A Closed-Loop Optimization Method and System for Contract Review Based on Weak User Feedback

Abstract

This invention discloses a closed-loop optimization method and system for contract review based on weak user feedback. The key technical points are: the system includes: a user input interface; a contract parsing module; a review logic initialization module; a review model module; an error history retrieval module; a result correction module; a user feedback storage module; and a closed-loop optimization module. This invention improves the accuracy and efficiency of contract review through an intelligent review process. By automatically parsing contract text, matching review checklists, applying dynamically optimized review logic, and combining a large language model to perform risk analysis on contracts, the system can not only identify potential problems but also continuously adjust the review logic based on weak user feedback, forming a closed-loop optimization. This method can flexibly adjust review rules according to contract characteristics, industry needs, and regulatory changes, thereby providing users with more accurate and personalized review services and continuously improving review effectiveness through the accumulation of feedback.

Description

Technical Field

[0001] This invention relates to the field of automated review technology, specifically to a closed-loop optimization method and system for contract review based on weak user feedback. Background Technology

[0002] As businesses continue to grow, contracts play an increasingly important role in daily operations. This is especially true for large enterprises and multinational corporations, where the sheer number and complexity of contracts, along with diverse legal, regulatory, and business terms, make contract management and review crucial. To ensure contract compliance, legality, and risk control, companies typically employ contract management systems to track and manage the entire contract lifecycle, covering drafting, negotiation, review, signing, performance, and archiving.

[0003] Currently, most existing contract management systems rely on predefined review checklists and fixed review logic. Typically, legal personnel set review standards during the contract review process and review the contract content accordingly. These traditional systems' review mechanisms, dependent on manually set rules, suffer from the following significant problems:

[0004] 1. Existing contract review systems typically rely on pre-defined review checklists and fixed review logic;

[0005] 2. Most existing systems only record user error feedback and lack an effective mechanism to collect and respond to user feedback information in a timely manner;

[0006] 3. Current contract review systems lack automated optimization capabilities based on machine learning and artificial intelligence;

[0007] The root cause of these shortcomings is that traditional contract management systems have failed to fully integrate modern artificial intelligence technology, especially large language models, and lack the ability for real-time optimization, dynamic updates, and intelligent feedback. To solve the above problems, we propose a closed-loop optimization method and system for contract review based on weak user feedback. Summary of the Invention

[0008] To address the shortcomings of existing technologies, this invention provides a closed-loop optimization method and system for contract review based on weak user feedback, thus resolving the problems mentioned in the background section.

[0009] The above-mentioned technical objective of the present invention is achieved through the following technical solution:

[0010] A closed-loop optimization method for contract review based on weak user feedback, the method comprising the following steps:

[0011] S1. Users upload the contract text to be reviewed to the platform through the system interface. The system preprocesses the contract text, generates basic contract information, and provides data support for subsequent review.

[0012] S2. The system parses the uploaded contract text, automatically matches an appropriate review checklist based on the contract type, content, and terms, and generates preliminary review points to ensure the relevance and accuracy of the review.

[0013] S3. The system loads relevant review logic from a predefined review logic library and automatically iterates and optimizes the loaded review logic using a large language model. Users can choose to apply new logic, reject new logic, or update the review logic according to their needs through "weak feedback" based on contract characteristics, industry requirements, or the latest regulations. User feedback information is recorded and used as a basis for system adjustments.

[0014] S4. Based on the confirmed review checklist, the system performs contract review through a large language model, automatically analyzes the contract text, identifies potential risks, and outputs preliminary review results.

[0015] S5. After the review is completed, the system generates preliminary review results and displays them to the user, allowing the user to provide immediate feedback;

[0016] S6. Based on the current review logic context, contract context, and machine review results, the system retrieves historical erroneous review data, analyzes and identifies potential misjudgments or errors in similar situations, and provides reference data for subsequent corrections.

[0017] S7. If similar erroneous data is retrieved, the system generates correction suggestions through the large language model and adjusts the current review logic or review results according to the suggestions. In this step, the system intelligently corrects the erroneous results, improves the accuracy of the review, and avoids repeating errors.

