Automatic contract text auditing method and system based on term unified modeling

Abstract

The invention discloses an automatic contract text auditing method and system based on clause unified modeling, and belongs to the technical field of contract auditing, and the auditing method comprises the following specific steps: I, accessing a third-party credit investigation mechanism or a credit rating platform to extract the credit information of both parties of a contract, and carrying out the credit investigation and auditing of the both parties of the contract; iI, establishing an initial contract template classified according to economic businesses, and extracting contract key information through an NLP technology; the optimal rule can be quickly identified and selected in a large number of detection rules, the auditing efficiency is remarkably improved, the time required by manual intervention is shortened, the auditing process is more flexible, the method can adapt to specific requirements of different contracts, potential risks in the contracts can be comprehensively identified, auditing personnel can be helped to find high-risk terms in time, and the contract auditing efficiency is improved. The law risk in contract fulfillment is reduced, the benefits of colleges and universities are protected, more stable risk control and compliance guarantee are provided for the colleges and universities, the contract fulfillment condition is monitored through integration with an accounting system, the compliance and the executive force of the contract are ensured, and the transparency and the traceability of contract management are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of contract review, and in particular to an automated contract text review method and system based on unified clause modeling. Background Art

[0002] In the modern business environment, contract management is becoming increasingly complex. In the field of higher education, colleges and universities sign contracts with multiple parties in their daily operations. Their contract management involves a wide range of content, including faculty appointments, scientific research projects, school-enterprise cooperation, procurement services, and many other aspects. Colleges and universities need to handle a large number of contracts to ensure compliance and reduce legal risks. The compliance and enforcement of these contracts are crucial to the reputation and financial security of the school. However, in the face of complex contract terms and diverse business needs, traditional manual review methods are often difficult to adapt to the efficiency requirements of modern university contract management. This review method often relies on manual operations, which is inefficient and prone to errors, resulting in a cumbersome and time-consuming contract management process. With the increasing complexity of the higher education environment and the frequent changes in laws and regulations, there is an urgent need for an efficient and reliable contract review solution.

[0003] After searching, Chinese patent number CN115809653A discloses an intelligent contract review method and system. Although this invention solves the current situation of large workload and inevitable errors in manual contract review in companies, improves the accuracy of contract review and improves the efficiency of contract review, the contract terms are not reviewed, the contract risks are high, and potential legal and financial risks cannot be identified in real time, the compliance and enforceability of the contract cannot be guaranteed, and more robust risk control and compliance guarantees cannot be provided for major universities, reducing the transparency and traceability of contract management. To this end, we propose an automated contract text review method and system based on unified modeling of terms. Summary of the invention

[0004] The purpose of the present invention is to solve the defects in the prior art and to propose an automated contract text review method and system based on unified clause modeling.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] The automated contract text review method based on unified clause modeling has the following specific steps:

[0007] Ⅰ. Access a third-party credit reporting agency or credit rating platform to extract the credit information of both parties to the contract, so as to conduct credit investigation and review on both parties to the contract;

[0008] II. Establish initial contract templates classified by economic business and extract key contract information through NLP technology;

[0009] III. Review the key information in the initial contract template based on OCR technology to identify the risk factors involved in the contract and mark the key points of the contract review;

[0010] IV. Generate electronic or paper contracts based on the needs of both parties to the contract, remind the contracting parties to confirm the terms and risks of the contract, and check the contract signing status in real time;

[0011] V. Review the integrity of the signed contract information and extract key contract data through NLP and OCR technologies for filing and registration;

[0012] VI. Interact with the financial accounting system for data, analyze the contract performance based on the extracted key contract information, and issue risk alerts based on the performance status.

[0013] 2. The automated contract text review method based on unified clause modeling according to claim 1 is characterized in that the specific steps of the credit investigation and review in step I are as follows:

[0014] S1.1: Connect with external third-party credit reporting agencies or credit rating platforms, and obtain the credit records, business conditions, historical litigation information and administrative penalty records of the contracting party by calling the corresponding API interface;

[0015] S1.2: Automatically analyze the financial data of the contracting party through public financial information or financial statements provided by suppliers or customers, automatically retrieve the contracting party's historical contract execution records, and query the contracting party's past contract performance through historical data comparison;

[0016] S1.3: Explore the relationship between the contracting party and other enterprises, identify its affiliated companies and upstream and downstream enterprises, and automatically detect the risk information of the contracting party and its affiliated parties by combining public judicial information and enterprise operation information;

[0017] S1.4: Based on the collected information, the contracting parties are classified into different risk levels based on the internal rules of the risk database. After the credit score and risk rating are generated, a risk assessment report is automatically generated, and potential risk points are highlighted. If the system identifies that the contracting party has a high risk of default, an early warning reminder will be automatically popped up.

