Contract template data processing method and device and computer equipment

Through online editing and multi-dimensional verification mechanisms, the problem of low data processing efficiency of electronic contract templates is solved, real-time changes and risk identification of contract templates are realized, and the accuracy and quality of contract content are improved.

CN119047450APending Publication Date: 2024-11-29CHINA CONSTRUCTION BANK +1
View PDF 0 Cites 3 Cited by

Patent Information

Application Number
CN202411193747.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-28
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

The data processing efficiency of existing electronic contract templates is low, and it is difficult for non-professional developers to ensure the accuracy of content editing contract templates, and it is difficult to take effect in real time, resulting in inefficient processing of contract content.

Method used

Provide a contract template data processing method, modify the contract template data through online editing requests, and call the trained contract approval model for multi-dimensional verification, including clause consistency, logical errors and syntax error verification, identify risk items, and Push risk warning messages.

Benefits of technology

Real-time changes in contract templates and shared editing by multiple people are realized, the accuracy and standardization of the contract content is improved, the possibility of errors is reduced, and potential risks are timely identified and avoided, which significantly improves the quality and processing efficiency of the contract.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119047450A_ABST
    Figure CN119047450A_ABST
Patent Text Reader

Abstract

The invention relates to the field of big data cloud, and particularly discloses a contract template data processing method and device, and computer equipment. The method comprises the following steps: in response to an online editing request carrying a contract template identifier sent by at least one contract template editing device, modifying first contract template data corresponding to the contract template identifier to obtain second contract template data, and synchronizing the second contract template data to the contract template editing device, calling a trained contract approval model to carry out at least two kinds of verification of clause consistency verification, logic error verification and grammar error verification on the second contract template data, under the condition that the second contract template data passes multi-dimensional verification, if it is identified that a risk item exists in the second contract template data, marking the risk item, and if it is identified that the risk item exists in the second contract template data, marking the risk item; and pushing a risk early warning message. By adopting the scheme, the processing efficiency of the contract template data can be effectively improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of big data cloud technology, and in particular to a contract template data processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] With the development of information technology, electronic contracts have been given the same legal effect as paper contracts, and paperless electronic contracts have gradually become a development trend of contracts. Therefore, it is particularly important to provide a solution for generating electronic contracts that can be flexibly edited and easy to manage.

[0003] At present, most electronic contracts are generated by developers pre-configuring contract templates, and then publishing the configured contract templates to the production deployment data package in the production environment. When it is necessary to generate an electronic contract, the corresponding contract template is directly taken from the production package, and then, based on template engines such as FreeMarker, the contract template is bound to customized information using the template engine to generate an electronic contract.

[0004] However, in the above solution, the contract template is edited by non-professional developers, and it is difficult to ensure the accuracy of the contract content. If the contract template data is modified, it is difficult for the contract template data to take effect in real time. It can be seen that the current electronic contract template data has the problem of low processing efficiency. Summary of the invention

[0005] Based on this, it is necessary to provide an efficient contract template data processing method, device, computer equipment, computer-readable storage medium and computer program product to address the above technical problems.

[0006] In a first aspect, the present application provides a method for processing contract template data, comprising:

[0007] In response to an online editing request carrying a contract template identifier sent by at least one contract template editing device, based on the contract editing data carried in the online editing request, modify the first contract template data corresponding to the contract template identifier to obtain second contract template data, and synchronize the second contract template data to the contract template editing device;

[0008] extracting contract feature data from the second contract template data, taking the contract feature data as input, calling a trained contract approval model to perform multi-dimensional verification on the second contract template data, wherein the multi-dimensional verification includes at least two of clause consistency verification, logic error verification, and syntax error verification, wherein the contract approval model is obtained by training a machine learning model using a standard contract sample;

[0009] If the second contract template data passes the multi-dimensional verification, extracting risk feature data in the second contract template data, and identifying whether the second contract template data has risk items based on the risk feature data;

[0010] If there are risk items in the second contract template data, the risk items are marked and a risk warning message is pushed.

[0011] In an exemplary embodiment, after pushing the risk warning message, the method further includes:

[0012] Receive a contract generation request sent by a business terminal;

[0013] Parsing the contract generation request, extracting business requirement data in the contract generation request, and determining a business scenario;

[0014] Filtering out a target contract template that matches the business requirement data and the business scenario from a plurality of pre-configured contract template data;

[0015] The business requirement data is filled into the target contract template, an electronic contract is generated, and the electronic contract is sent to the business terminal.

[0016] In an exemplary embodiment, the step of selecting a target contract template that matches the business requirement data and the business scenario from a plurality of pre-configured contract template data includes:

[0017] Extracting the first characteristic data in the contract template data and the second characteristic data in the business requirement data;

[0018] determining a matching score between the first feature data and the second feature data;

[0019] The contract template data with the highest matching score is used to determine the target contract template.

[0020] In an exemplary embodiment, performing clause consistency check on the second contract template data includes:

[0021] Extracting contract terms from contract feature data;

[0022] Filter out target contract terms that match the contract terms from a preset standard contract terms database;

[0023] Determine the semantic similarity between the contract terms and the target contract terms;

[0024] Based on the semantic similarity, it is determined whether there are any contract clauses in the second contract template data that do not match the standard contract clauses.

[0025] In an exemplary embodiment, the performing logic error checking on the second contract template data includes at least one of the following methods:

[0026] First, verify the consistency and rationality of the logical relationship between the contract terms in the contract feature data;

[0027] The second is to verify the consistency and rationality of the values ​​and dates in the contract characteristic data;

[0028] The third method is to verify whether the execution dependency of the contract terms in the contract feature data is correct.

