Induction model testing method, system, equipment and medium
By comparing the induction model test results before and after the code changes and filtering the differences, the problem of inducing model testing is solved, and a more efficient and accurate testing process is achieved.
Patent Information
- Application Number
- CN202510172092.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-17
- Publication Date
- 2025-06-06
AI Technical Summary
The output results of the induction model are complex and contain a large number of parameters, which requires a lot of manpower and is inefficient during testing.
By comparing the test results of the induction model after code changes with the induction model before code changes, and filtering the results, determining the actual differences, and filtering out the target test cases affected by code changes.
It improves the efficiency of the test, can find possible problems more intuitively and quickly, reduces manpower and material resources costs, and improves the coverage and accuracy of the test.
Smart Images
Figure CN120104485A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the field of navigation, and in particular to a testing method, system, equipment and medium for an induction model. Background Art
[0002] The induction model, also known as the driving assistance model, is a computational model that provides real-time driving advice to the driver based on a given route. Based on the pre-calculated route, the induction model prompts the driver to perform actions at a specific time or place, such as turning left or right, slowing down, turning on the lights, etc. These prompts are intended to help the driver drive more safely, comfortably, and efficiently. In order to ensure the correctness and effectiveness of the induction model, it needs to be tested. Through testing, possible errors in the induction model's operation prompts can be discovered and corrected to ensure that it can provide accurate assistance in various driving situations.
[0003] However, the output of the induced model is very complex, containing hundreds or even thousands of parameters. During testing, all the parameters returned by the induced model need to be verified to determine whether they meet expectations, which requires a lot of manpower and is inefficient. Summary of the invention
[0004] In order to solve the above problems, the present invention provides a testing method, system, equipment and medium for an induced model.
[0005] The first aspect of the present invention discloses a method for testing an induced model, comprising:
[0006] According to the induced model after the code modification, multiple target test cases are determined from all test cases;
[0007] Obtain the induced model before the code is modified as the original induced model;
[0008] Based on the induced model after the code modification and the original induced model, the plurality of target test cases are tested respectively to obtain the test results corresponding to the induced model after the code modification and the reference results corresponding to the original induced model;
[0009] Comparing the test result with the reference result to obtain a test difference, wherein the test difference includes at least one difference item;
[0010] According to the content of the difference items, the test differences are filtered to obtain the actual differences;
[0011] A target test case corresponding to the actual difference is determined, and the target test case is used as a test failure case of the induced model after the code is modified.
[0012] Furthermore, the step of determining a plurality of target test cases from all test cases according to the induced model after the code modification includes:
[0013] Obtaining the code corresponding to each of the test cases in the induced model after the code is modified as the test case code;
[0014] Determine whether the use case code corresponding to each of the test cases belongs to the code modification scope of the induced model after the code modification;
[0015] If so, the test case is selected as a target test case.
[0016] Further, the steps of testing a plurality of the target test cases based on the induced model after the code modification and the original induced model respectively to obtain the test results corresponding to the induced model after the code modification and the reference results corresponding to the original induced model include:
[0017] Obtaining the route starting point and route end point in each of the target test cases;
[0018] Inputting the route starting point, the route end point, and predetermined map data into a pre-prepared route generation model to obtain a test route;
[0019] The test route is input into the induction model after the code modification and the original induction model respectively, so as to obtain the test result corresponding to the induction model after the code modification and the reference result corresponding to the original induction model.
[0020] Further, the step of filtering the test differences according to the content of the difference items to obtain the actual differences includes:
[0021] Traverse all the difference items in the test difference, and for each of the difference items:
[0022] According to the type of the difference item, obtain the corresponding difference item filtering condition;
[0023] Determine whether the difference item meets the difference item filtering condition:
[0024] If they match, the difference items are filtered;
[0025] If not, the difference item is retained as the actual difference.
[0026] Further, the step of filtering the test differences according to the content of the difference items to obtain the actual differences includes:
[0027] Traverse all the difference items in the test difference, and for each of the difference items:
[0028] Get the corresponding target test case;
[0029] Get the third-party induced operation set corresponding to the target test case;
[0030] Comparing the induced operation of the induced model after the code modification in the difference item to see whether it conforms to the corresponding induced operation in the third-party induced operation set;
[0031] If they match, the difference items are filtered;
[0032] If not, the difference item is retained as the actual difference.