[0018] S8. The corrected review results are displayed to the user, and user feedback is collected. Users can submit "weak feedback" through the interface, such as confirmation, rejection, or suggestions for further modification of the review logic.

[0019] S9. User feedback and review results are stored together in the review result index library, forming a quadruple (Pi, Ci, RMi, RHi) containing the review logic context, contract context, machine review results and user feedback. This data is used for subsequent optimization and closed-loop updates.

[0020] S10. The system analyzes and applies user feedback in real time through the closed-loop optimization module, combines historical feedback data with the analysis of the large language model, and automatically optimizes the review logic. If the error feedback reaches a certain threshold, the closed-loop optimization module triggers the dynamic update of the review logic library, and the system automatically adjusts the review logic and applies it to the next review.

[0021] S11. All feedback information is processed and applied to the review logic, thus completing the review process and proceeding to the next round of review.

[0022] Furthermore, the "weak feedback" includes the following operations:

[0023] User confirmation of the application's new review logic;

[0024] Users reject the new censorship logic;

[0025] Users can update the review logic according to their actual needs to adapt to contract characteristics, regulatory changes, or business requirements.

[0026] Furthermore, the review logic initialization step includes:

[0027] The system loads predefined review logic designed by legal professionals and algorithm engineers.

[0028] The system intelligently updates the loaded review logic through a large language model and dynamically adjusts it based on business needs, regulatory changes, and user feedback.

[0029] Furthermore, the closed-loop optimization module automatically optimizes based on user feedback, historical data, and machine review results. The optimization process includes:

[0030] The review logic is updated based on user feedback;

[0031] The system is automatically corrected to improve the accuracy of contract review;

[0032] If the accumulated error messages reach a predetermined threshold, the review logic library will be automatically updated to ensure that the review model adapts to the latest business rules and regulatory requirements.

[0033] Furthermore, the error review history retrieval module identifies potential misjudgments in similar review logic contexts and contract contexts based on historical review data, and generates correction suggestions.

[0034] Furthermore, the user feedback information storage module is used to store weak user feedback and generate a quadruple (Pi, Ci, RMi, RHi) based on the feedback for subsequent optimization.

[0035] Furthermore, the feedback information database is used to record and analyze user interaction results, and to perform logical corrections based on the consistency between user and machine feedback, thereby continuously improving the accuracy of the review results.

[0036] This invention also provides a closed-loop optimization system for contract review based on weak user feedback, the system comprising:

[0037] The user input interface is used to receive contract text uploaded by users and provides preprocessing functions for basic contract information.

[0038] The contract parsing module is used to parse contract text, automatically identify contract types and clauses, and match them with the review checklist.

[0039] The review logic initialization module is used to load a predefined review logic library and dynamically optimize the loaded review logic in conjunction with a large language model, allowing users to adjust the logic based on feedback.

[0040] The review model module is used to perform contract review, conduct risk analysis using a large language model, and output preliminary review results;

[0041] The error history retrieval module is used to retrieve historical review errors and generate correction suggestions through a large language model to improve review accuracy.

[0042] The result correction module is used to automatically correct the review results, generate suggestions based on a large language model and make logical adjustments.

[0043] The user feedback storage module is used to store and manage user feedback information and generate four-tuple records for use by the closed-loop optimization module.

[0044] The closed-loop optimization module is used to continuously optimize the review logic by analyzing user feedback and machine review results in real time. If the error information accumulates to a certain threshold, the system will automatically update the review logic.

[0045] Furthermore, the system has a dynamically updated review logic library that supports intelligent updates based on user feedback, ensuring continuous optimization of the review logic.

[0046] Furthermore, the closed-loop optimization module performs automated logical adjustments based on user feedback and historical data to ensure the accuracy and adaptability of the contract review results.

