CN117311726B - Intelligent legal contract generation method and device, electronic equipment and storage medium - Google Patents
Intelligent legal contract generation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117311726B CN117311726B CN202311405545.6A CN202311405545A CN117311726B CN 117311726 B CN117311726 B CN 117311726B CN 202311405545 A CN202311405545 A CN 202311405545A CN 117311726 B CN117311726 B CN 117311726B
- Authority
- CN
- China
- Prior art keywords
- contract
- intelligent
- legal
- chain
- intelligent legal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 114
- 238000011161 development Methods 0.000 claims abstract description 24
- 238000001514 detection method Methods 0.000 claims description 23
- 238000012545 processing Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000009966 trimming Methods 0.000 claims description 2
- 230000010354 integration Effects 0.000 claims 1
- 238000013507 mapping Methods 0.000 abstract description 11
- 230000008569 process Effects 0.000 description 25
- 238000010586 diagram Methods 0.000 description 15
- 238000004891 communication Methods 0.000 description 13
- 230000003340 mental effect Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/40—Transformation of program code
- G06F8/41—Compilation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/34—Graphical or visual programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Technology Law (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to an intelligent legal contract generation method, an intelligent legal contract generation device, electronic equipment and a storage medium, wherein the method comprises the following steps: based on a BPMN method and legal contracts, a BPMN model of an intelligent legal contract is built, key information of a target intelligent legal contract is extracted through the BPMN model of the intelligent legal contract, and structured thinking chain prompt information is generated; inputting the structured thinking chain prompt information into a large language model which is subjected to fine adjustment in advance, and generating intelligent legal contracts corresponding to the structured thinking chain prompt information; the generated intelligent legal contracts are run by utilizing the intelligent contract integrated development environment to verify the correctness of the grammar structure and the contract logic. Therefore, the problems that the existing intelligent legal contract generation method based on the mapping rule is limited by domain expert knowledge, and legal risks of intelligent legal contracts generated are large due to factors such as knowledge domain, understanding difference and the like are solved.
Description
Technical Field
The present application relates to the technical field of intelligent contracts, and in particular, to an intelligent legal contract generating method, an apparatus, an electronic device, and a storage medium.
Background
An intelligent legal contract is an intelligent contract oriented to legal contracts, applicable legal constraints, and comprises main legal contract elements such as contracting parties, contract terms and the like, wherein the contract terms are written in a programmable manner and stored on a blockchain or a distributed ledger. Intelligent legal contracts can be automatically executed according to contract terms and facts without intervention of intermediaries or third parties, thereby increasing transparency and trust of contract execution and reducing risk of disputes.
Conventional intelligent legal contract generation methods generally require close collaboration of experts in different fields, so that business process models and labeling (BPMN, business Process Model and Notation) methods are widely applied to modeling legal contract terms and logic structures in order to meet the requirements of non-software developers for designing and generating intelligent legal contracts, generating intelligent legal contract template structures, and then generating intelligent legal contracts based on custom mapping rules.
BPMN is used as a popular business process modeling method, an intuitive graphical modeling mode is provided, the technical threshold of programming is reduced, legal experts, technicians, business personnel and the like can design and understand the business process of contracts more easily, and the problem of collaborative development of intelligent legal contracts across fields is solved.
However, existing BPMN-based methods for generating intelligent legal contracts typically require well-defined mapping rules to translate intelligent legal contract templates into intelligent legal contracts. However, the domain coupling, clause difference, structural complexity and the like of legal contracts cause problems of applicability, expandability, high efficiency and the like of mapping rules. The dynamic property of the intelligent legal contract template further aggravates the problems of low intelligent legal contract generation efficiency, incomplete property, inaccuracy and the like based on the mapping rule, and development complexity and cost overhead are increased.
In summary, the existing intelligent legal contract generation method is limited by mapping rules defined based on domain expert knowledge, and legal risks caused by knowledge domain, understanding variability and the like exist. The territory, diversity, dynamic property and the like of contract clauses enable the construction and maintenance of mapping rules to be high in cost, low in efficiency and poor in expandability, and the legal contracts with complex logic structures are difficult to process, so that the application prospect of intelligent legal contracts is limited.
Disclosure of Invention
The application provides an intelligent legal contract generation method, an intelligent legal contract generation device, electronic equipment and a storage medium, and aims to solve the problems that an existing intelligent legal contract generation method based on mapping rules is limited by domain expert knowledge, and legal risks of intelligent legal contracts are large due to factors such as knowledge domain, understanding difference and the like.
An embodiment of a first aspect of the present application provides an intelligent legal contract generating method applied to a model fine tuning stage, including the following steps: obtaining a structured thinking chain type prompt information set by using a preset BPMN method, wherein the structured thinking chain type prompt information set comprises a flow structure and element information of the BPMN method; generating intelligent contracts corresponding to each structured thinking chain prompt element in the structured thinking chain prompt information set; and fine-tuning the target large language model based on the intelligent contracts and the structured thinking chain prompt information set to obtain a fine-tuned large language model so as to generate corresponding target intelligent contracts.
