A domain model design method based on multi-agent and related device

Abstract

The present application discloses a domain model design method based on multi-agents and related devices, the method comprising: using the knowledge of the target domain to train the model design agent, the domain expert agent, the development agent and the test agent respectively; initiating an event storming request to the model design agent, and the model design agent performs event storming with the domain expert agent, the development agent and the test agent; the model design agent generates the final result of the event storming by using the event storming recognition result and the domain knowledge base of the target domain; initiating a domain model design request to the model design agent, and the model design agent collaborates with the domain expert agent, the development agent and the test agent to generate an initial model design; initiating a domain model review request to the model design agent, and the model design agent collaborates with the domain expert agent, the development agent and the test agent to optimize the initial model design.

Description

Technical Field

[0001] The present application relates to the field of software engineering technology, and in particular to a multi-agent based domain model design method and related devices. Background Art

[0002] One of the core challenges in software development is how to transform complex business requirements into maintainable and scalable software systems. Domain-driven design, as a software development methodology to address this challenge, has gained widespread attention and application in recent years.

[0003] The core concept is to focus on the business domain itself and drive the design and development of software by establishing a domain model that reflects domain concepts and business rules. It emphasizes close collaboration between domain experts, developers, and testers, and eliminates communication barriers through common languages ​​and models to ensure that the software system accurately reflects business requirements. Therefore, currently, domain experts, developers, and testers mainly communicate and collaborate with each other, and developers develop domain models based on the information of all personnel, and testers conduct tests.

[0004] However, this method is not only inefficient, but also relies on the knowledge and experience of professionals in the corresponding field. When there are insufficient professionals or when they cannot provide sufficient accurate information, it is easy to lead to poor model quality. In addition, due to the different professional backgrounds of personnel in various fields, communication problems are likely to occur, which will also affect the efficiency and quality of modeling. Summary of the invention

[0005] Based on the above-mentioned deficiencies of the prior art, the present application provides a multi-agent based domain model design method and related devices to solve the problems of low model design efficiency and low model design quality in the prior art.

[0006] In order to achieve the above objectives, this application provides the following technical solutions:

[0007] The first aspect of the present application provides a multi-agent based domain model design method, comprising:

[0008] Using the knowledge of the target domain, the model design agent, domain expert agent, development agent, and test agent are trained separately;

[0009] Initiate an event storming request to the model design agent, and obtain an event storming recognition result by asking the domain expert agent, the development agent, and the test agent for the recognition result of the associated information of the domain events in the target domain through the model design agent;

[0010] Designing an intelligent agent through the model, using the event storming recognition results and the domain knowledge base of the target domain, generating the final outcome of the event storming;

[0011] Initiate a domain model design request to the model design agent, and generate multiple design element information of the target domain based on the final result of the event storm through the model design agent;

[0012] The model design agent asks the domain expert agent, the development agent, and the test agent for suggestions on various design element information in the target domain, thereby obtaining design element suggestion results;

[0013] Generate an initial model design by using the model design agent, the design element suggestion results and the domain knowledge base of the target domain;

[0014] Initiate a domain model review request to the model design agent, and ask the domain expert agent, the development agent, and the test agent for optimization suggestions for the initial model design through the model design agent to obtain optimization suggestion feedback;

[0015] The model design agent uses the optimization suggestion feedback and the domain knowledge base of the target domain to optimize the initial model design to obtain an optimized model design.

[0016] Optionally, in the above-mentioned multi-agent-based domain model design method, after respectively training the model design agent, the domain expert agent, the development agent, and the test agent using the knowledge of the target domain, the method further includes:

[0017] Initiate a request to create a domain model design session to the domain model design module;

[0018] Requesting the agent management module to create an agent in the design session through the domain model design module;

[0019] The model design agent, the domain expert agent, the development agent and the test agent in the design session are created and initialized through the agent management module, and a successful session creation notification is fed back to the user.