[0029] In an exemplary embodiment, the step of identifying whether the second contract template data has a risk item based on the risk characteristic data includes:

[0030] Determine the risk category and risk impact level of the risk characteristic data;

[0031] Determining the risk level of the risk characteristic data based on the risk category and the risk impact degree;

[0032] The risk characteristic data with a risk level higher than a preset risk level is determined as a risk item.

[0033] In a second aspect, the present application also provides a contract template data processing device, including:

[0034] a data modification module, configured to respond to an online editing request carrying a contract template identifier sent by at least one contract template editing device, modify first contract template data corresponding to the contract template identifier based on the contract editing data carried in the online editing request, obtain second contract template data, and synchronize the second contract template data to the contract template editing device;

[0035] a data verification module, configured to extract contract feature data from the second contract template data, use the contract feature data as input, and call a trained contract approval model to perform multi-dimensional verification on the second contract template data, wherein the multi-dimensional verification includes at least two of clause consistency verification, logic error verification, and grammatical error verification, and the contract approval model is obtained by training a machine learning model using a standard contract sample;

[0036] a data prediction module, configured to extract risk feature data from the second contract template data when the second contract template data passes the multi-dimensional verification, and identify whether the second contract template data has risk items based on the risk feature data;

[0037] The data push module is used to mark the risk items and push risk warning messages if there are risk items in the second contract template data.

[0038] In a third aspect, the present application further provides a computer device including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in any one of the above-mentioned contract template data processing method embodiments when executing the computer program.

[0039] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in any one of the above-mentioned contract template data processing method embodiments.

[0040] In a fifth aspect, the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps in any one of the above-mentioned contract template data processing method embodiments.

[0041] The above-mentioned contract template data processing method, device, computer equipment, computer-readable storage medium and computer program product respond to an online editing request carrying a contract template identifier sent by at least one contract template editing device, and based on the contract editing data carried in the online editing request, modify the first contract template data corresponding to the contract template identifier in real time to obtain the second contract template data, and synchronize the second contract template data to the contract template editing device. In this way, multiple people can share and edit electronic contract template data, and can realize real-time changes to contract templates, saving the cumbersome operations of traditional offline modifications. In addition, by calling the trained contract approval model, the second contract template data can be intelligently, efficiently and accurately modified. Multi-dimensional verification, including at least two of the clause consistency verification, logical error verification and grammatical error verification, can improve the consistency and standardization of the contract template, reduce the possibility of errors in the contract content, and improve the quality and accuracy of the contract template content. Finally, when the second contract template data passes the multi-dimensional verification, the risk feature data in the second contract template data is extracted, and the risk prediction of the second contract template data is performed, which can identify potential risks in advance, which is conducive to timely avoidance of risks. When the risk items are identified, by marking the identified risk items and pushing risk warning messages, the relevant personnel can understand the potential risks in advance and solve the potential risks in time, thereby improving the quality of the contract. In summary, the above scheme efficiently realizes the real-time change of the contract template data through online shared editing of the contract template, and performs multi-dimensional verification on the modified contract template data through an automatic and intelligent multi-dimensional verification mechanism, thereby improving the consistency, logical correctness and grammatical standardization of the contract clauses, reducing the possibility of errors in the contract template content, and identifying the risk items of the contract template data. It can timely discover potential risk items and avoid risks in time, significantly improving the quality and accuracy of the contract, and reducing the number of repeated modifications of the contract template data. Therefore, the adoption of this scheme can effectively improve the processing efficiency of the contract template data. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0043] FIG1 is an application environment diagram of a method for processing contract template data in one embodiment;

[0044] Figure 2 A flowchart of a method for processing contract template data in one embodiment;

[0045] Figure 3 A schematic diagram of a flow chart of a method for processing contract template data in another embodiment;

[0046] Figure 4 A schematic diagram of a flow chart of a contract generation step in an embodiment;

[0047] Figure 5 A flowchart of a contract generation step in another embodiment;

[0048] Figure 6 A flowchart of a method for processing contract template data in one embodiment;

[0049] Figure 7 A schematic diagram of a flow chart of a method for processing contract template data in another embodiment;

[0050] Figure 8 is a structural block diagram of a contract template data processing device in an embodiment;

[0051] Fig. 9 It is a structural block diagram of a contract template data processing device in another embodiment;

[0052] FIG. 10 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. It should be noted that in the embodiments of the present application, certain software, groups, models and other existing solutions in the industry may be mentioned, which should be considered as exemplary, and their purpose is only to illustrate the feasibility of the implementation of the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0054] It should be noted that the user information (including but not limited to user device information such as contract template editing equipment, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, 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 relevant data must comply with relevant regulations. The acquisition, storage, use, and processing of data in the technical solution of this application are in compliance with relevant provisions of national laws and regulations.

[0055] The contract template data processing method provided in the embodiment of the present application can be applied in the application environment shown in FIG1 . In which, multiple contract template editing devices 102 communicate with the contract server 104 through a network. The data storage system can store the data that the contract server 104 needs to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers.

[0056] Specifically, multiple business personnel may respectively edit and maintain the contract template data online through different contract template editing devices 102, and the edited contract template data may be uploaded to the cloud in real time. If the business personnel edit the contract template data through the contract template editing device 102, at this time, the contract template editing device 102 will send an online editing request carrying the contract template identifier to the contract server 104. In response to the online editing request carrying the contract template identifier sent by at least one contract template editing device 102, the contract server 104 modifies the first contract template data corresponding to the contract template identifier to obtain the second contract template data, and uploads the second contract template data to the cloud, and the cloud synchronizes the second contract template data to the contract template editing device. Then, the contract server 104 performs multi-dimensional verification on the second contract template data, including at least two of the clause consistency verification, logical error verification, and grammatical error verification, so as to improve the consistency and standardization of the contract template. If the second contract template data passes the multi-dimensional verification, the second contract template data is further risk predicted, the identified risk items are marked, and a risk warning message is pushed so that relevant personnel can solve the potential risks in a timely manner.

