Contract processing method and device based on artificial intelligence, and intelligent agent

Abstract

The invention provides a contract processing method and device based on artificial intelligence, an intelligent agent, electronic equipment, a storage medium and a program product, and relates to the technical field of artificial intelligence, in particular to the technical fields of large models, content generation, contract editing, examination and management and the like. According to the specific implementation scheme, the method comprises the steps of determining contract type information of a to-be-generated contract based on interaction operation information, related to a contract generation intention, of a target object; based on the contract type information of the to-be-generated contract, displaying recommendation information for describing the to-be-generated contract in an input box of the interactive interface; and in response to a recommendation information-based determination operation of the target object, inputting the recommendation information and the contract type information into the contract generation large model to obtain a contract template.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, particularly to the fields of large models, content generation technology, contract editing, review and management, and specifically to artificial intelligence-based contract processing methods, devices, intelligent agents, electronic devices, storage media and program products. Background Technology

[0002] Traditional contract drafting processes are cumbersome and time-consuming. For example, contract texts require multiple steps, including reading, analysis, and comparison by professionals, to determine their legality and compliance. However, with the rapid development of artificial intelligence technology, contract processing tools have emerged, freeing up human resources. Nevertheless, contracts generated using these tools often differ significantly from user expectations. Summary of the Invention

[0003] This disclosure provides a contract processing method, apparatus, intelligent agent, electronic device, storage medium, and program product based on artificial intelligence.

[0004] According to one aspect of this disclosure, an artificial intelligence-based contract processing method is provided, comprising: determining contract type information of the contract to be generated based on interactive operation information of a target object related to the intention to generate a contract; displaying recommended information describing the contract to be generated in an input box of an interactive interface based on the contract type information of the contract to be generated; and, in response to the target object's determination operation based on the recommended information, inputting the recommended information and the contract type information into a large contract generation model to obtain a contract template.

[0005] According to another aspect of this disclosure, an artificial intelligence-based contract processing apparatus is provided, comprising: a first type determination module, configured to determine contract type information of the contract to be generated based on interactive operation information of a target object related to the intention to generate a contract; a recommendation display module, configured to display recommended information describing the contract to be generated in an input box of an interactive interface based on the contract type information of the contract to be generated; and a template generation module, configured to, in response to the determination operation of the target object based on the recommended information, input the recommended information and the contract type information into a large contract generation model to obtain a contract template.

[0006] According to another aspect of this disclosure, an artificial intelligence agent is provided, comprising: an input module for receiving input information; a processing module for determining a target task based on the input information received by the input module, determining a large model based on the target task, and obtaining output information by calling the large model to execute the method described above; and an output module for outputting the output information obtained by the processing module.

[0007] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the methods as disclosed herein.

[0008] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause a computer to perform the methods as disclosed herein.

[0009] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method as disclosed herein.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0011] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0012] Figure 1 The illustration schematically shows an exemplary system architecture for applying artificial intelligence-based contract processing methods and apparatus according to embodiments of the present disclosure;

[0013] Figure 2 A flowchart illustrating an artificial intelligence-based contract processing method according to an embodiment of the present disclosure is shown schematically.

[0014] Figure 3 This illustration schematically shows a view of navigating from a front-end page to an interactive interface according to an embodiment of the present disclosure;

[0015] Figure 4 This illustration schematically shows a diagram illustrating the determination of contract type information according to another embodiment of the present disclosure;

[0016] Figure 5 A schematic diagram illustrating the display of recommendation information according to an embodiment of the present disclosure is shown.

[0017] Figure 6 A schematic diagram illustrating the generation of an editing contract according to an embodiment of this disclosure is shown.

[0018] Figure 7 A schematic diagram illustrating the display of examination results according to another embodiment of this disclosure is shown;

[0019] Figure 8A flowchart illustrating an artificial intelligence-based contract processing method according to another embodiment of this disclosure is shown schematically;

[0020] Figure 9 A block diagram of an artificial intelligence-based contract processing apparatus according to an embodiment of the present disclosure is shown schematically.

[0021] Figure 10 A schematic diagram illustrating the structure of an intelligent agent of artificial intelligence according to embodiments of the present disclosure; and

[0022] Figure 11 A block diagram of an electronic device suitable for implementing an artificial intelligence-based contract processing method according to an embodiment of the present disclosure is shown schematically. Detailed Implementation

[0023] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0024] Traditional contract drafting requires the involvement of legal professionals, which is time-consuming, labor-intensive, and costly. Alternatively, publicly available online contract templates can be used, but these templates are relatively fixed and cannot adapt to the diverse needs of users.

[0025] In view of this, the present disclosure provides a contract processing method, apparatus, electronic device, storage medium, and program product based on artificial intelligence.