[0020] Optionally, in the above-mentioned multi-agent-based domain model design method, the event storming request is initiated to the model design agent, and the model design agent inquires the domain expert agent, the development agent, and the test agent about the recognition result of the associated information of the domain events in the target domain to obtain the event storming recognition result, including:

[0021] An event storming request is initiated to the model design agent, and the model design agent asks the domain expert agent for related information of domain events in the target domain, and asks the development agent and the test agent for supplementary suggestions on the related information of domain events in the target domain, so as to obtain the event storming identification result.

[0022] Optionally, in the above-mentioned multi-agent-based domain model design method, after generating the initial model design by the model design agent using the design element suggestion results and the domain knowledge base of the target domain, the method further includes:

[0023] The initial model design submitted by the model design agent is received through the domain model design module, and the initial model design is saved in the domain model management module.

[0024] Optionally, in the above-mentioned multi-agent-based domain model design method, after the model design agent optimizes the initial model design by using the optimization suggestion feedback and the domain knowledge base of the target domain to obtain the optimized model design, the method further includes:

[0025] Initiate a model publishing request to the domain model design module, and save the current optimized model design as the final model design to the domain model management module through the domain model design module;

[0026] The final model design is published through the domain model management module, and the user is notified after the model is successfully published.

[0027] The second aspect of the present application provides a multi-agent based domain model design device, comprising:

[0028] The training unit is used to train the model design agent, the domain expert agent, the development agent, and the test agent respectively by using the knowledge of the target domain;

[0029] An event storming unit is used to initiate an event storming request to the model design agent, and obtain an event storming recognition result by asking the domain expert agent, the development agent and the test agent for the recognition result of the associated information of the domain events in the target domain through the model design agent;

[0030] A summary generation unit, used to design an intelligent agent through the model, and use the event storming recognition result and the domain knowledge base of the target domain to generate the final result of the event storming;

[0031] An element generation unit, used to initiate a domain model design request to the model design agent, and generate a plurality of design element information of the target domain based on the final result of the event storm through the model design agent;

[0032] An element optimization unit is used to obtain a design element suggestion result by querying the domain expert agent, the development agent and the test agent through the model design agent about the suggestion result of each design element information of the target domain;

[0033] A model design unit, configured to generate an initial model design by using the model design agent, the design element suggestion results and the domain knowledge base of the target domain;

[0034] A model suggestion unit is used to initiate a domain model review request to the model design agent, and through the model design agent, ask the domain expert agent, the development agent and the test agent for optimization suggestions on the initial model design to obtain optimization suggestion feedback;

[0035] The model optimization unit is used to optimize the initial model design by using the optimization suggestion feedback and the domain knowledge base of the target domain through the model design intelligent agent to obtain an optimized model design.

[0036] Optionally, in the above-mentioned multi-agent-based domain model design device, it also includes:

[0037] A session request unit, used for initiating a request to create a domain model design session to the domain model design module;

[0038] A creation request unit, used for requesting the agent management module to create an agent in the design session through the domain model design module;

[0039] A session creation unit is used to create and initialize the model design agent, the domain expert agent, the development agent and the test agent in the design session through the agent management module, and to provide feedback to the user on the successful creation of the session.

[0040] Optionally, in the above-mentioned multi-agent-based domain model design device, the event storming unit includes:

[0041] The event storming sub-unit is used to initiate an event storming request to the model design agent, and obtain the event storming identification result by asking the domain expert agent for the related information of the domain events in the target domain through the model design agent, and asking the development agent and the test agent for supplementary suggestions on the related information of the domain events in the target domain.

[0042] Optionally, in the above-mentioned multi-agent-based domain model design device, it also includes:

[0043] The storage unit is used to receive the initial model design submitted by the model design agent through the domain model design module, and save the initial model design to the domain model management module.

[0044] Optionally, in the above-mentioned multi-agent-based domain model design device, it also includes:

[0045] A model determination unit is used to initiate a model publishing request to a domain model design module, and save the current optimized model design as a final model design to a domain model management module through the domain model design module;

[0046] The publishing unit is used to publish the final model design through the domain model management module and notify the user after the model is successfully published.

