Rail transit intelligent test method and device, electronic equipment and program product
By automatically generating test cases and analyzing fault causes using an expert model for rail transit testing, the problems of insufficient testing depth, low efficiency, and high cost in rail transit software testing have been solved, achieving efficient and intelligent test report generation and fault diagnosis.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-28
- Publication Date
- 2026-04-07
AI Technical Summary
In rail transit software testing, there are problems such as insufficient testing depth, low efficiency, high cost, and lack of intelligent diagnosis in result analysis. Existing technologies rely on manual design of test cases, which is difficult to fully cover various scenarios. Automated testing tools lack business logic analysis capabilities, test script maintenance costs are high, and the scarcity of senior experts has become a bottleneck.
Test cases are generated using a rail transit test expert model, automatically converted into executable scripts for test execution, and the actual results are compared with the expected results. Failed test cases are identified and the causes of failures are analyzed, and an intelligent test report is generated.
It has achieved a significant improvement in test case coverage and depth, greatly enhanced the efficiency and intelligence of automated testing, reduced human resource costs, generated high-value test reports to support decision-making, and solved the problems of insufficient test depth and low efficiency.
Smart Images
Figure CN121807688A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the interdisciplinary field of software testing and artificial intelligence, and in particular to an intelligent testing method, device, electronic equipment and program product for rail transit. Background Technology
[0002] Currently, in the testing of software systems (such as train operation control, signal management, passenger information services, and dispatching systems) in the rail transit field, such as... Figure 1 As shown, Figure 1 This diagram illustrates intelligent testing methods for rail transit in related technologies. The main technical solutions employed in these technologies include: Manual testing, where testers manually write test cases, set up test environments, execute test steps, and record results based on requirements documents, personal experience, and business knowledge. Automated testing based on fixed code logic, using tools like TopoLOGIC. Testers write automated scripts to simulate user operations, automating regression testing of certain test processes. Data-driven testing separates test data from test scripts, verifying the system's behavior under different data conditions by preparing a large amount of input and expected output data. Traditional test management tools, using traditional shared storage platforms for test case management, test plan development, and result tracking, but these lack intelligent generation and analysis capabilities. Static analysis tools for specific modules, using code scanning tools to perform security and reliability analysis on software source code, but this has a weak connection to business logic and functional testing.
[0003] However, the test case coverage and depth of related technologies are insufficient. Relying on manual test case design, they are easily limited by the experience and blind spots of testers, making it difficult to comprehensively cover various normal, boundary, and abnormal scenarios. Business scenario analysis capabilities are weak; the automated testing tools for related technologies cannot "understand" the business, only executing preset instructions. They lack the ability to deeply reason and analyze the business logic of rail transit (such as train timetable adjustments and abnormal train operation), and cannot automatically discover and construct complex test scenarios. Test script maintenance costs are high. Frequent iterations of rail transit software and changes in interface and business logic can cause many automated test scripts to fail, requiring significant manpower for script modification and maintenance, resulting in a low return on investment. High-quality testing heavily relies on experienced rail transit business experts, but such experts are scarce, becoming a bottleneck for testing efficiency and quality. When requirements change or new business models emerge, the cycle from understanding the changes to designing new test cases and writing scripts is too long, failing to meet the testing needs of rapid iteration, and urgently needs to be addressed. Summary of the Invention
[0004] This application provides a method, apparatus, electronic device, and program product for intelligent testing of rail transit, in order to solve problems such as insufficient testing depth, low efficiency, high cost, and lack of intelligent diagnosis in result analysis in rail transit software testing.
[0005] The first aspect of this application provides a method for intelligent testing of rail transit, including the following steps: Receive user requirements and generate test cases based on the rail transit test expert model; The test cases are received and converted into executable test scripts. Tests are then performed based on the executable test scripts to obtain actual test results. Obtain the actual test results, compare the actual test results with the expected test results generated by the rail transit test expert model, obtain the comparison results, identify the failed test cases, and the rail transit test expert model analyzes the fault causes of the failed test cases based on the comparison results and generates a test report.