[0026] According to embodiments of this disclosure, an artificial intelligence-based contract processing method is provided, comprising: determining contract type information of the contract to be generated based on interactive operation information of a target object related to the intention to generate a contract; displaying recommended information describing the contract to be generated in an input box of an interactive interface based on the contract type information of the contract to be generated; and, in response to the target object's determination operation based on the recommended information, inputting the recommended information and contract type information into a large contract generation model to obtain a contract template.

[0027] The AI-based contract processing method provided in this disclosure can dynamically generate recommended information based on interactive operation information reflecting the target object's intent through intelligent interactive functions. This simplifies the target object's input operations, enhances the professionalism of expressing contract generation needs, and lowers the participation threshold. Furthermore, by utilizing a large contract generation model, contract templates are intelligently generated based on recommended information, contract type information, and other information related to the target object's intent. This improves the intelligence, flexibility, and relevance of contract generation to the target object's intent.

[0028] In the technical solution disclosed herein, the collection, storage, use, processing, transmission, provision, disclosure, and application of user personal information comply with the provisions of relevant laws and regulations, necessary confidentiality measures have been taken, and there is no violation of public order and good morals.

[0029] In the technical solution disclosed herein, the user's authorization or consent is obtained before acquiring or collecting the user's personal information.

[0030] Figure 1 The illustration schematically depicts an exemplary system architecture for applying artificial intelligence-based contract processing methods and apparatus according to embodiments of the present disclosure.

[0031] It is important to note that Figure 1 The examples shown are merely examples of system architectures applicable to embodiments of this disclosure, intended to help those skilled in the art understand the technical content of this disclosure. They do not imply that embodiments of this disclosure cannot be used in other devices, systems, environments, or scenarios. For instance, in another embodiment, an exemplary system architecture for applying an AI-based contract processing method and apparatus may include a terminal device. However, the terminal device can implement the AI-based contract processing method and apparatus provided by embodiments of this disclosure without interacting with a server.

[0032] like Figure 1 As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, and 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between the terminal devices 101, 102, and 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0033] Developers can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send testing tools, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as knowledge reading applications, web browser applications, search applications, instant messaging tools, email clients, and / or social media platform software (for example only).

[0034] Terminal devices 101, 102, and 103 can be various electronic devices with displays and web browsing capabilities, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0035] Server 105 can be a server that provides various services, such as a back-end management server that provides testing tools for the product under test installed by users using terminal devices 101, 102, and 103 (for example only).

[0036] It should be noted that the AI-based contract processing method provided in this disclosure can generally be executed by server 105. Correspondingly, the AI-based contract processing apparatus provided in this disclosure can generally be located in server 105. The AI-based contract processing method provided in this disclosure can also be executed by a server or server cluster that is different from server 105 and capable of communicating with terminal devices 101, 102, 103 and / or server 105. Correspondingly, the AI-based contract processing apparatus provided in this disclosure can also be located in a server or server cluster that is different from server 105 and capable of communicating with terminal devices 101, 102, 103 and / or server 105.

[0037] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0038] It should be noted that the sequence numbers of the operations in the following methods are for descriptive purposes only and should not be considered as indicating the execution order of the operations. Unless explicitly stated otherwise, the method does not need to be executed in the exact order shown.

[0039] Figure 2 A flowchart illustrating an AI-based contract processing method according to an embodiment of this disclosure is shown schematically.

[0040] like Figure 2 As shown, the method includes operations S210~S230.

[0041] In operation S210, based on the interactive operation information of the target object related to the intention to generate the contract, the contract type information of the contract to be generated is determined.

[0042] In operation S220, based on the contract type information of the contract to be generated, recommended information describing the contract to be generated is displayed in the input box of the interactive interface.

[0043] In operation S230, in response to the determination operation based on recommendation information of the target object, the recommendation information and contract type information are input into the large contract generation model to obtain the contract template.

[0044] The target audience can refer to users who interact with the interface.

[0045] Interactive operations refer to actions performed by a target object through the input / output system of a terminal device. Examples include forwarding, saving, browsing, or entering information in an input box.

[0046] Interaction logs can be used to identify interaction information that reflects the actions performed by the target object. Based on this interaction information, user intent can be determined, such as the contract type information to be generated.

[0047] Contract type information may include, but is not limited to: sales contracts, lease contracts, confidentiality agreements, etc.

[0048] There are no restrictions on the type of interactive interface, as long as it has an input box or an editable display box, so as to display recommended information describing the contract to be generated in the interactive interface.

[0049] Recommended information can be understood as automatically recommended contract-related information presented to the target audience. For example, recommended information related to a lease contract might include: lease price, liability for breach of contract, ..., information about the leased items, etc. Similarly, recommended information related to a purchase contract might include: specific property information, transaction price, delivery method, ..., liability for breach of contract, etc. This recommended information clarifies the terms, limitations, and additional content required for generating the contract.

[0050] By interacting with the confirmation control, the target user can determine whether the recommended information meets their needs. If the information meets their needs, they can click the confirmation control to complete the confirmation process.

