Evaluation method and device of vehicle intelligent driving algorithm and related equipment

Abstract

The invention discloses an evaluation method and device for a vehicle intelligent driving algorithm and related equipment, and relates to the technical field of vehicles. The method comprises the steps that driving data and environment information of a vehicle based on an intelligent driving algorithm are acquired, the driving data and the environment information comprise numerical values of all third-level indexes in a preset evaluation index system, and the evaluation index system comprises at least one third-level index; the numerical value of each third-level index is compared with the target value of each third-level index, the score of each third-level index is determined, and under the condition that the numerical value of each third-level index is in the target value association interval, the score of each third-level index and the difference between the target value and the numerical value of each third-level index are in an inverse proportion relation; and calculating the score of the intelligent driving algorithm according to the score of each third-level index and a preset weight coefficient of each third-level index.

Description

Technical Field

[0001] The present application belongs to the field of vehicle technology, and in particular, relates to an evaluation method, device and related equipment for a vehicle intelligent driving algorithm. Background Art

[0002] With the rapid development of science and technology, autonomous driving technology has become a research hotspot in the automotive and artificial intelligence industries. Among them, the evaluation of vehicle intelligent driving algorithms is an indispensable part of the development of autonomous driving technology. By comprehensively and objectively evaluating the performance of intelligent driving algorithms, we can promote the continuous progress and innovation of autonomous driving technology, thereby enhancing user trust and acceptance. The current evaluation method of vehicle intelligent driving algorithms has a fixed scoring resolution, but this cannot increase the scoring resolution near the critical value of the evaluation index, so it is impossible to capture the detailed information of the critical value of the evaluation index, and thus it is impossible to further enhance user trust and acceptance. Summary of the invention

[0003] The embodiments of the present application provide a method, apparatus, and related equipment for evaluating a vehicle intelligent driving algorithm, which can amplify the scoring resolution near a first score.

[0004] In a first aspect, an embodiment of the present application provides a method for evaluating a vehicle intelligent driving algorithm, the method comprising:

[0005] Acquiring driving data and environmental information of the vehicle based on the intelligent driving algorithm, wherein the driving data and environmental information include values ​​of each three-level indicator in a preset evaluation indicator system, wherein the evaluation indicator system includes at least one of the three-level indicators;

[0006] Compare the value of each of the three-level indicators with the target value of each of the three-level indicators to determine the score of each of the three-level indicators, wherein, when the value of the three-level indicator is within the target value associated interval, the score of the three-level indicator is inversely proportional to the difference between the target value and the value of the three-level indicator;

[0007] The score of the intelligent driving algorithm is calculated based on the scores of each of the three-level indicators and the preset weight coefficients of each of the three-level indicators.

[0008] In a second aspect, an embodiment of the present application provides a device for evaluating a vehicle intelligent driving algorithm, the device comprising:

[0009] An acquisition module, used to acquire driving data and environmental information of the vehicle based on the intelligent driving algorithm, wherein the driving data and environmental information include values ​​of each three-level indicator in a preset evaluation index system, wherein the evaluation index system includes at least one of the three-level indicators;

[0010] A determination module, used for comparing the value of each of the three-level indicators with the target value of each of the three-level indicators, and determining the score of each of the three-level indicators, wherein, when the value of the three-level indicator is within the target value associated interval, the score of the three-level indicator and the difference between the target value and the value of the three-level indicator are in inverse proportion;

[0011] The first calculation module is used to calculate the score of the intelligent driving algorithm according to the scores of each of the three-level indicators and the preset weight coefficients of each of the three-level indicators.

[0012] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, it implements the evaluation method of the vehicle intelligent driving algorithm as described in any one of the above.

[0013] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, a method for evaluating a vehicle intelligent driving algorithm as described in any one of the above items is implemented.

[0014] In a fifth aspect, an embodiment of the present application provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the evaluation method of the vehicle intelligent driving algorithm as described in any one of the above.

[0015] In a sixth aspect, an embodiment of the present application provides a vehicle, comprising at least one of the following:

[0016] An evaluation device for a vehicle intelligent driving algorithm as described above;

[0017] Electronic devices as described above;

[0018] The computer readable storage medium as described above;

[0019] A computer program product as described above.

[0020] The evaluation method, device and related equipment of the vehicle intelligent driving algorithm of the embodiment of the present application can compare the driving data and environmental information of the vehicle based on the intelligent driving algorithm with the target value of each three-level indicator in the evaluation index system, and determine the score of each three-level indicator, wherein, when the value of the three-level indicator is in the target value associated interval, the score of the three-level indicator and the difference between the target value and the value of the three-level indicator are inversely proportional, and the evaluation index system includes at least one three-level indicator; finally, according to the score of each three-level indicator and the preset weight coefficient of each three-level indicator, the score of the intelligent driving algorithm is calculated. In this way, in the embodiment of the present application, since the score of the three-level indicator and the difference between the target value and the value of the three-level indicator are inversely proportional, not only when the value of the three-level indicator is closer to the target value, the corresponding score is larger, and when the value of the three-level indicator is farther away from the target value, the corresponding score is smaller, and as the value of the three-level indicator gradually approaches the target value, the change rate of its corresponding score also becomes larger, which can amplify the score resolution near the target value, so that the detailed information of the three-level indicator can be captured, thereby enhancing the user's trust and acceptance. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0022] Figure 1 It is a flowchart of a method for evaluating a vehicle intelligent driving algorithm provided in an embodiment of the present application;

[0023] Figure 2 is a flow chart of the scoring mechanism provided in the embodiment of the present application;

[0024] Figure 3 It is a weighted flowchart of the analytic hierarchy process provided in the embodiment of the present application;

[0025] Figure 4 It is the overall empowerment flow chart provided in the embodiment of the present application;

[0026] Figure 5 It is a structural schematic diagram of an evaluation device for a vehicle intelligent driving algorithm provided in an embodiment of the present application;

[0027] Figure 6 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0029] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0030] With the rapid development of science and technology, autonomous driving technology has become a research hotspot in the automotive and artificial intelligence industries. Among them, the evaluation of vehicle intelligent driving algorithms is an indispensable part of the development of autonomous driving technology. By comprehensively and objectively evaluating the performance of intelligent driving algorithms, we can promote the continuous progress and innovation of autonomous driving technology, thereby enhancing user trust and acceptance. The current evaluation method of vehicle intelligent driving algorithms has a fixed scoring resolution, but this cannot increase the scoring resolution near the critical value of the evaluation index, so it is impossible to capture the detailed information of the critical value of the evaluation index, and thus it is impossible to further enhance user trust and acceptance.

[0031] In order to solve the problems of the prior art, the embodiments of the present application provide a method, device and related equipment for evaluating a vehicle intelligent driving algorithm. The following first introduces the method for evaluating a vehicle intelligent driving algorithm provided by the embodiments of the present application.

[0032] Figure 1 FIG. 1 is a flow chart showing a method for evaluating a vehicle intelligent driving algorithm provided by an embodiment of the present application. Figure 1 As shown, a method for evaluating a vehicle intelligent driving algorithm may include the following steps S101 to S104:

[0033] S101, obtaining driving data and environmental information of a vehicle based on an intelligent driving algorithm, where the driving data and environmental information include values ​​of each three-level indicator in a preset evaluation indicator system, where the evaluation indicator system includes at least one three-level indicator;

[0034] S102, comparing the value of each third-level indicator with the target value of each third-level indicator in the evaluation indicator system, and determining the score of each third-level indicator, wherein, when the value of the third-level indicator is within the target value associated interval, the score of the third-level indicator and the difference between the target value and the value of the third-level indicator are in inverse proportion;

[0035] S103. Calculate the score of the intelligent driving algorithm according to the scores of each of the three-level indicators and the preset weight coefficients of each of the three-level indicators.

[0036] The evaluation method of the vehicle intelligent driving algorithm of the embodiment of the present application can compare the driving data and environmental information of the vehicle based on the intelligent driving algorithm with the target value of each three-level indicator in the evaluation index system, and determine the score of each three-level indicator, wherein, when the value of the three-level indicator is in the target value associated interval, the score of the three-level indicator and the difference between the target value and the value of the three-level indicator are inversely proportional, and the evaluation index system includes at least one three-level indicator; finally, according to the score of each three-level indicator and the preset weight coefficient of each three-level indicator, the score of the intelligent driving algorithm is calculated. In this way, in the embodiment of the present application, since the score of the three-level indicator and the difference between the target value and the value of the three-level indicator are inversely proportional, not only when the value of the three-level indicator is closer to the target value, the corresponding score is larger, and when the value of the three-level indicator is farther away from the target value, the corresponding score is smaller, and as the value of the three-level indicator is closer to the target value, the rate of change of its corresponding score also becomes larger, which can amplify the score resolution near the target value, so that the detailed information of the three-level indicator can be captured, thereby enhancing the user's trust and acceptance.

[0037] In S101, the driving data is data of driving a vehicle based on an intelligent driving algorithm. The environmental information is information of the environment when the vehicle is driving based on the intelligent driving algorithm. The driving data and environmental information may include values ​​of the three-level indicators in a preset evaluation index system.