[0018] 3. The automated contract text review method based on unified clause modeling according to claim 2 is characterized in that the specific steps of extracting key contract information in step II are as follows:

[0019] S2.1: Establish standardized contract templates according to different types of economic business, and review the legality, rationality, risk identification and modification suggestions of the clauses in each contract template through the legal department in accordance with the latest laws and regulations, industry policies and the regulations of the contracting universities;

[0020] S2.2: Based on actual business needs, both parties to the contract select the corresponding contract template, adjust and modify the template, and the audit system extracts the modified contract terms information in real time and provides real-time compliance prompts. At the same time, the audit system provides modification suggestions and records the change history during the modification process;

[0021] S2.3: Remove extra spaces, punctuation marks and formatting errors from the contract text, split the contract text into separate words or phrases using word segmentation technology, extract keywords corresponding to the contract to be tested from a comparison database containing industry keywords and legal terms, and compare each group of keywords with the contract text to identify important content in the text;

[0022] S2.4: Automatically identify important entities in the contract text through named entity recognition technology, annotate and store the identified entities, parse the grammatical structure of the contract text through syntactic analysis technology, identify the subject, predicate and object components in the sentence, and obtain the logical relationship between the various clauses of the contract;

[0023] S2.5: Extract key terms from the parsed text and classify them. Organize the extracted key terms into a standardized format. Then use the text similarity algorithm to compare the extracted terms with historical contract templates to identify similar terms and differences.

[0024] 4. The automated contract text review method based on unified clause modeling according to claim 3 is characterized in that the specific steps of identifying the risk factors involved in the contract in step III are as follows:

[0025] S3.1: Collect the images of the initial contract texts prepared by both parties and convert them into a format that can be processed by the audit system. Use OCR technology to extract the text in the images of the contract texts after the format conversion is completed, and convert the text in the images into an editable text format;

[0026] S3.2: Identify and remove irrelevant characters and noise in the text through regular expressions and text processing functions, then use dictionary and context information for comparison, identify recognition errors that occur during the OCR process, automatically correct incorrect characters, and then convert all texts into a unified character encoding;

[0027] S3.3: Use Chinese word segmentation tools to identify words in the cleaned text and split them into individual words or phrases to form a word list, identify and remove stop words in the word list, use a lemma restoration algorithm to lemma the word segmentation results, and then perform final text verification through text length check and specific format verification;

[0028] S3.4: Load the standard contract template that has been reviewed by the legal department, compare the extracted contract text with the standard template, analyze the clauses one by one, determine whether there are any omissions, changes or inconsistencies, and automatically identify the risk factors in the contract based on the preset rules in the risk library;

[0029] S3.5: Combine historical contract data and market data, use big data analysis technology to evaluate the risk factors of the contract, and then summarize the identified risk factors and evaluation results to generate a detailed risk assessment report.

[0030] 5. The automated contract text review method based on unified clause modeling according to claim 4 is characterized in that the specific steps of automatically identifying risk factors in the contract as described in S3.4 are as follows:

[0031] S4.1: The risk library receives the contract text to be reviewed and obtains the current contract review progress. Based on the current review progress, it extracts the required detection rules. Then, it integrates the current review status and review progress into a set of root nodes, and uses the new review status generated after applying different detection rules as child nodes. It sets the current risk assessment value, execution cost and expected effect attributes of each node.

[0032] S4.2: Perform random simulation on each child node to evaluate the different audit results that will be generated after the rule is applied. Through multiple iterations, the success rate and potential risks of the rule application are obtained, and the results of each simulation are recorded. Then, based on the simulation results, the detection rule with the highest success rate under the current node is selected, the tree structure is expanded, and a new child node is generated;

[0033] S4.3: During the expansion process, the risk library simultaneously identifies and marks potential risk points. After the expansion is completed, each node in the tree is evaluated, and its risk assessment value and execution cost are updated. Based on the evaluation results, the nodes that do not meet the preset requirements are pruned. Then, based on the structure of the tree, the path with the highest success rate and the lowest potential risk is selected as the final contract review plan;

[0034] S4.4: After the current audit progress is completed, a detailed risk assessment report will be generated, listing the risk factors found in the audit and their corresponding detection rules. The audit results and identified risk information will be fed back to the risk library for regular updates and adjustments to the detection rules. At the same time, when the next stage of the audit begins, the corresponding audit plan will be regenerated based on the next audit status to review the contract text.