[0057] The contract template editing device 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted devices may be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The contract server 104 may be an independent physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0058] In an exemplary embodiment, Figure 2 As shown, a contract template data processing method is provided, which is described by taking the method applied to the contract server 104 (hereinafter referred to as the server) in FIG. 1 as an example, and includes the following S200 to S800. Among them:

[0059] S200, in response to an online editing request carrying a contract template identifier sent by at least one contract template editing device, based on the contract editing data carried in the online editing request, modify the first contract template data corresponding to the contract template identifier, obtain second contract template data, and synchronize the second contract template data to the contract template editing device.

[0060] Contract template identification refers to data used to uniquely identify and distinguish different contract template data, including but not limited to template name, template code or template number, etc. Contract edit data includes new edits by users or modifications to existing data, including data modification, data insertion and deletion in general formats.

[0061] In order to improve the efficiency and accuracy of contract processing, developers can design and build a cloud-based contract management system that integrates functions such as online editing, version control, multi-dimensional verification and risk prediction to achieve flexible contract management.

[0062] In actual applications, business personnel can log in to the contract management system through a contract template editing device, select the contract template that needs to be edited and modified, and modify the contract template to be modified through the contract template editing interface. At this time, the contract template contract editing data is uploaded to the cloud for storage in real time, and the cloud also synchronizes the changed content to other contract template editing devices. After the business personnel completes the modification, they submit the editing request to the server online through the contract template editing device. It is understandable that since this system supports online contract editing and sharing, multiple business personnel can simultaneously edit and maintain the same contract template online, that is, the server can receive online editing requests sent by at least one contract editing terminal. The online editing request includes the contract template ID (Identity) and the specific changes for preview or direct editing.

[0063] After receiving the editing request, the server determines the first contract template data corresponding to the contract template identifier requested to be edited by the business personnel, and then verifies the legitimacy of the request, including checking whether the user authority of the user sending the request allows editing of the specified template, whether the current state of the template is open for editing, etc. In addition, to prevent data inconsistency caused by concurrent editing, the server can back up the current first contract template data in real time so that it can be restored to its original state when necessary or used for subsequent version comparison. After verifying that the user sending the request has the authority to edit the first contract template data, the server makes corresponding modifications to the first contract template data according to the contract editing data in the online editing request, including adding, deleting or modifying elements such as terms, conditions, and values ​​in the contract template. During the modification process, the server ensures that the structure and format of the contract content remain consistent. After the modification is completed, the server creates a new version record, namely the second contract template data. At the same time, the server synchronizes the second contract template data to the cloud in real time, and the cloud synchronizes the second contract template data to other contract template editing devices. It can be understood that the second contract template data can also be synchronized to other contract template editing devices by the server.

[0064] S400, extracting the contract feature data from the second contract template data, taking the contract feature data as input, calling the trained contract approval model to perform multi-dimensional verification on the second contract template data, the multi-dimensional verification including at least two of clause consistency verification, logic error verification and syntax error verification, the contract approval model is obtained by training a machine learning model using standard contract samples.

[0065] The contract feature data includes structural features (such as clause distribution, chapter division), text features (keyword frequency, semantic similarity) and logical features. In this embodiment, the contract approval model (hereinafter referred to as the model) can be obtained by training the machine learning model with standard contract samples covering different industries and different types. The standard contract samples include correct positive samples and incorrect negative samples. Specifically, the training process of the model can be: obtaining a large number of standard contract template samples, cleaning the text, including removing irrelevant characters, converting to a unified format, standardizing terms, etc. The contract samples are annotated, including labels such as clause consistency, logical errors, and grammatical errors, for supervised learning. Then, the contract feature data in the standard contract samples are extracted, including structural features (such as clause distribution, chapter division), text features (keyword frequency, semantic similarity), and logical features (conditional dependence, time series rationality), and the extracted contract feature data is divided into a training set, a validation set, and a test set.

[0066] Subsequently, select a suitable machine learning model, such as logistic regression, random forest, support vector machine or deep learning model such as LSTM (Long Short-Term Memory), to build the initial contract approval model. Next, input the labeled training set into the initial contract approval model for model training, and optimize the model weights through back propagation or gradient descent until the accuracy of the model meets the preset accuracy requirements. Then, evaluate the performance of the contract approval model on the test set through indicators such as accuracy, recall rate, and F1 score. Adjust the model parameters or try different model architectures based on the evaluation results until satisfactory performance indicators are achieved, and obtain the trained contract approval model.

[0067] In specific implementation, the server modifies the first contract template data based on the contract editing data in the online editing request, obtains the second contract template data, and automatically triggers the review process. Specifically, the feature data in the second contract template data can be extracted and input into the contract approval model, and the contract approval model performs multi-dimensional verification on the feature data, including at least two verification methods of clause consistency verification, logic error verification, and syntax error verification.

[0068] The clause consistency check mainly includes checking whether the clauses in the second contract template data (hereinafter referred to as the contract) are consistent with relevant laws, company policies, industry standards or previously agreed conditions. Specifically, it includes but is not limited to: ensuring that all clauses in the contract are not inconsistent with each other, for example, the coordination between payment terms and delivery terms; comparing the contract terms with the standard template or previous versions to verify whether there are any unauthorized changes; and checking whether the contract complies with the legal provisions of a specific jurisdiction to avoid compliance issues caused by regional differences.

[0069] Logical error checking focuses on analyzing whether the logical structure and content of the contract are reasonable and coherent, ensuring that the contract can accurately reflect the true intentions of the parties and has no logical loopholes or misleading statements. This includes but is not limited to: verifying the logic of conditional statements and confirming the logical order of contract terms, ensuring that they are arranged according to the logical process, without skipping or missing important steps, etc.