An embodiment of a second aspect of the present application provides an intelligent legal contract generating method applied to a model detection stage, including the following steps: based on a preset BPMN method and legal contracts, a BPMN model of an intelligent legal contract is built, key information of a target intelligent legal contract is extracted through the BPMN model of the intelligent legal contract, and structured thinking chain prompt information is generated according to the key information; inputting the structured thinking chain prompt information into a large language model after fine adjustment in advance, and generating a target intelligent legal contract corresponding to the structured thinking chain prompt information; and detecting the target intelligent legal contract by using a preset intelligent contract integrated development environment, and verifying the grammar structure of the target intelligent legal contract and the correctness of contract logic.
Optionally, in an embodiment of the present application, the extracting, by the BPMN model of the intelligent legal contract, key information of the target intelligent legal contract, and generating, according to the key information, structured thinking chain prompting information includes: and converting the key information of the target intelligent legal contract into the structured thinking chain prompt information based on an XML markup language format in a BPMN model of the intelligent legal contract.
Optionally, in an embodiment of the present application, the detecting the target smart legal contract using a preset smart contract integrated development environment, verifying the correctness of the grammar structure and the contract logic of the target smart legal contract includes: compiling the intelligent legal contracts by utilizing the preset intelligent contract integrated development environment to generate compiling results of the intelligent legal contracts; identifying whether the intelligent legal contract has the grammar error and the contract logic error according to the compiling result, and if the intelligent legal contract has the grammar error and the contract logic error, determining the positions of the grammar error and the contract logic error; and repairing the grammar error and the contract logic error according to the position and a preset solving strategy.
An embodiment of a third aspect of the present application provides an intelligent legal contract generating device, applied to a model fine tuning stage, including the following steps: the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a structured thinking chain type prompt information set by utilizing a preset BPMN method, wherein the structured thinking chain type prompt information set comprises a flow structure and element information of the BPMN method; the first generation module is used for generating intelligent contracts corresponding to each structured thinking chain prompt element in the structured thinking chain prompt information set; and the fine tuning module is used for fine tuning the target large language model based on the intelligent contracts and the structured thinking chain prompt information set to obtain the fine-tuned large language model so as to generate corresponding target intelligent contracts.
An embodiment of a fourth aspect of the present application provides an intelligent legal contract generating device, applied to a model detection stage, including the following steps: the construction module is used for constructing a BPMN model of the intelligent legal contract based on a preset BPMN method and the legal contract, extracting key information of a target intelligent legal contract through the BPMN model of the intelligent legal contract, and generating structural thinking chain prompt information according to the key information; the second generation module is used for inputting the structured thinking chain prompt information into a large language model which is subjected to fine adjustment in advance, and generating a target intelligent legal contract corresponding to the structured thinking chain prompt information; the detection module is used for detecting the target intelligent legal contract by utilizing a preset intelligent contract integrated development environment and verifying the grammar structure and contract logic correctness of the target intelligent legal contract.
Optionally, in one embodiment of the present application, the building block includes: the conversion unit is used for converting the key information of the target intelligent legal contract into the structured thinking chain prompt information based on an XML markup language format in the BPMN model of the intelligent legal contract.
Optionally, in one embodiment of the present application, the detection module includes: the compiling unit is used for compiling the intelligent legal contracts by utilizing the preset intelligent contract integrated development environment to generate compiling results of the intelligent legal contracts; the identification unit is used for identifying whether the intelligent legal contract has the grammar error and the contract logic error according to the compiling result, and if the intelligent legal contract has the grammar error and the contract logic error, determining the positions of the grammar error and the contract logic error; and the repairing unit is used for repairing the grammar error and the contract logic error according to the position and a preset solving strategy.
An embodiment of a fifth aspect of the present application provides an electronic device, including: the system comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the program to realize the intelligent legal contract generation method according to the embodiment.
Embodiments of a sixth aspect of the present application provide a computer-readable storage medium storing a computer program which, when executed by a processor, implements the intelligent legal contract generation method as above.
Thus, embodiments of the present application have the following benefits:
the embodiment of the application can construct a BPMN model of the intelligent legal contract based on the BPMN method and the legal contract, extract key information of the target intelligent legal contract through the BPMN model of the intelligent legal contract, and generate structural thinking chain prompt information according to the key information; inputting the structured thinking chain prompt information into a large language model which is subjected to fine adjustment in advance, and generating intelligent legal contracts corresponding to the structured thinking chain prompt information; and detecting intelligent legal contracts by utilizing a preset intelligent contract integrated development environment, and verifying the grammar structure and contract logic correctness of the intelligent legal contracts. The method and the device adapt to legal contracts with complex logic by combining a BPMN method and a large language model technology, so that the requirements of various legal contracts are met with automatic flow, low cost and high generation efficiency. Therefore, the problems that the existing intelligent legal contract generation method based on the mapping rule is limited by domain expert knowledge, and legal risks of intelligent legal contracts generated are large due to factors such as knowledge domain, understanding difference and the like are solved.