[0047] A third aspect of the present application provides an electronic device, including:

[0048] Memory and processor;

[0049] Wherein, the memory is used to store programs;

[0050] The processor is used to execute the program, and when the program is executed, it is specifically used to implement the multi-agent based domain model design method as described in any one of the above.

[0051] In a fourth aspect, the present application provides a computer storage medium for storing a computer program, which, when executed by a processor, is used to implement a multi-agent-based domain model design method as described in any one of the above.

[0052] The embodiment of the present application provides a multi-agent-based domain model design method, which uses the knowledge of the target domain to train the model design agent, the domain expert agent, the development agent and the test agent respectively, so that each agent can learn the knowledge and skills of the target domain and replace the role of the corresponding professional. When an event storm request is initiated to the model design agent, the model design agent inquires the domain expert agent, the development agent and the test agent, and obtains the event storm recognition result of the identification result of the associated information of the domain event of the target domain, thereby obtaining a large amount of associated information of the domain event of the target domain. Therefore, the model design agent can generate the final result of the event storm by using the event storm recognition result and the domain knowledge base of the target domain, and when the domain model design request is initiated to the model design agent, the model design agent generates multiple design element information of the target domain based on the final result of the event storm. Then, the model design agent inquires the domain expert agent, the development agent and the test agent, and obtains the recommended results of the various design element information of the target domain, so that the design elements can be further optimized and adjusted. Therefore, the model design agent can generate the initial model design by using the design element recommendation result and the domain knowledge base of the target domain. Then, a domain model review request is initiated to the model design agent, and the model design agent is used to ask the domain expert agent, development agent and test agent for optimization suggestions for the initial model design, and optimization suggestion feedback is obtained. Finally, the model design agent uses the optimization suggestion feedback and the domain knowledge base of the target domain to optimize the initial model design and obtain the optimized model design, thereby optimizing the model design and ensuring an accurate model design. Therefore, there is no need to rely on domain experts and other relevant personnel, and the domain model design of the relevant field can be automatically generated, which not only ensures the quality of the generated model design, but also effectively improves the efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0054] Figure 1 A flowchart of a multi-agent based domain model design method provided in an embodiment of the present application;

[0055] Figure 2 A flowchart of a method for creating a design session provided in an embodiment of the present application;

[0056] Figure 3 A flowchart of a model publishing method provided in an embodiment of the present application;

[0057] Figure 4 A schematic diagram of the architecture of a multi-agent based domain model design device provided in an embodiment of the present application;

[0058] Figure 5 A schematic diagram of the architecture of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0060] In this application, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0061] The present application embodiment provides a multi-agent based domain model design method, such as Figure 1 As shown, the following steps are included:

[0062] S101. Using the knowledge of the target domain, the model design agent, domain expert agent, development agent and test agent are trained respectively.

[0063] The target domain refers to the domain for which the domain model is currently being developed. For example, when a domain model for the order processing process needs to be designed for an e-commerce platform, the entire process from user order placement to order completion needs to be covered. In this case, the target domain is the e-commerce domain.

[0064] In order to no longer rely on domain experts and other relevant personnel, in the embodiments of the present application, based on artificial intelligence technology, model design agents, domain expert agents, development agents and testing agents are developed for various types of relevant personnel.

[0065] The model design agent, as the coordinator of domain model design, is responsible for organizing and guiding the entire modeling process. It will call other agents according to task requirements and integrate and analyze the suggestions they provide.

[0066] The domain expert agent is mainly responsible for providing domain knowledge, such as domain events, business processes, and business rules, to ensure that the model accurately reflects business needs. It will participate in the identification of domain events, the definition of entities and relationships, answer questions related to domain knowledge raised by other agents, and verify the business rules of the model.

[0067] The development agent is mainly used to evaluate the model from the perspective of code implementation and make optimization suggestions. It will participate in the design of entity attributes and methods, the definition of relationship types and rules, and consider technical feasibility and code quality.