[0047] In summary, the present invention has the following main beneficial effects:

[0048] 1. This invention introduces a user "weak feedback" mechanism, which allows the review logic to be dynamically adjusted according to contract content, business needs, and regulatory changes. Users can update or customize the review logic in real time during the review process, ensuring that the system can quickly adapt to different types and contents of contracts. This avoids system lag and misjudgment. The system is no longer limited to fixed review points, but can flexibly adjust the review list and strategies, enabling the system to quickly respond to changes in contract terms and business needs, and significantly improving the dynamic adaptability of the review.

[0049] 2. This invention establishes a real-time feedback information database that can record and analyze user feedback in a timely manner. It does not only record error logs, but also dynamically updates the review logic through feedback information. Users can provide immediate feedback after each review, and the system can automatically apply this feedback for optimization. By continuously collecting user feedback information, the system can continuously learn and improve, thereby improving the accuracy and efficiency of the review. User feedback becomes an important data source for the system's self-optimization, significantly improving the response speed and application efficiency of the feedback mechanism.

[0050] 3. By introducing a large language model, this invention automatically updates and optimizes the review logic during the system review process, possessing self-learning and adjustment capabilities. The system not only corrects errors based on historical data but also identifies complex clauses in contracts through intelligent models, improving the intelligence level of the review. The introduction of a closed-loop optimization module enables the system to continuously optimize the review logic based on user feedback and historical review results, reducing manual intervention and improving the level of automation and intelligence. This automated optimization mechanism greatly improves the efficiency and accuracy of the review. Attached Figure Description

[0051] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments. Based on the described embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] The following embodiments are used to illustrate the present invention, but should not be used to limit the scope of protection of the present invention. The conditions in the embodiments can be further adjusted according to specific conditions, and simple improvements to the method of the present invention under the premise of the concept of the present invention are all within the scope of protection claimed by the present invention.

[0054] Example 1

[0055] refer to Figure 1 A closed-loop optimization method for contract review based on weak user feedback, the method comprising the following steps:

[0056] S1. Users upload the contract text to be reviewed to the platform through the system interface. The system preprocesses the contract text, generates basic contract information, and provides data support for subsequent review.

[0057] S2. The system parses the uploaded contract text, automatically matches an appropriate review checklist based on the contract type, content, and terms, and generates preliminary review points to ensure the relevance and accuracy of the review.

[0058] S3. The system loads relevant review logic from a predefined review logic library and automatically iterates and optimizes the loaded review logic using a large language model. Users can choose to apply new logic, reject new logic, or update the review logic according to their needs through "weak feedback" based on contract characteristics, industry requirements, or the latest regulations. User feedback information is recorded and used as a basis for system adjustments.

[0059] S4. Based on the confirmed review checklist, the system performs contract review through a large language model, automatically analyzes the contract text, identifies potential risks, and outputs preliminary review results.

[0060] S5. After the review is completed, the system generates preliminary review results and displays them to the user, allowing the user to provide immediate feedback;

[0061] S6. Based on the current review logic context, contract context, and machine review results, the system retrieves historical erroneous review data, analyzes and identifies potential misjudgments or errors in similar situations, and provides reference data for subsequent corrections.

[0062] S7. If similar erroneous data is retrieved, the system generates correction suggestions through the large language model and adjusts the current review logic or review results according to the suggestions. In this step, the system intelligently corrects the erroneous results, improves the accuracy of the review, and avoids repeating errors.

[0063] S8. The corrected review results are displayed to the user, and user feedback is collected. Users can submit "weak feedback" through the interface, such as confirmation, rejection, or suggestions for further modification of the review logic.

[0064] S9. User feedback and review results are stored together in the review result index library, forming a quadruple (Pi, Ci, RMi, RHi) containing the review logic context, contract context, machine review results and user feedback. This data is used for subsequent optimization and closed-loop updates.

[0065] S10. The system analyzes and applies user feedback in real time through the closed-loop optimization module, combines historical feedback data with the analysis of the large language model, and automatically optimizes the review logic. If the error feedback reaches a certain threshold, the closed-loop optimization module triggers the dynamic update of the review logic library, and the system automatically adjusts the review logic and applies it to the next review.

[0066] S11. All feedback information is processed and applied to the review logic, thus completing the review process and proceeding to the next round of review.

