Contract auditing rule processing method and apparatus, computer device, readable storage medium, and program product

Abstract

The application relates to a contract auditing rule processing method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: in response to the current contract content input into a large model, displaying a contract auditing result on a contract auditing page; the contract auditing result is an auditing result output by the large model after auditing the current input contract content according to the current contract auditing rule; in the case that the score information input into the contract auditing result meets a preset score condition, determining a target result quantity; the target result quantity is the number of target auditing results output by the large model in succession for different contract contents under the current contract auditing rule; the target auditing result is a contract auditing result whose score information meets the preset score condition; in the case that the target result quantity meets a preset quantity, archiving the current contract auditing rule. The method can improve the effectiveness of the contract auditing rule.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for processing contract review rules. Background Technology

[0002] Contracts serve as the legal framework for business cooperation between companies. Review rules are derived from the focus and logic of legal professionals in reviewing certain legal clauses or standard contract clauses on a particular theme. Typically, one review rule corresponds to a theme within the contract. Contract review is an indispensable part of a company's daily operations and has long consumed a significant amount of corporate legal human resources.

[0003] Intelligent contract review, as an emerging functional service, already includes technologies that automate contract review using large-scale models. However, to ensure that large-scale model-based contract review systems can review contracts efficiently and accurately, users still need to manually write contract review rules. This approach lacks clear control standards and methods, resulting in low effectiveness of the contract review rules. Summary of the Invention

[0004] Therefore, it is necessary to provide a contract review rule processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can improve the effectiveness of contract review rules in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a method for processing contract review rules, including:

[0006] In response to the current contract content input to the large model, the contract review result is displayed on the contract review page; the contract review result is the review result output by the large model after reviewing the currently input contract content according to the current contract review rules;

[0007] If the scoring information input to the contract review result meets the preset scoring conditions, the target number of results is determined; the target number of results is the number of target review results continuously output by the large model for different contract contents under the current contract review rules; the target review result is the contract review result whose scoring information meets the preset scoring conditions; wherein, under the current contract review rules, each input of different contract contents corresponds to the same contract review topic.

[0008] If the number of target results meets the preset quantity, the current contract review rules will be archived.

[0009] In one embodiment, the method further includes:

[0010] If the scoring information input for the contract review result does not meet the preset scoring conditions, in response to the review rule editing operation input to the large model, a new current contract review rule is obtained; the new current contract review rule matches the contract review topic.

[0011] The new contract review result is displayed on the contract review page; the new contract review result is the review result output by the large model after reviewing the currently input contract content according to the new current contract review rules;

[0012] Obtain scoring information for the new contract review results until the scoring information input for the contract review results meets the preset scoring conditions.

[0013] In one embodiment, when the scoring information input for the contract review result does not meet the preset scoring conditions, in response to the review rule editing operation input to the large model, obtaining a new current contract review rule includes:

[0014] If the scoring information input for the contract review result does not meet the preset scoring conditions, the contract content input area of ​​the contract review page will be changed from unlocked to locked, and the review rule input area of ​​the contract review page will be changed from locked to unlocked.

[0015] In response to an edit operation on the audit rule input area that is in an unlocked state, the new current contract audit rule is obtained.

[0016] In one embodiment, the step of displaying the contract review result on the contract review page in response to the current contract content input to the large model includes:

[0017] If the currently entered contract content is not the first contract content entered under the current contract review rules, obtain the uploaded content set; the uploaded content set includes contract content entered historically under the current contract review rules;

[0018] Obtain the content similarity between the currently input contract content and each contract content in the uploaded content set;

[0019] If the similarity of all the content meets the preset similarity conditions, then the step of displaying the contract review results on the contract review page is executed.

[0020] In one embodiment, obtaining the content similarity between the currently input contract content and each contract content in the uploaded content set includes:

[0021] The hash function is used to perform hash operations on the currently input contract content and each contract content in the uploaded content set to obtain the hash parameters corresponding to the currently input contract content and each contract content in the uploaded content set.

[0022] Obtain the distance parameter between the currently input contract content and the hash parameters corresponding to each contract content in the uploaded content set;

[0023] The content similarity is determined based on the distance parameter.

[0024] In one embodiment, the method further includes:

[0025] If the scoring information input for the contract review result meets the preset scoring conditions and the number of target results does not meet the preset number, in response to the contract content input operation in the contract content input area of ​​the contract review page, new contract content input to the large model under the current contract review rules is obtained.

[0026] Return to the step of displaying the contract review results on the contract review page until the target number of results meets the preset number.

