Identity authentication method, device and computer equipment based on electronic signature

Abstract

The present application relates to data processing technology, and provides an identity authentication method, device, computer equipment and storage medium based on electronic signature. The method includes: obtaining a business validation document corresponding to a user ID; sending the business validation document to a user terminal; receiving an electronic signature of the user terminal in response to the business validation document; obtaining image information corresponding to the user ID and the electronic signature collected by an image collector; authenticating the image information according to a preset authentication method; when the authentication is passed, the user ID, the image information and the business validation document carrying the electronic signature are stored in correspondence. This method can ensure the security of user information.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an identity authentication method, device and computer equipment based on electronic signature. Background Art

[0002] With the development of data processing technology, identity authentication technology based on data processing has gradually developed, which has improved the efficiency of identity authentication and brought many conveniences to people's lives. Usually, after the business is completed, the business staff will ask the user to sign the business approval document to ensure the non-repudiation of the business approval document. At the same time, the identity of the signing user is authenticated according to the signature to ensure the validity of the business and the security of the corresponding user information.

[0003] At present, users are usually asked to sign paper business approval documents, but the archiving process of paper business approval documents is cumbersome and easy to lose, which leads to the leakage of corresponding user information and the problem of low user information security. Furthermore, the current electronic signature method is difficult to reflect the user's signing habits, and the identity of the signing user is not authenticated based on the electronic signature. There may be a problem of misappropriating other users' information to handle related business, which leads to the problem of low user information security. Summary of the invention

[0004] Based on this, it is necessary to provide an identity authentication method, device and computer equipment based on electronic signature that can improve the security of user information in response to the above technical problems.

[0005] An identity authentication method based on electronic signature, the method comprising:

[0006] Obtain the business validation document corresponding to the user ID;

[0007] Sending the business validation approval document to the user terminal;

[0008] Receiving an electronic signature from the user terminal corresponding to the feedback of the business validation approval document;

[0009] Acquire image information corresponding to the user identifier and the electronic signature acquired by an image collector;

[0010] Authenticating the image information according to a preset authentication method;

[0011] When the authentication is passed, the user identification, the image information and the business validation approval document carrying the electronic signature are stored correspondingly.

[0012] An identity authentication device based on electronic signature, the device comprising:

[0013] The approval document acquisition module is used to obtain the business effective approval document corresponding to the user ID;

[0014] A sending module, used for sending the service validation document to a user terminal;

[0015] A receiving module, used to receive the electronic signature of the user terminal corresponding to the feedback of the business validation approval document;

[0016] An image acquisition module, used to acquire image information corresponding to the user identification and the electronic signature acquired by the image collector;

[0017] An authentication module, used to authenticate the image information according to a preset authentication method;

[0018] The storage module is used to store the user identification, the image information and the business validation document carrying the electronic signature in correspondence when the authentication is passed.

[0019] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0020] Obtain the business validation document corresponding to the user ID;

[0021] Sending the business validation approval document to the user terminal;

[0022] Receiving an electronic signature from the user terminal corresponding to the feedback of the business validation approval document;

[0023] Acquire image information corresponding to the user identifier and the electronic signature acquired by an image collector;

[0024] Authenticating the image information according to a preset authentication method;

[0025] When the authentication is passed, the user identification, the image information and the business validation approval document carrying the electronic signature are stored correspondingly.

[0026] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0027] Obtain the business validation document corresponding to the user ID;

[0028] Sending the business validation approval document to the user terminal;

[0029] Receiving an electronic signature from the user terminal corresponding to the feedback of the business validation approval document;

[0030] Acquire image information corresponding to the user identifier and the electronic signature acquired by an image collector;

[0031] Authenticating the image information according to a preset authentication method;

[0032] When the authentication is passed, the user identification, the image information and the business validation approval document carrying the electronic signature are stored correspondingly.

[0033] The above-mentioned electronic signature-based identity authentication method, device, computer equipment and storage medium send the business validation document corresponding to the user ID to the user terminal, receive the electronic signature fed back by the user terminal, and obtain the image information corresponding to the user ID and the electronic signature collected by the image collector, and then authenticate the signing user based on the image information to ensure the authenticity of the signing user's identity and improve the security of user information. When the authentication is passed, the acquired user ID, image information and business validation document carrying the electronic signature are stored correspondingly to ensure the validity of the handled business and further improve the security of user information. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is an application scenario diagram of an identity authentication method based on electronic signature in an embodiment;

[0035] Figure 2 A schematic diagram of a flow chart of an identity authentication method based on electronic signature in one embodiment;

[0036] Figure 3 is a flow chart of an identity authentication method based on electronic signature in another embodiment;

[0037] Figure 4 is a structural block diagram of an identity authentication device based on electronic signature in one embodiment;

[0038] Figure 5 is a structural block diagram of an identity authentication device based on electronic signature in another embodiment;

[0039] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0041] The electronic signature-based identity authentication method provided in this application can be applied to Figure 1In the application environment shown. Among them, the salesman terminal 102 and the user terminal 106 communicate with the server 104, and the salesman terminal 102 and the user terminal 106 communicate with the server 104 respectively through the network. The salesman terminal 102 and the image collector 108 communicate through a data line or a network. The salesman terminal 102 sends the acquired business validation document to the user terminal 106 with the help of the server 104, and receives the electronic signature of the user terminal 106. The salesman terminal 102 obtains the image information corresponding to the electronic signature collected by the image collector 108, and authenticates the image information. When the authentication is passed, it indicates that the identity authentication of the signing user is passed, and the salesman terminal 102 stores the user identification, image information and the business validation document carrying the electronic signature accordingly. Among them, the salesman terminal 102 and the user terminal 106 can be, but not limited to, various personal computers, laptops, smart phones, tablet computers and portable wearable devices, and the server 104 can be implemented with an independent server or a server cluster composed of multiple servers. The image acquisition group may include, but is not limited to, high-definition cameras and video cameras.

[0042] In one embodiment, Figure 2 As shown, an identity authentication method based on electronic signature is provided, and the method is applied to Figure 1 The following steps are used as an example to illustrate the salesperson terminal in the example:

[0043] S202, obtaining a service validation document corresponding to the user identifier.

