Multi-dimensional evaluation method and device for data-real fusion test

Abstract

The invention discloses a multi-dimensional evaluation method and device for a digital-real fusion test, and belongs to the intelligent manufacturing and digital testing technology, and the method comprises the steps: building a three-dimensional evaluation module: obtaining the data accuracy, scene coverage and test timeliness of the digital-real fusion test, and generating a static credible evaluation value; establishing a closed-loop verification module: verifying model parameters of the digital model through actual measurement data to obtain the credibility of the physical equipment verification digital model, and calculating actual calibration parameters; verifying the test result generated by the specific scene and the test result of the entity equipment to obtain the credibility of the digital model verification entity equipment, and calculating the calibration parameters; generating a dynamic credible evaluation value; establishing a comprehensive evaluation module: calculating total credible evaluation according to the static credible evaluation value and the dynamic credible evaluation value; and generating six sub-item evaluations, and correspondingly generating a judgment mechanism. According to the invention, multi-dimensional comprehensive evaluation of the inherent capability of the digital test is realized.

Description

Technical Field

[0001] This invention belongs to the field of intelligent manufacturing and digital testing technology, specifically relating to a multi-dimensional evaluation method and device for data-real fusion testing. Background Technology

[0002] While fusion testing of digital and physical data is widely used in existing technologies, the methods for evaluating its results still have significant limitations. Current mainstream evaluation methods suffer from the following problems: First, the evaluation metrics are too simplistic, often focusing only on the deviation between the test results and the expected goals, while neglecting important dimensions such as test scenario coverage and testing efficiency. Second, the evaluation process is static, lacking continuous assessment of the dynamic interaction between the digital model and the physical testing. Third, the evaluation results are isolated, failing to establish an organic link between the evaluation metrics of digital testing and physical testing.

[0003] Taking the testing and evaluation of intelligent driving systems as an example, existing methods typically calculate the pass rate of digital simulation tests and the compliance rate of actual tests separately. This fails to reflect the correlation between the two types of test results, nor can it assess the overall effectiveness of the testing process. In the industrial manufacturing sector, the evaluation of digital production line testing often focuses only on the pass rate of the final product, while neglecting the comprehensiveness of the test scenario coverage and the efficiency of test resource utilization.

[0004] The shortcomings of these evaluation methods directly affect the optimization and improvement of testing work. Due to the lack of a systematic evaluation framework, test engineers struggle to accurately identify weaknesses in test plans and cannot scientifically adjust the resource allocation between digital testing and physical testing. Especially in the testing of complex systems, this evaluation deficiency may lead to the neglect of important testing blind spots or the waste of testing resources. Summary of the Invention

[0005] To solve the above-mentioned technical problems, the present invention adopts the following technical solution:

[0006] A multi-dimensional evaluation method for data-real fusion testing includes:

[0007] Step 1: Establish a three-dimensional evaluation module; including: obtaining the data accuracy of the data fusion test. Scenario coverage of data-real fusion testing Timeliness of data-real fusion testing Generate static reliability evaluation values ;

[0008] Step 2, establish a closed-loop verification module; including: verifying the model parameters of the digital model with actual measurement data using physical equipment to obtain the credibility of the digital model verified by the physical equipment, and calculating the actual calibration parameters. The digital model generates test results in specific scenarios and verifies them with the test results of physical equipment to obtain the credibility of the digital model in verifying the physical equipment, and calculates the digital verification parameters. Generate dynamic credibility evaluation values ;

[0009] Step 3, establish a comprehensive evaluation module; including: the static reliability evaluation value from Step 1. and the dynamic reliability evaluation value in step 2 Calculate the overall credibility evaluation Six sub-evaluations are generated, along with corresponding judgment mechanisms.