Additional aspects and advantages of the application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
FIG. 1 is a flow chart of a method for intelligent legal contract generation for use in a model tuning phase, provided in accordance with an embodiment of the present application;
FIG. 2 is a diagram illustrating a BPMN order execution structure-hint information-intelligent contract (in the example of a solubility code) according to one embodiment of the present application;
FIG. 3 is a schematic diagram of a BPMN parallel gateway structure-hint information-intelligent contract (taking a solubility code as an example) according to one embodiment of the present application;
FIG. 4 is a diagram of an example BPMN exclusive gateway structure-hint information-Intelligent contract (taking a solubility code as an example) provided by an embodiment of the present application;
FIG. 5 is a flow chart of a method of intelligent legal contract generation applied to a model detection phase, provided in accordance with an embodiment of the present application;
FIG. 6 is a schematic diagram of basic elements of a BPMN according to one embodiment of the present application;
FIG. 7 is a schematic diagram of an XML language representation BPMN model according to one embodiment of the present application;
FIG. 8 is a schematic diagram of the execution logic of a method for generating intelligent legal contracts for use in a fine model adjustment phase and a model detection phase according to one embodiment of the present application;
FIG. 9 is an exemplary diagram of an intelligent legal contract generation apparatus applied to a model tuning stage in accordance with an embodiment of the present application;
FIG. 10 is an exemplary diagram of an intelligent legal contract generation apparatus applied to a model detection phase in accordance with an embodiment of the present application;
fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
10-an intelligent legal contract generation device applied to a model fine adjustment stage and 20-an intelligent legal contract generation device applied to a model detection stage; 101-an acquisition module, 102-a first generation module and 103-a fine adjustment module; 201-a construction module, 202-a second generation module and 203-a detection module; 1101-memory, 1102-processor, 1103-communication interface.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of explaining the present application and are not to be construed as limiting the present application.
The following describes an intelligent legal contract generation method, an intelligent legal contract generation device, electronic equipment and a storage medium according to the embodiments of the application with reference to the accompanying drawings. Aiming at the problems mentioned in the background art, the application provides an intelligent legal contract generation method, wherein in the method, a BPMN model of an intelligent legal contract is built based on a BPMN method and legal contracts, key information of a target intelligent legal contract is extracted through the BPMN model of the intelligent legal contract, and structured thinking chain prompt information is generated according to the key information; inputting the structured thinking chain prompt information into a large language model which is subjected to fine adjustment in advance, and generating intelligent legal contracts corresponding to the structured thinking chain prompt information; and detecting the intelligent legal contracts by utilizing a preset intelligent contract integrated development environment, and verifying the grammar structure of the intelligent legal contracts and the correctness of contract logic. The method and the device adapt to legal contracts with complex logic by combining a BPMN method and a large language model technology, so that the requirements of various legal contracts are met with automatic flow, low cost and high generation efficiency. Therefore, the problems that the existing intelligent legal contract generation method based on the mapping rule is limited by domain expert knowledge, and legal risks of intelligent legal contracts generated are large due to factors such as knowledge domain, understanding difference and the like are solved.
Specifically, fig. 1 is a flowchart of an intelligent legal contract generating method applied to a model fine tuning stage according to an embodiment of the present application.
As shown in fig. 1, the intelligent legal contract generation method includes the steps of:
in step S101, a preset BPMN method is used to obtain a structured mind-chain prompt information set, where the structured mind-chain prompt information set includes a flow structure and element information of the BPMN method.
In the actual implementation process, a person skilled in the art can first deeply analyze a series of rules defined by the BPMN method, understand the defined elements, events, gateways and connecting lines, and understand the starting point, ending point, decision point, etc. of the represented flow.
Furthermore, according to the task driving principle, the embodiments of the present application can map the element relationships defined in the BPMN to key information in legal contracts, for example, map the communication relationships and execution logic between flows to the execution terms and conditions of the contracts, so as to obtain various structured thinking chain prompt information, and construct a structured thinking chain prompt information set.
The structured thinking chain prompt information refers to each step, condition and logic in the business process represented by the BPMN, and is structured into a coherent thinking chain. Therefore, the prompt information has a certain hierarchical structure, can guide the large language model to understand the flow rules of different layers, and can clearly show the relation and dependence among all parts in the flow.
It should be noted that, in the embodiment of the present application, a person skilled in the art may control branching, merging and decision in a service flow represented by a BPMN through a gateway element of the BPMN, where the gateway defines a flow direction between different paths, and mainly includes an exclusive gateway, a parallel gateway, a containing gateway, and an event-based gateway, and fig. 2, 3, and 4 provide three BPMN model-hint information-intelligent contract (taking a stability code as an example) matching example diagrams, which respectively represent a sequential execution structure, a parallel gateway structure, and an exclusive gateway structure of the BPMN model, so as to effectively help a designer of the BPMN model introduce conditions, judgment, and diversified behaviors in the flow.
In step S102, an intelligent contract corresponding to each structured mental chain hint element in the structured mental chain hint information set is generated.
In step S103, the target large language model is trimmed based on the intelligent contracts and the structured thinking chain prompt information set, so as to obtain the trimmed large language model, so as to generate corresponding target intelligent contracts.
After the structured mind chain type prompt information set is obtained, the embodiment of the application can generate intelligent contracts corresponding to each structured mind chain type prompt information, such as a solubility code and the like, aiming at each structured mind chain type prompt information in the designed structured mind chain type prompt information set.
Further, the embodiment of the application can be used for fine-tuning a preset large language model according to each prompt and the structured thinking chain prompt information and the corresponding intelligent contract thereof as a training data set.
The advanced programming languages developed for intelligent contracts such as the solubility should conform to the programming standard and grammar rule of intelligent legal contracts, and the logic consistency between the structured chain-type prompt information and the corresponding codes should be ensured, so that the structured chain-type prompt information can clearly guide a large language model to generate corresponding intelligent contracts.