[0044] Among them, the user ID is used to uniquely identify the user. The business effectiveness approval document refers to the approval document generated when the business is effective during the business handling process. The business effectiveness approval document may specifically refer to the document generated when the business acceptance is completed and effective. The business effectiveness approval document includes the business information corresponding to the corresponding business. For example, when the business is a policy preservation business, the business effectiveness approval document includes the policy preservation information, and may also include the policy information corresponding to the corresponding policy. The approval document refers to an approved file or document. In this embodiment, the approval document refers to a document generated according to the effective business and used to characterize the business information corresponding to the effective business. The business effectiveness document may specifically be a document in a specified format, such as the PDF format (Portable Document Format).

[0045] Specifically, the salesperson terminal detects a designated trigger operation, and when a designated trigger operation is detected, a corresponding business validation approval document is generated according to the detected designated trigger operation. The designated trigger operation is a pre-designated trigger operation, such as a trigger operation of a designated trigger control by a salesperson when the business acceptance is completed and effective. When the salesperson terminal detects a designated trigger operation triggered by a salesperson for the currently accepted business, a business validation approval document corresponding to the corresponding user ID is generated according to the detected designated trigger operation. Among them, the user ID corresponds to the currently accepted business.

[0046] S204, sending the service validation approval document to the user terminal.

[0047] Specifically, the salesperson terminal sends the obtained business validation document corresponding to the user identifier to the user terminal. Further, the salesperson terminal synchronizes the obtained business validation document to the user terminal via wired or wireless means. The salesperson terminal sends the business validation document to the user terminal via a designated web page or a designated client. The user terminal can receive the business validation document sent by the salesperson terminal via a designated web page or a designated client. The designated client is a program that runs on the user terminal and provides services to the user, and can specifically be an application software installed and running on the user terminal.

[0048] In one embodiment, the salesperson terminal sends the obtained business validation document to the user terminal with the help of the server. Specifically, the salesperson terminal sends the obtained business validation document to the server, and the server sends the received business validation document to the user terminal. The server can also store the received business validation document and the corresponding user identification locally.

[0049] In one embodiment, the user terminal displays the received business validation document and detects the electronic signature operation triggered by the user corresponding to the corresponding user ID on the business validation document. After reading the business validation document displayed by the user terminal, the user performs an electronic signature operation on the business validation document to confirm the business validation document.

[0050] S206, receiving the electronic signature of the user terminal in response to the business validation approval document.

[0051] Among them, electronic signature refers to the electronic signature of an electronic document, that is, the electronic signature refers to the electronic signature in the electronic document. The electronic signature can be implemented on a terminal with a touch screen that supports electronic signatures, or it can be implemented with the help of designated signature software. During the electronic signature process, the electronic signature can be encrypted with the help of algorithms such as symmetric encryption or asymmetric encryption to improve the security of the electronic signature.

[0052] Specifically, the user terminal detects the electronic signature operation of the user in response to the displayed business validation approval document, obtains the corresponding electronic signature according to the detected electronic signature operation, and sends the obtained electronic signature to the salesperson terminal.

[0053] In one embodiment, the user terminal synthesizes the acquired electronic signature with the corresponding business validity approval document according to a preset synthesis method to obtain the business validity approval document carrying the electronic signature, and sends the electronic signature and the business validity approval document carrying the electronic signature to the salesperson terminal.

[0054] In one embodiment, when the salesperson terminal obtains the electronic signature corresponding to the feedback from the user terminal, the electronic signature and the corresponding business effectiveness approval are synthesized in a preset manner to obtain the business effectiveness approval carrying the electronic signature, and the business effectiveness document carrying the electronic signature and the corresponding user identification are stored locally, or sent to the server for storage.

[0055] In one embodiment, when the user terminal displays the business validation approval document, the electronic signature of the corresponding user is collected through the electronic signature collector, and the collected electronic signature is sent to the salesperson terminal.

[0056] S208, acquiring image information corresponding to the user identification and the electronic signature collected by the image collector.

[0057] The image information refers to information in the form of images, videos, or audio. The image information may specifically be information such as images, videos, or audio collected by an image collector. In this embodiment, the image information may include, but is not limited to, user face images, user signature images, and signature videos. User face images include user headshots or user headshots, user signature images include signature photos collected when the user signs on the screen, and signature videos include videos collected during the user's signature process.

[0058] Specifically, the image collector detects a preset trigger operation. When the preset trigger operation is detected, the image information of the user corresponding to the corresponding user ID during the electronic signature process is collected according to the detected preset trigger operation, and the collected image information is sent to the salesperson's terminal. Among them, the image information collected by the image collector is information corresponding to the user ID and the electronic signature corresponding to the user ID. The preset trigger operation is, for example, a trigger operation of a preset control by a salesperson, and the preset control is, for example, a control that starts the image collector. The image collector collects the image information of the user performing an electronic signature operation on the business effectiveness approval document in real time according to the detected preset trigger operation. In other words, when the user performs an electronic signature operation, the image collector collects image information such as the user's face image, the user's signature image, and the signature video.

[0059] In one embodiment, when the salesperson terminal sends the acquired business validation document to the user terminal, the image collector is started to collect the image information of the user when performing the electronic signature through the image collector. In one embodiment, when the salesperson terminal sends the business validation document to the user terminal, it sends an image acquisition instruction to the image collector, and the image collector collects the image information corresponding to the user identification and the electronic signature according to the received image acquisition instruction.

[0060] In one embodiment, the salesperson terminal receives the image information collected and sent by the user terminal for the business effectiveness approval document. When the user terminal displays the received business effectiveness approval document, the electronic signature of the user corresponding to the displayed business effectiveness approval document is detected in real time, and the corresponding image information is collected through the image acquisition device. The image acquisition device can be a device built into the user terminal, such as a built-in camera of the user terminal, or it can be an independent device connected to the user terminal.

[0061] S210: Authenticate the image information according to a preset authentication method.