[0038] The above-mentioned evaluation index system includes at least one three-level index, which can be, for example, collision risk probability, following vehicle speed deviation, lateral distance of the near-side lane line, emergency braking, average speed, etc. In the embodiment of the present application, the three-level index is not limited to this, but can also be other indicators, which are not specifically limited here.

[0039] In S102, the numerical value of each third-level indicator is compared with the target value of each third-level indicator to determine the score of each third-level indicator. Exemplarily, the score of each third-level indicator can be determined based on the mapping relationship corresponding to the indicator type of each third-level indicator, according to the numerical value of each third-level indicator and the target value, the first multiple value and the second multiple value of each third-level indicator; or, the score of each third-level indicator can be obtained by linear mapping according to the gap between the numerical value of each third-level indicator and the target value of each third-level indicator.

[0040] When the value of the third-level indicator is in the target value associated interval, the score of the third-level indicator and the difference between the target value and the value of the third-level indicator are in inverse proportion, wherein, when the indicator type of the third-level indicator is a positive type, the target value associated interval is an interval in which the value of the third-level indicator is greater than or equal to the product of the target value of the third-level indicator and the first multiple value, and is less than the target value of the third-level indicator; when the indicator type of the third-level indicator is a negative type, the target value associated interval is an interval in which the value of the third-level indicator is greater than or equal to the target value of the third-level indicator, and is less than the product of the target value of the third-level indicator and the second multiple value; when the indicator type of the third-level indicator is an interval type, the target value associated interval is an interval in which the value of the third-level indicator is greater than or equal to the first value and less than the target value of the third-level indicator, and an interval in which the value of the third-level indicator is greater than or equal to the target value of the third-level indicator and is less than or equal to the second value.

[0041] In S103, the score of the intelligent driving algorithm is calculated based on the scores of each third-level indicator and the preset weight coefficient of each third-level indicator. For example, the scores of each second-level indicator can be calculated based on the scores of at least one third-level indicator in each second-level indicator and the weight coefficient of each second-level indicator; the scores of each first-level indicator are calculated based on the scores of at least one second-level indicator in each first-level indicator; the scores of at least one first-level indicator are multiplied by the preset weight coefficient of each first-level indicator, and the sum is calculated to obtain the score of the intelligent driving algorithm. Alternatively, the scores of each third-level indicator can be multiplied by the weight coefficients preset by humans for each third-level indicator, and the sum is calculated to obtain the score of the intelligent driving algorithm.

[0042] In some embodiments, the evaluation index system further includes index parameters of each third-level index, the index parameters include the index type and the first multiple value and the second multiple value of the target value, the first multiple value is less than the second multiple value, and the index type includes a positive type, a negative type and an interval type;

[0043] The above S102 may specifically include:

[0044] Based on the mapping relationship corresponding to the indicator type of each third-level indicator, the score of each third-level indicator is determined according to the value of each third-level indicator and the target value, first multiple value and second multiple value of each third-level indicator. Different indicator types correspond to different mapping relationships.

[0045] The above-mentioned indicator types include positive type, negative type and interval type. Among them, the larger the value of the positive type indicator, the higher the score; the larger the value of the negative type indicator, the lower the score; the closer the value of the interval type indicator is to the optimal value in the preset interval, the higher the score; if it exceeds the multiple range of this optimal value, the score is the lowest score.

[0046] Based on the mapping relationship corresponding to the indicator type of each third-level indicator, the score of each third-level indicator is determined according to the value of each third-level indicator and the target value, the first multiple value and the second multiple value of each third-level indicator. Different indicator types correspond to different mapping relationships, which may include: when the indicator type of the third-level indicator is a positive type, when the value of the third-level indicator is less than the product of the target value of the third-level indicator and the first multiple value, the score of the third-level indicator is determined to be zero; when the value of the third-level indicator is greater than or equal to the product of the target value of the third-level indicator and the first multiple value, and is less than the target value of the third-level indicator, the score of the third-level indicator is determined to be zero. The score of the third-level indicator is calculated based on the target value, the objective value and the preset resolution coefficient. The score of the third-level indicator is inversely proportional to the difference between the target value and the value of the third-level indicator. When the value of the third-level indicator is greater than or equal to the target value of the third-level indicator and less than the product of the target value of the third-level indicator and the second multiple value, the score of the third-level indicator is positively correlated to the difference between the value of the third-level indicator and the target value. The score of the third-level indicator is calculated based on the value of the third-level indicator, the objective value and the second multiple value. When the value of the third-level indicator is greater than the product of the target value of the third-level indicator and the second multiple value, the score of the third-level indicator is determined to be full marks. When the indicator type of the third-level indicator is a negative type, when the value of the third-level indicator is greater than the product of the target value of the third-level indicator and the second multiple value, the score of the third-level indicator is determined to be zero; when the value of the third-level indicator is greater than or equal to the target value of the third-level indicator, and less than the product of the target value of the third-level indicator and the second multiple value, the score of the third-level indicator is calculated based on the value, target value and preset resolution coefficient of the third-level indicator, and the score of the third-level indicator is inversely proportional to the difference between the target value and the value of the third-level indicator; when the value of the third-level indicator is less than the target value of the third-level indicator, and greater than or equal to the product of the target value of the third-level indicator and the first multiple value, the score of the third-level indicator is calculated based on the value, target value and first multiple value of the third-level indicator, and the score of the third-level indicator is positively correlated to the difference between the value of the third-level indicator and the target value; when the value of the third-level indicator is less than the product of the target value of the third-level indicator and the first multiple value, the score of the third-level indicator is determined to be full marks.In the case where the indicator type of the third-level indicator is an interval type, when the value of the third-level indicator is equal to the target value of the third-level indicator, the score of the third-level indicator is determined to be full marks, and the target value of the third-level indicator is calculated by the first value and the second value of the preset interval, and the first value is less than the second value; in the case where the value of the third-level indicator is greater than or equal to the first value and less than the target value of the third-level indicator, or greater than the target value of the third-level indicator and less than or equal to the second value, the score of the third-level indicator is calculated according to the value of the third-level indicator, the target value, the first value or the second value, and the score of the third-level indicator is positively correlated with the difference between the value of the third-level indicator and the first value or the second value; in the case of When the value of the indicator is less than the first value and greater than or equal to the product of the target value of the third-level indicator and the first multiple value, or when the value of the third-level indicator is greater than the second value and less than or equal to the product of the target value of the third-level indicator and the second multiple value, the score of the third-level indicator is calculated according to the value of the third-level indicator, the preset resolution coefficient, the first value or the second value, and the score of the third-level indicator is inversely proportional to the difference between the value of the third-level indicator and the first value or the second value; when the value of the third-level indicator is less than the product of the target value of the third-level indicator and the first multiple value, or when the value of the third-level indicator is greater than the product of the target value of the third-level indicator and the second multiple value, the score of the third-level indicator is determined to be zero.

[0047] In an embodiment of the present application, different indicator types correspond to different mapping relationships. Based on the mapping relationships corresponding to the indicator types of each third-level indicator, the scores of each third-level indicator can be accurately determined according to the values ​​of each third-level indicator and the target values, first multiple values, and second multiple values ​​of each third-level indicator, thereby meeting the requirements for determining the scores of third-level indicators of different indicator types.

[0048] In some embodiments, when the indicator type of the third-level indicator is a positive type, the above-mentioned mapping relationship corresponding to the indicator type of each third-level indicator is based on the value of each third-level indicator and the target value, the first multiple value and the second multiple value of each third-level indicator to determine the score of each third-level indicator, which may specifically include:

[0049] When the value of the third-level indicator is less than the product of the target value of the third-level indicator and the first multiple value, the score of the third-level indicator is determined to be zero;

[0050] When the value of the third-level indicator is greater than or equal to the product of the target value of the third-level indicator and the first multiple value, and less than the target value of the third-level indicator, the score of the third-level indicator is calculated according to the value of the third-level indicator, the target value and the preset resolution coefficient, and the score of the third-level indicator is inversely proportional to the difference between the target value and the value of the third-level indicator;

[0051] When the value of the third-level indicator is greater than or equal to the target value of the third-level indicator, and less than the product of the target value of the third-level indicator and the second multiple value, the score of the third-level indicator is calculated based on the value of the third-level indicator, the target value and the second multiple value. The score of the third-level indicator is positively correlated with the difference between the value of the third-level indicator and the target value.

[0052] When the value of the third-level indicator is greater than the product of the target value of the third-level indicator and the second multiple value, the score of the third-level indicator is determined to be full marks.

[0053] The scores of the three-level indicators are calculated based on the values ​​of the three-level indicators, the target values ​​and the preset resolution coefficients. For example, the scores of the three-level indicators can be obtained by calculating according to the values ​​of the three-level indicators, the target values ​​and the preset resolution coefficients according to the preset formulas (1) to (5). The formulas (1) to (5) are as follows:

[0054]

[0055] Among them, ε1(j) is the correlation coefficient of the jth indicator, Δ is the calculated value of the predetermined indicator X j The maximum distance from the reference value X0, the value range of |X0(j)-X1(j)| is [0, Δ], that is, the value range of ε1 is [ρ / (1+ρ), 1], ρ is the resolution coefficient, which is between (0, 1), C0 is the target value of the above three-level indicators, C1 is the value of the three-level indicators, here we take ρ=1 / 3, that is, the value range of ε1 can be [0.25, 1], so after calculating ε1, it needs to be multiplied by 80 points, that is, [0.25*80, 1*80], so here is a 20-80 segment mapping.