[0051] The contract generation model can be used for retrieval enhancement by indexing legal knowledge information from the knowledge base that matches the contract type information. This allows the contract generation model to automatically generate contract templates that match and comply with the terms of the contract, based on recommended information, legal knowledge information, and contract type information. However, it is not limited to this. The contract generation model can also be used to index pre-defined contract templates from the knowledge base that match the contract type information. These pre-defined templates can then be adjusted based on recommended information and contract type information to quickly generate contract templates that match both the contract type and recommended information.

[0052] The AI-based contract processing method provided in this disclosure can dynamically generate recommended information based on interactive operation information reflecting the target object's intent through intelligent interactive functions. This simplifies the target object's input operations and improves the standardization and comprehensiveness of expressing contract generation needs through recommended information, avoiding the problem of unprofessional expression of contract generation needs due to the target object being a non-legal professional. Furthermore, a large-scale contract generation model is used to intelligently generate contract templates based on recommended information, contract type information, and other information related to the target object's intent, thereby improving the flexibility of contract generation and the matching degree between the generated target contract and the target object's intent.

[0053] The above section provided an overview of how to generate contract templates. The following section will further explain how to determine the contract type information through interactive operation information.

[0054] According to embodiments of this disclosure, for example, Figure 2 The illustrated operation S210, based on the interactive operation information of the target object related to the intention to generate a contract, determines the contract type information of the contract to be generated. This may include: in the event of a triggering event for displaying an interactive interface, determining the interactive operation information related to the intention to generate a contract from the set of interactive operation information generated by the target object on the front-end page. Based on the intention recognition result of the interactive operation information, the contract type information of the contract to be generated is determined.

[0055] The preceding page can be the access page before the interactive interface is displayed. Trigger events can be used to trigger the display of the interactive interface; for example, after a trigger event occurs, a jump to the interactive interface is triggered. Trigger events can include action events that occur on the preceding page and are used to link to the interactive interface. Action events can include click events on controls or entries linked to the interactive interface.

[0056] Figure 3 The illustration shows a schematic diagram of a jump from a front-end page to an interactive interface according to an embodiment of the present disclosure.

[0057] like Figure 3 As shown, the front page 310 can display a search box 311 and a page tab bar 313 related to the search term 312 (e.g., query) entered in the search box 311. In response to a click operation on the target page tab bar 314 used to jump to the interactive interface 320, a trigger event for displaying the interactive interface 320 is determined.

[0058] Optionally, while displaying the interactive interface on the screen, the set of interactive operation information generated on the front interface can be obtained.

[0059] The interactive operation information in the interactive operation information set can be information recorded through operations on interactive controls on the front-end page. Interactive operation information related to the intention to generate a contract can be determined from this set. For example, input information typed into an input box on the front-end page that represents the intention to generate a contract can be used as interactive operation information, or recorded information from clicking, for example, a "Contract Generation" control.

[0060] The set of interactive information can include search terms entered in the search box, clicked other page tabs, and web pages viewed corresponding to those tabs. Interactive information relevant to generating the contract intent can be identified from this set.

[0061] The contract type information for the contract to be generated can be determined based on the intent recognition results of the interactive operation information. For example, the interactive operation information includes information such as saving or forwarding a rental introduction webpage. The intent of the target object can be determined through the interactive operation information. The means of identifying the target object's intent are not limited; for example, intent recognition using a large model or semantic recognition can be used to determine the intent recognition result. Based on the intent recognition result, the contract type information is determined.

[0062] According to embodiments of this disclosure, by linking the front-end page with the interactive interface, the target object can access the interactive interface through multiple means, thereby increasing the applicability of the interactive interface. Furthermore, determining the target object's intent based on interaction information from the front-end page expands the scope and richness of information revealing the target object's intent, improves the effectiveness of determining contract type information, and enhances the matching degree between subsequent recommendation information and user needs.

[0063] The preceding text explained in detail how to determine contract type information from the set of interactive operation information generated on the configuration page. However, in practical applications, it cannot be guaranteed that contract type information will always be determined from the interactive operation information. The following interaction methods can be used to further guide the target object to express the required contract type information.

[0064] According to embodiments of this disclosure, when performing such Figure 2 During operation S210, if the contract type information cannot be determined based on the interactive operation information, the AI-based contract processing method may further include: displaying guidance information on the interactive interface. The guidance information is used to guide the target object to input contract type information. In response to the target object's selection of the guidance information, the contract type information is determined.

[0065] Figure 4A schematic diagram illustrating the determination of contract type information according to another embodiment of this disclosure is shown.

[0066] like Figure 4 As shown, guidance information can be displayed on the interactive interface 410. The types of guidance information may include guidance statement 411 "Help me generate a cooperation agreement?", guidance word 412 "cooperation agreement", etc.

