File electronic signature optimization method and system based on model
The file image feature vector is extracted through a model-based method, the signature position is identified and the integrity index is calculated, which solves the problem of lack of signature integrity verification in the existing technology, and improves the security and reliability of electronic signatures of documents.
Patent Information
- Application Number
- CN202411619601.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-13
- Publication Date
- 2025-04-11
AI Technical Summary
There is a lack of methods for verifying the integrity of electronic signatures of documents in the prior art, resulting in insufficient security and reliability.
A model-based method is used to obtain file images, extract feature vectors, identify the signature position, and calculate the signature integrity index to determine whether the signature is complete.
It realizes the integrity verification of electronic signatures of documents, improves security and reliability, and ensures the integrity and latest signatures.
Smart Images
Figure CN119808169A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of document processing, and more specifically, relates to a model-based document electronic signature optimization method and system. Background Art
[0002] An electronic seal is a digital signature used to verify the authenticity and integrity of a document. It uses technical means to ensure that the document has not been tampered with and confirm the identity of the signatory. The following are the main features and working principles of an electronic seal:
[0003] Key Features:
[0004] Legal effect: In many countries and regions, electronic seals have the same legal effect as traditional seals and can be used to sign important documents such as contracts and agreements.
[0005] Security: Electronic seals usually use encryption technology to ensure that the signing process is safe and reliable and prevent forgery and tampering.
[0006] Convenience: Electronic seals can be quickly generated and applied on electronic devices, avoiding the cumbersome process of paper documents.
[0007] Traceability: Documents using electronic seals can usually record information such as the time and place of signing, providing a complete audit trail.
[0008] Working principle:
[0009] Generate a seal: The signatory uses dedicated software to generate an electronic seal, which usually includes a signature, personal information, and other authentication information.
[0010] Encryption: The signatory uses a private key to encrypt the document, generate a digital signature, and embed the electronic seal into the document.
[0011] Verification: The recipient uses the public key to decrypt the electronic seal and verify the validity of the signature to confirm the authenticity and integrity of the document.
[0012] Records: In some systems, signed information may be recorded to a blockchain or timestamping service, further enhancing security and traceability.
[0013] However, there is no technical solution in the prior art that can verify the integrity of the electronic signature of a document, thereby improving security. Summary of the invention
[0014] In order to solve the above technical problems, the present invention proposes a model-based document electronic signature optimization method, comprising:
[0015] Acquire a file image of the current file, identify the document in the file image, set a file image feature vector extraction model, traverse and extract feature vectors of sample points at each position in the file image;
[0016] A signature position recognition model is set, and each position in the document image is traversed according to the feature vector of the sample point at each position, and a response value of the signature position is calculated. When the response value of the signature position exceeds a position corresponding threshold, the corresponding position is the position where the signature is located;
[0017] Set up a signature integrity verification model, calculate the signature integrity index based on the response value of the signature position, and determine whether the signature is complete based on the signature integrity index. If the signature is complete, store it, otherwise prompt the user to check.
[0018] Furthermore, the document image feature vector extraction model includes:
[0019]
[0020] Where F(x, y) is the feature vector of the sample point at the current position (x, y) on the file image, n is the number of sample points, and w i is the weight of the sample point at the i-th position, α i is the adjustment factor of the i-th position sample point, (x i ,y i ) is the i-th position sample point of the file image, β i is the adjustment factor of the angle of the i-th position sample point, θ i is the angle of the sample point at the ith position, c j is the weight of the sample point at the jth position, γ j is the first adjustment factor of the j-th position sample point, δ j is the second adjustment factor of the j-th position sample point.
[0021] Furthermore, the signature position recognition model includes:
[0022]
[0023] Among them, R is the response value of the signature position, C j is the jth position (x j ,y j ) is the confidence of the feature vector of the sample point, λ j is the jth position (x j ,y j ) is the adjustment factor of the eigenvector of the sample point at j ,y j ) is the jth position (xj ,y j ) is the feature vector of the sample point, T j is the jth position (x j ,y j ) is the threshold value for accurate signature verification, q is the number of sample points, a l is the angle weight of the sample point at the lth position, θ′ l is the angle of the sample point at the lth position.