[0035] An automated contract text review system based on unified clause modeling, including a contract investigation module, a risk library management module, a template management module, a clause extraction module, an OCR recognition module, a contract review module, a risk assessment module, a signing and filing module, a performance monitoring module, an analysis report module, and a permission management module;

[0036] The contract investigation module is used to conduct credit investigation on both parties to the contract, including creditworthiness, qualifications, relevance and contract performance assessment;

[0037] The risk library management module is used to establish a risk library, and set line detection rules and standards for each audit process, and gradually sort out the risk factors in the contract audit process;

[0038] The template management module is used to establish and maintain multiple groups of standard contract templates that have passed legal review;

[0039] The clause extraction module is used to extract and structure key clauses in the contract text through NLP technology to form standardized clause data;

[0040] The OCR recognition module is used to convert paper contracts or image documents into editable text through OCR technology;

[0041] The contract review module is used to conduct a comprehensive review of the extracted contract text and standard templates, and identify potential high-risk clauses;

[0042] The risk assessment module is used to assess the risk factors in the contract text based on the contract review results and the detection rules in the risk library to generate a risk report and mark high-risk clauses;

[0043] The signing and filing module is used to record signing information and automatically file contracts;

[0044] The performance monitoring module is used to monitor the performance of the contract in real time based on the extracted key information;

[0045] The analysis report module is used to conduct a comprehensive analysis of the data of the entire contract review process and generate various management reports;

[0046] The authority management module is used to perform authority management on system users.

[0047] As a further solution of the present invention, the specific steps of establishing a risk library by the risk library management module are as follows:

[0048] S5.1: Collect historical cases and expert opinions, identify legal risk, financial risk and performance risk by analyzing historical contract data and industry practice data, and then design the risk type, risk description, impact level, detection rules and response measures stored in the risk library;

[0049] S5.2: For each risk factor, formulate specific line detection rules and standards, and set the trigger conditions and response measures for each rule. Then, input the identified risk factors and their corresponding detection rules into the risk library, and organize and classify them;

[0050] S5.3: The initial risk library is constructed by simulating the contract review process test, and the rules are adjusted and optimized according to the test results. Based on market changes, legal and regulatory updates, university needs and internal enterprise feedback, the risk library is regularly reviewed and updated, new risk factors and detection rules are added, and no longer applicable content is removed. At the same time, documents and manuals for the use of the risk library are generated, detailing the functions and usage of the risk library;

[0051] S5.4: Automatically connect the constructed risk library with the contract review process, and automatically identify risks based on the review progress and detection rules. When risk factors are detected, early warning information is automatically generated to promptly remind contract reviewers to pay attention and handle them.

[0052] As a further solution of the present invention, the signing and filing module automatically performs specific steps of contract filing: after the contract is reviewed and approved, when online signing is selected, an electronic contract containing all relevant terms and information is generated. After the contract is generated, the relevant parties sign online through the electronic signing platform, and the identity information and signing time of each signatory are recorded to ensure the legality of the contract. After the electronic signing is completed, the system automatically uploads the contract data to the contract management database and generates a filing record;

[0053] When offline signing is selected, the contract will be printed into a paper version after review and all clauses will be clearly visible. After the contract is printed, the relevant parties sign and stamp on the paper contract. After stamping, the contract is scanned by a scanner or high-quality camera to generate a high-resolution image file. After the signing and filing module receives the scanned contract image, it removes image noise, adjusts image contrast and brightness to improve recognition accuracy, and then uses OCR technology to recognize the contract text and extract key information in the contract, including signatory information, contract terms, date and other relevant content. After recognition, the system will verify the extracted information and compare it with the standard template or original contract data to ensure the accuracy of the information. The contract information recognized and verified by OCR will be stored in the contract management system to generate an electronic filing record, and then the electronic version of the contract will be associated with the identification data to ensure the archiving integrity of the contract. After filing is completed, the system automatically notifies the relevant parties to confirm the filing status and information of the contract. At the same time, relevant personnel can query the filed contract information through the contract management system.

[0054] As a further solution of the present invention, the specific steps of the performance monitoring module to monitor the performance of the contract in real time are as follows:

[0055] S6.1: Extract key information such as payment terms, delivery period, amount, and bank account information of both parties from the signed contract, and process the contract text using NLP technology to form a standardized data format;

[0056] S6.2: Connect the extracted key information with the financial accounting system through API or database, and update and synchronize the various sets of contract data in real time. Regularly monitor the progress of contract performance according to the set monitoring frequency, and check the payment date and delivery time key nodes stipulated in the contract terms;

[0057] S6.3: Extract actual account information from the financial accounting system and compare it with the contract terms. Automatically detect contract performance based on the risk library detection rules. When it is detected that the funds have not been received on time or the funds are abnormal, automatically generate risk warning information and notify the corresponding contract management personnel through the system. At the same time, regularly generate reports on contract performance, summarizing all performance analysis results, risk warnings and processing situations.