[0067] This invention also provides a closed-loop optimization system for contract review based on weak user feedback, the system comprising:

[0068] The user input interface is used to receive contract text uploaded by users and provides preprocessing functions for basic contract information.

[0069] The contract parsing module is used to parse contract text, automatically identify contract types and clauses, and match them with the review checklist.

[0070] The review logic initialization module is used to load a predefined review logic library and dynamically optimize the loaded review logic in conjunction with a large language model, allowing users to adjust the logic based on feedback.

[0071] The review model module is used to perform contract review, conduct risk analysis using a large language model, and output preliminary review results;

[0072] The error history retrieval module is used to retrieve historical review errors and generate correction suggestions through a large language model to improve review accuracy.

[0073] The result correction module is used to automatically correct the review results, generate suggestions based on a large language model and make logical adjustments.

[0074] The user feedback storage module is used to store and manage user feedback information and generate four-tuple records for use by the closed-loop optimization module.

[0075] The closed-loop optimization module is used to continuously optimize the review logic by analyzing user feedback and machine review results in real time. If the error information accumulates to a certain threshold, the system will automatically update the review logic.

[0076] Example 2

[0077] This embodiment describes how to implement a closed-loop optimization method for contract review based on weak user feedback. This method optimizes the contract review process through specific steps and dynamically adjusts the review logic to ensure the accuracy and adaptability of the review results. The steps are as follows:

[0078] Step 1, User uploads contract text: The user uploads the contract text to be reviewed to the platform through the system interface. After receiving the contract, the platform performs preliminary preprocessing on the text and extracts basic information from the contract (such as contract number, signatories, signing date, etc.) to prepare data support for subsequent review.

[0079] Step 2, Contract Parsing and Review Checklist Generation: The system parses the contract text and automatically generates a matching review checklist based on factors such as contract type and clause content. The system identifies key clauses of the contract (such as payment clauses and breach of contract clauses) to provide basic data for subsequent review points.

[0080] Step 3, Loading Review Logic and User Feedback: The system loads relevant review logic from the predefined review logic library. Subsequently, the system performs preliminary optimization of the review logic based on user needs and contract characteristics, combined with the large language model. During this process, users can provide "weak feedback" to the review logic provided by the system, such as confirming, rejecting, or adjusting the review logic. The system will record this feedback and use it as the basis for subsequent optimization.

[0081] Step 4, Contract Review and Preliminary Risk Identification: Based on the review checklist confirmed by the user, the system performs a contract review. The system conducts a comprehensive analysis of the contract text through a large language model, automatically identifies potential legal risks (such as unreasonable clauses, conflicts of laws, etc.), and generates preliminary review results.

[0082] Step 5, User Feedback Collection and Display: After the review is completed, the system displays the preliminary review results to the user. The user can provide feedback on the results, such as confirming that the review is correct, expressing rejection opinions, or suggesting modifications to the review logic. At this time, the user's "weak feedback" will affect the update of the review logic and affect the accuracy of subsequent review results.

[0083] Step 6, Historical Data Retrieval and Misjudgment Analysis: The system analyzes historical review data through the error history retrieval module, identifies potential misjudgments or errors in similar situations, and provides correction suggestions by combining historical data with the current review logic to help improve review accuracy.

[0084] Step 7, Review Result Correction and Feedback Update: Based on historical data and misjudgment analysis results, the system generates correction suggestions and adjusts the current review logic or review results. Users can provide feedback again based on the adjusted review results. All feedback will be recorded and stored for subsequent optimization.

[0085] Step 8, Closed-loop optimization and review logic update: The system analyzes and applies user feedback in real time through the closed-loop optimization module, combines historical feedback data with the analysis of the large language model, and automatically optimizes the review logic. If the error feedback reaches a certain threshold, the system will trigger a dynamic update of the review logic library, and the optimized review logic will be applied to the next review.

[0086] Step 9, Continuous Optimization and the Next Round of Review: After each review is completed, user feedback and review results are stored and used to optimize the logic of the next round of review. Through closed-loop optimization, the system continuously improves the accuracy and efficiency of the review, ensuring that each review can be dynamically adjusted based on user feedback and historical data.