[0070] Grammatical error checking involves checking the grammatical correctness of the contract text to ensure the standardization and readability of the language. Specifically, it includes but is not limited to: correcting spelling errors and punctuation errors. Ensure that the sentence structure is correct and there are no incomplete or redundant components. Use the correct tense and voice to avoid semantic ambiguity. Maintain consistency in style and ensure the accurate use of professional terms and industry terms. It is understandable that in other embodiments, the above-mentioned multi-dimensional verification may not need to be completed by the contract approval model, and can be directly verified by the server according to multiple preset verification rules.

[0071] S600, when the second contract template data passes the multi-dimensional verification, extract the risk characteristic data in the second contract template data, and identify whether there are risk items in the second contract template data based on the risk characteristic data.

[0072] Risk characteristic data refers to keywords and their contextual information used to characterize potential risks, such as "breach of contract", "compensation", "force majeure" and "confidentiality obligation".

[0073] If the second contract template data passes the above-mentioned multi-dimensional verification, the risk prediction process will be automatically triggered. Specifically, the server may analyze the text data of the second contract template, identify and extract the keywords and their contextual information that match the risk characteristic dictionary, and obtain risk characteristic data. Then, with the risk characteristic data as input, the preset risk prediction mechanism or risk prediction model is called to perform risk prediction on the second contract template data, scan and match the predefined risk keywords, phrases or patterns, and automatically identify potential risk items. Specifically, it includes but is not limited to predicting the types of risks that may exist in the second contract template data and their severity, such as legal compliance risks, financial risks, execution risks, etc., and giving the probability of risk occurrence to determine whether there are potential risks in the second contract template data.

[0074] S800: If there are risk items in the second contract template data, the risk items are marked and a risk warning message is pushed.

[0075] Risk items refer to factors in the contract that may potentially cause disputes, losses, non-compliance or other negative impacts. These risk items may involve legal compliance, financial terms, difficulty of execution, responsibility attribution, etc. For example, unclear payment terms, overly stringent breach of contract compensation provisions, lack of clear service standard definitions, etc. can all be considered risk items.

[0076] Following the previous step, if there is no risk item in the second contract template data, the second contract template data is pushed to the file server for storage, so that each channel end can query the electronic contract service and generate an electronic contract in real time. In this embodiment, the file server can be a NAS (Network Attached Storage) file server cluster. If the server identifies that there is a risk item in the second contract template data, the risk item is marked. At the same time, according to the preset warning message push mechanism, a risk warning message can be sent through multiple notification channels such as email, SMS, and instant messaging software to notify relevant personnel such as contract managers to check the risk items in time and take measures to eliminate potential risks. Among them, the risk warning message can include risk details and recommended countermeasures. Furthermore, the server can also record the processing status of each risk warning, including the recipient's response time, processing progress and final results, to facilitate subsequent audits and improvements. According to the actual effect and feedback of the risk warning processing, the risk identification model, scoring system and warning mechanism can be continuously optimized to improve the accuracy and efficiency of the system.

[0077] In the above-mentioned electronic contract data processing method, in response to an online editing request carrying a contract template identifier sent by at least one contract template editing device, based on the contract editing data carried in the online editing request, the first contract template data corresponding to the contract template identifier is modified in real time to obtain the second contract template data, and the second contract template data is synchronized to the contract template editing device. In this way, multiple people can share and edit the electronic contract template data, and the real-time change of the contract template can be realized, saving the cumbersome operation of traditional offline modification. In addition, by calling the trained contract approval model, the second contract template data is intelligently, efficiently and accurately verified in multiple dimensions, including clause one At least two of the following checks, i.e. consistency check, logic error check and syntax error check, can improve the consistency and standardization of the contract template, reduce the possibility of errors in the contract content, and improve the quality and accuracy of the content of the contract template. Finally, when the second contract template data passes the multi-dimensional check, the risk feature data in the second contract template data is extracted, and the risk prediction of the second contract template data is performed, which can identify potential risks in advance and is conducive to timely avoidance of risks. When the risk items are identified, the identified risk items are marked and the risk warning message is pushed, so that the relevant personnel can understand the potential risks in advance and solve the potential risks in time, thereby improving the quality of the contract. In summary, the above scheme realizes the real-time change of the contract template data efficiently through the online shared editing of the contract template, and performs multi-dimensional check on the modified contract template data through the automatic and intelligent multi-dimensional check mechanism, thereby improving the consistency, logical correctness and syntax standardization of the contract terms, reducing the possibility of errors in the contract template content, and identifying the risk items of the contract template data. The potential risk items can be discovered in time, and the risks can be avoided in time, which significantly improves the quality and accuracy of the contract and reduces the number of repeated modifications of the contract template data. Therefore, the adoption of this scheme can effectively improve the processing efficiency of the contract template data.

[0078] In an exemplary embodiment, Figure 3 As shown, in an exemplary embodiment, after S800, the method further includes:

[0079] S820: Receive a contract generation request sent by the business terminal.

[0080] S840, parsing the contract generation request, extracting business requirement data in the contract generation request, and determining the business scenario.

[0081] S860, selecting a target contract template that matches the business requirement data and the business scenario from the pre-configured multiple contract template data.

[0082] S880, fill the business requirement data into the target contract template, generate an electronic contract, and send the electronic contract to the business terminal.

[0083] Business requirement data refers to the specific information about a specific business transaction or cooperation that needs to be provided when initiating a contract generation request, including the specific values ​​of contract variables, which can ensure that the generated contract content accurately reflects the actual intentions and details. For example, if an enterprise is to sign a procurement contract, the business requirement data may include the supplier name, the list of purchased items, the unit price, the total amount, the delivery time, etc. Contract variables refer to specific values ​​that can be changed in the contract template. For example, in a sales contract, "buyer's name", "seller's name", "goods description", "quantity", "price", "delivery date", etc. are all contract variables. When each new contract is generated, these variables will be filled with actual business requirement data to meet the needs of the specific transaction.