[0058] Compared with the prior art, the present invention has the following beneficial effects:

[0059] The present invention is connected with an external third-party credit reporting agency or credit rating platform, and obtains various credit data of the contracting parties by calling the corresponding API interface, conducts credit investigation on both parties to the contract, and then collects historical cases and expert opinions, establishes a corresponding risk library by analyzing historical contract data and industry practice data, formulates specific line detection rules and standards for the risk library for each risk factor, automatically connects the constructed risk library with the contract review process, and according to the review progress and detection rules, for each review progress, constructs a corresponding detection plan to automatically identify the risk information of each process of the contract, establishes and maintains multiple groups of standard contract templates that have passed legal review, and then extracts key information from the contract through NLP technology and OCR intelligent recognition, marks the review points in the contract, and when the contract passes the review, signs the contract online or offline according to the choice of both parties to the contract, and records the identity information and signing time of each signatory, and files the signed contract data. After the filing is completed, the system automatically notifies the relevant parties to confirm the filing status and information of the contract, and the relevant personnel can query the filing through the contract management system The contract information is extracted from the signed contract, including payment terms, delivery period, amount and bank account information of both parties to the contract. The NLP technology processes the contract text to form a standardized data format, connects the extracted key information with the financial accounting system through API or database, and updates and synchronizes the various data of the contract in real time. According to the set monitoring frequency, the progress of contract performance is monitored regularly. At the same time, a report on contract performance is generated regularly, summarizing all performance analysis results, risk warnings and processing situations. It can quickly identify and select the best rules from a large number of detection rules, significantly improve the efficiency of the audit, reduce the time required for manual intervention, make the audit process more flexible, adapt to the specific needs of different contracts, and comprehensively identify potential risks in the contract, helping auditors to promptly discover high-risk clauses, reduce legal risks in contract performance, protect the interests of colleges and universities, and provide more robust risk control and compliance guarantees for major colleges and universities. It also monitors contract performance through integration with the accounting system, ensures the compliance and execution of the contract, and improves the transparency and traceability of contract management. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0061] Figure 1 A flowchart of the automated contract text review method based on unified clause modeling proposed by the present invention;

[0062] Figure 2 This is a system block diagram of the automated contract text review system based on unified clause modeling proposed by the present invention;

[0063] Figure 3 This is a contract management system diagram of the automated contract text review system based on unified clause modeling proposed by the present invention. DETAILED DESCRIPTION

[0064] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0065] Example 1

[0066] Reference Figure 1 , Figure 3 This embodiment discloses an automated contract text review method based on unified clause modeling. The specific steps of the review method are as follows:

[0067] Access a third-party credit reporting agency or credit rating platform to conduct credit investigation and review on both parties to the contract.

[0068] Specifically, it connects with external third-party credit reporting agencies or credit rating platforms, and obtains the credit record, operating conditions, historical litigation information and administrative penalty records of the contracting party by calling the corresponding API interface. It automatically analyzes the financial data of the contracting party through public financial report information or financial statements provided by suppliers or customers, automatically retrieves the contracting party's historical contract execution records, and inquires about the contracting party's past contract performance through historical data comparison. It explores the relationship between the contracting party and other companies, identifies its affiliated companies and upstream and downstream companies, and automatically detects the risk information of the contracting party and its affiliates in combination with public judicial information and corporate operating information. According to the collected groups of information, the contracting party is classified into different risk levels based on the internal rules of the risk library. After the credit score and risk rating are generated, a risk assessment report is automatically generated, and potential risk points are highlighted. If the system identifies that the contracting party has a high risk of default, an early warning reminder will be automatically popped up.

[0069] Establish initial contract templates classified by economic business and extract key contract information through NLP technology.

