Intelligent algorithm development auxiliary tool for Lingpivot plasma control system

Abstract

The invention discloses an intelligent algorithm development auxiliary tool for a Lingpivot plasma control system, which belongs to the technical field of plasma control systems and comprises a visualization module, an AI question and answer module and a WebView panel. The visualization module is used for analyzing a PCS project directory, generating an interactive view based on WebView, and supporting architecture analysis, file generation, code navigation and bidirectional editing synchronization; the AI question and answer module adopts a locally deployed retrieval enhancement generation system and is combined with a PCS knowledge vector database to provide field-specific query answers; and the WebView panel is used for serving as an interactive page of a user with the visualization module and the AI question and answer module, rendering a tree view and an organizational structure diagram of the visualization module, and displaying questions and answers of the AI question and answer module. According to the method, complex parameter configuration and multi-file management are simplified, and the operation time is remarkably shortened.

Description

Technical Field

[0001] This invention belongs to the field of plasma control system (PCS) technology, specifically relating to an intelligent algorithm development auxiliary tool for the Ling Shu plasma control system. Background Technology

[0002] The plasma control system (PCS) is a core technology for achieving controlled nuclear fusion in tokamak devices. It precisely controls the plasma discharge process to ensure the stability, safety, and efficiency of the experiment. The Ling Shu plasma control system, designed specifically for the China Fusion Engineering Experimental Reactor (CFETR) and validated on the EAST superconducting tokamak device, employs a component-based distributed control framework. The core control logic is implemented in C++, the user interface is defined using Interface Description Language (IDL), and parameter configuration is stored using Extensible Markup Language (XML). Its control algorithm development involves complex parameter definitions, multi-file management, and real-time framework integration. The algorithm needs to be registered with the data engine to support efficient data access and real-time processing.

[0003] In traditional development models, developers must manually edit multiple configuration files and parameter definitions, resulting in a cumbersome and error-prone development process and low efficiency. On one hand, existing tools lack user-friendly visual interfaces, making it difficult for developers to intuitively understand the architecture of the Ling Shu plasma control system (including the hierarchical relationships of control categories, control algorithms, and data subsets), leading to long development cycles and high learning curves. On the other hand, the lack of highly automated and intelligent development tools to assist in control algorithm development means that parameter configuration, file generation, and code integration rely on manual operations, involving repetitive tasks, increasing the risk of errors, and failing to meet the demands of rapid iteration. Developers must consult numerous documents or rely on expert guidance, resulting in low knowledge acquisition efficiency and impacting development progress. The existing development model limits the efficiency and engineering level of control algorithm development in the Ling Shu plasma control system. Summary of the Invention

[0004] To solve the above-mentioned technical problems, the present invention adopts the following technical solution:

[0005] A smart algorithm development aid tool for the Ling Shu plasma control system includes: a visualization module, an AI question-and-answer module, and a WebView panel;

[0006] The visualization module is used to parse the PCS project directory and generate an interactive view based on WebView, supporting architecture parsing, file generation, code navigation, and bidirectional editing synchronization; the visualization module includes: PCS architecture tree building module, change content parsing module, and automated content generation module;

[0007] The AI ​​question-answering module uses a locally deployed retrieval enhancement generation system, combined with the PCS knowledge vector database, to provide domain-specific query answers;

[0008] The WebView panel serves as the interaction page between the user and the visualization and AI Q&A modules. It renders the tree view and organizational chart of the visualization module and displays the questions and answers from the AI ​​Q&A module.

[0009] The present invention has the following beneficial effects:

[0010] This invention solves the problem of lacking an intuitive visual interface by enabling code-view interaction. Through the Language Services Protocol (LSP), it allows users in the integrated development environment (VS Code) to jump from a variable of a custom control type in a control algorithm file to the corresponding content in the Extensible Markup Language (XML) file that defines that variable. Simultaneously, it provides an "Open in PlasmaX" function to locate the variable in the code to the architecture node in the visual view, achieving seamless code-view interaction, improving interaction efficiency, and providing a more intuitive development experience.