[0056] The score of the third-level indicator is calculated based on the value, target value and second multiple value of the third-level indicator. For example, the score of the third-level indicator can be calculated based on the value, target value, second multiple value of the third-level indicator and formula (6). Formula (6) is as follows:

[0057]

[0058] Among them, s is the score of the third-level indicator, x is the value of the third-level indicator, xopt is the target value of the third-level indicator, and multiple[1] is the second multiple.

[0059] In the embodiment of the present application, based on the mapping relationship corresponding to the positive type, when the value of the third-level indicator is in different ranges related to the target value, the first multiple value, and the second multiple value of the third-level indicator, the corresponding score calculation method is used.

[0060] In some embodiments, when the indicator type of the third-level indicator is a negative type, the above-mentioned mapping relationship corresponding to the indicator type of each third-level indicator is based on the value of each third-level indicator and the target value, the first multiple value and the second multiple value of each third-level indicator to determine the score of each third-level indicator, which may specifically include:

[0061] When the value of the third-level indicator is greater than the product of the target value of the third-level indicator and the second multiple value, the score of the third-level indicator is determined to be zero;

[0062] When the value of the third-level indicator is greater than or equal to the target value of the third-level indicator, and less than the product of the target value of the third-level indicator and the second multiple value, the score of the third-level indicator is calculated according to the value of the third-level indicator, the target value and the preset resolution coefficient. The score of the third-level indicator is inversely proportional to the difference between the target value and the value of the third-level indicator.

[0063] When the value of the third-level indicator is less than the target value of the third-level indicator, and is greater than or equal to the product of the target value of the third-level indicator and the first multiple value, the score of the third-level indicator is calculated based on the value of the third-level indicator, the target value and the first multiple value. The score of the third-level indicator is positively correlated with the difference between the value of the third-level indicator and the target value.

[0064] When the value of the third-level indicator is less than the product of the target value of the third-level indicator and the first multiple value, the score of the third-level indicator is determined to be the full score.

[0065] The scores of the three-level indicators are calculated based on the numerical values, target values ​​and preset resolution coefficients of the three-level indicators. For example, the scores of the three-level indicators can be calculated based on the numerical values, target values ​​and preset resolution coefficients of the three-level indicators according to the above formulas (1) to (5), which will not be repeated here.

[0066] The score of the third-level indicator is calculated based on the value, target value and first multiple value of the third-level indicator. For example, the score of the third-level indicator can be calculated based on the value, target value, first multiple value of the third-level indicator and formula (7). Formula (7) is as follows:

[0067]

[0068] Among them, s is the score of the third-level indicator, x is the value of the third-level indicator, xopt is the target value of the third-level indicator, and multiple[0] is the first multiple.

[0069] In an embodiment of the present application, based on the mapping relationship corresponding to the negative type, when the numerical value of the third-level indicator is in different ranges related to the target value of the third-level indicator, the score of the third-level indicator can be accurately calculated through the score calculation method corresponding to the different ranges, thereby increasing the objectivity of the score evaluation of the third-level indicator.

[0070] In some embodiments, when the indicator type of the third-level indicator is an interval type, the above-mentioned mapping relationship corresponding to the indicator type of each third-level indicator is based on the value of each third-level indicator and the target value, the first multiple value and the second multiple value of each third-level indicator to determine the score of each third-level indicator, which may specifically include:

[0071] In the case where the value of the third-level indicator is equal to the target value of the third-level indicator, the score of the third-level indicator is determined to be full score, and the target value of the third-level indicator is calculated by the first value and the second value of the preset interval, and the first value is less than the second value;

[0072] When the value of the third-level indicator is greater than or equal to the first value and less than the target value of the third-level indicator, or greater than the target value of the third-level indicator and less than or equal to the second value, the score of the third-level indicator is calculated according to the value of the third-level indicator, the target value, the first value or the second value, and the score of the third-level indicator is positively correlated with the difference between the value of the third-level indicator and the first value or the second value;

[0073] When the value of the third-level indicator is less than the first value and greater than or equal to the product of the target value of the third-level indicator and the first multiple value, or when the value of the third-level indicator is greater than the second value and less than or equal to the product of the target value of the third-level indicator and the second multiple value, the score of the third-level indicator is calculated according to the value of the third-level indicator, the preset resolution coefficient, the first value or the second value, and the score of the third-level indicator is inversely proportional to the difference between the value of the third-level indicator and the first value or the second value;

[0074] When the value of the third-level indicator is less than the product of the target value of the third-level indicator and the first multiple value, or the value of the third-level indicator is greater than the product of the target value of the third-level indicator and the second multiple value, the score of the third-level indicator is determined to be zero.

[0075] The target value of the above-mentioned three-level indicator is calculated by the first value and the second value of the preset interval. For example, the average of the first value and the second value can be determined as the target value. The above-mentioned first value is smaller than the second value, and the first value is greater than the product of the target value of the three-level indicator and the first multiple value, and the second value is smaller than the product of the target value of the three-level indicator and the second multiple value.

[0076] In the above case where the value of the third-level indicator is greater than or equal to the first value and less than the target value of the third-level indicator, or greater than the target value of the third-level indicator and less than or equal to the second value, the score of the third-level indicator is calculated according to the value, target value, first value or second value of the third-level indicator. Exemplarily, when the value of the third-level indicator is greater than or equal to the first value and less than the target value of the third-level indicator, the score of the third-level indicator is calculated according to the value, target value and first value of the third-level indicator and formula (8). Formula (8) is as follows:

[0077]

[0078] Among them, s is the score of the third-level indicator, x is the value of the third-level indicator, xopt is the target value of the third-level indicator, and T0 is the first value.

[0079] When the value of the third-level indicator is greater than the target value of the third-level indicator and less than or equal to the second value, the score of the third-level indicator is calculated according to the value of the third-level indicator, the target value and the second value, and formula (9). Formula (9) is as follows:

[0080]

[0081] Among them, s is the score of the third-level indicator, x is the value of the third-level indicator, xopt is the target value of the third-level indicator, and T1 is the second value.

[0082] The score of the third-level indicator is calculated based on the value of the third-level indicator, the preset resolution coefficient, the first value or the second value. For example, the score of the third-level indicator can be obtained by calculating based on the value of the third-level indicator, the preset resolution coefficient, the first value or the second value according to the above formulas (1) to (5), which will not be repeated here.

[0083] In an embodiment of the present application, based on the mapping relationship corresponding to the interval type, when the numerical value of the third-level indicator is in different ranges related to the target value of the third-level indicator, the score of the third-level indicator can be accurately calculated through the score calculation method corresponding to the different ranges, thereby increasing the objectivity of the score evaluation of the third-level indicator.

[0084] As an implementation of the present application, in order to ensure the accuracy and reliability of the scoring, before the above S103, the above method may further include:

[0085] According to the scores of each third-level indicator, the weight coefficient of each third-level indicator is calculated, and the weight coefficient of the third-level indicator is positively correlated with the first score distance, and the first score distance is the distance between the score of the third-level indicator and the preset first score;

[0086] The above S103 may specifically include:

[0087] The score of the intelligent driving algorithm is calculated based on the scores of each third-level indicator and the weight coefficient of each third-level indicator.

[0088] The first score distance is the distance between the score of the third-level indicator and the preset first score. The first score, for example, can be 80 points. This application is an embodiment and is not limited thereto. It can also be other values, which are not specifically limited here. The weight coefficient of the third-level indicator is positively correlated with the first score distance.

[0089] The weight coefficient of each third-level indicator is calculated according to the score of each third-level indicator. For example, the weight coefficient of each third-level indicator can be obtained by calculating according to the first score distance between the score of each third-level indicator and the preset first score according to the following formulas (10) and (11). Formula (10) is as follows:

[0090]

[0091] Among them, out j (x) is the value calculated by the inverse Gaussian weight for the jth third-level indicator, and all the third-level indicators under the second-level indicators under the first-level indicator are calculated out. j (x), normalized out j (x) Calculate the weight coefficient of the corresponding three-level indicators:

[0092]

[0093] s j (x) is the weight coefficient of the jth third-level indicator under a certain second-level indicator, d(x,x i ) represents the first score distance between the score of the third-level indicator x and the preset first score x0, and σ is the standard deviation of the Gaussian function, which controls the rate at which the weight changes with distance.

[0094] In an embodiment of the present application, the weight coefficient of each third-level indicator is calculated by the score of each third-level indicator. Since the weight coefficient of the third-level indicator is positively correlated with the distance from the first score, the farther the score of the third-level indicator is from the first score, the larger the weight coefficient of the corresponding third-level indicator, thereby amplifying the influence of the third-level indicator whose score is far away from the first score, thereby ensuring the accuracy and reliability of the scoring of the intelligent driving algorithm.