[0067] The system can determine the contract type information in response to the target object's selection of guidance information. A selection operation can refer to a click operation. Any operation that can represent selecting a target guidance information from multiple guidance information options is acceptable.

[0068] According to embodiments of this disclosure, when the contract type information cannot be determined based on the interactive operation information, guidance information is actively displayed to further guide the target object to express effective information, thereby improving the user experience of human-computer interaction.

[0069] The preceding text explained how to determine the contract type information for the contract to be generated. The following text will explain how to determine recommended information based on the contract type information through human-computer interaction.

[0070] According to embodiments of this disclosure, for example, Figure 2 The operation S220 shown, based on the contract type information of the contract to be generated, displays recommended information describing the contract to be generated in the input box of the interactive interface. This may include: determining recommended word groups that match the contract type information from the candidate recommended word set, and using them as recommended information. The recommended information is displayed in an editable state in the input box of the interactive interface.

[0071] Figure 5 A schematic diagram illustrating the display of recommendation information according to an embodiment of the present disclosure is shown.

[0072] like Figure 5 As shown, once the contract type information 530 has been determined, recommended information 520 can be displayed on the interactive interface 510. The recommended information 520 may include contract topic information that matches the contract type information 530.

[0073] Taking a purchase contract as an example, recommended information can include specific property information, transaction price such as monthly rent, delivery method, and liability for breach of contract, etc.

[0074] Optionally, the recommended information is used to deeply characterize the target audience's detailed needs for the generated contract. By proactively outputting recommended phrases as recommended information, it is possible to effectively guide the target audience in expressing their needs for the generated contract while lowering the barrier to entry for expressing professional content such as terms and specifications.

[0075] Optionally, the recommendation information can be displayed in an editable state to allow the target object to further edit the recommendation information. In response to the target object's editing operation, the modified recommendation information is determined and used as the recommendation information.

[0076] Optionally, the editing operation may include deleting at least one recommended word from the displayed recommendations, or adding at least one recommended word.

[0077] According to embodiments of this disclosure, recommended information can be automatically displayed in the input boxes of the interactive interface, thereby improving the guidance for the target audience to express their needs and lowering the threshold for them to express professional content such as terms and specifications. Furthermore, displaying recommended information in the input boxes facilitates editing operations for the target audience, further enhancing their flexibility and enabling more targeted contract template generation.

[0078] The above text explained the role of recommendation information. The following text will explain how to construct recommendation phrases as recommendation information.

[0079] Optionally, legal knowledge information matching the contract type information can be retrieved from a knowledge base. Based on the legal knowledge information, multiple contract subheadings matching the contract type information are determined. Each contract subheading corresponds to a contract sub-content or contract clause.

[0080] Based on multiple contract subheadings, recommended phrases matching the contract type information are determined. For example, a mapping relationship between contract type information and recommended phrases can be established. Based on the contract type information of the contract to be generated, recommended phrases for the contract to be generated are determined. These recommended phrases are then displayed as recommendation information on the interactive interface.

[0081] By pre-constructing mapping relationships, interaction efficiency can be improved, avoiding issues that degrade user experience. Furthermore, pre-constructing mapping relationships, by extracting information from legal knowledge, enhances accuracy and effectiveness.

[0082] The preceding text explained how to guide the target audience to express their intention to generate a contract, thereby improving the effectiveness and accuracy of the generated contract template. The following text will explain how to utilize the aforementioned information, such as contract type information and recommendation information, to generate a contract template.

[0083] According to embodiments of this disclosure, for example, Figure 2The operation S230 shown involves inputting recommendation information and contract type information into a large-scale contract generation model to obtain a contract template. This can include: using the large-scale contract generation model to retrieve legal knowledge information matching the contract type information and a pre-defined contract template matching the contract type information from a knowledge base; extracting the legal knowledge information using the recommendation information to obtain the target legal knowledge information; and adjusting the pre-defined contract template using the recommendation information and the target legal knowledge information to obtain the final contract template.

[0084] Retrieval enhancements are achieved by leveraging a large-scale contract generation model, such as retrieving legal knowledge and pre-defined contract templates from a knowledge base that match contract type information. This improves the utilization rate of enhanced retrieval knowledge and the accuracy of subsequent outputs from the large-scale contract generation model, preventing illusions in the model.

[0085] Optionally, the pre-ordered contract template can be adjusted using recommended information and legal knowledge to obtain a new contract template. However, this is not the only option. Recommended information can be used to filter legal knowledge content to extract more targeted legal information.

[0086] Alternatively, a large contract generation model can be used to directly generate contract templates based on recommended information and target legal knowledge. Compared to directly generating contract templates, adjusting a pre-defined contract template using recommended information and target legal knowledge allows for defining the contract format, supplementing key contract content not covered in the recommended information, and improving the efficiency of contract template generation.