[0011] This invention addresses the issue of insufficient automation through an automated file generation method. It integrates an IDL (Interactive Data Language) compiler and algorithm templates to automatically generate C++ source code, IDL files, and configuration files, and registers variables with the data engine. Users can generate a complete code framework simply by inputting parameters in the WebView, a process that takes only a few seconds. Compared to manually writing IDL and code, this saves over 90% of the time and significantly improves the level of engineering sophistication.

[0012] This invention addresses the lack of domain-specific intelligent support through RAG (Retrieval Enhanced Generation)-driven intelligent question-answering functionality. Based on a locally deployed vector database and a large language model (DeepSeek-R1), combined with PCS domain documents (such as technical manuals and experimental reports), this invention provides targeted technical guidance. Users input queries (e.g., "How to configure plasma current parameters"), and the system generates answers in real time, improving efficiency several times compared to manually consulting documents and significantly lowering the learning curve.

[0013] This invention solves the problems of cumbersome parameter configuration and multi-file management through a visual parameter editing and architecture management method. Based on the VS Code embedded web view interface (WebView API), this invention provides an interactive view rendering PCS architecture, supporting form-based parameter editing and keyword filtering. After the user edits parameters or the architecture in the WebView, the plugin automatically updates the files. Compared to the tedious process of traditional manual file editing, PlasmaX simplifies complex parameter configuration and multi-file management, significantly reducing operation time. Attached Figure Description

[0014] Figure 1 This is a schematic diagram of the overall functional architecture modules of the present invention.

[0015] Figure 2 This is a diagram illustrating the structure and workflow of the visualization module of the present invention;

[0016] Figure 3 Here is a flowchart of the interaction between code and view in the visualization module of the present invention; wherein, (a) is a flowchart of the code navigation of the visualization module, (b) is a flowchart of the jump definition of the visualization module, and (c) is a flowchart of the positioning of the visualization module in the plug-in view.

[0017] Figure 4 This is a diagram illustrating the structure and workflow of the AI ​​question-answering module of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.

[0019] This invention proposes PlasmaX (hereinafter referred to as a plugin), an intelligent algorithm development aid tool for the Ling Shu Plasma Control System (PCS). It is a VS Code (Visual Studio Code, a free and open-source cross-platform code editor) plugin for developing control algorithms for the PCS. It integrates a visualization module and a search-enhanced generation (RAG)-driven intelligent question-answering module, solving traditional development problems through a visual interface, automated processes, and intelligent support. The technical solution of this invention is described in detail below with flowcharts and principle diagrams.

[0020] The intelligent algorithm development aid tool for the Ling Shu plasma control system of the present invention includes: a visualization module and an AI question-and-answer module.

[0021] The overall architecture of this invention uses an embedded WebView panel as the core interactive page, integrating a visualization module, an AI (artificial intelligence) question-answering module, and the WebView panel to form a collaborative intelligent development environment, such as... Figure 1 As shown.

[0022] The visualization module parses the PCS project directory to generate interactive views (tree diagrams and organizational charts) based on WebView, supporting architecture parsing, file generation, code navigation (including jumping to definitions and locating in the plugin view), and bidirectional editing synchronization. The AI ​​question-and-answer module uses a locally deployed search-enhanced generation (RAG) system combined with the PCS knowledge vector database to provide domain-specific query answers. The WebView panel serves as the interaction page between the user and the visualization and AI question-and-answer modules, rendering the tree view and organizational chart of the visualization module and displaying questions and answers from the AI ​​question-and-answer module.

[0023] The WebView panel serves as the interactive page for users to interact with the visualization and AI Q&A modules. It renders the tree view and organizational chart of the visualization module and displays questions and answers from the AI ​​Q&A module. All modules collaborate closely through the WebView panel and PCS files, ensuring an efficient and consistent development process from architecture analysis to code generation and knowledge retrieval.

