Test result recording method and device, storage medium and electronic device

Abstract

The invention discloses a test result recording method and device, a storage medium and an electronic device, and the method comprises the steps: analyzing a demand document of an electric power spot market through a large language model, and obtaining a test demand for testing the electric power spot market; generating a test case for testing the electric power spot market based on the test demand; and recording a test result obtained by executing the test case on the electric power spot market. The problems of low testing efficiency and poor flexibility caused by the fact that the testing process of the electric power spot market generally depends on manual operation are solved.

Description

Technical Field

[0001] The present application relates to the technical field of electricity spot market testing, and in particular to a method and device for recording test results, a storage medium, and an electronic device. Background Art

[0002] The electricity spot market is a crucial component of modern power systems, involving complex functions such as real-time data collection, price forecasting, and trade execution. Systems associated with this market require high levels of stability, accuracy, and security. Therefore, comprehensive and efficient testing is crucial for ensuring system quality. However, with the ever-changing demands of the electricity spot market and the increasing complexity of system integration, traditional testing methods are no longer able to meet the requirements for efficient and accurate testing.

[0003] The current testing process for electricity spot trading systems typically relies on manual labor, including requirements analysis, test case writing, and case review. This is not only time-consuming and labor-intensive, but also prone to missed tests. Requirements specifications are often manually constructed, and test case execution and bug management also rely on manual labor. This leads to low testing efficiency, difficulty adapting to changing requirements, and poor test accuracy and flexibility.

[0004] In related technologies, the testing process for the electricity spot market usually relies on manual operations, resulting in low testing efficiency and poor flexibility, and no effective solution has yet been found. Summary of the Invention

[0005] The embodiments of the present application provide a method and device for recording test results, a storage medium, and an electronic device to at least solve the problem in the prior art that the testing process for the electricity spot market usually relies on manual operation, resulting in low testing efficiency and poor flexibility.

[0006] According to one embodiment of the embodiments of the present application, a method for recording test results is provided, including: parsing a demand document of an electricity spot market through a large language model to obtain test requirements for testing the electricity spot market; generating a test case for testing the electricity spot market based on the test requirements; and recording the test results obtained by executing the test case on the electricity spot market.

[0007] In an exemplary embodiment, a demand document of an electricity spot market is parsed through a large language model to obtain test requirements for testing the electricity spot market, including: refining the demand document to obtain a demand document with redundant information removed, wherein the redundant information includes: information irrelevant to testing the electricity spot market, and redundant symbols; and converting the demand document with redundant information removed into the test requirements through the large language model.

[0008] In an exemplary embodiment, the large language model is used to parse the demand document of the power spot market to obtain the test requirements for testing the power spot market, including: determining the test requirements by the following formula: y1~p θ (y|prompt thought (z))·p θ (z|prompt refine (x)); where y1 represents the test requirement, x represents the requirement document, z represents the requirement content after the requirement document is refined, and p θ Represents the conditional probability distribution of the large language model, and the large language model analyzes the requirement document through the input prompt.

[0009] In an exemplary embodiment, generating a test case for testing the electricity spot market based on the test requirement includes: inputting the test requirement into the large language model to obtain the test case using the following formula: Among them, y2 represents the final generated output, n represents the total number of steps to generate the test case, and x i represents the partial output generated in step i, x i Depends on x1,x2,x3,...,x i-1 , the output finally generated includes: the test case or the partial output.

[0010] In an exemplary embodiment, recording the test results obtained by executing the test case on the electricity spot market includes: creating a test sheet through the test case; executing the test case through the test sheet to obtain an execution result; using the execution result as the test result, and recording the test result.

[0011] In an exemplary embodiment, after recording the test results obtained by executing the test case on the electricity spot market, it includes: obtaining process data generated during the execution of the test case; analyzing the process data and the test results, and generating a test report based on the obtained analysis results.

[0012] According to another embodiment of the embodiments of the present application, a test result recording device is also provided, including: a parsing module, used to parse the demand document of the electricity spot market through a large language model to obtain test requirements for testing the electricity spot market; a generation module, used to generate test cases for testing the electricity spot market based on the test requirements; and a recording module, used to record the test results obtained by executing the test cases on the electricity spot market.

[0013] According to another aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is configured to execute the above method when running.