[0024] Furthermore, the signature integrity verification model includes:
[0025]
[0026] Where I is the signature integrity index, H(D) is the hash value of document D in the file image, H(R) is the hash value of the response value of the signature position, T′ is the time, γ′ is the first adjustment factor of the hash value of document D, δ′ is the second adjustment factor of the hash value of document D, Var(H(D(t))) is the variance of the hash value of document D in the file image at time t, Cov(H(D l ), H(R l )) is the covariance of the hash value of the lth document D in the file image and the hash value of the response value of the lth signature position, m is the number of documents, ∈ l is the adjustment factor for the lth document.
[0027] Furthermore, when the signature integrity index exceeds an integrity threshold, the signature is in a complete state.
[0028] Furthermore, documents with complete signatures are grouped into one file, and documents with incomplete signatures are grouped into another file.
[0029] The present invention also proposes a model-based document electronic signature optimization system, comprising:
[0030] A feature acquisition module is used to acquire a file image of the current file, identify the document in the file image, set a file image feature vector extraction model, traverse and extract feature vectors of sample points at each position in the file image;
[0031] A position recognition module is used to set a signature position recognition model, and traverse each position in the document image according to the feature vector of the sample point at each position, and calculate the response value of the signature position. When the response value of the signature position exceeds the position corresponding threshold, the corresponding position is the signature position;
[0032] The integrity verification module is used to set the signature integrity verification model, calculate the signature integrity index according to the response value of the signature position, and judge whether the signature is complete according to the signature integrity index. If the signature is complete, it is stored, otherwise the user is prompted to check.
[0033] Furthermore, the document image feature vector extraction model includes:
[0034]
[0035] Where F(x, y) is the feature vector of the sample point at the current position (x, y) on the file image, n is the number of sample points, and w i is the weight of the sample point at the i-th position, α i is the adjustment factor of the i-th position sample point, (x i ,y i ) is the i-th position sample point of the file image, β i is the adjustment factor of the angle of the i-th position sample point, θ i is the angle of the sample point at the ith position, c j is the weight of the sample point at the jth position, γ j is the first adjustment factor of the j-th position sample point, δ j is the second adjustment factor of the j-th position sample point.
[0036] Furthermore, the signature position recognition model includes:
[0037]
[0038] Among them, R is the response value of the signature position, C j is the jth position (x j ,y j ) is the confidence of the feature vector of the sample point, λ j is the jth position (x j ,y j ) is the adjustment factor of the eigenvector of the sample point at j ,y j ) is the jth position (x j ,y j ) is the feature vector of the sample point, T j is the jth position (x j ,y j ) is the threshold value for accurate signature verification, q is the number of sample points, a l is the angle weight of the sample point at the lth position, θ′ l is the angle of the sample point at the lth position.
[0039] Furthermore, the signature integrity verification model includes:
[0040]
[0041] Where I is the signature integrity index, H(D) is the hash value of document D in the file image, H(R) is the hash value of the response value of the signature position, T′ is the time, γ′ is the first adjustment factor of the hash value of document D, δ′ is the second adjustment factor of the hash value of document D, Var(H(D(t))) is the variance of the hash value of document D in the file image at time t, Cov(H(D l ), H(R l )) is the covariance of the hash value of the lth document D in the file image and the hash value of the response value of the lth signature position, m is the number of documents, ∈ l is the adjustment factor for the lth document.
[0042] In general, the above technical solution conceived by the present invention has the following beneficial effects compared with the prior art:
[0043] Through the technical solution of the present invention, the integrity of the electronic signature of the document can be verified to check whether the electronic signature is complete and whether it is the latest signature, thereby ensuring security and reliability. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] Figure 1 is a flow chart of the method of embodiment 1 of the present invention;
[0045] Figure 2 It is a structural diagram of the system of embodiment 2 of the present invention. DETAILED DESCRIPTION
[0046] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.
[0047] The method provided by the present invention can be implemented in the following terminal environment, and the terminal may include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, and the instruction is loaded and executed by the processor to implement the method described in the following embodiment.
[0048] The processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts in the entire terminal, and executes various functions of the terminal and processes data by running or executing instructions, programs, code sets or instruction sets stored in the storage medium, and calling data stored in the storage medium.
[0049] The storage medium may include a random access memory (RAM) or a read-only memory (ROM). The storage medium may be used to store instructions, programs, codes, code sets or instructions.
[0050] The display screen is used to display the user interface of each application.
[0051] In addition, those skilled in the art can understand that the structure of the above terminal does not constitute a limitation on the terminal, and the terminal may include more or fewer components, or combine certain components, or arrange the components differently. For example, the terminal also includes components such as a radio frequency circuit, an input unit, a sensor, an audio circuit, and a power supply, which will not be described in detail here.