[0006] Optionally, before receiving the user request, the method further includes: Acquire domain data on rail transit, and train a pre-set large model based on the domain data to obtain a rail transit test expert model.
[0007] Optionally, the domain information includes at least one of the following: technical specifications, requirements documents, design documents, historical test case libraries, fault reports, operation and maintenance logs, and industry standard documents.
[0008] Optionally, receiving user requirements and generating test cases based on the rail transit test expert model includes: Based on the rail transit test expert model and the user requirements, multiple sub-scenarios, preconditions, triggering events and a first expected result related to the user requirements are derived, and a test scenario is generated based on the multiple sub-scenarios, the preconditions, the triggering events and the first expected result.
[0009] Optionally, the test case includes a second expected result, and the expected test result is determined based on the first expected result and the second expected result.
[0010] Optionally, receiving the test cases, converting the test cases into executable test scripts, and executing tests based on the executable test scripts to obtain actual test results includes: The test cases described in natural language are parsed, and the pre-encapsulated test operation library is called to directly drive the method under test to execute the test cases and obtain the actual test results.
[0011] A second aspect of this application provides an intelligent testing device for rail transit, comprising: The receiving module is used to receive user requirements and generate test cases based on the rail transit test expert model. The testing module is used to receive the test cases, convert the test cases into executable test scripts, execute tests based on the executable test scripts, and obtain actual test results. The analysis module is used to obtain actual test results, compare the actual test results with the expected test results generated by the rail transit test expert model, obtain comparison results, and identify the failed test cases. The rail transit test expert model analyzes the fault causes of the failed test cases based on the comparison results and generates a test report.
[0012] Optionally, before receiving the user request, the receiving module is further configured to: Acquire domain data on rail transit, and train a pre-set large model based on the domain data to obtain a rail transit test expert model.
[0013] Optionally, the domain information includes at least one of the following: technical specifications, requirements documents, design documents, historical test case libraries, fault reports, operation and maintenance logs, and industry standard documents.
[0014] Optionally, the receiving module is specifically used for: Based on the rail transit test expert model and the user requirements, multiple sub-scenarios, preconditions, triggering events and a first expected result related to the user requirements are derived, and a test scenario is generated based on the multiple sub-scenarios, the preconditions, the triggering events and the first expected result.
[0015] Optionally, the test case includes a second expected result, and the expected test result is determined based on the first expected result and the second expected result.
[0016] Optionally, the test module is specifically used for: The test cases described in natural language are parsed, and the pre-encapsulated test operation library is called to directly drive the method under test to execute the test cases and obtain the actual test results.
[0017] A third aspect of this application provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being configured to perform the intelligent testing method for rail transit as described in the above embodiments.
[0018] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the intelligent testing method for rail transit as described in the above embodiments.
[0019] A fifth aspect of this application provides a computer program product storing a computer program that, when executed by a processor, implements the intelligent testing method for rail transit as described in the above embodiments.
[0020] Therefore, this application embodiment receives user requirements and generates test cases based on the rail transit test expert model; it receives the test cases, converts them into executable test scripts, executes the tests based on the executable test scripts, and obtains actual test results; it acquires the actual test results, compares them with the expected test results generated by the rail transit test expert model, obtains the comparison results, identifies the failed test cases, and the rail transit test expert model analyzes the fault causes of the failed test cases based on the comparison results, generating a test report. This solves the problems of insufficient test depth, low efficiency, high cost, and lack of intelligent diagnostics in result analysis in rail transit software testing.
[0021] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description
[0022] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a schematic diagram of intelligent testing methods for rail transit in related technologies; Figure 2 This is a flowchart of an intelligent testing method for rail transit provided according to an embodiment of this application; Figure 3 This is a schematic diagram of an intelligent testing method for rail transit according to an embodiment of this application; Figure 4 This is a schematic diagram of an intelligent testing device for rail transit provided according to an embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation
[0023] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.