[0062] Among them, the preset authentication method is a pre-set method for authenticating image information. The preset authentication method can specifically be an authentication method for authenticating the currently acquired image information based on the existing image information. The preset authentication method, for example, matches the existing image information with the currently acquired image information. Authentication refers to verifying the authenticity of the identity of the user involved in the image information. Authentication can specifically be verifying the authenticity of the identity of the signing user based on the image information.

[0063] Specifically, when the salesperson terminal obtains the image information corresponding to the user identification and the corresponding electronic signature, the obtained image information is authenticated according to the preset authentication method to authenticate the user identity corresponding to the image information. In other words, the salesperson terminal authenticates the authenticity of the identity of the user who performs the electronic signature operation on the business validation approval document by authenticating the obtained image information according to the preset authentication method. The salesperson terminal queries the pre-stored preset image information according to the user identification, and authenticates the obtained image information according to the queried preset image information.

[0064] In one embodiment, the salesperson terminal matches the preset image information queried according to the user identification with the acquired image information, and determines the authentication result corresponding to the image information according to the matching result. When the match is successful, the authentication result is determined to be authentication passed, that is, the authentication is successful; when the match fails, the authentication result is determined to be authentication failed, that is, the authentication fails.

[0065] In one embodiment, the salesperson terminal obtains the matching rate between the preset image information and the image information, and compares the obtained matching rate with the matching rate threshold. When the matching rate reaches the matching rate threshold, the salesperson terminal determines that the authentication result is authentication passed.

[0066] S212, when the authentication is passed, the user identification, image information and the business validation document carrying the electronic signature are stored correspondingly.

[0067] Specifically, when the authentication is passed, it indicates that the image information corresponding to the user identification and the electronic signature matches or is consistent with the preset image information queried according to the user identification, and the salesperson terminal synthesizes the obtained electronic signature with the corresponding business validation document according to the preset synthesis method to obtain the business validation document carrying the electronic signature. The salesperson terminal stores the corresponding information locally.

[0068] In one embodiment, when the authentication is passed, the salesperson terminal sends the authenticated image information, the business validation document with an electronic signature, and the corresponding user identification to the server, and the server stores the received image information, the business validation document with an electronic signature, and the user identification locally, or stores them in a cloud server or a network server.

[0069] In one embodiment, when the match is successful, it indicates that the user corresponding to the user identifier corresponding to the business validation document is the same as the user who performed the electronic signature operation on the business validation document, that is, the user corresponding to the currently accepted and effective business is the same user as the user who handled the business. When the authenticity of the identity of the user currently handling the business is determined, the salesperson terminal ends the current electronic signature process and the identity authentication process based on the electronic signature.

[0070] The above-mentioned identity authentication method based on electronic signature sends the business validation document corresponding to the user ID to the user terminal, receives the corresponding electronic signature fed back by the user terminal, and obtains the image information corresponding to the user ID and the electronic signature collected by the image collector, and authenticates the signing user based on the image information to ensure the authenticity of the signing user's identity, thereby improving the security of user information. When the authentication is passed, the acquired user ID, image information and business validation document carrying the electronic signature are stored correspondingly to ensure the validity of the handled business and further improve the security of user information.

[0071] In one embodiment, the image information includes a user face image; step S210 includes: preprocessing the user face image; inputting the preprocessed user face image into a pre-trained feature point recognition model for prediction to obtain target face feature point measurement values; querying pre-stored preset face feature point measurement values ​​according to the user identifier; and authenticating the target face feature point measurement values ​​according to the preset face feature point measurement values.

[0072] Among them, the user face image refers to an image containing the user's face. The user face image can specifically be a user head portrait or a user headshot collected when the user performs an electronic signature operation. Preprocessing refers to the process of processing the acquired user face image to meet the preset requirements. The preset processing method specifically includes at least one of face detection, face key point detection, face correction and normalization. The feature point recognition model is a model obtained by model training based on a pre-acquired training sample set, which can be used to extract the target face feature point measurement value from the preprocessed user face image. The target face feature point measurement value refers to the face feature point measurement value extracted from the user face image. The preset face feature point measurement value refers to the pre-stored face feature point measurement value. The face feature point measurement value refers to the measurement value of the face feature point. The face feature point measurement value can be a relative measurement value, such as the relative position between each feature point, or an absolute measurement value, such as the position of each feature point relative to the coordinate origin.

[0073] Specifically, the salesperson terminal obtains the corresponding user face image from the image information, performs face detection on the obtained user face image to identify the face contour in the user face image, that is, determines the position of the face in the user face image, and extracts the identified face image from the user face image. The salesperson terminal detects the key features of the face in the extracted face image, such as the position of the corners of the eyes, the position of the nose, the contour points of the face, the position of the mouth, the position of the eyebrows, etc., and aligns and calibrates the face through affine transformation according to the detected key features to obtain the pre-processed user face image. The salesperson terminal uses the pre-processed user face image as an input feature, inputs the pre-trained feature point recognition model for prediction, and obtains the corresponding target face feature point measurement value. Further, the salesperson terminal queries the pre-stored preset face feature point measurement value corresponding to the user identifier locally or on the server according to the user identifier, and authenticates the obtained target face feature point measurement value according to the queried preset face feature point measurement value.

[0074] In one embodiment, the salesperson terminal matches the preset facial feature point measurement values ​​queried with the obtained target facial feature point measurement values, and determines the corresponding authentication result according to the matching result. When the matching rate between the preset facial feature point measurement values ​​and the target facial feature point measurement values ​​reaches the matching rate threshold, the salesperson terminal determines that the user performing the electronic signature operation is the user corresponding to the business.

[0075] In one embodiment, the image information includes a user signature image. The salesperson terminal authenticates the user who performs the electronic signature operation based on the user signature image in the image information. The salesperson terminal can specifically authenticate the user identity based on the electronic signature in the user signature image, or can authenticate the user identity based on the user information in the user signature image.

[0076] In the above embodiment, with the help of the trained feature point recognition model, the identity of the user performing the electronic signature operation is authenticated according to the user's facial image in the image information, thereby improving the authentication efficiency and accuracy.

