Method, device and equipment for electronic signature verification and computer storage medium
By storing multiple verification images in different storage areas of the blockchain and allowing user devices to select a signature image for verification, the problem of poor security in electronic signature verification is solved, achieving higher security and accuracy.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA MOBILE COMM CORP GUANGXI CO LTD
- Filing Date
- 2024-12-17
- Publication Date
- 2026-06-19
AI Technical Summary
The security of electronic signature verification in existing technologies is poor because electronic signatures are stored on the blockchain, which can be accessed by any individual with access rights, resulting in low information transparency.
By storing multiple verification images with different texts in different storage areas of the blockchain, user devices select a signature image and verify it. After the verification is successful, the server generates an electronic signature. The intermediate layer server ensures secure communication and avoids direct transmission of the complete signature.
It improves the security of electronic signature storage and verification, prevents unauthorized signature acquisition, and enhances the accuracy and security of user authentication.
Smart Images
Figure CN122247625A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of blockchain technology, and in particular relates to a method, apparatus, device and computer storage medium for electronic signature verification. Background Technology
[0002] Electronic signatures are an important method of identity authentication and are widely used in various industries, such as banking, hospitals, and law. Ensuring the security of electronic signature verification has become a crucial issue.
[0003] Existing methods for verifying electronic signatures often store the electronic signature in the blockchain and then compare it with the user's signature on the signature canvas. Because the blockchain is transparent, any individual with access rights can query and obtain the stored electronic signature information. Therefore, the security of existing methods for verifying electronic signatures is poor. Summary of the Invention
[0004] This application provides a method, apparatus, device, and computer storage medium for electronic signature verification to address the problem of poor security in existing electronic signature verification methods.
[0005] In a first aspect, embodiments of this application provide a method for verifying electronic signatures, applied to a server, the method comprising:
[0006] Receive an electronic signature acquisition request sent by the user equipment. The electronic signature acquisition request includes the user identifier.
[0007] The verification images of the text corresponding to the user identifier are obtained from different storage areas of the blockchain device. The verification images include the signature image corresponding to the user identifier; multiple verification images of different texts are stored in different storage areas.
[0008] Send a verification image to the user equipment so that the user equipment can select a signature image from the verification image;
[0009] Receive the selection result sent by the user equipment;
[0010] If the selection results include a signature image of text corresponding to the user identifier, the signature image is verified according to the preset signature image identifier. If the verification passes, an electronic signature is generated and sent to the user device.
[0011] Secondly, embodiments of this application provide a method for verifying electronic signatures, applied to user equipment, the method comprising:
[0012] Send an electronic signature retrieval request to the server. The electronic signature retrieval request includes the user identifier.
[0013] The system receives a verification image sent by the server. The verification image includes a signature image corresponding to the user identifier and is stored in different storage areas of the blockchain device.
[0014] Based on the image selection command input by the user, the verification image is selected, and the selection result is obtained;
[0015] Send the selection result to the server. The selection result includes the verification image selected by the user device. When the server selects a signature image containing text corresponding to the user identifier, it verifies the signature image according to the preset signature image identifier. If the verification passes, it generates an electronic signature.
[0016] Receive electronic signatures sent by server equipment.
[0017] Thirdly, embodiments of this application provide an electronic signature verification device applied to a server, the device comprising:
[0018] The receiving module is used to receive electronic signature acquisition requests sent by user equipment. The electronic signature acquisition request includes a user identifier.
[0019] The acquisition module is used to acquire verification images of text corresponding to user identifiers from different storage areas of the blockchain device. The verification images include the signature image corresponding to the user identifier; different storage areas store multiple verification images of different texts.
[0020] The sending module is used to send a verification image to the user equipment so that the user equipment can select a signature image from the verification image;
[0021] The receiving module is also used to receive the selection results sent by the user equipment;
[0022] The sending module is also used to verify the signature image according to the preset signature image identifier when the selection result includes a signature image of text corresponding to the user identifier. If the verification is successful, the module combines and generates an electronic signature and sends the electronic signature to the user device.
[0023] Fourthly, embodiments of this application provide an electronic signature verification device applied to a user equipment, the device comprising:
[0024] The sending module is used to send an electronic signature retrieval request to the server. The electronic signature retrieval request includes the user identifier.
[0025] The receiving module is used to receive the verification image sent by the server. The verification image includes the signature image corresponding to the user identifier and is stored in different storage areas of the blockchain device.