[0024] The intelligent testing method for rail transit according to embodiments of this application is described below with reference to the accompanying drawings. Addressing the problems of insufficient testing depth, low efficiency, high cost, and lack of intelligent diagnostics in result analysis mentioned in the background art of rail transit software testing, this application provides an intelligent testing method for rail transit. In this method, embodiments of this application receive user requirements and generate test cases based on the user requirements using a rail transit testing expert model; receive the test cases and convert them into executable test scripts; execute the tests based on the executable test scripts to obtain actual test results; obtain the actual test results and compare them with the expected test results generated by the rail transit testing expert model to obtain comparison results; identify the failed test cases; and the rail transit testing expert model analyzes the fault causes of the failed test cases based on the comparison results and generates a test report. This solves the problems of insufficient testing depth, low efficiency, high cost, and lack of intelligent diagnostics in result analysis in rail transit software testing.
[0025] Specifically, Figure 2 This is a flowchart illustrating an intelligent testing method for rail transit provided in an embodiment of this application.
[0026] like Figure 2 As shown, the intelligent testing method for rail transit includes the following steps: In step S201, user requirements are received, and test cases are generated based on the rail transit test expert model. A test case is a standardized description of a set of test conditions, input data, execution steps, and expected results designed for a specific test objective.
[0027] Specifically, users can input requirements described in natural language or upload requirement documents, and the rail transit test expert model will automatically generate test cases, including test steps, expected results, test environment requirements, test input requirements, and test method descriptions.
[0028] Optionally, in some embodiments, receiving user requirements and generating test cases based on the rail transit test expert model includes: deriving multiple sub-scenarios, preconditions, triggering events, and first expected results related to the user requirements based on the rail transit test expert model and the user requirements, and generating test scenarios based on the multiple sub-scenarios, preconditions, triggering events, and first expected results.
[0029] Understandably, through scenario analysis and mining, such as when a user submits a scenario analysis request (e.g., "Analyze why the planned train did not select the expected route under certain conditions"), the rail transit test expert model, based on its learned knowledge, derives various sub-scenarios, preconditions, triggering events, and the first expected result under that scenario, and automatically transforms them into testable scenarios (test scenarios).
[0030] Optionally, in some embodiments, before receiving user requests, the method further includes: acquiring domain data on rail transit, and training a preset large model based on the domain data on rail transit to obtain a rail transit test expert model.
[0031] Optionally, in some embodiments, domain information includes at least one of technical specifications, requirements documents, design documents, historical test case libraries, fault reports, operation and maintenance logs, and industry standard documents.
[0032] Understandably, collecting and organizing authoritative materials in the rail transit field (domain materials), including but not limited to technical specifications, system requirement documents, design documents, historical test case libraries, fault reports, operation and maintenance logs, and industry standard documents, is used to conduct domain-adaptive training on the basic DeepSeek large model (pre-set large model). The training objective is to enable the model to deeply understand the professional terminology, business logic, safety rules, and testing points of rail transit, resulting in a rail transit testing expert model that serves as the intelligent brain of the entire system.
[0033] In step S202, test cases are received and converted into executable test scripts. Tests are then performed based on the executable test scripts to obtain actual test results.
[0034] Optionally, in some embodiments, receiving test cases and converting them into executable test scripts, executing tests based on the executable test scripts, and obtaining actual test results includes: parsing test cases described in natural language, calling a pre-encapsulated test operation library to directly drive the method under test to execute the test cases, and obtaining actual test results.
[0035] Among them, an executable test script is a piece of program code written in a specific automated testing framework or programming language that can be directly parsed by a computer and drive the system under test to perform specific operations. It transforms manually defined test cases into a sequence of instructions that can be understood and executed by a machine, and is the core technology carrier for achieving test automation. A pre-packaged test operation library is a collection of pre-developed and integrated software components containing a series of reusable basic test operation instructions.