[0024] The structure and workflow of the visualization module of this invention are as follows: Figure 2 As shown, the visualization module includes: a PCS architecture tree construction module, a change content parsing module, and an automated content generation module; the workflow of the visualization module includes:

[0025] Regarding the PCS architecture tree construction module, when the intelligent algorithm development auxiliary tool for the Ling Shu plasma control system of this invention is activated (plugin activation) or the Ling Shu plasma control system project file in the workspace of the integrated development environment (VS Code) is changed (file change), the module starts by parsing the Ling Shu plasma control system project file, scanning the PCS directory in the workspace and parsing the project file. The parsed project file includes Extensible Markup Language (XML) files under each level of directory. The module extracts hierarchical structures such as control category, control algorithm, and data item subset to construct the PCS architecture tree, providing a data foundation for subsequent operations. Based on this architecture tree, the PCS architecture tree construction module renders a visual architecture view (including a tree view and organizational chart) through the WebView application programming interface (API) provided by VS Code. Developers can quickly locate nodes by filtering by keywords and modify parameters (such as waveform data and control logic) in the visual architecture view using a form interface (view editing change). The changes are then processed by the change content parsing module to modify the Ling Shu plasma control system project file in the workspace.

[0026] Regarding the change content parsing module, when the visual architecture view of the WebView panel is edited, the modified parameters will be sent to the plugin backend via the message passing (postMessage) mechanism. The change content parsing module will parse the corresponding PCS architecture tree node changes in the modified parameters, and lock the corresponding files and changes that need to be changed in the workspace based on the changed PCS architecture nodes, thereby updating the Extensible Markup Language (XML) and Interface Description Language (IDL) files.

[0027] After the view in the WebView panel is modified, the Ling Shu plasma control system project file in the work area is synchronously modified through the change content parsing module. When the Ling Shu plasma control system project file in the work area is modified externally, the intelligent algorithm development auxiliary tool for the Ling Shu plasma control system detects the changes in the Ling Shu plasma control system project file and resynchronizes the data rendering page through the PCS architecture tree building module to achieve bidirectional synchronization and ensure data consistency.

[0028] Regarding the automated content generation module, when the "Generate Code Framework" button is clicked on the page, the WebView panel will transmit the synchronized visual architecture view data directly to the automated content generation module by clicking "Generate File". The automated content generation module uses the IDL compiler to generate IDL files, and combines them with the C++ source code and configuration files generated by the template engine to generate statements for registering variables to the data engine in the Lingshu Plasma Control System project file.

[0029] The visualization module further enhances interactivity based on the Language Services Protocol (LSP) functionality. Figure 3 This is a flowchart illustrating the logical interaction between code and view in the visualization module of this invention. Code navigation (jumping to the definition and locating within the plugin view) is as follows: Figure 3 As shown in (a). Developers can jump from the variable name in the algorithm core logic (C++ file) to the variable definition in the Extensible Markup Language (XML) file, or locate the WebView node from the variable name in the algorithm core logic (C++ file) and jump directly to the corresponding node in the visual architecture view in the WebView panel.

[0030] For the implementation of the jump definition in the visualization module, such as Figure 3 As shown in (b), the plugin parses the registration statement in the algorithm header file, establishes a mapping relationship between variable identifiers and registration statements, and obtains the unique identifier (varname) of the variable. Using varname, the system searches for the configuration file, i.e., the XML file in the directory structure, locates the target location of the (variable), and jumps to the target location of the variable.

[0031] For the implementation of locating the visualization module in the plugin view, such as Figure 3 As shown in (c), by parsing the variable at the current cursor position, the algorithm header file registration statement is also parsed to obtain the variable's unique identifier (varname). During the visualization architecture parsing process, the system establishes a mapping relationship between varname and architecture nodes, i.e., a hash mapping table. Therefore, by looking up the hash mapping table using varname, the target position can be directly located on the page, opening the WebView panel and highlighting the corresponding node in the visualization architecture view. The architecture tree and parameter editing results of the visualization module provide input for automated generation, and the generated files, in turn, support LSP navigation, forming a closed-loop process that significantly reduces error rates and repetitive workload.