[0077] In one embodiment, the image information includes a signature video; step S210 includes: obtaining a signature timestamp corresponding to the electronic signature; extracting a target signature image from the signature video according to the signature timestamp; extracting a target face image from the target signature image through a trained face recognition model; obtaining a preset face image corresponding to the user identifier; and authenticating the target face image according to the preset face image.

[0078] Among them, the signature video refers to the video collected when the user performs an electronic signature operation. The signature timestamp refers to the timestamp collected when the user performs an electronic signature operation. The signature timestamp can specifically be the time corresponding to when the user performs the electronic signature. The target signature image refers to the image corresponding to when the user performs the electronic signature operation. The target signature image can specifically be an image extracted from the signature video and corresponding to the electronic signature operation. The target signature image can specifically be one or more video frames in the signature video. The preset face image is a pre-stored face image corresponding to the user identification.

[0079] Specifically, the salesperson terminal obtains the signature video from the image information, obtains the signature timestamp corresponding to the electronic signature from the local or user terminal, and determines the timestamp matching the signature timestamp in the signature video based on the acquired signature timestamp, and then extracts the corresponding target signature image from the signature video based on the determined timestamp. The salesperson terminal inputs the extracted target signature image into the trained face recognition model for prediction, and obtains the corresponding target face image, that is, extracts the corresponding target face image from the target signature image. Furthermore, the salesperson terminal queries the pre-stored preset face image corresponding to the user identification in the local or server, and matches the queried preset face image with the extracted target face image, and determines the corresponding authentication result based on the matching result.

[0080] In one embodiment, when the user terminal detects the user's electronic signature operation on the business validation approval document, it obtains the corresponding electronic signature in real time, and records the signature timestamp corresponding to the electronic signature, and sends the obtained electronic signature and corresponding signature timestamp to the salesperson terminal.

[0081] In one embodiment, the salesperson terminal obtains the signing time period corresponding to the electronic signature, and determines the starting signing timestamp and the ending signing timestamp according to the signature timestamp. The salesperson terminal determines the starting timestamp that matches the starting signing timestamp and the ending timestamp that matches the ending signing timestamp in the signature video, and extracts one or more corresponding target signature images from the signature video according to the determined starting timestamp and ending timestamp. In other words, the salesperson terminal extracts the target signature images corresponding to each timestamp from the starting timestamp to the ending timestamp from the signature video.

[0082] Furthermore, the salesperson terminal screens the extracted target signature images according to a preset screening method, and extracts the target face image from the screened target signature images through the trained face recognition model. The salesperson terminal queries the corresponding preset face image according to the user identifier, and authenticates the extracted target face image according to the queried preset face image. The preset screening method is a pre-set method for screening the final target signature image from multiple target signature images, such as screening according to the clarity or completeness of the target face image in the target signature image.

[0083] In one embodiment, the salesperson terminal sequentially inputs multiple target signature images extracted from the signature video into the trained face recognition model for prediction, and obtains the target face image corresponding to each target signature image. The salesperson terminal selects the final target face image from the multiple target face images according to a preset selection method, and authenticates the selected target face image according to the preset face image. The preset selection method is a pre-specified method for selecting the final target face image from multiple target face images, such as selecting according to key features in the target face image.

[0084] In the above embodiment, with the help of the trained face recognition model, the identity of the user performing the electronic signature operation is authenticated according to the target signature image corresponding to the timestamp in the signature video that matches the signature timestamp, thereby improving the authentication efficiency and accuracy, thereby effectively ensuring the security of user information.

[0085] In one embodiment, the above-mentioned identity authentication method based on electronic signature also includes: authenticating the electronic signature according to a specified authentication method; step S212 includes: when both the image information and the electronic signature are authenticated, the user identification, image information and the business effectiveness approval document carrying the electronic signature are stored correspondingly.

[0086] Among them, the designated authentication method is a pre-designated method for authenticating the acquired electronic signature. The designated authentication method may specifically be authenticating the acquired electronic signature according to a pre-stored preset electronic signature, such as matching the preset electronic signature with the electronic signature, and determining the authentication result corresponding to the electronic signature according to the matching result. The designated authentication method may also specifically be pre-processing the electronic signature to obtain the corresponding electronic signature features, and authenticating the obtained electronic signature features according to the pre-stored preset electronic signature features. Electronic signature features include stroke features or signature trajectories.

[0087] Specifically, when the salesperson terminal obtains the electronic signature corresponding to the user identification and the business effectiveness approval document, the obtained electronic signature is authenticated according to the specified authentication method to authenticate the identity of the user performing the electronic signature operation. The salesperson terminal queries the pre-stored preset electronic signature according to the user identification, and authenticates the currently obtained electronic signature according to the preset electronic signature. When the authentication results corresponding to the image information and the electronic signature are both authenticated, the salesperson terminal synthesizes the authenticated electronic signature with the corresponding business effectiveness approval document according to the preset synthesis method to obtain the business effectiveness approval document carrying the electronic signature. The salesperson terminal stores the authenticated image information, the business effectiveness approval document carrying the electronic signature and the corresponding user identification locally, or sends them to the server for corresponding storage.

[0088] In one embodiment, the salesperson terminal authenticates the image information in accordance with a preset authentication method and authenticates the corresponding electronic signature in accordance with a specified authentication method. In one embodiment, when the image information authentication is passed, the salesperson terminal authenticates the corresponding electronic signature in accordance with a specified authentication method. When the electronic signature authentication is passed, the authenticated image information, the business validation document carrying the authenticated electronic signature, and the corresponding user identification are stored in correspondence.

[0089] In the above embodiment, the electronic signature and image information obtained during the electronic signature process are authenticated separately. When both are authenticated, it is determined that the user performing the electronic signature operation is the user corresponding to the business, which improves the accuracy of authentication and thus improves the security of user information.

[0090] In one embodiment, an electronic signature is authenticated according to a specified authentication method, including: decomposing the electronic signature into strokes according to a preset decomposition method to obtain a corresponding plurality of strokes; inputting each stroke in turn into a pre-trained feature recognition model for prediction to obtain a target stroke feature corresponding to each stroke; querying a pre-stored preset stroke feature according to a user identifier; and authenticating the target stroke feature according to the preset stroke feature.