[0087] According to embodiments of this disclosure, a predetermined contract template and legal knowledge information are obtained by utilizing a large contract generation model retrieval enhancement technique, and the legal knowledge information is further filtered based on recommendation information, thereby improving the accuracy, efficiency, and flexibility of contract template generation.

[0088] The preceding text explained how to generate a contract template. This template can be displayed as an initial template on the interactive interface, allowing the target user to further modify it. The following text explains how to determine the target contract template.

[0089] According to embodiments of this disclosure, when performing such Figure 2 Following operation S230, the AI-based contract processing method may further include: generating an edited contract in response to the editing operation on the contract template; inputting the contract type information and the edited contract into an evaluation model to obtain an evaluation result; and, if the evaluation result indicates that the edited contract lacks clauses matching the contract type information, revising the edited contract based on the evaluation result to obtain the target contract template.

[0090] Figure 6 A schematic diagram illustrating the generation and editing of an agreement according to an embodiment of this disclosure is shown.

[0091] like Figure 6 As shown, contract template 610 can be displayed in an editable state on the interactive interface. In response to editing operations performed on contract template 610 by the target object, such as deleting the ID numbers of Party A and Party B, an editable contract 620 is generated.

[0092] Editing operations can refer to deleting, modifying, or adding contract content.

[0093] Optionally, the edited contract can be used as the target contract template. However, it is not limited to this. Contract type information and the edited contract can also be input into the evaluation model to obtain evaluation results. If the evaluation results indicate that the edited contract conforms to the terms and conditions matching the contract type information, the edited contract will be used as the target contract template.

[0094] If the evaluation results indicate that the edited contract contains clauses that do not match the contract type information, the edited contract is revised based on the evaluation results to obtain the target contract template.

[0095] Optionally, the target contract template can be displayed as the final template on the interactive interface.

[0096] The revised contract template can also be displayed on the interactive interface for further editing by the target user.

[0097] The revised contract template can be displayed in an editable state on the interactive interface. Upon receiving a confirmation action for the revised contract template, the revised contract template will be used as the target contract template.

[0098] Upon receiving an edit request for the revised contract template, the edited contract is evaluated and corrected.

[0099] The above operations can be repeated until the target object is confirmed and the evaluation results indicate that the edited contract meets the terms and conditions, thus obtaining the target contract template.

[0100] This ensures that the target contract template meets the target audience's expectations, complies with the terms and conditions, and complies with the regulations.

[0101] The above section explained how to generate a target contract template. The following section will explain how to use the target contract template to generate a complete contract.

[0102] According to embodiments of this disclosure, when performing such Figure 2Following operation S230, the AI-based contract processing method may further include: obtaining the target contract in response to the completed information filling operation for the target contract template; extracting target content from the target contract using review indicator information that matches the contract type information; and inputting the target content and review indicator information into the review model to obtain the review result.

[0103] Optionally, the target contract template includes multiple fields to be filled. These fields may include, for example, fields involving specific object information such as "Party A", "Party B", "Delivery Method", and "Delivery Amount".

[0104] The target can upload a document with populated information. However, it's not limited to this. Information can also be populated in an editable state through the interactive interface, as long as the target contract with all fields to be filled is available.

[0105] A full review of the target contract is possible, but not limited to this; partial reviews are also possible. For example, multiple review indicators can be identified that match the contract type information. The target content corresponding to any review indicator can be extracted from the target contract. The target content and review indicator information are then input into the large-scale review model to obtain the review result for any given target content. Alternatively, multiple target contents corresponding one-to-one with multiple review indicator information can be extracted from the target contract. Each group of review contents, such as the target content and its corresponding review indicator information, is then input into the large-scale review model to obtain the review result for the target contract.

[0106] Based on contract type information, review indicators that match the contract type information are determined, thereby improving the targeting and flexibility of the review. Target content matching the review indicators is extracted from the target contract to filter out noisy information, thus improving the review accuracy of the large-scale review model.

[0107] According to embodiments of this disclosure, when performing such Figure 2 Prior to operation S210, the AI-based contract processing method may further include: determining, based on the review results, a prompt message for content in the target contract that failed the review. In response to a selection operation for content that failed the review, the prompt message for that content is displayed in a split-screen view of the interactive interface.

[0108] Optionally, if the review result indicates that the review has passed, the feedback information can be directly displayed on the interactive interface. If the review result indicates that the review has failed, a prompt message indicating that the review failed is displayed, along with the feedback message on the interactive interface. In response to the selection operation for the review-failed content in the target contract, the prompt message is displayed in a split-screen format on the interactive interface.

[0109] Optionally, the notification message may include at least one of the following: the reason for failure to pass the review, compliant content, or non-compliant content marked with a flag.

[0110] For example, content that fails review may include multiple contract contents. The content that fails review can be categorized using review indicator information. For instance, multiple contract contents in the target contract corresponding to each review indicator can be grouped into a community. If any part of this community fails review, then the entire community is determined to have failed review and is identified as content that fails review.