[0068] The test agent mainly evaluates the model from a testing perspective, identifies potential edge cases and risks, and designs test cases.

[0069] In order to enable the model design agent, domain expert agent, development agent and test agent to learn the relevant domain knowledge and intelligence of the target domain, and thus use their own abilities to respond to questions in the target domain, it is necessary to first use the knowledge of the target domain to train the model design agent, domain expert agent, development agent and test agent respectively.

[0070] Optionally, in order to facilitate the management of each agent and the storage of the domain model, an agent management module can be set up. Therefore, when it is necessary to develop a domain model of the target domain, the user can request the agent management module to train each agent.

[0071] Optionally, in order to facilitate the dialogue between various agents and realize the domain model design of the target domain, in another embodiment of the present application, after executing step S101, it can further include the creation of a design session. Figure 2 As shown, a method for creating a design session provided in an embodiment of the present application includes:

[0072] S201. Initiate a request to create a domain model design session to the domain model design module.

[0073] In order to facilitate users in design, a domain model design module is set up in an embodiment of the present application, which is mainly used to provide a visual domain modeling interface, such as event storm wall, UML class diagram, sequence diagram, etc., as well as to initiate different types of design activities, and support users and multiple agents to collaborate in domain modeling.

[0074] So the user requests the domain model design module to create a model design session.

[0075] S202. Request the agent management module to create an agent in the design session through the domain model design module.

[0076] S203. Create and initialize the model design agent, domain expert agent, development agent and test agent in the design session through the agent management module, and provide the user with a notification of successful session creation.

[0077] Specifically, the trained agents are used to create the agents in the design session, and the user is notified after the creation is successful.

[0078] S102, initiating an event storming request to the model design agent, and obtaining the event storming recognition result by asking the domain expert agent, the development agent, and the test agent for the recognition result of the correlation information of the domain events in the target domain through the model design agent.

[0079] It should be noted that event storming, as a fast and lightweight domain modeling method, can effectively help teams quickly explore and understand business domains. It mainly focuses on domain events and gradually sorts out business processes, key rules, domain concepts and the relationships between them.

[0080] Therefore, in this application, an event storm request is initiated to the model design agent, and the model design agent respectively initiates multiple questions related to the domain events of the target domain to the domain expert agent, the development agent, and the test agent. The domain expert agent, the development agent, and the test agent respectively read the information in the domain knowledge base, and analyze and judge the corresponding questions according to their own capabilities, and feedback them to the model design agent as a reply. The model design agent summarizes and analyzes the information replied by the domain expert agent, the development agent, and the test agent to obtain the event storm recognition result.

[0081] Optionally, in another embodiment of the present application, a specific implementation of step S102 includes:

[0082] An event storming request is initiated to the model design agent. The model design agent asks the domain expert agent for the related information of the domain events in the target domain, and asks the development agent and the test agent for additional suggestions on the related information of the domain events in the target domain, so as to obtain the event storming recognition result.

[0083] It should be noted that since the domain expert agent can obtain more comprehensive information about domain events, in an embodiment of the present application, the model design agent is first used to inquire about the correlation information of the domain events in the target domain of the domain expert agent, so that the domain expert agent can provide the overall correlation information of the domain events, and then further inquire about the development agent and the test agent, so that the development agent and the test agent can further supplement the correlation information of the domain events from the perspective of development and testing.

[0084] For example, the model design agent asks the domain expert agent: "What are the key domain events in the e-commerce platform?" The domain expert agent combines the domain knowledge base to identify key domain events such as "user order", "successful payment", "order delivery", and "order completion", and feeds back to the model design agent. The model design agent asks the domain expert agent: "What are the causes, consequences, and processes of these key domain events?" The domain expert agent combines the domain knowledge base to answer the model design agent's business process questions. And so on, ask for information related to other domain events. Then ask the development agent and the test agent to supplement the domain events, such as exception handling. After analyzing the questions asked, the development agent and the test agent give additional opinions.