[0026] The selection module is used to select images from the verification images based on the image selection instructions input by the user, and obtain the selection results;
[0027] The sending module is also used to send the selection result to the server. The selection result includes the verification image selected by the user device. When the server includes a signature image of the text corresponding to the user identifier in the selection result, it verifies the signature image according to the preset signature image identifier. If the verification passes, it combines and generates an electronic signature.
[0028] The receiving module is also used to receive electronic signatures sent by the server device.
[0029] Fifthly, embodiments of this application provide a terminal device, the device including: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements the electronic signature verification method as described in the first or second aspect.
[0030] In a sixth aspect, embodiments of this application provide a computer storage medium storing computer program instructions, which, when executed by a processor, implement the electronic signature verification method as described in the first or second aspect.
[0031] In a seventh aspect, embodiments of this application provide a computer program product in which instructions, when executed by a processor of an electronic device, cause the electronic device to perform an electronic signature verification method as described in the first or second aspect.
[0032] This application provides a method, apparatus, device, and computer storage medium for electronic signature verification. In this method, a user device first sends an electronic signature retrieval request, including a user identifier, to a server. Upon receiving the request, the server retrieves verification images of the text corresponding to the user identifier from different storage areas of the blockchain device. Each verification image includes a signature image corresponding to the user identifier. Multiple verification images of different texts are stored in different storage areas. The storage device stores signature images, not the complete electronic signature, thus improving the security of electronic signature storage. The server device acts as an intermediary layer, ensuring secure communication between the user device and the storage device. The server sends verification images to the user device. After receiving the verification images, the user device selects a signature image from the verification images and sends the selection result to the server. The server receives the selection result. If the selection result includes a signature image of the text corresponding to the user identifier, the server verifies the signature image according to a preset signature image identifier. If the verification passes, the server generates an electronic signature and sends it to the user device. Only after the user passes the verification does the server device generate the target signature image based on the signature image identifier, thus improving the security of electronic signature verification. Attached Figure Description
[0033] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0034] Figure 1 This is a schematic diagram of the structure of the electronic signature verification system provided in the embodiments of this application;
[0035] Figure 2 This is a flowchart illustrating the electronic signature verification method provided in an embodiment of this application;
[0036] Figure 3 This is a flowchart illustrating the method for obtaining a signature image provided in an embodiment of this application;
[0037] Figure 4 This is a flowchart illustrating the text segmentation method provided in an embodiment of this application;
[0038] Figure 5 This is a schematic flowchart of the contour extraction method provided in the embodiments of this application;
[0039] Figure 6 This is a schematic diagram of the structure of a device applied to a server according to an embodiment of this application;
[0040] Figure 7 This is a schematic diagram of the structure of a device applied to a user equipment according to an embodiment of this application;
[0041] Figure 8 This is a schematic diagram of the structure of the terminal device provided in the embodiments of this application. Detailed Implementation
[0042] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.
[0043] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.
[0044] With the development of e-commerce and e-government, the industry has put forward many security requirements for electronic contracts and electronic signature functions. How to resolve the conflict between the legal openness and storage confidentiality of image signatures has become an important issue. Existing technology uploads electronic signatures to the blockchain, which can achieve the purpose of being publicly available and tamper-proof. However, if the complete image signature is directly published on the blockchain, it may be stolen by external visitors to the Internet, making the security of electronic signature verification low.
[0045] To address the shortcomings of existing technologies, this application provides a method, apparatus, device, and computer storage medium for electronic signature verification. In this method, a user device first sends an electronic signature retrieval request, including a user identifier, to a server. Upon receiving the request, the server retrieves verification images of the text corresponding to the user identifier from different storage areas of the blockchain device. Each verification image includes a signature image corresponding to the user identifier. Multiple verification images of different texts are stored in different storage areas. The storage device stores signature images, not complete electronic signatures, thus improving the security of electronic signature storage. The server device acts as an intermediary layer, ensuring secure communication between the user device and the storage device. The server sends verification images to the user device. Upon receiving the verification images, the user device selects a signature image from the verification images and sends the selection result to the server. The server receives the selection result. If the selection result includes a signature image of the text corresponding to the user identifier, the server verifies the signature image according to a preset signature image identifier, combines the signature images to generate an electronic signature, and sends the electronic signature to the user device. Only after the user passes verification does the server device generate the target signature image based on the signature image identifier, further enhancing the security of electronic signature verification.
[0046] The electronic signature verification system provided in the embodiments of this application will be introduced first below.
