CN-121979707-A - Autonomous health automatic test system and method based on semantic model driving

CN121979707ACN 121979707 ACN121979707 ACN 121979707ACN-121979707-A

Abstract

An automatic autonomous health test system and method based on semantic model driving belongs to the technical field of autonomous health test and comprises the steps of 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, receiving an execution instruction fed back by the large model, calling a corresponding bottom function to extract autonomous health data from a database according to the execution instruction sent by an interface module of the large model, driving test execution through telemetry data received by an interface of a test system, generating a remote control instruction, sending the remote control instruction outwards through the interface of the test system, and judging a test result. According to the invention, through the semantic driving of the large model, the automatic execution of the autonomous health test logic is realized, and the downloaded autonomous health event report is automatically judged.

Inventors

QU XIAOYU
WANG WEIQI
HE LINLU
LI YONG
ZHANG WEI
YOU JIA
XU KAIHANG
DENG YUE
LI TIANNAN

Assignees

中国空间技术研究院

Dates

Publication Date: 20260505
Application Date: 20251211

Claims (9)

1. Automatic autonomous health testing system based on semantic model driving, characterized by comprising: The database is used for storing autonomous health data subjected to structuring processing; The large model interface module is used for 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, receiving an execution instruction fed back by the large model and sending the execution instruction to the autonomous health test module; The autonomous health test module comprises a plurality of bottom functions, is used for calling corresponding bottom functions to extract autonomous health data from the database according to the execution instruction sent by the large model interface module, and telemetering data received through a test system interface, driving test execution, generating a remote control instruction, sending the remote control instruction outwards through the test system interface, and judging a test result; and the test system interface is used for establishing communication connection with an external test system according to the test interface data in the database so as to realize interaction of telemetry and remote control data.
2. The autonomous health automatic test system driven based on a semantic model according to claim 1, wherein the database is relational data for data storage by a key value method.
3. The automatic test system for autonomous health based on semantic model driving according to claim 1, wherein the autonomous health data comprises test interface data, autonomous health event code data and autonomous health item data, the test interface data is used for recording interface data between a software system and a current test system and comprises a telemetry remote control interface and an autonomous health subscription data stream, the autonomous health event code data is used for recording autonomous health event codes of a model and is used for comparison and analysis during autonomous test, and the autonomous health item data describes interpretation telemetry, interpretation relation and interpretation time of autonomous health events according to software requirement design and is used for carrying out structural storage as execution parameters of automatic test to complete structured processing of the autonomous health data.
4. The autonomous health testing system based on semantic model driving according to claim 1, wherein the autonomous health testing module comprises a semantic model and related calling function tools, the semantic model transmits autonomous health testing flow and calling software tool time to the semantic model based on prompt word engineering, the semantic model creates dialogue with a user in a dialogue box at the front end of the system after establishing a dialogue scene, automatically completes health testing data extraction according to natural language input of the user, calculates a set threshold value, sends a threshold value modification instruction, monitors event reports, and completes autonomous health testing.
5. The autonomous health automatic test system driven by a semantic model according to claim 1, wherein the test system interface is an interface module of the autonomous health automatic test system and the currently running test system, an instruction is sent to the test system through a remote control interface, telemetry data sent by the test system is subscribed through a telemetry interface, and an autonomous health event report is monitored and interpreted.
6. An automatic test method for autonomous health implemented by the automatic test system for autonomous health based on semantic model driving according to any one of claims 1 to 5, comprising: 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; And according to the execution instruction sent by the large model interface module, calling a corresponding bottom function to extract autonomous health data from a database, driving test execution by telemetry data received through 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.
7. The method of claim 6, wherein the large model performs database query and data merging according to the input of the front-end user, interprets the test input of the front-end user according to the data structure required by the output of the prompt word, misreports the illegal test input, and feeds back the execution instruction through the input check.
8. A computer readable storage medium storing a computer program, which when executed by a processor performs the steps of the method according to claim 6.
9. Autonomous health automatic test equipment driven on the basis of a semantic model, comprising a memory, a processor and a computer program stored in said memory and executable on said processor, characterized in that said processor implements the steps of the method according to claim 6 when executing said computer program.

Description

Autonomous health automatic test system and method based on semantic model driving Technical Field The invention relates to an autonomous health automatic test system and method based on semantic model driving, and belongs to the technical field of autonomous health tests. Background During the comprehensive test period of the traditional autonomous health of the spacecraft, the judgment threshold values of various autonomous health projects in software requirements are modified and set, the autonomous health triggering working conditions are manufactured manually, and event reports and disposal measures generated after the autonomous health software function triggering are checked. The current autonomous health test is completely dependent on manual operation for related operation, and has the following main bottlenecks that firstly, the structuring level of the software requirement file is low due to the fact that the software requirement is manually processed before the autonomous health test, secondly, a large number of setting instructions are required to be manually sent in the test process, the autonomous health working condition is set, and the test result is manually interpreted. The current autonomous health test data has a low structuring level, is realized manually in the whole process, and does not have automatic test capability. Disclosure of Invention The invention solves the technical problems of overcoming the defects of the prior art, providing an autonomous health automatic test system and an autonomous health automatic test method based on semantic model driving, and solving the problems of autonomous health related data structuring and autonomous health semantic driving autonomous test. The technical scheme of the invention is that the automatic autonomous health testing system based on semantic model driving in the first aspect comprises: The database is used for storing autonomous health data subjected to structuring processing; The large model interface module is used for 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, receiving an execution instruction fed back by the large model and sending the execution instruction to the autonomous health test module; The autonomous health test module comprises a plurality of bottom functions, is used for calling corresponding bottom functions to extract autonomous health data from the database according to the execution instruction sent by the large model interface module, and telemetering data received through a test system interface, driving test execution, generating a remote control instruction, sending the remote control instruction outwards through the test system interface, and judging a test result; and the test system interface is used for establishing communication connection with an external test system according to the test interface data in the database so as to realize interaction of telemetry and remote control data. Further, the database is relational data for storing data by key value method. The autonomous health event data are used for recording model autonomous health event codes and are used for comparison and analysis in autonomous test, and the autonomous health event data describe interpretation telemetry, interpretation relation and interpretation time of autonomous health events according to software requirement design and are used for carrying out structural storage as execution parameters of automatic test to complete autonomous health data structural processing. The autonomous health test module further comprises a semantic model and a related calling function tool, the semantic model transmits autonomous health test flow and the time for calling the software tool to the semantic model based on prompt word engineering, the semantic model establishes a dialogue scene and then generates a dialogue with a user in a dialogue box at the front end of the system, and the autonomous health test is completed by automatically completing health test data extraction, calculating a set threshold value, sending a threshold value modification instruction, monitoring an event report and completing autonomous health test according to natural language input of the user. Further, the test system interface is an interface module of the autonomous health automatic test system and the current running test system, an instruction is sent to the test system through the remote control interface, telemetry data sent by the test system is subscribed through the telemetry interface, and the autonomous health event report is monitored and interpreted. In a second aspect, an automatic test method for autonomous health implemented by using the automatic test system for autonomous health driven based on a semantic model includes: receiving a natural language test instruction input by a user, conve