[0087] In summary, this invention provides a closed-loop optimization method and system for contract review based on weak user feedback. It aims to improve the accuracy and efficiency of contract review through an intelligent review process. By automatically parsing contract text, matching review checklists, applying dynamically optimized review logic, and combining a large language model to perform risk analysis on contracts, the system can not only identify potential problems but also continuously adjust the review logic based on weak user feedback, forming a closed-loop optimization. This method can flexibly adjust review rules according to contract characteristics, industry needs, and regulatory changes, thereby providing users with more accurate and personalized review services and continuously improving review effectiveness through the accumulation of feedback.

[0088] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that, unless otherwise defined, the technical or scientific terms used in this invention should be understood in the ordinary sense by those skilled in the art to which this invention pertains, and the terms "comprising" or "including" or similar terms used in this invention mean that the element or object preceding the word covers the element or object listed after the word and its equivalents.

[0089] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A closed-loop optimization method for contract review based on weak user feedback, characterized in that, The method includes the following steps: S1. Users upload the contract text to be reviewed to the platform through the system interface. The system preprocesses the contract text, generates basic contract information, and provides data support for subsequent review. S2. The system parses the uploaded contract text, automatically matches an appropriate review checklist based on the contract type, content, and terms, and generates preliminary review points to ensure the relevance and accuracy of the review. S3. The system loads relevant review logic from a predefined review logic library and automatically iterates and optimizes the loaded review logic using a large language model. Users can choose to apply new logic, reject new logic, or update the review logic according to their needs through "weak feedback" based on contract characteristics, industry requirements, or the latest regulations. The information provided by users is recorded and used as a basis for system adjustments. S4. Based on the review checklist generated in step S2, the system performs contract review through a large language model, automatically analyzes the contract text, identifies potential risks, and outputs preliminary review results. S5. After the review is completed, the system generates preliminary review results and displays them to the user, allowing the user to provide immediate feedback; S6. Based on the current review logic context, contract context, and machine review results, the system retrieves historical erroneous review data, analyzes and identifies potential misjudgments or errors in similar situations, and provides reference data for subsequent corrections. S7. If similar erroneous data is retrieved, the system generates correction suggestions through a large language model and adjusts the current review logic according to the suggestions. In this step, the system intelligently corrects the erroneous results, improves the accuracy of the review, and avoids repeating errors. S8. The corrected review results are displayed to the user, and user feedback is collected. The user submits "weak feedback" through the interface to confirm, reject, or suggest further modifications to the review logic. S9. User feedback and review results are stored together in the review result index library, forming a quadruple Pi, Ci, RMi, RHi containing the review logic context, contract context, machine review results and user feedback. This data is used for subsequent optimization and closed-loop updates. S10. The system analyzes and applies user feedback in real time through the closed-loop optimization module, combines historical feedback data with the analysis of the large language model, and automatically optimizes the review logic. If the error feedback reaches a certain threshold, the closed-loop optimization module triggers the dynamic update of the review logic library, and the system automatically adjusts the review logic and applies it to the next review. S11. All feedback information is processed and applied to the review logic, thus completing the review process and proceeding to the next round of review.

2. The contract review closed-loop optimization method based on weak user feedback as described in claim 1, characterized in that, The "weak feedback" provided by the user in S3 and S8 includes the following operations: User confirmation of the application's new review logic; Users reject the new censorship logic; Users can update the review logic according to their actual needs to adapt to contract characteristics, regulatory changes, or business requirements.

3. The contract review closed-loop optimization method based on weak user feedback as described in claim 1, characterized in that, The closed-loop optimization module automatically optimizes based on user feedback, historical data, and machine review results. The optimization process includes: The review logic is updated based on user feedback; The system is automatically corrected to improve the accuracy of contract review; If the accumulated error messages reach a predetermined threshold, the review logic library will be automatically updated to ensure that the review model adapts to the latest business rules and regulatory requirements.

Images