[0027] Secondly, this application also provides a contract review rule processing device, comprising:

[0028] The display module is used to respond to the contract content currently input into the large model and display the contract review result on the contract review page; the contract review result is the review result output by the large model after reviewing the currently input contract content according to the current contract review rules;

[0029] The determination module is used to determine the target number of results when the scoring information input to the contract review result meets the preset scoring conditions; the target number of results is the number of target review results continuously output by the large model for different contract contents under the current contract review rules; the target review result is the contract review result where the scoring information meets the preset scoring conditions; wherein, under the current contract review rules, each input of different contract contents corresponds to the same contract review topic;

[0030] The archiving module is used to archive the current contract review rules when the number of target results meets a preset number.

[0031] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program that, when executed by the processor, implements the steps of the method described above.

[0032] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the above-described method.

[0033] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the above-described method.

[0034] The aforementioned contract review rule processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product, in response to the contract content currently input into the large model, display the contract review results on the contract review page; the contract review results are the review results output by the large model after reviewing the currently input contract content according to the current contract review rules; if the scoring information input into the contract review results meets the preset scoring conditions, the target number of results is determined; the target number of results is the number of target review results continuously output by the large model for different contract contents under the current contract review rules; the target review results are the contract review results where the scoring information meets the preset scoring conditions; wherein, each input contract content and the current contract review rule correspond to the same contract review topic; if the target number of results meets the preset number, the current contract review rules are archived.

[0035] In this way, by responding to the contract content input by the large model and displaying the review results, and determining the number of consecutive compliant review results based on the scoring information of the review results, the current contract review rules are archived when the number reaches the target. This allows the large model to use the corresponding contract review rules to output review results that meet the user's expectations for different contract clauses under the same contract review topic. This not only effectively improves the compliance of contract review rule writing, but also significantly improves the efficiency and effectiveness of users writing contract review rules for the large model-based contract review system. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a flowchart illustrating a contract review rule processing method in one embodiment;

[0038] Figure 2 This is a schematic diagram of a contract review page in one embodiment;

[0039] Figure 3 This is a flowchart illustrating a contract review rule processing method in another embodiment;

[0040] Figure 4 This is a structural block diagram of a contract review rule processing device in one embodiment;

[0041] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0043] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0044] In one embodiment, such as Figure 1 As shown, a method for processing contract review rules is provided, which can be applied to computer devices. It is understood that the computer device can be a terminal, a server, or a system that includes both a terminal and a server. This embodiment illustrates the application of this method to a computer device, wherein the computer device is equipped with a contract review system that integrates a large model. The method includes the following steps:

[0045] Step S110: In response to the current contract content input into the large model, display the contract review results on the contract review page.

[0046] The contract review result is the result output by the large model after reviewing the current input contract content according to the current contract review rules.

[0047] The contract review page is a user-interactive front-end page associated with the main model. Users can input the contract content to be reviewed and the review rules for that content.

[0048] In practice, contract review rules are derived from the review focus and logic of legal personnel on a certain legal clause or standard contract clause on a certain topic. Usually, a contract review rule corresponds to a topic in the contract (i.e., the contract review topic). Legal personnel need to specify the content they focus on for this contract review topic and the conditions under which they determine that the contract content (contract clauses) under this contract review topic have risks.

[0049] In this application, the contract content input into the large-scale model for review can be professional shipping contracts that require legal risk review, such as voyage charter contracts and heavy cargo transportation contracts. These shipping contracts to be reviewed include professional clauses such as maritime law and international trade terms; or they can be contract content from other fields that require legal risk review. This application does not impose specific restrictions on this.

[0050] In practice, users can enter the contract content that needs to be reviewed for legal risks on the contract review page. The contract content can include contract terms. The large model can respond to the entered contract content, review the entered contract content according to the current contract review rules, and display the contract review results on the contract review page.

[0051] In practical applications, the contract review page also includes a review entry point, such as a review button. After the user enters the contract content to be reviewed, they can click the review button, and the large model will review the currently entered contract content according to the current contract review rules.

[0052] The current contract review rules and the input contract content both correspond to the same contract review topic. The current contract review rules can be user-written contract review rules that require compliance / validity testing.

[0053] Step S120: If the scoring information input for the contract review results meets the preset scoring conditions, determine the target number of results.

[0054] The number of target results refers to the number of target review results continuously output by the large model for different contract contents under the current contract review rules.

[0055] The target review result is the contract review result where the scoring information meets the preset scoring conditions.

[0056] Under the current contract review rules, each different contract content entered corresponds to the same contract review topic.

[0057] In practice, after the contract review page displays the contract review result corresponding to the currently entered contract content, the user can rate the contract review result and enter the rating information. This rating information is used to represent the user's satisfaction with the contract review result output by the large model.

