Enterprise contract automatic auditing method and device and electronic equipment

By identifying the core data of the enterprise and the content data of the electronic signature, using the editing distance algorithm to calculate the similarity, and automatically reviewing it in combination with preset rules, the problem of low contract review efficiency and reliability in the existing technology is solved, and efficient and reliable are achieved automatic contract review.

CN119090433APending Publication Date: 2024-12-06XINGYUNSHUJU (BEIJING) TECH CO LTD
View PDF 9 Cites 0 Cited by

Patent Information

Application Number
CN202411138522.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing automatic enterprise contract audit method consumes a lot of time and memory resources, and is not efficient and reliable, which has problems such as human error and high calculation consumption.

Method used

By identifying the core data of the enterprise and the content data of the electronic signature, using the editing distance algorithm for similarity calculation, and combining preset audit rules for automatic audit, storage and real-time status monitoring, reducing calculation consumption and improving efficiency.

Benefits of technology

It improves the efficiency and reliability of contract audits, ensures the effectiveness and standardization of audit results, and reduces memory resources and time costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119090433A_ABST
    Figure CN119090433A_ABST
Patent Text Reader

Abstract

The invention provides an enterprise contract automatic auditing method and apparatus, and an electronic device. The method comprises the steps of identifying enterprise core data and electronic signature content data from a contract file of a target enterprise; verifying the electronic signature content data based on the enterprise name data, and if the verification is passed, performing similarity calculation on the enterprise core data and enterprise structured data sent by the target enterprise based on an editing distance algorithm to obtain target similarity calculation result data; and if the target similarity calculation result data meets an auditing passing rule, judging that the contract file of the target enterprise passes auditing so as to carry out storage and real-time state monitoring on the contract file. According to the method, the efficiency and the automation degree of contract auditing can be improved, the reliability and the normalization of the contract auditing process can be effectively improved to ensure the effectiveness and the reliability of the contract auditing result, and the memory resources and the time cost consumed by calculation in the contract auditing process can be effectively reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device and electronic equipment for automatic review of enterprise contracts. Background Art

[0002] Before the development of the automatic contract review function on the enterprise side, the enterprise-related content and documents were mainly uploaded to the system in the form of system structured data and files and displayed on the front-end interface. Only after manual review by market business personnel can the enterprise-related services be opened and used. Due to the small number of contract documents in the early stage and the low requirements for the quality and results of contract review, manual review can still be coped with, but with the increasing number of enterprise-side customers, the number of related contracts has also increased, and the forms of documents have emerged in an endless stream. Manual review of contracts requires a lot of time and human resources, especially for a large number of contracts or complex contracts, manual review may take a long time to complete, resulting in low efficiency. Manual review is prone to negligence and errors. Auditors may make mistakes due to fatigue, lack of concentration or personal bias, resulting in inaccurate contract review or omission of important information. There may be differences in the understanding of contract terms between different auditors, resulting in low consistency and accuracy of the review results. This inconsistency may affect contract execution and risk management. Therefore, some automatic contract review methods for enterprises have emerged to solve the above-mentioned problems of manual contract review.

[0003] However, although the existing automatic contract review methods for enterprises can realize automatic review of contracts, they usually involve the combination of complex algorithms such as artificial intelligence models and other data processing, which not only requires a lot of time cost and data training model, but also consumes a lot of memory resources during model training and application; and simple text recognition methods that do not use complex algorithms such as artificial intelligence models cannot guarantee the effectiveness and reliability of the contract review results, and will also affect the efficiency of contract review.

[0004] Therefore, there is an urgent need to design an automatic contract review method for enterprises that can not only ensure the efficiency, effectiveness and reliability of contract review results, but also reduce the memory resources and time costs consumed in the contract review process. Summary of the invention

[0005] In view of this, the embodiments of the present application provide a method, device and electronic device for automatic review of enterprise contracts to eliminate or improve one or more defects existing in the prior art.

[0006] One aspect of the present application provides an enterprise contract automatic review method, comprising:

[0007] Identify the target enterprise's contract documents to obtain the target enterprise's corresponding core data and electronic signature content data;

[0008] Verifying the electronic signature content data based on the enterprise name data included in the enterprise core data, and if the electronic signature content data passes the verification, then calculating the similarity between the enterprise core data and the enterprise structured data pre-issued by the target enterprise based on the edit distance algorithm to obtain the corresponding target similarity calculation result data;

[0009] If the target similarity calculation result data meets the preset review pass rule, it is determined that the contract document of the target enterprise has passed the review so as to store the contract document and monitor its status in real time.

[0010] In some embodiments of the present application, before obtaining the enterprise core data and electronic signature content data corresponding to the target enterprise from the contract document of the target enterprise, the method further includes:

[0011] Receiving contract review requests respectively sent by various enterprises from a preset data interface, wherein the contract review requests include: a contract document pre-generated by the enterprise based on a target contract type template and enterprise structured data for the contract document provided by the enterprise;

[0012] The received contract documents of each of the enterprises are added to a preset core queue.

[0013] In some embodiments of the present application, the identification of the contract document of the target enterprise to obtain the enterprise core data and electronic signature content data corresponding to the target enterprise includes:

[0014] Extracting the contract documents of each enterprise from the core queue in sequence and taking the enterprise to which the currently extracted contract document belongs as the current target enterprise;

[0015] Based on the preset core data extraction rules, extract the corresponding enterprise core data and electronic signature content data from the contract documents of the target enterprise;

[0016] It is determined whether the extracted enterprise core data and the electronic signature content data meet their corresponding content recognition thresholds respectively. If so, the enterprise core data and the electronic signature content data are stored.

[0017] In some embodiments of the present application, the information type corresponding to the enterprise core data is the same as the information type corresponding to the enterprise structured data, or the information type corresponding to the enterprise structured data is less than the information type corresponding to the enterprise core data;

[0018] The information types corresponding to the core data of the enterprise include: enterprise name, principal, personal information, enterprise title, tax number, purchaser's address, telephone number, contract start and end dates, and account opening information.