[0091] Among them, the preset decomposition method is a preset method for decomposing the electronic signature into corresponding strokes. The preset decomposition method can specifically be to decompose the electronic signature according to the constituent strokes of the electronic signature, such as decomposing the various strokes that constitute the electronic signature according to the writing rules of Chinese characters. The feature recognition model is a model obtained by model training based on a pre-acquired training sample set, which can be used to predict unknown stroke features based on known stroke correspondences. The target stroke feature refers to the stroke feature correspondingly extracted from the stroke. The target stroke feature is used to characterize the features of the corresponding strokes in the electronic signature. The target stroke features include but are not limited to the angle of inclination of the stroke, the angle of bending, the number of fluctuations and the length of the stroke. The preset stroke feature is a pre-stored stroke feature corresponding to the user identifier.

[0092] Specifically, the salesperson terminal decomposes the obtained electronic signature according to the preset decomposition method to obtain multiple strokes constituting the electronic signature. The salesperson terminal sequentially inputs the obtained multiple strokes into the trained feature recognition model for prediction to obtain the target stroke feature corresponding to each stroke. The salesperson terminal queries the preset stroke feature corresponding to the user ID locally or on the server according to the user ID, and authenticates the target stroke feature according to the preset stroke feature queried.

[0093] In one embodiment, the salesperson terminal sorts the multiple strokes obtained according to the writing rules of Chinese characters in the electronic signature, and inputs the multiple strokes into the feature recognition model in sequence according to the sorting for prediction, and obtains the target stroke features corresponding to each of the multiple strokes. The writing rules of Chinese characters can specifically be the order of writing strokes of Chinese characters. The salesperson terminal sorts the multiple strokes constituting the electronic signature according to the order in which the strokes are written in the electronic signature. In one embodiment, the salesperson terminal queries the multiple preset stroke features corresponding to the corresponding electronic signature according to the user identification, and the multiple stroke features correspond to the multiple strokes constituting the electronic signature respectively. The salesperson terminal authenticates the corresponding target stroke features among the multiple target stroke features obtained using the multiple preset stroke features queried.

[0094] In one embodiment, the preset stroke features obtained by the salesperson terminal are matched with the corresponding target stroke features to obtain the corresponding target matching rate, and the target matching rate is compared with the preset matching rate. When the target matching rate reaches the preset matching rate, it is determined that the target stroke feature authentication is passed.

[0095] In the above embodiment, the corresponding target stroke features are obtained according to the strokes of the electronic signature through the trained feature recognition model, and the identity of the user performing the electronic signature operation is authenticated according to the obtained target stroke features, thereby improving the authentication efficiency and accuracy, thereby effectively ensuring the security of user information.

[0096] In one embodiment, authenticating an electronic signature according to a specified authentication method includes: obtaining a target signature trajectory corresponding to the electronic signature; querying a pre-stored preset signature trajectory according to a user identifier; and authenticating the electronic signature according to the preset signature trajectory and the target signature trajectory.

[0097] Among them, the target signature trajectory refers to the trajectory characteristics of the user's name when performing an electronic signature operation. The target signature trajectory can specifically be the stroke order or writing font when the user writes his name. According to the writing rules of Chinese characters, each stroke that makes up a Chinese character has a standard writing order, but due to different personal writing habits, users may not write in the standard writing order when performing electronic signature operations. Similarly, Chinese characters correspond to different fonts, such as regular script, regular script, running script, running script, cursive script, and official script. Due to different personal writing habits, users may be accustomed to a specific font or a combination of multiple different fonts when performing electronic signature operations. Users performing electronic signature operations can be authenticated based on the writing order and writing font of their names.

[0098] Specifically, the salesperson terminal obtains the target signature track corresponding to the user identifier from the local or user terminal, and queries the pre-stored preset signature track corresponding to the user identifier according to the user identifier. The salesperson terminal authenticates the obtained target signature track according to the queried preset signature track to realize the authentication of the corresponding electronic signature.

[0099] In one embodiment, the salesperson terminal matches the preset signature track that has been queried with the acquired target signature track, and determines the authentication result corresponding to the target signature track according to the matching result, and then determines the authentication result of the electronic signature. Specifically, when the preset signature track matches the target signature track successfully, the salesperson terminal determines that the authentication result corresponding to the target signature track is authentication passed, and correspondingly determines that the electronic signature corresponding to the target signature track is authentication passed.

[0100] In one embodiment, when the user terminal detects the electronic signature, it also records the target signature trajectory corresponding to the electronic signature, and sends the acquired electronic signature and the corresponding target signature trajectory to the salesperson terminal.

[0101] In the above embodiment, the target signature trajectory corresponding to the corresponding electronic signature is authenticated according to the preset signature trajectory to realize the authentication of the electronic signature, thereby realizing the authentication of the identity of the user performing the electronic signature operation, thereby improving the authentication efficiency and accuracy, thereby effectively ensuring the security of user information.

[0102] In one embodiment, the above-mentioned identity authentication method based on electronic signature also includes: obtaining a business query instruction corresponding to the user identification sent by the user terminal; obtaining the target image information corresponding to the business query instruction collected by the image collector; authenticating the target image information based on the image information; when the target image information is authenticated, sending the business effectiveness approval document carrying the electronic signature to the user terminal.

[0103] The business query instruction is an instruction for triggering a business query operation. The target image information refers to the image information collected corresponding to the business query instruction. The target image information may be the image information collected for the user who triggered the business query instruction when the business query process is triggered according to the business query instruction.

[0104] Specifically, the user terminal detects the user identification information entered by the user and the designated trigger operation triggered by the user information, determines the corresponding user identification according to the detected user information, generates the corresponding business query instruction according to the detected designated trigger operation, and sends the generated business query instruction and the determined user identification to the salesperson terminal. The user identification information may be a user identification or other information used to identify a user.