[0014] According to another aspect of an embodiment of the present application, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the method through the computer program.

[0015] According to another aspect of the embodiments of the present application, a computer program product is provided, including a computer program, which implements the steps of any of the above method embodiments when executed by a processor.

[0016] In an embodiment of the present application, the demand document of the electricity spot market is parsed by a large language model to obtain test requirements for testing the electricity spot market; based on the test requirements, a test case for testing the electricity spot market is generated; and the test results obtained by executing the test case on the electricity spot market are recorded. In other words, by inputting the demand document of the electricity spot market into the large language model, parsing the test requirements, and then generating test cases based on the test requirements, the test results obtained by executing the test case on the electricity spot market are recorded, thereby achieving the technical effect of automatically, efficiently and flexibly testing the electricity spot market. Therefore, the above embodiment solves the problem in the prior art that the test process for the electricity spot market usually relies on manual operation, resulting in low test efficiency and poor flexibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 This is a hardware structure block diagram of a computer terminal for a method for recording test results according to an embodiment of the present application;

[0019] Figure 2 is a flowchart of a method for recording test results according to an embodiment of the present application;

[0020] Figure 3 1 is a flow chart of automatic voice demand analysis according to a method for recording test results according to an embodiment of the present application;

[0021] Figure 4 4 is a structural block diagram of a device for recording test results according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices; "plurality" means two or more.

[0024] The method embodiments provided in the embodiments of the present application can be executed in a computer terminal or similar computing device or cloud platform or independent physical server or software platform, wherein the above software platform is run through one or more servers. Taking running on a computer terminal as an example, Figure 1 This is a hardware structure block diagram of a computer terminal for recording a test result according to an embodiment of the present application. Figure 1 As shown, the computer terminal may include one or more ( Figure 1 Only one is shown in the figure) processor 102 and memory 104 for storing data. In an exemplary embodiment, the computer terminal may further include a transmission device 106 for communication functions and an input / output device 108. The processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. For example, the computer terminal may also include Figure 1 More or fewer components than shown, or with Figure 1 Equivalent functions or comparisons shown Figure 1 Shown are different configurations with more functionality.

[0025] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, implementing the above-mentioned method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0026] The transmission device 106 is used to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by a computer terminal's communications provider. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0027] In this embodiment, a method for recording test results is provided, which is applied to the above-mentioned computer terminal. Figure 2 : is a flowchart of a method for recording test results according to an embodiment of the present application, the process comprising the following steps:

[0028] Step S202: parsing the demand document of the electricity spot market through a large language model to obtain test requirements for testing the electricity spot market;

[0029] It is understood that the embodiments of this application utilize a large language model to perform in-depth semantic analysis of the requirements document. The model first removes redundant and irrelevant information from the text, then understands the business processes, functional requirements, performance indicators, and other information described in the document, and converts this information into structured test requirements. These test requirements include all the functional points, boundary conditions, and expected performance of the system, forming the basis for subsequent test case design.

[0030] Step S204: generating a test case for testing the electricity spot market based on the test requirements;

[0031] After defining the test requirements, the large model (i.e., the large language model) generates specific test cases based on these requirements. Each test case includes the test scenario, input data, execution steps, and expected results. The large model generates test cases covering normal paths, boundary conditions, and abnormal scenarios, ensuring that every module and function of the entire electricity spot market is fully tested.

[0032] Step S206: Record the test results obtained by executing the test case on the electricity spot market.

[0033] Once a test case is designed and executed, the system automatically records every step and result of the test. This includes actual output, execution status (pass / fail), execution time, and environment information. The automated testing platform provides real-time feedback on test results, allowing testers and developers to quickly understand the test status, conduct detailed analysis of failed cases, and locate and fix defects.

[0034] In an embodiment of the present application, the demand document of the electricity spot market is parsed by a large language model to obtain test requirements for testing the electricity spot market; based on the test requirements, a test case for testing the electricity spot market is generated; and the test results obtained by executing the test case on the electricity spot market are recorded. In other words, by inputting the demand document of the electricity spot market into the large language model, parsing the test requirements, and then generating test cases based on the test requirements, the test results obtained by executing the test case on the electricity spot market are recorded, thereby achieving the technical effect of automatically, efficiently and flexibly testing the electricity spot market. Therefore, the above embodiment solves the problem in the prior art that the test process for the electricity spot market usually relies on manual operation, resulting in low test efficiency and poor flexibility.