[0095] In some embodiments, the evaluation index system includes at least one primary index, the primary index includes at least one secondary index, and the secondary index includes at least one tertiary index;

[0096] The score of the intelligent driving algorithm is calculated based on the scores of each of the three-level indicators and the weight coefficients of each of the three-level indicators, which may specifically include:

[0097] The scores of each secondary indicator are calculated based on the score of at least one third-level indicator in each secondary indicator and the weight coefficient of each third-level indicator;

[0098] The scores of each first-level indicator are calculated based on the score of at least one second-level indicator in each first-level indicator and the preset weight coefficient of each second-level indicator;

[0099] Multiply the score of at least one first-level indicator by the preset weight coefficient of each first-level indicator, and sum them up to obtain the score of the intelligent driving algorithm.

[0100] The at least one first-level indicator may be safety, functionality, comfort and efficiency. The first-level efficiency indicator may include second-level indicators of driving and parking, and the second-level driving indicator may include a third-level indicator of average speed. In the embodiments of the present application, it is not limited to this, and only specific examples are given here.

[0101] The scores of each secondary indicator are calculated based on the scores of at least one tertiary indicator in each secondary indicator and the weight coefficients of each tertiary indicator. Exemplarily, the scores of at least one tertiary indicator in each secondary indicator may be multiplied by the weight coefficients of each tertiary indicator, and the initial scores of each secondary indicator are summed up; when there is no score of at least one tertiary indicator of the secondary indicator that is less than a preset score threshold, the initial score of each secondary indicator is determined as the score of the secondary indicator; when there is a score of at least one tertiary indicator of the secondary indicator that is less than a preset score threshold, the product of the initial score of the secondary indicator and the preset adjustment coefficient is determined as the score of the secondary indicator.

[0102] The scores of the first-level indicators are calculated based on the scores of at least one second-level indicator in each first-level indicator and the preset weight coefficients of each second-level indicator. For example, the weight coefficients of the second-level indicators are calculated based on the scores of the second-level indicators. The weight coefficients of the second-level indicators are positively correlated with the second score distance. The second score distance is the distance between the score of the second-level indicator and the preset second score. The scores of the first-level indicators are calculated based on the scores and weight coefficients of at least one second-level indicator in each first-level indicator. Alternatively, the scores of the first-level indicators can be obtained by multiplying the scores of at least one second-level indicator in each first-level indicator by the preset weight coefficients and summing them.

[0103] In an embodiment of the present application, the evaluation index system may include at least one first-level indicator, the first-level indicator includes at least one second-level indicator, and the second-level indicator includes at least one tertiary indicator. By calculating the second-level indicator scores and the first-level indicator scores layer by layer, the specific performance of the intelligent driving algorithm at each level can be displayed to the user, thereby improving the readability of the intelligent driving algorithm evaluation.

[0104] In some embodiments, the scores of the secondary indicators are calculated based on the scores of at least one tertiary indicator in each secondary indicator and the weight coefficients of the tertiary indicators, and specifically may include:

[0105] Multiply the score of at least one third-level indicator in each second-level indicator by the weight coefficient of each third-level indicator, and sum them up to obtain the initial score of each second-level indicator;

[0106] In the case where the score of at least one of the third-level indicators of the second-level indicator is less than the preset score threshold, the product of the initial score of the second-level indicator and the preset adjustment coefficient is determined as the score of the second-level indicator;

[0107] The scores of each first-level indicator are calculated based on the score of at least one second-level indicator in each first-level indicator and the preset weight coefficient of each second-level indicator, including:

[0108] According to the scores of each secondary indicator, the weight coefficient of each secondary indicator is calculated. The weight coefficient of the secondary indicator is positively correlated with the second score distance. The second score distance is the distance between the score of the secondary indicator and the preset second score.

[0109] Multiply the score of at least one secondary indicator in each primary indicator by the weight coefficient of each secondary indicator, and sum them up to obtain the initial score of each primary indicator;

[0110] The product of the initial score of the first-level indicator and the adjustment coefficient is determined as the score of the first-level indicator.

[0111] The adjustment coefficient is a value between 0 and 1, and illustratively, may be 0.8 or 0.9.

[0112] The above-mentioned preset score threshold can be 80 points. In the embodiment of the present application, it is not limited to this value and can be set according to the actual needs of the user. No specific limitation is made here.

[0113] The weight coefficient of each secondary indicator is calculated according to the score of each secondary indicator. For example, the score of each secondary indicator can be calculated according to the above formulas (10) and (11) to obtain the weight coefficient of each secondary indicator.

[0114] The above-mentioned second score, illustratively, can be 80 points. The present application is an embodiment and is not limited thereto. It can also be other values ​​and is not specifically limited here.

[0115] In the embodiment of the present application, when there is a score of at least one of the third-level indicators of the secondary indicator that is less than the preset score threshold, the product of the initial score of the secondary indicator and the preset adjustment coefficient is determined as the score of the secondary indicator, which can avoid the situation where the indicator items that perform poorly are overwhelmed because some indicator items perform too well, resulting in a higher reported score, thereby improving the accuracy of the secondary indicator score; correspondingly, when calculating the primary indicator based on the adjusted secondary indicator, the product of the initial score of the primary indicator and the adjustment coefficient is also determined as the score of the primary indicator to improve the accuracy of the primary indicator score. In addition, since the weight coefficient of the secondary indicator is positively correlated with the distance from the second score, the farther the score of the secondary indicator is from the second score, the larger the weight coefficient of the corresponding secondary indicator is, thereby amplifying the influence of the secondary indicator whose score is far away from the second score, further ensuring the accuracy and reliability of the first-level indicator score.

[0116] In some embodiments, the above indicator parameters may also include indicator priorities, and different indicator priorities correspond to different adjustment coefficients;

[0117] When the score of at least one of the third-level indicators of the second-level indicator is less than the preset score threshold, the product of the initial score of the second-level indicator and the preset adjustment coefficient is determined as the score of the second-level indicator, including:

[0118] In the case where the score of at least one third-level indicator among the second-level indicators is less than a preset score threshold, the third-level indicator less than the preset score threshold is determined as the target third-level indicator;

[0119] The score of the secondary indicator is determined as the product of the initial score of the secondary indicator and the adjustment coefficient corresponding to the indicator priority of the target third-level indicator.

[0120] The above indicator priority can take the values ​​of "0" and "1". Different indicator priorities correspond to different adjustment coefficients. For example, if the indicator priority = 0, it means that the indicator is important. When the score of the indicator is lower than 80, in order to ensure the consistency of the evaluation, the final score of the algorithm will be multiplied by the adjustment coefficient of 0.8 for adjustment; if the indicator priority = 1, it means that the indicator is relatively important. When the score of the indicator is lower than 80, the final score of the algorithm will be multiplied by the adjustment coefficient of 0.9 for correction to ensure the accuracy and reliability of the scoring results.

[0121] In the embodiment of the present application, since the indicator priorities of the target third-level indicators that are less than the preset score threshold are different, different adjustment coefficients will result. Therefore, the product of the initial score of the secondary indicator and the adjustment coefficient corresponding to the indicator priority of the target third-level indicator is determined as the score of the secondary indicator, which can meet the adjustment needs of different indicator priorities, thereby ensuring the accuracy and reliability of the scoring results.

[0122] As another implementation of the present application, in order to improve the objectivity of the weight coefficient of the primary indicator, before multiplying the score of at least one primary indicator by the preset weight coefficient of each primary indicator and summing them to obtain the score of the intelligent driving algorithm, the method may further include:

[0123] Obtaining an importance scale obtained by at least one user scoring at least one primary indicator;

[0124] Based on at least one importance scale, a judgment matrix is ​​constructed;

[0125] The judgment matrix is ​​calculated to obtain the preset weight coefficients of each first-level indicator.

[0126] The importance scale obtained by at least one user scoring at least one primary indicator may, for example, be an importance scale obtained by at least one expert user comparing the importance of n primary indicators pairwise.

[0127] The judgment matrix constructed based on at least one importance scale may be:

[0128] Judgment Matrix Security Comfort Efficiency Functional Security 1 7 8 5 Comfort 1 / 7 1 2 1 / 2 Efficiency 1 / 8 1 / 2 1 1 / 3 Functional 1 / 5 2 3 1

[0129] The above calculation of the judgment matrix obtains the preset weight coefficients of each first-level indicator. For example, the weight coefficient of the first-level safety indicator is 0.63704698, the weight coefficient of the first-level comfort indicator is 0.1040204, the weight coefficient of the first-level efficiency indicator is 0.06277271, and the weight coefficient of the first-level functionality indicator is 0.19616.

[0130] In the embodiment of the present application, since each user scales the importance of at least one first-level indicator with subjective factors, a judgment matrix is ​​constructed by obtaining the importance scale obtained by at least one user scoring at least one first-level indicator, and the judgment matrix is ​​calculated to obtain the preset weight coefficient of each first-level indicator. This can reduce the influence of each user's subjective importance scaling of the first-level indicators, thereby improving the objectivity of the weight coefficient of the first-level indicator.

[0131] In order to facilitate the understanding of the evaluation method of the vehicle intelligent driving algorithm in the embodiment of the present application, the actual application process of the evaluation method of the vehicle intelligent driving algorithm is described as follows:

[0132] 1Indicator system

[0133] In order to describe the evaluation method of the autonomous driving algorithm (i.e. the above-mentioned intelligent driving algorithm) more completely and meticulously, a hierarchical evaluation index system for autonomous driving evaluation (i.e. the above-mentioned evaluation index system) is proposed. The evaluation system is divided into three layers: the first-level index layer, the second-level index layer, and the third-level index layer. For details, see Table 1.