[0019] In some embodiments of the present application, the electronic signature content data is verified based on the enterprise name data included in the enterprise core data. If the electronic signature content data passes the verification, based on the edit distance algorithm, the similarity calculation is performed on the enterprise core data and the enterprise structured data pre-issued by the target enterprise to obtain the corresponding target similarity calculation result data, including:

[0020] Verifying the electronic signature content data based on the enterprise name data included in the enterprise core data, and if the text corresponding to the electronic signature content data is the same as the enterprise name data, determining that the electronic signature content data passes the verification;

[0021] According to each information type contained in the enterprise structured data issued in advance by the target enterprise, character strings identical to each information type in the enterprise structured data are extracted from the enterprise core data to form target audit data corresponding to the enterprise core data;

[0022] Extracting each character string in the target audit data and each character string in the enterprise structured data pre-issued by the target enterprise, and extracting one character string from each of the target audit data and the enterprise structured data according to a preset extraction order to form a comparison group, and executing a preset edit distance algorithm for each of the comparison groups to obtain similarity calculation result data corresponding to each of the comparison groups;

[0023] The similarity calculation result data corresponding to each of the comparison groups are aggregated into corresponding target similarity calculation result data.

[0024] In some embodiments of the present application, the edit distance algorithm includes:

[0025] Using the character string corresponding to the target audit data in the current comparison group as the source character string, and using the character string corresponding to the enterprise structured data in the comparison group as the target character string;

[0026] The current initial problem is set as: the minimum edit distance required to convert the source string into the target string;

[0027] Decompose the initial problem into sub-problems, wherein the sub-problem is the minimum edit distance d[i][j] required to convert the first i characters in the source string into the first j characters in the target string, where i is greater than 1 and less than the length of the source string, and j is greater than 1 and less than the length of the target string;

[0028] If the i-th character in the source string is the same as the j-th character in the target string, then d[i][j]=d[i-1][j-1], where d[i-1][j-1] represents the minimum edit distance required to convert the first i-1 characters in the source string to the first j-1 characters in the target string;

[0029] If the i-th character in the source string is different from the j-th character in the target string, a deletion operation is performed on the i-th character in the source string, an insertion operation is performed on the j-th character in the target string, and a replacement operation is performed on the source string to replace the i-th character in the source string with the j-th character in the target string;

[0030] Selecting the minimum value from the values ​​of d[i][j] obtained after the deletion operation, the insertion operation, and the replacement operation as the solution value of the subproblem;

[0031] The similarity calculation result data corresponding to the current comparison group is calculated based on the solution value of the sub-problem, the length of the source character string and the length of the target character string.

[0032] In some embodiments of the present application, before verifying the electronic signature content data based on the enterprise name data included in the enterprise core data, the method further includes:

[0033] Based on the pre-acquired data of the person in charge corresponding to the target enterprise, the authenticity of at least one of the information types corresponding to the enterprise core data, including the enterprise name, principal, personal information, company title, tax number, purchaser's address, telephone number, contract start and end dates, and account opening information, is verified. If the target audit data passes the authenticity verification, the enterprise name data in the enterprise core data is extracted for electronic signature content data verification.

[0034] In some embodiments of the present application, if the target similarity calculation result data satisfies the preset review pass rule, then it is determined that the contract document of the target enterprise has passed the review to store and monitor the real-time status of the contract document, including:

[0035] Determine whether the value corresponding to the target similarity calculation result data is within a preset audit passing value range, and if so, determine that the target similarity calculation result data has passed the audit;

[0036] Adding the contract document of the target enterprise to a preset core delay queue so as to remove the contract document from the core delay queue at a time point before the contract corresponding to the contract document expires;

[0037] For the contract document of the target enterprise taken out from the core delay queue, sending a notification message for prompting the target enterprise to renew the contract document;

[0038] If it is monitored in real time or the contract document of the target enterprise is currently at the expiration of the service deadline, the enterprise service corresponding to the contract document will be automatically deactivated.

[0039] Another aspect of the present application provides a contract automatic review device, comprising:

[0040] A contract document identification module, used to identify the contract document of the target enterprise and obtain the enterprise core data and electronic signature content data corresponding to the target enterprise;

[0041] A verification and review module, used to verify the electronic signature content data based on the enterprise name data contained in the enterprise core data. If the electronic signature content data passes the verification, similarity calculation is performed on the enterprise core data and the enterprise structured data pre-issued by the target enterprise based on the edit distance algorithm to obtain the corresponding target similarity calculation result data;

[0042] The storage and monitoring module is used to determine that the contract document of the target enterprise has passed the review if the target similarity calculation result data meets the preset review pass rules, so as to store the contract document and monitor its status in real time.

[0043] The third aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for automatic enterprise contract review when executing the computer program.

[0044] The fourth aspect of the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for automatic review of enterprise contracts is implemented.

[0045] The fifth aspect of the present application provides a computer program product, including a computer program, which implements the automatic enterprise contract review method when executed by a processor.

[0046] The automatic review method for enterprise contracts provided in the present application obtains the enterprise core data and electronic signature content data corresponding to the target enterprise by identifying the contract document of the target enterprise; verifies the electronic signature content data based on the enterprise name data contained in the enterprise core data; if the electronic signature content data passes the verification, then based on the edit distance algorithm, performs similarity calculation on the enterprise core data and the enterprise structured data pre-issued by the target enterprise to obtain the corresponding target similarity calculation result data; if the target similarity calculation result data meets the preset review pass rules, then it is determined that the contract document of the target enterprise has passed the review so as to store the contract document and monitor its status in real time, which can improve the efficiency and automation of contract review, effectively improve the reliability and standardization of the contract review process to ensure the validity and reliability of the contract review results, and effectively reduce the memory resources and time costs consumed by calculation during the contract review process.

[0047] Additional advantages, purposes, and features of the present application will be partially described in the following description, and will become partially apparent to those skilled in the art after studying the following, or may be learned from the practice of the present application. The purposes and other advantages of the present application can be achieved and obtained by the structures specifically pointed out in the specification and the drawings.