[0010] A multi-dimensional evaluation device for data-real fusion testing includes the following modules:

[0011] The 3D evaluation acquisition module obtains the accuracy of data from the data-real fusion test. Scenario coverage of data-real fusion testing Timeliness of data-real fusion testing Generate static reliability evaluation values ;

[0012] The closed-loop verification acquisition module uses measured data from physical equipment to verify the model parameters of the digital model, thereby obtaining the credibility of the physical equipment in verifying the digital model and calculating the actual calibration parameters. The digital model generates test results in specific scenarios and verifies them with the test results of physical equipment to obtain the credibility of the digital model in verifying the physical equipment, and calculates the digital verification parameters. Generate dynamic credibility evaluation values ;

[0013] The comprehensive evaluation acquisition module generates static reliable evaluation values ​​from the three-dimensional evaluation acquisition module. The dynamic trustworthy evaluation value generated by the closed-loop verification module. Calculate the overall credibility evaluation Six sub-evaluations are generated, along with corresponding judgment mechanisms.

[0014] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the multidimensional evaluation method for data-real fusion testing.

[0015] A non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the multidimensional evaluation method for data-real fusion testing as described in any one of claims 1 to 7.

[0016] The present invention has the following beneficial effects:

[0017] This invention addresses the problems of existing data-real fusion testing and evaluation methods, such as the simplification of evaluation indicators, the static nature of the evaluation process, and the isolation of evaluation results. It provides a multi-dimensional, dynamic, and interconnected comprehensive evaluation method. This method does not change the original testing process and methods; instead, it establishes a more comprehensive, dynamic, and interconnected evaluation system through systematic analysis of existing test results, providing a scientific basis for optimizing testing work. Specifically, it is reflected in:

[0018] This invention establishes a system that includes data accuracy. Scene coverage Test timeliness A three-dimensional static evaluation module with three dimensions is used, and a weighted calculation is employed to generate the initial credibility (static credibility evaluation value). This enables a multi-dimensional comprehensive evaluation of the inherent capabilities (accuracy, breadth, and efficiency) of digital testing.

[0019] This invention establishes a closed-loop dynamic verification module to calculate in real time the reliability of the digital model parameters (actual calibration parameters) based on the measured data of the physical equipment. The credibility of physical equipment test results verified by digital models in specific scenarios (digital calibration parameters) Based on the fusion of the two, a dynamic correction coefficient (dynamic reliability evaluation value) is generated. This enables continuous evaluation and feedback of the dynamic interaction process between digital models and physical equipment.

[0020] This invention establishes an evaluation fusion mechanism, employing a product form ( ) Integrate initial credibility (static credibility evaluation value) ) and dynamic correction coefficient (dynamic reliability evaluation value) It generates six sub-item combined evaluations, realizing the organic connection and in-depth collaborative analysis between digital testing and physical equipment testing evaluation indicators. Significant deficiencies in any dimension will affect the final evaluation.

[0021] This invention achieves intelligent optimization of the evaluation system based on the testing focus and precise location of weak links in the testing by setting an adaptive weight adjustment mechanism for the three-dimensional static evaluation module and the closed-loop dynamic verification module, and establishing a judgment mechanism for the sub-item combination evaluation (such as scene adaptability defect judgment, scene library expansion warning, and over-optimization identification), and constructing a visual analysis interface and intelligent optimization suggestion report. This significantly improves the engineering guidance value of the evaluation results. Attached Figure Description

[0022] Figure 1 This is an architecture diagram of the multi-dimensional evaluation method for data-real fusion testing according to the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.

[0024] This invention relates to the fields of intelligent manufacturing and digital testing technology, and is applicable to complex system verification scenarios requiring collaborative testing of digital models and actual equipment, such as autonomous driving and aero-engines, which have high reliability requirements, enabling multi-dimensional evaluation of their testing. The multi-dimensional evaluation method for data-real fusion testing of this invention specifically includes:

[0025] Step 1, establish a three-dimensional evaluation module; including:

[0026] Step 1.1: Obtain the data accuracy of the data fusion test. Data accuracy The error rate is calculated by comparing the numerical test results with the benchmark data. The calculation formula is as follows: ,in, For numerical test results, For benchmark test data, This refers to the maximum allowable error threshold for benchmark test data.