[0105] Furthermore, the salesperson terminal obtains the target image information corresponding to the business query instruction collected by the image collector. The salesperson terminal queries the image information stored corresponding to the user ID according to the user ID, matches the queried image information with the acquired target image information, and determines the authentication result corresponding to the target image information according to the matching result. When the match is successful, the salesperson terminal determines that the authentication result corresponding to the target image information is authentication passed, and according to the user ID corresponding to the target image information that has passed the authentication, the salesperson terminal queries the business effectiveness approval document stored corresponding to the user ID and carrying the electronic tag and sends it to the user terminal.

[0106] In one embodiment, the target image information includes a target user's facial image or a business query video. Similar to the above-mentioned steps of authenticating the identity of the user who performs the electronic signature operation based on the image information, the salesperson terminal authenticates the identity of the user who triggers the business query instruction based on the target image information. When the authentication is successful, the salesperson terminal queries and feeds back the corresponding user information according to the business query instruction. Among them, the user information includes but is not limited to the image information corresponding to the user ID and the business validation approval document carrying the electronic signature.

[0107] In the above embodiment, the identity of the user who triggers the service query instruction is authenticated based on the acquired target image information and the existing image information, and corresponding user information is fed back when the authentication is successful, thereby improving the security of the user information.

[0108] In one embodiment, when the salesperson terminal obtains the business effective approval document, the corresponding seal is obtained, and the obtained business effective approval document and seal are sent to the user terminal. When the user terminal detects the electronic signature, the electronic signature, the seal and the corresponding business effective approval document are synthesized to obtain the business effective approval document carrying the electronic signature and the seal, and the business effective approval document carrying the electronic signature and the seal is sent to the salesperson terminal. When the salesperson terminal receives the electronic signature fed back by the user terminal or the business effective approval document carrying the electronic signature, the electronic signature, the seal and the corresponding business effective approval document are synthesized to obtain the business effective approval document carrying the electronic signature and the seal.

[0109] In one embodiment, the salesperson terminal can obtain the seal from the seal system. When the user identity authentication of the electronic signature operation is passed, the salesperson terminal can send the corresponding user identification, image information and the business validation document carrying the electronic signature to the image system for storage. When the user identity authentication of the business query instruction is passed, the salesperson terminal can query the corresponding user information from the image system according to the user identification.

[0110] like Figure 3As shown, in one embodiment, an identity authentication method based on electronic signature is provided, and the method specifically includes the following steps:

[0111] S302, obtaining a service validation document corresponding to the user identifier.

[0112] S304, sending the service validation document to the user terminal.

[0113] S306, receiving the electronic signature of the user terminal in response to the business validation approval document.

[0114] S308, acquiring image information corresponding to the user identification and the electronic signature collected by the image collector.

[0115] S310, the image information includes a user face image; the user face image is pre-processed.

[0116] S312, input the preprocessed user face image into a pre-trained feature point recognition model for prediction to obtain the target face feature point measurement values.

[0117] S314, querying pre-stored preset facial feature point measurement values ​​according to the user identifier.

[0118] S316: Authenticate the target facial feature point measurement values ​​according to the preset facial feature point measurement values.

[0119] S318, the image information includes the signature video; and the signature timestamp corresponding to the electronic signature is obtained.

[0120] S320, extracting a target signature image from the signature video according to the signature timestamp.

[0121] S322, extracting a target face image from the target signature image using a trained face recognition model.

[0122] S324, obtaining a preset face image corresponding to the user identifier.

[0123] S326, authenticating the target facial image according to the preset facial image.

[0124] S328, decomposing the electronic signature into strokes according to a preset decomposition method to obtain a corresponding plurality of strokes.

[0125] S330, inputting each stroke into a pre-trained feature recognition model in sequence for prediction, and obtaining target stroke features corresponding to each stroke.

[0126] S332, querying pre-stored preset stroke features according to the user identifier.

[0127] S334, authenticating the target stroke feature according to the preset stroke feature.

[0128] S336, obtaining the target signature trajectory corresponding to the electronic signature.

[0129] S338, querying the pre-stored preset signature trajectory according to the user identifier.

[0130] S340, authenticating the electronic signature according to the preset signature trajectory and the target signature trajectory.

[0131] S342, when both the image information and the electronic signature are authenticated, the user identification, the image information and the business validation document carrying the electronic signature are stored correspondingly.

[0132] In the above embodiments, a variety of authentication methods are provided for authenticating image information and electronic signatures respectively. When the image information and electronic signature authentication are passed, it is determined that the user performing the electronic signature operation and the user corresponding to the business are the corresponding users, and the electronic signature process is completed, and the corresponding user information is stored accordingly, thereby ensuring the security of user information.

[0133] It should be understood that although Figure 2-3 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2-3 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0134] In one embodiment, Figure 4 As shown, an identity authentication device 400 based on electronic signature is provided, comprising: an approval acquisition module 402, a sending module 404, a receiving module 406, an image acquisition module 408, an authentication module 410 and a storage module 412, wherein:

[0135] The approval document acquisition module 402 is used to acquire the service validation approval document corresponding to the user identifier.

[0136] The sending module 404 is used to send the service validation approval document to the user terminal.

[0137] The receiving module 406 is used to receive the electronic signature of the user terminal in response to the business validation approval document.

[0138] The image acquisition module 408 is used to acquire the image information corresponding to the user identification and the electronic signature acquired by the image collector;

[0139] The authentication module 410 is used to authenticate the image information according to a preset authentication method.

[0140] The storage module 412 is used to store the user identification, image information and the business validation document carrying the electronic signature in correspondence when the authentication is passed.

[0141] In one embodiment, the image information includes a user face image; the authentication module 410 is also used to pre-process the user face image; input the pre-processed user face image into a pre-trained feature point recognition model for prediction to obtain target face feature point measurement values; query the pre-stored preset face feature point measurement values ​​according to the user identifier; and authenticate the target face feature point measurement values ​​according to the preset face feature point measurement values.