[0084] In actual applications, a contract template database is maintained in the server, and each contract template is associated with a specific business scenario label and applicable conditions. In specific implementation, business personnel or users can apply for business through various channels and send a contract generation request to the server by calling the contract service interface. The request contains necessary authentication information, business identification, and basic data related to the contract. After receiving the contract generation request, the server verifies the legitimacy of the received request, including but not limited to checking the source, the validity of the authentication information, and the integrity of the data. After the contract generation request passes the legitimacy verification, the contract generation request can be parsed. For example, if the request data format is JSON, the JSON parsing library is used to convert the data in the request into an operable data structure (such as a dictionary or object). If the request is in other formats, the parsing method of other corresponding formats is used to convert the data in the request into an operable data structure. Then, the business requirement data (such as the names of both parties, the amount, the date, etc.) is accurately extracted from the parsed data, and the business scenario is identified according to the business requirement data. Then, through keyword matching and business logic judgment, according to the extracted business requirement data and business scenarios, the target contract template that best matches the business requirement data and business scenarios is screened from the contract template database. Next, a template engine (such as FreeMarker, Mustache, etc.) is used to map the contract variables and elements in the extracted business demand data to the placeholders of the target contract template, implement dynamic content filling, generate an electronic contract, and send the electronic contract to the business terminal. Finally, the generated electronic contract is returned to the business terminal. In addition, after the first draft of the electronic contract is generated, a preview function can also be provided to allow the user or system to perform a final check to confirm that the information is correct.

[0085] In this embodiment, the electronic contract is generated by template matching and dynamic filling, which can flexibly respond to different business scenarios and personalized needs, and enhance the adaptability of the system. In addition, the automated filling process can reduce manual filling errors and improve the accuracy and professionalism of the contract.

[0086] like Figure 4 As shown, in an exemplary embodiment, S860 includes: S862, extracting the first characteristic data in the contract template data and the second characteristic data in the business requirement data, determining the matching score between the first characteristic data and the second characteristic data, and determining the contract template data with the highest matching score as the target contract template.

[0087] In this embodiment, the first characteristic data includes but is not limited to key terms and contract elements in the contract template, etc. The second characteristic data includes but is not limited to keywords and characteristic elements in business requirements, such as term category, value range, time limit, etc.

[0088] In specific implementation, all contract templates in the contract template database can be traversed, and the first feature data in each contract template can be extracted by natural language processing. Then, the second feature data in the business demand data can be extracted in the same way. Then, the first feature data and the second feature data are standardized and cleaned, and then the first feature data and the second feature data are compared, and a matching score is calculated according to the pre-defined matching rules. Specifically, each keyword can be given a certain weight to reflect its importance to the matching degree, and a classification matching rule can be established according to the type of contract terms (such as payment terms, service scope, breach of contract liability, etc.). Different categories may have different scoring standards. For features containing numerical values ​​or conditions (such as price ranges, contract terms), an acceptable range or conditional expression is set, and points are deducted if the range is exceeded. The TF-IDF value (term frequency-inverse document frequency) of the first feature data is calculated, compared with the second feature data, and the similarity score is calculated. For multi-dimensional feature vectors (such as multiple keywords or categories), the cosine similarity of the two vectors can be calculated to reflect their directional consistency in multiple dimensions. For numerical ranges and specific conditions, the proportion or distance that meets the conditions is directly calculated and converted into part of the matching score. Then, the matching scores of the above-mentioned various aspects are integrated into a comprehensive matching score by weighted summation or linear combination. Then, the matching scores of all contract templates are compared, and the contract template with the highest matching score is determined as the target contract template. In other embodiments, the cosine similarity between the first feature data and the second feature data can be calculated, and the contract template with the highest cosine similarity can be determined as the target template contract.

[0089] In this embodiment, by calculating the matching score between the first characteristic data in the contract template and the second characteristic data in the business requirement data, the target template contract can be screened out quickly and accurately.

[0090] like Figure 5 As shown, in an exemplary embodiment, performing a clause consistency check on the second contract template data includes:

[0091] S420, extracting contract terms from the contract feature data.

[0092] S422, selecting target contract terms that match the contract terms from a preset standard contract terms database.

[0093] S424, determining the semantic similarity between the contract terms and the target contract terms.

[0094] S426: Determine, based on the semantic similarity, whether there are any contract clauses in the second contract template data that do not match the standard contract clauses.

[0095] In actual application, a comprehensive database of standard contract terms is built on the server, including typical terms extracted and summarized from various authoritative legal resources and historical contract cases. Each clause should have a clear definition, applicable scenarios and standard expression form.

[0096] In specific implementation, the server may pre-process the second contract template data, including removing irrelevant symbols, dividing into paragraphs, standardizing the text format, etc., and then extract the pre-processed contract feature data through named entity recognition, keyword extraction, syntactic analysis, etc. Then, the contract feature data is input into the contract approval model, and the contract approval model extracts the contract terms in the contract feature data. The extracted contract terms are preliminarily matched with the standard terms database, and possible corresponding items, namely the target contract terms, are screened out. For the target contract terms that are preliminarily matched successfully, a more sophisticated comparison method is used, such as semantic similarity calculation (such as using TF-IDF, Word2Vec, BERT and other models), to evaluate the semantic difference between the target contract terms and the contract terms. If the contract terms and the standard target contract terms have significant differences in meaning and expression, the contract terms are marked as "inconsistent". In other embodiments, the similarity between the contract terms in the contract feature data and the standard contract terms can also be directly calculated. By comparing the similarity, it is determined whether the contract terms are consistent with the standard contract terms. If the similarity is lower than the preset similarity threshold, the contract terms are marked as "inconsistent". Furthermore, a clause consistency verification report can be generated, listing all marked inconsistent clauses and their locations, references to standard clauses, and suggested correction directions. It is understandable that the above clause consistency verification does not need to be completed by the contract approval model. The server can directly extract the pre-processed contract feature data according to the preset clause consistency verification rules, and then perform preliminary keyword matching on the extracted contract clauses with the standard clause database. The clause consistency verification process is the same as the verification process of the above contract approval model.