[0085] S103. Design an intelligent agent through the model, use the event storming recognition results and the domain knowledge base of the target field to generate the final results of the event storming.

[0086] Specifically, the model design agent can preliminarily determine information such as aggregation, bounded context, and core subdomains based on the final results of the event storming fed back by each agent and the domain knowledge base, form the final results of the event storming, and submit it to the domain model design module.

[0087] Among them, the domain knowledge base of the target domain can store various knowledge related to the target domain based on technologies such as knowledge graphs, such as domain concepts, business rules, design patterns, case libraries, etc., to provide domain knowledge support for the training and use of each intelligent agent. Therefore, each intelligent agent needs to rely on the information in the domain knowledge base of the target domain during its work.

[0088] S104. Initiate a domain model design request to the model design agent, and generate design element information of multiple target domains based on the final results of event storming through the model design agent.

[0089] The design element information refers to the element information in the model design, including but not limited to entities, relationships, rules, attributes, and methods.

[0090] Since the final results of event storming contain a large amount of information about domain events in the target domain, we can preliminarily analyze multiple design element information in the target domain, for example, identify entities such as "orders", "products", and "users", and design some attributes and methods of the entities.

[0091] S105. The model design agent asks the domain expert agent, the development agent, and the test agent for the recommended results of the design element information for each target field, and obtains the design element recommendation results.

[0092] It should be noted that since the design element information generated based on event storming may contain inaccurate information or omission of important information, in an embodiment of the present application, the design element information of each target field that has been generated will be further queried for modification suggestions from domain expert agents, development agents and test agents. The domain expert agents, development agents and test agents will give corresponding suggestions from their respective perspectives to obtain design element suggestion results, and the generated design element information will be adjusted according to the suggestion results.

[0093] For example, after identifying entities such as "order", "goods", and "user", the domain expert agent is asked questions. After analyzing the problem, the domain expert agent recommends splitting the "order bill" and "order logistics" entities from the order, and supplements the attributes of the relevant entities. The model design agent asks the development agent: "How to design the attributes and methods of these entities to ensure the quality of code implementation." After the development agent analyzes, it recommends migrating the "payment" method of the "order" entity to the "order bill" entity to improve the maintainability of the model, and gives naming suggestions for entity methods. The model design agent asks the test agent: "Are there potential risks in the model design, and how to design test cases?" After the test agent analyzes, it recommends adding necessary verification rules for each entity, such as order amount, product inventory, etc., to improve the robustness of the model, and gives test case design suggestions.

[0094] S106. Generate an initial model design by using the model design agent, design element suggestion results and the domain knowledge base of the target domain.

[0095] Specifically, the model design agent uses the design element suggestion results to adjust the design element information of the target domain, and then uses the adjusted design element information in combination with the knowledge in the domain knowledge base of the target domain to generate an initial model design.

[0096] Optionally, in another embodiment of the present application, after executing step S106, the following may be further included:

[0097] The domain model design module receives the initial model design submitted by the model design agent and saves the initial model design to the domain model management module.

[0098] S107. Initiate a domain model review request to the model design agent, and ask the domain expert agent, development agent, and test agent through the model design agent to obtain optimization suggestions for each initial model design and obtain optimization suggestion feedback.

[0099] Considering that the initial model design may still have deficiencies, users can request the model design agent to conduct a domain model review. The model design agent asks the domain expert agent, development agent, and test agent to find out the problems in the initial model design and give corresponding suggestions. Each agent analyzes and judges the initial model design based on the information in the domain knowledge base and feeds back the analysis results to the model design agent.

[0100] For example, the model design agent requests the domain expert agent for review, and the domain expert agent proactively analyzes questions such as "Does the model design meet business requirements? Is there any conflict in business rules?" and gives feedback. The model design agent requests the development agent for review, and the development agent proactively analyzes questions such as "Does the model design use the value object design pattern as much as possible? Do all business interfaces use intention-explicit naming?" and gives feedback. The model design agent requests the test agent for review, and the test agent proactively analyzes questions such as "Have all the boundary conditions of the model design been considered?" and gives feedback.

[0101] S108. The model design agent optimizes the initial model design using the optimization suggestion feedback and the domain knowledge base of the target domain to obtain an optimized model design.

[0102] Specifically, the model design agent combines the optimization suggestions fed back by each agent and the knowledge of the domain knowledge base to optimize the model design, for example, to improve entity attributes, adjust relationships, etc., to obtain the optimized model design, and submit it to the domain model design module. The domain model design module saves the optimized model design to the domain model management module to facilitate the management of the optimized model design.

[0103] Optionally, in another embodiment of the present application, after executing step S108, the model may be further published. Figure 3 As shown, a model publishing method provided in an embodiment of the present application includes:

[0104] S301. Initiate a model publishing request to the domain model design module, and save the current optimized model design as the final model design to the domain model management module through the domain model design module.

[0105] It should be noted that the optimization of the model design can be performed multiple times. When the user believes that the model design meets the requirements and can be released, he can request the domain model design module to release the model. The domain model design module saves the current optimized model design as the final model design to the domain model management module to trigger the domain model management module to release it.

[0106] S302. Publish the final model design through the domain model management module and notify the user after the model is successfully published.

[0107] The embodiment of the present application provides a multi-agent-based domain model design method, which uses the knowledge of the target domain to train the model design agent, the domain expert agent, the development agent and the test agent respectively, so that each agent can learn the knowledge and skills of the target domain and replace the role of the corresponding professional. When an event storm request is initiated to the model design agent, the model design agent inquires the domain expert agent, the development agent and the test agent, and obtains the event storm recognition result of the identification result of the associated information of the domain event of the target domain, thereby obtaining a large amount of associated information of the domain event of the target domain. Therefore, the model design agent can generate the final result of the event storm by using the event storm recognition result and the domain knowledge base of the target domain, and when the domain model design request is initiated to the model design agent, the model design agent generates multiple design element information of the target domain based on the final result of the event storm. Then, the model design agent inquires the domain expert agent, the development agent and the test agent, and obtains the recommended results of the various design element information of the target domain, so that the design elements can be further optimized and adjusted. Therefore, the model design agent can generate the initial model design by using the design element recommendation result and the domain knowledge base of the target domain. Then, a domain model review request is initiated to the model design agent, and the model design agent is used to ask the domain expert agent, development agent and test agent for optimization suggestions for the initial model design, and optimization suggestion feedback is obtained. Finally, the model design agent uses the optimization suggestion feedback and the domain knowledge base of the target domain to optimize the initial model design and obtain the optimized model design, thereby optimizing the model design and ensuring an accurate model design. Therefore, there is no need to rely on domain experts and other relevant personnel, and the domain model design of the relevant field can be automatically generated, which not only ensures the quality of the generated model design, but also effectively improves the efficiency.

[0108] Another embodiment of the present application provides a multi-agent based domain model design device, such as Figure 4 As shown, including:

[0109] The training unit 401 is used to utilize the knowledge of the target domain to train the model design agent, the domain expert agent, the development agent and the test agent respectively.

[0110] The event storming unit 402 is used to initiate an event storming request to the model design agent, and obtain the event storming recognition result by asking the domain expert agent, the development agent and the test agent for the recognition result of the correlation information of the domain events in the target domain through the model design agent.

[0111] The summary generation unit 403 is used to design an intelligent agent through a model, use the event storming recognition results and the domain knowledge base of the target domain, and generate the final results of the event storming.

[0112] The element generation unit 404 is used to initiate a domain model design request to the model design agent, and generate multiple design element information of the target domain based on the final results of the event storm through the model design agent.

[0113] The element optimization unit 405 is used to obtain the design element suggestion results by querying the domain expert agent, the development agent and the test agent through the model design agent for the suggestion results of the various design element information in the target domain.

[0114] The model design unit 406 is used to generate an initial model design by using the design element suggestion results and the domain knowledge base of the target domain through the model design agent.

[0115] The model suggestion unit 407 is used to initiate a domain model review request to the model design agent, and obtain optimization suggestion feedback for the initial model design by asking the domain expert agent, the development agent and the test agent through the model design agent.

[0116] The model optimization unit 408 is used to optimize the initial model design by using the optimization suggestion feedback and the domain knowledge base of the target domain through the model design intelligent agent to obtain an optimized model design.

[0117] Optionally, in another embodiment of the present application, the multi-agent based domain model design device further includes:

[0118] The session request unit is used to initiate a request to the domain model design module to create a domain model design session.

[0119] A creation request unit is used to request the agent management module to create an agent in the design session through the domain model design module.

[0120] The session creation unit is used to create and initialize the model design agent, domain expert agent, development agent and test agent in the design session through the agent management module, and provide the user with feedback on the successful session creation.

[0121] Optionally, in the multi-agent based domain model design device provided in another embodiment of the present application, the event storm unit includes:

[0122] The event storming sub-unit is used to initiate an event storming request to the model design agent, and obtain the event storming recognition result by asking the domain expert agent for the related information of the domain events in the target domain through the model design agent, and asking the development agent and the test agent for supplementary suggestions on the related information of the domain events in the target domain.

[0123] Optionally, in another embodiment of the present application, the multi-agent based domain model design device further includes:

[0124] The storage unit is used to receive the initial model design submitted by the model design agent through the domain model design module, and save the initial model design to the domain model management module.

[0125] Optionally, in another embodiment of the present application, the multi-agent based domain model design device further includes:

[0126] The model determination unit is used to initiate a model publishing request to the domain model design module, and save the current optimized model design as the final model design to the domain model management module through the domain model design module.

[0127] The publishing unit is used to publish the final model design through the domain model management module and notify the user after the model is successfully published.

[0128] It should be noted that the specific working process of each unit provided in the above embodiments of the present application can refer to the implementation process of the corresponding steps in the above method embodiments, and will not be repeated here.

[0129] Another embodiment of the present application provides an electronic device, such as Figure 5 As shown, including:

[0130] Memory 501 and processor 502 .

[0131] The memory 501 is used to store programs.

[0132] The processor 502 is used to execute the program stored in the memory 501. When the program is executed, it is specifically used to implement the multi-agent based domain model design method provided in any one of the above embodiments.

[0133] Another embodiment of the present application provides a computer storage medium for storing a computer program, which, when executed by a processor, is used to implement any of the multi-agent-based domain model design methods described above.

[0134] Computer storage media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0135] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0136] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A multi-agent based domain model design method, characterized in that: include: Using the knowledge of the target domain, the model design agent, domain expert agent, development agent, and test agent are trained separately; Initiate an event storming request to the model design agent, and obtain an event storming recognition result by asking the domain expert agent, the development agent, and the test agent for the recognition result of the associated information of the domain events in the target domain through the model design agent; Designing an intelligent agent through the model, using the event storming recognition results and the domain knowledge base of the target domain, generating the final outcome of the event storming; Initiate a domain model design request to the model design agent, and generate multiple design element information of the target domain based on the final result of the event storm through the model design agent; The model design agent asks the domain expert agent, the development agent, and the test agent for suggestions on various design element information in the target domain, thereby obtaining design element suggestion results; Generate an initial model design by using the model design agent, the design element suggestion results and the domain knowledge base of the target domain; Initiate a domain model review request to the model design agent, and ask the domain expert agent, the development agent, and the test agent for optimization suggestions for the initial model design through the model design agent to obtain optimization suggestion feedback; The model design agent uses the optimization suggestion feedback and the domain knowledge base of the target domain to optimize the initial model design to obtain an optimized model design.

2. The method according to claim 1, characterized in that After respectively training the model design agent, the domain expert agent, the development agent, and the test agent using the knowledge of the target domain, the method further includes: Initiate a request to the domain model design module to create a domain model design session; Requesting the agent management module to create an agent in the design session through the domain model design module; The model design agent, the domain expert agent, the development agent and the test agent in the design session are created and initialized through the agent management module, and a successful session creation notification is fed back to the user.

3. The method according to claim 1, characterized in that The initiating an event storming request to the model design agent, and obtaining an event storming recognition result by querying the domain expert agent, the development agent, and the test agent through the model design agent about the recognition result of the associated information of the domain events in the target domain, includes: An event storming request is initiated to the model design agent, and the model design agent asks the domain expert agent for related information of domain events in the target domain, and asks the development agent and the test agent for supplementary suggestions on the related information of domain events in the target domain, so as to obtain the event storming identification result.

4. The method according to claim 1, characterized in that: After generating the initial model design by the model design agent using the design element suggestion results and the domain knowledge base of the target domain, the method further includes: The initial model design submitted by the model design agent is received through the domain model design module, and the initial model design is saved in the domain model management module.

5. The method according to claim 1, characterized in that After the model design agent optimizes the initial model design by using the optimization suggestion feedback and the domain knowledge base of the target domain to obtain the optimized model design, the method further includes: Initiate a model publishing request to the domain model design module, and save the current optimized model design as the final model design to the domain model management module through the domain model design module; The final model design is published through the domain model management module, and the user is notified after the model is successfully published.

6. A domain model design device based on multi-agent, characterized in that: include: The training unit is used to train the model design agent, the domain expert agent, the development agent, and the test agent respectively by using the knowledge of the target domain; An event storming unit is used to initiate an event storming request to the model design agent, and obtain an event storming recognition result by asking the domain expert agent, the development agent and the test agent for the recognition result of the associated information of the domain events in the target domain through the model design agent; A summary generation unit, used to design an intelligent agent through the model, and use the event storming recognition result and the domain knowledge base of the target domain to generate the final result of the event storming; An element generation unit, used to initiate a domain model design request to the model design agent, and generate a plurality of design element information of the target domain based on the final result of the event storm through the model design agent; An element optimization unit is used to obtain a design element suggestion result by querying the domain expert agent, the development agent and the test agent through the model design agent about the suggestion result of each design element information of the target domain; A model design unit, configured to generate an initial model design by using the model design agent, the design element suggestion results and the domain knowledge base of the target domain; A model suggestion unit is used to initiate a domain model review request to the model design agent, and through the model design agent, ask the domain expert agent, the development agent and the test agent for optimization suggestions on the initial model design to obtain optimization suggestion feedback; The model optimization unit is used to optimize the initial model design by using the optimization suggestion feedback and the domain knowledge base of the target domain through the model design intelligent agent to obtain an optimized model design.

7. The device according to claim 6, characterized in that Also includes: A session request unit, used for initiating a request to create a domain model design session to the domain model design module; A creation request unit, used for requesting the agent management module to create an agent in the design session through the domain model design module; A session creation unit is used to create and initialize the model design agent, the domain expert agent, the development agent and the test agent in the design session through the agent management module, and to provide feedback to the user on the successful creation of the session.

8. The device according to claim 6, characterized in that The event storm unit comprises: The event storming sub-unit is used to initiate an event storming request to the model design agent, and obtain the event storming identification result by asking the domain expert agent for the related information of the domain events in the target domain through the model design agent, and asking the development agent and the test agent for supplementary suggestions on the related information of the domain events in the target domain.

9. An electronic device, characterized in that: include: Memory and processor; Wherein, the memory is used to store programs; The processor is used to execute the program, and when the program is executed, it is specifically used to implement the multi-agent based domain model design method as described in any one of claims 1 to 5.

10. A computer storage medium, characterized in that: Used to store a computer program, which, when executed by a processor, is used to implement the multi-agent based domain model design method as described in any one of claims 1 to 5.

Images