[0070] Specifically, standardized contract templates are established according to different types of economic business. Based on the latest laws, regulations and industry policies, the legal department reviews the legality, rationality, risk identification and modification suggestions of the clauses in each contract template. According to actual business needs, the two parties to the contract select the corresponding contract template, adjust and modify the template, and the review system extracts the modified contract clause information in real time and provides real-time compliance prompts. At the same time, the review system provides modification suggestions and records the change history during the modification process, removes unnecessary spaces, punctuation marks and formatting errors in the contract text, and then splits the contract text into separate words or phrases through word segmentation technology, from words containing industry keywords and legal Keywords corresponding to the contract to be tested are extracted from the term comparison database, and each group of keywords is compared with the contract text to identify the important content in the text. The important entities in the contract text are automatically identified through named entity recognition technology, and the identified entities are annotated and stored. The grammatical structure of the contract text is parsed through syntactic analysis technology, and the subject, predicate and object components in the sentence are identified to obtain the logical relationship between the various clauses of the contract. Key clauses are extracted from the parsed text and classified. At the same time, the extracted key clauses are organized into a standardized format. Then, the text similarity algorithm is used to compare the extracted clauses with historical contract templates to identify similar clauses and differences.

[0071] Review the key information in the initial contract template based on OCR technology to identify the risk factors involved in the contract and mark the key points of the contract review.

[0072] Specifically, collect the images of the initial contract texts drafted by both parties to the contract, and convert them into a format that can be processed by the audit system. Use OCR technology to extract the text in the images of the contract text after the format conversion is completed, and convert the text in the image into an editable text format. Use regular expressions and text processing functions to identify and remove irrelevant characters and noise in the text. Then use dictionaries and context information for comparison, identify recognition errors that occur during the OCR process, and automatically correct erroneous characters. Then convert all texts into a unified character encoding, use Chinese word segmentation tools to identify the vocabulary in the cleaned text, and split it into separate words or phrases. Form a word list, identify and remove stop words in the word list, use a word form restoration algorithm to restore the word form of the segmentation results, and then perform final text verification through text length check and specific format verification. Load the standard contract template that has been reviewed by legal affairs, compare the extracted contract text with the standard template, analyze the clauses one by one, and determine whether there are any omissions, changes or inconsistencies. Based on the preset rules in the risk library, automatically identify the risk factors in the contract, combine historical contract data and market data, use big data analysis technology to evaluate the risk factors of the contract, and then summarize the identified risk factors and evaluation results to generate a detailed risk assessment report.

[0073] It should be further explained that the risk library receives the contract text to be reviewed and obtains the current contract review progress. Based on the current review progress, it extracts the required groups of detection rules, then integrates the current review status and review progress into a group of root nodes, and uses the new review status generated after applying different detection rules as child nodes. It sets the current risk assessment value, execution cost and expected effect of each node, performs random simulation on each child node, evaluates the different review results that will be generated after the rule is applied, obtains the success rate and potential risks of the rule application through multiple iterations, and records the results of each simulation. Then, based on the simulation results, selects the detection rule with the highest success rate under the current node, expands the tree structure, and generates new child nodes. Node. During the expansion process, the risk library simultaneously identifies and marks potential risk points. After the expansion is completed, each node in the tree is evaluated, and its risk assessment value and execution cost are updated. Based on the evaluation results, the nodes that do not meet the preset requirements are pruned. Then, based on the structure of the tree, the path with the highest success rate and the lowest potential risk is selected as the final contract review plan. After the current review progress is completed, a detailed risk assessment report is generated, listing the risk factors found in the review and their corresponding detection rules. The audit results and identified risk information are fed back to the risk library for regular updates and adjustments to the detection rules. At the same time, when the next stage of the review begins, the corresponding audit plan is regenerated based on the next audit status to review the contract text.

[0074] Generate electronic or paper contracts based on the needs of both parties to the contract, remind the contracting parties to confirm the terms and risks of the contract, and check the contract signing status in real time.

[0075] Review the integrity of the signed contract information and extract key contract data through NLP and OCR technologies for filing and registration.

[0076] It interacts with the financial accounting system and analyzes the contract performance based on the extracted key contract information, while also issuing risk alerts based on the performance status.

[0077] Example 2

[0078] Reference Figure 2-3 This embodiment discloses an automated contract text review system based on unified clause modeling, including a contract investigation module, a risk library management module, a template management module, a clause extraction module, an OCR recognition module, a contract review module, a risk assessment module, a signing and filing module, a performance monitoring module, an analysis report module, and a permission management module.

[0079] The contract investigation module is used to conduct credit investigations on both parties to the contract, including creditworthiness, qualifications, relevance and performance assessments; the risk library management module is used to establish a risk library, and at the same time set line detection rules and standards for each review process, gradually sorting out the risk factors in the contract review process.