[0047] Figure 1 A schematic diagram of the structure of an electronic signature verification system 100 provided in one embodiment of this application is shown. Figure 1 As shown, the system may include user equipment 110, server 120, and blockchain device 130. Server 120 may include signature acquisition module 121, network communication module 122, intelligent analysis module 123, and internal storage module 124.
[0048] The user equipment 110 includes a screen and operating devices for information display and interaction. This user equipment can be a touchscreen, keyboard and mouse, stylus, or other interactive device. The signature acquisition module 121, equipped with a camera or image scanning module, acquires the user's paper signature, converts it into a digital image, and sends it to the intelligent analysis module 123. It can also acquire electronic signature images uploaded by the user equipment 110. The network communication module 122 is used for communication between the internal modules of server 120 and external systems. The intelligent analysis module 123 is used for the recognition and verification of electronic signatures. The internal storage module 124 is used to store user identification information. The blockchain device 130 is an external blockchain server cluster, which can include a public or internal network blockchain server cluster, used for the uploading, publication, and storage of verification images on the blockchain.
[0049] The method for verifying electronic signatures provided in the embodiments of this application is described below with reference to the accompanying drawings.
[0050] Figure 2 A flowchart illustrating an embodiment of an electronic signature verification method provided in this application is shown. Figure 2 As shown, the method may include the following steps: S201 to S203.
[0051] S201, the user equipment sends an electronic signature acquisition request to the server. The electronic signature acquisition request includes the user identifier.
[0052] The user equipment is a device that communicates with the server, which may include a smartphone, tablet, or computer; the electronic signature is a signature in the form of an electronic image used to prove the user's identity; and the user identifier is a string or number used to uniquely identify the user, which may include a username or a user identification document (ID).
[0053] In some embodiments, when a user equipment sends an electronic signature retrieval request to a server, it can send a request containing the user's identifier to the server via Hypertext Transfer Protocol Secure (HTTPS).
[0054] The user equipment sends an electronic signature retrieval request to the server to obtain an electronic signature associated with a specific user identifier.
[0055] S202, the server receives the electronic signature acquisition request sent by the user device and obtains the verification image of the text corresponding to the user identifier from different storage areas of the blockchain device. The verification image includes the signature image corresponding to the user identifier; different storage areas store multiple verification images of different texts.
[0056] The blockchain consists of multiple data blocks connected by a chain structure, featuring distributed storage and transparency; the verification image is an image used to verify the user's identity, and the verification images of the text corresponding to the user's identifier are stored in different storage areas of the blockchain device.
[0057] In some embodiments, the verification image may be a single-character image, including a signature image corresponding to the user identifier and other images of the text corresponding to the user identifier. Other images of the text corresponding to the user identifier may be signature images with the same text as the signature image corresponding to the user identifier but different handwriting.
[0058] In one example, the image could be part of the user's own signature, the same word signed by someone else, or an image of the same word generated by artificial intelligence that does not resemble the user's own handwriting style.
[0059] The server first parses the user identifier in the request and uses the user identifier to obtain the data on the blockchain device. Since the electronic signature image is split into multiple single-character signature images and stored in different storage areas of the blockchain device, even if the signature image stored in the blockchain device is obtained, the corresponding electronic signature image cannot be obtained, thus improving the security of electronic signature image storage and verification.
[0060] By acquiring a verification image, it can be used for subsequent user verification and electronic signature combinations.
[0061] S203, the server sends a verification image to the user equipment so that the user equipment can select a signature image from the verification image.
[0062] The server sends the acquired verification image back to the user's device application or web interface so that the user can select from the verification images to authenticate.
[0063] S204, the user equipment receives the verification image and selects the verification image according to the image selection instruction input by the user, and obtains the selection result.
[0064] The image selection instruction is an input instruction used to select an image from the verification image.
[0065] In some embodiments, the verification image may be selected only once, and the verification is successful if the selection is correct; alternatively, the verification image may be displayed multiple times and selected multiple times, and the verification is considered successful when all selections by the user are correct or the correct proportion reaches a set value. Each time the verification image is displayed, the verification image displayed on the user device may not include the user's signature image or may include at least one user's signature image.
[0066] In some embodiments, selecting a verification image may include selecting whether the verification image includes the user's signature image, or selecting which option in the verification image belongs to the user's signature image.
[0067] In some embodiments, the selection result may include the selection result displayed for each verification image. The selection result may include the verification image displayed this time not including the user's signature image or the target image selected in the verification image displayed this time. The target image is the verification image that belongs to the user's signature image selected by the user.