[0142] In one embodiment, the image information includes a signature video; the authentication module 410 is also used to obtain a signature timestamp corresponding to the electronic signature; extract a target signature image from the signature video according to the signature timestamp; extract a target face image from the target signature image through a trained face recognition model; obtain a preset face image corresponding to the user identification; and authenticate the target face image according to the preset face image.

[0143] In one embodiment, the authentication module 410 is also used to authenticate the electronic signature according to a specified authentication method; the storage module 412 is also used to store the user identification, image information and the business validation document carrying the electronic signature in correspondence when both the image information and the electronic signature are authenticated.

[0144] In one embodiment, the authentication module 410 is also used to decompose the electronic signature into strokes according to a preset decomposition method to obtain a corresponding plurality of strokes; input each stroke in turn into a pre-trained feature recognition model for prediction to obtain a target stroke feature corresponding to each stroke; query the pre-stored preset stroke features according to the user identifier; and authenticate the target stroke features according to the preset stroke features.

[0145] In one embodiment, the authentication module 410 is further used to obtain a target signature trajectory corresponding to the electronic signature; query a pre-stored preset signature trajectory according to the user identifier; and authenticate the electronic signature according to the preset signature trajectory and the target signature trajectory.

[0146] In one embodiment, Figure 5 As shown, the identity authentication device 400 based on electronic signature further includes: a query module 414;

[0147] The query module 414 is used to obtain the business query instruction corresponding to the user identification sent by the user terminal; obtain the target image information corresponding to the business query instruction collected by the image collector; authenticate the target image information based on the image information; when the target image information is authenticated, the business effectiveness approval document carrying the electronic signature is sent to the user terminal.

[0148] For the specific definition of the identity authentication device based on electronic signature, please refer to the definition of the identity authentication method based on electronic signature above, which will not be repeated here. Each module in the above-mentioned identity authentication device based on electronic signature can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0149] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an identity authentication method based on an electronic signature is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0150] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0151] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program: obtaining a business validation approval corresponding to a user identifier; sending the business validation approval to a user terminal; receiving an electronic signature of the user terminal in response to feedback of the business validation approval; obtaining image information corresponding to the user identifier and the electronic signature collected by an image collector; authenticating the image information according to a preset authentication method; and when the authentication is passed, storing the user identifier, the image information, and the business validation approval carrying the electronic signature in correspondence.

[0152] In one embodiment, the image information includes a user face image; the image information is authenticated according to a preset authentication method, including: preprocessing the user face image; inputting the preprocessed user face image into a pre-trained feature point recognition model for prediction to obtain target face feature point measurement values; querying pre-stored preset face feature point measurement values ​​according to the user identifier; and authenticating the target face feature point measurement values ​​according to the preset face feature point measurement values.

[0153] In one embodiment, the image information includes a signature video; the image information is authenticated according to a preset authentication method, including: obtaining a signature timestamp corresponding to the electronic signature; extracting a target signature image from the signature video according to the signature timestamp; extracting a target face image from the target signature image through a trained face recognition model; obtaining a preset face image corresponding to a user identifier; and authenticating the target face image according to the preset face image.

[0154] In one embodiment, when the processor executes the computer program, it also implements the following steps: authenticating the electronic signature according to a specified authentication method; when the authentication is passed, the user identification, image information and the business effectiveness approval document carrying the electronic signature are stored correspondingly, including: when the image information and the electronic signature are both authenticated, the user identification, image information and the business effectiveness approval document carrying the electronic signature are stored correspondingly.

[0155] In one embodiment, an electronic signature is authenticated according to a specified authentication method, including: decomposing the electronic signature into strokes according to a preset decomposition method to obtain a corresponding plurality of strokes; inputting each stroke in turn into a pre-trained feature recognition model for prediction to obtain a target stroke feature corresponding to each stroke; querying a pre-stored preset stroke feature according to a user identifier; and authenticating the target stroke feature according to the preset stroke feature.

[0156] In one embodiment, authenticating an electronic signature according to a specified authentication method includes: obtaining a target signature trajectory corresponding to the electronic signature; querying a pre-stored preset signature trajectory according to a user identifier; and authenticating the electronic signature according to the preset signature trajectory and the target signature trajectory.

[0157] In one embodiment, when the processor executes the computer program, it also implements the following steps: obtaining a business query instruction corresponding to the user identification sent by the user terminal; obtaining target image information corresponding to the business query instruction collected by the image collector; authenticating the target image information based on the image information; when the target image information is authenticated, sending the business effectiveness approval document carrying the electronic signature to the user terminal.

[0158] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: obtaining a business validation approval document corresponding to a user identifier; sending the business validation approval document to a user terminal; receiving an electronic signature of the user terminal in response to feedback of the business validation approval document; obtaining image information corresponding to the user identifier and the electronic signature collected by an image collector; authenticating the image information according to a preset authentication method; and when the authentication is passed, storing the user identifier, the image information, and the business validation approval document carrying the electronic signature in correspondence.

[0159] In one embodiment, the image information includes a user face image; the image information is authenticated according to a preset authentication method, including: preprocessing the user face image; inputting the preprocessed user face image into a pre-trained feature point recognition model for prediction to obtain target face feature point measurement values; querying pre-stored preset face feature point measurement values ​​according to the user identifier; and authenticating the target face feature point measurement values ​​according to the preset face feature point measurement values.

[0160] In one embodiment, the image information includes a signature video; the image information is authenticated according to a preset authentication method, including: obtaining a signature timestamp corresponding to the electronic signature; extracting a target signature image from the signature video according to the signature timestamp; extracting a target face image from the target signature image through a trained face recognition model; obtaining a preset face image corresponding to a user identifier; and authenticating the target face image according to the preset face image.

[0161] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: authenticating the electronic signature according to a specified authentication method; when the authentication is passed, the user identification, image information and the business validity approval document carrying the electronic signature are stored correspondingly, including: when the image information and the electronic signature are both authenticated, the user identification, image information and the business validity approval document carrying the electronic signature are stored correspondingly.