[0027] Step 1.2: Obtain the scenario coverage for the data-real fusion test. Scene coverage This is obtained by statistically analyzing the ratio of the number of key scenarios covered by digital testing to the total number of demand scenarios.

[0028] Step 1.3, Obtain the test timeliness of the data-real fusion test. Test timeliness The test timeliness E is calculated based on the ratio of the digital test completion time to the actual test completion time. When the digital test time is less than or equal to 1 / 10 of the actual test time, the test timeliness E takes the maximum value of 1.

[0029] Step 1.4: Generate static reliability evaluation values ,in, , , These are the accuracy weight, coverage weight, and test timeliness weight, respectively, all set to 1 / 3 by default.

[0030] Step 2, establish a closed-loop verification module; including:

[0031] Step 2.1: The physical equipment verifies the model parameters of the digital model using measured data to obtain the reliability of the physical equipment in verifying the digital model, and calculates the actual calibration parameters. , These are the predicted values ​​from the digital model. These are actual measured data. This represents the maximum allowable deviation from the measured data.

[0032] Step 2.2: The digital model generates test results in a specific scenario and verifies them with the test results of the physical equipment to obtain the credibility of the digital model in verifying the physical equipment, and calculates the digital verification parameters. , For test results in a specific scenario, Generate values ​​for the digital model. Maximum allowable deviation for generating values ​​for digital models;

[0033] Step 2.3: Generate dynamic reliability evaluation values ,in , These are the actual calibration parameter weights and the calibration actual parameter weights, respectively, both of which are 1 / 2 by default.

[0034] Step 3, establish a comprehensive evaluation module; including:

[0035] Step 3.1, Calculate the overall credibility assessment Strengthening static reliability evaluation values ​​through product form With dynamic credibility evaluation value The coupling effect highlights the synergistic effect of static and dynamic evaluation; a low score in any dimension will significantly affect the overall evaluation.

[0036] Step 3.2: Generate six sub-evaluations and their corresponding judgment mechanisms:

[0037] Evaluation of the combination of data accuracy and actual calibration parameters. This measures the synergistic effect between the basic accuracy of digital test results and the reliability of model parameters.

[0038] Evaluation of the combination of data accuracy and data verification parameters. ; Evaluate the actual generalization ability of digital test results in specific scenarios;

[0039] Evaluation based on a combination of scene coverage and actual number of tests. This reflects the correlation between the comprehensiveness of scenario coverage in digital testing and the consistency of model parameters.

[0040] Evaluation of the combination of scene coverage and numerical verification parameters. To verify the effectiveness of the digital test scenario library in covering actual demand scenarios;

[0041] Evaluation of the combination of test timeliness and actual calibration parameters. The combined advantages of speed in quantitative digital testing and the real-time performance of the model;

[0042] Evaluation of the combination of test timeliness and numerical verification parameters. ; Evaluate the ability of digital testing to maintain the credibility of results during rapid iteration.

[0043] The weight adjustment mechanism in step 1.4 includes:

[0044] When the test focuses on accuracy verification, automatically improve The weighting coefficients are adjusted by a certain margin. =0.1×(1- );

[0045] When testing focuses on scene coverage, automatically improve The weighting coefficients are adjusted by a certain margin. =0.1×(1- );

[0046] When testing focuses on testing efficiency, automatically improve The weighting coefficients are adjusted by a certain margin. =0.1×(1- );

[0047] After each adjustment , , Perform normalization processing to ensure .