[0036] Specifically, upon receiving the generated test cases, the rail transit test expert model can automatically convert the test steps described in natural language into scripts executable by the automated testing framework. Alternatively, the system provides an intelligent driver layer that directly parses the natural language test cases and drives the system under test to execute tests by calling pre-packaged test operation libraries, eliminating the need to generate intermediate scripts and thus avoiding script maintenance issues.
[0037] It should be noted that the automated test execution engine in this application embodiment executes tests in the test environment and monitors the system status, logs and output results in real time.
[0038] In step S203, the actual test results are obtained, and the actual test results are compared with the expected test results generated by the rail transit test expert model to obtain the comparison results. The failed test cases are identified, and the rail transit test expert model analyzes the causes of failure of the failed test cases based on the comparison results and generates a test report.
[0039] Specifically, this application's embodiments capture actual test results and automatically compare them with the expected results (expected test results) generated by the rail transit test expert model. For test cases that fail, the model (rail transit test expert model) analyzes them, combines system logs and error information, infers the most likely causes of failure (such as "time asynchrony", "interface communication timeout", and "logic configuration error"), provides troubleshooting suggestions, and generates a test report.
[0040] Furthermore, the rail transit testing expert model automatically generates well-structured and comprehensive test reports. These reports not only include traditional test content records but also risk level assessments (classifying the impact and severity of discovered defects); quality trend analysis (comparing results with historical data to analyze quality trends); and improvement suggestions (providing supplementary test cases or code optimizations to address weaknesses). Simultaneously, the test reports support natural language question answering, allowing users to ask follow-up questions such as "Why did this test case fail?" or "How should this test item be tested?" Optionally, in some embodiments, the test cases include a second expected result, and the expected test result is determined based on the first and second expected results.
[0041] It is understandable that the first expected result is included in the test scenario generated by the rail transit test expert model; the second expected result is included in the test cases generated by the rail transit test expert model; the expected test result is determined based on the first and second expected results, thus ensuring the accuracy of intelligent testing.
[0042] Therefore, this application embodiment, through the generation and reasoning capabilities of large models, automatically generates comprehensive and sufficiently in-depth test cases, effectively discovering defects that are difficult for humans to anticipate. Deepening business scenario analysis enables the testing system to understand and analyze complex rail transit business logic, automatically deriving various potential and related business scenarios and fault chains for test verification. This application embodiment achieves a fully automated closed-loop testing process, greatly freeing up manpower. It reduces the absolute dependence on the business expertise of test personnel and lowers the long-term maintenance costs of automated scripts through intelligent maintenance. The generated test reports not only include results but also risk-based assessments and defect root cause analyses, providing high-quality decision-making basis for project management.
[0043] To facilitate those skilled in the art to further understand the intelligent testing method for rail transit in the embodiments of this application, the following is combined with... Figure 3 The embodiments shown will be described in detail.
[0044] Specifically, such as Figure 3 As shown, Figure 3 This diagram illustrates an intelligent testing method for rail transit according to one embodiment of this application. The core architecture of this embodiment includes a domain knowledge fusion and model training module, an intelligent test design and analysis module, an automated test execution engine, and a result intelligent analysis and report generation module. This constructs a closed-loop system with a rail transit test expert model as its intelligent core. Users interact with the system through natural language, and test data flows intelligently between modules, ultimately generating a high-value test report. The entire process is highly automated and intelligent, forming a complete feedback and optimization closed loop.
[0045] Furthermore, compared with related technologies, this invention has the following significant advantages: By using machine intelligence to compensate for the blind spots of the human brain, the coverage and depth of test cases are improved by orders of magnitude, enabling more effective discovery of deep and hidden defects and greatly ensuring the security of testing. The embodiments of this application liberate testers from repetitive design, writing, and execution work, allowing them to focus on more creative test strategy development and complex problem troubleshooting. Test case design and execution time is shortened from the "several people, several days" level to the "hours" or even "minutes" level. It reduces reliance on senior business experts, lowering human resource costs; through intelligent maintenance, it significantly reduces the long-term maintenance costs of automated testing. It solidifies the knowledge and experience of domain experts into a trained model, forming the organization's digital assets and solving the problem of knowledge loss caused by personnel turnover. The system framework has universality; by changing the training data, this model can be quickly migrated to other safety-critical areas such as aviation and cargo, possessing broad application prospects. The in-depth analysis reports and risk warnings provided by the embodiments of this application can help project managers more clearly grasp the software quality status and make more timely and accurate release decisions.