[0048] Those skilled in the art will understand that the purposes and advantages that can be achieved by the present application are not limited to the above specific description, and the above and other purposes that can be achieved by the present application will be more clearly understood based on the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The drawings described herein are used to provide a further understanding of the present application, constitute a part of the present application, and do not constitute a limitation of the present application. The components in the drawings are not drawn to scale, but are only for the purpose of illustrating the principles of the present application. In order to facilitate the illustration and description of some parts of the present application, the corresponding parts in the drawings may be enlarged, that is, they may become larger relative to other components in the exemplary device actually manufactured according to the present application. In the drawings:

[0050] Figure 1 This is a first flow chart of the method for automatic review of enterprise contracts in one embodiment of the present application.

[0051] Figure 2 This is a second flow chart of the method for automatic review of enterprise contracts in one embodiment of the present application.

[0052] Figure 3 This is a schematic diagram of the execution process of the automatic enterprise contract review method in an example of this application.

[0053] Figure 4This is a third flow chart of the method for automatic review of enterprise contracts in one embodiment of the present application.

[0054] Figure 5 It is a schematic diagram of the structure of an automatic enterprise contract review device in one embodiment of the present application. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the implementation modes and the accompanying drawings. Here, the illustrative implementation modes and descriptions of the present application are used to explain the present application, but are not intended to limit the present application.

[0056] It should also be noted here that in order to avoid obscuring the present application due to unnecessary details, only the structures and / or processing steps closely related to the scheme according to the present application are shown in the accompanying drawings, while other details that are not very relevant to the present application are omitted.

[0057] It should be emphasized that the term “include / comprises” when used herein refers to the presence of features, elements, steps or components, but does not exclude the presence or addition of one or more other features, elements, steps or components.

[0058] It should also be noted that, unless otherwise specified, the term “connection” herein may refer not only to a direct connection but also to an indirect connection involving an intermediate.

[0059] Hereinafter, embodiments of the present application will be described with reference to the accompanying drawings. In the accompanying drawings, the same reference numerals represent the same or similar components, or the same or similar steps.

[0060] Manual contract review currently has the following problems:

[0061] 1. Manual review of a single contract takes a long time and may result in omissions or human errors.

[0062] 2. There are tens of thousands of contracts with corporate customers, and the cost of manual review is high, requiring a large amount of manpower, material resources and high time costs.

[0063] 3. In the early days, business personnel were required to call and remind customers when contracts expired. Companies were not aware that contracts had expired when services expired, and failure to renew contracts in a timely manner led to service suspensions, resulting in economic losses.

[0064] 4. The real-time rate of manual contract review is low, resulting in some important and high-time documents not being processed in a timely manner.

[0065] 5. Manual reviews are usually processed in batches and cannot handle contract changes or emergencies in real time, which may cause delays or miss important information.

[0066] In order to solve the above-mentioned problem of manual contract review, in the automatic enterprise contract review method provided by this application, enterprise customers upload important data in a structured form through an interface, and the system authenticates enterprise information by comparing structured data and manually reviewed documents. This can help companies solve the problem of manually reviewing a large number of enterprise customer contracts, save resources and time costs for manual contract review, and can automatically review according to preset rules and processes to ensure the rigor and standardization of the review; it automatically reminds customers to renew their contracts before the contract expires, and automatically deactivates the service after the expiration.

[0067] In order to provide an automatic enterprise contract review method that can not only ensure the efficiency, effectiveness and reliability of contract review results, but also reduce the memory resources and time costs consumed in the contract review process, the embodiments of the present application respectively provide an automatic enterprise contract review method, an automatic enterprise contract review device for executing the automatic enterprise contract review method, an electronic device, a computer-readable storage medium and a computer program product.

[0068] The details are described in detail through the following examples.

[0069] Based on this, the embodiment of the present application provides an enterprise contract automatic review method that can be implemented by an enterprise contract automatic review device, see Figure 1 The enterprise contract automatic review method specifically includes the following contents:

[0070] Step 100: Identify the target enterprise's contract documents and obtain the enterprise core data and electronic signature content data corresponding to the target enterprise.

[0071] In one or more embodiments of the present application, the target enterprise refers to the enterprise that is currently to undergo automatic enterprise contract review. During the specific review process, the target enterprise can be referred to by its corresponding unique identifier; in addition, the contract file refers to the contract document data, which can usually be in the form of a PDF file or other file formats, which can be set according to actual application requirements. Among them, the contract file in the unified PDF file format mainly involves the content related to the power of attorney and the letter of commitment.

[0072] It can be understood that the enterprise core data refers to the various data used to represent the core attribute information corresponding to the target enterprise, such as enterprise name data, principal data, personal information data, enterprise header data, tax number data, purchaser address data, telephone data and account opening information data, etc.

[0073] The electronic signature content data refers to the text data contained in the electronic signature image identified from the page containing the electronic signature image in the contract document.

[0074] Step 200: Verify the electronic signature content data based on the enterprise name data contained in the enterprise core data. If the electronic signature content data passes the verification, calculate the similarity between the enterprise core data and the enterprise structured data pre-issued by the target enterprise based on the edit distance algorithm to obtain the corresponding target similarity calculation result data.

[0075] In step 200, the enterprise structured data pre-issued by the target enterprise refers to structured data pre-filled by the target enterprise based on a preset structured data extraction template or requirement. In one example, the enterprise structured data may include enterprise invoice header data, tax number data, purchaser address data, telephone data, and service start and end date data, etc. The target enterprise may upload it together with the contract document through the data interface provided by the auditing agency.

[0076] The information type corresponding to the enterprise structured data needs to overlap with the information type corresponding to the enterprise structured data, so that the similarity calculation can be performed between the data with overlapping information types in the two.