[0097] In this embodiment, by performing intelligent clause consistency verification on the contract template data, the time cost of manual clause-by-clause verification can be greatly reduced, and inconsistent contract clauses can be detected efficiently and accurately.

[0098] In an exemplary embodiment, performing logic error checking on the second contract template data includes at least one of the following methods:

[0099] The first one is to verify the consistency and rationality of the logical relationship between the contract terms in the contract feature data.

[0100] The second is to verify the consistency and rationality of the values ​​and dates in the contract characteristic data.

[0101] The third method is to verify whether the execution dependencies of the contract terms in the contract feature data are correct.

[0102] In this embodiment, the logical error check of the second contract template data includes checking the consistency and rationality of the logical relationship between the contract clauses in the second contract template data, verifying the consistency and rationality of the numerical values ​​and dates in the contract feature data, and verifying whether the execution dependency relationship of the contract clauses in the contract feature data is correct.

[0103] Specifically, the verification of logical relationships can be: pre-setting logical rules based on legal knowledge and contract terms, such as "if there is a breach of contract clause, there must be a corresponding breach of contract liability clause", "rent payment terms should be associated with the lease term". These rules can be Boolean logic, conditional dependencies, etc. In the actual verification process, the server can classify and label the terms in the contract template, such as "payment terms", "breach of contract liability", "term and termination", to facilitate the application of logical rules, and then traverse the contract terms based on the classification labels and logical rule sets to check whether there are logical omissions or contradictions in the contract terms. For example, check whether the logical structure of "if...then..." is complete and reasonable.

[0104] Verification of values ​​and dates can be done by: using regular expressions or natural language processing techniques to identify and extract all values ​​(such as amounts, quantities) and date information in the contract. Comparing the consistency of values ​​or dates of the same type, such as ensuring that the total amounts mentioned in different parts are the same and that the start and end dates are in a logical order. Setting corresponding thresholds based on industry standards or common sense to determine whether the values ​​are within a reasonable range (such as rent should not be much lower than the market price) and whether the date intervals are reasonable (such as the lease term should not exceed the property rights period of the building).

[0105] Verification of execution dependencies can be done by: building a dependency graph for clause execution based on the logic between contract clauses, such as when a clause becomes effective depending on the completion of another clause. Applying a topological sorting algorithm, check whether the clause execution sequence forms a closed loop, whether there are start clauses without dependencies and end clauses without successors, and ensure the consistency of the execution path. In addition, loop and conflict detection is also performed on contract clauses, that is, checking whether there is a logical loop, that is, clause A depends on clause B, and B depends on clause A indirectly or directly, which is usually not allowed in contracts.

[0106] In this embodiment, by verifying the consistency and rationality of the logical relationship between the contract terms in the second contract template data, verifying the consistency and rationality of the numerical values ​​and dates in the contract characteristic data, and verifying the execution dependency of the contract terms in the contract characteristic data, the contract can be made more standardized and accurate, the contract terms can be performed according to the correct logic, and potential execution problems can be resolved in advance.

[0107] In other embodiments, the contract approval model can be used to check the consistency of clauses, and the contract approval model can predict whether each clause complies with the standard format or requirements of a specific type of contract, and mark inconsistent clauses. The logic error check can be performed by analyzing the logical structure in the contract, such as conditional statements, timelines, numerical relationships, etc., to ensure the logical coherence and rationality of the clauses, predict the logical path in the contract, and identify the combination of clauses that may lead to logical contradictions or execution difficulties, such as unreasonable combinations of payment clauses and delivery clauses.

[0108] Regarding grammatical error checking, it can be to identify and mark spelling errors, improper punctuation, syntactic errors, etc. After obtaining the verification results output by the contract approval model, the verification results can also be integrated to generate a detailed verification report, including the error type, location, and recommended modification plan. The contract administrator can correct the contract template based on the verification results and submit it for verification again. The model will continuously optimize the revised contract template based on the feedback to improve the verification accuracy. In this embodiment, the contract approval model is used to perform intelligent approval and multi-dimensional verification of the contract template data, which can achieve accurate and efficient approval and verification, and improve the quality and standardization of the contract template data.

[0109] like Figure 6 As shown, in an exemplary embodiment, S600 includes: S620, determining the risk category and risk impact degree of the risk characteristic data, determining the risk level of the risk characteristic data based on the risk category and risk impact degree, and determining the risk characteristic data with a risk level higher than a preset risk level as a risk item.

[0110] In practical applications, a dictionary containing typical risk feature keywords can be constructed based on legal and risk management knowledge. In addition, a risk prediction model is trained based on contract data of known risk items. The model can output risk categories and risk impact levels (such as high, medium, and low). In addition, a risk rating system can be constructed by combining risk categories and risk impact levels. For example, high risk category + high impact level = extremely high risk level; low risk category + low impact level = low risk level. Among them, high risk may refer to clauses that directly affect financial health or legal compliance; medium risk may involve difficulties at the execution level; and low risk may be a minor misstatement.