[0046] Therefore, by training the DeepSeek model in a targeted manner, transforming it from a general-purpose large model into a domain expert proficient in rail transit operations, the foundation for achieving high-quality test design and analysis is laid. Utilizing the logical reasoning and associative capabilities of the large model, multi-dimensional and multi-level test scenarios and test cases are automatically derived from a single requirement or scenario, overcoming the limitations of traditional template- or rule-based generation methods. This allows for the direct conversion of test intentions described in natural language into control instructions (or intermediate scripts) for the system under test, building a bridge of "what you think is what you test," significantly lowering the threshold for using and maintaining automated testing. The embodiments of this application no longer simply determine "pass / fail," but rather utilize the natural language understanding and analysis capabilities of the large model to analyze the causes of test failures and extract valuable content from massive amounts of test data to provide decision-making suggestions, maximizing the value of test data. The various isolated stages in the test lifecycle (design, execution, analysis) are organically integrated through a unified large model brain, forming a self-perceiving, self-decision-making, and self-executing intelligent closed-loop system.
[0047] According to the intelligent testing method for rail transit proposed in this application, the method receives user requirements and generates test cases based on a rail transit testing expert model. It then receives the test cases, converts them into executable test scripts, executes the tests based on the executable test scripts, and obtains the actual test results. The actual test results are then compared with the expected test results generated by the rail transit testing expert model to obtain the comparison results. Failed test cases are identified, and the rail transit testing expert model analyzes the causes of failure for the failed test cases based on the comparison results, generating a test report. This solves the problems of insufficient test depth, low efficiency, high cost, and lack of intelligent diagnostics in result analysis in rail transit software testing.
[0048] Next, the intelligent testing device for rail transit proposed according to the embodiments of this application is described with reference to the accompanying drawings.
[0049] Figure 4 This is a block diagram of an intelligent testing device for rail transit according to an embodiment of this application.
[0050] like Figure 4 As shown, the intelligent testing device 10 for rail transit includes: a receiving module 100, a testing module 200, and an analysis module 300.
[0051] The receiving module 100 is used to receive user requirements and generate test cases based on the rail transit test expert model. Test module 200 is used to receive test cases, convert the test cases into executable test scripts, execute tests based on the executable test scripts, and obtain actual test results; The analysis module 300 is used to obtain the actual test results, compare the actual test results with the expected test results generated by the rail transit test expert model, obtain the comparison results, and identify the failed test cases. Based on the comparison results, the rail transit test expert model analyzes the failure causes of the failed test cases and generates a test report.
[0052] Optionally, before receiving user requests, the receiving module 100 is also used to: acquire domain data on rail transit, and train a preset large model based on the domain data on rail transit to obtain a rail transit test expert model.
[0053] Optionally, domain information includes at least one of the following: technical specifications, requirements documents, design documents, historical test case libraries, fault reports, operation and maintenance logs, and industry standard documents.
[0054] Optionally, the receiving module 100 is specifically used to: derive multiple sub-scenarios, preconditions, triggering events and first expected results related to user needs based on the rail transit test expert model and user needs, and generate test scenarios based on the multiple sub-scenarios, preconditions, triggering events and first expected results.
[0055] Optionally, the test cases include a second expected result, and the expected test result is determined based on the first and second expected results.
[0056] Optionally, the test module 200 is specifically used to: parse test cases described in natural language, call the pre-encapsulated test operation library to directly drive the method under test to execute the test cases, and obtain the actual test results.