[0077] Of course, in order to further improve the reliability and effectiveness of the similarity calculation results, in one embodiment of the present application, the information type corresponding to the enterprise core data is the same as the information type corresponding to the enterprise structured data, or the information type corresponding to the enterprise structured data is less than the information type corresponding to the enterprise core data;

[0078] The information types corresponding to the core data of the enterprise may include: enterprise name, principal, personal information, enterprise header, tax number, purchaser's address, telephone number, contract start and end dates, and account opening information, which can be specifically specified based on the information type template pre-set by the audit agency.

[0079] Correspondingly, if the information type corresponding to the enterprise core data is the same as the information type corresponding to the enterprise structured data, the information type corresponding to the enterprise structured data may include: enterprise name, principal, personal information, enterprise header, tax number, purchaser's address, telephone number, contract start and end dates, and account opening information.

[0080] If the information type corresponding to the enterprise structured data is less than the information type corresponding to the enterprise core data, the information type corresponding to the enterprise structured data may include: enterprise title, tax number, purchaser address, telephone number and contract start and end dates.

[0081] In addition, step 200 of the present application can effectively reduce the memory resources and time costs consumed in the contract review process by using an edit distance algorithm to calculate the similarity between the enterprise core data and the enterprise structured data pre-issued by the target enterprise. The edit distance algorithm (Edit Distance Algorithm) is an algorithm for calculating the similarity between strings, and is used to calculate the edit distance between two strings, where the edit distance refers to the minimum number of edits required to convert one string into another.

[0082] Step 300: If the target similarity calculation result data meets the preset review pass rule, it is determined that the contract document of the target enterprise has passed the review so as to store the contract document and monitor its status in real time.

[0083] From the above description, it can be seen that the automatic enterprise contract review method provided in the embodiment of the present application can improve the efficiency and automation of contract review, can effectively improve the reliability and standardization of the contract review process to ensure the effectiveness and reliability of the contract review results, and can effectively reduce the memory resources and time costs consumed in the calculation of the contract review process.

[0084] In order to further improve the orderliness and reliability of the automatic review of enterprise contracts, in an automatic review method for enterprise contracts provided in an embodiment of the present application, see Figure 2 The method for automatically reviewing enterprise contracts includes the following contents before step 100:

[0085] Step 010: Receive contract review requests sent by various enterprises from a preset data interface, wherein the contract review request includes: a contract document pre-generated by the enterprise based on a target contract type template and enterprise structured data for the contract document provided by the enterprise.

[0086] It is understandable that the review agency can actually provide various contract type templates suitable for various different contract types, and store the correspondence between these contract type templates and various contract types, and can, based on the template acquisition request containing the contract type sent by the enterprise, select the contract type template corresponding to the contract type required by the template acquisition request from the stored various contract type templates, determine the contract type template as the current target contract type template, and then send it to the enterprise.

[0087] Step 020: Add all received contract documents of the enterprises to a preset core queue.

[0088] In one or more embodiments thereof, the core queue refers to a queue set in a container, which can be called a core queue container.

[0089] In one example, see Figure 3 , the corresponding client device of the enterprise uploads the enterprise structured data and PDF contract files (prepare a unified PDF contract file template) through the data interface. After receiving the request, the corresponding server of the audit agency enters the core queue developed by the audit agency itself. This core queue mainly ensures the orderliness, real-time, and efficient storage and access of the contract files. The invoicing service customers of the audit agency are mainly enterprises. The enterprises use the enterprise contract templates provided by the audit agency and upload them in the manner required by the audit agency. The relevant template forms and contents are uniformly formulated by staff involved in the legal, business operations, and risk control departments. For example, for logistics companies, there are corporate customers who have toll invoices.

[0090] In order to further improve the accuracy and reliability of the extraction of enterprise core data and electronic signature content data, in an enterprise contract automatic review method provided in an embodiment of the present application, see Figure 2 Step 100 in the enterprise contract automatic review method specifically includes the following contents:

[0091] Step 110: extracting the contract documents of each enterprise from the core queue in sequence and taking the enterprise to which the currently extracted contract document belongs as the current target enterprise.

[0092] Step 120: Based on the preset core data extraction rules, extract the corresponding enterprise core data and electronic signature content data from the contract documents of the target enterprise.

[0093] In one example, after a contract is obtained from the core queue, it enters the automatic review stage: the PDF file is split into each page of data, and the system can parse a page or the entire PDF file separately according to the configuration requirements. The recognition system parses the contract template to extract the customer's core data, and compares the extracted core data with the structured data passed in by the interface.

[0094] Step 130: Determine whether the extracted enterprise core data and the electronic signature content data meet their corresponding content recognition thresholds respectively. If so, store the enterprise core data and the electronic signature content data.

[0095] In one example, when identifying the company's title, tax number, address, and phone number, the location information to be identified is configured in advance, and the content recognition rate is above 80% to be qualified. When reviewing the seal, the content recognition rate between the seal and the company name must be 100% to be qualified. These are the review rules that have been determined when the template is generated. In other words, the content recognition threshold corresponding to the company's core data can be set between 80% and 100%, and the content recognition threshold corresponding to the electronic signature content data can be set to 100%.

[0096] In order to further reduce the memory resources and time cost consumed by calculation during the contract review process, in an enterprise contract automatic review method provided in an embodiment of the present application, see Figure 2 Step 200 in the enterprise contract automatic review method specifically includes the following contents:

[0097] Step 210: verify the electronic signature content data based on the enterprise name data included in the enterprise core data. If the text corresponding to the electronic signature content data is the same as the enterprise name data, it is determined that the electronic signature content data has passed the verification.

[0098] That is to say, after the text is recognized, the electronic signature needs to be recognized, and the recognized signature content needs to be compared and verified with the company name to ensure that it is the electronic signature of the current company. After all the text and signature are recognized, the text similarity calculation will be performed on the recognized content through the following steps 220 to 240. Only when the similarity is high and reaches a certain value, it can be said that the contract review is completed.

[0099] Step 220: According to each information type contained in the enterprise structured data pre-issued by the target enterprise, character strings identical to each information type in the enterprise structured data are extracted from the enterprise core data to form target audit data corresponding to the enterprise core data.