[0111] In specific implementation, the extracted risk feature data can be first converted into the format required by the risk prediction model, which may include coded risk features, standardized values, etc. Then, the converted risk feature data is input into the risk prediction model to obtain the risk category and impact degree of each risk feature data. Then, according to the pre-constructed risk level system, the risk level of the risk feature data is determined, and the risk level includes extremely high risk level, high risk level and low risk level, and then the risk feature data with a risk level higher than the preset risk level (such as high risk level) is determined as a risk item. It can be understood that in other embodiments, the risk prediction model can be used for risk prediction, and the risk category and risk impact degree of the risk feature data can be determined directly according to the preset risk category and risk impact degree judgment rules, and then the risk level of the risk feature data can be determined according to the preset risk level system, and the risk feature data with a risk level higher than the preset risk level (such as high risk level) is determined as a risk item. Further, the risk prediction results can be integrated, a risk report can be generated, and the risk report can be pushed so that the contract manager can view the risks in time and eliminate potential risks.

[0112] In this embodiment, risk prediction is performed on risk feature data through a risk prediction model, which can efficiently and accurately assess potential risks and identify high-risk items.

[0113] In order to make a clearer description of the contract template data processing method provided by this application, the following is a specific embodiment and attached Figure 7 To illustrate, this specific embodiment includes the following steps:

[0114] S200, in response to an online editing request carrying a contract template identifier sent by at least one contract template editing device, based on the contract editing data carried in the online editing request, modify the first contract template data corresponding to the contract template identifier, obtain second contract template data, and synchronize the second contract template data to the contract template editing device.

[0115] S460, extracting the contract feature data from the second contract template data, taking the contract feature data as input, calling the trained contract approval model to perform at least two of clause consistency check, logic error check and syntax error check on the second contract template data, wherein the contract approval model is obtained by training a machine learning model using standard contract samples.

[0116] S620, when the second contract template data passes multi-dimensional verification, extract the risk characteristic data in the second contract template data, determine the risk category and risk impact degree of the risk characteristic data, determine the risk level of the risk characteristic data based on the risk category and risk impact degree, and determine the risk characteristic data with a risk level higher than the preset risk level as a risk item.

[0117] S800: If there are risk items in the second contract template data, the risk items are marked and a risk warning message is pushed.

[0118] S900, receiving a contract generation request sent by a business terminal, parsing the contract generation request, extracting business requirement data in the contract generation request, and determining a business scenario.

[0119] S920, extracting the first characteristic data in the contract template data and the second characteristic data in the business requirement data, and determining a matching score between the first characteristic data and the second characteristic data.

[0120] S940, determining the contract template data with the highest matching score as the target contract template, filling the business requirement data into the target contract template, generating an electronic contract, and sending the electronic contract to the business terminal.

[0121] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, 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 can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0122] Based on the same inventive concept, the embodiment of the present application also provides a contract template data processing device for implementing the contract template data processing method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the contract template data processing device provided below can refer to the limitations of the contract template data processing method above, and will not be repeated here.

[0123] In an exemplary embodiment, Figure 8 As shown, a contract template data processing device 800 is provided, comprising: a data modification module 810, a data verification module 820, a data prediction module 830 and a data push module 840, wherein:

[0124] The data modification module 810 is used to respond to an online editing request carrying a contract template identifier sent by at least one contract template editing device, modify the first contract template data corresponding to the contract template identifier based on the contract editing data carried in the online editing request, obtain the second contract template data, and synchronize the second contract template data to the contract template editing device.

[0125] The data verification module 820 is used to extract the contract feature data in the second contract template data, and use the contract feature data as input to call the trained contract approval model to perform multi-dimensional verification on the second contract template data. The multi-dimensional verification includes at least two of the clause consistency verification, logical error verification, and syntax error verification.

[0126] The data prediction module 830 is used to extract the risk characteristic data in the second contract template data when the second contract template data passes the multi-dimensional verification, and identify whether there are risk items in the second contract template data based on the risk characteristic data.

[0127] The data push module 840 is used to mark the risk item and push a risk warning message if there is a risk item in the second contract template data.

[0128] like Fig. 9 As shown, in an exemplary embodiment, the device also includes: a contract generation module 850, which is used to receive a contract generation request sent by a business terminal, parse the contract generation request, extract the business requirement data in the contract generation request, and determine the business scenario, filter out a target contract template that matches the business requirement data and the business scenario from a plurality of pre-configured contract template data, fill the business requirement data into the target contract template, generate an electronic contract, and send the electronic contract to the business terminal.

[0129] In an exemplary embodiment, the contract generation module 850 is also used to extract the first characteristic data in the contract template data and the second characteristic data in the business requirement data, determine the matching score between the first characteristic data and the second characteristic data, and determine the contract template data with the highest matching score as the target contract template.

[0130] In an exemplary embodiment, the data verification module 820 is also used to extract contract terms from the contract feature data, filter out target contract terms that match the contract terms from a preset standard contract terms database, determine the semantic similarity between the contract terms and the target contract terms, and determine whether there are contract terms in the second contract template data that do not match the standard contract terms based on the semantic similarity.

[0131] In an exemplary embodiment, the data verification module 820 is further configured to perform at least one of the following operations:

[0132] The first is to verify the consistency and rationality of the logical relationship between the contract terms in the contract feature data;

[0133] The second is to verify the consistency and rationality of the values ​​and dates in the contract characteristic data;

[0134] The third method is to verify whether the execution dependencies of the contract terms in the contract feature data are correct.

[0135] In an exemplary embodiment, the data prediction module 830 is also used to determine the risk category and risk impact degree of the risk characteristic data, determine the risk level of the risk characteristic data based on the risk category and risk impact degree, and determine the risk characteristic data with a risk level higher than a preset risk level as a risk item.

[0136] Each module in the above-mentioned contract template data processing device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0137] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG10. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as contract template data and standard contract clause data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a contract template data processing method is implemented.

[0138] Those skilled in the art will understand that the structure shown in FIG. 10 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0139] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps in any one of the above-mentioned contract template data processing method embodiments are implemented.

