Autonomous health automatic test system and method based on semantic model driving

Abstract

The invention discloses an autonomous health automatic test system and method based on semantic model driving, and belongs to the technical field of autonomous health test, and the method comprises the steps: receiving a natural language test instruction input by a user, converting the natural language test instruction into a prompt word sequence executable by a large model, interacting with the large model, and receiving an execution instruction fed back by the large model; according to an execution instruction sent by the large model interface module, calling a corresponding underlying function to extract autonomous health data from a database, driving test execution through telemetry data received by a test system interface, generating a remote control instruction, sending the remote control instruction outwards through the test system interface, and judging a test result. Through large model semantic driving, automatic execution of autonomous health test logic is realized, and the downloaded autonomous health event report is automatically judged.

Description

Technical Field

[0001] This invention relates to a semantic model-driven autonomous health automatic testing system and method, belonging to the field of autonomous health testing technology. Background Technology

[0002] Traditional spacecraft autonomous health testing, during comprehensive testing, primarily involves modifying and setting thresholds for various autonomous health items in the software requirements, manually creating autonomous health trigger conditions, and checking the event reports and handling measures generated after the autonomous health software functions are triggered. Current autonomous health testing relies entirely on manual operations, which presents several bottlenecks: first, the low level of structure in software requirement documents necessitates manual processing of the software requirements before autonomous health testing; second, the testing process requires manually sending numerous setting commands to configure autonomous health conditions and manually interpreting test results. Furthermore, current autonomous health test data has a low level of structure and is entirely manual, lacking automated testing capabilities. Summary of the Invention

[0003] The technical problem solved by this invention is to overcome the shortcomings of the prior art and provide an autonomous health automatic testing system and method based on semantic model-driven approach, which solves the problems of data structuring related to autonomous health and semantic-driven autonomous testing of autonomous health.

[0004] The technical solution of this invention is: Firstly, a semantic model-driven autonomous health automatic testing system, comprising: A database used to store structured autonomous health data; The large model interface module is used to receive natural language test instructions input by the user, convert the natural language test instructions into a sequence of prompt words that can be executed by the large model, interact with the large model, receive the execution instructions fed back by the large model, and send them to the autonomous health test module. The autonomous health test module includes multiple low-level functions, which are used to call the corresponding low-level functions to extract autonomous health data from the database and telemetry data received through the test system interface according to the execution instructions sent by the large model interface module, drive test execution, generate remote control instructions and send them out through the test system interface, and make judgments on the test results. The test system interface is used to establish a communication connection with an external test system based on the test interface data in the database, so as to realize the interaction of telemetry and remote control data.

[0005] Furthermore, the database is a relational database that stores data in a key-value pair manner.

[0006] Furthermore, the autonomous health data includes test interface data, autonomous health event code data, and autonomous health project data. The test interface data is used to record the interface data between the software system and the current test system, including telemetry and remote control interfaces, and autonomous health subscription data streams. The autonomous health event code data is used to record the autonomous health event codes of the model for comparison and analysis during autonomous testing. The autonomous health project data describes the interpretation telemetry, interpretation relationship, and interpretation time of autonomous health events according to the software requirements design, and is stored in a structured manner as execution parameters for automatic testing, thus completing the structured processing of autonomous health data.

[0007] Furthermore, the autonomous health test module includes a semantic model and related calling function tools. The semantic model is based on prompt word engineering, which transmits the autonomous health test process and the timing of calling software tools to the semantic model. After establishing a dialogue scenario, the semantic model generates a dialogue with the user in the system front-end dialog box. Based on the user's natural language input, it automatically completes the extraction of health test data, calculates and sets thresholds, sends threshold modification instructions, monitors event reports, and completes the autonomous health test.

[0008] Furthermore, the test system interface is an interface module between the autonomous health automatic test system and the currently running test system. It sends instructions to the test system through the remote control interface and subscribes to the telemetry data sent by the test system through the telemetry interface to monitor and interpret autonomous health event reports.

[0009] Secondly, an automated health testing method implemented using the aforementioned semantic model-driven automated health testing system includes: Receive natural language test instructions input by the user, convert the natural language test instructions into a sequence of prompt words that can be executed by the large model, interact with the large model, and receive execution instructions fed back by the large model; Based on the execution instructions sent by the large model interface module, the corresponding underlying functions are called to extract autonomous health data from the database and telemetry data received through the test system interface, drive test execution, generate remote control instructions and send them out through the test system interface, and make judgments on the test results.

[0010] Furthermore, the large model performs database queries and data merging based on the input from the front-end user, and judges the test input from the front-end user according to the data structure required by the prompt words, and reports errors for illegal test input; after the input check, the large model module sends out execution instructions.

[0011] Thirdly, a computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the semantic model-driven autonomous health automatic testing method.