In addition, the large language model adopts a huge data set and a deep learning technology to train the language model in the natural language processing field, and the model usually has billions or even billions of parameters, can learn and understand large-scale language data including grammar, semantics, logic and the like, can generate a large amount of codes in a short time, remarkably improves the generation efficiency, and has strong text understanding and generation capability.
It can be understood that, in the embodiment of the present application, a series of rules defined by the BPMN method are deeply analyzed to generate specific prompt information capable of guiding the large model to generate the intelligent contract, and the prompt information and the corresponding intelligent contract form a huge corpus, so as to fine tune the preset large language model, so that the preset large language model can understand and learn the specific rules and structures executed by the process, and the generated intelligent contract is more accurate and consistent, and provides support for the subsequent intelligent legal contract generation.
According to the intelligent legal contract generation method applied to the model fine tuning stage provided by the embodiment of the application, a structured thinking chain prompt information set is obtained through a series of rules defined by a BPMN method, wherein the structured thinking chain prompt information set comprises element information and a flow structure defined in the rules; generating intelligent contracts corresponding to each structured thinking chain prompt element in the structured thinking chain prompt information set; and fine-tuning the target large language model based on the intelligent contracts and the structured thinking chain prompt information set to obtain the fine-tuned large language model so as to generate corresponding target intelligent contracts. The method and the device adapt to legal contracts with complex logic by combining a BPMN method and a large language model technology, so that the requirements of various legal contracts are met with automatic flow, low cost and high generation efficiency.
FIG. 5 is a flowchart of an intelligent legal contract generation method applied to a model detection stage according to an embodiment of the present application.
As shown in fig. 5, the intelligent legal contract generation method includes the steps of:
in step S501, a BPMN model of an intelligent legal contract is constructed based on a preset BPMN method and legal contracts, key information of a target intelligent legal contract is extracted through the BPMN model of the intelligent legal contract, and structured thinking chain prompt information is generated according to the key information.
In the model detection stage, the embodiment of the application needs to analyze the flow and terms of legal contracts first, model information such as various stages, conditions, limitations and the like of the legal contracts by using a BPMN method to obtain a BPMN model of the intelligent legal contracts, and extract key information in target intelligent legal contracts according to the BPMN model of the intelligent legal contracts, wherein the key information comprises communication relations among contracts, contract terms, conditions, principal information and the like, so as to generate structured thinking chain prompt information.
It should be appreciated by those skilled in the art that the BPMN method provides a set of standard symbols representing elements of activities, events, gateways, connections, etc. in a business process, which may be used to describe various aspects of the business process, thereby helping one to better understand, analyze, and optimize the business process.
Therefore, the embodiment of the application can graphically model the legal contracts represented by natural language as business processes, automatically extract the generated structured processes and contract key information in the BPMN model of the intelligent legal contracts, and construct the structured thinking chain prompt information, thereby improving the generation efficiency of the prompt information, reducing the interference of human factors and ensuring the accuracy and the integrity of the prompt information.
Optionally, in one embodiment of the present application, extracting key information of the target intelligent legal contract through a BPMN model of the intelligent legal contract, and generating the structured thinking chain prompt information according to the key information includes: and converting the key information of the target intelligent legal contract into the structured thinking chain prompt information based on the XML markup language format in the BPMN model of the intelligent legal contract.
It should be noted that, before extracting the key information of the objective intelligent legal contract through the BPMN model of the intelligent legal contract, the embodiments of the present application also need to determine the type of contract (such as a buy-sell contract, a lease contract, an auction contract, etc.), understand the main objective of the contract and the expectations of both parties of the transaction, and determine the purpose of the legal contract and the involved business processes, including roles of the parties, the sequence of activities, decision points, information transfer, etc.
In addition, embodiments of the present application may also utilize a series of rules defined by the BPMN method to model the business process of legal contracts into a flow chart in which various symbols may be used to represent activities, events, gateways, connections, etc., as shown in fig. 6, to clearly reveal the process logic of the contract.
Wherein the BPMN is a standardized symbol and method for graphically representing and describing business processes, formulated and maintained by business process management initiative organizations, the BPMN standardization ensuring a common understanding of the flow diagrams among different organizations and people.
Further, embodiments of the present application may analyze and extract key information of a target intelligent legal contract from a BPMN model of the intelligent legal contract, including the order of the contract flow, conditions, triggering events, and other critical parts of the contract execution.
Secondly, the embodiment of the application can utilize XML markup language format in the BPMN model of the intelligent legal contract to convert the key information of the extracted target intelligent legal contract into structured and easily understood structured thinking chain prompt information, and the prompt information can accurately express the logic and conditions of the contract so as to guide a large language model to generate the corresponding intelligent legal contract.
In the actual execution process, the embodiment of the application can automatically generate the prompt information by extracting necessary contract information from the XML markup language format file of the BPMN model of the intelligent legal contract through writing the script file in advance, so that the automatic data extraction operation can effectively reduce the workload of manual extraction of a user and improve the intelligent degree and the use convenience of the system.
Wherein the BPMN is a standardized symbol and method for graphically representing and describing a business process, which defines a set of graphic symbols and XML language to describe individual elements in the business process and relationships between individual elements, the XML language being a markup language for storing and transmitting data, which can describe the structure and meaning of the data using tags.