[0134] Table 1:

[0135]

[0136]

[0137] 2 Scoring Model

[0138] All indicators have expected values, that is, optimal values. Here, when the algorithm achieves an indicator that just meets the expected value, the score is 80 points. If it is better than the expected value, the score will be higher, up to 100 points. If it is worse than the expected value, the score will be lower, up to 0 points. We set two scores as the dividing line between valuable evaluation and worthless evaluation.

[0139] According to the above information, the indicator system is divided into three layers. The third layer of indicators is the most basic indicator, and the scoring is calculated from the third layer of indicators. The indicators can be roughly classified and parameters can be set, such as priority. There is no need to strictly classify the indicators, but only to make a rough distinction between the indicators, which is highly executable. Autonomous driving indicators have different positive and negative types. Only by distinguishing between positive and negative can we better judge the trend. Here, the parameter kind represents the setting of the positive and negative nature of the indicator. At the same time, when the actual calculation result of a certain indicator is very poor and has no further calculation and evaluation value, it can be directly given 0 points. Similarly, the actual calculation result of the indicator is very good and there is no need for further evaluation. All can be attributed to 100 points. The specific scoring boundary scoring model requires some basic parameters. The parameters are shown in Table 2 below:

[0140] Table 2:

[0141]

[0142] Among them, "priority" represents the priority of the three-level indicators, and its value is "0" and "1". If priority = 0, it means that the indicator is very important. When the score of the indicator is lower than 80, in order to ensure the consistency of the evaluation, the final score of the algorithm will be adjusted by multiplying the consistency coefficient (i.e. the above adjustment coefficient) 0.8; if priority = 1, it means that the indicator is generally important. When the score of the indicator is lower than 80, the final score of the algorithm will be multiplied by the consistency coefficient 0.9 for correction to ensure the accuracy and reliability of the scoring results.

[0143] "kind" is the positive or negative nature of the three-level indicator, and its value range is "1", "-1" and "0". Specifically, if kind = 1, it means that the indicator is a positive indicator (i.e. the positive type mentioned above), that is, the larger the indicator value, the higher the score; if kind = -1, it means that the indicator is a negative indicator (i.e. the negative type mentioned above), that is, the larger the indicator value, the lower the score; if kind = 0, it means that the indicator is an interval indicator (i.e. the interval type mentioned above), and its scoring mechanism is: the closer the indicator value is to the set optimal value interval, the higher the score, and if it exceeds this interval, the score is the lowest score.

[0144] "Optimal" is the benchmark value of the third-level indicator (i.e. the target value mentioned above). For positive and negative indicators, it represents the required value of the design indicator. If the actual value does not meet this benchmark, the score will be lower than 80 points. For interval indicators, "optimal" represents the optimal value. The closer the actual value is to this optimal value, the closer the score is to the full score of 100 points.

[0145] "Multiple" is the multiple of the benchmark value of the third-level indicator, which usually contains two key parameters [x, y]. [x, y] is calculated by dividing the reasonable interval range by "optimal". Taking the reasonable interval [min, max] as an example, [x, y] can be called a reasonable range. Among them, x represents the ratio of the minimum value min to the benchmark value optimal, that is, x = min / optimal; and y represents the ratio of the maximum value max to the benchmark value optimal, that is, y = max / optimal.

[0146] like Figure 2 As shown, the scoring process may specifically include:

[0147] (1) First determine the indicator type and proceed to the next step based on the type:

[0148] (2) Then, determine the relationship between the actual calculated value of the indicator (i.e., the value of the above-mentioned third-level indicator) and the optimal score range of the designed value of the indicator. ① For positive indicators, if the actual calculated value of the indicator < optimal * multiple[0] (i.e., the above-mentioned first multiple), that is, the actual calculated value of the indicator is much smaller than the optimal value, directly give it 0 points. If the actual calculated value of the indicator > optimal * multiple[1] (i.e., the above-mentioned second multiple), that is, the actual calculated value of the indicator is much larger than the optimal value, directly give it 100 points (i.e., the above-mentioned full score). If the actual calculated value of the indicator is between optimal * multiple[0] and optimal, then score it between 20 - 80 points. If the actual calculated value of the indicator is between optimal and optimal * multiple[1], then score it between 80 - 100 points. ② For negative indicators, if the actual calculated value of the indicator < optimal * multiple[0], that is, the actual calculated value of the indicator is much smaller than the optimal value, directly give it 100 points. If the actual calculated value of the indicator > optimal * multiple[1], that is, the actual calculated value of the indicator is much smaller than the optimal value, directly give it 0 points. If the actual calculated value of the indicator is between optimal * multiple[0] and optimal, then score it between 80 - 100 points. If the actual calculated value of the indicator > optimal * multiple[1], that is, the actual calculated value of the indicator is much larger than the optimal value, directly give it 0 points. If the actual calculated value of the indicator is between optimal and optimal * multiple[1], then score it between 20 - 80 points. ③ For interval indicators, the indicator is qualified within the reasonable interval. The reasonable interval range is [T0, T1]. The expected value optimal, that is, the optimal value, is calculated within the reasonable interval through the left value and right value of the interval (i.e., the above-mentioned first value and second value). When the actual calculated value of the indicator < optimal * multiple[0] or the actual calculated value of the indicator > optimal * multiple[1], that is, the actual calculated value of the indicator is much smaller than the optimal value, directly give it 0 points. If the actual calculated value of the indicator is between T0 and optimal or between optimal and T1, then score it between 80 - 100 points. If the actual calculated value of the indicator is between optimal * multiple[0] and T0, or between T1 and optimal * multiple[1], then score it between 20 - 80 points.

[0149] (3) Scoring interpolation steps, which are divided into three cases

[0150] 1) Case 1: 80 - 100 linear mapping

[0151] ① If the indicator is a positive indicator, the actual calculated value of the indicator is greater than optimal and less than optimal*multiple[1], that is, the actual calculated value of the indicator is better than the optimal value but not far better than the optimal value.

[0152]

[0153] ② If the indicator is negative, the actual calculated value of the indicator is less than optimal and greater than optimal*multiple[0], that is, the actual calculated value of the indicator is better than the optimal value but not far better than the optimal value.

[0154]

[0155] ③ If the indicator is interval type, when the actual calculation of the indicator is greater than T0 and less than optimal

[0156]

[0157] The actual calculated value of the indicator is greater than optimal and less than T1, that is, the actual calculated value of the indicator

[0158]

[0159] 2) Case 2: 20-80 mapping

[0160] Determine the reference sequence C0. The reference sequence value is composed of the optimal values ​​of each indicator. Here, the single case standard value is set to C1, and the optimal value is C0. The next step is to perform dimensionless processing. Use the mean method to perform dimensionless processing on each indicator.

[0161]

[0162] After dimensionless processing, the correlation coefficient between the comparison sequence value and the reference value can be calculated.

[0163] The correlation coefficient calculation formula is:

[0164]

[0165] Among them, Δ is the maximum distance between the calculated value of the predetermined indicator and the reference value, ε1(j) is the correlation coefficient of the jth indicator in the single case, the value range of |X0(j)-X1(j)| is [0, Δ], that is, the value range of ε1 is [ρ / (1+ρ), 1], ρ is the resolution coefficient, which is between (0, 1). In the embodiment of the present application, ρ=1 / 3 can be taken as an example, that is, the value range of ε1 is [0.25, 1]. Because this model is a 20-80 segment mapping, after calculating ε1, it needs to be multiplied by 80 points, that is, [0.25*80, 1*80]. In the interval indicator, Δ represents the maximum distance between the calculated value and T0 when the calculated value of the indicator is less than T0, or the maximum distance between the calculated value and T1 when the calculated value is greater than T1.

[0166] (4) After steps (2) and (3), the third-level indicators are scored in percentage. The second-level scores are inferred in reverse order, and the third-level indicators need to be weighted. Weight assignment is generally done by experts. The algorithm evaluation report should highlight the indicators with poor performance. When the key indicator scores are low, the parent indicator to which the indicator belongs should be lowered. The weight of the third-level indicator itself uses inverse distance Gaussian weighting, which is an advanced spatial interpolation weighting method. This method attempts to improve on the traditional inverse distance weighting (IDW) by introducing a Gaussian function to optimize the weight distribution. In this method, the weight of the observation point far away from the estimated point will increase rapidly as the distance increases.

[0167]

[0168] Among them, out j (x) is the value calculated by the inverse Gaussian weight for the jth third-level indicator, and all the third-level indicators under the second-level indicators under the first-level indicator are calculated out. j (x), normalized out j (x) Calculate the weights of the corresponding three-level indicators:

[0169]

[0170] s j (x) is the weight of the jth third-level indicator under a second-level indicator, d(x,x i ) represents the distance between the third-level indicator score x and the known expected point x0 (here 80 points), and σ is the standard deviation of the Gaussian function, which controls the rate at which the weight changes with distance. After the introduction of the inverse Gaussian function, the weight increases faster with increasing distance, which can to a certain extent avoid the small impact of distant points on local estimates, making the results more accurately reflect better or worse information. This method is particularly suitable for spatial data interpolation that requires a high degree of attention to local characteristics.