[0035] In some optional embodiments, a demand document of an electricity spot market is parsed through a large language model to obtain test requirements for testing the electricity spot market, including: refining the demand document to obtain a demand document with redundant information removed, wherein the redundant information includes: information irrelevant to the testing of the electricity spot market, redundant symbols; and converting the demand document with redundant information removed into the test requirements through the large language model.

[0036] After receiving the requirements document, the large language model pre-processes it to remove redundant information irrelevant to the test. This includes, but is not limited to, information irrelevant to testing the electricity spot market. For example, irrelevant information that does not directly impact the test content, such as project background information, non-technical project goals, team member introductions, and project history, is removed from the requirements document. Redundant symbols, including extraneous punctuation, spaces, and code comments, can interfere with the model's understanding of the text.

[0037] In addition, preprocessing can also include format adjustment, for example, converting the requirements document into a more standard format that is easier for the model to parse, such as removing complex table structures and converting it into plain text or a specific markup language format.

[0038] The refined documents (i.e. the requirements documents after preprocessing as mentioned above) will be input into the large language model, which will convert this information into specific test requirements through deep semantic understanding and context analysis. The generation of test requirements involves the following key points: First, identify user stories from the documents to understand the expected behaviors and requirements of users when operating the electricity spot market system. Second, deeply understand the description of system functions, including data input, processing logic, output results, and possible exception handling. Finally, the model can identify the implicit boundary conditions and exception handling requirements in the document, which are particularly important parts of the test case. Finally, the large language model will output the test requirements.

[0039] Through the above steps, the large language model can effectively process the requirements documents of the power spot market system, extract key test requirements, and further generate specific test cases, thereby greatly improving the efficiency and accuracy of the testing process. This approach reduces the time spent on manually parsing requirements documents and writing test cases, while also improving the accuracy of test requirements and the coverage of test cases through the model's deep understanding capabilities.

[0040] In some other optional embodiments, the demand document of the electricity spot market is parsed by a large language model to obtain the test requirements for testing the electricity spot market, including: determining the test requirements by the following formula: y1~p θ (y|prompt thought (z))·p θ (z|prompt refine (x)); where y1 represents the test requirement, x represents the requirement document, z represents the requirement content after the requirement document is refined, and p θ Represents the conditional probability distribution of the large language model, and the large language model analyzes the requirement document through the input prompt.

[0041] It should be noted that the above embodiment of refining the requirement document to obtain the test requirements does not conflict with the above embodiment of determining the test requirements through a formula.

[0042] In an exemplary embodiment, generating a test case for testing the electricity spot market based on the test requirement includes: inputting the test requirement into the large language model to obtain the test case using the following formula: Among them, y2 represents the final generated output, n represents the total number of steps to generate the test case, and x i represents the partial output generated in step i, x i Depends on x1,x2,x3,...,x i-1 , the output finally generated includes: the test case or the partial output.

[0043] It can be understood that the core of the embodiment of the present application in generating test cases is to utilize the conditional probability distribution capability of the large language model to gradually generate the various components of the test cases.

[0044] The specific steps for generating test cases may include:

[0045] 1) Input the test requirements as the initial input x1 into the large model.

[0046] 2) Based on the test requirements and the current parameters of the large language model, generate x2 a preliminary description of the test case, such as a summary of the test scenario.

[0047] 3) Starting from 2), use the output of the previous step as the condition for the next step (for example, use x2 as the condition for generating x3). For example, based on the summary of the test scenario, generate detailed input conditions and expected outputs.

[0048] 4) Repeat the above process and continue iterating until a complete test case y2 is generated. y2 covers all key testing requirements of the electricity spot market.

[0049] For example, suppose the requirements document for the electricity spot market mentions a "real-time data collection" feature. In its first step, the model might generate a "normal path for testing real-time data collection." Next, based on the output of the first step, the model generates specific input conditions (e.g., simulating a real-time data flow), expected outputs (frequency and format of data collection), and execution steps (including data flow initialization, collection, and verification of data integrity). Each step is based on the output of the previous step and the model's parameters, ultimately resulting in a detailed test case that fully covers the testing requirements for the "real-time data collection" feature.