[0058] The computer device can compare the rating information of the contract review result corresponding to the currently input contract content with the preset rating conditions. If the rating information of the contract review result meets the preset rating conditions, such as the rating information of the contract review result indicating that the contract review result score is 85 points, and the preset rating condition is that the contract review result score is greater than 80 points, then it is determined that the rating information of the contract review result meets the preset rating conditions, and the computer device can further determine the target result quantity.

[0059] The target result quantity refers to the number of target review results continuously output by the large model for different contract contents under the current contract review rules; the target review result is the contract review result where the scoring information meets the preset scoring conditions; and under the current contract review rules, each input of different contract contents corresponds to the same contract review topic.

[0060] Step S130: If the number of target results meets the preset number, archive the current contract review rules.

[0061] In practice, the computer equipment can archive the current contract review rules if the number of target results meets the preset quantity.

[0062] Specifically, for the same contract review rule, users can continuously input different contract content under that rule. Each input contract content and the contract review rule used to review it both correspond to the same contract review topic. For each input contract content, the large model will output a corresponding contract review result. Users can input corresponding scoring information for each contract review result output by the large model. Contract review results whose scoring information meets preset scoring conditions can be used as target review results. Only when the large model can continuously output target review results for continuously input different contract content, and the number of target review results meets the preset number, will the contract review rule be archived and subsequently used as a new contract review rule for application by the large model. Under the current contract review rule, if the scoring information of the contract review result corresponding to any input contract content does not meet the preset scoring conditions, the user can modify the current contract review rule. The modified contract review rule will be used as the new current contract review rule for compliance / effectiveness testing again, and the corresponding number of consecutive compliant results (i.e., the number of target results) will be reset to zero.

[0063] For example, the preset quantity can be 5. When a user enters 5 different contract contents A1, A2, A3, A4, and A5 consecutively under the current contract review rule Ra1, and the score information of the contract review results corresponding to A1, A2, A3, A4, and A5 all meet the preset score conditions, then the current contract review rule Ra1 is determined to have passed the test and can be archived.

[0064] In the above contract review rule processing method, the contract review result is displayed on the contract review page in response to the current contract content input to the large model. The contract review result is the review result output by the large model after reviewing the current input contract content according to the current contract review rules. If the scoring information input to the contract review result meets the preset scoring conditions, the target number of results is determined. The target number of results is the number of consecutive target review results output by the large model for different contract contents under the current contract review rules. The target review result is the contract review result where the scoring information meets the preset scoring conditions. Each input contract content and the current contract review rule correspond to the same contract review topic. If the target number of results meets the preset number, the current contract review rule is archived.

[0065] In this way, by responding to the contract content input by the large model and displaying the review results, and determining the number of consecutive compliant review results based on the scoring information of the review results, the current contract review rules are archived when the number reaches the target. This allows the large model to use the corresponding contract review rules to output review results that meet the user's expectations for different contract clauses under the same contract review topic. This not only effectively improves the compliance of contract review rule writing, but also significantly improves the efficiency and effectiveness of users writing contract review rules for the large model-based contract review system.

[0066] In some embodiments, the method further includes: if the scoring information input for the contract review result does not meet the preset scoring conditions, in response to the editing operation of the review rules input to the large model, obtaining a new current contract review rule; the new current contract review rule matches the contract review topic; displaying the new contract review result on the contract review page; the new contract review result is the review result output by the large model after reviewing the currently input contract content according to the new current contract review rule; obtaining the scoring information for the new contract review result until the scoring information input for the contract review result meets the preset scoring conditions.

[0067] In practice, if the scoring information of the contract review result corresponding to the currently input contract content does not meet the preset scoring conditions, the user can edit the current contract review rules. Specifically, the user can input the review rule editing operation into the large model on the contract review page, allowing the large model to obtain the new current contract review rules. The number of consecutive compliant results corresponding to the new current contract review rules is reset to 0. The large model reviews the currently input contract content according to the new current contract review rules and displays the new contract review result on the contract review page for the user to score. Thus, the computer device can obtain the scoring information of the new contract review result. If the scoring information of the new contract review result meets the preset scoring conditions, the process returns to the step of determining the target number of results; if the scoring information of the new contract review result does not meet the preset scoring conditions, the process returns to the step of responding to the review rule editing operation input into the large model and obtaining the new current contract review rules, until the scoring information input into the contract review result meets the preset scoring conditions.