[0068] By receiving image selection instructions from the user, the system selects a verification image and generates a selection result, which is then used by the server for verification, thereby improving the security of electronic signature verification.
[0069] S205, the user equipment sends the selection result to the server.
[0070] S206, the server receives the selection result. If the selection result includes a signature image of the text corresponding to the user identifier, the server verifies the signature image according to the preset signature image identifier. If the verification passes, the server generates an electronic signature.
[0071] If the selected results do not include a signature image of the text corresponding to the user identifier, the user verification is deemed to have failed, and a verification failure message is sent to the user device.
[0072] In some embodiments, the signature image is verified according to a preset signature image identifier. If the image identifier in the user's selection result is the same as the signature image identifier of the text corresponding to the user identifier in the verification image, the signature images are combined to generate an electronic seal according to the correspondence between the user identifier and the signature image identifier. The correspondence between the user identifier and the signature image identifier is stored in the server.
[0073] In some embodiments, if the image identifier in the user's selection result is different from the signature image identifier of the text corresponding to the user identifier in the verification image, the user verification is determined to have failed, and a verification failure message is sent to the user device.
[0074] Since users know their own handwriting best, the system will only allow them to use the electronic signature if they select the correct handwriting and are identified as the signatory. If a user selects the wrong handwriting multiple times, the system will consider the user not to be the signatory and refuse service, thus preventing impersonation of users from obtaining electronic signatures.
[0075] The server verifies the selected image identifier and signature image identifier. If the verification is successful, the signature images are combined sequentially according to the correspondence between the user identifier and the signature image identifier to generate an electronic seal, which improves the security of signature verification.
[0076] S207, The server sends an electronic signature to the user equipment.
[0077] The server sends an electronic signature to the verified user device, which the user can then use to sign documents.
[0078] After receiving a request for an electronic signature, the server retrieves verification images of the text corresponding to the user's identifier from different storage areas of the blockchain device. Multiple verification images of different texts are stored in different storage areas. The storage device stores signature images, not the complete electronic signature, enhancing the security of electronic signature storage. The server device acts as an intermediary layer, ensuring secure communication between the user device and the storage device. The server sends verification images to the user device. After receiving the verification images, the user device selects a signature image from the verification images and sends the selection result to the server. The server receives the selection result. If the selection result includes a signature image of the text corresponding to the user's identifier, it verifies the signature image according to a preset signature image identifier, combines the results to generate an electronic signature, and sends the electronic signature to the user device. Only after the user passes verification does the server device generate the target signature image based on the signature image identifier, improving the verification security of the electronic signature.
[0079] In some embodiments, such as Figure 3 As shown, before receiving the electronic signature acquisition request from the user equipment, the method may further include: S301 to S303.
[0080] S301, The server obtains the user's electronic signature image.
[0081] The electronic signature image can be a scanned document, a photograph, or an image captured from a touchscreen device.
[0082] S302, the server performs text segmentation on the electronic signature image to obtain multiple signature images.
[0083] The signature image is an image of a single segmented character.
[0084] In some embodiments, when performing text segmentation on an electronic signature image, an image recognition algorithm can be used to identify the text outlines in the image and segment the text based on these outlines. The image recognition algorithm can include operator-based image recognition algorithms and deep learning network-based image recognition algorithms. Operators can include the Sobel operator, the Canny edge detection operator, and the Prewitt cross-differentiation operator, etc., and deep learning networks can include convolutional neural networks and recurrent neural networks, etc.
[0085] By segmenting text, electronic signature images can be more accurately identified and analyzed, reducing background noise and interference from other information, improving the accuracy of signature verification, and making signature images easier to manage and use.
[0086] S303, the server sends and stores the signature image to the storage area corresponding to the text in the blockchain device.
[0087] When storing signature images, different text signature images are stored in different storage areas of the blockchain device, while images with the same text are stored in the same storage area.
[0088] By segmenting the electronic signature image into text, single-character signature images are obtained and stored in different storage areas of the blockchain device, thereby improving the security of electronic signature image storage.
[0089] In some embodiments, the electronic signature image is split into n signature images character by character according to the user's name, with each character having its own signature image. If the user signs X times (X>=1), then each time the name is split into a single character image as the signature image, resulting in nX signature images.
[0090] In some embodiments, before the server sends the signature image to the storage area corresponding to the text in the blockchain device, it may further include:
[0091] Assign a random user identifier to each user account, and a random signature image identifier to each signature image. Store the relationship between the user identifier and the corresponding signature image identifier, as well as the order of the signature image identifiers, on the server.