[0080] Specifically, historical cases and expert opinions are collected, and risk factors such as legal risk, financial risk and performance risk are identified by analyzing historical contract data and industry practice data. Then, the risk type, risk description, impact level, detection rules and response measures stored in the risk library are designed. For each risk factor, specific line detection rules and standards are formulated, and the trigger conditions and response measures for each rule are set. The identified risk factors and their corresponding detection rules are then entered into the risk library, sorted and classified. The initial risk library constructed by simulating the contract review process test is constructed, and the rules are adjusted and optimized according to the test results. Then, based on market changes, legal and regulatory updates, university needs and internal enterprise feedback, the risk library is regularly reviewed and updated, new risk factors and detection rules are added, and content that is no longer applicable is eliminated. At the same time, documents and manuals for the use of the risk library are generated, detailing the functions and usage of the risk library. The constructed risk library is automatically connected to the contract review process, and risks are automatically identified according to the review progress and detection rules. When risk factors are detected, early warning information is automatically generated to promptly remind contract reviewers to pay attention and handle them.

[0081] The template management module is used to establish and maintain multiple sets of standard contract templates that have passed legal review; the clause extraction module is used to extract and structure key clauses in the contract text through NLP technology to form standardized clause data; the OCR recognition module is used to convert paper contracts or image documents into editable text through OCR technology; the contract review module is used to conduct a comprehensive review of the extracted contract text and standard templates, and identify potential high-risk clauses; the risk assessment module is used to evaluate the risk factors in the contract text based on the contract review results and the detection rules in the risk library, so as to generate a risk report and mark high-risk clauses;

[0082] The signing and filing module is used to record signing information and automatically file contracts.

[0083] Specifically, after the contract is reviewed and approved, when online signing is selected, an electronic contract containing all relevant terms and information is generated. After the contract is generated, the relevant parties sign online through the electronic signature platform, and record the identity information and signing time of each signatory to ensure the legality of the contract. When the electronic signature is completed, the system automatically uploads the contract data to the contract management database and generates a filing record; when offline signing is selected, the contract is printed into a paper version after review and approval, and ensure that all terms are clearly visible. After the contract is printed, the relevant parties sign and stamp on the paper contract. After the stamp is completed, the contract is scanned by a scanner or high-quality camera equipment to generate a high-resolution image file. The signing and filing module receives the scanned contract image. After the image is taken, image noise is removed, and image contrast and brightness are adjusted to improve recognition accuracy. The contract text is then recognized using OCR technology to extract key information from the contract, including signatory information, contract terms, dates, and other relevant content. After recognition, the system will verify the extracted information and compare it with the standard template or original contract data to ensure the accuracy of the information. The contract information that has been recognized and verified by OCR will be stored in the contract management system to generate an electronic filing record. The electronic version of the contract will then be associated with the recognition data to ensure the integrity of the contract archive. After filing is completed, the system automatically notifies the relevant parties to confirm the filing status and information of the contract. At the same time, relevant personnel can query the filed contract information through the contract management system.

[0084] The performance monitoring module is used to monitor the performance of the contract in real time based on the extracted key information.

[0085] Specifically, key information such as payment terms, delivery period, amount, and bank account information of both parties to the contract are extracted from the signed contract, and the contract text is processed by NLP technology to form a standardized data format. The extracted key information is connected to the financial accounting system through API or database, and each group of contract data is updated and synchronized in real time. According to the set monitoring frequency, the progress of contract performance is monitored regularly, and the key nodes of payment date and delivery time stipulated in the contract terms are checked. The actual account information is extracted from the financial accounting system and compared with the contract terms. The contract performance is automatically detected according to the risk library detection rules. When it is detected that the payment is not received on time or the amount is abnormal, risk warning information is automatically generated, and the corresponding contract management personnel are notified through the system. At the same time, reports on contract performance are generated regularly to summarize all performance analysis results, risk warnings and processing situations.

[0086] The analysis report module is used to conduct a comprehensive analysis of the data of the entire contract review process and generate various management reports; the authority management module is used to manage the authority of system users.

Claims

1. An automated contract text review method based on unified clause modeling, characterized in that: The specific steps of this audit method are as follows: Ⅰ. Access a third-party credit reporting agency or credit rating platform to extract the credit information of both parties to the contract, so as to conduct credit investigation and review on both parties to the contract; II. Establish initial contract templates classified by economic business and extract key contract information through NLP technology; III. Review the key information in the initial contract template based on OCR technology to identify the risk factors involved in the contract and mark the key points of the contract review; IV. Generate electronic or paper contracts based on the needs of both parties to the contract, remind the contracting parties to confirm the terms and risks of the contract, and check the contract signing status in real time; V. Review the integrity of the signed contract information and extract key contract data through NLP and OCR technologies for filing and registration; VI. Interact with the financial accounting system for data, analyze the contract performance based on the extracted key contract information, and issue risk alerts based on the performance status.