[0012] Fourthly, a semantic model-driven autonomous health automatic testing device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the semantic model-driven autonomous health automatic testing method.

[0013] The advantages of this invention compared to the prior art are: (1) This invention realizes the structured processing of data related to autonomous health by establishing data key-value relationships, laying the foundation for software to realize autonomous health data processing; (2) This invention realizes the automatic execution of autonomous health test logic and automatically judges the transmitted autonomous health event reports through large model semantic drive. Attached Figure Description

[0014] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0015] To better understand the above technical solutions, the technical solutions of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solutions of the present invention, rather than limitations on the technical solutions of the present invention. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0016] The following description, in conjunction with the accompanying drawings, provides a more detailed account of the semantic model-driven autonomous health testing system and method provided in the embodiments of the present invention.

[0017] A semantic model-driven autonomous health testing system includes: A database used to store structured autonomous health data; The large model interface module is used to receive natural language test instructions input by the user, convert the natural language test instructions into a sequence of prompt words that can be executed by the large model, interact with the large model, receive the execution instructions fed back by the large model, and send them to the autonomous health test module. The autonomous health testing module includes multiple low-level functions used to extract autonomous health data from the database and telemetry data received through the test system interface, based on execution instructions sent by the large model interface module; drive test execution; generate remote control instructions and send them outward through the test system interface; and make judgments on the test results. Figure 1 As shown; The test system interface is used to establish a communication connection with an external test system based on the test interface data in the database, so as to realize the interaction of telemetry and remote control data.

[0018] Specific implementation methods may include: 1. Methods for structuring autonomous health data Based on the software requirements for spacecraft autonomous health design, the software requirements are generalized and structured. Test interface data, autonomous health event code data, and autonomous health project data involved in autonomous health testing are structured and stored in the model database using key-value pairs. Test interface data mainly records the interface data between the software system and the current test system, including telemetry and remote control interfaces, autonomous health subscription data streams, etc. Autonomous health event code data mainly records the autonomous health event codes for the model, used for comparison and analysis during autonomous testing. Autonomous health project data describes the interpretation of autonomous health events, including telemetry, interpretation relationships, and interpretation times, according to the software requirements, and is stored as execution parameters for automated testing.

[0019] 2. Semantic-driven autonomous health automated testing The software system, based on a large-model prompt word project, describes the autonomous health testing process, including database data updates, database test task extraction, test data merging, and test initiation. Prompt words establish the basic concepts of autonomous health testing within the large model, define the call relationship between the large model and underlying functions, and enable the large model to autonomously call backend functions. On the software system frontend, users interact with the large model using natural language. After parsing the user's semantics, the large model drives the backend to complete the autonomous health test and generate a test report.

[0020] 3. Software System Components The software consists of a large model interface module, a test system interface module, an autonomous health test module, and a model database. The large model interface module interacts with the large model via network connection, sending prompts to the large model to form an execution agent, and progressively sending and recording user interactions with the large model. The test system interface establishes a remote control and telemetry connection with the current test system based on the basic structural data. The autonomous health test module primarily performs autonomous health testing, setting test statuses for autonomous health items according to basic data, checking test results, and generating test reports. The autonomous health test module comprises a series of low-level functions that perform specific functionalities. The model database is a relational database that records structured data related to the comprehensive autonomous health of each model.

[0021] The solution provided in the embodiments of the present invention specifically includes: 1. Methods for structuring autonomous health data Based on the design software requirements for spacecraft autonomous health, the software requirements are generalized and structured. Test interface data, autonomous health event codes, and autonomous health items are stored in a model database according to a fixed structure. The model database is a relational database, where various model data are stored in key-value pairs. Other software modules retrieve the corresponding values ​​by calling the keys.

[0022] The basic model information data is stored in a structured manner as follows:

[0023] The event code mapping is stored in a structured manner as follows:

[0024] The structured storage of automated test input data is as follows:

[0025] 2. Semantic-driven autonomous health automated testing Based on the prompt words, autonomous health automatic test execution agents are constructed. The execution agents are oriented towards autonomous health test execution, establish the connection between the backend underlying functions and test steps according to the prompt words, restrict the relevant test boundaries, query and merge relevant data in the database, and specifically execute each test step.