[0092] The user identifier can be used to find the corresponding signature image, but the relationship between the user identifier and the corresponding signature image, as well as the order of the signature images, are not published on the blockchain and are not made public. They are only stored on the server. Even if others traverse the publicly available image chain, they cannot accurately obtain the complete electronic signature image.
[0093] In some embodiments, such as Figure 4As shown, text segmentation is performed on the electronic signature image to obtain multiple signature images, which may include: S401 to S403.
[0094] S401, The server extracts the contour of the electronic signature image to obtain a text segmentation image;
[0095] S402, the server inputs the text segmentation image into the text recognition model, uses the convolution kernel of the text recognition model to extract the shape features of the text segmentation image, and determines the corresponding signature text by weighted summation based on the shape features and preset model parameters;
[0096] S403, the server segments the text image based on the signature text to obtain multiple signature images.
[0097] By employing contour extraction and character recognition technologies, signature images can be identified and segmented more accurately, improving verification accuracy. Automated image processing and segmentation reduce manual operations and increase processing efficiency.
[0098] The weighted summation process is actually a scoring mechanism used to evaluate the similarity between the text features extracted from the text segmentation image and the known text, and to take the known text with the highest similarity as the corresponding signature text.
[0099] In some embodiments, such as Figure 5 As shown, contour extraction is performed on the electronic signature image to obtain a text segmentation image, which may include: S501 to S504.
[0100] S501, the server converts the electronic signature image into a grayscale image.
[0101] Grayscale image processing involves processing grayscale images, which contain only brightness information and not color information. Therefore, it is simpler and less computationally intensive than color image processing, allowing for faster contour extraction and feature recognition. Converting color electronic signature images to grayscale simplifies the data, reduces computational complexity, and increases processing speed, thus improving the efficiency and accuracy of subsequent processing.
[0102] S502, the server calculates the gradient magnitude of each pixel in the grayscale image.
[0103] In some embodiments, the gradient magnitude is obtained by calculating the square root of the sum of the squares of the components of the gradient in the x and y directions.
[0104] Gradient is the rate of change of image brightness. Areas with large gradient magnitudes are usually located at edges or contours in the image. By calculating gradient magnitudes, servers can more easily identify these key features, providing a foundation for subsequent contour extraction.
[0105] S503, the server determines the target segmentation threshold based on the relationship between gradient magnitude and segmentation threshold.
[0106] In some embodiments, the segmentation threshold can be the average gradient magnitude of all pixels in the grayscale image.
[0107] By selecting an appropriate segmentation threshold, the server can distinguish edges and contours in an image from the background and other non-critical features. This helps reduce noise and interference, improving the accuracy and stability of contour extraction.
[0108] S504, the server extracts the contour of the grayscale image based on the target segmentation threshold to obtain the text segmentation image.
[0109] By using grayscale conversion and gradient calculation, the complexity of data processing is reduced and the processing speed is improved, resulting in segmented images containing text outlines.
[0110] In some embodiments, before segmenting the text segmentation image according to the signature text to obtain multiple signature images, the method may further include:
[0111] The server obtains the name information of the user corresponding to the target signature image;
[0112] The server compares the signature text with the text of the name information. If the signature text and the text of the name information are different, the server determines the loss function value based on the signature text and the text of the name information.
[0113] The server determines the target model parameters based on the loss function value and updates the text recognition model until the signature text matches the text in the name information, thus obtaining the target signature text.
[0114] The text segmentation image is segmented based on the signature text to obtain multiple signature images, including:
[0115] The server segments the text image based on the target signature text, resulting in multiple signature images.
[0116] By continuously updating the model parameters until the signature text matches the name information, the model's recognition accuracy and segmentation accuracy can be improved, which helps to adapt to constantly changing signature styles and image quality.
[0117] In some embodiments, the server sending and storing a signature image to the storage area corresponding to the text in the blockchain device may include:
[0118] The server assigns a signature image identifier to the signature image and stores the correspondence between the signature image identifier and the user identifier, as well as the combination relationship of the signature image identifiers;
[0119] The server sends the signature image and signature image identifier to the storage area corresponding to the text in the blockchain device for use in the blockchain device's storage.
[0120] The correspondence between signature image identifiers and user identifiers refers to which signature image identifiers correspond to which user identifiers. The combination relationship of signature image identifiers refers to the order relationship between signature images, which can be recombined into an electronic signature according to the order relationship. Both signature image identifiers and user identifiers can be randomly assigned.