[0111] Figure 7 A schematic diagram illustrating the display of examination results according to another embodiment of this disclosure is shown.

[0112] like Figure 7 As shown, the interactive interface can be split into 700 screens, with the target contract displayed on the left side screen 710. The content that failed review for each review indicator in the target contract is grouped into a single unit; for example, clicking any part of the failed review content will select all failed review content. Optionally, non-compliant contract content within the failed review content can be highlighted, for example, by underlining it.

[0113] like Figure 7 As shown, the right-hand screen 720 of the interactive interface 700 displays a prompt message indicating that the content failed the review. The prompt message includes: the reason for the failure, compliant content, and non-compliant content marked with a deletion mark or bold text.

[0114] This increases the richness of the displayed information.

[0115] Figure 8 A flowchart illustrating an artificial intelligence-based contract processing method according to another embodiment of this disclosure is shown.

[0116] like Figure 8 As shown, based on the interactive operation information 810 related to the target object's intention to generate a contract, the contract type information 820 of the contract to be generated is determined. Based on the contract type information 820 of the contract to be generated, recommended information 830 describing the contract to be generated is displayed in the input box of the interactive interface.

[0117] like Figure 8 As shown, in response to the target object's determination operation based on recommendation information, recommendation information 830 and contract type information 820 are input into the large contract generation model M810 to obtain contract template 840. In response to the target object's editing operation on contract template 840, an edited contract 841 is generated.

[0118] like Figure 8As shown, contract type information 820 and edited contract 841 are input into the large evaluation model M820 to obtain evaluation result 850. If evaluation result 860 indicates that edited contract 841 conforms to the terms matching contract type information 820, then edited contract 841 is used as the target contract template 860. If evaluation result 850 indicates that edited contract 841 does not conform to the terms matching contract type information 820, then edited contract 841 is modified based on evaluation result 850 to obtain the target contract template 860.

[0119] like Figure 8 As shown, in response to the completion of the information filling operation for the target contract template 860, the target contract 870 is obtained. Using the review indicator information 880 that matches the contract type information 820, the target content 871 is extracted from the target contract 870. The target content 871 and the review indicator information 880 are input into the review big model M830 to obtain the review result 890.

[0120] Optionally, since the input data to be processed is all text, the contract generation model, evaluation model, and review model can each be a large language model. Different types of training samples can be used to train the open-source pre-trained large language model to obtain the contract generation model, evaluation model, and review model.

[0121] Figure 9 A block diagram of an artificial intelligence-based contract processing apparatus according to an embodiment of the present disclosure is shown schematically.

[0122] like Figure 9 As shown, the AI-based contract processing device 900 of this embodiment includes a first type determination module 910, a recommendation display module 920, and a template generation module 930.

[0123] The first type determination module 910 is used to determine the contract type information of the contract to be generated based on the interactive operation information of the target object related to the intention to generate the contract.

[0124] The recommendation display module 920 is used to display recommended information describing the contract to be generated in the input box of the interactive interface based on the contract type information of the contract to be generated.

[0125] The template generation module 930 is used to respond to the determination operation based on the recommendation information of the target object, input the recommendation information and contract type information into the large contract generation model, and obtain the contract template.

[0126] According to an embodiment of this disclosure, the first type determination module includes a type determination submodule.

[0127] The type determination submodule, upon the occurrence of a trigger event for displaying the interactive interface, determines the interactive operation information related to the intent to generate the contract from the set of interactive operation information generated by the target object on the front-end page. The trigger event includes operation events occurring on the front-end page that link to the interactive interface. Based on the intent recognition results of the interactive operation information, the contract type information of the contract to be generated is determined.

[0128] According to embodiments of this disclosure, the AI-based contract processing apparatus further includes a guidance module and a second type determination module.

[0129] The guidance module is used to display guidance information on the interactive interface when the contract type information cannot be determined based on the interactive operation information. This guidance information is used to guide the target user to input the contract type information.

[0130] The second type determination module is used to determine the contract type information in response to the target object's selection operation on the guiding information.

[0131] According to embodiments of this disclosure, the recommendation display module includes a recommendation submodule and a recommendation display submodule.

[0132] The recommendation submodule is used to determine the recommended word groups that match the contract type information from the candidate recommendation word set, and use them as recommendation information.

[0133] The Recommendation Display submodule is used to display recommendation information in an editable state in the input boxes of the interactive interface.

[0134] According to embodiments of this disclosure, the template generation module includes: a retrieval enhancement submodule, an extraction submodule, and an adjustment submodule.

[0135] The retrieval enhancement submodule is used to retrieve legal knowledge information that matches the contract type information and pre-defined contract templates that match the contract type information from the knowledge base using the contract generation big model.

[0136] The extraction submodule is used to extract legal knowledge information using the recommended information to obtain the target legal knowledge information.