[0068] For example, if the scoring information of the contract review result corresponding to the currently input contract content A1 does not meet the preset scoring conditions, the user can edit the current contract review rule Ra1. The large model then obtains a new current contract review rule Ra2, reviews the currently input contract content A1 according to the new current contract review rule Ra2, outputs a new contract review result corresponding to contract content A1, and obtains the scoring information for the new contract review result. This process continues until the scoring information of the contract review result for contract content A1 meets the preset scoring conditions. Contract review rule Ra2 and contract review rule Ra1 both correspond to the same contract review topic.

[0069] The technical solution of this embodiment, in response to the editing operation of the review rules input to the large model, obtains a new current contract review rule when the scoring information input to the contract review result does not meet the preset scoring conditions; the new current contract review rule matches the contract review topic; the new contract review result is displayed on the contract review page; the new contract review result is the review result output by the large model after reviewing the currently input contract content according to the new current contract review rule; and the scoring information of the new contract review result is obtained until the scoring information input to the contract review result meets the preset scoring conditions.

[0070] Thus, when the scoring information of the contract review results does not meet the preset scoring conditions, the system can obtain new contract review rules that match the review topic by editing the review rules input into the large model. The large model will then re-review the contract based on the new rules and display the corresponding review results. The scoring information will be obtained again in a loop until the results meet the standards. This allows for flexible adjustment and optimization of contract review rules, ensuring that the rules are accurately matched with the corresponding review topics, continuously improving the accuracy and compliance of contract review results, and guaranteeing the adaptability of contract review rules.

[0071] In some embodiments, the contract review page includes a contract content input area and a review rule input area. The contract content input area is for users to input contract content, and the review rule input area is for users to input contract review rules. The contract content input area and the review rule input area are interlocked; that is, when the contract content input area is in an inputtable state (unlocked), the review rule input area is in an input-unable state (locked); conversely, when the contract content input area is in an input-unable state, the review rule input area is in an inputtable state for contract review rules. When a user inputs the current contract review rule in the review rule input area, the review rule input area will change from an unlocked state to a locked state, and the contract content input area will change from a locked state to an unlocked state, allowing the user to input different contract content multiple times.

[0072] In this way, setting the contract content input area and the review rule input area on the contract review page to an interlocked state, with only one of them in an unlocked state where input is allowed and the other in a locked state where input is not allowed, and automatically switching the locked state of the two areas after the user completes the input of the review rules to support multiple inputs of different contract content, can effectively avoid user errors during input operations, standardize the interactive operation process, simplify the user operation logic, and improve the orderliness, convenience and reliability of contract content and review rule input.

[0073] In some embodiments, if the scoring information input for the contract review result does not meet the preset scoring conditions, in response to the editing operation of the review rules input to the large model, a new current contract review rule is obtained, including: if the scoring information input for the contract review result does not meet the preset scoring conditions, changing the contract content input area of ​​the contract review page from an unlocked state to a locked state, and changing the review rule input area of ​​the contract review page from a locked state to an unlocked state; in response to the editing operation of the review rule input area in the unlocked state, a new current contract review rule is obtained.

[0074] In practice, when the scoring information input for the contract review result does not meet the preset scoring conditions, in response to the editing operation of the review rules input to the large model, during the process of obtaining new current contract review rules, the computer device can change the contract content input area of ​​the contract review page from an unlocked state to a locked state, and change the review rule input area of ​​the contract review page from a locked state to an unlocked state. The user can then perform the review rule editing operation in the unlocked review rule input area and input new contract review rules. Thus, the computer device can obtain new current contract review rules in response to the review rule editing operation in the unlocked review rule input area.

[0075] The technical solution of this embodiment involves setting the contract content input area of ​​the contract review page from an unlocked state to a locked state and setting the review rule input area of ​​the contract review page from a locked state to an unlocked state when the scoring information input for the contract review result does not meet the preset scoring conditions; in response to the review rule editing operation in the review rule input area which is in the unlocked state, a new current contract review rule is obtained.

[0076] Thus, when the scoring information of the contract review result does not meet the preset scoring conditions, by setting the contract content input area on the contract review page to a locked state and the review rule input area to an unlocked state, the new current contract review rules are obtained only by responding to the editing operation of the review rule input area. This can effectively prevent users from accidentally modifying the contract content, accurately guide users to focus on editing and adjusting the review rules, simplify the interactive operation logic, and improve the pertinence and ease of operation of the review rule adjustment.

[0077] In some embodiments, to prevent the repeated uploading of the same contract content, contract content similarity detection is required. Specifically, in response to the contract content currently input to the large model, the contract review result is displayed on the contract review page, including: if the currently input contract content is not the first contract content input under the current contract review rules, obtaining the uploaded content set; the uploaded content set includes contract content input historically under the current contract review rules; obtaining the content similarity between the currently input contract content and each contract content in the uploaded content set; and if each content similarity meets the preset similarity conditions, executing the step of displaying the contract review result on the contract review page.

