] A second input unit is used to input the pressure distribution range feature, the pressure change trend feature, the pen drop angle distribution range feature, the pen drop angle change trend feature, the target pressure distribution range feature, the target pressure change trend feature, the target pen drop angle distribution range feature and the target pen drop angle change trend feature into the pressure similarity calculation model;

[0103] A time series pressure similarity calculation subunit, used to calculate the time series pressure similarity according to the pressure distribution range characteristics, pressure change trend characteristics, pen drop angle distribution range characteristics, pen drop angle change trend characteristics, target pressure distribution range characteristics, target pressure change trend characteristics, target pen drop angle distribution range characteristics and target pen drop angle change trend characteristics through a time series pressure similarity calculation model;

[0104] Among them, the time series similarity calculation model is obtained by training the neural network to be trained using the historical time series information and its corresponding target time series information.

[0105] An embodiment of the present application also provides an electronic device, which includes: a processor and a memory, wherein the processor and the memory are connected via a communication bus; wherein the processor is used to call and execute a program stored in the memory; and the memory is used to store a program, which is used to implement a bank online handwritten signature identity authentication method.

[0106] Reference below Figure 3 , which shows a schematic diagram of the structure of an electronic device suitable for implementing the disclosed embodiment of the present invention. The electronic device in the disclosed embodiment of the present invention may include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments disclosed in the present invention.

[0107] like Figure 3 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In RAM 303, various programs and data required for the operation of the electronic device are also stored. The processing device 301, ROM 302, and RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0108] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0109] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the bank online handwritten signature identity authentication method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above functions defined in the bank online handwritten signature identity authentication method of the embodiment disclosed in the present invention are executed.

[0110] Furthermore, an embodiment of the present invention also provides a computer-readable storage medium, in which computer-executable instructions are stored, and the computer-executable instructions are used to execute a bank online handwritten signature identity authentication method.

[0111] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: collects target user information and handwritten signature information of the target user through an online device, wherein the handwritten signature information includes signature image information, timing coordinate information and timing pressure information; obtains the target handwritten signature information of the target user according to the target user information, wherein the target handwritten signature information includes target signature image information, target timing coordinate information and target timing pressure information; calculates the signature similarity of the target user according to the signature image information, the timing coordinate information, the timing pressure information, the target signature image information, the target timing coordinate information and the target timing pressure information; if the signature similarity of the target user is greater than a preset similarity threshold, determines that the handwritten signature verification of the target user is passed.

[0112] In the context disclosed by the present invention, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0113] It should be noted that the computer-readable medium disclosed in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0114] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0115] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The system and system embodiments described above are merely schematic, in which the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0116] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0117] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0118] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for online handwritten signature authentication in a bank, characterized in that, the method includes: collecting target user information and handwritten signature information of a target user through an online device, wherein the handwritten signature information includes signature picture information, time series coordinate information, and time series pressure information; acquiring the target handwritten signature information of the target user according to the target user information, wherein the target handwritten signature information includes target signature picture information, target time series coordinate information, and target time series pressure information; calculating the signature similarity of the target user according to the signature picture information, the time series coordinate information, the time series pressure information, the target signature picture information, the target time series coordinate information, and the target time series pressure information; if the signature similarity of the target user is greater than a preset similarity threshold, determining that the handwritten signature verification of the target user is passed; the calculating the signature similarity of the target user according to the signature picture information, the time series coordinate information, the time series pressure information, the target signature picture information, the target time series coordinate information, and the target time series pressure information includes: extracting behavior features from the signature picture information, extracting coordinate distribution range features, coordinate change trend features, and signature speed features from the time series coordinate information, and extracting pressure distribution range features, pressure change trend features, pen-down angle distribution range features, and pen-down angle change trend features from the time series pressure information; extracting target behavior features from the target signature picture information, extracting target coordinate distribution range features, target coordinate change trend features, and target signature speed features from the target time series coordinate information, and extracting target pressure distribution range features, target pressure change trend features, target pen-down angle distribution range features, and target pen-down angle change trend features from the target time series pressure information; calculating the signature picture similarity between the signature picture and the target signature picture according to the behavior features and the target behavior features; calculating the time series coordinate similarity according to the coordinate distribution range features, the coordinate change trend features, the signature speed features, the target coordinate distribution range features, the target coordinate change trend features, and the target signature speed features; calculating the time series pressure similarity according to the pressure distribution range features, the pressure change trend features, the pen-down angle distribution range features, the pen-down angle change trend features, the target pressure distribution range features, the target pressure change trend features, the target pen-down angle distribution range features, and the target pen-down angle change trend features; calculating the signature similarity of the target user according to the signature picture similarity, the time series coordinate similarity, and the time series pressure similarity.

2. The method according to claim 1, characterized in that, the calculating the signature picture similarity between the signature picture and the target signature picture according to the behavior features and the target behavior features includes: Input the behavioral feature and the target behavioral feature into a behavioral similarity calculation model, so that the behavioral similarity calculation model calculates the signature picture similarity between the signature picture and the target signature picture according to the behavioral feature and the target behavioral feature; Wherein, the behavioral similarity calculation model is obtained by training a neural network to be trained using historical signature picture information and the corresponding target signature picture information.