[0033] Further, the step of filtering the test differences according to the content of the difference items to obtain the actual differences includes:
[0034] Traverse all the difference items in the test difference, and for each of the difference items:
[0035] acquiring local map data corresponding to the difference item from the map data corresponding to the difference item;
[0036] Determining whether the difference item is caused by a change in the local map data:
[0037] If yes, filtering the difference items;
[0038] If not, the difference term is retained as the actual difference.
[0039] Further, the step of filtering the test differences according to the content of the difference items to obtain the actual differences includes:
[0040] Traverse all the difference items in the test difference, and for each of the difference items:
[0041] Check whether the difference item meets the predefined difference tolerance rules:
[0042] If yes, filtering the difference items;
[0043] If not, the difference term is retained as the actual difference.
[0044] The second aspect of the present invention discloses a test system for an induced model, comprising:
[0045] A first determination module is used to determine a plurality of target test cases from all test cases according to the induced model after the code modification;
[0046] An acquisition module is used to acquire the induced model before the code is modified as the original induced model;
[0047] A testing module, used to test the plurality of target test cases based on the induced model after the code modification and the original induced model, respectively, to obtain the test results corresponding to the induced model after the code modification and the reference results corresponding to the original induced model;
[0048] A comparison module, used for comparing the test result with the reference result to obtain a test difference, wherein the test difference includes at least one difference item;
[0049] A filtering module, used for filtering the test differences according to the content of the difference items to obtain the actual differences;
[0050] The second determination module is used to determine the target test case corresponding to the actual difference and use it as the test failure case of the induced model after the code is modified.
[0051] The third aspect of the present invention discloses an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and is characterized in that when the processor executes the computer program, the steps of any induced model testing method disclosed in the first aspect of the present invention are implemented.
[0052] The fourth aspect of the present invention discloses a storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of any one of the induced model testing methods disclosed in the first aspect of the present invention.
[0053] The present invention can find possible problems more intuitively and quickly by comparing the test results of the current induction model with the test results of the stable historical version of the induction model and filtering the comparison results, thereby greatly improving the test efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0055] Figure 1 It is a flow chart of a testing method of an induced model disclosed in an embodiment of the present invention;
[0056] Figure 2 is a schematic diagram comparing two induction operations disclosed in an embodiment of the present invention;
[0057] Figure 3 It is a structural schematic diagram of a testing system for an induction model disclosed in an embodiment of the present invention;
[0058] Figure 4 It is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION
[0059] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below 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 of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0060] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, or product end including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products, or ends.
[0061] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0062] The present invention provides a test method for an induced model, which compares the test results of the induced model before the code modification to verify whether the modification of the code modification of the induced model is accurate. The present invention reduces the cost of manpower and material resources, reduces the subjective influence of the evaluators, improves the coverage of the induced model test, and ensures the accuracy and objectivity of the model evaluation results.
[0063] See also Figure 1 As shown, Figure 1 FIG. 1 is a flow chart of a method for testing an induced model disclosed in an embodiment of the present invention. Figure 1 As shown, the testing method of the induction model may include the following operations:
[0064] S101. Determine multiple target test cases from all test cases according to the induced model after the code modification;
[0065] In an optional embodiment, the step of determining a plurality of target test cases from all test cases according to the induced model after the code modification includes:
[0066] Obtaining the code corresponding to each of the test cases in the induced model after the code is modified as the test case code;
[0067] Determine whether the use case code corresponding to each of the test cases belongs to the code modification scope of the induced model after the code modification;
[0068] If so, the test case is selected as a target test case.
[0069] A test case is a set of input data, execution conditions, and expected results designed to verify the functionality, performance, reliability, etc. of a software system. By running test cases, you can check whether the software meets the predetermined requirements and specifications, thereby discovering and fixing defects and errors in the software.
[0070] The code corresponding to the test case refers to the source code covered by the test case. Each test case corresponds to a specific code path and logic branch of the induced model. When the test case is executed, the corresponding code will be called and run. By analyzing the code corresponding to the test case, the test coverage can be evaluated and the weak links that are not covered by the test can be found.
[0071] It can be seen that this optional embodiment can quickly and accurately screen out target test cases affected by code changes by judging whether the test case code corresponding to each test case covers the code changes, avoiding unnecessary testing of all test cases and improving test efficiency. At the same time, this method can ensure that the selected target test cases are directly related to the code changes, and the test results can reflect the impact of the code changes, thereby improving the pertinence and effectiveness of the test. Focusing on testing the selected target test cases can detect defects introduced by code changes as early as possible, reducing software quality risks.
[0072] S102, obtaining an induction model before the code is modified as an original induction model;
[0073] The original induced model reflects the system behavior before the code is changed. It is a stable version that has been tested and verified. Its test results can be used as a reference benchmark to evaluate the impact of code changes.