[0078] In practice, when the computer device responds to the contract content currently input into the large model and displays the contract review results on the contract review page, it can obtain the uploaded content set if the currently input contract content is not the first contract content entered under the current contract review rules. The uploaded content set includes contract content input in the past under the current contract review rules. It can also obtain the content similarity between the currently input contract content and each contract content in the uploaded content set. If the content similarity of each content meets the preset similarity conditions, it can execute the step of displaying the contract review results on the contract review page.

[0079] For example, after obtaining the currently entered contract content A3, if this content is not the first contract entered under the current contract review rule Ra1 (e.g., the user has previously entered contract content A1 and A2 under Ra1 for review), the computer device can obtain the uploaded content set. This uploaded content set includes previously entered contract content A1 and A2 under Ra1. The computer device calculates the content similarity between contract content A3 and contract content A1 and A2. If the content similarity between contract content A3 and contract content A1 and A2 both meet the preset similarity conditions, the step of displaying the contract review results on the contract review page is executed.

[0080] Among them, if the content similarity between two contracts meets the preset similarity condition, it indicates that the content of the two contracts is not similar.

[0081] The technical solution of this embodiment involves obtaining an uploaded content set when the currently input contract content is not the first contract content entered under the current contract review rules; the uploaded content set includes contract content entered historically under the current contract review rules; obtaining the content similarity between the currently input contract content and each contract content in the uploaded content set; and, if each content similarity meets the preset similarity conditions, executing the step of displaying the contract review results on the contract review page.

[0082] In this way, by performing similarity detection on newly input contract content under the current contract review rules and comparing it with previously uploaded contract content one by one, the newly input contract content is only reviewed when the similarity of each content meets the preset similarity conditions, and the corresponding contract review results are displayed. This can effectively avoid the repeated uploading and review of the same or highly similar contract content, reduce redundant system operations, and improve the processing efficiency of contract review and the utilization rate of system resources.

[0083] In some embodiments, obtaining the content similarity between the currently input contract content and each contract content in the uploaded content set includes: performing hash operations on the currently input contract content and each contract content in the uploaded content set respectively using a preset hash function to obtain the hash parameters corresponding to the currently input contract content and each contract content in the uploaded content set respectively; obtaining the distance parameter between the hash parameters corresponding to the currently input contract content and each contract content in the uploaded content set respectively; and determining the content similarity based on the distance parameter.

[0084] In practice, when the computer device obtains the content similarity between the currently input contract content and each contract content in the uploaded content set, it can perform hash operations on the currently input contract content and each contract content in the uploaded content set using a preset hash function to obtain the hash parameters corresponding to the currently input contract content and each contract content in the uploaded content set. Then, it obtains the distance parameter between the hash parameters corresponding to the currently input contract content and each contract content in the uploaded content set; and determines the content similarity between the currently input contract content and each contract content in the uploaded content set based on the distance parameter.

[0085] The hash parameters corresponding to each contract in the uploaded content set can be pre-calculated and stored. Once the hash parameters corresponding to the currently input contract content are calculated, the hash parameters corresponding to each contract in the uploaded content set are directly called to calculate the distance parameter between the currently input contract content and the hash parameters corresponding to each contract in the uploaded content set.

[0086] In some embodiments, the distance parameter can be Hamming distance, which is negatively correlated with content similarity. If the Hamming distance between the currently input contract content and the contract content in the uploaded content set is greater than a preset distance threshold, the content similarity between the two is determined to meet the preset similarity condition; otherwise, the content similarity between the two is determined not to meet the preset similarity condition.

[0087] The technical solution of this embodiment uses a preset hash function to perform hash operations on the currently input contract content and each contract content in the uploaded content set to obtain the hash parameters corresponding to the currently input contract content and each contract content in the uploaded content set; obtains the distance parameters between the hash parameters corresponding to the currently input contract content and each contract content in the uploaded content set; and determines the content similarity based on the distance parameters.

[0088] In this way, by performing hash operations on the currently input contract content and the historical contract content in the uploaded content set using a preset hash function to obtain the corresponding hash parameters, and determining the content similarity based on the distance parameter between the hash parameters, contract content similarity comparison can be quickly achieved with low computational overhead, greatly improving the efficiency and accuracy of contract content duplication detection, and ensuring the efficient and reliable operation of the duplicate upload detection process.