[0050] The above embodiment combines the intelligent generation capability of a large language model with the coherence of sequence generation, and can generate test cases efficiently and accurately, providing strong support for automated testing of the electricity spot market.

[0051] In an exemplary embodiment, recording the test results obtained by executing the test case on the electricity spot market includes: creating a test sheet through the test case; executing the test case through the test sheet to obtain an execution result; using the execution result as the test result, and recording the test result.

[0052] When test cases are ready, the automated testing system automatically generates a test ticket for each test case. The test ticket contains detailed information about the specific test case, such as the case ID, description, input data, expected results, execution priority, etc., and integrates this information into an executable test task.

[0053] Test orders are dispatched to the automated testing platform, which executes the test cases according to the instructions in the order. Test execution may involve simulating user actions, data input, interaction with the electricity spot market system, and comparing actual results with expected results. The system records every step and output of the execution process in real time, including but not limited to operation timestamps, system response times, and error messages.

[0054] After test execution is complete, the automation platform records the results of each test case. These results include the test status (pass / fail), actual output, comparison with expected output, and any relevant test notes or defect descriptions. Recording test results is the foundation for subsequent analysis and report generation.

[0055] Furthermore, after recording the test results obtained by executing the test case on the electricity spot market, it includes: obtaining process data generated during the execution of the test case; analyzing the process data and the test results, and generating a test report based on the obtained analysis results.

[0056] After recording the test results, the system further collects detailed process data during the test execution. This includes but is not limited to test environment information, system configuration, actual operation steps, input data, system responses, error logs, etc. This data is crucial for in-depth analysis of test failure causes and system performance.

[0057] Automated testing systems analyze collected process data and test results. This analysis may include identifying patterns in test failures, locating potential system defects, and evaluating performance metrics. This process may leverage statistical analysis, machine learning algorithms, or the predictive power of large models to provide deeper test insights.

[0058] Based on the above analysis results, the system automatically generates a detailed test report. This report includes key information such as the execution status of all test cases, pass rate, failure rate, defect list, and performance data. Furthermore, for test cases that failed, the report provides a detailed defect description, steps to reproduce the issue, scope of impact, and defect priority, helping the development team quickly locate and fix the problem.

[0059] The entire process is highly automated, reducing the need for manual intervention and improving testing efficiency and report accuracy. By combining a large language model with an automated testing platform, the electricity spot market testing process has become more intelligent, enabling rapid response to system changes and updated requirements, ensuring that the system meets expected quality standards before going live.

[0060] In order to better understand the process of the above-mentioned test result recording method, the above-mentioned test result recording method is described below in combination with an optional embodiment, but is not used to limit the technical solution of the embodiment of the present application.

[0061] The electricity spot market testing process in related technologies relies too much on manual operations, involving multiple steps such as requirement document parsing, test case writing, and case review, which makes testing time-consuming and prone to omissions. Requirements review usually relies on manual interpretation of requirement documents one by one, making it difficult to capture complex requirement changes in a timely manner and unable to efficiently identify potential improvement points or omissions. The test case writing process also needs to be done manually and is usually based on the developer or tester's understanding of the requirements. It lacks automated support, resulting in incomplete test case coverage. Especially when dealing with complex scenarios such as real-time transactions and price forecasting, the accuracy and comprehensiveness of the test cases cannot be guaranteed.

[0062] Furthermore, related technologies have significant shortcomings in generating examples, building automated testing processes, managing bugs, and generating reports. Example development is typically done manually by testers, and data needs to be imported from the system for verification, which not only increases the manual burden but also easily introduces human error. Test process construction often relies on manually associating requirements with test cases, and lacks systematic automated support, making it difficult to implement full-chain testing. Bug management and reporting also rely on manual operations, including priority assignment, reproduction steps, and report writing. This results in inefficient test result feedback and optimization, and an inability to quickly respond to changes in system requirements.