[0052] Example 1
[0053] like Figure 1 As shown, an embodiment of the present invention provides a model-based document electronic signature optimization method, comprising:
[0054] Step 101, obtaining a file image of a current file, identifying a document in the file image, setting a file image feature vector extraction model, traversing and extracting a feature vector of a sample point at each position in the file image;
[0055] Specifically, the document image feature vector extraction model includes:
[0056]
[0057] Where F(x, y) is the feature vector of the sample point at the current position (x, y) on the file image, n is the number of sample points, and w i is the weight of the sample point at the i-th position, α i is the adjustment factor of the i-th position sample point, (x i ,y i ) is the i-th position sample point of the file image, β i is the adjustment factor of the angle of the i-th position sample point, θ i is the angle of the sample point at the ith position, c j is the weight of the sample point at the jth position, γ j is the first adjustment factor of the j-th position sample point, δ j is the second adjustment factor of the j-th position sample point.
[0058] Step 102, setting a signature position recognition model, and traversing each position in the document image according to the feature vector of the sample point at each position, calculating the response value of the signature position, when the response value of the signature position exceeds the position corresponding threshold, the corresponding position is the signature position;
[0059] Specifically, the signature position recognition model includes:
[0060]
[0061] Among them, R is the response value of the signature position, C j is the jth position (x j ,y j ) is the confidence of the feature vector of the sample point, λ j is the jth position (x j ,y j ) is the adjustment factor of the eigenvector of the sample point at j ,y j ) is the jth position (x j ,y j ) is the feature vector of the sample point, T j is the jth position (x j ,y j ) is the threshold value for accurate signature verification, q is the number of sample points, q l is the angle weight of the sample point at the lth position, θ′ l is the angle of the sample point at the lth position.
[0062] Step 103, setting a signature integrity verification model, calculating a signature integrity index according to the response value of the signature position, judging whether the signature is complete according to the signature integrity index, and if the signature is complete, storing it, otherwise prompting the user to check.
[0063] Specifically, the signature integrity verification model includes:
[0064]
[0065] Where I is the signature integrity index, H(D) is the hash value of document D in the file image, H(R) is the hash value of the response value of the signature position, T′ is the time, γ′ is the first adjustment factor of the hash value of document D, δ′ is the second adjustment factor of the hash value of document D, Var(H(D(t))) is the variance of the hash value of document D in the file image at time t, Cov(H(D l ), H(R l)) is the covariance of the hash value of the lth document D in the file image and the hash value of the response value of the lth signature position, m is the number of documents, ∈ l is the adjustment factor for the lth document.
[0066] Specifically, when the signature integrity index exceeds the integrity threshold, the signature is in a complete state.
[0067] Specifically, documents with complete signatures are grouped into one file, and documents with incomplete signatures are grouped into another file.
[0068] Example 2
[0069] like Figure 2 As shown, the embodiment of the present invention also provides a model-based document electronic signature optimization system, including:
[0070] A feature acquisition module is used to acquire a file image of the current file, identify the document in the file image, set a file image feature vector extraction model, traverse and extract feature vectors of sample points at each position in the file image;
[0071] Specifically, the document image feature vector extraction model includes:
[0072]
[0073] Where F(x, y) is the feature vector of the sample point at the current position (x, y) on the file image, n is the number of sample points, and w i is the weight of the sample point at the i-th position, α i is the adjustment factor of the i-th position sample point, (x i ,y i ) is the i-th position sample point of the file image, β i is the adjustment factor of the angle of the i-th position sample point, θ i is the angle of the sample point at the ith position, c j is the weight of the sample point at the jth position, γ j is the first adjustment factor of the j-th position sample point, δ j is the second adjustment factor of the j-th position sample point.
[0074] A position recognition module is used to set a signature position recognition model, and traverse each position in the document image according to the feature vector of the sample point at each position, and calculate the response value of the signature position. When the response value of the signature position exceeds the position corresponding threshold, the corresponding position is the signature position;
[0075] Specifically, the signature position recognition model includes:
[0076]
[0077] Among them, R is the response value of the signature position, C j is the jth position (x j ,y j ) is the confidence of the feature vector of the sample point, λ j is the jth position (x j ,y j ) is the adjustment factor of the eigenvector of the sample point at j ,y j ) is the jth position (x j ,y j ) is the feature vector of the sample point, T j is the jth position (x j ,y j ) is the threshold value for accurate signature verification, q is the number of sample points, a l is the angle weight of the sample point at the lth position, θ′ l is the angle of the sample point at the lth position.