[0032] like Figure 4 As shown, the AI ​​question-answering module utilizes a local search-enhanced generation (RAG) system to display domain-specific answers through an embedded WebView panel, sharing an interface with the visualization module. Developers can access the technical guidance provided by the AI ​​question-answering module in real time while editing parameters.

[0033] The entire process begins with building a knowledge database. The AI ​​question-answering module uses LanceDB (an efficient vector database) to store documents related to the Ling Shu Plasma Control System (PCS), such as technical manuals, experimental reports, and algorithm specifications. After data cleaning and structuring (knowledge processing), these documents generate high-dimensional embedding vectors using bge-large-zh (a Chinese embedding model). Semantic information is captured through deep learning and stored back into LanceDB, forming a structured knowledge database: a data-blocked knowledge base. This provides a reliable data source for subsequent queries. At the same time, local deployment ensures the confidentiality and integrity of sensitive information in the Ling Shu PCS.

[0034] Based on this database, developers input queries (such as "how to configure plasma current parameters") into the WebView panel. The DeepSeek-R1 Large Language Model (LLM) rewrites the query based on the input to optimize keywords and semantics, enhancing retrieval accuracy. The RAG system vectorizes the rewritten query based on bge-large-zh. A multi-path recall retrieval method (vector retrieval and keyword retrieval) returns the most relevant results (question + related knowledge). Vector retrieval performs similarity matching based on embedded vectors, while keyword retrieval matches based on key terms in the query, retrieving the most relevant document fragments. The query content and the most relevant document fragments retrieved—the question and related knowledge—are used as context input to the DeepSeek-R1 prediction model for inference analysis, generating accurate and structured answers. The output answer is displayed in text form in the WebView panel.

[0035] The large language model in the AI ​​question-answering module is deployed locally to ensure data security. The answers can guide developers to adjust parameters or optimize algorithms during the development of PCS control algorithms. Developers can edit and verify the guidance content at the same time, which enhances development efficiency and learning experience, and provides real-time support for the development of Ling Shu PCS algorithms.

[0036] This invention proposes an intelligent algorithm development aid tool for the Ling Shu plasma control system. By integrating a visualization module (page display, automated file generation, and Language Service Protocol (LSP) functionality) and a RAG (Retrieval Enhanced Generation)-driven AI question-answering module, it solves the problems of cumbersome parameter configuration, lack of visualization, insufficient automation, and lack of domain-specific intelligent support in traditional PCS algorithm development. This invention provides an intuitive WebView panel for visual operation of the PCS architecture, ensures real-time consistency between parameter editing and files through a two-way synchronization mechanism, automatically generates code and configuration files to reduce repetitive work, and provides domain-specific technical guidance in conjunction with a local RAG system, significantly improving development efficiency, accuracy, and engineering level, and providing a completely new development solution for nuclear fusion research.

[0037] In addition, alternative solutions that can achieve the purpose of the invention include:

[0038] (1) Standalone desktop application to replace the VS Code plugin:

[0039] This approach allows for the development of standalone desktop applications with custom graphical user interfaces (GUIs), replacing the VS Code plugin (no longer based on the VS Code editor environment), while retaining the parameter editing functionality of the visual module and the AI ​​question-and-answer module. However, this solution increases development costs and eliminates the integration advantages of the VS Code IDE, requiring a redesign of related synchronization and interaction logic to adapt to the new GUI framework.

[0040] (2) Cloud deployment to replace the local RAG system:

[0041] The RAG system can be relocated from on-premises to cloud deployment, utilizing a third-party Large Language Model (LLM) and integrating with VS Code plugins via secure APIs, while retaining query processing capabilities to improve system processing power and data storage scalability. However, this alternative sacrifices local data security and may introduce the risk of data breaches.