Fig. 7 is an exemplary diagram representing a BPMN model in XML language. As shown in FIG. 7, the < process > element defines a simple flow including a start event, a task, and an end event; the < sequence flow > element defines the sequential flow between the individual elements; the graphic symbols of the BPMN model may be represented in XML language with corresponding elements such as < startEvent >, < task >, < endEvent >, etc.; meanwhile, the graphic position and size information of the BPMN model is defined by a < BPMNShape > element, and the connection line between flows is defined by a < bpmnndi: BPMNEdge > element.
Therefore, the embodiment of the application can automatically extract the key information from the BPMN model of the intelligent legal contract, customize according to specific contract requirements and convert the key information into the structured thinking chain prompt information, thereby providing reliable data support and basis for generating the intelligent legal contract which is more flexible and accords with specific scenes.
In step S502, the structured mind chain prompt information is input into the pre-trimmed large language model, and a target intelligent legal contract corresponding to the structured mind chain prompt information is generated.
After the structured mental chain prompt information is generated, further, the embodiment of the application can input the generated structured mental chain prompt information into a large language model which is finely tuned in advance, and analyze logic, conditions and key elements in each structured mental chain prompt information through the large language model, as shown in fig. 8, so as to accurately generate intelligent legal contracts corresponding to each structured mental chain prompt information.
Therefore, the embodiment of the application can generate the structured thinking chain prompt information by utilizing the communication relation and the execution logic among all the processes in the BPMN model of the intelligent legal contract, so that the trimmed large language model can understand the rules and logic of the intelligent legal contract, and is easier to adapt to the continuously changing requirements and contract logic so as to generate the intelligent legal contract with more intelligence.
In step S503, the target intelligent legal contract is detected by using the preset intelligent contract integrated development environment, and the grammar structure and contract logic correctness of the target intelligent legal contract are verified.
After the intelligent legal contracts corresponding to the structured thinking chain prompt information are generated, further, the embodiment of the application can also use intelligent contract integrated development environments such as a Remix platform to carry out inspection and test on the generated intelligent legal contracts.
Optionally, in one embodiment of the present application, detecting the target smart legal contract using the preset smart contract integrated development environment, verifying the correctness of the grammar structure and the contract logic of the target smart legal contract includes: compiling the intelligent legal contracts by utilizing a preset intelligent contract integrated development environment to generate compiling results of the intelligent legal contracts; identifying whether the intelligent legal contract has grammar errors and contract logic errors according to the compiling result, and if the intelligent legal contract has the grammar errors and the contract logic errors, determining the positions of the grammar errors and the contract logic errors; and repairing grammar errors and contract logic errors according to the positions and the preset solving strategies.
As an implementation manner, the embodiment of the application can create a new project on the Remix platform and upload intelligent legal contracts written in the resolution programming language to the Remix platform; and the compiler of the Remix platform is utilized to compile the uploaded intelligent legal contracts, the compiler can check grammar errors and contract logic problems in the intelligent legal contracts, and if grammar errors or contract logic errors exist or both errors exist, remix can provide specific error information (reasons, solutions and the like of the errors) of each error and specific positions of error codes.
Secondly, the embodiment of the application can also use a static analysis tool plug-in of the Remix platform to check potential problems in codes, including security holes, code complexity and other aspects, so as to help discover possible problems in intelligent legal contracts and prevent potential errors in advance; in addition, the Remix platform can also use built-in simulated transaction and test functions to simulate the execution situation of the intelligent legal contract so as to help verify the behavior of the intelligent legal contract under different conditions and ensure the on-schedule execution of the intelligent legal contract.
At the same time, the Remix platform may also provide the functionality of estimating the Gas costs required for contract execution, so that the costs required to deploy and execute intelligent legal contracts can be appreciated.
It can be understood that the communication relation and execution logic between each flow in the BPMN model of the intelligent legal contract are utilized to generate the structured thinking chain prompt, the trimmed large language model is used for understanding rules and logic of the contract to generate the intelligent legal contract, and the intelligent legal contract integrated development environment such as a Remix platform can be used for carrying out test on the generated intelligent legal contract, so that the dependence on fixed mapping rules is reduced, the structured thinking chain prompt information can be customized according to specific contract requirements, the flexibility of the generated code is improved, and the generated code better meets the requirements of specific scenes.
According to the intelligent legal contract generation method applied to the model detection stage, a BPMN model of the intelligent legal contract is built based on a BPMN method and legal contracts, key information of a target intelligent legal contract is extracted through the BPMN model of the intelligent legal contract, and structured thinking chain prompt information is generated according to the key information; inputting the structured thinking chain prompt information into a large language model which is subjected to fine adjustment in advance, and generating intelligent legal contracts corresponding to the structured thinking chain prompt information; and detecting the intelligent legal contracts by utilizing a preset intelligent contract integrated development environment, and verifying the grammar structure of the intelligent legal contracts and the correctness of contract logic. The method and the device adapt to legal contracts with complex logic by combining a BPMN method and a large language model technology, so that the requirements of various legal contracts are met with automatic flow, low cost and high generation efficiency.
Next, an intelligent legal contract generating apparatus according to an embodiment of the present application will be described with reference to the drawings.
FIG. 9 is a block diagram of an intelligent legal contract generation apparatus applied to a model tuning stage according to an embodiment of the present application.