[0089] In some embodiments, the method further includes: when the scoring information input for the contract review result meets the preset scoring conditions and the number of target results does not meet the preset number, in response to the contract content input operation in the contract content input area of ​​the contract review page, obtaining new contract content input for the large model under the current contract review rules; returning to the step of displaying the contract review result on the contract review page until the number of target results meets the preset number.

[0090] In specific implementation, the method further includes: if the scoring information of the contract review result corresponding to the currently input contract content meets the preset scoring conditions, and the target number of results does not meet the preset number, the user can input new contract content again under the current contract review rules. Correspondingly, the large model can respond to the contract content input operation in the contract content input area of ​​the contract review page, obtain the new contract content input to the large model under the current contract review rules, review the new contract content according to the current contract review rules, and return to the step of displaying the contract review result on the contract review page, until the target number of results meets the preset number.

[0091] In some embodiments, after obtaining new contract content, content similarity detection is still required: the computer device can perform the steps of obtaining the uploaded content set, obtaining the content similarity between the currently input contract content and each contract content in the uploaded content set, and determining whether the content similarity meets the preset similarity conditions. Only if the conditions are met will the new contract content be reviewed. That is, for contract content that is not entered for the first time under the same contract review rules, content similarity detection is required.

[0092] For example, the preset quantity can be 5. If the current contract content entered by the user under the current contract review rule Ra1 is A3, and the large model outputs the contract review result for contract content A3, and the user's rating information for the contract review result corresponding to contract content A3 meets the preset rating conditions, and the rating information for the contract review results corresponding to the contract content A1 and A2 entered by the user under the current contract review rule Ra1 also meets the preset rating conditions, then the target result quantity is 3. Since the preset quantity is not met, the user can enter a new contract content A4 under the current contract review rule Ra1 to continue to conduct compliance / validity testing on the current contract review rule Ra1.

[0093] The technical solution of this embodiment, when the scoring information input for the contract review result meets the preset scoring conditions but the target number of results does not meet the preset number, responds to the contract content input operation in the contract content input area of ​​the contract review page, obtains new contract content input for the large model under the current contract review rules, and returns to the step of displaying the contract review result on the contract review page until the target number of results meets the preset number. Thus, when the scoring information of the contract review result meets the preset scoring conditions but the target number of results has not reached the preset number, new contract content can continue to be input under the current contract review rules, and the review result display step can be executed repeatedly until the target number of results meets the requirement. This allows for continuous verification of the current contract review rules using multiple different contract samples, ensuring that the rule has a stable and reliable review effect under the same contract review topic, further improving the sufficiency and rigor of the contract review rule verification.

[0094] In some embodiments, for the convenience of those skilled in the art, such as Figure 2 The image shows a schematic diagram of a contract review page 200. Figure 2 As shown, the contract review page 200 includes a contract content input area 210, a review rule input area 220, a review result display area 230, and a scoring information input area 240. The contract content input area 210 and the review rule input area 220 are interlocked. Figure 3 As shown, a flowchart illustrating another method for processing contract review rules is presented. Assuming a user wants to write contract review rules for contract review topic A, the overall process includes three stages: the rule writing stage, the rule testing stage, and the online approval and application stage.

[0095] During the rule drafting phase, the contract content input area 210 is first unlocked, and the rule input area 220 is locked. Users can input the contract clause A1 to be reviewed in the unlocked contract content input area 210. Then, the contract content input area 210 is unlocked and the rule input area 220 is unlocked. Users can then input the contract review rule to be tested in the unlocked rule input area 220, which will serve as the current contract review rule. Furthermore, the contract review system provides review rule templates for users to refer to when inputting the contract review rule to be tested. The large model can review contract clause A1 according to the input current contract review rule, and display the contract review result for contract clause A1 in the review result display area 230. Users can input a rating for the contract review result in the rating information input area 240 based on their satisfaction with the review result. If the user is dissatisfied with the contract review result, i.e., the contract review result score is lower than the preset score threshold, the contract content input area 210 is changed from unlocked to locked, and the review rule input area 220 is changed from locked to unlocked. The user can then perform review rule editing operations in the unlocked review rule input area 220, entering new current contract review rules. The large model reviews contract clause A1 according to the new current contract review rules, and displays the new contract review result in the review result display area 230. The user can rate the new contract review result again until the user is satisfied with the contract review result of contract clause A1. When the user is satisfied with the contract review result of contract clause A1, i.e., when the score information of the contract review result of contract clause A1 meets the preset scoring conditions, the corresponding current contract review rule is Ra1.