[0042] (3) Other models to replace DeepSeek-R1 Large Language Model (LLM):

[0043] This invention uses the DeepSeek-R1 Large Language Model (LLM) as the default choice due to its excellent performance in general semantic understanding and response efficiency. The DeepSeek-R1 LLM can be replaced with other adapted models, such as LLaMA (Large Language Model, an efficient open-source language model) or GPT-Neo (Generative Pre-trained Transformer, another open-source language model), combined with a local LanceDB (efficient vector database) for semantic retrieval and knowledge matching, maintaining the integration of the RAG pipeline and the WebView panel. Other plugin settings remain unchanged.

[0044] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The embodiments of the present invention can be implemented using various computer languages.

[0045] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations 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, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0046] 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.

[0047] 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 1 A step that specifies a function in one or more boxes.

[0048] 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.

[0049] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

[0050] The above description is merely an embodiment of the present invention and does not limit the scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention specification and drawings, or direct or indirect applications in other related system fields, are similarly included within the protection scope of the present invention.

[0051] The contents not described in detail in this specification are existing technologies known to those skilled in the art.

Claims

1. A smart algorithm development aid tool for the Ling Shu plasma control system, characterized in that, include: Visualization module, AI Q&A module, WebView panel; The visualization module is used to parse the PCS project directory and generate an interactive view based on WebView, supporting architecture parsing, file generation, code navigation, and bidirectional editing synchronization; the visualization module includes: PCS architecture tree building module, change content parsing module, and automated content generation module; The AI ​​question-answering module uses a locally deployed retrieval enhancement generation system, combined with the PCS knowledge vector database, to provide domain-specific query answers; The WebView panel serves as the interaction page between the user and the visualization and AI Q&A modules. It renders the tree view and organizational chart of the visualization module and displays the questions and answers from the AI ​​Q&A module.

2. The intelligent algorithm development auxiliary tool for the Ling Shu plasma control system according to claim 1, characterized in that, Regarding the PCS architecture tree construction module of the visualization module, when the intelligent algorithm development auxiliary tool for the Lingshu plasma control system is activated or the Lingshu plasma control system project file in the workspace of the integrated development environment is changed, the PCS directory in the workspace is scanned and the project file is parsed, starting from parsing the Lingshu plasma control system project file. The parsed project file includes the extensible markup language files under each level of directory, and the control directory, control algorithm, and data item subset are extracted to construct the PCS architecture tree. Based on the PCS architecture tree, the PCS architecture tree building module renders a visual architecture view through the WebView application interface provided by VS Code. Developers can quickly locate nodes by filtering by keywords, modify parameters of the visual architecture view using the form interface, and modify the Lingshu plasma control system project file in the workspace through the change content parsing module.

3. The intelligent algorithm development auxiliary tool for the Ling Shu plasma control system according to claim 2, characterized in that, Regarding the change content parsing module of the visualization module, when the visualization architecture view of the WebView panel is edited, the modified parameters are sent to the plugin backend through the message passing mechanism. The change content parsing module parses the corresponding PCS architecture tree node changes in the modified parameters, and locks the corresponding files and changes that need to be changed in the workspace based on the changed PCS architecture nodes, thereby updating the Extensible Markup Language and Interface Description Language files. After the view in the WebView panel is modified, the Ling Shu plasma control system project file in the work area is synchronously modified through the change content parsing module. When the Ling Shu plasma control system project file in the work area is modified externally, the intelligent algorithm development auxiliary tool for the Ling Shu plasma control system detects the changes in the Ling Shu plasma control system project file and resynchronizes the data rendering page through the PCS architecture tree building module.

4. The intelligent algorithm development auxiliary tool for the Ling Shu plasma control system according to claim 3, characterized in that, Regarding the automated content generation module of the visualization module, when the "Generate Code Framework" button is clicked on the page, the WebView panel will transmit the synchronized visualization architecture view data directly to the automated content generation module by clicking "Generate File". The automated content generation module uses the IDL compiler to generate IDL files, and combines them with the C++ source code and configuration files generated by the template engine to generate statements for registering variables to the data engine in the Lingshu Plasma Control System project file.