[0078] The integrity verification module is used to set the signature integrity verification model, calculate the signature integrity index according to the response value of the signature position, and judge whether the signature is complete according to the signature integrity index. If the signature is complete, it is stored, otherwise the user is prompted to check.
[0079] Specifically, the signature integrity verification model includes:
[0080]
[0081] Where I is the signature integrity index, H(D) is the hash value of document D in the file image, H(R) is the hash value of the response value of the signature position, T′ is the time, γ′ is the first adjustment factor of the hash value of document D, δ′ is the second adjustment factor of the hash value of document D, Var(H(D(t))) is the variance of the hash value of document D in the file image at time t, Cov(H(D l ), H(R l )) is the covariance of the hash value of the lth document D in the file image and the hash value of the response value of the lth signature position, m is the number of documents, ∈ l is the adjustment factor for the lth document.
[0082] Specifically, when the signature integrity index exceeds the integrity threshold, the signature is in a complete state.
[0083] Specifically, documents with complete signatures are grouped into one file, and documents with incomplete signatures are grouped into another file.
[0084] Example 3
[0085] The embodiment of the present invention further provides a storage medium storing a plurality of instructions, wherein the instructions are used to implement the model-based document electronic signature optimization method.
[0086] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.
[0087] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps: Step 101, obtaining a file image of a current file, identifying a document in the file image, setting a file image feature vector extraction model, traversing and extracting feature vectors of sample points at each position in the file image;
[0088] Specifically, the document image feature vector extraction model includes:
[0089]
[0090] Where F(x, y) is the feature vector of the sample point at the current position (x, y) on the file image, n is the number of sample points, and w i is the weight of the sample point at the i-th position, α i is the adjustment factor of the i-th position sample point, (x i ,y i ) is the i-th position sample point of the file image, β i is the adjustment factor of the angle of the i-th position sample point, θ i is the angle of the sample point at the ith position, c j is the weight of the sample point at the jth position, γ j is the first adjustment factor of the j-th position sample point, δ j is the second adjustment factor of the j-th position sample point.
[0091] Step 102, setting a signature position recognition model, and traversing each position in the document image according to the feature vector of the sample point at each position, calculating the response value of the signature position, when the response value of the signature position exceeds the position corresponding threshold, the corresponding position is the signature position;
[0092] Specifically, the signature position recognition model includes:
[0093]
[0094] Among them, R is the response value of the signature position, C j is the jth position (xj ,y j ) is the confidence of the feature vector of the sample point, λ j is the jth position (x j ,y j ) is the adjustment factor of the eigenvector of the sample point at j ,y j ) is the jth position (x j ,y j ) is the feature vector of the sample point, T j is the jth position (x j ,y j ) is the threshold value for accurate signature verification, q is the number of sample points, a l is the angle weight of the sample point at the lth position, θ′ l is the angle of the sample point at the lth position.
[0095] Step 103, setting a signature integrity verification model, calculating a signature integrity index according to the response value of the signature position, judging whether the signature is complete according to the signature integrity index, and if the signature is complete, storing it, otherwise prompting the user to check.
[0096] Specifically, the signature integrity verification model includes:
[0097]
[0098] Where I is the signature integrity index, H(D) is the hash value of document D in the file image, H(R) is the hash value of the response value of the signature position, T′ is the time, γ′ is the first adjustment factor of the hash value of document D, δ′ is the second adjustment factor of the hash value of document D, Var(H(D)t))) is the variance of the hash value of document D in the file image at time t, Cov(H(D l ), H(R l )) is the covariance of the hash value of the lth document D in the file image and the hash value of the response value of the lth signature position, m is the number of documents, ∈ l is the adjustment factor for the lth document.
[0099] Specifically, when the signature integrity index exceeds the integrity threshold, the signature is in a complete state.
[0100] Specifically, documents with complete signatures are grouped into one file, and documents with incomplete signatures are grouped into another file.
[0101] Example 4
[0102] An embodiment of the present invention also proposes an electronic device, including a processor and a storage medium connected to the processor, wherein the storage medium stores a plurality of instructions, and the instructions can be loaded and executed by the processor so that the processor can execute the model-based document electronic signature optimization method.
[0103] Specifically, the electronic device of this embodiment may be a computer terminal, and the computer terminal may include: one or more processors, and a storage medium.