[0096] The next step is the rule testing phase: The current contract review rule Ra1 is locked (i.e., review rule input area 220 is locked, and contract content input area 210 is unlocked). Ra1 is used to review other contract clauses under review topic A (such as the same clause in another contract, or another clause under the same topic in the same contract) A2, A3, A4… and so on. The contract review results are then scored. To prevent duplicate uploads of the same contract content, clause content similarity detection is performed, specifically as follows: After locking the contract review rule, the hash value of each input clause is calculated and stored. When a user inputs a new contract clause, the system calculates the hash value of that clause and the Hamming distance between the hash values ​​of that clause and all previously uploaded contract clauses to determine content similarity. If the Hamming distance between the current input and the hash values ​​of all historically input contract clauses is greater than a set threshold, then the currently input contract clause is considered to have passed the content similarity detection and can be reviewed.

[0097] The user scores the contract review results of Ra1 - A2, A3, and A4. When the scores of consecutive N (preset quantity) contract review results are all >= Y (the preset score threshold included in the preset scoring condition), then the current contract review rule passes the test for Ra1 and can be archived (at this time, the rule archiving button is unlocked and the user can complete the archiving by clicking). If the review result of a certain contract is not satisfactory halfway (score < Y), then the user needs to unlock the review rule input area 220 to adjust the current contract review rule. At this time, the number of test attempts will be reset to zero, and the user needs to retest the new current contract review rule.

[0098] Online approval application stage of the review rule: Experts in the legal department regularly review the archived contract review rules and submit them to the leadership of the legal department for approval. The approved contract review rules automatically flow into the contract review application and are applied as new contract review rules.

[0099] In this way, for different contract clauses under the same contract review theme, the large - model can adopt the corresponding contract review rules to output review results that meet user expectations. This can not only effectively improve the compliance of writing contract review rules but also significantly enhance the efficiency and effectiveness of users in writing contract review rules for the contract review system based on the large - model.

[0100] It should be understood that although the steps in the flowcharts involved in the above - mentioned embodiments are displayed in sequence according to the arrows, these steps do not necessarily need to be executed in the order indicated by the arrows. Unless there is a clear statement in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above - mentioned embodiments may include multiple steps or multiple stages. These steps or stages do not necessarily need to be executed at the same moment but can be executed at different moments. The execution order of these steps or stages does not necessarily need to be sequential, but can be executed alternately or in rotation with at least a part of other steps or steps or stages in other steps. It can be understood that the steps in different embodiments can be freely combined as needed, and all non - contradictory combinations formed belong to the scope protected by this application.

[0101] Based on the same inventive concept, the embodiments of the present application also provide a contract review rule processing device for implementing the contract review rule processing method involved above. The implementation solutions provided by this device to solve problems are similar to the implementation solutions recorded in the above - mentioned method. Therefore, the specific limitations in one or more embodiments of the contract review rule processing device provided below can refer to the limitations on the contract review rule processing method in the above text and will not be repeated here.

[0102] In one exemplary embodiment, such as Figure 4 As shown, a contract review rule processing device is provided, including: a display module 410, a determination module 420, and an archiving module 430, wherein:

[0103] The display module 410 is used to display the contract review result on the contract review page in response to the contract content currently input to the large model; the contract review result is the review result output by the large model after reviewing the currently input contract content according to the current contract review rules.

[0104] The determination module 420 is used to determine the number of target results when the scoring information input to the contract review result meets the preset scoring conditions; the number of target results is the number of target review results continuously output by the large model for different contract contents under the current contract review rules; the target review result is the contract review result where the scoring information meets the preset scoring conditions; wherein, under the current contract review rules, each input of different contract contents corresponds to the same contract review topic.

[0105] The archiving module 430 is used to archive the current contract review rules when the number of target results meets the preset number.

[0106] In one embodiment, the device further includes: an editing module, configured to, in response to an editing operation on the large model, obtain a new current contract review rule when the scoring information input for the contract review result does not meet the preset scoring conditions; the new current contract review rule matches the contract review topic; display the new contract review result on the contract review page; the new contract review result is the review result output by the large model after reviewing the currently input contract content according to the new current contract review rule; and obtain scoring information for the new contract review result until the scoring information input for the contract review result meets the preset scoring conditions.

[0107] In one embodiment, the editing module is specifically configured to, when the scoring information input for the contract review result does not meet the preset scoring conditions, set the contract content input area of ​​the contract review page from an unlocked state to a locked state, and set the review rule input area of ​​the contract review page from a locked state to an unlocked state; in response to the review rule editing operation on the review rule input area which is in the unlocked state, obtain the new current contract review rule.

[0108] In one embodiment, the display module 410 is specifically configured to: obtain an uploaded content set when the currently input contract content is not the first contract content entered under the current contract review rules; the uploaded content set includes contract content entered historically under the current contract review rules; obtain the content similarity between the currently input contract content and each contract content in the uploaded content set; and, if all the content similarities meet preset similarity conditions, execute the step of displaying the contract review results on the contract review page.