[0063] To solve the above problems, the optional embodiment of the present application proposes a method and system for intelligent testing process of the electricity spot market based on a large model (equivalent to the recording method of the above test results), which aims to effectively improve the testing efficiency, accuracy and flexibility of the electricity spot market system through automated demand analysis, test case generation, and case verification. Compared with existing manual operations and traditional automation tools, the optional embodiment of the present application introduces a large model to automatically parse requirements and intelligentize the test process, reducing errors and delays in manual operations and improving test efficiency, accuracy and flexibility. Specifically, by automatically parsing the requirement documents, clear user stories and test requirements are generated, and then test cases covering all key functions are automatically generated. With the help of deep semantic understanding, the optional embodiment of the present application optimizes the automated generation of the test process to ensure the coverage of the entire chain test. In addition, the intelligence of case generation, BUG management and report generation makes the testing process more efficient and accurate, reducing manual intervention. Through integration with existing project management tools, continuous integration and continuous testing are supported to ensure that the system can respond quickly and maintain high quality when requirements change.

[0064] The specific execution steps of the optional embodiment of this application include:

[0065] Step 1: Automated requirements analysis.

[0066] In the automated requirement analysis, the optional embodiment of the present application adopts an improved Chain of Thought (CoT) method, namely the "Refine + Thinking" framework method, which includes two steps: refinement and thinking. The refinement step converts the requirement document into a concise text input by removing irrelevant information and redundant symbols; the thinking step helps the model analyze the logical relationship between requirements and converts complex requirement content into executable system requirements or user stories. The requirement analysis process using the "Refine and Thinking" framework is as follows: Figure 3 shown.

[0067] During the requirements parsing process, the model analyzes the requirements document based on the input prompts, extracting key requirements and generating structured output. The parsed requirements serve as the basis for subsequent automated test case generation, ensuring that the generated test methods cover the system's core functions and boundary conditions.

[0068] The demand analysis process can be expressed by the following formula:

[0069] y~p θ (y|prompt thought (z))·p θ (z|prompt refine (x));

[0070] Where x represents the initial requirement document; z represents the refined requirement content; y represents the parsed user story or system requirement; p θ Represents the conditional probability distribution of a large language model.

[0071] Step 2: Test case generation.

[0072] When generating test cases, the "thinking" step in the "refine + think" process is further optimized to generate comprehensive test scenarios, including normal usage paths, abnormal scenarios, and boundary conditions. By inputting the parsed requirements information into the large language model, test cases that meet actual business needs can be automatically generated.

[0073] The process of generating test cases can be expressed by the following formula:

[0074]

[0075] Here, y represents the final generated output, such as a test case or text content; n is the total number of steps required to generate the output; xi is the partial output generated in step i, which depends on the previously generated x1, x2, …, xi; and pθ represents the conditional probability distribution controlled by the large model, used to calculate the probability of each step. The model generates each test case step by step based on the requirement logic of the previous step, ensuring comprehensive coverage of every business functional module. Furthermore, test cases include input conditions, expected outputs, execution steps, and possible boundary conditions, ensuring comprehensiveness and effectiveness.

[0076] Step 3: Automated test execution.

[0077] An optional embodiment of this application integrates an automated execution module into the test process to achieve automatic scheduling and execution of test tasks. After the test order is created, the system will automatically execute the relevant test tasks based on the generated test cases and record the real-time test results. The automated test execution process includes the following key steps:

[0078] 1) Test order creation: Automatically create test orders based on generated test cases, reducing the time and errors of manual management of test orders.

[0079] 2) Real-time result recording and analysis: During the test execution process, the system automatically records the execution results of each test step and analyzes the test results in real time to detect whether there are any unexpected situations.

[0080] 3) Defect capture: The system automatically identifies and records defects in testing, including generating defect reports, describing the reproduction steps and related data environment information.

[0081] Step 4: The test report is automatically generated.

[0082] The system of the optional embodiment of the present application (equivalent to the above-mentioned automated test system or automated test platform or automated platform) can automatically generate detailed test reports, reduce manual operations, and improve the efficiency and accuracy of report generation. The automated report generation module covers the entire process from test data collection to report output.

[0083] The system collects input data, output results, execution time, and test environment information for each test step in real time during test execution. All test results are stored in a structured format, ensuring that reports fully reflect the test execution status.

[0084] After collecting test results, the system automatically compares the actual output of each test step with the expected output and marks the test result as passed or failed. For test cases that failed, the system will annotate and record the relevant details for further analysis and remediation.