3. The method according to claim 1, wherein, the calculating of the temporal coordinate similarity according to the coordinate distribution range feature, the coordinate change trend feature, the signature speed feature, the target coordinate distribution range feature, the target coordinate change trend feature, and the target signature speed feature includes: Input the coordinate distribution range feature, the coordinate change trend feature, the signature speed feature, the target coordinate distribution range feature, the target coordinate change trend feature, and the target signature speed feature into a temporal coordinate similarity calculation model; The temporal coordinate similarity calculation model calculates the temporal coordinate similarity according to the coordinate distribution range feature, the coordinate change trend feature, the signature speed feature, the target coordinate distribution range feature, the target coordinate change trend feature, and the target signature speed feature; Wherein, the temporal coordinate similarity calculation model is obtained by training a neural network to be trained using historical temporal coordinate information and the corresponding target temporal coordinate information.

4. The method according to claim 1, wherein, the calculating of the temporal pressure similarity according to the pressure distribution range feature, the pressure change trend feature, the pen-down angle distribution range feature, the pen-down angle change trend feature, the target pressure distribution range feature, the target pressure change trend feature, the target pen-down angle distribution range feature, and the target pen-down angle change trend feature includes: Input the pressure distribution range feature, the pressure change trend feature, the pen-down angle distribution range feature, the pen-down angle change trend feature, the target pressure distribution range feature, the target pressure change trend feature, the target pen-down angle distribution range feature, and the target pen-down angle change trend feature into a temporal pressure similarity calculation model; The temporal pressure similarity calculation model calculates the temporal pressure similarity according to the pressure distribution range feature, the pressure change trend feature, the pen-down angle distribution range feature, the pen-down angle change trend feature, the target pressure distribution range feature, the target pressure change trend feature, the target pen-down angle distribution range feature, and the target pen-down angle change trend feature; Wherein, the temporal pressure similarity calculation model is obtained by training a neural network to be trained using historical temporal information and the corresponding target temporal information.

5. A bank online handwritten signature authentication system, wherein, the system includes: A data acquisition unit, configured to acquire target user information and handwritten signature information of a target user through an online device, wherein the handwritten signature information includes signature picture information, time series coordinate information, and time series pressure information; A target handwritten signature information acquisition unit, configured to acquire target handwritten signature information of the target user according to the target user information, wherein the target handwritten signature information includes target signature picture information, target time series coordinate information, and target time series pressure information; A signature similarity calculation unit, configured to calculate the signature similarity of the target user according to the signature picture information, the time series coordinate information, the time series pressure information, the target signature picture information, the target time series coordinate information, and the target time series pressure information; A verification passed determination unit, configured to determine that the handwritten signature verification of the target user passes if the signature similarity of the target user is greater than a preset similarity threshold; The signature similarity calculation unit includes: A first feature extraction unit, configured to extract behavior features from the signature picture information, extract coordinate distribution range features, coordinate change trend features, and signature speed features from the time series coordinate information, and extract pressure distribution range features, pressure change trend features, pen-down angle distribution range features, and pen-down angle change trend features from the time series pressure information; A second feature extraction unit, configured to extract target behavior features from the target signature picture information, extract target coordinate distribution range features, target coordinate change trend features, and target signature speed features from the target time series coordinate information, and extract target pressure distribution range features, target pressure change trend features, target pen-down angle distribution range features, and target pen-down angle change trend features from the target time series pressure information; A signature picture similarity calculation unit, configured to calculate the signature picture similarity between the signature picture and the target signature picture according to the behavior features and the target behavior features; A time series coordinate similarity calculation unit, configured to calculate the time series coordinate similarity according to the coordinate distribution range features, the coordinate change trend features, the signature speed features, the target coordinate distribution range features, the target coordinate change trend features, and the target signature speed features; A time series pressure similarity calculation unit, configured to calculate the time series pressure similarity according to the pressure distribution range features, the pressure change trend features, the pen-down angle distribution range features, the pen-down angle change trend features, the target pressure distribution range features, the target pressure change trend features, the target pen-down angle distribution range features, and the target pen-down angle change trend features; A signature similarity calculation subunit, configured to calculate the signature similarity of the target user according to the signature picture similarity, the time series coordinate similarity, and the time series pressure similarity.

6. The system according to claim 5, wherein, The signature picture similarity calculation unit includes: The signature picture similarity calculation sub-unit is configured to input the behavior feature and the target behavior feature into a behavior similarity calculation model, so that the behavior similarity calculation model calculates the signature picture similarity between the signature picture and the target signature picture according to the behavior feature and the target behavior feature; Wherein, the behavior similarity calculation model is obtained by training a neural network to be trained using historical signature picture information and the corresponding target signature picture information.

7. An electronic device, characterized in that, the electronic device includes a processor and a memory, the memory is used to store program codes and data for bank online handwritten signature authentication, and the processor is used to call program instructions in the memory to execute a bank online handwritten signature authentication method according to any one of claims 1-4.

8. A storage medium, characterized in that, the storage medium includes a stored program, wherein when the program runs, it controls the device where the storage medium is located to execute a bank online handwritten signature authentication method according to any one of claims 1-4.

Images