[0100] Step 230: Extract each character string in the target audit data and each character string in the enterprise structured data pre-issued by the target enterprise, and extract one character string from each of the target audit data and the enterprise structured data according to a preset extraction order to form a comparison group, and execute a preset edit distance algorithm for each of the comparison groups to obtain the similarity calculation result data corresponding to each of the comparison groups.

[0101] Step 240: Aggregate the similarity calculation result data corresponding to each of the comparison groups into corresponding target similarity calculation result data.

[0102] In order to further reduce the memory resources and time cost consumed by calculation during the contract review process, in an automatic contract review method for an enterprise provided in an embodiment of the present application, the edit distance algorithm in the automatic contract review method for an enterprise specifically includes the following contents:

[0103] (1) taking the character string corresponding to the target audit data in the current comparison group as the source character string s1, and taking the character string corresponding to the enterprise structured data in the comparison group as the target character string s2;

[0104] (2) The current initial problem is set as: the edit distance d[m][n] required to convert the source string s1 into the target string s2, where m is the length of the source string s1 and n is the length of the target string;

[0105] (3) decomposing the initial problem into sub-problems, wherein the sub-problem is the minimum edit distance d[i][j] required to convert the first i characters in the source string s1 into the first j characters in the target string s2;

[0106] (4) If the i-th character in the source string s1 is the same as the j-th character in the target string s2, then d[i][j]=d[i-1][j-1], where d[i-1][j-1] represents the minimum edit distance required to convert the first i-1 characters in the source string s1 to the first j-1 characters in the target string;

[0107] (5) If the i-th character in the source string s1 is different from the j-th character in the target string s2, a deletion operation is performed on the i-th character in the source string s1, an insertion operation is performed on the j-th character in the target string s2, and a replacement operation is performed on the source string s1 to replace the i-th character in the source string s1 with the j-th character in the target string s2.

[0108] (6) selecting the minimum value among the values ​​of d[i][j] obtained after the deletion operation, the insertion operation, and the replacement operation as the solution value of the subproblem;

[0109] (7) Based on the solution values ​​corresponding to the respective sub-problems, the length m of the source string s1 and the length n of the target string s2, similarity calculation result data corresponding to the current comparison group is calculated.

[0110] That is to say, the edit distance algorithm provided in the above embodiment of the present application is an efficient string comparison algorithm, which aims to solve the performance bottleneck of the traditional edit distance calculation method. The algorithm is based on the idea of ​​dynamic programming, uses a matrix structure to record the similarity between characters, and through carefully designed comparison logic, significantly improves the calculation speed while ensuring accuracy. Using the dynamic programming method, the string comparison problem is decomposed into sub-problems and efficiently solved by filling the matrix. The complex problem of calculating the edit distance between two strings is decomposed into simple sub-problems of calculating the edit distance between each substring. This decomposition method is based on the idea of ​​dynamic programming. Its core content is as follows:

[0111] (1) Problem decomposition: Assume there are source string s1 and target string s2, with lengths of m and n respectively. We want to calculate the edit distance between them, that is, the minimum number of operations (insertion, deletion, substitution) required to transform s1 into s2. The problem can be decomposed in the following way:

[0112] a. Define subproblems: Define d[i][j] as the minimum edit distance required to convert the first i characters of s1 to the first j characters of s2. The initial problem is to find d[m][n], which is the edit distance to convert the entire s1 to s2.

[0113] b. Initialization boundary conditions: If s1 is an empty string (length 0), then converting it to s2 requires j insertion operations, so d[0][j] = j. Similarly, if s2 is an empty string (length 0), then converting s1 to s2 requires i deletion operations, so d[i][0] = i.

[0114] c. Recursively define the solution of the subproblem: Consider how to construct the solution of the current problem through the solution of the subproblem: If the audit agency knows d[i-1][j], which is the edit distance of converting the first i-1 characters of s1 to the first j characters of s2, the audit agency can get d[i][j] by deleting the i-th character of s1. At this time, the edit distance increases by 1, so: d[i][j] = d[i-1][j] + 1.

[0115] If d[i][j-1] is known, that is, the edit distance of converting the first i characters of s1 to the first j-1 characters of s2, the auditing agency can obtain d[i][j] by inserting the jth character of s2. At this time, the edit distance increases by 1, so: d[i][j] = d[i][j-1] + 1.

[0116] If d[i-1][j-1] is known, i.e., the edit distance of converting the first i-1 characters of s1 to the first j-1 characters of s2, the auditor can obtain d[i][j] by replacing the i-th character of s1 with the j-th character of s2 (or leaving it unchanged if they are the same). If the characters are different, the edit distance increases by 1, otherwise it does not increase. Therefore, d[i][j] = d[i-1][j-1] + (s1[i-1] ! = s2[j-1]).

[0117] d. Solution to the combinatorial subproblem: For each d[i][j], select the minimum edit distance among the three operations of deletion, insertion, and replacement, that is: d[i][j] = min(d[i-1][j]+1,d[i][j-1]+1,d[i-1][j-1]+(s1[i-1]!=s2[j-1])).

[0118] (2) Calculation logic of similarity:

[0119] Similarity = 1 – minimum edit distance / max (string length m of s1, string length n of s2)

[0120] In other words, the automatic enterprise contract review method provided in the embodiment of the present application can optimize the space and time complexity of the algorithm: while ensuring the accuracy of the calculation, it can optimize the use of memory and time, so that it can still maintain excellent performance under large-scale string comparison tasks.

[0121] In order to further illustrate the above-mentioned edit distance algorithm, that is, the minimum number of changes required to edit text A into text B, in an application example of the present application, an example of the execution principle of the edit distance algorithm is also given:

[0122] a. Create a comparison matrix: First, create a two-dimensional matrix with the number of rows equal to the length of the source string plus one and the number of columns equal to the length of the target string plus one.

[0123] b. Initialize the matrix: Initialize the first row and the first column of the matrix to 0 to the length of the target string and the length of the source string, respectively, indicating the edit distance from the empty string to the target string or the source string.

[0124] c. Fill the matrix: Starting from the first character of the source string and the target string, compare the characters one by one and fill the matrix. If the two characters are the same, the edit cost is 0; if they are different, the cost is 1. According to the insertion, deletion and replacement operations, update the edit distance of the corresponding position in the matrix.

[0125] d. Calculate the minimum edit distance: The value of the last matrix element is the minimum edit distance between the source string and the target string.

[0126] Among them, the state transfer equation includes:

[0127] a. If the i-th character of A is equal to the j-th character of B, that is, A.charAt(i-1) == B.charAt(j-1), then d[i][j] = d[i-1][j-1], and no operation is required.

[0128] b. Otherwise, the value of d[i][j] can be obtained through the following three operations:

[0129] Replacement: d[i][j]=d[i-1][j-1]+1;

[0130] Delete: d[i][j] = d[i-1][j] + 1;

[0131] Insert: d[i][j] = d[i][j-1] + 1;

[0132] Take the minimum value of these three operations as the value of d[i][j].

[0133] Taking s1 = "kitten" and s2 = "sitting" as an example, the filling process of the dynamic planning table is shown in Table 1:

[0134] Table 1

[0135] Filling process number Filling content 1 ""sitting 2 ""01234567 3 k11234567 4 i22123456 5 t33212345 6 t44321234 7 e55432234 8 n66543323

[0136] Finally, we get d[6][7]=3, which means that the minimum edit distance for "kitten" to become "sitting" is 3.

[0137] The final similarity is Similarity = 1–3 / 7 = 0.5714.

[0138] In order to further improve the reliability and effectiveness of the automatic review of enterprise contracts, in an automatic review method for enterprise contracts provided in an embodiment of the present application, see Figure 4 The method for automatically reviewing enterprise contracts further includes the following contents between step 100 and step 200:

[0139] Step 030: Based on the pre-acquired data of the person in charge corresponding to the target enterprise, authenticity verification is performed on at least one of the information types corresponding to the enterprise core data, including the enterprise name, principal, personal information, company title, tax number, purchaser's address, telephone number, contract start and end dates, and account opening information. If the target audit data passes the authenticity verification, the enterprise name data in the enterprise core data is extracted for electronic signature content data verification.

[0140] Specifically, it can verify whether the basic information related to the enterprise is true and accurate. During the automatic contract review process, the data structure of the agent corresponding to the enterprise is queried, and then the relationship between the principal and the enterprise in the contract is verified to be a correct authorization relationship. This includes whether the service start and end dates in the contract are consistent with the prescribed service period, etc.

[0141] In order to further improve the reliability and effectiveness of storing and real-time monitoring the contract file, in an automatic contract review method for an enterprise provided in an embodiment of the present application, see Figure 4 Step 300 in the enterprise contract automatic review method specifically includes the following contents:

[0142] Step 310: determining whether the value corresponding to the target similarity calculation result data is within a preset audit passing value range, and if so, determining that the target similarity calculation result data has passed the audit;

[0143] If not, a notification message that the contract review has not passed is sent to the client device of the target enterprise.

[0144] Step 320: adding the contract document of the target enterprise to a preset core delay queue so as to take the contract document out of the core delay queue at a time point before the contract corresponding to the contract document expires;

[0145] The core delay queue is a queue set in a container, which can be called a delay queue container. When it is detected that the current time point is the time point before the contract expiration corresponding to the contract document, the contract document is taken out from the core delay queue. The time point before the contract expiration can be calculated in advance according to the deadline in the contract start and end dates corresponding to the contract document. For example, the time point before the contract expiration can be set to 10 days or half a month before the deadline.

[0146] Step 330: For the contract document of the target enterprise taken out from the core delay queue, a notification message is sent to the target enterprise to prompt the target enterprise to renew the contract document.

[0147] Step 340: If it is monitored in real time or the contract document of the target enterprise is currently in a service deadline expiration state, the enterprise service corresponding to the contract document is automatically deactivated.

[0148] That is to say, the reviewed contract document will enter the core delay queue. It will be removed from the delay queue 10 days before the contract expires, and a text message will be sent to the customer to remind them to renew the contract in advance. When the service deadline of the contract expires, the enterprise service will be automatically deactivated.

[0149] That is to say, the automatic review method for corporate contracts provided in the embodiment of the present application obtains the text content and seal content in the file by identifying the PDF file template; compares the core data according to the verification rules and calculates the similarity of the compared content, and finally determines the review result by judging the size of the content similarity; the core queue container ensures the efficiency, orderliness and real-time automatic review of the contract submitted by the customer; the automatic review function can also ensure that the customer is reminded to renew the contract in advance at the specified time before the contract expires, and the corporate service is automatically deactivated when the contract expires.

[0150] In summary, the method for automatic review of enterprise contracts provided by the embodiment of the present application has the following beneficial effects:

[0151] (1) Formulate a unified corporate contract template and standardize the contract form to improve text recognition accuracy: The recognition system needs to be highly accurate and able to accurately recognize the text content in the contract, including special formats, fonts, and layouts. The recognized file content is used as the basis for the legality of the enterprise and the service period of the enterprise, and is compared with structured data to calculate the content similarity. When the similarity reaches a certain range, the contract is approved to ensure the high accuracy of the system's automatic review.

[0152] (2) Signature and seal recognition: It can identify important information such as signatures and seals in contracts. The system identifies the signature content and compares it with the company name to determine whether it is the signature information of the current company, thereby ensuring the integrity and legality of the contract.

[0153] (3) Rapid processing and batch processing, achieving rapid text recognition and processing capabilities, capable of processing large amounts of contract documents and improving audit efficiency.

[0154] (4) Integration and automation: It can be integrated into the automatic contract review system to realize automated contract identification, review and processing processes.

[0155] From the software level, the present application also provides an enterprise contract automatic review device for executing all or part of the enterprise contract automatic review method, see Figure 5 The enterprise contract automatic review device specifically includes the following contents:

[0156] The contract document identification module 10 is used to identify the contract document of the target enterprise and obtain the enterprise core data and electronic signature content data corresponding to the target enterprise.

[0157] The verification and review module 20 is used to verify the electronic signature content data based on the enterprise name data contained in the enterprise core data. If the electronic signature content data passes the verification, the similarity between the enterprise core data and the enterprise structured data pre-issued by the target enterprise is calculated based on the edit distance algorithm to obtain the corresponding target similarity calculation result data.

[0158] The storage and monitoring module 30 is used to determine that the contract document of the target enterprise has passed the review if the target similarity calculation result data meets the preset review pass rule, so as to store and monitor the status of the contract document in real time.

[0159] The embodiment of the automatic enterprise contract review device provided in the present application can be specifically used to execute the processing flow of the embodiment of the automatic enterprise contract review method in the above-mentioned embodiment. Its functions will not be repeated here, and reference can be made to the detailed description of the embodiment of the automatic enterprise contract review method in the above-mentioned embodiment.

[0160] The part of the automatic auditing device for enterprise contracts that performs automatic auditing of enterprise contracts can be executed in the corresponding server of the auditing agency, etc., or it can be completed in the client device. The specific selection can be made based on the processing capacity of the client device and the limitations of the user's usage scenario. This application does not limit this. If all operations are completed in the client device, the client device can also include a processor for specific processing of the automatic auditing of enterprise contracts.

[0161] The client device may have a communication module (i.e., a communication unit) that can communicate with a remote server to achieve data transmission with the server. The server may include a server on the task scheduling center side, and other implementation scenarios may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, or a server cluster consisting of multiple servers, or a server structure of a distributed device.

[0162] The server and the client device may communicate with each other using any suitable network protocol, including network protocols that have not yet been developed on the date of filing this application. The network protocols may include, for example, TCP / IP, UDP / IP, HTTP, HTTPS, etc. Of course, the network protocols may also include, for example, RPC (Remote Procedure Call Protocol) and REST (Representational State Transfer) protocols used on top of the above protocols.

[0163] From the above description, it can be seen that the enterprise contract automatic review device provided in the embodiment of the present application can improve the efficiency and automation of contract review, can effectively improve the reliability and standardization of the contract review process to ensure the effectiveness and reliability of the contract review results, and can effectively reduce the memory resources and time costs consumed in the calculation of the contract review process.

[0164] The embodiment of the present application also provides an electronic device, which may include a processor, a memory, a receiver and a transmitter, wherein the processor is used to execute the enterprise contract automatic review method mentioned in the above embodiment, wherein the processor and the memory may be connected via a bus or other means, such as by bus connection. The receiver may be connected to the processor and the memory via wired or wireless means.

[0165] The processor may be a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.

[0166] As a non-transient computer-readable storage medium, the memory can be used to store non-transient software programs, non-transient computer executable programs and modules, such as program instructions / modules corresponding to the enterprise contract automatic review method in the embodiment of the present application. The processor executes various functional applications and data processing of the processor by running the non-transient software programs, instructions and modules stored in the memory, that is, the enterprise contract automatic review method in the above method embodiment is implemented.

[0167] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor 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.

[0168] The one or more modules are stored in the memory, and when executed by the processor, the enterprise contract automatic review method in the embodiment is executed.

[0169] In some embodiments of the present application, the user equipment may include a processor, a memory, and a transceiver unit, which may include a receiver and a transmitter. The processor, memory, receiver, and transmitter may be connected through a bus system. The memory is used to store computer instructions, and the processor is used to execute the computer instructions stored in the memory to control the transceiver unit to send and receive signals.

[0170] As an implementation method, the functions of the receiver and the transmitter in the present application can be considered to be implemented through a transceiver circuit or a dedicated chip for transceiver, and the processor can be considered to be implemented through a dedicated processing chip, a processing circuit or a general chip.

[0171] As another implementation method, it is possible to use a general-purpose computer to implement the server provided in the embodiment of the present application, that is, to store the program code for implementing the functions of the processor, receiver, and transmitter in a memory, and the general-purpose processor implements the functions of the processor, receiver, and transmitter by executing the code in the memory.

[0172] The embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the aforementioned enterprise contract automatic review method are implemented. The computer-readable storage medium can be a tangible storage medium, such as a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a floppy disk, a hard disk, a removable storage disk, a CD-ROM, or any other form of storage medium known in the technical field.

[0173] An embodiment of the present application also provides a computer program product, including a computer program, which implements the automatic enterprise contract review method when executed by a processor.

[0174] It should be understood by those skilled in the art that the exemplary components, systems and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software or a combination of the two. Whether it is specifically performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link via a data signal carried in a carrier.

[0175] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0176] In the present application, features described and / or illustrated for one embodiment may be used in the same manner or in a similar manner in one or more other embodiments, and / or combined with features of other embodiments or replace features of other embodiments.

[0177] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the embodiments of the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for automatic auditing of enterprise contracts, characterized in that: include: Identify the target enterprise's contract documents to obtain the target enterprise's corresponding core data and electronic signature content data; Verifying the electronic signature content data based on the enterprise name data included in the enterprise core data, and if the electronic signature content data passes the verification, then calculating the similarity between the enterprise core data and the enterprise structured data pre-issued by the target enterprise based on the edit distance algorithm to obtain the corresponding target similarity calculation result data; If the target similarity calculation result data meets the preset review pass rule, it is determined that the contract document of the target enterprise has passed the review so as to store the contract document and monitor its status in real time.

2. The method for automatic auditing of enterprise contracts according to claim 1 is characterized in that: Before obtaining the core enterprise data and electronic signature content data corresponding to the target enterprise from the contract document of the target enterprise, the method further includes: Receiving contract review requests respectively sent by various enterprises from a preset data interface, wherein the contract review requests include: a contract document pre-generated by the enterprise based on a target contract type template and enterprise structured data for the contract document provided by the enterprise; The received contract documents of each of the enterprises are added to a preset core queue.