[0048] The weight adjustment mechanism in step 2.3 includes:

[0049] When testing focuses on convergence capability, i.e., more accurate testing is required, automatic improvement is needed. The weighting coefficients are adjusted by a certain margin. =0.1×(1- );

[0050] When testing focuses on generalization ability, i.e., when more scenarios need to be covered, automatically improve... The weighting coefficient is adjusted by [percentage]. =0.1×(1- );

[0051] After each adjustment , Perform normalization processing to ensure .

[0052] The determination mechanism for the sub-item evaluation in step 3.2 includes:

[0053] Step 3.2.1, establish a judgment mechanism for sub-item evaluation:

[0054] when and The absolute value of the difference exceeds When the test is deemed to have a scenario adaptability defect, the following is determined: The scenario adaptability threshold for the accuracy of test results;

[0055] when and The ratio is lower than When this occurs, a scenario library expansion warning is triggered, indicating insufficient scenario coverage during testing. A capacity threshold for testing scenario coverage;

[0056] like Value greater than Value At that time, it was identified as excessively sacrificing accuracy for testing efficiency optimization, among which... The over-optimization threshold for testing timeliness;

[0057] Step 3.2.2, Build a visual analysis interface:

[0058] The results of the six sub-items are displayed simultaneously using a hexagonal radar chart;

[0059] Step 3.2.3: Generate an intelligent optimization suggestion report:

[0060] It automatically identifies the lowest-performing item among the six sub-evaluations and provides feedback suggestions.

[0061] The following is in conjunction with the appendix Figure 1 The specific embodiments of the present invention will be described in detail below. The multi-dimensional evaluation method for data-real fusion testing described in the present invention can be divided into the following key steps in its implementation process.

[0062] Firstly, in the 3D evaluation module, the system synchronously collects digital test results and compares them with benchmark data using formulas. Calculate data accuracy For example, in a car braking test scenario, if the digital simulation measures a braking distance of 38.5 meters, the actual test benchmark is 40 meters, and the industry allowable error is 5 meters, then the data accuracy... The value is 0.7. Simultaneously, the system calculates the proportion of key scenarios covered by the digital test. For example, if the intelligent driving test covers 85 scenarios while the standard requires 100, the scenario coverage C value is 0.85. The test timeliness E value is determined by comparing the time taken for digital and actual testing. When the digital test time is less than one-tenth of the actual test time, the maximum value of 1 is taken. When the digital test time exceeds one-tenth of the actual test time, E = 1 - (digital test time / actual test time). The evaluation results of these three dimensions are weighted to generate a static reliability evaluation value. Data accuracy The initial weights for scenario coverage (C) and test timeliness (E) are both set to 1 / 3 to ensure a balanced consideration.

[0063] The key to implementing the closed-loop verification module lies in the dynamic verification process. The system verifies the reliability of the model parameters using measured data from physical equipment. For example, in engine temperature testing, if the predicted temperature is 650℃ but the actual measured temperature is 680℃, the actual measured parameters will be verified. The value is 0.7. Simultaneously, the model's adaptability is verified for specific scenarios, such as when the digital prediction is 95 MPa but the actual measured load is 90 MPa under extreme load conditions, the parameters are calibrated accordingly. The value is 0.75. These two parameters are fused to generate a dynamic reliability evaluation value. Actual calibration parameters Sum of calibration parameters The initial weights are each 50% to ensure objectivity.

[0064] The comprehensive evaluation module calculates the overall credibility evaluation using a product approach. The system assigns a value such that deficiencies in any dimension will significantly impact the final result. It also generates six sub-evaluations and uses a geometric mean method to analyze the synergistic relationships between the dimensions.

[0065] The entire implementation process is presented intuitively through a visual interface. A hexagonal radar chart clearly displays the status of each evaluation indicator, and color coding can be used to distinguish between different states such as compliance and warning. The system supports data drill-down functionality; clicking on any indicator allows viewing the detailed calculation process. An anomaly detection mechanism monitors the relationships between indicators in real time, and when an anomaly is detected... and When an anomaly such as a difference exceeding 0.3 is detected, an automatic inspection process is triggered, and optimization suggestions are generated. This implementation method ensures both the standardization of the evaluation process and provides sufficient flexibility to adapt to the testing needs of different industries.