[0074] S103, testing the plurality of target test cases based on the induced model after the code modification and the original induced model, respectively, to obtain the test results corresponding to the induced model after the code modification and the reference results corresponding to the original induced model;
[0075] In an optional embodiment, the steps of testing a plurality of the target test cases based on the induced model after the code modification and the original induced model respectively to obtain the test results corresponding to the induced model after the code modification and the reference results corresponding to the original induced model include:
[0076] Obtaining the route starting point and route end point in each of the target test cases;
[0077] Inputting the route starting point, the route end point, and predetermined map data into a pre-prepared route generation model to obtain a test route;
[0078] The test route is input into the induction model after the code modification and the original induction model respectively, so as to obtain the test result corresponding to the induction model after the code modification and the reference result corresponding to the original induction model.
[0079] The route generation model is a model based on machine learning or rule engines. It can automatically generate a test route that meets the requirements based on the input route starting point, end point and map data.
[0080] It can be seen that the automatic generation of test routes in this optional embodiment can reduce the workload of manually designing and writing test cases, reduce testing costs, and improve testing efficiency.
[0081] S104, comparing the test result with the reference result to obtain a test difference, where the test difference includes at least one difference item;
[0082] The test result is compared with the reference result based on a text comparison tool, wherein the difference item is, for example, the reference result is the coordinate (100, 90), turn left, while the test result is the coordinate (96, 92), turn left.
[0083] S105, filtering the test differences according to the difference items to obtain actual differences;
[0084] In an optional embodiment, the step of filtering the test differences according to the content of the difference items to obtain the actual differences includes:
[0085] Traverse all the difference items in the test difference, and for each of the difference items:
[0086] According to the type of the difference item, obtain the corresponding difference item filtering condition;
[0087] Determine whether the difference item meets the difference item filtering condition:
[0088] If they match, the difference items are filtered;
[0089] If not, the difference item is retained as the actual difference.
[0090] For example, in a difference item, the reference result is the coordinate (100, 90), turn left, and the test result is the coordinate (96, 92), turn left. The difference type is the coordinate value difference, and the preset difference item filtering condition of the coordinate value difference is that if the coordinate difference is less than the preset threshold, the difference item should be filtered out.
[0091] It can be seen that this optional embodiment improves the accuracy and efficiency of the induced model test through an intelligent difference filtering mechanism, reduces false alarms and the workload of manual processing, and has significant technical advantages and practical value.
[0092] In another optional embodiment, the step of filtering the test differences according to the content of the difference items to obtain the actual differences includes:
[0093] Traverse all the difference items in the test difference, and for each of the difference items:
[0094] Get the corresponding target test case;
[0095] Get the third-party induced operation set corresponding to the target test case;
[0096] Comparing the induced operation of the induced model after the code modification in the difference item to see whether it conforms to the corresponding induced operation in the third-party induced operation set;
[0097] If they match, the difference items are filtered;
[0098] If not, the difference item is retained as the actual difference.
[0099] In this optional embodiment, the third-party induced operation set can be the pre-prepared induced operations of the map provider corresponding to the target test cases. By comparing the output of the induced model after the code is modified with the induced operations of the third party, it can be determined whether the modified model meets industry standards and user expectations.
[0100] It can be seen that this optional embodiment introduces the induction operation of a third party as a reference standard. The test results are no longer completely dependent on the original induction model, but are compared with industry standards, thereby improving the objectivity and credibility of the test results.
[0101] In yet another optional embodiment, the step of filtering the test differences according to the content of the difference items to obtain the actual differences includes:
[0102] Traverse all the difference items in the test difference, and for each of the difference items:
[0103] acquiring local map data corresponding to the difference item from the map data corresponding to the difference item;
[0104] Determining whether the difference item is caused by a change in the local map data:
[0105] If yes, filtering the difference items;
[0106] If not, the difference term is retained as the actual difference.
[0107] For example, in a difference item, the original guidance model gives the guidance operation of turning left at an intersection, and the guidance operation given by the code-modified guidance model at the intersection is turning U-turn, and the road guidance sign for the intersection in the map data is changed from turning left to turning U-turn, then the difference item should be filtered out.
[0108] It can be seen that this optional embodiment, by introducing the analysis of local map data changes, intelligently identifies and filters out differences caused by non-code changes, improves the pertinence, accuracy and efficiency of the induction model test, and has significant technical advantages and practical value. This method can adapt to the dynamic changes of map data, ensure the validity and reliability of the test results, and provide strong support for the continuous optimization and upgrading of the induction model.
[0109] In yet another optional embodiment, the step of filtering the test differences according to the content of the difference items to obtain the actual differences includes:
[0110] Traverse all the difference items in the test difference, and for each of the difference items:
[0111] Check whether the difference item meets the predefined difference tolerance rules:
[0112] If yes, filtering the difference items;
[0113] If not, the difference term is retained as the actual difference.
[0114] For example, Figure 2 A schematic diagram comparing two induction operations is shown. On the left is the induction operation given by the original induction model at an intersection: a straight left model; on the right is the induction operation given by the induction model after the code modification at the intersection: a left fork in a Y-shaped intersection / small triangle, which is caused by different threshold boundaries of the route angle, but has no impact on the end user and should be filtered out.
[0115] Difference tolerance rules can be continuously iterated based on historical testing experience. By filtering out differences that are acceptable to users, the test results focus more on differences that have a substantial impact on user experience, thereby improving the practicality and effectiveness of the test.
[0116] It can be seen that this optional embodiment can adaptively filter out differences that are acceptable to users through continuous iteration and optimization of rules, so that the test results can be more focused on key issues and the problem location and repair process can be accelerated. While improving the effectiveness of the test, it also reduces unnecessary workload, and has significant technical advantages and practical value.
[0117] S106: Determine a target test case corresponding to the actual difference, and use it as a test failure case of the induced model after the code is modified.
[0118] It can be seen that this embodiment can find possible problems more intuitively and quickly by comparing the test results of the current induction model with the test results of the stable historical version of the induction model and filtering the comparison results, thereby greatly improving the test efficiency.
[0119] like Figure 3 As shown, the present invention provides a test system for an induced model, comprising:
[0120] A first determination module 301 is used to determine a plurality of target test cases from all test cases according to the induced model after the code modification;
[0121] An acquisition module 302 is used to acquire the induction model before the code is modified as the original induction model;
[0122] The testing module 303 is used to test the plurality of target test cases based on the induced model after the code modification and the original induced model, respectively, to obtain the test results corresponding to the induced model after the code modification and the reference results corresponding to the original induced model;
[0123] A comparison module 304 is used to compare the test result with the reference result to obtain a test difference, wherein the test difference includes at least one difference item;
[0124] A filtering module 305 is used to filter the test differences according to the difference items to obtain actual differences;
[0125] The second determination module 306 is used to determine the target test case corresponding to the actual difference and use it as the test failure case of the induced model after the code modification.
[0126] The specific definition of the test system of the induction model can be found in the definition of the test method of the induction model mentioned above, which will not be repeated here. Each module in the test system of the induction model can be implemented in whole or in part by software, hardware and a combination thereof. The above modules can be embedded in or independent of the processor in the electronic device in hardware format, or can be stored in the memory of the electronic device in software format, so that the processor can call the operations corresponding to the above modules.
[0127] It should be noted that, in order to highlight the innovative part of the present invention, the present embodiment does not introduce modules that are not closely related to solving the technical problem proposed by the present invention, but this does not mean that there are no other modules in the present embodiment.
[0128] like Figure 4 As described above, the electronic device 1 provided by the present invention may include a memory 12, a processor 13 and a bus, and may also include a computer program stored in the memory 12 and executable on the processor 13, such as a test program for an induced model.
[0129] The memory 12 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 12 may be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 12 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 12 may also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 12 may not only be used to store application software and various types of data installed in the electronic device 1, such as the code for testing the induced model, etc., but may also be used to temporarily store data that has been output or is to be output.
[0130] In some embodiments, the processor 13 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor 13 is the control core (Control Unit) of the electronic device 1, and uses various interfaces and lines to connect various components of the entire electronic device 1, and executes or executes programs or modules (such as test programs of induced models, etc.) stored in the memory 12, and calls data stored in the memory 12 to execute various functions of the electronic device 1 and process data.
[0131] The processor 13 executes the operating system and various installed application programs of the electronic device 1. The processor 13 executes the application programs to implement the steps in the above-mentioned induced model testing method.
[0132] Exemplarily, the computer program may be divided into one or more modules, which are stored in the memory 12 and executed by the processor 13 to complete the present application. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the electronic device 1. For example, the computer program may be divided into a first determination module 301, an acquisition module 302, a test module 303, a comparison module 304, a filtering module 305, and a second determination module 306.
[0133] The above-mentioned integrated unit implemented in the form of a software function module can be stored in a computer-readable storage medium, and the storage medium can be non-volatile or volatile. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a computer device, or a network device, etc.) or a processor to perform part of the functions of the test method of the induced model described in each embodiment of the present application.
[0134] In one embodiment, a storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps implemented when the processor executes the computer program can also be implemented.
[0135] In summary, the test method, system, device and medium of the induction model disclosed in the present invention can more intuitively and quickly find possible problems, thereby greatly improving the efficiency of the test. Therefore, the present invention effectively overcomes various shortcomings in the prior art and has high industrial utilization value.
[0136] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.
Claims
1. A test method for an induced model, characterized in that: The method comprises: According to the induced model after the code modification, multiple target test cases are determined from all test cases; Obtain the induced model before the code is modified as the original induced model; Based on the induced model after the code modification and the original induced model, the plurality of target test cases are tested respectively to obtain the test results corresponding to the induced model after the code modification and the reference results corresponding to the original induced model; Comparing the test result with the reference result to obtain a test difference, wherein the test difference includes at least one difference item; According to the content of the difference items, the test differences are filtered to obtain the actual differences; A target test case corresponding to the actual difference is determined, and the target test case is used as a test failure case of the induced model after the code is modified.
2. The testing method of an induced model according to claim 1, characterized in that: The step of determining multiple target test cases from all test cases according to the induced model after the code modification includes: Obtaining the code corresponding to each of the test cases in the induced model after the code is modified as the test case code; Determine whether the use case code corresponding to each of the test cases belongs to the code modification scope of the induced model after the code modification; If so, the test case is selected as a target test case.
3. The testing method of an induced model according to claim 1, characterized in that: The steps of testing a plurality of the target test cases based on the induced model after the code modification and the original induced model respectively to obtain the test results corresponding to the induced model after the code modification and the reference results corresponding to the original induced model include: Obtaining the route starting point and route end point in each of the target test cases; Inputting the route starting point, the route end point, and predetermined map data into a pre-prepared route generation model to obtain a test route; The test route is input into the induction model after the code modification and the original induction model respectively, so as to obtain the test result corresponding to the induction model after the code modification and the reference result corresponding to the original induction model.
4. The testing method of an induced model according to claim 1, characterized in that: The steps of filtering the test differences according to the difference items to obtain the actual differences include: Traverse all the difference items in the test difference, for each of the difference items: According to the type of the difference item, obtain the corresponding difference item filtering condition; Determine whether the difference item meets the difference item filtering condition: If they match, the difference items are filtered; If not, the difference item is retained as the actual difference.
5. The testing method of an induced model according to claim 1, characterized in that: The steps of filtering the test differences according to the difference items to obtain the actual differences include: Traverse all the difference items in the test difference, and for each of the difference items: Get the corresponding target test case; Get the third-party induced operation set corresponding to the target test case; Comparing the induced operation of the induced model after the code modification in the difference item to see whether it conforms to the corresponding induced operation in the third-party induced operation set; If they match, the difference items are filtered; If not, the difference item is retained as the actual difference.
6. The testing method of an induced model according to claim 1, characterized in that: The steps of filtering the test differences according to the difference items to obtain the actual differences include: Traverse all the difference items in the test difference, and for each of the difference items: acquiring local map data corresponding to the difference item from the map data corresponding to the difference item; Determining whether the difference item is caused by a change in the local map data: If yes, filtering the difference items; If not, the difference term is retained as the actual difference.
7. The testing method of an induced model according to claim 1, characterized in that: The steps of filtering the test differences according to the difference items to obtain the actual differences include: Traverse all the difference items in the test difference, and for each of the difference items: Check whether the difference item meets the predefined difference tolerance rules: If yes, filtering the difference items; If not, the difference term is retained as the actual difference.
8. A test system for an induction model, characterized in that: include: A first determination module is used to determine a plurality of target test cases from all test cases according to the induced model after the code modification; An acquisition module is used to acquire the induced model before the code is modified as the original induced model; A testing module, used to test the plurality of target test cases based on the induced model after the code modification and the original induced model, respectively, to obtain the test results corresponding to the induced model after the code modification and the reference results corresponding to the original induced model; A comparison module, used for comparing the test result with the reference result to obtain a test difference, wherein the test difference includes at least one difference item; A filtering module, used for filtering the test differences according to the content of the difference items to obtain the actual differences; The second determination module is used to determine the target test case corresponding to the actual difference and use it as the test failure case of the induced model after the code is modified.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the testing method of the induced model according to any one of claims 1 to 7 are implemented.
10. A storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the testing method of the induced model according to any one of claims 1 to 7 are implemented.