[0057] It should be noted that the foregoing explanation of the embodiment of the intelligent testing method for rail transit also applies to the intelligent testing device for rail transit in this embodiment, and will not be repeated here.
[0058] According to the intelligent testing device for rail transit proposed in this application, the device receives user requirements and generates test cases based on a rail transit testing expert model. It then receives the test cases, converts them into executable test scripts, executes the tests based on the executable test scripts, and obtains actual test results. The actual test results are then compared with the expected test results generated by the rail transit testing expert model to obtain comparison results. Failed test cases are identified, and the rail transit testing expert model analyzes the causes of failure for the failed test cases based on the comparison results, generating a test report. This solves the problems of insufficient test depth, low efficiency, high cost, and lack of intelligent diagnostics in result analysis in rail transit software testing.
[0059] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 501, the processor 502, and the computer program stored on the memory 501 and capable of running on the processor 502.
[0060] When the processor 502 executes the program, it implements the intelligent testing method for rail transit provided in the above embodiments.
[0061] Furthermore, electronic devices also include: Communication interface 503 is used for communication between memory 501 and processor 502.
[0062] The memory 501 is used to store computer programs that can run on the processor 502.
[0063] Memory 501 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.
[0064] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.
[0065] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.
[0066] Processor 502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.
[0067] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described intelligent testing method for rail transit.
[0068] This application also provides a computer program product, which stores a computer program that, when executed by a processor, implements the above-described intelligent testing method for rail transit.
[0069] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.
[0070] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0071] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.
[0072] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
[0073] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.
Claims
1. A smart testing method for rail transit, characterized in that, Includes the following steps: Receive user requirements and generate test cases based on the rail transit test expert model; The test cases are received and converted into executable test scripts. Tests are then performed based on the executable test scripts to obtain actual test results. Obtain the actual test results, compare the actual test results with the expected test results generated by the rail transit test expert model, obtain the comparison results, identify the failed test cases, and the rail transit test expert model analyzes the fault causes of the failed test cases based on the comparison results and generates a test report.
2. The method according to claim 1, characterized in that, Before receiving user requests, the following is also included: Acquire domain data on rail transit, and train a pre-set large model based on the domain data to obtain a rail transit test expert model.
3. The method according to claim 2, characterized in that, The domain information includes at least one of the following: technical specifications, requirements documents, design documents, historical test case libraries, fault reports, operation and maintenance logs, and industry standard documents.
4. The method according to claim 1, characterized in that, The process of receiving user requests and generating test cases based on the rail transit test expert model includes: Based on the rail transit test expert model and the user requirements, multiple sub-scenarios, preconditions, triggering events and a first expected result related to the user requirements are derived, and a test scenario is generated based on the multiple sub-scenarios, the preconditions, the triggering events and the first expected result.
5. The method according to claim 4, characterized in that, The test case includes a second expected result, and the expected test result is determined based on the first expected result and the second expected result.
6. The method according to claim 1, characterized in that, The process of receiving the test cases, converting them into executable test scripts, executing tests based on the executable test scripts, and obtaining actual test results includes: The test cases described in natural language are parsed, and the pre-encapsulated test operation library is called to directly drive the method under test to execute the test cases and obtain the actual test results.
7. A smart testing device for rail transit, characterized in that, include: The receiving module is used to receive user requirements and generate test cases based on the rail transit test expert model. The testing module is used to receive the test cases, convert the test cases into executable test scripts, execute tests based on the executable test scripts, and obtain actual test results. The analysis module is used to obtain actual test results, compare the actual test results with the expected test results generated by the rail transit test expert model, obtain comparison results, and identify the failed test cases. The rail transit test expert model analyzes the fault causes of the failed test cases based on the comparison results and generates a test report.
8. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the intelligent testing method for rail transit as described in any one of claims 1-6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the intelligent testing method for rail transit as described in any one of claims 1-6.
10. A computer program product, said computer program product storing a computer program, characterized in that, When the program is executed by the processor, it implements the intelligent testing method for rail transit as described in any one of claims 1-6.