As shown in fig. 9, the intelligent legal contract generating apparatus 10 includes: an acquisition module 101, a first generation module 102 and a fine tuning module 103.
The obtaining module 101 is configured to obtain a structured mind chain type prompt information set by using a preset BPMN method, where the structured mind chain type prompt information set includes a flow structure and element information of the BPMN method.
The first generation module 102 is configured to generate an intelligent contract corresponding to each structured mental chaining hint element in the structured mental chaining hint information set.
And the fine tuning module 103 is configured to fine tune the target large language model based on the intelligent contracts and the structured thinking chain prompt information set, so as to obtain the fine-tuned large language model, so as to generate corresponding target intelligent contracts.
The intelligent legal contract generation device applied to the model fine tuning stage provided by the embodiment of the application comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a structured thinking chain type prompt information set by utilizing a series of rules defined by a BPMN method, and the structured thinking chain type prompt information set comprises element information and a flow structure defined in the rules; the first generation module is used for generating intelligent contracts corresponding to each structured thinking chain prompt element in the structured thinking chain prompt information set; and the fine tuning module is used for fine tuning the target large language model based on the intelligent contracts and the structured thinking chain prompt information set to obtain the fine-tuned large language model so as to generate corresponding target intelligent contracts. The method and the device adapt to legal contracts with complex logic by combining a BPMN method and a large language model technology, so that the requirements of various legal contracts are met with automatic flow, low cost and high generation efficiency.
FIG. 10 is a block diagram of an intelligent legal contract generation apparatus, applied to a model detection stage, according to an embodiment of the present application.
As shown in fig. 10, the intelligent legal contract generating apparatus 20 applied to the model detection stage includes: a construction module 201, a second generation module 202 and a detection module 203.
The construction module 201 is configured to construct a BPMN model of an intelligent legal contract based on a preset BPMN method and legal contracts, extract key information of a target intelligent legal contract through the BPMN model of the intelligent legal contract, and generate structured thinking chain prompt information according to the key information.
The second generation module 202 is configured to input the structured mind chain type prompt information into the pre-trimmed large language model, and generate a target intelligent legal contract corresponding to the structured mind chain type prompt information.
The detection module 203 is configured to detect a target intelligent legal contract by using a preset intelligent contract integrated development environment, and verify the grammar structure and the correctness of the contract logic of the target intelligent legal contract.
Optionally, in one embodiment of the present application, the building module 201 includes: the conversion unit is used for converting the key information of the target intelligent legal contract into the structured thinking chain prompt information based on the XML markup language format in the BPMN model of the intelligent legal contract.
Optionally, in one embodiment of the present application, the detection module 203 includes: a compiling unit, an identifying unit and a repairing unit.
The compiling unit is used for compiling the intelligent legal contracts by utilizing a preset intelligent contract integrated development environment and generating compiling results of the intelligent legal contracts.
And the identification unit is used for identifying whether the intelligent legal contract has grammar errors and contract logic errors according to the compiling result, and determining the positions of the grammar errors and the contract logic errors if the intelligent legal contract has the grammar errors and the contract logic errors.
And the repairing unit is used for repairing grammar errors and contract logic errors according to the positions and the preset solving strategies.
It should be noted that the foregoing explanation of the embodiment of the method for generating an intelligent legal contract is also applicable to the intelligent legal contract generating device of this embodiment, and will not be repeated here.
The intelligent legal contract generation device applied to the model detection stage provided by the embodiment of the application comprises a construction module, a control module and a control module, wherein the construction module is used for constructing a BPMN model of an intelligent legal contract based on a BPMN method and the legal contract, extracting key information of a target intelligent legal contract through the BPMN model of the intelligent legal contract, and generating structural thinking chain prompt information according to the key information; the second generation module is used for inputting the structured thinking chain prompt information into the large language model after the preliminary trimming to generate intelligent legal contracts corresponding to the structured thinking chain prompt information; the detection module is used for detecting the intelligent legal contracts by utilizing a preset intelligent contract integrated development environment and verifying the grammar structure of the intelligent legal contracts and the correctness of contract logic. The method and the device adapt to legal contracts with complex logic by combining a BPMN method and a large language model technology, so that the requirements of various legal contracts are met with automatic flow, low cost and high generation efficiency.
Fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device may include:
memory 1101, processor 1102, and a computer program stored on memory 1101 and executable on processor 1102.
The processor 1102 implements the intelligent legal contract generation method provided in the above embodiments when executing a program.
Further, the electronic device further includes:
a communication interface 1103 for communication between the memory 1101 and the processor 1102.
Memory 1101 for storing a computer program executable on processor 1102.
The memory 1101 may include a high-speed RAM memory or may further include a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory.
If the memory 1101, the processor 1102, and the communication interface 1103 are implemented independently, the communication interface 1103, the memory 1101, and the processor 1102 may be connected to each other through a bus and perform communication with each other. The bus may be an industry standard architecture (Industry Standard Architecture, abbreviated ISA) bus, an external device interconnect (Peripheral Component, abbreviated PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, abbreviated EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in FIG. 11, but not only one bus or one type of bus.
Alternatively, in a specific implementation, if the memory 1101, the processor 1102, and the communication interface 1103 are integrated on a chip, the memory 1101, the processor 1102, and the communication interface 1103 may perform communication with each other through internal interfaces.