[0109] In one embodiment, the display module 410 is specifically used to perform hash operations on the currently input contract content and each contract content in the uploaded content set using a preset hash function to obtain hash parameters corresponding to the currently input contract content and each contract content in the uploaded content set; obtain distance parameters between the hash parameters corresponding to the currently input contract content and each contract content in the uploaded content set; and determine the content similarity based on the distance parameters.

[0110] In one embodiment, the determining module 420 is further configured to, in response to a contract content input operation in the contract content input area of ​​the contract review page, obtain new contract content input to the large model under the current contract review rules, and return to the step of displaying the contract review results on the contract review page until the number of target results meets the preset number, when the scoring information input for the contract review results meets the preset scoring conditions and the number of target results does not meet the preset number.

[0111] Each module in the aforementioned contract review rule processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0112] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a contract review rule processing method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0113] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0114] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0115] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0116] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0117] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0118] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0119] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0120] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for processing contract review rules, characterized in that, The method includes: In response to the current contract content input to the large model, the contract review result is displayed on the contract review page; the contract review result is the review result output by the large model after reviewing the currently input contract content according to the current contract review rules; If the scoring information input to the contract review result meets the preset scoring conditions, the target number of results is determined; the target number of results is the number of target review results continuously output by the large model for different contract contents under the current contract review rules; the target review result is the contract review result whose scoring information meets the preset scoring conditions; wherein, under the current contract review rules, each input of different contract contents corresponds to the same contract review topic. If the number of target results meets the preset quantity, the current contract review rules will be archived.

2. The method according to claim 1, characterized in that, The method further includes: If the scoring information input for the contract review result does not meet the preset scoring conditions, in response to the review rule editing operation input to the large model, a new current contract review rule is obtained; the new current contract review rule matches the contract review topic. The new contract review result is displayed on the contract review page; the new contract review result is the review result output by the large model after reviewing the currently input contract content according to the new current contract review rules; Obtain scoring information for the new contract review results until the scoring information input for the contract review results meets the preset scoring conditions.

3. The method according to claim 2, characterized in that, When the scoring information input for the contract review result does not meet the preset scoring conditions, in response to the review rule editing operation input to the large model, a new current contract review rule is obtained, including: If the scoring information input for the contract review result does not meet the preset scoring conditions, the contract content input area of ​​the contract review page will be changed from unlocked to locked, and the review rule input area of ​​the contract review page will be changed from locked to unlocked. In response to an edit operation on the audit rule input area that is in an unlocked state, the new current contract audit rule is obtained.

4. The method according to claim 1, characterized in that, The response to the current contract content input to the large model displays the contract review results on the contract review page, including: If the currently entered contract content is not the first contract content entered under the current contract review rules, obtain the uploaded content set; the uploaded content set includes contract content entered historically under the current contract review rules; Obtain the content similarity between the currently input contract content and each contract content in the uploaded content set; If the similarity of all the content meets the preset similarity conditions, then the step of displaying the contract review results on the contract review page is executed.

5. The method according to claim 4, characterized in that, The step of obtaining the content similarity between the currently input contract content and each contract content in the uploaded content set includes: The hash function is used to perform hash operations on the currently input contract content and each contract content in the uploaded content set to obtain the hash parameters corresponding to the currently input contract content and each contract content in the uploaded content set. Obtain the distance parameter between the currently input contract content and the hash parameters corresponding to each contract content in the uploaded content set; The content similarity is determined based on the distance parameter.

6. The method according to claim 1, characterized in that, The method further includes: If the scoring information input for the contract review result meets the preset scoring conditions and the number of target results does not meet the preset number, in response to the contract content input operation in the contract content input area of ​​the contract review page, new contract content input to the large model under the current contract review rules is obtained. Return to the step of displaying the contract review results on the contract review page until the target number of results meets the preset number.

7. A contract review rule processing device, characterized in that, The device includes: The display module is used to respond to the contract content currently input into the large model and display the contract review result on the contract review page; the contract review result is the review result output by the large model after reviewing the currently input contract content according to the current contract review rules; The determination module is used to determine the target number of results when the scoring information input to the contract review result meets the preset scoring conditions; the target number of results is the number of target review results continuously output by the large model for different contract contents under the current contract review rules; the target review result is the contract review result where the scoring information meets the preset scoring conditions; wherein, under the current contract review rules, each input of different contract contents corresponds to the same contract review topic; The archiving module is used to archive the current contract review rules when the number of target results meets a preset number.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images