[0104] Among them, the storage medium can be used to store software programs and modules, such as a model-based file electronic signature optimization method in an embodiment of the present invention, and the corresponding program instructions / modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the storage medium, that is, realizing the above-mentioned model-based file electronic signature optimization method. The storage medium may include a high-speed random storage medium, and may also include a non-volatile storage medium, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include a storage medium remotely arranged relative to the processor, and these remote storage media may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0105] The processor can call the information and application stored in the storage medium through the transmission system to perform the following steps: Step 101, obtain the file image of the current file, identify the document in the file image, set the file image feature vector extraction model, traverse and extract the feature vector of the sample point at each position in the file image;
[0106] Specifically, the document image feature vector extraction model includes:
[0107]
[0108] Where F(x, y) is the feature vector of the sample point at the current position (x, y) on the file image, n is the number of sample points, and w i is the weight of the sample point at the i-th position, α i is the adjustment factor of the i-th position sample point, (x i ,y i ) is the i-th position sample point of the file image, β i is the adjustment factor of the angle of the i-th position sample point, θ i is the angle of the sample point at the ith position, c j is the weight of the sample point at the jth position, γ j is the first adjustment factor of the j-th position sample point, δ jis the second adjustment factor of the j-th position sample point.
[0109] Step 102, setting a signature position recognition model, and traversing each position in the document image according to the feature vector of the sample point at each position, calculating the response value of the signature position, when the response value of the signature position exceeds the position corresponding threshold, the corresponding position is the signature position;
[0110] Specifically, the signature position recognition model includes:
[0111]
[0112] Among them, R is the response value of the signature position, C j is the jth position (x j ,y j ) is the confidence of the feature vector of the sample point, λ j is the jth position (x j ,y j ) is the adjustment factor of the eigenvector of the sample point at j ,y j ) is the jth position (x j ,y j ) is the feature vector of the sample point, T j is the jth position (x j ,y j ) is the threshold value for accurate signature verification, q is the number of sample points, a l is the angle weight of the sample point at the lth position, θ′ l is the angle of the sample point at the lth position.
[0113] Step 103, setting a signature integrity verification model, calculating a signature integrity index according to the response value of the signature position, judging whether the signature is complete according to the signature integrity index, and if the signature is complete, storing it, otherwise prompting the user to check.
[0114] Specifically, the signature integrity verification model includes:
[0115]
[0116] Where I is the signature integrity index, H(D) is the hash value of document D in the file image, H(R) is the hash value of the response value of the signature position, T′ is the time, γ′ is the first adjustment factor of the hash value of document D, δ′ is the second adjustment factor of the hash value of document D, Var(H(D(t))) is the variance of the hash value of document D in the file image at time t, Cov(H(D l ), H(R l)) is the covariance of the hash value of the lth document D in the file image and the hash value of the response value of the lth signature position, m is the number of documents, ∈ l is the adjustment factor for the lth document.
[0117] Specifically, when the signature integrity index exceeds the integrity threshold, the signature is in a complete state.
[0118] Specifically, documents with complete signatures are grouped into one file, and documents with incomplete signatures are grouped into another file.
[0119] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.
[0120] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0121] In the several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the system embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.
[0122] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0123] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0124] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only storage medium (ROM, Read-Only Memory), random access storage medium (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.
[0125] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived therefrom are still within the scope of protection of the invention.
Claims
1. A model-based document electronic signature optimization method, characterized in that: include: Acquire a file image of the current file, identify the document in the file image, set a file image feature vector extraction model, traverse and extract feature vectors of sample points at each position in the file image; A signature position recognition model is set, and each position in the document image is traversed according to the feature vector of the sample point at each position, and a response value of the signature position is calculated. When the response value of the signature position exceeds a position corresponding threshold, the corresponding position is the position where the signature is located; Set up a signature integrity verification model, calculate the signature integrity index based on the response value of the signature position, and determine whether the signature is complete based on the signature integrity index. If the signature is complete, store it, otherwise prompt the user to check.
2. A model-based document electronic signature optimization method as claimed in claim 1, characterized in that: The document image feature vector extraction model includes: Where F(x, y) is the feature vector of the sample point at the current position (x, y) on the file image, n is the number of sample points, and w i is the weight of the sample point at the i-th position, α i is the adjustment factor of the i-th position sample point, (x i ,y i ) is the i-th position sample point of the file image, β i is the adjustment factor of the angle of the i-th position sample point, θ i is the angle of the sample point at the ith position, c j is the weight of the sample point at the jth position, γ j is the first adjustment factor of the j-th position sample point, δ j is the second adjustment factor of the j-th position sample point.