The processor 1102 may be a central processing unit (Central Processing Unit, abbreviated as CPU) or an application specific integrated circuit (Application Specific Integrated Circuit, abbreviated as ASIC) or one or more integrated circuits configured to implement embodiments of the present application.
Embodiments of the present application also provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the intelligent legal contract generation method as above.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or N embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "N" is at least two, such as two, three, etc., unless explicitly defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order from that shown or discussed, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present application.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or N wires, a portable computer cartridge (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. Although embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.
Claims (8)
1. An intelligent legal contract generation method is applied to a model fine tuning stage and is characterized by comprising the following steps:
obtaining a structured thinking chain type prompt information set by using a preset BPMN method, wherein the structured thinking chain type prompt information set comprises a flow structure and element information of the BPMN method;
generating intelligent contracts corresponding to each structured thinking chain prompt element in the structured thinking chain prompt information set;
trimming the target large language model based on the intelligent contracts and the structured thinking chain prompt information set to obtain a trimmed large language model so as to generate corresponding target intelligent contracts;
the intelligent legal contract generation method is applied to a model detection stage and comprises the following steps of:
Based on the preset BPMN method and legal contracts, a BPMN model of an intelligent legal contract is constructed, key information of a target intelligent legal contract is extracted through the BPMN model of the intelligent legal contract, and structured thinking chain prompt information is generated according to the key information;
inputting the structured thinking chain prompt information into a large language model after fine adjustment in advance, and generating a target intelligent legal contract corresponding to the structured thinking chain prompt information;
and detecting the target intelligent legal contract by using a preset intelligent contract integrated development environment, and verifying the grammar structure of the target intelligent legal contract and the correctness of contract logic.
2. The method according to claim 1, wherein extracting key information of a target intelligent legal contract through the BPMN model of the intelligent legal contract and generating structured thinking chain prompt information according to the key information comprises:
and converting the key information of the target intelligent legal contract into the structured thinking chain prompt information based on an XML markup language format in a BPMN model of the intelligent legal contract.
3. The method of claim 1, wherein the detecting the target smart legal contract using a preset smart contract integration development environment, verifying the correctness of the grammar structure and contract logic of the target smart legal contract, comprises:
Compiling the intelligent legal contracts by utilizing the preset intelligent contract integrated development environment to generate compiling results of the intelligent legal contracts;
identifying whether the intelligent legal contract has grammar errors and contract logic errors according to the compiling result, and if the intelligent legal contract has the grammar errors and the contract logic errors, determining the positions of the grammar errors and the contract logic errors;
and repairing the grammar error and the contract logic error according to the position and a preset solving strategy.
4. An intelligent legal contract generation device applied to a model fine tuning stage, comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a structured thinking chain type prompt information set by utilizing a preset BPMN method, wherein the structured thinking chain type prompt information set comprises a flow structure and element information of the BPMN method;
the first generation module is used for generating intelligent contracts corresponding to each structured thinking chain prompt element in the structured thinking chain prompt information set;
the fine tuning module is used for fine tuning the target large language model based on the intelligent contracts and the structured thinking chain prompt information set to obtain a fine-tuned large language model so as to generate corresponding target intelligent contracts;
The intelligent legal contract generation device is applied to a model detection stage, and comprises the following components:
the construction module is used for constructing a BPMN model of an intelligent legal contract based on the preset BPMN method and the legal contract, extracting key information of a target intelligent legal contract through the BPMN model of the intelligent legal contract, and generating structural thinking chain prompt information according to the key information;
the second generation module is used for inputting the structured thinking chain prompt information into a large language model which is subjected to fine adjustment in advance, and generating a target intelligent legal contract corresponding to the structured thinking chain prompt information;
the detection module is used for detecting the target intelligent legal contract by utilizing a preset intelligent contract integrated development environment and verifying the grammar structure and contract logic correctness of the target intelligent legal contract.
5. The apparatus of claim 4, wherein the build module comprises:
the conversion unit is used for converting the key information of the target intelligent legal contract into the structured thinking chain prompt information based on an XML markup language format in the BPMN model of the intelligent legal contract.
6. The apparatus of claim 4, wherein the detection module comprises:
The compiling unit is used for compiling the intelligent legal contracts by utilizing the preset intelligent contract integrated development environment to generate compiling results of the intelligent legal contracts;
the identification unit is used for identifying whether the intelligent legal contract has grammar errors and contract logic errors according to the compiling result, and if the intelligent legal contract has the grammar errors and the contract logic errors, determining the positions of the grammar errors and the contract logic errors;
and the repairing unit is used for repairing the grammar error and the contract logic error according to the position and a preset solving strategy.
7. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the intelligent legal contract generation method of any of claims 1-3.