[0066] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The embodiments of the present invention can be implemented using various computer languages.

[0067] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0068] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0069] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0070] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0071] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

[0072] The above description is merely an embodiment of the present invention and does not limit the scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention specification and drawings, or direct or indirect applications in other related system fields, are similarly included within the protection scope of the present invention.

[0073] The contents not described in detail in this specification are existing technologies known to those skilled in the art.

Claims

1. A multi-dimensional evaluation method for data-real fusion testing, characterized in that, include: Step 1: Establish a three-dimensional evaluation module; including: obtaining the data accuracy of the data fusion test. Scenario coverage of data-real fusion testing Timeliness of data-real fusion testing Generate static reliability evaluation values ; Step 2, establish a closed-loop verification module; including: verifying the model parameters of the digital model with actual measurement data using physical equipment to obtain the credibility of the digital model verified by the physical equipment, and calculating the actual calibration parameters. The digital model generates test results in specific scenarios and verifies them with the test results of physical equipment to obtain the credibility of the digital model in verifying the physical equipment, and calculates the digital verification parameters. Generate dynamic credibility evaluation values ; Step 3, establish a comprehensive evaluation module; including: the static reliability evaluation value from Step 1. and the dynamic reliability evaluation value in step 2 Calculate the overall credibility evaluation Six sub-evaluations are generated, along with corresponding judgment mechanisms.

2. The multi-dimensional evaluation method for data-real fusion testing according to claim 1, characterized in that, Step 1 includes: Step 1.1: Obtain the data accuracy of the data fusion test. Data accuracy The error rate is calculated by comparing the numerical test results with the benchmark data. The calculation formula is as follows: ,in, For numerical test results, For benchmark test data, This refers to the maximum allowable error threshold for benchmark test data. Step 1.2: Obtain the scenario coverage for the data-real fusion test. Scene coverage This is obtained by statistically analyzing the ratio of the number of key scenarios covered by digital testing to the total number of demand scenarios. Step 1.3, Obtain the test timeliness of the data-real fusion test. Test timeliness The test timeliness E is calculated based on the ratio of the digital test completion time to the actual test completion time. When the digital test time is less than or equal to 1 / 10 of the actual test time, the test timeliness E takes the maximum value of 1. Step 1.4: Generate static reliability evaluation values ,in, , , These are the accuracy weight, coverage weight, and test timeliness weight, respectively.

3. The multi-dimensional evaluation method for data-real fusion testing according to claim 2, characterized in that, Step 2 includes: In step 2.1, the actual calibration parameters are calculated. , These are the predicted values ​​from the digital model. These are actual measured data. This represents the maximum allowable deviation from the measured data. In step 2.2, the numerical calibration parameters are calculated. , For test results in a specific scenario, Generate values ​​for the digital model. Maximum allowable deviation for generating values ​​for digital models; In step 2.3, a dynamic reliability evaluation value is generated. ,in , These are the actual calibration parameter weights and the calibration actual parameter weights, respectively, both of which are 1 / 2 by default.