[0171] Therefore, the initial score γ of the secondary index is:

[0172] γ init =∑s j ε1(j)

[0173] The corresponding total score of the secondary indicator needs to be adjusted by multiplying it by the consistency coefficient. The consistency coefficient is related to the priority of the corresponding third-level indicator with a score less than 80. If the priority is 0, the adjustment coefficient is 0.8, and if the priority is 1, the adjustment coefficient is 0.9. The final score of the secondary indicator γ out for:

[0174] γ out =γ init , any ε1(j)≥80

[0175] γ out =τ×γ init , there exists at least one ε1(j)<80

[0176] If at least one indicator with a score less than 80 has a priority of 0, then τ is 0.8; if all indicators with a score less than 80 have a priority of 1, then τ is 0.9.

[0177] (5) Calculation of first-level indicator scores

[0178] After obtaining the secondary scores, it is necessary to calculate the secondary weights and obtain the corresponding primary indicator scores. The secondary indicator weights still use the inverse distance Gaussian weighting. Similarly, when calculating the primary indicator scores, it is necessary to determine whether there are any indicator items with a score less than 80 points among the third-level indicators under all the second-level indicators. If at least one second-level indicator is less than 80 points, the corresponding total score of the first-level indicator needs to be multiplied by the consistency coefficient for adjustment. The consistency coefficient is related to the priority of the corresponding third-level indicator with a score less than 80 points. If the priority is 0, the adjustment coefficient is 0.8, and if the priority is 1, the adjustment coefficient is 0.9. This can avoid the situation where some indicator items perform too well and the unqualified indicator items are submerged, resulting in a higher reported score. Items that need to be optimized by the omitting algorithm.

[0179] The initial scores of the first-level indicators are:

[0180] sco init =∑s j γ(j)

[0181] sco=sco init , any ε1(j)≥80

[0182] sco=τ×sco init , there exists at least one ε1(j)<80

[0183] (6) Overall score calculation

[0184] According to step (5), the score of each first-level indicator will be calculated. The overall score needs to consider the weight calculation of the first-level indicators. The weight calculation of the first-level indicators adopts the Analytic Hierarchy Process (AHP), which is a method of decomposing complex problems into multiple levels and factors, and then determining the importance of each factor relative to the overall goal through expert judgment and experience evaluation, so as to obtain the final decision result. Its basic principle is to decompose the problem into relevant factors when analyzing a phenomenon or problem, and form a multi-level structural model according to the relationship between them. Then, through experience or expert judgment, determine the degree of influence of each factor on the overall goal, and rank the weights to obtain the final decision result.

[0185] The specific process of AHP is as follows: Figure 3 As shown, it includes four steps, namely:

[0186] Step 1: Scale determination and construction of judgment matrix;

[0187] This step is the source of the original data (judgment matrix). For example, this article uses a 1-10 point scale (the lowest is 1 point and the highest is 10 points); and combines the expert scores to finally obtain the judgment matrix table.

[0188] Step 2: Eigenvector, eigenroot calculation and weight calculation;

[0189] The purpose of this step is to calculate the weight value. If the weight needs to be calculated, the eigenvector value must be calculated first, and the maximum eigenvalue (CI) must be obtained for the next step of consistency check.

[0190] Step 3: consistency test analysis;

[0191] When constructing a judgment matrix, there may be logical errors, such as A is more important than B, B is more important than C, but C is more important than A. Therefore, it is necessary to use consistency test to see if there is a problem. The consistency test uses CR value for analysis. If the CR value is less than 0.1, it means that the consistency test has passed, otherwise it means that the consistency test has not passed.

[0192] In the calculation of CR, CR = CI / RI. The CI value is obtained when calculating the eigenvector, and the RI value is directly obtained by looking up the table.

[0193] If the data does not pass the consistency check, it is necessary to check whether there are logical problems, etc., and re-enter the judgment matrix for analysis.

[0194] Step 4: Analyze the conclusions.

[0195] If the weights have been calculated and the judgment matrix satisfies the consistency check, a conclusion can be drawn and further analysis can be continued.

[0196] Construct a judgment matrix: For each layer of factors in the hierarchical model, through expert judgment and experience evaluation, the importance of n indicators is compared pairwise according to the importance scale table shown in Table 3 below, and scores are given according to the scale of 1 to 10 in the table.

[0197] Table 3:

[0198]

[0199] Based on the importance scale, a judgment matrix can be constructed, such as Table 4 below, which represents the relative importance of the factor relative to the factors in the previous layer.

[0200] Table 4:

[0201]

[0202]

[0203] According to the judgment matrix, the weight of each first-level indicator is calculated, and the score of the vehicle intelligent driving algorithm is obtained according to the score of the first-level indicator in step (5).

[0204] The overall empowerment process is as follows Figure 4 As shown in the figure, in the scoring mechanism, the system will first compare the actual value of each indicator with the set reference benchmark value one by one, and then calculate the score of each three-level indicator based on the normal distribution distance function model. After the calculation of all three-level indicator scores is completed, the system will further combine the weights of each three-level indicator, and calculate the first and second level indicator scores through weighted average and consistency test. Finally, the total score of the use case that fully reflects the overall performance is obtained by combining the subjectively set weights.

[0205] Finally, the final vehicle intelligent driving algorithm scores are graded:

[0206] excellent good generally Poor 90≤score≤100 80≤Score<90 60≤score<80 0≤score<60

[0207] Based on the evaluation method of the vehicle intelligent driving algorithm provided in the above embodiment, accordingly, the present application also provides a specific implementation of the evaluation device of the vehicle intelligent driving algorithm. Please refer to the following embodiment.

[0208] like Figure 5 As shown, the evaluation device 500 for the vehicle intelligent driving algorithm provided in the embodiment of the present application may include the following modules: an acquisition module 501, a determination module 502 and a first calculation module 503.

[0209] An acquisition module 501 is used to acquire driving data and environmental information of a vehicle based on an intelligent driving algorithm, wherein the driving data and environmental information include values ​​of each three-level indicator in a preset evaluation index system, and the evaluation index system includes at least one three-level indicator;

[0210] A determination module 502 is used to compare the value of each third-level indicator with the target value of each third-level indicator to determine the score of each third-level indicator, wherein, when the value of the third-level indicator is within the target value associated interval, the score of the third-level indicator is inversely proportional to the difference between the target value and the value of the third-level indicator;

[0211] The first calculation module 503 is used to calculate the score of the intelligent driving algorithm according to the scores of each of the three-level indicators and the preset weight coefficients of each of the three-level indicators.

[0212] The evaluation device of the vehicle intelligent driving algorithm of the embodiment of the present application can compare the driving data and environmental information of the vehicle based on the intelligent driving algorithm with the target value of each three-level indicator in the evaluation index system, and determine the score of each three-level indicator, wherein, when the value of the three-level indicator is in the target value associated interval, the score of the three-level indicator and the difference between the target value and the value of the three-level indicator are inversely proportional, and the evaluation index system includes at least one three-level indicator; finally, according to the score of each three-level indicator and the preset weight coefficient of each three-level indicator, the score of the intelligent driving algorithm is calculated. In this way, in the embodiment of the present application, since the score of the three-level indicator and the difference between the target value and the value of the three-level indicator are inversely proportional, not only when the value of the three-level indicator is closer to the target value, the corresponding score is larger, and when the value of the three-level indicator is farther away from the target value, the corresponding score is smaller, and as the value of the three-level indicator is closer to the target value, the rate of change of its corresponding score also becomes larger, which can amplify the score resolution near the target value, so that the detailed information of the three-level indicator can be captured, thereby enhancing the user's trust and acceptance.

[0213] In some embodiments, the evaluation index system further includes index parameters of each third-level index, the index parameters include the index type and the first multiple value and the second multiple value of the target value, the first multiple value is less than the second multiple value, and the index type includes a positive type, a negative type and an interval type;

[0214] The above-mentioned determination module 502 may specifically include:

[0215] The determination unit is used to determine the scores of each third-level indicator based on the mapping relationship corresponding to the indicator type of each third-level indicator, according to the numerical value of each third-level indicator and the target value, first multiple value and second multiple value of each third-level indicator. Different indicator types correspond to different mapping relationships.

[0216] In some embodiments, when the indicator type of the third-level indicator is a positive type, the above-mentioned determination unit may specifically include:

[0217] The first determination subunit is used to determine the score of the third-level indicator as zero when the value of the third-level indicator is less than the product of the target value of the third-level indicator and the first multiple value;

[0218] The first calculation subunit is used for calculating the score of the third-level indicator according to the value of the third-level indicator, the target value and the preset resolution coefficient when the value of the third-level indicator is greater than or equal to the product of the target value of the third-level indicator and the first multiple value, and less than the target value of the third-level indicator, and the score of the third-level indicator is inversely proportional to the difference between the target value and the value of the third-level indicator;

[0219] The second calculation subunit is used to calculate the score of the third-level indicator according to the value of the third-level indicator, the target value and the second multiple value when the value of the third-level indicator is greater than or equal to the target value of the third-level indicator and less than the product of the target value of the third-level indicator and the second multiple value, and the score of the third-level indicator is positively correlated with the difference between the value of the third-level indicator and the target value;

[0220] The second determination subunit is used to determine that the score of the third-level indicator is full marks when the value of the third-level indicator is greater than the product of the target value of the third-level indicator and the second multiple value.

[0221] In some embodiments, when the indicator type of the third-level indicator is a negative type, the above-mentioned determination unit may specifically include:

[0222] The third determination subunit is used to determine the score of the third-level indicator as zero when the value of the third-level indicator is greater than the product of the target value of the third-level indicator and the second multiple value;

[0223] The third calculation subunit is used to calculate the score of the third-level indicator according to the value of the third-level indicator, the target value and the preset resolution coefficient when the value of the third-level indicator is greater than or equal to the target value of the third-level indicator and less than the product of the target value of the third-level indicator and the second multiple value, and the score of the third-level indicator is inversely proportional to the difference between the target value and the value of the third-level indicator;

[0224] The fourth calculation subunit is used to calculate the score of the third-level indicator according to the value of the third-level indicator, the target value and the first multiple value when the value of the third-level indicator is less than the target value of the third-level indicator and is greater than or equal to the product of the target value of the third-level indicator and the first multiple value, and the score of the third-level indicator is positively correlated with the difference between the value of the third-level indicator and the target value;

[0225] The fourth determination subunit is used to determine that the score of the third-level indicator is full marks when the value of the third-level indicator is less than the product of the target value of the third-level indicator and the first multiple value.

[0226] In some embodiments, when the indicator type of the third-level indicator is an interval type, the above-mentioned determination unit may specifically include:

[0227] A fifth determining subunit is used to determine that the score of the third-level indicator is a full score when the value of the third-level indicator is equal to the target value of the third-level indicator, and the target value of the third-level indicator is calculated by a first value and a second value in a preset interval, and the first value is less than the second value;

[0228] a fifth calculation subunit, for calculating the score of the third-level indicator according to the value of the third-level indicator, the target value, the first value or the second value, when the value of the third-level indicator is greater than or equal to the first value and less than the target value of the third-level indicator, or greater than the target value of the third-level indicator and less than or equal to the second value, wherein the score of the third-level indicator is positively correlated with the difference between the value of the third-level indicator and the first value or the second value;

[0229] a sixth calculation subunit, for calculating the score of the third-level indicator according to the value of the third-level indicator, the preset resolution coefficient, the first value or the second value, when the value of the third-level indicator is less than the first value and greater than or equal to the product of the target value of the third-level indicator and the first multiple value, or when the value of the third-level indicator is greater than the second value and less than or equal to the product of the target value of the third-level indicator and the second multiple value, and the score of the third-level indicator is inversely proportional to the difference between the value of the third-level indicator and the first value or the second value;

[0230] The sixth determination subunit is used to determine that the score of the third-level indicator is zero when the value of the third-level indicator is less than the product of the target value of the third-level indicator and the first multiple value, or when the value of the third-level indicator is greater than the product of the target value of the third-level indicator and the second multiple value.

[0231] As an implementation of the present application, in order to ensure the accuracy and reliability of the scoring, the above-mentioned device 500 may further include:

[0232] A second calculation module is used to calculate the weight coefficient of each third-level indicator according to the score of each third-level indicator, the weight coefficient of the third-level indicator is positively correlated with the first score distance, and the first score distance is the distance between the score of the third-level indicator and the preset first score;

[0233] The first calculation module 503 is further used to calculate the score of the intelligent driving algorithm according to the scores of each of the three-level indicators and the weight coefficients of each of the three-level indicators.

[0234] In some embodiments, the evaluation index system includes at least one primary index, the primary index includes at least one secondary index, and the secondary index includes at least one tertiary index;

[0235] The first calculation module 503 may specifically include:

[0236] A first calculation unit is used to calculate the scores of each secondary indicator according to the score of at least one third-level indicator in each secondary indicator and the weight coefficient of each third-level indicator;

[0237] A second calculation unit is used to calculate the scores of each first-level indicator according to the score of at least one second-level indicator in each first-level indicator and the preset weight coefficient of each second-level indicator;

[0238] The third calculation unit is used to multiply the score of at least one first-level indicator by the preset weight coefficient of each first-level indicator, and sum them up to obtain the score of the intelligent driving algorithm.

[0239] In some embodiments, the first calculation unit may specifically include:

[0240] The seventh calculation subunit is used to multiply the score of at least one third-level indicator in each second-level indicator by the weight coefficient of each third-level indicator, and sum them to obtain the initial score of each second-level indicator;

[0241] The seventh determination subunit is used to determine the score of the secondary indicator as the product of the initial score of the secondary indicator and the preset adjustment coefficient when the score of at least one third-level indicator of the secondary indicator is less than the preset score threshold.

[0242] The second calculation unit may specifically include:

[0243] An eighth calculation subunit is used to calculate the weight coefficient of each secondary indicator according to the score of each secondary indicator, the weight coefficient of the secondary indicator is positively correlated with the second score distance, and the second score distance is the distance between the score of the secondary indicator and the preset second score;

[0244] The ninth calculation subunit is used to multiply the score of at least one secondary indicator in each primary indicator by the weight coefficient of each secondary indicator, and sum them to obtain the initial score of each primary indicator;

[0245] The eighth determination subunit is used to determine the product of the initial score of the first-level indicator and the adjustment coefficient as the score of the first-level indicator.

[0246] In some embodiments, the above indicator parameters also include indicator priorities, and different indicator priorities correspond to different adjustment coefficients;

[0247] The seventh determination subunit mentioned above can be specifically used to determine the third-level indicator that is less than the preset score threshold as the target third-level indicator when there is a score of at least one third-level indicator among the second-level indicators that is less than the preset score threshold; and determine the product of the initial score of the second-level indicator and the adjustment coefficient corresponding to the indicator priority of the target third-level indicator as the score of the second-level indicator.

[0248] As another implementation of the present application, in order to improve the objectivity of the weight coefficient of the primary indicator, the first calculation module 503 may further include:

[0249] An acquisition unit, used to acquire an importance scale obtained by at least one user scoring at least one primary indicator;

[0250] A construction unit, used for constructing a judgment matrix based on at least one importance scale;

[0251] The fourth calculation unit is used to calculate the judgment matrix to obtain the preset weight coefficient of each primary indicator.

[0252] Figure 6 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0253] The electronic device may include a processor 601 and a memory 602 storing computer program instructions.

[0254] Specifically, the processor 601 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0255] The memory 602 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 602 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 602 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 602 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 602 is a non-volatile solid-state memory.

[0256] In certain embodiments, the memory 602 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0257] The processor 601 implements any one of the vehicle intelligent driving algorithm evaluation methods in the above embodiments by reading and executing computer program instructions stored in the memory 602.

[0258] In one example, the electronic device may further include a communication interface 603 and a bus 610. Figure 6 As shown, the processor 601, the memory 602, and the communication interface 603 are connected via a bus 610 and communicate with each other.

[0259] The communication interface 603 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0260] Bus 610 includes hardware, software or both, and the parts of electronic equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 610 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the application considers any suitable bus or interconnection.

[0261] The electronic device can execute the evaluation method of the vehicle intelligent driving algorithm in the embodiment of the present application, thereby realizing the combination Figure 1 and Figure 5 A method and device for evaluating a vehicle intelligent driving algorithm are described.

[0262] In addition, in combination with the evaluation method of the vehicle intelligent driving algorithm in the above embodiment, the embodiment of the present application can provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the evaluation methods of the vehicle intelligent driving algorithm in the above embodiment is implemented.

[0263] In combination with the vehicle intelligent driving algorithm evaluation method in the above-mentioned embodiments, an embodiment of the present application may provide a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes any one of the vehicle intelligent driving algorithm evaluation methods as above.

[0264] In combination with the evaluation method of the vehicle intelligent driving algorithm in the above embodiment, the embodiment of the present application can provide a vehicle for implementation. The vehicle includes at least one of the following: the evaluation device of the vehicle intelligent driving algorithm as described above; the electronic device as described above; the computer-readable storage medium as described above; the computer program product as described above.

[0265] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0266] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0267] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0268] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0269] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A method for evaluating a vehicle intelligent driving algorithm, characterized in that: include: Acquiring driving data and environmental information of the vehicle based on the intelligent driving algorithm, wherein the driving data and environmental information include values ​​of each three-level indicator in a preset evaluation indicator system, wherein the evaluation indicator system includes at least one of the three-level indicators; Compare the value of each of the three-level indicators with the target value of each of the three-level indicators to determine the score of each of the three-level indicators, wherein, when the value of the three-level indicator is within the target value associated interval, the score of the three-level indicator is inversely proportional to the difference between the target value and the value of the three-level indicator; The score of the intelligent driving algorithm is calculated based on the scores of each of the three-level indicators and the preset weight coefficients of each of the three-level indicators.

2. The method according to claim 1, characterized in that The evaluation index system also includes index parameters of each of the three-level indicators, the index parameters include index type and a first multiple value and a second multiple value of the target value, the first multiple value is smaller than the second multiple value, and the index type includes a positive type, a negative type and an interval type; The step of comparing the values ​​of the three-level indicators with the target values ​​of the three-level indicators to determine the scores of the three-level indicators includes: Based on the mapping relationship corresponding to the indicator type of each of the third-level indicators, the score of each of the third-level indicators is determined according to the value of each of the third-level indicators and the target value, first multiple value and second multiple value of each of the third-level indicators, and different indicator types correspond to different mapping relationships.