8. A computer-readable storage medium having stored thereon a computer program, characterized in that the program is executed by a processor for implementing the intelligent legal contract generation method as claimed in any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311405545.6A CN117311726B (en) | 2023-10-26 | 2023-10-26 | Intelligent legal contract generation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311405545.6A CN117311726B (en) | 2023-10-26 | 2023-10-26 | Intelligent legal contract generation method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117311726A CN117311726A (en) | 2023-12-29 |
| CN117311726B true CN117311726B (en) | 2024-04-09 |
Family
ID=89262117
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311405545.6A Active CN117311726B (en) | 2023-10-26 | 2023-10-26 | Intelligent legal contract generation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117311726B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110555320A (en) * | 2019-08-21 | 2019-12-10 | 杭州趣链科技有限公司 | formal verification method based on block chain deposit-verification intelligent contract |
| CN111695805A (en) * | 2020-06-10 | 2020-09-22 | 北京航空航天大学 | Intelligent contract model construction method and system for legal contracts |
| CN113448592A (en) * | 2021-02-08 | 2021-09-28 | 北京科技大学 | Intelligent legal contract generation method based on contract text markup language |
| CN115268847A (en) * | 2022-07-18 | 2022-11-01 | 中国工商银行股份有限公司 | Block chain intelligent contract generation method and device and electronic equipment |
| WO2022234913A1 (en) * | 2021-05-04 | 2022-11-10 | 인제대학교 산학협력단 | Method for generating process model of plant procedure document, and system therefor |
| CN115878112A (en) * | 2022-11-15 | 2023-03-31 | 哈尔滨工业大学 | Multi-party complex business agreement intelligent contract generating system and generating method thereof |
| CN116775879A (en) * | 2023-06-29 | 2023-09-19 | 浙江中控技术股份有限公司 | Fine tuning training method of large language model, contract risk review method and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7805302B2 (en) * | 2002-05-20 | 2010-09-28 | Microsoft Corporation | Applying a structured language model to information extraction |
| US11257073B2 (en) * | 2018-01-31 | 2022-02-22 | Salesforce.Com, Inc. | Systems, methods, and apparatuses for implementing machine learning models for smart contracts using distributed ledger technologies in a cloud based computing environment |
-
2023
- 2023-10-26 CN CN202311405545.6A patent/CN117311726B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110555320A (en) * | 2019-08-21 | 2019-12-10 | 杭州趣链科技有限公司 | formal verification method based on block chain deposit-verification intelligent contract |
| CN111695805A (en) * | 2020-06-10 | 2020-09-22 | 北京航空航天大学 | Intelligent contract model construction method and system for legal contracts |
| CN113448592A (en) * | 2021-02-08 | 2021-09-28 | 北京科技大学 | Intelligent legal contract generation method based on contract text markup language |
| WO2022234913A1 (en) * | 2021-05-04 | 2022-11-10 | 인제대학교 산학협력단 | Method for generating process model of plant procedure document, and system therefor |
| CN115268847A (en) * | 2022-07-18 | 2022-11-01 | 中国工商银行股份有限公司 | Block chain intelligent contract generation method and device and electronic equipment |
| CN115878112A (en) * | 2022-11-15 | 2023-03-31 | 哈尔滨工业大学 | Multi-party complex business agreement intelligent contract generating system and generating method thereof |
| CN116775879A (en) * | 2023-06-29 | 2023-09-19 | 浙江中控技术股份有限公司 | Fine tuning training method of large language model, contract risk review method and system |
Non-Patent Citations (2)
| Title |
|---|
| VulHunter: Hunting Vulnerable Smart Contracts at EVM Bytecode-Level via Multiple Instance Learning;Zhaoxuan Li 等;IEEE Transactions on Software Engineering;20230922;第49卷(第11期);全文 * |
| 面向信用服务的BPMN智能合约范式研究;李洁 等;信息安全研究;20220531;第8卷(第5期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117311726A (en) | 2023-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lúcio et al. | Model transformation intents and their properties | |
| Küster et al. | Validation of model transformations–first experiences using a white box approach | |
| US9594543B2 (en) | Activity diagram model-based system behavior simulation method | |
| EP2546738A1 (en) | Systems and methods for verifying model equivalence | |
| US20030125920A1 (en) | LSI design verification apparatus, LSI design verification method, and LSI design verification program | |
| CN104965956A (en) | RUCM based demand verification method | |
| Debreceni et al. | Automated model merge by design space exploration | |
| CN103593335A (en) | Chinese semantic proofreading method based on ontology consistency verification and reasoning | |
| Semeráth et al. | Graph constraint evaluation over partial models by constraint rewriting | |
| KR20060070609A (en) | Apparatus and method for product-line architecture description and verification | |
| Abdelnabi et al. | Generating uml class diagram from natural language requirements: A survey of approaches and techniques | |
| CN103064787A (en) | Embedded assembly modeling and testing method based on expansion interface automata model | |
| Bernaerts et al. | Validating industrial requirements with a contract-based approach | |
| CN109325217B (en) | File conversion method, system, device and computer readable storage medium | |
| Azzouzi et al. | A survey on systems engineering methodologies for large multi-energy cyber-physical systems | |
| CN117311726B (en) | Intelligent legal contract generation method and device, electronic equipment and storage medium | |
| Zhang et al. | Towards correct product derivation in model-driven product lines | |
| Elekes et al. | Assessing the specification of modelling language semantics: a study on UML PSSM | |
| Nastov et al. | MBSE and V&V: a tool-equipped method for combining various V&V strategies | |
| Farah-Stapleton et al. | Behavioral modeling of software intensive system architectures | |
| Lai et al. | Defining and verifying behaviour of domain specific language with fUML | |
| Ahmad et al. | A tool-based boilerplate technique to improve SRS quality: an evaluation | |
| Wang et al. | Using workflow patterns to model and validate service requirements | |
| Diamantopoulos et al. | Mining Software Engineering Data for Software Reuse | |
| Xu et al. | Basic Model Study of Automatic Generation Method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |