Configuration method, device and system of configuration project, terminal equipment and storage medium

Abstract

The invention provides a configuration method, device and system of a configuration project, terminal equipment and a storage medium. The method comprises the following steps: acquiring a structured request sent by a client; the structured request comprises a user demand in a natural language format and a resource description list which is obtained from a resource index table and corresponds to the user demand; loading a preset structure rule template, and filling in the preset structure rule template based on the structured request to obtain a target structure rule file; calling a large language model, inputting the target structure rule file into the large language model, and obtaining response information output by the large language model; the response information is a combination of element skills; and sending the response information to the client, so that the client configures the configuration project according to the response information. According to the method, manual configuration operation of the user is not needed, the configuration process is simpler and more convenient, and the configuration efficiency of the configuration project is improved.

Description

A configuration method, apparatus, system, terminal equipment, and storage medium for configuration engineering. Technical Field

[0001] This application relates to the field of industrial automation technology, and in particular to a configuration method, apparatus, system, terminal equipment, and storage medium for configuration engineering. Background Technology

[0002] In the field of industrial automation, human-machine interface (HMI) is the core equipment for realizing monitoring, operation and analysis functions. Its design and configuration often need to be customized according to the specific needs of users.

[0003] Currently, in the configuration process of a configuration project, users often need to convert their requirements into a project program through graphical programming. That is, users need to manually complete the configuration project step by step in the configuration software by dragging and dropping controls, setting properties, and writing scripts. However, this technical solution relies entirely on manual operation by users, the configuration process is complex and prone to errors, resulting in low configuration efficiency for configuration projects.

[0004] Therefore, how to improve the configuration efficiency of configuration engineering is a technical problem that needs to be solved by those skilled in the art. Summary of the Invention

[0005] The purpose of this application is to provide a configuration method, apparatus, system, terminal equipment, computer-readable storage medium, and computer program product for configuration engineering, aiming to improve the configuration efficiency of configuration engineering.

[0006] Firstly, this application provides a configuration method for a configuration project. Applied to a server, the method includes: obtaining a structured request sent by a client; the structured request includes user requirements in natural language format and a list of resource descriptions corresponding to the user requirements obtained from a resource index table; loading a preset structure rule template and filling in the preset structure rule template based on the structured request to obtain a target structure rule file; calling a large language model, inputting the target structure rule file into the large language model, and obtaining response information output by the large language model; the response information is a combination of meta-skills; and sending the response information to the client so that the client configures the configuration project according to the response information.

[0007] In one embodiment, the step of calling the large language model, inputting the target structure rule file into the large language model, and obtaining the response information output by the large language model includes: calling the large language model through a dynamic library, inputting the target structure rule file into the large language model, and obtaining the response information output by the large language model.

[0008] In one embodiment, loading a preset structure rule template and filling in the preset structure rule template based on the structured request to obtain a target structure rule file includes: obtaining extended association information from a preset database according to the user's requirements; loading the preset structure rule template and filling in the preset structure rule template based on the structured request and the extended association information to obtain a target structure rule file.

[0009] In one embodiment, after calling the large language model, inputting the target structure rule file into the large language model, and obtaining the response information output by the large language model, the method further includes: performing a first verification operation on the response information; the first verification operation includes the relevance of the response information to the user's requirements, the legality of the response information, and the accuracy of the format; if the first verification operation passes, the method proceeds to the step of sending the response information to the client so that the client can configure the configuration project according to the response information.

[0010] Secondly, this application provides a configuration method for a configuration project. Applied to a client, the method includes: obtaining user requirements in natural language format; obtaining a list of resource descriptions corresponding to the user requirements from a resource index table; generating a corresponding structured request; and sending the structured request to a server, so that the server loads a preset structure rule template and fills in the preset structure rule template based on the structured request to obtain a target structure rule file; invoking a large language model, inputting the target structure rule file into the large language model, and obtaining response information output by the large language model; the response information is a combination of meta-skills; receiving the response information fed back by the server, and configuring the configuration project according to the response information.

[0011] In one embodiment, receiving the response information from the server and configuring the configuration project based on the response information includes: receiving the response information from the server; performing a second verification operation on the response information; the second verification operation includes the executability of the response information in the client, the completeness of the response information, and the accuracy of the format; if the second verification operation passes, configuring the configuration project based on the response information.

[0012] Thirdly, this application also provides a configuration device for a configuration project. Applied to a server, the device includes: an acquisition module for acquiring a structured request sent by a client; the structured request includes user requirements in natural language format and a list of resource descriptions corresponding to the user requirements obtained from a resource index table; a setting module for loading a preset structure rule template and filling in the preset structure rule template based on the structured request to obtain a target structure rule file; an invocation module for invoking a large language model, inputting the target structure rule file into the large language model, and acquiring response information output by the large language model; the response information is a combination of meta-skills; and a sending module for sending the response information to the client so that the client configures the configuration project according to the response information.

[0013] Fourthly, this application also provides a configuration device for a configuration project. Applied to a client, the device includes: a sending module, used to acquire user requirements in natural language format, obtain a list of resource descriptions corresponding to the user requirements from a resource index table, generate a corresponding structured request, and send the structured request to a server, so that the server loads a preset structure rule template, fills in the preset structure rule template based on the structured request, and obtains a target structure rule file; calling a large language model, inputting the target structure rule file into the large language model, and acquiring the response information output by the large language model; the response information is a combination of meta-skills; and a configuration module, used to receive the response information fed back by the server, and configure the configuration project according to the response information.

[0014] Fifthly, this application also provides a configuration system for configuration engineering, the system including a client and a server, the client and the server being communicatively connected; the client is used to obtain user requirements in natural language format, retrieve a list of resource descriptions corresponding to the user requirements from a resource index table, generate a corresponding structured request, and send the structured request to the server, so that the server loads a preset structure rule template, fills in the preset structure rule template based on the structured request, and obtains a target structure rule file; it calls a large language model, inputs the target structure rule file into the large language model, and obtains the large language model... The system includes: response information output by the language model; the response information being a combination of meta-skills; receiving the response information from the server and configuring the configuration project based on the response information; the server acquiring the structured request sent by the client; loading a preset structure rule template and filling in the preset structure rule template based on the structured request to obtain a target structure rule file; calling a large language model, inputting the target structure rule file into the large language model, and acquiring the response information output by the large language model; and sending the response information to the client so that the client can configure the configuration project based on the response information.

[0015] Sixthly, this application also provides a terminal device. The terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described above.

[0016] Seventhly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method described above.

[0017] Eighthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method described above.

[0018] This application provides a configuration system for a configuration project. After receiving a structured request from a client, a preset structured rule template is loaded, and the template is filled in based on the structured request to obtain a target structured rule file. The target structured rule file is then input into a large language model, and the response information output by the large language model is obtained. The client then configures the configuration project based on the response information. In this method, the user only needs to input user requirements in natural language format, and the large language model can convert these requirements into response information including a combination of meta-skills. The client then configures the configuration project based on the response information, eliminating the need for manual configuration by the user. This simplifies the configuration process and improves the efficiency of configuration project setup.

[0019] It is understood that the configuration device, system, terminal equipment, computer-readable storage medium and computer program product for configuration engineering provided in the embodiments of this application have the same beneficial effects as the configuration method for configuration engineering described above, and will not be repeated here. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0021] Figure 1 is a system architecture diagram of a configuration engineering system provided in an embodiment of this application; Figure 2 is a flowchart of a configuration method of a configuration engineering system provided in an embodiment of this application; Figure 3 is a flowchart of another configuration method of a configuration engineering system provided in an embodiment of this application; Figure 4 is a schematic diagram of establishing a configuration interface according to the actual needs of the factory in an embodiment of this application; Figure 5 is a schematic diagram of parameter settings for the initial running state of the configuration engineering system in an embodiment of this application; Figure 6 is a schematic diagram of the output response information of the large language model in an embodiment of this application; Figure 7 is a diagram of the execution result of the executor of the client in an embodiment of this application; Figure 8 is a structural schematic diagram of a configuration device for a configuration engineering system provided in an embodiment of this application; Figure 9 is a structural schematic diagram of another configuration device for a configuration engineering system provided in an embodiment of this application; Figure 10 is a structural schematic diagram of a terminal device provided in an embodiment of this application. Detailed Implementation

[0022] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of this application with unnecessary detail.

[0023] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0024] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0025] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0026] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0027] References to "one embodiment" or "some embodiments" in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized. "A plurality" means "two or more."

[0028] Figure 1 is a configuration system architecture diagram of a configuration project provided in an embodiment of this application. As shown in Figure 1, the configuration system of the configuration project includes a client 110 and a server 120; the client 110 and the server 120 are connected in communication; the client 110 is used to obtain user requirements in natural language format, obtain a list of resource descriptions corresponding to the user requirements from the resource index table, generate a corresponding structured request, and send the structured request to the server 120 so that the server 120 loads a preset structure rule template, fills in the preset structure rule template based on the structured request, and obtains a target structure rule file; it calls a large language model, inputs the target structure rule file into the large language model, and obtains... The system retrieves response information output by the large language model; the response information is a combination of meta-skills; it receives response information from the server 120 and configures the configuration project according to the response information; the server 120 is used to obtain structured requests sent by the client 110; it loads a preset structure rule template and fills in the preset structure rule template based on the structured request to obtain the target structure rule file; it calls the large language model, inputs the target structure rule file into the large language model, and obtains the response information output by the large language model; it sends the response information to the client so that the client 110 can configure the configuration project according to the response information.

[0029] Specifically, the client and server communicate using the HTTPS protocol; when the client and server establish communication, the server assigns a unique identifier to each client.

[0030] Big data models can be set up on the server or on other servers and communicate with the server based on the HTTPS protocol.

[0031] The dialog interface used in the client is built from an open-source front-end interface library.

[0032] In practical applications, the configuration system of a configuration project can also include a resource database; it mainly stores key data such as client file resources and dialogue records, and can also act as a resource provider for the server. After receiving a file upload request from the client, the server stores the file data corresponding to the file upload request in the resource database, and then transfers the file data to the large language model through a dynamic library.

[0033] This application provides a configuration system for a configuration project. After receiving a structured request from a client, a preset structured rule template is loaded, and the preset structured rule template is filled in based on the structured request to obtain a target structured rule file. The target structured rule file is then input into a large language model, and the response information output by the large language model is obtained. The client then configures the configuration project based on the response information. In this method, the user only needs to input user requirements in natural language format, and the large language model can convert the user requirements in natural language format into response information including a combination of meta-skills. The client configures the configuration project based on the response information, eliminating the need for manual configuration by the user. This makes the configuration process simpler and more convenient, improving the configuration efficiency of the configuration project.

[0034] This application provides a configuration method for a configuration project, which can be executed by the server when running the corresponding computer program. Figure 2 is a flowchart of a configuration method for a configuration project provided by this application. For ease of explanation, only the parts related to this embodiment are shown. The method provided by this embodiment includes the following steps: S210: Obtain a structured request sent by the client; the structured request includes user requirements in natural language format and a list of resource descriptions corresponding to the user requirements obtained from the resource index table.

[0035] A structured request refers to a standard-formatted data packet, typically in JSON format, sent from the client to the server. This structured request includes a user query and a list of resource descriptions. The user query is text in natural language format; the resource description list is a list of resource descriptions corresponding to the resource identifiers in the user query, retrieved from the resource index table. The client pre-configures the resource index table, and each functional element created in the configuration project will be registered in this table. The registered information includes, but is not limited to, the objects and attributes of various functional elements, script objects, configuration software settings, configuration project settings, and screen editing operations.

[0036] The resource description list includes description information for at least one resource object. The description information for each resource object includes at least one of the following: a unique identifier, a type, and a name. The resource object is the specific object in the configuration project that corresponds to the resource identifier mentioned in the user requirements.

[0037] For example, suppose a user request in natural language format is "In the script Script_8, write a function to increase the fan speed if the exhaust temperature exceeds 350."; its corresponding resource identifier is "Script_8". Based on this resource identifier, the corresponding resource description information is retrieved from the resource index table to obtain a list of resource descriptions.

[0038] Specifically, the user inputs their requirements in natural language format into the client's dialog interface; a resource identifier is determined based on the user's requirements, and the corresponding resource description information is retrieved from the resource index table based on the resource identifier to obtain a list of resource descriptions; then, a corresponding structured request is generated based on the user's requirements and the list of resource descriptions, and the structured request is sent to the server through a network interface such as HTTPS; the server receives the structured request from the client.

[0039] It should be noted that in practical applications, if the resource description information corresponding to the resource identifier is not found in the resource index table, the client can generate the corresponding prompt message, such as "The specified script was not found", and terminate the process to avoid generating an invalid structured request and sending the invalid structured request to the server.

[0040] S220: Load the preset structure rule template and fill in the preset structure rule template based on the structured request to obtain the target structure rule file.

[0041] Among them, the preset structure rule template refers to the pre-written text that guides the large language model on how to analyze user requirements in natural language format and output response information corresponding to the user requirements.

[0042] The preset structure rule template, such as the Prompt template, includes multiple fixed structures, such as role settings, inference rules, output format, and placeholders; the target structure rule file is the text corresponding to the current user needs, used to guide the large language model on how to analyze the user needs in natural language format and output response information corresponding to the user needs.

[0043] In this step, the server loads a preset structure rule template, fills in the placeholders with the user requirements and resource description list from the currently determined structured request, and obtains the target structure rule file.

[0044] In a specific example, the user query in natural language format is filled into the [Input] section of the preset structure rule template; the resource description list (context_resources) in the structured request is converted into a new format and filled into the [Element Resource] section of the preset structure rule template to obtain the target structure rule file.

[0045] S230: Call the large language model, input the target structure rule file into the large language model, and obtain the response information output by the large language model; the response information is a combination of meta-skills.

[0046] Meta-skills refer to predefined, standardized operational instructions, such as creating pages, adding, deleting, modifying, and querying controls and scripts, script writing, commenting, and optimization.

[0047] Large language models refer to a type of artificial intelligence model for natural language processing and code generation. The main function of a large language model is to perform reasoning on input requests from the server, output response information, and then return the response information to the server.

[0048] It should be noted that the response information is generally a JSON-formatted array, with each array element identifying a meta-skill; that is, the response information is a combination of meta-skills. In a specific example, the format of the response information is [{"ExecutorType":"Executor Type","Executor":{"id":"Number","name":"Name"},"Comtype":"Command Type","Command":{"Skill":"Operation"}}]. S240: Send the response information to the client so that the client can configure the configuration project according to the response information.

[0049] Specifically, after receiving the response information, the server sends the response information to the client; the client determines the corresponding meta-skill based on the response information, and calls the corresponding application programming interface of the configuration software to execute the meta-skill, adjust and configure the functional components in the configuration project, so as to configure the configuration project.

[0050] Configuration engineering refers to the configuration of industrial application scenarios, such as factory exhaust fan control systems and workshop monitoring systems. Functional components are the basic functional units that make up a configuration engineering system; these include graphical components, such as screens (pages), buttons, text boxes, dashboards, trend graphs, pipeline animations, and other controls, as well as data components, such as script data, variable parameters, alarm definitions, data logging recipes, and report templates.

[0051] Specifically, after obtaining the response information, the client determines multiple meta-skills based on the response information; classifies each meta-skill, and for different types of meta-skills, uses the corresponding actuator to call the application programming interface of the configuration software to set the corresponding functional elements in the configuration software and complete the configuration of the configuration project.

[0052] In practical applications, after configuring the configuration project, the client then synchronously updates the local resource index table.

[0053] This application provides a configuration method for a configuration project. After receiving a structured request sent by a client, a preset structure rule template is loaded, and the preset structure rule template is filled in based on the structured request to obtain a target structure rule file. The target structure rule file is then input into a large language model, and the response information output by the large language model is obtained. The client then configures the configuration project based on the response information. In this method, the user only needs to input user requirements in natural language format, and the large language model can convert the user requirements in natural language format into response information including a combination of meta-skills. The client configures the configuration project based on the response information, eliminating the need for manual configuration by the user. This makes the configuration process simpler and more convenient, improving the configuration efficiency of the configuration project.

[0054] Based on the above embodiments, this embodiment further explains and optimizes the technical solution. Specifically, in this embodiment, calling the large language model, inputting the target structure rule file into the large language model, and obtaining the response information output by the large language model includes: calling the large language model through a dynamic library, inputting the target structure rule file into the large language model, and obtaining the response information output by the large language model.

[0055] Specifically, the server calls a function provided by the dynamic library, passing the target structure rule file as a parameter. The dynamic library sends the target structure rule file to the large language model server via HTTPS and waits for a response. Upon receiving the target structure rule file, the large language model server uses the large language model to determine the corresponding response information and sends it to the dynamic library. The dynamic library then returns the response information to the server. Here, a dynamic library refers to packaging a series of complex code logics, such as network communication, data formatting, and error handling, into a clearly defined, simple-interface functional module. In practical applications, the server encapsulates the use of the large language model into a dynamic library, including functions such as natural language dialogue, file upload, and large model parameter settings.

[0056] In this embodiment, the large language model is called through a dynamic library. When it is necessary to change the large language model or the application interface, only the encapsulated dynamic library needs to be modified, which can improve the configuration flexibility of the configuration project.

[0057] Based on the above embodiments, this embodiment further explains and optimizes the technical solution. Specifically, in this embodiment, loading a preset structure rule template and filling in the preset structure rule template based on a structured request to obtain a target structure rule file includes: obtaining extended association information from a preset database according to user needs; loading a preset structure rule template and filling in the preset structure rule template based on a structured request and extended association information to obtain a target structure rule file.

[0058] The preset database refers to a database stored on the server or client side that contains a large number of complete user requirements. Extended related information refers to supplementary knowledge or data retrieved from the preset database that is semantically or functionally related to the current user requirement. When the user requirement involves a specific function, such as "alarms," ​​the extended related information includes standard alarm function prototypes, parameter descriptions, or typical alarm handling process examples extracted from the database. When the user requirement is ambiguous, such as "code optimization," the extended related information includes code optimization rules or historical code optimization-related text.

[0059] Specifically, after receiving a structured request, the server performs semantic analysis on the user requirements in the structured request to obtain keywords or requirement information; based on the keywords or requirement information, it searches for corresponding extended related information from a preset database; when generating the target structure rule file, it fills the placeholders in the preset structure rule template with the user requirements, resource description list and extended related information from the structured request to obtain the target structure rule file.

[0060] According to the method of this embodiment, when the information required by the user is incomplete, extended related information is obtained from a preset database, and the target structure rule file is determined based on the structured request and the extended related information, so that the data information in the target structure rule file is more complete, thereby improving the accuracy of the determined response information.

[0061] Based on the above embodiments, this embodiment further explains and optimizes the technical solution. Specifically, in this embodiment, after calling the large language model, inputting the target structure rule file into the large language model, and obtaining the response information output by the large language model, the method further includes: performing a first verification operation on the response information; the first verification operation includes the relevance of the response information to the user's requirements, the legality of the response information, and the accuracy of the format; if the first verification operation passes, the step of sending the response information to the client is executed so that the client can configure the configuration project according to the response information is executed.

[0062] In this embodiment, the first verification operation refers to the verification operation performed by the server on the response information. That is, before sending the response information output by the large language model to the client, the server first performs pre-checking and cleaning filtering on the response information.

[0063] Specifically, if the server performs the first verification operation on the response information and it passes, the response information will be sent to the client; otherwise, if the response information is determined to be incorrect, the obtained response information will be discarded, or the reason why the verification operation failed will be displayed.

[0064] In this embodiment, the first verification operation includes any one or a combination of two or more of the following operations: Relevance of the response information to the user's needs: Determining the semantic and intentional relevance of the combination of meta-skills to the user's needs. Specifically, keyword matching can be used to determine whether the combination of meta-skills can solve the user's problem. For example, if the user's need is "write a script," but the response information is the meta-skill "create a button," then the response information is irrelevant to the user's need; if the user's need is the operation "screen A," but the executor of the meta-skill in the response information is "screen B," then the response information is irrelevant to the user's need.

[0065] Response information validity: Determine whether the meta-skills and their parameters in the response information conform to the system's predefined business rules and constraints. Specifically, this can be done by checking whether the name of the meta-skill in the response information can be found in the predefined meta-skill document list, and whether the parameter values ​​corresponding to the meta-skill are within the allowed range, etc.

[0066] Response information format accuracy: Determine whether the response information strictly conforms to the data structure specified in the [Output] section of the technical disclosure document. This includes determining whether the response information is in JSON format and whether each object in the array within the response information contains the pre-defined required fields.

[0067] In this embodiment, the server sends the response information to the client only after the first verification operation of the response information is passed, ensuring the validity of the response information and preventing the client from using invalid response information to perform configuration operations on the configuration project, thus avoiding waste of processing resources.

[0068] Based on the above embodiments, this embodiment further explains and optimizes the technical solution. Specifically, in this embodiment, the preset structure rule template includes: role limitation, answer range, preprocessing, element resources, reasoning rules, input placeholders, meta-skills, and output format.

[0069] The role definition specifies the role that the large model plays. For example, "You are now playing the role of a developer who is proficient in software development, JS and Qt code writing, and you should also be familiar with the content of all uploaded documents."

[0070] The scope of responses is limited to the scope of responses for the large model. For example, "Only skill-related questions that exist in the document 'Meta-Skills' can be answered; other questions are prohibited from being answered and will be handled according to the error handling document."

[0071] Preprocessing is a task that guides large language models before inference. For example, preprocessing is performed in the following steps: 1. First, understand the core syntax of the ECMAScript 3 version in the JS code.

[0072] 2. Parse the content of all uploaded documents.

[0073] 3. Understand the content and purpose of all documents.

[0074] Element resources are resources provided by the client. Resource format parsing method: {"Widget(control)":[{"id":"element number","screenid":"screen number","name":"name"}],"(Script) script":[{"id":"number","name":"name"}]}.

[0075] Inference rules refer to the logical chains and rules that guide the inference of large language models.

[0076] Input placeholders: Upon receiving a user request in natural language format from the client, the content in the placeholders is replaced with that user request. Meta-skills represent the skills that the large language model can implement; the output of the large language model is a combination of meta-skills. Examples include creating various pages, controls, and scripts (CRUD operations), script writing, commenting, and optimization. The data structure of a meta-skill is: {"Executor Type Number": [{"Command Type": [{"Skill Name":"Name","Skill Function":"Explanation","Candidate Value":[Candidate Value Content (empty if no candidate value)]}]}].

[0077] Output format specifies the output content and format of the large language model. For example, the large language model should output in the following format: 1. JSON format: [{"ExecutorType":"Executor type","Executor":{"id":"ID","name":"Name"},"Comtype":"Command type","Command":{"Skill":"Operation"}}]; 2. The response output should be in JSON format, as shown above; 3. Outputting `json` is prohibited.

[0078] Additionally, the preset structure rule template may include: examples, dialogue examples provided for use by large language models for inference. For example, "Please refer to the uploaded 'Example' document for the requirements of [input] and return the output."

[0079] Error handling guides the output content after a language model makes a reasoning error or a request fails to meet requirements. For example, "Please comply with ethics and regulations, and output the error according to the uploaded error handling document."

[0080] Based on the above embodiments, this embodiment further explains and optimizes the technical solution. Specifically, in this embodiment, the reasoning rules include: 1. Input range verification rules: Analyze whether the user requirements corresponding to the [input] conform to the [answer range]. If not, refer to error handling; 2. Element parsing rules: Parse elements such as "element resource", "executor type", "executor", and "command type" from the user requirements in the [input]. When parsing "element resource", refer to the [element resource] in the target structure rule file for querying. If the object exists in the [element resource], return the object's unique identifier (id) and name (name); if the user requirements corresponding to the [input] include an addition requirement, it is also necessary to find the added object executor; if neither of them exists, the default returned object's id and name are NULL; 3. Type and skill coding mapping rules: including: 3.1 Coding mapping: Based on system documents such as "Executor Type" and "Command Type", convert the parsed "Executor Type" and "Command Type" into corresponding standard numbers and codes, such as executor type number and command type code; 3.2 Skill Mapping and Decomposition: Based on the executor type and command type, query the "Meta-Skills" document, analyze the skill code, and return the attribute code when answering; 3.3 Specific Task Executor Attribution: It is stipulated that for all engineering structure resources, such as screens, sub-screens, pop-up screens, template screens, variable groups, scripts, recipes, reports, etc., the executor type for adding, deleting, and renaming operations is "Project (Main)"; 4. Domain Knowledge Constraint Rules: When the user requirements include code writing functions, the reasoning must refer to the uploaded "Script Built-in Function Usage Manual", "Script Writing Rules", "Examples", and other documents to ensure that the generated code conforms to the specifications of the specific configuration environment.

[0081] 5. Operation Priority Rules: If the user request involves add, rename, or delete operations, they should be arranged in priority order, and the output instruction sequence must also be arranged in priority order; the priority order is as follows: Add > Rename > Delete; 6. User Request Processing Rules; 6.1 If the user request corresponding to [Input] includes a request to add a functional component, this request is only responsible for adding, and the value of Command in the returned response information is specified as {"id":number,"name":"NULL"}; 6.2 If the user request corresponding to [Input] includes a request to modify a screen, sub-screen, pop-up screen, template screen, variable group, script, recipe, or report name, except for adding functional requirements, the renamed object in the returned response needs to use the new name; 6.3 If the user request corresponding to [Input] includes a request to optimize code or add code comments, if no code is provided, the specific response format {"skill":"operation"} should be returned directly in the JSON response for this function as {"getcode":"NULL"} to guide the user to provide the code, and [] should not be returned; 6.4 If [Input] The corresponding user requirements include the need to add code comments; there is no need to judge whether the code is correct or conforms to the rules. 7. Output Rules; 7.1 Output Data Structure: The JSON data ID of all added function requirements' response information will automatically increment starting from 10000, and the name value will be fixed as "NULL"; 7.2 Command Merging and Optimization: If multiple commands in the response have the same executor type, executor, and command type, please merge the responses. If it is a script, please format the code accordingly; 7.3 Output Format: The output must strictly comply with the JSON format specification requirements defined in [Output]; 7.4 Handling Escape Characters: All escape characters in the response information will be standardized, such as replacing '\\\n', '\\\\', '\\\ / ' with '\n', '\\', '\ / ' to ensure the accuracy of the generated string; any additional formatting tags (such as "json") are prohibited.

[0082] The inference rules provided in this embodiment can ensure that the large language model outputs response information that corresponds to the user's needs efficiently and accurately, so that the client can configure the configuration project according to the response information.

[0083] Another configuration method for a configuration project provided in this application embodiment can be executed by the client when running the corresponding computer program. Figure 3 is a flowchart of another configuration method for a configuration project provided in this application embodiment. For ease of explanation, only the parts related to this embodiment are shown. The method provided in this embodiment includes the following steps: S310: Obtain user requirements in natural language format, obtain the resource description list corresponding to the user requirements from the resource index table, generate the corresponding structured request, and send the structured request to the server so that the server loads the preset structure rule template and fills in the preset structure rule template based on the structured request to obtain the target structure rule file; call the large language model, input the target structure rule file into the large language model, and obtain the response information output by the large language model; the response information is a combination of meta-skills; S330: Receive the response information fed back by the server and configure the configuration project according to the response information.

[0084] This application provides a configuration method for a configuration project. After receiving a structured request sent by a client, a preset structure rule template is loaded, and the preset structure rule template is filled in based on the structured request to obtain a target structure rule file. The target structure rule file is then input into a large language model, and the response information output by the large language model is obtained. The client then configures the configuration project based on the response information. In this method, the user only needs to input user requirements in natural language format, and the large language model can convert the user requirements in natural language format into response information including a combination of meta-skills. The client configures the configuration project based on the response information, eliminating the need for manual configuration by the user. This makes the configuration process simpler and more convenient, improving the configuration efficiency of the configuration project.

[0085] Based on the above embodiments, this embodiment further explains and optimizes the technical solution. Specifically, in this embodiment, receiving response information from the server and configuring the configuration project according to the response information includes: receiving response information from the server; performing a second verification operation on the response information; the second verification operation includes the executability of the response information in the client, the completeness of the response information, and the accuracy of the format; if the second verification operation passes, configuring the configuration project according to the response information.

[0086] In this embodiment, the second verification operation refers to the verification operation performed by the client on the response information. That is, before calling the application programming interface (API) of the configuration software to execute the meta-skill, the client performs executability verification on the received response information.

[0087] Specifically, if the client passes the second verification operation on the response information, the application programming interface (API) of the configuration software is called to execute the meta-skill; otherwise, it is determined that there is a problem with the executability of the response information, so the response information obtained this time is discarded, or the reason why the verification operation failed is indicated.

[0088] In this embodiment, the second verification operation includes any one or a combination of two or more of the following operations: Executability of the response information on the client: Determining whether the client has the ability to execute each meta-skill in the response information. Specifically, this can involve determining whether the client's local meta-skill library contains the names of each meta-skill in the response information; determining whether the client has registered a submodule executor to process the skill; and determining whether the client has the application programming interface (API) of the configuration software mapped to each meta-skill, etc.

[0089] Completeness of Response Information: It is understood that for a client to successfully execute a meta-skill, all necessary preconditions or dependent steps must be met. In this embodiment, based on prior knowledge, the client knows that executing meta-skill A requires the successful execution of meta-skills B and C first. Therefore, when the response information includes meta-skill A, the client needs to check whether the response information contains all necessary prerequisite meta-skills B and C, and whether the execution order is accurate. If meta-skills B and C are not included, or the execution order is inaccurate, the client cannot execute meta-skill A normally, indicating that the response information is incomplete.

[0090] Response information format accuracy: Validate the data structure of the response information; including determining whether the validation parameter values ​​in the array of the response information are valid, and whether each object in the array of the response information contains the pre-required fields, etc.

[0091] In this embodiment, the client performs a second verification operation on the response information to ensure that the client's current operating environment can safely and completely execute the meta-skills in the response information, preventing configuration engineering failure or abnormality due to execution failure.

[0092] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be described in detail below with reference to actual application scenarios. For example, in a factory, there are motors and exhaust fans. When the exhaust temperature reaches a certain threshold, it is necessary to adjust the speed of the exhaust fan or the power of the motor.

[0093] Figure 4 is a schematic diagram of the configuration interface established according to the actual needs of the factory in this embodiment. The configuration interface is established in advance according to the actual needs of the factory; the initial running state of the configuration project is determined, and the parameter setting diagram of the initial running state of the configuration project is shown in Figure 5; a preset structure rule template is pre-built in the server; wherein, the preset structure rule template includes role restrictions, answer range, preprocessing, element resources, inference rules, input placeholders, meta-skills, and output format; the specific steps of a configuration method for a configuration project are as follows: the user inputs user requirements using natural language in the client's dialog interface; for example: "Please complete the adaptive temperature adjustment function in the Script_8 script. When the program is in the startup state, please monitor whether the exhaust temperature exceeds 350 degrees. If it is higher, increase..." The fan speed is set to the upper limit of 1000 rpm. If the exhaust temperature is still too high after the fan speed reaches the upper limit, the main unit power is reduced. The main unit power cannot be lower than the lower limit of 15 rpm. The client parses the user requirements, identifies the resource identifiers corresponding to the current configuration project, and obtains the resource description list corresponding to the resource identifiers from the resource index table. Based on the user requirements and the resource description list, a structured request is generated and sent to the server. The server receives the structured request and loads the preset structure rule template from the storage. The preset structure rule template contains fixed structures (such as [role setting], [reasoning rules], [output format]) and variable placeholders for filling (such as [element resources], [input]). The resource description list (context_resources) is formatted and filled into the [Element Resource] section of the template; the user requirement (user_query) is filled into the [Input] section of the template; a target structure rule file is generated; the server calls the large language model through the encapsulated dynamic library and sends the target structure rule file as input to the large language model; the large language model generates corresponding response information based on the target structure rule file; the response information is a combination of meta-skills; Figure 6 is a schematic diagram of the large language model outputting response information. The server obtains the response information and performs a first verification operation on the response information; if the first verification operation passes, the response information is sent to the client; Figure 7 is a diagram of the execution result of the client's executor. The client performs a second verification operation on the response information; if the second verification operation passes, the meta-skills in the response information are classified, and different types of executors are used to execute different meta-skills; the executor calls the API of the configuration software corresponding to the meta-skill to present the corresponding functional components in the configuration project; the functional components include controls, pages, or script code.