[0137] The adjustment submodule is used to adjust the pre-defined contract template using recommended information and target legal knowledge information to obtain the contract template.

[0138] According to embodiments of this disclosure, the AI-based contract processing apparatus further includes an editing module, an evaluation module, and a template correction module.

[0139] The editing module is used to generate an edited contract in response to editing operations on the contract template.

[0140] The evaluation module is used to input contract type information and edited contracts into the evaluation model to obtain evaluation results.

[0141] The template correction module is used to correct the edited contract based on the evaluation results when the evaluation results indicate that there are clauses in the edited contract that do not match the contract type information, so as to obtain the target contract template.

[0142] According to embodiments of this disclosure, the AI-based contract processing apparatus further includes: a filling module, a content extraction module, and a review module.

[0143] The fill module is used to obtain the target contract in response to the completion of the information fill operation for the target contract template.

[0144] The content extraction module is used to extract target content from the target contract by utilizing review indicator information that matches the contract type information.

[0145] The review module is used to input the target content and review indicator information into the review model to obtain the review results.

[0146] According to embodiments of this disclosure, the AI-based contract processing apparatus further includes: a prompt confirmation module and a prompt display module.

[0147] The prompt confirmation module is used to determine the prompt message for the content in the target contract that failed the review based on the review results.

[0148] The prompt display module is used to respond to the selection operation of content that has failed the review by displaying prompt information in a split screen of the interactive interface. The prompt information includes at least one of the following: reason for failure to pass the review, compliant content, and non-compliant content marked with a flag.

[0149] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0150] According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform a method as described in the embodiments of the present disclosure.

[0151] Figure 10 A schematic block diagram of an artificial intelligence agent according to an embodiment of the present disclosure is shown.

[0152] In embodiments of this disclosure, such as Figure 10 As shown, the AI ​​agent 1000 may include an input module 1010, a processing module 1020, and an output module 1030.

[0153] Input module 1010 is used to receive input information.

[0154] The processing module 1020 is used to determine the target task based on the input information received by the input module, determine the large model based on the target task, and execute the artificial intelligence-based contract processing method provided in the embodiments of this disclosure by calling the large model.

[0155] Output module 1030 is used to output the output information obtained by the processing module.

[0156] According to embodiments of this disclosure, the input module 1010 is responsible for receiving or sensing information such as queries, requests, instructions, signals, or data from the outside world (e.g., users or the external environment), and converting it into a format that the AI ​​agent 1000 can understand and process. The input module 1010 is the primary link for the AI ​​agent 1000 to interact with the outside world, enabling the AI ​​agent 1000 to efficiently and accurately obtain necessary "sensory" information from the outside world and respond to this information.

[0157] In the example, input module 1010 can input the recommendation information and contract type information described above.

[0158] In the example, processing module 1020 is the core support for the AI ​​agent 1000's ability to handle complex tasks. Processing module 1020 can execute the AI-based contract processing method described above.

[0159] In the example, the performance of the processing module 1020 is closely related to the large model on which the AI ​​agent 1000 is based. To fully leverage the capabilities of the large model, the internal structure of the processing module 1020 can be designed to be highly configurable and scalable to handle various types of tasks and requirements in real-world scenarios.

[0160] In the example, after the AI ​​agent 1000 responds to the determination operation based on the recommendation information, the processing module 1020 can process the recommendation information and contract type information, obtain the contract template, and pass it to the output module 1030.

[0161] Understandably, while large-scale models possess excellent language understanding and generation capabilities, like humans, their ability to solve tasks is limited without the aid of any tools. However, once the AI ​​agent 1000 is given the ability to invoke tools, it can perform tasks such as using a calculator to complete mathematical calculations, using Python (a programming language) to perform data analysis, and using a search engine to generate weather forecasts.

[0162] In the example, output module 1030 can output a contract template and display it on the interactive interface.

[0163] The AI ​​agent 1000 according to the embodiments of this disclosure can simply and effectively improve the level of intelligence, as well as enhance flexibility and versatility.

[0164] According to embodiments of the present disclosure, a non-transitory computer-readable storage medium stores computer instructions, wherein the computer instructions are used to cause a computer to perform methods as described in embodiments of the present disclosure.

[0165] According to embodiments of the present disclosure, a computer program product includes a computer program that, when executed by a processor, implements the methods as described in embodiments of the present disclosure.

[0166] Figure 11 A schematic block diagram of an example electronic device 1100 that can be used to implement embodiments of the present disclosure is shown.

[0167] Electronic devices are intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0168] like Figure 11 As shown, device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in read-only memory (ROM) 1102 or a computer program loaded into random access memory (RAM) 1103 from storage unit 1108. The RAM 1103 may also store various programs and data required for the operation of device 1100. The computing unit 1101, ROM 1102, and RAM 1103 are interconnected via bus 1104. Input / output (I / O) interface 1105 is also connected to bus 1104.