[0121] By leveraging the immutability and distributed nature of blockchain to store signature images, the distributed storage of blockchain ensures that signature images will not be lost due to a single point of failure, thereby ensuring the security and permanent preservation of signature images. It also prevents unauthorized tampering and enhances the integrity and reliability of the data.
[0122] By assigning identifiers to signed images and saving the relationships between them, it can be ensured that each signed image can be tracked and managed.
[0123] In some embodiments, the server stores the correspondence between signature image identifiers and user identifiers, and the combination relationship of signature image identifiers to generate an electronic signature, which may include:
[0124] The server obtains the signature image identifier corresponding to the user identifier based on the relationship between the signature image identifier and the user identifier.
[0125] The server combines signature image identifiers according to the combination relationship of the signature image identifiers to generate an electronic signature.
[0126] By using the user identifier, the signature image identifier corresponding to the user identifier can be quickly obtained.
[0127] The signature image and signature image identifier are only sent to the storage area of the blockchain device for storage. The association between the signature image identifiers is stored in the server and not sent. Even if others obtain the stored signature images, they cannot obtain the sequence relationship of the signature images. Therefore, they cannot recombine the signature images into an electronic signature, which improves the security of electronic signature use.
[0128] Figure 6 An embodiment of this application illustrates an electronic signature verification device 600, applied to a server. This device may include:
[0129] The receiving module 601 is used to receive an electronic signature acquisition request sent by the user equipment. The electronic signature acquisition request includes a user identifier.
[0130] The acquisition module 602 is used to acquire verification images of text corresponding to user identifiers from different storage areas of the blockchain device. The verification images include signature images corresponding to user identifiers; multiple verification images of different texts are stored in different storage areas.
[0131] The sending module 603 is used to send a verification image to the user equipment so that the user equipment can select a signature image from the verification image;
[0132] The receiving module 601 is also used to receive the selection result sent by the user equipment;
[0133] The sending module 603 is also used to verify the signature image according to the preset signature image identifier when the selection result includes a signature image of text corresponding to the user identifier, and combine them to generate an electronic signature and send the electronic signature to the user equipment if the verification is successful.
[0134] In some embodiments, the electronic signature verification device 600 may further include:
[0135] The acquisition module 602 is also used to acquire the user's electronic signature image;
[0136] The segmentation module is used to segment the text in the electronic signature image to obtain multiple signature images;
[0137] The sending module 603 is also used to send and store the signature image to the storage area corresponding to the text in the blockchain device.
[0138] In some embodiments, the electronic signature verification device 600 may further include:
[0139] The extraction module is used to extract the contours of electronic signature images to obtain text segmentation images;
[0140] The recognition module is used to input the text segmentation image into the text recognition model, use the convolution kernel of the text recognition model to extract the shape features of the text segmentation image, and determine the corresponding signature text by weighted summation based on the shape features and preset model parameters.
[0141] The segmentation module is also used to segment the text image based on the signature text to obtain multiple signature images.
[0142] In some embodiments, the electronic signature verification device 600 may further include:
[0143] The conversion module is used to convert electronic signature images into grayscale images;
[0144] The calculation module is used to calculate the gradient magnitude of each pixel in a grayscale image;
[0145] The determination module is used to determine the target segmentation threshold based on the relationship between the gradient magnitude and the segmentation threshold;
[0146] The extraction module is also used to extract the contours of the grayscale image based on the target segmentation threshold to obtain the text segmentation image.
[0147] In some embodiments, the electronic signature verification device 600 may further include:
[0148] The acquisition module 602 is also used to acquire the name information of the user corresponding to the target signature image;
[0149] The determination module is also used to compare the text of the signature and the text of the name information. When the text of the signature and the text of the name information are different, the loss function value is determined based on the text of the signature and the text of the name information.
[0150] The update module is used to determine the target model parameters based on the loss function value and update the text recognition model until the signature text is the same as the text in the name information, thus obtaining the target signature text;
[0151] The segmentation module is also used to segment the text image based on the target signature text to obtain multiple signature images.
[0152] In some embodiments, the electronic signature verification device 600 may further include:
[0153] The storage module is used to assign signature image identifiers to signature images, and to store the correspondence between signature image identifiers and user identifiers, as well as the combination relationship of signature image identifiers;
[0154] The sending module 603 is also used to send the signature image and signature image identifier to the storage area corresponding to the text in the blockchain device for storage in the blockchain device.