[0094] Running the configuration project and selecting the adaptive temperature control function, we can observe that the initial exhaust temperature is 100°C, the exhaust fan speed is 500 rpm, and the main unit power is 102 kW. The exhaust temperature continues to rise, reaching the temperature threshold of 350°C. When the exhaust temperature exceeds the temperature threshold of 350°C, the ordering fan is adjusted first. The exhaust fan speed increases to 600 rpm, at which point the exhaust temperature drops to 275°C. The exhaust fan speed continues to increase to the upper limit of 1000 rpm, but the exhaust temperature continues to rise to 500°C, indicating that the adjustment through the exhaust fan has failed. After the first stage of adjustment fails, the main unit power is adjusted, reducing it to 100 kW. Gradually reducing the main unit power, the exhaust temperature continues to decrease and remains within the normal range, indicating that the adaptive temperature control is complete.

[0095] This application provides a configuration method for a configuration project. After receiving a structured request sent by a client, a preset structure rule template is loaded, and the preset structure rule template is filled in based on the structured request to obtain a target structure rule file. The target structure rule file is then input into a large language model, and the response information output by the large language model is obtained. The client then configures the configuration project based on the response information. In this method, the user only needs to input user requirements in natural language format, and the large language model can convert the user requirements in natural language format into response information including a combination of meta-skills. The client configures the configuration project based on the response information, eliminating the need for manual configuration by the user. This makes the configuration process simpler and more convenient, improving the configuration efficiency of the configuration project.

[0096] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0097] It should be noted that the information collection process (such as the facial image collection process, fingerprint information collection process, etc.) / feature extraction process involved in this application is carried out with the user's knowledge and permission. That is, the information collection process / feature extraction process complies with the requirements of laws and regulations and does not constitute an act that harms the public interest.

[0098] Figure 8 shows a schematic diagram of a configuration device for a configuration project provided in an embodiment of this application. As shown in Figure 8, the configuration device for a configuration project in this embodiment includes an acquisition module 810, a setting module 820, a calling module 830, and a sending module 840. The acquisition module 810 is used to acquire a structured request sent by a client. The structured request includes user requirements in natural language format and a list of resource descriptions corresponding to the user requirements obtained from a resource index table. The setting module 820 is used to load a preset structure rule template and fill in the preset structure rule template based on the structured request to obtain a target structure rule file. The calling module 830 is used to call a large language model, input the target structure rule file into the large language model, and acquire the response information output by the large language model. The response information is a combination of meta-skills. The sending module 840 is used to send the response information to the client so that the client can configure the configuration project according to the response information.

[0099] The configuration device for configuration engineering provided in this application embodiment has the same beneficial effects as the configuration method for configuration engineering described above.

[0100] In one embodiment, the calling module 830 includes a calling submodule, which is used to call the large language model through a dynamic library, input the target structure rule file into the large language model, and obtain the response information output by the large language model.

[0101] In one embodiment, the setting module 820 includes: an extended association information acquisition submodule, used to acquire extended association information from a preset database according to user needs; and a setting submodule, used to load a preset structure rule template and fill in the preset structure rule template based on the structured request and extended association information to obtain a target structure rule file.

[0102] In one embodiment, a configuration device for a configuration engineering system further includes: a first verification operation submodule, used to perform a first verification operation on the response information; the first verification operation includes the relevance of the response information to the user's requirements, the legality of the response information, and the accuracy of the format; if the first verification operation passes, the sending module 840 is invoked.

[0103] Figure 9 shows a schematic diagram of another configuration device for a configuration project provided in this embodiment. As shown in Figure 9, the configuration device for the configuration project in this embodiment includes a sending module 910 and a configuration module 920. The sending module 910 is used to obtain user requirements in natural language format, obtain a list of resource descriptions corresponding to the user requirements from the resource index table, generate a corresponding structured request, and send the structured request to the server so that the server loads a preset structure rule template and fills in the preset structure rule template based on the structured request to obtain a target structure rule file; it calls a large language model, inputs the target structure rule file into the large language model, and obtains the response information output by the large language model; the response information is a combination of meta-skills; the configuration module 920 is used to receive the response information fed back by the server and configure the configuration project according to the response information.

[0104] The configuration device for configuration engineering provided in this application embodiment has the same beneficial effects as the configuration method for configuration engineering described above.

[0105] In one embodiment, the configuration module 920 includes: a response information receiving submodule for receiving response information from the server; a second verification operation submodule for performing a second verification operation on the response information; the second verification operation includes the executability of the response information in the client, the integrity of the response information, and the accuracy of the format; if the second verification operation passes, the configuration project is configured according to the response information.

[0106] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0107] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0108] Figure 10 is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. As shown in Figure 10, the terminal device 1000 of this embodiment includes a memory 1010, a processor 1020, and a computer program 1030 stored in the memory 1010 and executable on the processor 1020; when the processor 1020 executes the computer program 1030, it implements the steps in the configuration method embodiments of the above-mentioned configuration projects; or when the processor 1020 executes the computer program 1030, it implements the functions of each module / unit in the above-mentioned device embodiments.

[0109] For example, the computer program 1030 can be divided into one or more modules / units, and one or more modules / units are stored in the memory 1010 and executed by the processor 1020 to implement the method of the embodiments of this application. One or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program 1030 in the terminal device 1000. For example, the computer program 1030 can be divided into an acquisition module, a setting module, a calling module, and a sending module. The specific functions of each module are as follows: the acquisition module is used to acquire a structured request sent by the client; the structured request includes user requirements in natural language format and a list of resource descriptions corresponding to the user requirements obtained from a resource index table; the setting module is used to load a preset structure rule template and fill in the preset structure rule template based on the structured request to obtain a target structure rule file; the calling module is used to call a large language model, input the target structure rule file into the large language model, and acquire the response information output by the large language model; the response information is a combination of meta-skills; the sending module is used to send the response information to the client so that the client configures the configuration project according to the response information.