[0026] The agent executes database queries and merges data based on the user's input, and outputs the required data structure according to the prompts. The agent also interprets the user's test input, reporting errors for invalid input. After passing the input check, the agent calls the underlying function based on the user's input. The function call is as follows:

[0027] The Agent prompt message is as follows: 1) Your name is Xiao T, and you are my testing assistant. I need you to help me complete the test. You need to ask me what kind of test I need to complete and wait for my reply. 2) If I need to view the model data, I will provide you with the model code (SCID), which will be used later. You provide me with the structure data, such as {'SCID':'YG999999','Tasktype':'GetdataFromDB'}; 3) If I need to complete the self-health test, you need to confirm the model code (SCID) and test items with me. I will provide you with the model code and test item name. The model code usually consists of 8 characters. You provide me with the structured data such as {'SCID':'YG9999999','Task':'XXX','Tasktype':'Healthtest'}; 4) If I haven't told you the model code, please look it up in the previous text; 5) If I need to import data, please provide me with the data structure, such as {'Tasktype':'WriteDB'}; 6) If I ask you which self-health items you haven't tested, you provide me with the model code (SCID) in the current conversation, with the structured data such as {'SCID':'YG999999','Tasktype':'Asklast'}; 3. Software System Components The newly added parts of the software system consist of a semantic model interface module, basic function modules, and a structured database. The semantic interface module establishes a connection with the large model server via network connection and links with the Qwen3.0 model via chat. It sends prompts for the executing agent to the large model and displays the text feedback from the large model on the software front end, allowing the executing agent to independently interact with the large model. The basic function module completes specific functions related to autonomous health testing, such as subscribing to telemetry data, parsing event reports, and changing autonomous health status thresholds. The structured database stores test interface data, autonomous health event codes, and structured data for autonomous health items.

[0028] This invention provides a computer-readable storage medium storing computer instructions that, when executed on a computer, cause the computer to perform... Figure 1 The method described.

[0029] 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 embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0030] 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 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0031] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0032] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0033] 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.

[0034] The contents not described in detail in this specification are common knowledge to those skilled in the art.

Claims

1. A semantic model-driven autonomous health automatic testing system, characterized in that, include: A database used to store structured autonomous health data; The large model interface module is used to receive natural language test instructions input by the user, convert the natural language test instructions into a sequence of prompt words that can be executed by the large model, interact with the large model, receive the execution instructions fed back by the large model, and send them to the autonomous health test module. The autonomous health test module includes multiple low-level functions, which are used to call the corresponding low-level functions to extract autonomous health data from the database and telemetry data received through the test system interface according to the execution instructions sent by the large model interface module, drive test execution, generate remote control instructions and send them out through the test system interface, and make judgments on the test results. The test system interface is used to establish a communication connection with an external test system based on the test interface data in the database, so as to realize the interaction of telemetry and remote control data.

2. The autonomous health automatic testing system based on semantic model driving according to claim 1, characterized in that, The database is a relational database that stores data in a key-value pair manner.

3. The autonomous health automatic testing system based on semantic model driving according to claim 1, characterized in that, The autonomous health data includes test interface data, autonomous health event code data, and autonomous health project data. The test interface data records the interface data between the software system and the current test system, including telemetry and remote control interfaces, and autonomous health subscription data streams. The autonomous health event code data records the autonomous health event codes of the model for comparison and analysis during autonomous testing. The autonomous health project data describes the interpretation telemetry, interpretation relationship, and interpretation time of autonomous health events according to the software requirements design, and stores them in a structured manner as execution parameters for automatic testing, thus completing the structured processing of autonomous health data.

4. The autonomous health automatic testing system based on semantic model driving according to claim 1, characterized in that, The autonomous health test module includes a semantic model and related calling function tools. The semantic model is based on prompt word engineering, which transmits the autonomous health test process and the timing of calling software tools to the semantic model. After establishing a dialogue scenario, the semantic model generates a dialogue with the user in the system front-end dialog box. Based on the user's natural language input, it automatically completes the extraction of health test data, calculates and sets thresholds, sends threshold modification instructions, monitors event reports, and completes the autonomous health test.

5. The autonomous health automatic testing system based on semantic model driving according to claim 1, characterized in that, The test system interface is an interface module between the autonomous health automatic test system and the currently running test system. It sends instructions to the test system through the remote control interface and subscribes to the telemetry data sent by the test system through the telemetry interface to monitor and interpret autonomous health event reports.

6. A method for autonomous health automatic testing implemented using the semantic model-driven autonomous health automatic testing system according to any one of claims 1 to 5, characterized in that, include: Receive natural language test instructions input by the user, convert the natural language test instructions into a sequence of prompt words that can be executed by the large model, interact with the large model, and receive execution instructions fed back by the large model; Based on the execution instructions sent by the large model interface module, the corresponding underlying functions are called to extract autonomous health data from the database and telemetry data received through the test system interface, drive test execution, generate remote control instructions and send them out through the test system interface, and make judgments on the test results.

7. The method according to claim 6, characterized in that, The large model performs database queries and data merging based on the input from the front-end user, and interprets the test input from the front-end user according to the data structure required by the prompt words, and reports errors for illegal test input; after the input check, the large model module sends out execution instructions.

8. 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 claim 6.

9. A semantic model-driven autonomous health testing 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 claim 6.

Images