[0155] In some embodiments, the electronic signature verification device 600 may further include:
[0156] The acquisition module 602 is also used to acquire the signature image identifier corresponding to the user identifier based on the relationship between the signature image identifier and the user identifier;
[0157] The generation module is used to combine signature image identifiers according to the combination relationship of signature image identifiers to generate electronic signatures.
[0158] Figure 6 The various modules in the illustrated device can achieve Figure 2 The various steps involved, and the corresponding technical effects achieved, will not be elaborated upon here for the sake of brevity.
[0159] Figure 7An embodiment of this application illustrates an electronic signature verification device 700, applied to a user equipment. The device may include:
[0160] The sending module 701 is used to send an electronic signature acquisition request to the server. The electronic signature acquisition request includes a user identifier.
[0161] The receiving module 702 is used to receive the verification image sent by the server. The verification image includes the signature image corresponding to the user identifier and is stored in different storage areas of the blockchain device.
[0162] The selection module 703 is used to select a verification image according to the image selection command input by the user and obtain the selection result;
[0163] The sending module 701 is also used to send the selection result to the server. The selection result includes the verification image selected by the user equipment. When the server includes a signature image of the text corresponding to the user identifier in the selection result, it verifies the signature image according to the preset signature image identifier. If the verification is successful, it combines and generates an electronic signature.
[0164] The receiving module 702 is also used to receive electronic signatures sent by the server device.
[0165] Figure 7 The various modules in the illustrated device can achieve Figure 2 The various steps involved, and the corresponding technical effects achieved, will not be elaborated upon here for the sake of brevity.
[0166] Figure 8 A schematic diagram of the hardware structure of the terminal device provided in an embodiment of this application is shown.
[0167] The terminal device may include a processor 801 and a memory 802 storing computer program instructions.
[0168] Specifically, the processor 801 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.
[0169] Memory 802 may include mass storage for data or instructions. For example, and not limitingly, memory 802 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. In one instance, memory 802 may include removable or non-removable (or fixed) media, or memory 802 may be non-volatile solid-state memory. Memory 802 may be internal or external to the integrated gateway disaster recovery device.
[0170] In one example, memory 802 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method of electronic signature verification according to this disclosure.
[0171] The processor 801 reads and executes computer program instructions stored in the memory 802 to achieve... Figure 2 The method for verifying electronic signatures in the illustrated embodiment.
[0172] In one example, the terminal device may also include a communication interface 803 and a bus 804. Wherein, for example... Figure 8 As shown, the processor 801, memory 802, and communication interface 803 are connected through bus 804 and complete communication with each other.
[0173] The communication interface 803 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.
[0174] Bus 804 includes hardware, software, or both, that couples components of an end device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 804 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, this application contemplates any suitable bus or interconnect.
[0175] Furthermore, in conjunction with the electronic signature verification methods in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the electronic signature verification methods in the above embodiments.
[0176] This application also provides a computer program product, including a computer program, which, when executed, implements any of the electronic signature verification methods described in the above embodiments.
[0177] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.
[0178] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or text segments used to perform the required tasks. Programs or text segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, read-only memory (ROM), flash memory, erasable read-only memory (EROM), floppy disks, compact disc read-only memory (CD-ROM), optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Text segments can be downloaded via computer networks such as the Internet, intranets, etc.
[0179] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.
[0180] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.
[0181] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.
Claims
1. A method for verifying electronic signatures, characterized in that, Applied to servers, including: Receive an electronic signature acquisition request sent by a user equipment, wherein the electronic signature acquisition request includes a user identifier; Verification images of text corresponding to user identifiers are obtained from different storage areas of the blockchain device. The verification images include signature images corresponding to user identifiers. Multiple verification images of different texts are stored in different storage areas. The verification image is sent to the user equipment for the user equipment to select a signature image from the verification image; Receive the selection result sent by the user equipment; If the selection results include a signature image of the text corresponding to the user identifier, the signature image is verified according to a preset signature image identifier. If the verification passes, an electronic signature is generated and sent to the user device.
2. The method for verifying electronic signatures according to claim 1, characterized in that, Before receiving the electronic signature retrieval request sent by the user equipment, the method further includes: Obtain the user's electronic signature image; The electronic signature image is segmented to obtain multiple signature images; Send and store the signature image to the storage area corresponding to the text in the blockchain device.
3. The method for verifying electronic signatures according to claim 2, characterized in that, The electronic signature image is segmented to obtain multiple signature images, including: Contour extraction is performed on the electronic signature image to obtain a text segmentation image; The text segmentation image is input into the text recognition model. The convolution kernel of the text recognition model is used to extract the shape features of the text segmentation image. The corresponding signature text is determined by weighted summation based on the shape features and preset model parameters. The text segmentation image is segmented based on the signature text to obtain multiple signature images.