4. The multi-dimensional evaluation method for data-real fusion testing according to claim 3, characterized in that, Step 3 includes: Step 3.1, Calculate the overall credibility assessment Strengthening static reliability evaluation values ​​through product form With dynamic credibility evaluation value The coupling effect highlights the synergistic effect of static and dynamic evaluation; a low score in any dimension will significantly affect the overall evaluation. Step 3.2: Generate six sub-evaluations and their corresponding judgment mechanisms: Evaluation of the combination of data accuracy and actual calibration parameters. This measures the synergistic effect between the basic accuracy of digital test results and the reliability of model parameters. Evaluation of the combination of data accuracy and data verification parameters. ; Evaluate the actual generalization ability of digital test results in specific scenarios; Evaluation based on a combination of scene coverage and actual number of tests. This reflects the correlation between the comprehensiveness of scenario coverage in digital testing and the consistency of model parameters. Evaluation of the combination of scene coverage and numerical verification parameters. To verify the effectiveness of the digital test scenario library in covering actual demand scenarios; Evaluation of the combination of test timeliness and actual calibration parameters. The combined advantages of speed in quantitative digital testing and the real-time performance of the model; Evaluation of the combination of test timeliness and numerical verification parameters. ; Evaluate the ability of digital testing to maintain the credibility of results during rapid iteration.

5. The multi-dimensional evaluation method for data-real fusion testing according to claim 2, characterized in that, The weight adjustment mechanism in step 1.4 includes: When testing focuses on accuracy verification, automatically improve The weighting coefficients are adjusted by a certain margin. =0.1×(1- ); When testing focuses on scene coverage, automatically improve The weighting coefficients are adjusted by a certain margin. =0.1×(1- ); When testing focuses on testing efficiency, automatically improve The weighting coefficients are adjusted by a certain margin. =0.1×(1- ); After each adjustment , , Perform normalization processing to ensure .

6. The multi-dimensional evaluation method for data-real fusion testing according to claim 3, characterized in that, The weight adjustment mechanism in step 2.3 includes: When the test focuses on convergence capability, automatically increase The weighting coefficients are adjusted by a certain margin. =0.1×(1- ); When testing focuses on generalization ability, automatically improve The weighting coefficients are adjusted by a certain margin. =0.1×(1- ); After each adjustment , Perform normalization processing to ensure .

7. The multi-dimensional evaluation method for data-real fusion testing according to claim 4, characterized in that, The determination mechanism for the sub-item evaluation in step 3.2 includes: Step 3.2.1, establish a judgment mechanism for sub-item evaluation: when and The absolute value of the difference exceeds When the test is deemed to have a scenario adaptability defect, the following is determined: The scenario adaptability threshold for the accuracy of test results; when and The ratio is lower than When this occurs, a scenario library expansion warning is triggered, indicating insufficient scenario coverage during testing. A capacity threshold for testing scenario coverage; like Value greater than Value At that time, it was identified as excessively sacrificing accuracy for testing efficiency optimization, among which... The over-optimization threshold for testing timeliness; Step 3.2.2: Construct a visual analysis interface: Use a hexagonal radar chart to simultaneously display the evaluation results of the six sub-items; Step 3.2.3: Generate intelligent optimization suggestion report: automatically identify the lowest-ranked item among the six sub-evaluations and provide feedback suggestions.

8. A multi-dimensional evaluation device for data-real fusion testing, characterized in that, Includes the following modules: The 3D evaluation acquisition module obtains the accuracy of data from the data-real fusion test. Scenario coverage of data-real fusion testing Timeliness of data-real fusion testing Generate static reliability evaluation values ; The closed-loop verification acquisition module uses measured data from physical equipment to verify the model parameters of the digital model, thereby obtaining the credibility of the physical equipment in verifying the digital model and calculating the actual calibration parameters. ; The digital model generates test results in a specific scenario and verifies them with the test results of the physical equipment to obtain the credibility of the digital model in verifying the physical equipment, and calculates the digital verification parameters. Generate dynamic credibility evaluation values ; The comprehensive evaluation acquisition module generates static reliable evaluation values ​​from the three-dimensional evaluation acquisition module. The dynamic trustworthy evaluation value generated by the closed-loop verification module. Calculate the overall credibility evaluation Six sub-evaluations are generated, along with corresponding judgment mechanisms.

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 program, it implements the steps of the multi-dimensional evaluation method for data-real fusion testing as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the multidimensional evaluation method for data-real fusion testing as described in any one of claims 1 to 7.

Images