3. The method for automatic auditing of enterprise contracts according to claim 2 is characterized in that: The core enterprise data and electronic signature content data corresponding to the target enterprise are obtained by identifying the contract document of the target enterprise, including: Extracting the contract documents of each enterprise from the core queue in sequence and taking the enterprise to which the currently extracted contract document belongs as the current target enterprise; Based on the preset core data extraction rules, extract the corresponding enterprise core data and electronic signature content data from the contract documents of the target enterprise; It is determined whether the extracted enterprise core data and the electronic signature content data meet their corresponding content recognition thresholds respectively. If so, the enterprise core data and the electronic signature content data are stored.

4. The method for automatic auditing of enterprise contracts according to claim 1 is characterized in that: The information type corresponding to the enterprise core data is the same as the information type corresponding to the enterprise structured data, or the information type corresponding to the enterprise structured data is less than the information type corresponding to the enterprise core data; The information types corresponding to the core data of the enterprise include: enterprise name, principal, personal information, enterprise title, tax number, purchaser's address, telephone number, contract start and end dates, and account opening information.

5. The method for automatic auditing of enterprise contracts according to claim 4 is characterized in that: The electronic signature content data is verified based on the enterprise name data included in the enterprise core data. If the electronic signature content data passes the verification, similarity calculation is performed on the enterprise core data and the enterprise structured data pre-issued by the target enterprise based on the edit distance algorithm to obtain corresponding target similarity calculation result data, including: Verifying the electronic signature content data based on the enterprise name data included in the enterprise core data, and if the text corresponding to the electronic signature content data is the same as the enterprise name data, determining that the electronic signature content data passes the verification; According to each information type contained in the enterprise structured data issued in advance by the target enterprise, character strings identical to each information type in the enterprise structured data are extracted from the enterprise core data to form target audit data corresponding to the enterprise core data; Extracting each character string in the target audit data and each character string in the enterprise structured data pre-issued by the target enterprise, and extracting one character string from each of the target audit data and the enterprise structured data according to a preset extraction order to form a comparison group, and executing a preset edit distance algorithm for each of the comparison groups to obtain similarity calculation result data corresponding to each of the comparison groups; The similarity calculation result data corresponding to each of the comparison groups are aggregated into corresponding target similarity calculation result data.

6. The method for automatic auditing of enterprise contracts according to claim 5 is characterized in that: The edit distance algorithm includes: Using the character string corresponding to the target audit data in the current comparison group as the source character string, and using the character string corresponding to the enterprise structured data in the comparison group as the target character string; The current initial problem is set as: the minimum edit distance required to convert the source string into the target string; Decompose the initial problem into sub-problems, wherein the sub-problem is the minimum edit distance d[i][j] required to convert the first i characters in the source string into the first j characters in the target string, where i is greater than 1 and less than the length of the source string, and j is greater than 1 and less than the length of the target string; If the i-th character in the source string is the same as the j-th character in the target string, then d[i][j]=d[i-1][j-1], where d[i-1][j-1] represents the minimum edit distance required to convert the first i-1 characters in the source string to the first j-1 characters in the target string; If the i-th character in the source string is different from the j-th character in the target string, a deletion operation is performed on the i-th character in the source string, an insertion operation is performed on the j-th character in the target string, and a replacement operation is performed on the source string to replace the i-th character in the source string with the j-th character in the target string; Selecting the minimum value from the values ​​of d[i][j] obtained after the deletion operation, the insertion operation, and the replacement operation as the solution value of the subproblem; The similarity calculation result data corresponding to the current comparison group is calculated based on the solution value of the sub-problem, the length of the source character string and the length of the target character string.

7. The method for automatic auditing of enterprise contracts according to claim 4 is characterized in that: Before verifying the electronic signature content data based on the enterprise name data included in the enterprise core data, the method further includes: Based on the pre-acquired data of the person in charge corresponding to the target enterprise, the authenticity of at least one of the information types corresponding to the enterprise core data, including the enterprise name, principal, personal information, company title, tax number, purchaser's address, telephone number, contract start and end dates, and account opening information, is verified. If the target audit data passes the authenticity verification, the enterprise name data in the enterprise core data is extracted for electronic signature content data verification.

8. The method for automatic auditing of enterprise contracts according to any one of claims 1 to 7, characterized in that: If the target similarity calculation result data meets the preset review pass rule, it is determined that the contract document of the target enterprise has passed the review to store and monitor the real-time status of the contract document, including: Determine whether the value corresponding to the target similarity calculation result data is within a preset audit passing value range, and if so, determine that the target similarity calculation result data has passed the audit; Adding the contract document of the target enterprise to a preset core delay queue so as to remove the contract document from the core delay queue at a time point before the contract corresponding to the contract document expires; For the contract document of the target enterprise taken out from the core delay queue, sending a notification message for prompting the target enterprise to renew the contract document; If it is monitored in real time or the contract document of the target enterprise is currently at the expiration of the service deadline, the enterprise service corresponding to the contract document will be automatically deactivated.

9. A contract automatic review device, characterized in that: include: A contract document identification module, used to identify the contract document of the target enterprise and obtain the enterprise core data and electronic signature content data corresponding to the target enterprise; A verification and review module, used to verify the electronic signature content data based on the enterprise name data contained in the enterprise core data. If the electronic signature content data passes the verification, similarity calculation is performed on the enterprise core data and the enterprise structured data pre-issued by the target enterprise based on the edit distance algorithm to obtain the corresponding target similarity calculation result data; The storage and monitoring module is used to determine that the contract document of the target enterprise has passed the review if the target similarity calculation result data meets the preset review pass rules, so as to store the contract document and monitor its status in real time.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for automatic review of enterprise contracts as described in any one of claims 1 to 8 is implemented.

Citation Information

Patent Citations

  • Contract management system and contract review method

    CN108764843A

  • Method and device for searching contract modification part, computer equipment and storage medium

    CN109933754A

  • Contract auditing method, apparatus and device, and medium

    CN110837998A

  • Double-recording method and device for electronic contract signing, computer equipment and storage medium

    CN111401826A

  • Intelligent order checking method and system based on OCR engine

    CN114973290A