4. The method for verifying electronic signatures according to claim 3, characterized in that, The step of extracting the contour of the electronic signature image to obtain a text segmentation image includes: Convert the electronic signature image into a grayscale image; Calculate the gradient magnitude of each pixel in the grayscale image; The target segmentation threshold is determined based on the relationship between gradient magnitude and segmentation threshold. The grayscale image is subjected to contour extraction based on the target segmentation threshold to obtain a text segmentation image.
5. The method for verifying electronic signatures according to claim 3, characterized in that, Before segmenting the text image according to the signature text to obtain multiple signature images, the method further includes: Obtain the name information of the user corresponding to the electronic signature image; By comparing the signature text with the text of the name information, if the signature text and the text of the name information are different, the loss function value is determined based on the text of the signature text and the text of the name information. The target model parameters are determined based on the loss function value, and the text recognition model is updated until the signature text is the same as the text in the name information, thus obtaining the target signature text. The text segmentation image is segmented based on the signature text to obtain multiple signature images, including: The text segmentation image is segmented based on the target signature text to obtain multiple signature images.
6. The method for verifying electronic signatures according to claim 2, characterized in that, Sending and storing the signature image to the storage area corresponding to the text in the blockchain device includes: Assign a signature image identifier to the signature image, and store the correspondence between the signature image identifier and the user identifier, as well as the combination relationship of the signature image identifiers; The signature image and signature image identifier are sent to the storage area corresponding to the text in the blockchain device for storage by the blockchain device.
7. The method for verifying electronic signatures according to claim 1, characterized in that, The server stores the correspondence between signature image identifiers and user identifiers, as well as the combination relationship of signature image identifiers. The combination generates an electronic signature, including: Obtain the signature image identifier corresponding to the user identifier based on the relationship between the signature image identifier and the user identifier; The signature images are combined according to the combination relationship of the signature image identifiers to generate an electronic signature.
8. A method for verifying electronic signatures, characterized in that, Applied to user equipment, including: Send an electronic signature retrieval request to the server, the electronic signature retrieval request including a user identifier; The system receives a verification image sent by the server. The verification image includes a signature image corresponding to the user identifier and is stored in different storage areas of the blockchain device. Based on the image selection command input by the user, the verification image is selected to obtain the selection result; The selection result is sent to the server. The selection result includes the verification image selected by the user device. When the server selects a signature image containing the text corresponding to the user identifier, it verifies the signature image according to the preset signature image identifier. If the verification passes, an electronic signature is generated. Receive electronic signatures sent by the server device.
9. A device for verifying electronic signatures, characterized in that, Applied to servers, including: The receiving module is used to receive an electronic signature acquisition request sent by the user equipment, wherein the electronic signature acquisition request includes a user identifier; The acquisition module is used to acquire verification images of text corresponding to user identifiers from different storage areas of the blockchain device. The verification images include signature images corresponding to user identifiers; multiple verification images of different texts are stored in different storage areas. The sending module is used to send the verification image to the user equipment so that the user equipment can select a signature image from the verification image; The receiving module is also used to receive the selection results sent by the user equipment; The sending module is also used to verify the signature image according to a preset signature image identifier when the selection result includes a signature image of the text corresponding to the user identifier, and to generate an electronic signature and send the electronic signature to the user device if the verification is successful.
10. A device for verifying electronic signatures, characterized in that, Applied to user equipment, including: The sending module is used to send an electronic signature acquisition request to the server, wherein the electronic signature acquisition request includes a user identifier; The receiving module is used to receive a verification image sent by the server. The verification image includes a signature image corresponding to the user identifier and is stored in different storage areas of the blockchain device. The selection module is used to select the verification image according to the image selection command input by the user and obtain the selection result; The sending module is also used to send the selection result to the server. The selection result includes the verification image selected by the user equipment, so that when the server includes a signature image of the text corresponding to the user identifier in the selection result, it can verify the signature image according to the preset signature image identifier. If the verification is successful, an electronic signature can be generated by combining the signature images. The receiving module is also used to receive electronic signatures sent by the server device.
11. A terminal device, characterized in that, The device includes: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements the electronic signature verification method as described in any one of claims 1-8.
12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions, which, when executed by a processor, implement the electronic signature verification method as described in any one of claims 1-8.
13. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device performs the electronic signature verification method as described in any one of claims 1-8.