[0085] When automatically generating a test report, the system will list the defects found during the test. The report content includes:

[0086] 1) Defect title: Describe the module involved in the defect and its main problem.

[0087] 2) Reproduction steps: Describe in detail the steps on how to reproduce the defect.

[0088] 3) Comparison of actual results with expected results: Helps developers quickly locate and solve problems.

[0089] The test report includes statistical information on the overall test results, such as the total number of test cases executed, pass rate, and failure rate. The system provides a tabular summary of the results, allowing project teams to quickly understand the testing status. Basic charts, such as a bar chart showing test case pass rates and a line chart showing changes in the number of defects, are also generated to help project managers track testing progress and project quality.

[0090] The system automatically verifies test results against pre-set factory standards. For example, it checks whether the repair rate for "fatal" and "serious" defects has reached 100%, and clearly indicates in the report whether the product meets factory standards.

[0091] The main standards checked by this system include:

[0092] 1) Whether all test cases have been executed.

[0093] 2) Whether high-priority defects have been fixed and meet requirements.

[0094] 3) Whether the repair rate of interface and prompt information errors reaches 95% or above.

[0095] Finally, the system automatically generates a structured test report that includes a summary of test results, a list of defects, and compliance check results. The generated report is saved to a designated directory and notified to relevant personnel for review and approval.

[0096] In summary, the optional embodiments of the present application parse complex requirements through a refined thinking process, automatically generate user stories and test requirements, and ensure that test cases cover all core functions. Generate test cases covering normal paths, boundary values, and abnormal scenarios according to different scenarios to ensure that the system is fully verified under various conditions. After the test is executed, the system automatically captures defects and generates a detailed defect report, including information such as reproduction steps, affected modules, and priority, thereby simplifying the defect management process of the testing team and improving the efficiency and accuracy of defect handling.

[0097] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0098] The embodiment of the present application also provides a structural block diagram of a device for recording test results. Figure 4 is a structural block diagram of a device for recording test results according to an embodiment of the present application; Figure 4 Shown, including:

[0099] A parsing module 42 is configured to parse a demand document of the electricity spot market using a large language model to obtain a test requirement for testing the electricity spot market;

[0100] A generating module 44, configured to generate a test case for testing the electricity spot market based on the test requirements;

[0101] The recording module 46 is configured to record the test results obtained by executing the test case on the electricity spot market.

[0102] Through the above-mentioned device, the demand document of the electricity spot market is parsed by the large language model to obtain the test requirements for testing the electricity spot market; based on the test requirements, a test case for testing the electricity spot market is generated; and the test results obtained by executing the test case on the electricity spot market are recorded. In other words, by inputting the demand document of the electricity spot market into the large language model, parsing the test requirements, and then generating the test case according to the test requirements, the test results obtained by executing the test case on the electricity spot market are recorded, thereby achieving the technical effect of automatically, efficiently and flexibly testing the electricity spot market. Therefore, through the above-mentioned embodiment, the problem in the prior art that the test process of the electricity spot market usually relies on manual operation, resulting in low test efficiency and poor flexibility, is solved.

[0103] In an exemplary embodiment, the parsing module 42 is further used to: refine the requirement document to obtain a requirement document with redundant information removed, wherein the redundant information includes: information irrelevant to the testing of the electricity spot market and redundant symbols; and convert the requirement document with redundant information removed into the test requirement through the large language model.

[0104] In an exemplary embodiment, the analysis module 42 is further configured to determine the test requirement by the following formula: θ (y|prompt thought (z))·p θ (z|prompt refine (x)); where y1 represents the test requirement, x represents the requirement document, z represents the requirement content after the requirement document is refined, and p θ Represents the conditional probability distribution of the large language model, and the large language model analyzes the requirement document through the input prompt.

[0105] In an exemplary embodiment, the generating module 44 is further configured to input the test requirement into the large language model to obtain the test case using the following formula: Among them, y2 represents the final generated output, n represents the total number of steps to generate the test case, and x i represents the partial output generated in step i, x i Depends on x1,x2,x3,...,x i-1 , the output finally generated includes: the test case or the partial output.

[0106] In an exemplary embodiment, the recording module 46 is further configured to: create a test sheet using the test case; execute the test case using the test sheet to obtain an execution result; use the execution result as the test result, and record the test result.