3. The method according to claim 2, characterized in that In the case where the indicator type of the third-level indicator is the positive type, the score of each third-level indicator is determined based on the mapping relationship corresponding to the indicator type of each third-level indicator, according to the value of each third-level indicator and the target value, the first multiple value and the second multiple value of each third-level indicator, including: When the value of the third-level indicator is less than the product of the target value of the third-level indicator and the first multiple value, the score of the third-level indicator is determined to be zero; When the value of the third-level indicator is greater than or equal to the product of the target value of the third-level indicator and the first multiple value, and less than the target value of the third-level indicator, the score of the third-level indicator is calculated according to the value of the third-level indicator, the target value and the preset resolution coefficient, and the score of the third-level indicator is inversely proportional to the difference between the target value and the value of the third-level indicator; In the case where the value of the third-level indicator is greater than or equal to the target value of the third-level indicator and less than the product of the target value of the third-level indicator and the second multiple value, the score of the third-level indicator is calculated according to the value of the third-level indicator, the target value and the second multiple value, and the score of the third-level indicator is positively correlated with the difference between the value of the third-level indicator and the target value; When the value of the third-level indicator is greater than the product of the target value of the third-level indicator and the second multiple value, the score of the third-level indicator is determined to be a full score.

4. The method according to claim 2, characterized in that: In the case where the indicator type of the third-level indicator is the negative type, the score of each third-level indicator is determined based on the mapping relationship corresponding to the indicator type of each third-level indicator and according to the value of each third-level indicator and the target value, the first multiple value and the second multiple value of each third-level indicator, including: When the value of the third-level indicator is greater than the product of the target value of the third-level indicator and the second multiple value, the score of the third-level indicator is determined to be zero; When the value of the third-level indicator is greater than or equal to the target value of the third-level indicator and less than the product of the target value of the third-level indicator and the second multiple value, the score of the third-level indicator is calculated according to the value of the third-level indicator, the target value and the preset resolution coefficient, and the score of the third-level indicator is inversely proportional to the difference between the target value and the value of the third-level indicator; When the value of the third-level indicator is less than the target value of the third-level indicator and is greater than or equal to the product of the target value of the third-level indicator and the first multiple value, the score of the third-level indicator is calculated according to the value of the third-level indicator, the target value and the first multiple value, and the score of the third-level indicator is positively correlated with the difference between the value of the third-level indicator and the target value; When the value of the third-level indicator is less than the product of the target value of the third-level indicator and the first multiple value, the score of the third-level indicator is determined to be a full score.

5. The method according to claim 2, characterized in that: In the case where the indicator type of the third-level indicator is the interval type, the determining the score of each third-level indicator based on the mapping relationship corresponding to the indicator type of each third-level indicator and according to the value of each third-level indicator and the target value, the first multiple value and the second multiple value of each third-level indicator includes: In the case where the value of the third-level indicator is equal to the target value of the third-level indicator, determining that the score of the third-level indicator is full score, the target value of the third-level indicator is calculated by a first value and a second value in a preset interval, and the first value is less than the second value; In the case where the value of the third-level indicator is greater than or equal to the first value and less than the target value of the third-level indicator, or greater than the target value of the third-level indicator and less than or equal to the second value, the score of the third-level indicator is calculated according to the value of the third-level indicator, the target value, the first value or the second value, and the score of the third-level indicator is positively correlated with the difference between the value of the third-level indicator and the first value or the second value; In the case where the value of the third-level indicator is less than the first value and greater than or equal to the product of the target value of the third-level indicator and the first multiple value, or the value of the third-level indicator is greater than the second value and less than or equal to the product of the target value of the third-level indicator and the second multiple value, the score of the third-level indicator is calculated according to the value of the third-level indicator, the preset resolution coefficient, the first value or the second value, and the score of the third-level indicator is inversely proportional to the difference between the value of the third-level indicator and the first value or the second value; When the value of the third-level indicator is less than the product of the target value of the third-level indicator and the first multiple value, or the value of the third-level indicator is greater than the product of the target value of the third-level indicator and the second multiple value, the score of the third-level indicator is determined to be zero.

6. The method according to claim 2, characterized in that Before calculating the score of the intelligent driving algorithm according to the scores of each of the three-level indicators and the preset weight coefficients of each of the three-level indicators, the method further includes: According to the scores of each of the three-level indicators, a weight coefficient of each of the three-level indicators is calculated, wherein the weight coefficient of the three-level indicator is positively correlated with a first score distance, and the first score distance is the distance between the score of the three-level indicator and a preset first score; The step of calculating the score of the intelligent driving algorithm according to the scores of each of the three-level indicators and the preset weight coefficients of each of the three-level indicators includes: The score of the intelligent driving algorithm is calculated based on the scores of each of the three-level indicators and the weight coefficients of each of the three-level indicators.

7. The method according to claim 6, characterized in that The evaluation index system includes at least one first-level index, the first-level index includes at least one second-level index, and the second-level index includes at least one third-level index; The scoring of the intelligent driving algorithm is calculated based on the scores of each of the three-level indicators and the weight coefficients of each of the three-level indicators, including: Calculate the scores of the secondary indicators according to the score of at least one tertiary indicator in each of the secondary indicators and the weight coefficient of each tertiary indicator; Calculate the scores of each of the first-level indicators according to the score of at least one second-level indicator in each of the first-level indicators and the preset weight coefficient of each of the second-level indicators; The score of the at least one primary indicator is multiplied by the preset weight coefficient of each primary indicator, and the sum is calculated to obtain the score of the intelligent driving algorithm.

8. The method according to claim 7, characterized in that The step of calculating the scores of the secondary indicators according to the scores of at least one tertiary indicator in each of the secondary indicators and the weight coefficients of the tertiary indicators comprises: Multiplying the score of at least one third-level indicator in each of the second-level indicators by the weight coefficient of each of the third-level indicators, and summing them to obtain the initial score of each of the second-level indicators; In the case where the score of at least one of the third-level indicators of the second-level indicator is less than a preset score threshold, the product of the initial score of the second-level indicator and the preset adjustment coefficient is determined as the score of the second-level indicator; The step of calculating the scores of each of the first-level indicators according to the score of at least one second-level indicator in each of the first-level indicators and the preset weight coefficient of each of the second-level indicators includes: According to the scores of the secondary indicators, a weight coefficient of each secondary indicator is calculated, wherein the weight coefficient of the secondary indicator is positively correlated with the second score distance, and the second score distance is the distance between the score of the secondary indicator and a preset second score; Multiplying the score of at least one secondary indicator in each of the primary indicators by the weight coefficient of each of the secondary indicators, and summing them to obtain the initial score of each of the primary indicators; The product of the initial score of the first-level indicator and the adjustment coefficient is determined as the score of the first-level indicator.

9. The method according to claim 8, characterized in that The indicator parameters also include indicator priorities, and different indicator priorities correspond to different adjustment coefficients; In the case where the score of at least one of the third-level indicators of the second-level indicator is less than a preset score threshold, the product of the initial score of the second-level indicator and the preset adjustment coefficient is determined as the score of the second-level indicator, including: In the case where a score of at least one of the third-level indicators of the second-level indicators is less than a preset score threshold, the third-level indicator less than the preset score threshold is determined as a target third-level indicator; The product of the initial score of the secondary indicator and the adjustment coefficient corresponding to the indicator priority of the target third-level indicator is determined as the score of the secondary indicator.

10. The method according to claim 7, characterized in that Before multiplying the score of the at least one primary indicator by the preset weight coefficient of each primary indicator and summing them to obtain the score of the intelligent driving algorithm, the method further includes: Obtaining an importance scale obtained by at least one user scoring the at least one primary indicator; Based on the at least one importance scale, constructing a judgment matrix; The judgment matrix is ​​calculated to obtain a preset weight coefficient for each of the first-level indicators.

11. A vehicle intelligent driving algorithm evaluation device, characterized in that: The device comprises: An acquisition module, used to acquire driving data and environmental information of the vehicle based on the intelligent driving algorithm, wherein the driving data and environmental information include values ​​of each three-level indicator in a preset evaluation index system, wherein the evaluation index system includes at least one of the three-level indicators; A determination module, used for comparing the value of each of the three-level indicators with the target value of each of the three-level indicators, and determining the score of each of the three-level indicators, wherein, when the value of the three-level indicator is within the target value associated interval, the score of the three-level indicator and the difference between the target value and the value of the three-level indicator are in inverse proportion; The first calculation module is used to calculate the score of the intelligent driving algorithm according to the scores of each of the three-level indicators and the preset weight coefficients of each of the three-level indicators.

12. An electronic device, characterized in that: The device includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, it implements the evaluation method of the vehicle intelligent driving algorithm as described in any one of claims 1-10.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by the processor, the evaluation method of the vehicle intelligent driving algorithm as described in any one of claims 1-10 is implemented.

14. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the evaluation method for the vehicle intelligent driving algorithm as described in any one of claims 1 to 10.

15. A vehicle, characterized in that: Include at least one of the following: The evaluation device for a vehicle intelligent driving algorithm as claimed in claim 11; The electronic device as claimed in claim 12; The computer readable storage medium of claim 13; The computer program product of claim 14.

Images