3. A model-based document electronic signature optimization method as claimed in claim 2, characterized in that: The signature position recognition model includes: Among them, R is the response value of the signature position, C j is the jth position (x j ,y j ) is the confidence of the feature vector of the sample point, λ j is the jth position (x j ,y j ) is the adjustment factor of the eigenvector of the sample point at j ,y j ) is the jth position (x j ,y j ) is the feature vector of the sample point, T j is the jth position (x j ,y j ) is the threshold value for accurate signature verification, q is the number of sample points, a l is the angle weight of the sample point at the lth position, θ′ l is the angle of the sample point at the lth position.
4. A model-based document electronic signature optimization method as claimed in claim 3, characterized in that: The signature integrity verification model includes: Where I is the signature integrity index, H(D) is the hash value of document D in the file image, H(R) is the hash value of the response value of the signature position, T′ is the time, γ′ is the first adjustment factor of the hash value of document D, δ′ is the second adjustment factor of the hash value of document D, Var(H(D(t))) is the variance of the hash value of document D in the file image at time t, Cov(H(D l ), H(R l )) is the covariance of the hash value of the l-th document D in the file image and the hash value of the response value of the l-th signature position, m is the number of documents, and ∈ is the adjustment factor of the l-th document.
5. A model-based document electronic signature optimization method as claimed in claim 4, characterized in that: When the signature integrity index exceeds the integrity threshold, the signature is in a complete state.
6. A model-based document electronic signature optimization method as claimed in claim 1, characterized in that: The documents with complete signatures are grouped into one file, and the documents with incomplete signatures are grouped into another file.
7. A model-based document electronic signature optimization system, characterized in that: include: A feature acquisition module is used to acquire a file image of the current file, identify the document in the file image, set a file image feature vector extraction model, traverse and extract feature vectors of sample points at each position in the file image; A position recognition module is used to set a signature position recognition model, and traverse each position in the document image according to the feature vector of the sample point at each position, and calculate the response value of the signature position. When the response value of the signature position exceeds the position corresponding threshold, the corresponding position is the signature position; The integrity verification module is used to set the signature integrity verification model, calculate the signature integrity index according to the response value of the signature position, and judge whether the signature is complete according to the signature integrity index. If the signature is complete, it is stored, otherwise the user is prompted to check.
8. A model-based document electronic signature optimization system as claimed in claim 7, characterized in that: The document image feature vector extraction model includes: Where F(x, y) is the feature vector of the sample point at the current position (x, y) on the file image, n is the number of sample points, and w i is the weight of the sample point at the i-th position, α i is the adjustment factor of the i-th position sample point, (x i ,y i ) is the i-th position sample point of the file image, β i is the adjustment factor of the angle of the i-th position sample point, θ i is the angle of the sample point at the ith position, c j is the weight of the sample point at the jth position, γ j is the first adjustment factor of the j-th position sample point, δ j is the second adjustment factor of the j-th position sample point.
9. A model-based document electronic signature optimization system as claimed in claim 8, characterized in that: The signature position recognition model includes: Among them, R is the response value of the signature position, C j is the jth position (x j ,y j ) is the confidence of the feature vector of the sample point, λ j is the jth position (x j ,y j ) is the adjustment factor of the eigenvector of the sample point at j ,y j ) is the jth position (x j ,y j ) is the feature vector of the sample point, T j is the jth position (x j ,y j ) is the threshold value for accurate signature verification, q is the number of sample points, a l is the angle weight of the sample point at the lth position, θ′ l is the angle of the sample point at the lth position.
10. A model-based document electronic signature optimization system as claimed in claim 9, characterized in that: The signature integrity verification model includes: Where I is the signature integrity index, H(D) is the hash value of document D in the file image, H(R) is the hash value of the response value of the signature position, T′ is the time, γ′ is the first adjustment factor of the hash value of document D, δ′ is the second adjustment factor of the hash value of document D, Var(H(D(t))) is the variance of the hash value of document D in the file image at time t, Cov(H(D l ), H(R l )) is the covariance of the hash value of the lth document D in the file image and the hash value of the response value of the lth signature position, m is the number of documents, ∈ l is the adjustment factor for the lth document.