[0140] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in any one of the above-mentioned contract template data processing method embodiments are implemented.

[0141] In an exemplary embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps of any one of the above-mentioned contract template data processing method embodiments.

[0142] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0143] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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.

[0144] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for processing contract template data, characterized in that: The method comprises: In response to an online editing request carrying a contract template identifier sent by at least one contract template editing device, based on the contract editing data carried in the online editing request, modify the first contract template data corresponding to the contract template identifier to obtain second contract template data, and synchronize the second contract template data to the contract template editing device; extracting contract feature data from the second contract template data, taking the contract feature data as input, calling a trained contract approval model to perform multi-dimensional verification on the second contract template data, wherein the multi-dimensional verification includes at least two of clause consistency verification, logic error verification, and syntax error verification, and the contract approval model is obtained by training a machine learning model using standard contract samples; If the second contract template data passes the multi-dimensional verification, extracting risk feature data from the second contract template data, and identifying whether the second contract template data has risk items based on the risk feature data; If there are risk items in the second contract template data, the risk items are marked and a risk warning message is pushed.

2. The method according to claim 1, characterized in that After pushing the risk warning message, the method further includes: Receive a contract generation request sent by a business terminal; Parsing the contract generation request, extracting business requirement data in the contract generation request, and determining a business scenario; Filtering out a target contract template that matches the business requirement data and the business scenario from a plurality of pre-configured contract template data; The business requirement data is filled into the target contract template, an electronic contract is generated, and the electronic contract is sent to the business terminal.

3. The method according to claim 2, characterized in that The step of selecting a target contract template matching the business demand data from a plurality of contract template data pre-configured under the business scenario includes: Extracting the first characteristic data in the contract template data and the second characteristic data in the business requirement data; Determining a matching score between the first feature data and the second feature data; The contract template data with the highest matching score is determined as the target contract template.

4. The method according to any one of claims 1 to 3, characterized in that: The second contract template data is subjected to clause consistency check, including: Extracting contract terms from the contract feature data; Filtering target contract terms that match the contract terms from a preset standard contract terms database; Determining semantic similarity between the contract clause and the target contract clause; Based on the semantic similarity, it is determined whether there are any contract clauses in the second contract template data that do not match the standard contract clauses.

5. The method according to any one of claims 1 to 3, characterized in that: The performing logic error checking on the second contract template data includes at least one of the following methods: First, verify the consistency and rationality of the logical relationship between the contract terms in the contract feature data; The second is to verify the consistency and rationality of the values ​​and dates in the contract characteristic data; The third method is to verify whether the execution dependency of the contract terms in the contract feature data is correct.

6. The method according to any one of claims 1 to 3, characterized in that: The identifying, based on the risk characteristic data, whether the second contract template data has a risk item includes: Confirm the risk category and risk impact level of the risk characteristic data; Determining the risk level of the risk characteristic data based on the risk category and the risk impact degree; The risk characteristic data with a risk level higher than a preset risk level is determined as a risk item.

7. A contract template data processing device, characterized in that: The device comprises: A data modification module, configured to respond to an online editing request carrying a contract template identifier sent by at least one contract template editing device, modify first contract template data corresponding to the contract template identifier based on contract editing data carried in the online editing request, obtain second contract template data, and synchronize the second contract template data to the contract template editing device; a data verification module, configured to extract contract feature data from the second contract template data, use the contract feature data as input, and call a trained contract approval model to perform multi-dimensional verification on the second contract template data, wherein the multi-dimensional verification includes at least two of clause consistency verification, logic error verification, and grammatical error verification, and the contract approval model is obtained by training a machine learning model using a standard contract sample; a data prediction module, configured to extract risk feature data from the second contract template data when the second contract template data passes the multi-dimensional verification, and identify whether the second contract template data has risk items based on the risk feature data; The data push module is used to mark the risk items and push risk warning messages if there are risk items in the second contract template data.

8. The device according to claim 7, characterized in that The device also includes: a contract generation module, which is used to receive a contract generation request sent by a business terminal, parse the contract generation request, extract business requirement data in the contract generation request, and determine the business scenario, filter out a target contract template that matches the business requirement data and the business scenario from a plurality of pre-configured contract template data, fill the business requirement data into the target contract template, generate an electronic contract, and send the electronic contract to the business terminal.

9. The device according to claim 8, characterized in that The contract generation module is also used to extract the first characteristic data in the contract template data and the second characteristic data in the business demand data, determine the matching score between the first characteristic data and the second characteristic data, and determine the contract template data with the highest matching score as the target contract template.

10. The device according to any one of claims 7 to 9, characterized in that: The data verification module is also used to extract contract terms from the contract feature data, screen out target contract terms that match the contract terms from a preset standard contract terms database, determine the semantic similarity between the contract terms and the target contract terms, and determine whether there are contract terms in the second contract template data that do not match the standard contract terms based on the semantic similarity.

11. The device according to any one of claims 7 to 9, characterized in that: The data verification module is further configured to perform at least one of the following operations: First, verify the consistency and rationality of the logical relationship between the contract terms in the contract feature data; The second is to verify the consistency and rationality of the values ​​and dates in the contract characteristic data; The third method is to verify whether the execution dependency of the contract terms in the contract feature data is correct.

12. The device according to any one of claims 7 to 9, characterized in that The data prediction module is also used to determine the risk category and risk impact degree of the risk characteristic data, determine the risk level of the risk characteristic data based on the risk category and the risk impact degree, and determine the risk characteristic data with a risk level higher than a preset risk level as a risk item.

13. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

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

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

Citation Information

Cited By

  • Safety intelligent supervision system and method applied to housing platform

    CN119477608A

  • Intelligent contract generation method and device, electronic equipment and storage medium

    CN119940328A

  • Graphical user interface for syntax and policy compliance review

    US12430491B1