[0162] In one embodiment, an electronic signature is authenticated according to a specified authentication method, including: decomposing the electronic signature into strokes according to a preset decomposition method to obtain a corresponding plurality of strokes; inputting each stroke in turn into a pre-trained feature recognition model for prediction to obtain a target stroke feature corresponding to each stroke; querying a pre-stored preset stroke feature according to a user identifier; and authenticating the target stroke feature according to the preset stroke feature.

[0163] In one embodiment, authenticating an electronic signature according to a specified authentication method includes: obtaining a target signature trajectory corresponding to the electronic signature; querying a pre-stored preset signature trajectory according to a user identifier; and authenticating the electronic signature according to the preset signature trajectory and the target signature trajectory.

[0164] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining a business query instruction corresponding to the user identifier sent by the user terminal; obtaining target image information corresponding to the business query instruction collected by the image collector; authenticating the target image information based on the image information; when the target image information is authenticated, sending the business effectiveness approval document carrying the electronic signature to the user terminal.

[0165] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0166] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0167] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. An identity authentication method based on electronic signature, the method comprising: Obtain the business validation document corresponding to the user ID; Sending the business validation approval document to the user terminal; Receiving an electronic signature from the user terminal corresponding to the feedback of the business validation approval document; Acquire image information corresponding to the user identifier and the electronic signature acquired by an image collector; When the image information is a user face image, identifying the face contour in the user face image and extracting the identified face image, detecting key features in the identified face image, and performing affine transformation on the key features to align and calibrate the face, thereby obtaining a preprocessed user face image; Input the pre-processed user face image into a pre-trained feature point recognition model for prediction, obtain target face feature point measurement values, query pre-stored preset face feature point measurement values ​​according to the user identifier, and authenticate the target face feature point measurement values ​​according to the preset face feature point measurement values; Decomposing the electronic signature into strokes according to a preset decomposition method to obtain a corresponding plurality of strokes, sorting the obtained plurality of strokes according to the stroke writing order of the Chinese characters in the electronic signature, and inputting each of the strokes into a pre-trained feature recognition model in sequence according to the sorting to perform prediction, obtaining a target stroke feature corresponding to each of the strokes, querying a pre-stored preset stroke feature according to the user identifier, authenticating the target stroke feature according to the preset stroke feature, wherein the target stroke feature includes an inclination angle of the stroke, a bending angle, a number of fluctuations, and a length of the stroke; Acquire a target signature trajectory corresponding to the electronic signature, query a pre-stored preset signature trajectory according to the user identifier, and authenticate the electronic signature according to the preset signature trajectory and the target signature trajectory, wherein the target signature trajectory includes the stroke sequence or writing font of the user's name; When both the image information and the electronic signature are authenticated, the user identification, the image information and the business validation approval document carrying the electronic signature are stored correspondingly.

2. The method according to claim 1, characterized in that The method further comprises: The image information also includes a signature video; When the image information is a signature video, obtaining a signature timestamp corresponding to the electronic signature; Extracting a target signature image from the signature video according to the signature timestamp; Extracting a target face image from the target signature image using a trained face recognition model; Acquire a preset face image corresponding to the user identifier; The target facial image is authenticated according to the preset facial image.

3. The method according to claim 1, characterized in that: The image information includes the user's face image, user signature image and signature video.

4. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Acquire a service query instruction corresponding to the user identifier sent by the user terminal; Acquire target image information corresponding to the business query instruction collected by the image collector; authenticating the target image information according to the image information; When the target image information is authenticated, the business validation document carrying the electronic signature is sent to the user terminal.

5. An identity authentication device based on electronic signature, characterized in that: The device comprises: The approval document acquisition module is used to obtain the business effective approval document corresponding to the user ID; A sending module, used for sending the service validation document to a user terminal; A receiving module, used to receive the electronic signature of the user terminal corresponding to the feedback of the business validation approval document; An image acquisition module, used to acquire image information corresponding to the user identification and the electronic signature acquired by the image collector; A preprocessing module, for, when the image information is a user face image, identifying a face contour in the user face image and extracting the identified face image, detecting key features in the identified face image, and performing affine transformation on the key features to align and calibrate the face, thereby obtaining a preprocessed user face image; An authentication module is used to input the pre-processed user face image into a pre-trained feature point recognition model for prediction, obtain target face feature point measurement values, query pre-stored preset face feature point measurement values ​​according to the user identifier, and authenticate the target face feature point measurement values ​​according to the preset face feature point measurement values; The authentication module is also used to decompose the electronic signature into strokes according to a preset decomposition method to obtain a corresponding plurality of strokes, sort the obtained plurality of strokes according to the stroke writing order of the Chinese characters in the electronic signature, and input each of the strokes into a pre-trained feature recognition model in sequence according to the sorting to perform prediction, obtain target stroke features corresponding to each of the strokes, query the pre-stored preset stroke features according to the user identifier, and authenticate the target stroke features according to the preset stroke features, wherein the target stroke features include the inclination angle of the stroke, the bending angle, the number of fluctuations and the length of the stroke; The authentication module is further used to obtain a target signature trajectory corresponding to the electronic signature, query a pre-stored preset signature trajectory according to the user identifier, and authenticate the electronic signature according to the preset signature trajectory and the target signature trajectory, wherein the target signature trajectory includes the stroke sequence or writing font of the user's name; The storage module is used to store the user identification, the image information and the business validation approval document carrying the electronic signature in correspondence when the image information and the electronic signature are both authenticated.

6. The device according to claim 5, characterized in that The image information includes a signature video, and the authentication module is also used to obtain a signature timestamp corresponding to the electronic signature; extract a target signature image from the signature video according to the signature timestamp, extract a target face image from the target signature image through a trained face recognition model, obtain a preset face image corresponding to the user identification, and authenticate the target face image according to the preset face image.

7. The device according to claim 5, characterized in that The image information includes the user's face image, user signature image and signature video.

8. The device according to claim 5, characterized in that The device also includes a query module, which is used to obtain a business query instruction corresponding to the user identifier sent by the user terminal, obtain the target image information corresponding to the business query instruction collected by the image collector, authenticate the target image information based on the image information, and when the target image information is authenticated, send the business validity approval document carrying the electronic signature to the user terminal.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images