2. The automated contract text review method based on unified clause modeling according to claim 1 is characterized in that: The specific steps of credit investigation and review described in Step Ⅰ are as follows: S1.1: Connect with external third-party credit reporting agencies or credit rating platforms, and obtain the credit records, business conditions, historical litigation information and administrative penalty records of the contracting party by calling the corresponding API interface; S1.2: Automatically analyze the financial data of the contracting party through public financial information or financial statements provided by suppliers or customers, automatically retrieve the contracting party's historical contract execution records, and query the contracting party's past contract performance through historical data comparison; S1.3: Explore the relationship between the contracting party and other enterprises, identify its affiliated companies and upstream and downstream enterprises, and automatically detect the risk information of the contracting party and its affiliated parties by combining public judicial information and enterprise operation information. Then extract the information of the contracting enterprise's registered capital, shareholders and investment ratio, legal representative and main responsible persons, obtain the information of the related persons of the enterprise person in charge through a third-party database, and compare the extracted information of the enterprise person in charge and his related persons with the project leader of the university. If the name of the person in charge is the same, a reminder will be issued; S1.4: Based on the collected information, the contracting parties are classified into different risk levels based on the internal rules of the risk database. After the credit score and risk rating are generated, a risk assessment report is automatically generated, and potential risk points are highlighted. If the system identifies that the contracting party has a high risk of default, an early warning reminder will be automatically popped up.

3. The automated contract text review method based on unified clause modeling according to claim 2 is characterized in that: The specific steps for extracting key contract information in step II are as follows: S2.1: Establish standardized contract templates according to different types of economic business, and review the legality, rationality, risk identification and modification suggestions of the clauses in each contract template through the legal department in accordance with the latest laws and regulations, industry policies and the regulations of the contracting universities; S2.2: Based on actual business needs, both parties to the contract select the corresponding contract template, adjust and modify the template, and the audit system extracts the modified contract terms information in real time and provides real-time compliance prompts. At the same time, the audit system provides modification suggestions and records the change history during the modification process; S2.3: Remove extra spaces, punctuation marks and formatting errors from the contract text, split the contract text into separate words or phrases using word segmentation technology, extract keywords corresponding to the contract to be tested from a comparison database containing industry keywords and legal terms, and compare each group of keywords with the contract text to identify important content in the text; S2.4: Automatically identify important entities in the contract text through named entity recognition technology, annotate and store the identified entities, parse the grammatical structure of the contract text through syntactic analysis technology, identify the subject, predicate and object components in the sentence, and obtain the logical relationship between the various clauses of the contract; S2.5: Extract key terms from the parsed text and classify them. Organize the extracted key terms into a standardized format. Then use the text similarity algorithm to compare the extracted terms with historical contract templates to identify similar terms and differences.

4. The automated contract text review method based on unified clause modeling according to claim 3 is characterized in that: The specific steps for identifying the risk factors involved in the contract as described in Step III are as follows: S3.1: Collect the images of the initial contract texts prepared by both parties and convert them into a format that can be processed by the audit system. Use OCR technology to extract the text in the images of the contract texts after the format conversion is completed, and convert the text in the images into an editable text format; S3.2: Identify and remove irrelevant characters and noise in the text through regular expressions and text processing functions, then use dictionary and context information for comparison, identify recognition errors that occur during the OCR process, automatically correct incorrect characters, and then convert all texts into a unified character encoding; S3.3: Use Chinese word segmentation tools to identify words in the cleaned text and split them into individual words or phrases to form a word list, identify and remove stop words in the word list, use a lemma restoration algorithm to lemma the word segmentation results, and then perform final text verification through text length check and specific format verification; S3.4: Load the standard contract template that has been reviewed by the legal department, compare the extracted contract text with the standard template, analyze the clauses one by one, determine whether there are any omissions, changes or inconsistencies, and automatically identify the risk factors in the contract based on the preset rules in the risk library; S3.5: Combine historical contract data and market data, use big data analysis technology to evaluate the risk factors of the contract, and then summarize the identified risk factors and evaluation results to generate a detailed risk assessment report.

5. The automated contract text review method based on unified clause modeling according to claim 4 is characterized in that: The specific steps for automatically identifying risk factors in contracts as described in S3.4 are as follows: S4.1: The risk library receives the contract text to be reviewed and obtains the current contract review progress. Based on the current review progress, it extracts the required detection rules. Then, it integrates the current review status and review progress into a set of root nodes, and uses the new review status generated after applying different detection rules as child nodes. It sets the current risk assessment value, execution cost and expected effect attributes of each node. S4.2: Perform random simulation on each child node to evaluate the different audit results that will be generated after the rule is applied. Through multiple iterations, the success rate and potential risks of the rule application are obtained, and the results of each simulation are recorded. Then, based on the simulation results, the detection rule with the highest success rate under the current node is selected, the tree structure is expanded, and a new child node is generated; S4.3: During the expansion process, the risk library simultaneously identifies and marks potential risk points. After the expansion is completed, each node in the tree is evaluated, and its risk assessment value and execution cost are updated. Based on the evaluation results, the nodes that do not meet the preset requirements are pruned. Then, based on the structure of the tree, the path with the highest success rate and the lowest potential risk is selected as the final contract review plan; S4.4: After the current audit progress is completed, a detailed risk assessment report will be generated, listing the risk factors found in the audit and their corresponding detection rules. The audit results and identified risk information will be fed back to the risk library for regular updates and adjustments to the detection rules. At the same time, when the next stage of the audit begins, the corresponding audit plan will be regenerated based on the next audit status to review the contract text.

6. An automated contract text review system based on unified clause modeling, used to implement the automated contract text review method based on unified clause modeling as described in any one of claims 1 to 5, characterized in that: It includes contract investigation module, risk library management module, template management module, clause extraction module, OCR recognition module, contract review module, risk assessment module, signing and filing module, performance monitoring module, analysis report module and authority management module; The contract investigation module is used to conduct credit investigation on both parties to the contract, including creditworthiness, qualifications, relevance and contract performance assessment; The risk library management module is used to establish a risk library, and set line detection rules and standards for each audit process, and gradually sort out the risk factors in the contract audit process; The template management module is used to establish and maintain multiple groups of standard contract templates that have passed legal review; The clause extraction module is used to extract and structure key clauses in the contract text through NLP technology to form standardized clause data; The OCR recognition module is used to convert paper contracts or image documents into editable text through OCR technology; The contract review module is used to conduct a comprehensive review of the extracted contract text and standard templates, and identify potential high-risk clauses; The risk assessment module is used to assess the risk factors in the contract text based on the contract review results and the detection rules in the risk library to generate a risk report and mark high-risk clauses; The signing and filing module is used to record signing information and automatically file contracts; The performance monitoring module is used to monitor the performance of the contract in real time based on the extracted key information; The analysis report module is used to conduct a comprehensive analysis of the data of the entire contract review process and generate various management reports; The authority management module is used to perform authority management on system users.

7. The automated contract text review system based on unified clause modeling according to claim 6 is characterized in that: The specific steps of establishing a risk library by the risk library management module are as follows: S5.1: Collect historical cases and expert opinions, identify legal risk, financial risk and performance risk by analyzing historical contract data and industry practice data, and then design the risk type, risk description, impact level, detection rules and response measures stored in the risk library; S5.2: For each risk factor, formulate specific line detection rules and standards, and set the trigger conditions and response measures for each rule. Then, input the identified risk factors and their corresponding detection rules into the risk library, and organize and classify them; S5.3: The initial risk library is constructed by simulating the contract review process test, and the rules are adjusted and optimized according to the test results. Based on market changes, legal and regulatory updates, university needs and internal enterprise feedback, the risk library is regularly reviewed and updated, new risk factors and detection rules are added, and no longer applicable content is removed. At the same time, documents and manuals for the use of the risk library are generated, detailing the functions and usage of the risk library; S5.4: Automatically connect the constructed risk library with the contract review process, and automatically identify risks based on the review progress and detection rules. When risk factors are detected, early warning information is automatically generated to promptly remind contract reviewers to pay attention and handle them.

8. The automated contract text review system based on unified clause modeling according to claim 6 is characterized in that: The specific steps of the contract performance monitoring module to monitor the contract performance in real time are as follows: S6.1: Extract key information such as payment terms, delivery period, amount, and bank account information of both parties from the signed contract, and process the contract text using NLP technology to form a standardized data format; S6.2: Connect the extracted key information with the financial accounting system through API or database, and update and synchronize the various sets of contract data in real time. Regularly monitor the progress of contract performance according to the set monitoring frequency, and check the payment date and delivery time key nodes stipulated in the contract terms; S6.3: Extract actual account information from the financial accounting system and compare it with the contract terms. Automatically detect contract performance based on the risk library detection rules. When it is detected that the funds have not been received on time or the funds are abnormal, automatically generate risk warning information and notify the corresponding contract management personnel through the system. At the same time, regularly generate reports on contract performance, summarizing all performance analysis results, risk warnings and handling situations.

Images