[0110] In applications, terminal device 1000 can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. Terminal device 1000 may include, but is not limited to, memory 1010 and processor 1020. Those skilled in the art will understand that Figure 10 is merely an example of a terminal device and does not constitute a limitation on the terminal device. It may include more or fewer components than shown, or combine certain components, or different components. For example, terminal device may also include input / output devices, network access devices, buses, etc.; wherein, input / output devices may include cameras, audio acquisition / playback devices, displays, etc.; network access devices may include communication modules for wireless communication with external devices.

[0111] In applications, the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0112] In applications, memory can be an internal storage unit of a terminal device, such as its hard drive or RAM; it can also be an external storage device, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card; or it can include both internal and external storage units. Memory is used to store operating systems, applications, boot loaders, data, and other programs, such as computer program code. Memory can also be used to temporarily store data that has been output or will be output.

[0113] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement the steps in the above-described method embodiments.

[0114] This application implements all or part of the processes in the methods of the above embodiments, which can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to a terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, such as a USB flash drive, a portable hard drive, a magnetic disk, or an optical disk.

[0115] The computer-readable storage medium provided in this application embodiment has the same beneficial effects as the configuration method of the above-described configuration engineering.

[0116] This application also provides a computer program product, including a computer program that, when executed by a processor, can implement the steps in the various method embodiments described above.

[0117] The computer program product provided in this application embodiment has the same beneficial effects as the configuration method of the above-described configuration engineering.

[0118] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0119] Those skilled in the art will recognize that the device and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0120] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interface, or the device may be indirectly coupled or communicated, and may be electrical, mechanical, or other forms.

[0121] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A configuration method for a configuration engineering system, characterized in that, Applied to the server side, the method includes: obtaining a structured request sent by a client; the structured request includes user requirements in natural language format and a list of resource descriptions corresponding to the user requirements obtained from a resource index table; loading a preset structure rule template and filling in the preset structure rule template based on the structured request to obtain a target structure rule file; calling a large language model, inputting the target structure rule file into the large language model, and obtaining response information output by the large language model; the response information is a combination of meta-skills; and sending the response information to the client so that the client configures the configuration project according to the response information.

2. The method according to claim 1, characterized in that, The step of calling the large language model, inputting the target structure rule file into the large language model, and obtaining the response information output by the large language model includes: calling the large language model through a dynamic library, inputting the target structure rule file into the large language model, and obtaining the response information output by the large language model.

3. The method according to claim 1, characterized in that, The process of loading a preset structure rule template and filling in the preset structure rule template based on the structured request to obtain a target structure rule file includes: obtaining extended association information from a preset database according to the user's requirements; loading a preset structure rule template and filling in the preset structure rule template based on the structured request and the extended association information to obtain a target structure rule file.

4. The method according to claim 1, characterized in that, After invoking the large language model, inputting the target structure rule file into the large language model, and obtaining the response information output by the large language model, the method further includes: performing a first verification operation on the response information; the first verification operation includes the relevance of the response information to the user's requirements, the legality of the response information, and the accuracy of the format; if the first verification operation passes, the method proceeds to the step of sending the response information to the client so that the client can configure the configuration project according to the response information.

5. A configuration method for a configuration engineering system, characterized in that, Applied to a client, the method includes: obtaining user requirements in natural language format; obtaining a list of resource descriptions corresponding to the user requirements from a resource index table; generating a corresponding structured request; and sending the structured request to a server, so that the server loads a preset structured rule template and fills in the preset structured rule template based on the structured request to obtain a target structured rule file; invoking a large language model, inputting the target structured rule file into the large language model, and obtaining response information output by the large language model; the response information is a combination of meta-skills; receiving the response information fed back by the server, and configuring the configuration project according to the response information.

6. The method according to claim 5, characterized in that, The step of receiving the response information from the server and configuring the configuration project according to the response information includes: receiving the response information from the server; performing a second verification operation on the response information; the second verification operation includes the executability of the response information in the client, the completeness of the response information, and the accuracy of the format; if the second verification operation passes, configuring the configuration project according to the response information.

7. A configuration device for a configuration engineering system, characterized in that, The device, applied on the server side, includes: an acquisition module for acquiring a structured request sent by a client; the structured request includes user requirements in natural language format and a list of resource descriptions corresponding to the user requirements obtained from a resource index table; a setting module for loading a preset structure rule template and filling in the preset structure rule template based on the structured request to obtain a target structure rule file; an invocation module for invoking a large language model, inputting the target structure rule file into the large language model, and acquiring response information output by the large language model; the response information is a combination of meta-skills; and a sending module for sending the response information to the client so that the client can configure the configuration project according to the response information.

8. A configuration system for configuration engineering, characterized in that, The system includes a client and a server, and the client and the server are connected in communication. The client is used to obtain user requirements in natural language format, obtain a list of resource descriptions corresponding to the user requirements from the resource index table, generate a corresponding structured request, and send the structured request to the server so that the server loads a preset structure rule template and fills in the preset structure rule template based on the structured request to obtain a target structure rule file. Call the large language model, input the target structure rule file into the large language model, and obtain the response information output by the large language model; The response information is a combination of meta-skills; the server receives the response information from the server and configures the configuration project according to the response information; the server is used to obtain the structured request sent by the client; Load the preset structure rule template, and fill in the preset structure rule template based on the structured request to obtain the target structure rule file; The target structure rule file is input into the large language model, and the response information output by the large language model is obtained. The response information is then sent to the client so that the client can configure the configuration project according to the response information.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 4 or 5 to 6.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 4 or 5 to 6.

Images