5. The intelligent algorithm development auxiliary tool for the Ling Shu plasma control system according to claim 4, characterized in that, Regarding the automated content generation module, when the "Generate Code Framework" button is clicked on the page, the WebView panel will transmit the synchronized visual architecture view data directly to the automated content generation module by clicking "Generate File". The automated content generation module uses the IDL compiler to generate IDL files, and combines them with the C++ source code and configuration files generated by the template engine to generate statements for registering variables to the data engine in the Lingshu Plasma Control System project file.

6. The intelligent algorithm development auxiliary tool for the Ling Shu plasma control system according to claim 1, characterized in that, The code navigation includes: jumping to the definition and locating in the plugin view; For the implementation of the jump definition, the plugin parses the registration statement in the algorithm header file, establishes a mapping relationship between variable identifiers and registration statements, and obtains the unique identifier of the variable; through the unique identifier of the variable, the system searches the configuration file, locates the target location, and jumps to the target location; For the implementation of positioning in the plugin view, the unique identifier of the variable is obtained by parsing the variable at the current cursor position and the registration statement in the algorithm header file. During the visualization architecture parsing process, the system establishes a mapping relationship between the unique identifier of the variable and the architecture node, namely a hash mapping table. By looking up the hash mapping table through the unique identifier of the variable, the target position can be located directly on the page, the WebView panel is opened, and the corresponding node in the visualization architecture view is highlighted. The architecture tree and parameter editing results of the visualization module provide input for automated generation, and the generated file in turn supports LSP navigation, forming a closed loop process.

7. The intelligent algorithm development auxiliary tool for the Ling Shu plasma control system according to claim 1, characterized in that, The AI ​​question-answering module utilizes a local retrieval-enhanced generation system, displays domain-specific answers through an embedded WebView panel, shares an interface with the visualization module, and allows developers to access technical guidance from the AI ​​question-answering module in real time while editing parameters. Starting with the construction of a knowledge database, the AI ​​question-answering module uses an efficient vector database to store documents related to the Ling Shu plasma control system. After data cleaning and structuring, the documents generate high-dimensional embedding vectors using bge-large-zh. Semantic information is captured through deep learning and stored back into the efficient vector database, forming a structured knowledge database: a data block knowledge base. At the same time, local deployment ensures the confidentiality and integrity of sensitive information of the Ling Shu plasma control system. Based on a data-segmented knowledge base, developers input queries into the WebView panel. The DeepSeek-R1 large language model rewrites the query based on the input to optimize keywords and semantics, enhancing retrieval accuracy. The retrieval enhancement generation system vectorizes the rewritten query based on bge-large-zh. Multi-path recall retrieval returns the most relevant results: vector retrieval performs similarity matching based on embedded vectors, and keyword retrieval matches based on key terms in the query to retrieve the most relevant document fragments. The query content and the most relevant document fragments retrieved are used as context input to the DeepSeek-R1 prediction model for inference and analysis, generating accurate and structured answers. The output answers are displayed in text form in the WebView panel.

8. The intelligent algorithm development auxiliary tool for the Ling Shu plasma control system according to any one of claims 2 to 5, characterized in that, Develop a standalone desktop application with a custom graphical user interface to replace the VS Code plugin, while retaining the parameter editing functionality of the visualization module and the AI ​​Q&A module.

9. The intelligent algorithm development auxiliary tool for the Ling Shu plasma control system according to any one of claims 1 to 7, characterized in that, The search enhancement generation system was relocated from local deployment to cloud deployment, utilizing a third-party large language model and integrating with the VS Code plugin via a secure API, while retaining query processing functionality.

10. The intelligent algorithm development auxiliary tool for the Ling Shu plasma control system according to any one of claims 1 to 7, characterized in that, Replace the DeepSeek-R1 large language model with LLaMA, GPT-Neo, or other adapted models, and combine it with a local high-efficiency vector database for semantic retrieval and knowledge matching, while maintaining the integration of the retrieval enhancement generation pipeline and the WebView panel.

Images