Low-code development method and system based on hybrid orchestration of intelligent agent and intelligent service

Abstract

The invention belongs to the technical field of low-code development, and provides a low-code development method and system based on mixed orchestration of agents and intelligent services, and the method comprises the steps: creating an application form; according to the business scene function of the created application form, constructing an intelligent agent, and obtaining mapping information between the business scene function and the intelligent agent; performing task decomposition on the created application form to obtain a plurality of sub-application forms; judging the service scene function of the obtained sub-application form, and analyzing the function intention of the sub-application form; task arrangement is performed according to a judgment analysis result of the sub-application form, and arrangement agent calling or arrangement intelligent service calling is selected according to a function intention analysis result of the sub-application form, so that the difficulty of low code development in a complex application scene is reduced; functions of a low-code platform are packaged into an intelligent agent, and intelligent and efficient development of low codes is achieved through hard code mixed arrangement of the intelligent agent and intelligent services.

Description

Technical Field

[0001] The present invention belongs to the field of low-code development technology, and specifically relates to a low-code development method and system based on hybrid orchestration of intelligent agents and intelligent services. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Low Code is a visual application development method that delivers applications with less code and at a faster speed, automating the code that programmers do not want to develop; through a set of digital technology tool platforms, based on more efficient methods such as graphical drag and drop and parameterized configuration, it can achieve rapid construction, data orchestration, ecological connection, and middle-office services, and realize scenario application innovation in digital transformation with a small amount of code or no code.

[0004] Low-code development is a technology that uses visual drag-and-drop and configurable parameters to quickly build applications. It allows developers to assemble preset functional modules (such as login interfaces, data tables, and approval processes) like building blocks without having to write code from scratch, and then complete application development through simple logical settings.

[0005] Big models are automated learning systems based on artificial intelligence (AI) technology. They learn from large amounts of data, extract useful information, and make predictions and decisions based on this information. However, the development of big models faces several significant challenges: They require significant computing resources and time during the learning process, significantly increasing their R&D costs; and their generalization capabilities are limited to adapting to new problems and scenarios.

[0006] In the existing technology, low-code development can be achieved through service orchestration, that is, tasks are decomposed and planned according to the developer's task description, intelligent agents are built through large models, and the call of functions and development of forms are achieved by selecting and calling intelligent agents; however, currently intelligent agents can only achieve a single function and lack the complexity of requirements; when there are functional modules with high coupling and contextual information connections in the low-code platform, information distortion will occur in the intelligent agent during the information flow process, making low-code development difficult in complex and long-process scenarios, that is, low-code development cannot be achieved by calling the orchestration intelligent agent. Summary of the Invention

[0007] To solve the above problems, the present invention proposes a low-code development method and system based on the hybrid orchestration of intelligent agents and intelligent services. The functions of the low-code platform are encapsulated into intelligent agents. For functions with high coupling, the calls of intelligent agents are orchestrated through intelligent services, and the calls of intelligent agents are orchestrated. Low-code intelligent development is achieved through hard-coded hybrid orchestration of intelligent agents and intelligent services.

[0008] According to some embodiments, a first solution of the present invention provides a low-code development method based on hybrid orchestration of intelligent agents and intelligent services, which adopts the following technical solutions: A low-code development approach based on hybrid orchestration of intelligent agents and intelligent services, including: Create an application form; According to the business scenario functions of the created application form, an intelligent agent is constructed to obtain the mapping information between the business scenario functions and the intelligent agent; Decompose the created application form into several sub-application forms; Determine the business scenario function of the obtained sub-application form and analyze the functional intent of the sub-application form; Based on the analysis results of functional intent, the tasks of sub-application forms are orchestrated to complete the low-code development of application forms based on the hybrid orchestration of intelligent agents and intelligent services. Among them, in the process of task orchestration, the calling object of task orchestration is determined according to the single function principle of the function intention analysis result. When the analysis result is a single function, the orchestration intelligent agent call is adopted, otherwise the orchestration intelligent service call is adopted.

[0009] As a further technical limitation, when choreographing agent calls, agents are matched in the obtained mapping information according to the single function of the functional intent analysis result, and the task orchestration of the sub-application form is completed by calling the matched agent.

[0010] As a further technical limitation, when orchestrating intelligent service calls, matching agents are selected in the mapping information based on the business scenario functions of the functional intent analysis results, and the task orchestration of the sub-application form is completed by calling several matched agents.

[0011] Furthermore, in the process of orchestrating intelligent service calls, a hard-coded method is used to select matching intelligent agents in series to obtain intelligent services; the calling order of the intelligent agents in the intelligent services is determined according to the business scenario functions of the functional intent analysis results, and the calls of the intelligent agents are encoded in a hard-coded manner. After identifying the user's intention, the intelligent service is directly called to complete the business scenario functions.

[0012] As a further technical limitation, during the task decomposition process, the created application form is comprehensively evaluated, and the comprehensive evaluation result obtained is the sub-application form; the comprehensive evaluation includes three dimensions, namely, the entity modeling of the application form, the development scenario of the application form user platform, and the construction of the business scenario function of the application form.

[0013] As a further technical limitation, the process of creating an application form includes creating a project, creating entity modeling, selecting a form template type, binding the form to BE, selecting displayed BE fields, creating components and forms based on the selected field information, and saving form metadata information.

[0014] According to some embodiments, a second solution of the present invention provides a low-code development system based on hybrid orchestration of intelligent agents and intelligent services, which adopts the following technical solutions: A low-code development system based on hybrid orchestration of intelligent agents and intelligent services, including: A creation module configured to create an application form; A construction module is configured to construct an intelligent agent according to the business scenario function of the created application form and obtain mapping information between the business scenario function and the intelligent agent; A decomposition module is configured to perform task decomposition on the created application form to obtain a plurality of sub-application forms; An analysis module configured to determine the business scenario function of the obtained sub-application form and analyze the functional intent of the sub-application form; The orchestration module is configured to perform task orchestration of sub-application forms based on the analysis results of functional intent, completing the low-code development of application forms based on the hybrid orchestration of intelligent agents and intelligent services; Among them, in the process of task orchestration, the calling object of task orchestration is determined according to the single function principle of the function intention analysis result. When the analysis result is a single function, the orchestration intelligent agent call is adopted, otherwise the orchestration intelligent service call is adopted.

[0015] According to some embodiments, a third solution of the present invention provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a program thereon, which, when executed by a processor, implements the steps of the low-code development method based on hybrid orchestration of intelligent agents and intelligent services as described in the first embodiment of the present invention.

[0016] According to some embodiments, a fourth solution of the present invention provides an electronic device, which adopts the following technical solution: An electronic device includes a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, it implements the steps in the low-code development method based on hybrid orchestration of intelligent agents and intelligent services as described in the first scheme of the present invention.

[0017] According to some embodiments, a fifth solution of the present invention provides a computer program product, which adopts the following technical solution: A computer program product includes software code, and the program in the software code executes the steps in the low-code development method based on hybrid orchestration of intelligent agents and intelligent services as described in the first embodiment of the present invention.

[0018] Compared with the prior art, the present invention has the following beneficial effects: The present invention decomposes the created application form into tasks to obtain several sub-application forms; arranges tasks based on the judgment and analysis results of the sub-application forms; and selects to arrange intelligent body calls or intelligent service calls based on the functional intent analysis results of the sub-application forms, thereby reducing the difficulty of low-code development in complex application scenarios.

[0019] The present invention constructs an intelligent body according to the business scenario function of the application form and obtains a mapping relationship between the business scenario function and the intelligent body; in the process of orchestrating the intelligent service call, the business scenario function and the intelligent body are matched in the obtained mapping relationship according to the single function of the business scenario function in the function intent analysis result, and the intelligent body in the orchestration of the intelligent service is determined. By calling the determined intelligent body, the task orchestration is completed, and the low-code development of multi-functional application forms in complex scenarios is completed quickly and efficiently.

[0020] The present invention encapsulates the functions of the low-code platform into intelligent bodies. For functions with high coupling, it orchestrates the calls of intelligent bodies through intelligent services and orchestrates the calls of intelligent bodies, and realizes low-code intelligent development through hard-coded mixed orchestration of intelligent bodies and intelligent services. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings constituting a part of the specification of this embodiment are used to provide a further understanding of this embodiment. The schematic embodiments and descriptions of this embodiment are used to explain this embodiment and do not constitute an improper limitation on this embodiment.

[0022] Figure 1 This is a flowchart of the low-code development method based on hybrid orchestration of intelligent agents and intelligent services in Example 1 of the present invention; Figure 2 This is a flowchart of orchestrating agent calls in Example 1 of the present invention; Figure 3 This is a schematic diagram of the structure of the intelligent service in the first embodiment of the present invention; Figure 4 This is a flow chart of the hybrid orchestration of intelligent agents and intelligent services in the first embodiment of the present invention; Figure 5 This is a structural block diagram of the low-code development system based on hybrid orchestration of intelligent agents and intelligent services in Example 2 of the present invention. DETAILED DESCRIPTION

[0023] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0024] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0025] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0026] In the present invention, terms such as "upper", "lower", "left", "right", "front", "back", "vertical", "horizontal", "side", "bottom", etc. indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. They are relational words determined only for the convenience of describing the structural relationships of the various parts or elements of the present invention, and do not specifically refer to any part or element in the present invention, and should not be understood as limiting the present invention.

[0027] In the absence of conflict, the embodiments of the present invention and the features thereof may be combined with each other.

[0028] Example 1 Embodiment 1 of the present invention introduces a low-code development method based on hybrid orchestration of intelligent agents and intelligent services.

[0029] like Figure 1 The low-code development method shown in the figure is based on the hybrid orchestration of intelligent agents and intelligent services, including: Create an application form; According to the business scenario functions of the created application form, an intelligent agent is constructed to obtain the mapping information between the business scenario functions and the intelligent agent; Decompose the created application form into several sub-application forms; Determine the business scenario function of the obtained sub-application form and analyze the functional intent of the sub-application form; Based on the analysis results of functional intent, the tasks of sub-application forms are orchestrated to complete the low-code development of application forms based on the hybrid orchestration of intelligent agents and intelligent services. Among them, in the process of task orchestration, the calling object of task orchestration is determined according to the single function principle of the function intention analysis result. When the analysis result is a single function, the orchestration intelligent agent call is adopted, otherwise the orchestration intelligent service call is adopted.

[0030] This embodiment uses the modeling knowledge, function manual and other information of the low-code platform as the knowledge base of the intelligent agent for pre-training, which can enable the intelligent agent to understand the user's needs, decompose tasks and orchestrate the task execution process; encapsulate the functions of the low-code platform into an intelligent agent, and at the same time, for some functions with a high degree of coupling, orchestrate the call of the intelligent agent through intelligent services and expose the call of the intelligent service to the intelligent assistant; and realize the intelligent development of code through the hard-coded hybrid orchestration of the intelligent agent and intelligent service.

[0031] This embodiment encapsulates the development steps of the low-code platform into an intelligent agent that can be called by a large model, and at the same time encapsulates intelligent services and fixedly orchestrates the calls of some intelligent agents; after the intelligent assistant accesses the intelligent agent and after communicating with the intelligent assistant, the capabilities of the intelligent agent are used to automatically orchestrate the calls of the intelligent agent and intelligent services to achieve intelligent development.

[0032] As one or more implementation methods, this embodiment creates an application form in a modeling language based on the independence and integrity of business scenarios. The created application form at least includes creating a project, creating a BE (entity modeling), selecting a form template type, binding the form to the BE, selecting the BE fields to be displayed, creating components and forms based on the selected field information, and saving form metadata information.

[0033] In this embodiment, each independent and complete step is encapsulated into an intelligent agent, and the input information required for each step is used as the input of the intelligent agent. At the same time, the output information of the intelligent agent, the capabilities provided by the intelligence, and the identification of the intelligent agent are stored in a specific table. The decomposed tasks, intelligent agent functions, and intelligent agent identification relationship information (that is, the mapping information between business scenario functions and intelligent agents) are input into the big model. The big model can understand the orchestration tasks, or analyze user intentions, identify what functions need to be performed, and then match the corresponding intelligent agent through the mapping information, call the intelligent agent, and intelligently generate the calling intelligent agent to complete the specific function.

[0034] It should be noted that this embodiment conducts a comprehensive evaluation on the created application form, and the comprehensive evaluation result obtained is the sub-application form; wherein, the comprehensive evaluation includes three dimensions, namely, the entity modeling of the application form, the development scenario of the application form user platform, and the construction of the business scenario function of the application form.

[0035] As one or more implementation methods, a comprehensive evaluation of the application form is performed through entity modeling of the application form. Specifically: the application form is abstracted into an entity-attribute-relationship for representing data associations and thing descriptions. In the application form, objects with business relationships are defined as entities, specific business processes are defined as events, and special instructions for entities and events are defined as instructions. According to the obtained entity-attribute-relationship, the description of data associations and things in the application form is completed, and a sub-application form is obtained.

[0036] As one or more implementation methods, a comprehensive evaluation of application forms is conducted through the development scenarios of the application form user platform. Specifically: the development scenarios of the application form user platform include enterprise internal system construction and development scenarios, cross-departmental collaboration tool development scenarios, and rapid trial and error application development scenarios; that is, the enterprise internal system construction and development scenarios use low-code platforms to quickly build business systems such as supply chain management, warehousing and logistics, and production planning (for example: supply chain and ERP system development) to help enterprises realize business process automation; business departments in cross-departmental collaboration tool development scenarios can independently build data analysis dashboards or approval processes without relying on IT department scheduling (for example: a platform can support natural language processing, image recognition, etc.), and business personnel can directly adjust the process logic through the visual interface; in rapid trial and error application development scenarios, enterprises can quickly verify new functions or business models (for example: the production department uses a low-code platform to build a production planning system, completes the online verification within a week, and reduces trial and error costs; mainstream platforms can provide a visual development environment) and support drag-and-drop component construction and intelligent model access to meet the needs of different enterprise scenarios.

[0037] As one or more implementation methods, a comprehensive evaluation of the application form is conducted through the construction of the business scenario functions of the application form. During the construction process, the business model, the functions and performance requirements of the IT system, and the availability and scalability of various equipment components need to be considered to ensure that the rapid development and changes of the application form business can be supported.

[0038] like Figure 2 As shown, in this embodiment, on a low-code platform, orchestration agents are called from the sub-application form generated after task decomposition: creating a project, creating an entity file and adding entity field information, and then creating a form. When a user enters the application creation requirement into the intelligent assistant, the intelligent assistant leverages the capabilities of the large model to decompose the task and sequentially call the encapsulated agents to complete the application creation.

[0039] It should be noted that relying on large models for task decomposition and orchestration requires control. If the task granularity is too small and the agent call chain is too long, unpredictable information distortion may often occur during the transfer process. Therefore, for fine-grained tasks, or functional points with high task coupling and many execution steps, by encapsulating intelligent services and connecting intelligent agents through hard-coded intelligent service content, the information flow between agents is more reliable. For such scenarios, large models directly orchestrate intelligent agents and intelligent services, and low-code development is completed by calling intelligent agents or intelligent services.

[0040] This embodiment takes the development scenario of adding new components to a form and changing component properties as an example to introduce the low-code development method based on the hybrid orchestration of intelligent agents and intelligent services.

[0041] The agents in this embodiment include agents for form metadata parsing, adding components, adjusting component properties, etc. When agents are called sequentially, they need to handle input and output issues between agents. When orchestrating agent calls in this business scenario, input and output issues are prone to occur, especially when processing structural data containing model descriptions; therefore, by adding Figure 3 The intelligent service shown is composed of several intelligent agents connected in series. By hard-coding the calls of the intelligent agents, it is better suitable for this scenario. After identifying the user's intention, the intelligent service is directly called to complete the function the user wants to achieve.

[0042] To achieve low-code development with complex functions and long processes, you can use Figure 4 The hybrid orchestration method of intelligent agents and intelligent services shown in the figure determines the task orchestration method by judging the functional quantity of the functional intent of the sub-application form after task decomposition, and completes the low-code development of application forms based on the hybrid orchestration of intelligent agents and intelligent services; simplifies task coding and improves the reliability of intelligent agents in assisting intelligent development.

[0043] It should be noted that this embodiment determines the calling object of task orchestration based on the single function principle of the functional intent analysis result. When the analysis result is a single function, the orchestration agent call is adopted; otherwise, the orchestration intelligent service call is adopted.

[0044] In one or more embodiments, when an orchestration agent call is used, an agent is matched in the obtained mapping information according to a single function of the functional intent analysis result, and the task orchestration of the sub-application form is completed by calling the matched agent; When using orchestrated intelligent service calls, matching agents are selected from the mapping information based on the business scenario functions of the functional intent analysis results, and the task orchestration of the sub-application form is completed by calling several matching agents.

[0045] It should be noted that in the process of orchestrating intelligent service calls, a hard-coded method is used to select matching intelligent agents in series to obtain intelligent services; the calling order of the intelligent agents in the intelligent services is determined according to the business scenario functions of the functional intent analysis results, and the calls of the intelligent agents are encoded in a hard-coded manner. After identifying the user's intention, the intelligent service is directly called to complete the business scenario function.

[0046] This embodiment is based on low-code intelligent development under the collaboration of multiple agents. It decomposes the process of creating low-code applications under the low-code platform into several functional modules, and then creates several agents that can realize these sub-functions. Each agent contains a description of the function that can be realized, tools for realizing the function, prompt words and knowledge base, etc. After the intelligent assistant of the low-code platform is connected to the large model, it will automatically decompose the task of creating light applications according to the user's requirements, and then orchestrate the call of the agent according to the decomposition steps to meet the user's needs; for some functional modules of the low-code platform with high coupling and contextual information connection, in order to solve the problem of information distortion that occurs in the information flow process of the large model, it also supports pre-set intelligent services. The call of the agent is orchestrated in a hard-coded manner in the intelligent service, and the intelligent assistant then calls the intelligent service to complete the corresponding task; it also supports the mixed orchestration of agents and intelligent services to solve the problem that intelligent development is not easy to use in some complex and long low-code development scenarios.

[0047] This embodiment will decompose the created application form into tasks to obtain several sub-application forms; perform task orchestration based on the judgment and analysis results of the sub-application form, and choose to orchestrate the call of the intelligent agent or the call of the intelligent service based on the functional intent analysis results of the sub-application form, thereby reducing the difficulty of low-code development in complex application scenarios; construct an intelligent agent based on the business scenario function of the application form to obtain a mapping relationship between the business scenario function and the intelligent agent; in the process of orchestrating the intelligent service call, the business scenario function and the intelligent agent are matched in the obtained mapping relationship based on the single function of the business scenario function in the functional intent analysis result, and the intelligent agent in the orchestration intelligent service is determined. The task orchestration is completed by calling the determined intelligent agent, and the low-code development of multi-functional application forms in complex scenarios is completed quickly and efficiently; the functions of the low-code platform are encapsulated into intelligent agents, and for functions with high coupling, the calls of the intelligent agents and the calls of the orchestrated intelligent agents are orchestrated through intelligent services, and low-code intelligent development is achieved through hard-coded mixed orchestration of intelligent agents and intelligent services.

[0048] Example 2 Example 2 of the present invention introduces a low-code development system based on hybrid orchestration of intelligent agents and intelligent services.

[0049] like Figure 5 The low-code development system shown in the figure is based on the hybrid orchestration of intelligent agents and intelligent services, including: A creation module configured to create an application form; A construction module is configured to construct an intelligent agent according to the business scenario function of the created application form and obtain mapping information between the business scenario function and the intelligent agent; A decomposition module is configured to perform task decomposition on the created application form to obtain a plurality of sub-application forms; An analysis module configured to determine the business scenario function of the obtained sub-application form and analyze the functional intent of the sub-application form; The orchestration module is configured to perform task orchestration of sub-application forms based on the analysis results of functional intent, completing the low-code development of application forms based on the hybrid orchestration of intelligent agents and intelligent services; Among them, in the process of task orchestration, the calling object of task orchestration is determined according to the single function principle of the function intention analysis result. When the analysis result is a single function, the orchestration intelligent agent call is adopted, otherwise the orchestration intelligent service call is adopted.

[0050] The detailed steps are the same as the low-code development method based on hybrid orchestration of intelligent agents and intelligent services provided in Example 1, and will not be repeated here.

[0051] Example 3 A third embodiment of the present invention provides a computer-readable storage medium.

[0052] A computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps of the low-code development method based on hybrid orchestration of intelligent agents and intelligent services as described in Example 1 of the present invention.

[0053] The detailed steps are the same as the low-code development method based on hybrid orchestration of intelligent agents and intelligent services provided in Example 1, and will not be repeated here.

[0054] Example 4 A fourth embodiment of the present invention provides an electronic device.

[0055] An electronic device includes a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, it implements the steps in the low-code development method based on hybrid orchestration of intelligent agents and intelligent services as described in Example 1 of the present invention.

[0056] The detailed steps are the same as the low-code development method based on hybrid orchestration of intelligent agents and intelligent services provided in Example 1, and will not be repeated here.

[0057] Example 5 A fifth embodiment of the present invention provides a computer program product.

[0058] A computer program product includes software code, and the program in the software code executes the steps in the low-code development method based on hybrid orchestration of intelligent agents and intelligent services as described in Example 1 of the present invention.

[0059] The detailed steps are the same as the low-code development method based on hybrid orchestration of intelligent agents and intelligent services provided in Example 1, and will not be repeated here.

[0060] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk drives, CD-ROMs, optical storage devices, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention may be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0061] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0062] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0063] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1The steps for the function specified in one or more boxes.

[0064] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0065] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

[0066] The above description is merely a preferred embodiment of this embodiment and is not intended to limit this embodiment. Those skilled in the art will readily appreciate that this embodiment may be modified and varied in various ways. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of this embodiment shall be within the scope of protection of this embodiment.

Claims

1. A low-code development method based on hybrid orchestration of intelligent agents and intelligent services, characterized in that: include: Create an application form; According to the business scenario functions of the created application form, an intelligent agent is constructed to obtain the mapping information between the business scenario functions and the intelligent agent; Decompose the created application form into several sub-application forms; Determine the business scenario function of the obtained sub-application form and analyze the functional intent of the sub-application form; Based on the analysis results of functional intent, the tasks of sub-application forms are orchestrated to complete the low-code development of application forms based on the hybrid orchestration of intelligent agents and intelligent services. Among them, in the process of task orchestration, the calling object of task orchestration is determined according to the single function principle of the function intention analysis result. When the analysis result is a single function, the orchestration intelligent agent call is adopted, otherwise the orchestration intelligent service call is adopted.

2. A low-code development method based on hybrid orchestration of intelligent agents and intelligent services as described in claim 1, characterized in that: When using orchestration agent calls, agents are matched in the obtained mapping information based on the single function of the functional intent analysis result, and the task orchestration of the sub-application form is completed by calling the matched agent.

3. A low-code development method based on hybrid orchestration of intelligent agents and intelligent services as described in claim 1, characterized in that: When using orchestrated intelligent service calls, matching agents are selected from the mapping information based on the business scenario functions of the functional intent analysis results, and the task orchestration of the sub-application form is completed by calling several matching agents.

4. A low-code development method based on hybrid orchestration of intelligent agents and intelligent services as described in claim 3, characterized in that: In the process of orchestrating intelligent service calls, a hard-coded method is used to select matching intelligent agents in series to obtain intelligent services; the calling order of the intelligent agents in the intelligent services is determined according to the business scenario functions of the functional intent analysis results, and the calls of the intelligent agents are encoded in a hard-coded manner. After identifying the user intent, the intelligent service is directly called to complete the business scenario functions.

5. A low-code development method based on hybrid orchestration of intelligent agents and intelligent services as described in claim 1, characterized in that: During the task decomposition process, the created application form is comprehensively evaluated, and the comprehensive evaluation result is the sub-application form; the comprehensive evaluation includes three dimensions, namely, entity modeling of the application form, development scenario of the application form user platform, and construction of business scenario functions of the application form.

6. A low-code development method based on hybrid orchestration of intelligent agents and intelligent services as described in claim 1, characterized in that: The process of creating an application form includes creating a project, creating entity modeling, selecting a form template type, binding the form to BE, selecting displayed BE fields, creating components and forms based on the selected field information, and saving form metadata information.

7. A low-code development system based on hybrid orchestration of intelligent agents and intelligent services, characterized by: include: A creation module configured to create an application form; A construction module is configured to construct an intelligent agent according to the business scenario function of the created application form and obtain mapping information between the business scenario function and the intelligent agent; A decomposition module is configured to perform task decomposition on the created application form to obtain a plurality of sub-application forms; An analysis module configured to determine the business scenario function of the obtained sub-application form and analyze the functional intent of the sub-application form; The orchestration module is configured to perform task orchestration of sub-application forms based on the analysis results of functional intent, completing the low-code development of application forms based on the hybrid orchestration of intelligent agents and intelligent services; Among them, in the process of task orchestration, the calling object of task orchestration is determined according to the single function principle of the function intention analysis result. When the analysis result is a single function, the orchestration intelligent agent call is adopted, otherwise the orchestration intelligent service call is adopted.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the low-code development method based on hybrid orchestration of intelligent agents and intelligent services as described in any one of claims 1 to 6 are implemented.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the steps of the low-code development method based on hybrid orchestration of intelligent agents and intelligent services as described in any one of claims 1 to 6 are implemented.

10. A computer program product comprising software code, characterized in that The program in the software code executes the steps of the low-code development method based on hybrid orchestration of intelligent agents and intelligent services as described in any one of claims 1-6.

Images