[0107] In an exemplary embodiment, the device also includes a report generation module for recording the test results obtained after executing the test case on the electricity spot market: obtaining process data generated during the execution of the test case; analyzing the process data and the test results, and generating a test report based on the obtained analysis results.

[0108] An embodiment of the present application further provides a storage medium, which includes a stored program, wherein the program executes any of the above methods when it is run.

[0109] Optionally, in this embodiment, the storage medium may be configured to store program codes for executing the following steps:

[0110] S1, parsing a demand document of the electricity spot market using a large language model to obtain test requirements for testing the electricity spot market;

[0111] S2, generating a test case for testing the electricity spot market based on the test requirements;

[0112] S3, recording the test results obtained by executing the test case on the electricity spot market.

[0113] An embodiment of the present application further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0114] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0115] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0116] S1, parsing a demand document of the electricity spot market using a large language model to obtain test requirements for testing the electricity spot market;

[0117] S2, generating a test case for testing the electricity spot market based on the test requirements;

[0118] S3, recording the test results obtained by executing the test case on the electricity spot market.

[0119] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store program codes.

[0120] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in any one of the above method embodiments are implemented.

[0121] An embodiment of the present application further provides another computer program product, comprising a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any of the above method embodiments are implemented.

[0122] An embodiment of the present application also provides a computer program, which includes computer instructions stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps of any of the above method embodiments.

[0123] Optionally, specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0124] Obviously, those skilled in the art should understand that the modules or steps of the present application described above can be implemented using a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices. Alternatively, they can be implemented using program code executable by the computing device, so that they can be stored in a storage device and executed by the computing device. In some cases, the steps shown or described can be performed in a different order than herein, or they can be made into separate integrated circuit modules, or multiple modules or steps can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0125] The above description is merely a preferred embodiment of the present application and is not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A method for recording test results, characterized in that: include: Parsing a demand document of the electricity spot market through a large language model to obtain a test requirement for testing the electricity spot market; generating a test case for testing the electricity spot market based on the test requirements; Record test results obtained by executing the test case on the electricity spot market.

2. The method for recording test results according to claim 1, wherein: The power spot market requirement document is parsed using a large language model to obtain test requirements for testing the power spot market, including: Refining the requirement document to obtain a requirement document with redundant information removed, wherein the redundant information includes: information irrelevant to testing the electricity spot market and redundant symbols; The requirement document with redundant information removed is converted into the test requirement through the large language model.

3. The method for recording test results according to claim 1, wherein: The power spot market requirement document is parsed using a large language model to obtain test requirements for testing the power spot market, including: The test requirements are determined by the following formula: y1~p θ (y|prompt thought (z))·p θ (z|prompt refine (x)); Among them, y1 represents the test requirement, x represents the requirement document, z represents the requirement content after the requirement document is refined, and p θ represents the conditional probability distribution of the large language model, and the large language model analyzes the requirement document through the input prompt.

4. The method for recording test results according to claim 1, wherein: Generating a test case for testing the electricity spot market based on the test requirement, including: The test requirements are input into the large language model to obtain the test case using the following formula: Among them, y2 represents the final generated output, n represents the total number of steps to generate the test case, and x i represents the partial output generated in step i, x i Depends on x1,x2,x3,...,x i-1 , the output finally generated includes: the test case or the partial output.

5. The method for recording test results according to claim 1, wherein: Recording test results obtained by executing the test case on the electricity spot market, including: Create a test order using the test case; Execute the test case through the test sheet to obtain the execution result; The execution result is used as the test result, and the test result is recorded.

6. The method for recording test results according to claim 1, wherein: After recording the test results obtained by executing the test case on the electricity spot market, the method further includes: Acquire process data generated during the execution of the test case; The process data and the test results are analyzed, and a test report is generated according to the obtained analysis results.

7. A device for recording test results, characterized in that: include: A parsing module, configured to parse a demand document of the electricity spot market using a large language model to obtain a test requirement for testing the electricity spot market; A generating module, configured to generate a test case for testing the electricity spot market based on the test requirements; A recording module is used to record the test results obtained by executing the test case on the electricity spot market.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 6 when executed.

9. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 6 through the computer program.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images