[0169] Multiple components in device 1100 are connected to input / output (I / O) interface 1105, including: input unit 1106, such as a keyboard, mouse, etc.; output unit 1107, such as various types of displays, speakers, etc.; storage unit 1108, such as a disk, optical disk, etc.; and communication unit 1109, such as a network card, modem, wireless transceiver, etc. Communication unit 1109 allows device 1100 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0170] The computing unit 1101 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1101 performs the various methods and processes described above, such as AI-based contract processing or testing methods. For example, in some embodiments, the AI-based contract processing or testing methods may be implemented as computer software programs tangibly contained in a machine-readable medium, such as storage unit 1108. In some embodiments, part or all of the computer program may be loaded and / or installed on device 1100 via ROM 1102 and / or communication unit 1109. When the computer program is loaded into RAM 1103 and executed by the computing unit 1101, one or more steps of the AI-based contract processing or testing methods described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured by any other suitable means (e.g., by means of firmware) to perform an AI-based contract processing method or testing method.

[0171] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0172] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0173] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0174] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0175] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0176] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, distributed system servers, or servers incorporating blockchain technology.

[0177] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0178] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A contract processing method based on artificial intelligence, comprising: Based on the interactive operation information of the target object related to the intention of generating the contract, determine the contract type information of the contract to be generated; Based on the contract type information of the contract to be generated, recommended information describing the contract to be generated is displayed in the input box of the interactive interface; as well as In response to the determination operation of the target object based on the recommendation information, the recommendation information and the contract type information are input into the large contract generation model to obtain a contract template.

2. The method according to claim 1, wherein, The method for determining the contract type information of the contract to be generated based on the interactive operation information related to the intention to generate the contract of the target object includes: In the event of a triggering event for displaying the interactive interface, interactive operation information related to generating the contract intent is determined from the set of interactive operation information generated by the target object on the front-end page, wherein the triggering event includes operation events occurring on the front-end page that link to the interactive interface; and Based on the intent recognition results of the interactive operation information, the contract type information of the contract to be generated is determined.

3. The method according to claim 1 or 2, further comprising: If the contract type information cannot be determined based on the interactive operation information, guidance information is displayed on the interactive interface, wherein the guidance information is used to guide the target object to input the contract type information; and In response to the target object's selection operation on the guidance information, the contract type information is determined.

4. The method according to any one of claims 1 to 3, wherein, Based on the contract type information of the contract to be generated, recommended information describing the contract to be generated is displayed in the input box of the interactive interface, including: Determine the recommended word group that matches the contract type information from the candidate recommended word set, and use it as the recommended information; and The recommended information is displayed in an editable state in the input box of the interactive interface.

5. The method according to any one of claims 1 to 4, wherein, The step of inputting the recommendation information and the contract type information into the large contract generation model to obtain a contract template includes: The contract generation model is used to obtain legal knowledge information that matches the contract type information and a pre-defined contract template that matches the contract type information from the knowledge base. The legal knowledge information is extracted using the recommended information to obtain the target legal knowledge information; and The predetermined contract template is adjusted using the recommended information and the target legal knowledge information to obtain the contract template.

6. The method according to any one of claims 1 to 5, further comprising: In response to the editing operation on the contract template, an editable contract is generated; The contract type information and the edited contract are input into the large evaluation model to obtain the evaluation results; as well as If the evaluation results indicate that the edited contract contains clauses that do not match the contract type information, the edited contract is revised based on the evaluation results to obtain the target contract template.

7. The method according to claim 6, further comprising: Upon completion of the information filling operation for the target contract template, the target contract is obtained; Using review indicator information that matches the contract type information, target content is extracted from the target contract; as well as The target content and the review indicator information are input into the review model to obtain the review results.

8. The method according to claim 7, further comprising: Based on the review results, a prompt message is generated regarding the content of the target contract that failed the review. In response to the selection operation for the content that failed the review, the prompt information is displayed in a split screen of the interactive interface, wherein the prompt information includes at least one of the following: reason for failure to pass the review, compliant content, and non-compliant content marked with a flag.

9. A contract processing device based on artificial intelligence, comprising: The first type determination module is used to determine the contract type information of the contract to be generated based on the interactive operation information of the target object related to the intention to generate the contract. The recommendation display module is used to display recommended information describing the contract to be generated in the input box of the interactive interface based on the contract type information of the contract to be generated; as well as The template generation module is used to respond to the determination operation of the target object based on the recommendation information, input the recommendation information and the contract type information into the large contract generation model to obtain the contract template.

10. An intelligent agent of artificial intelligence, comprising: The input module is used to receive input information; The processing module is configured to determine a target task based on the input information received by the input module, determine a large model based on the target task, and execute the method of any one of claims 1 to 8 by calling the large model to obtain output information; as well as An output module is used to output the output information obtained by the processing module.

11. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 8.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 8.

13. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 8.

Images