A safety evaluation method, device and storage medium for an automotive NOA system

Abstract

The present invention provides a safety evaluation method, device and storage medium for an automotive NOA system, which relates to the technical field of navigation assisted driving safety. In the present invention, an initial weight is constructed through the direct influence and fluctuation influence of scenario factors on each evaluation index; then the initial weight is corrected by secondary indexes, which improves the accuracy of the index weight, thereby improving the scientific rationality of the safety evaluation scheme.

Description

Technical Field

[0001] The present invention relates to the technical field of navigation-assisted driving safety, and particularly to a safety evaluation method, device, and storage medium for an automotive NOA system. Background Art

[0002] NOA, that is, Navigation Autopilot or Navigation Assistant function, is essentially a deep integration of navigation technology and assisted driving function. In the current safety evaluation of NOA systems, the evaluation results may be affected by factors such as the personal experience, cognition, and preference of the evaluator, lacking objectivity and consistency. This subjectivity may limit the accuracy and reliability of the NOA system safety evaluation, thus affecting the quality and effect of decision-making.

[0003] To solve this problem, researchers have been seeking more objective and accurate methods to determine the weights of NOA system safety evaluation indicators. Some researchers have tried to use machine learning algorithms, data mining techniques, etc. for weight allocation to reduce the influence of subjective factors. However, these methods still have some problems, such as difficulty in interpretation, insufficient generalization ability, etc., and need to be further improved and perfected.

[0004] Therefore, aiming at the subjectivity problem of judgment index weights in NOA system safety evaluation, conducting in-depth research and exploring more objective and accurate methods has important practical significance and theoretical value. This can help us better understand the safety status of NOA systems, improve the accuracy and reliability of evaluation, and provide a more reliable basis for relevant decision-making. Currently, the commonly used methods for determining index weights in the evaluation field are the Analytic Hierarchy Process and the Entropy Weight Method, and both of these methods have certain limitations in terms of evaluation objectivity and calculation simplicity.

[0005] Based on the above problems, the present invention is proposed. Summary of the Invention

[0006] In view of the above problems, the present invention provides a safety evaluation method, device, and storage medium for an automotive NOA system, which constructs an initial weight through the direct influence and fluctuation influence of scenario factors on each evaluation index; then uses secondary indicators to correct the initial weight, improving the accuracy of the index weight, thereby enhancing the scientific rationality of the safety evaluation scheme.

[0007] In a first aspect, the present invention provides a safety evaluation method for an automotive NOA system, including:

[0008] Obtaining a plurality of safety evaluation indicators of an automotive navigation autopilot system, and a plurality of scenario factors for each evaluation indicator;

[0009] Using statistical methods, determine the static influence degree of the presence of each scenario factor on each evaluation index, and construct a first influence vector of multiple scenario factors on each evaluation index according to the static influence degree;

[0010] Using experimental methods, determine the dynamic influence degree of each scenario factor on each evaluation index when fluctuating, and construct a second influence vector of multiple scenario factors on each evaluation index according to the dynamic influence degree;

[0011] According to the first influence vector and the second influence vector, determine the influence value of each evaluation index;

[0012] Integrate the influence values of each evaluation index to obtain the initial weight of each evaluation index;

[0013] Obtain the target evaluation index with inaccurate initial weight, and split the target evaluation index into multiple secondary indexes, where the multiple secondary indexes include severity index, exposure probability index, and controllability index;

[0014] Determine the initial weight of each secondary index respectively, and integrate the initial weights of multiple secondary indexes to obtain the latest weight of the target evaluation index;

[0015] Perform weighted summation on each evaluation index according to the weight to obtain the safety evaluation result of the vehicle navigation automatic driving system.

[0016] In a second aspect, the present invention provides an electronic device, including:

[0017] At least one processor, and a memory communicatively connected to at least one of the processors;

[0018] The memory stores instructions executable by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the safety evaluation method of the vehicle NOA system according to any embodiment.

[0019] In a third aspect, the present invention provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are executable by one or more processors to implement the safety evaluation method of the vehicle NOA system according to any embodiment.

[0020] Compared with the prior art, the present invention has the following technical effects:

[0021] 1. The present invention uses statistical methods to obtain the static influence degree of the presence of scenario factors on evaluation indicators, and uses experimental methods to obtain the dynamic influence degree of the fluctuations of scenario factors on evaluation indicators. The influence values of each evaluation indicator are determined from both static and dynamic aspects, comprehensively evaluating the influence on the evaluation indicators. By synthesizing the influence values of each evaluation indicator, the initial weight of each evaluation indicator is obtained, correlating different evaluation indicators, so that the initial weight can reflect the importance of each evaluation indicator among all evaluation indicators. The present invention also takes into account that when the initial weight is inaccurate, the initial weight is split into different types of secondary indicators, and the initial weights of the secondary indicators are synthesized to update the inaccurate initial weight.

[0022] 2. The present invention adopts a single-scenario analysis method to independently analyze the indicators corresponding to each scenario, so as to determine the weights of the corresponding evaluation indicators according to the characteristics of each scenario.

[0023] 3. The present invention introduces a judgment mechanism for whether the initial weight is accurate, so as to further improve the objectivity of determining the weights of the vehicle NOA system safety evaluation indicators by splitting the indicators and setting the weights of different secondary indicators. Through this method, more accurate and objective weights of the vehicle NOA system safety evaluation indicators can be obtained, so as to better evaluate the safety performance of the vehicle.

[0024] The above description is only an overview of the technical solution of the present invention. In order to be able to understand the technical means of the present invention more clearly, it can be implemented according to the content of the specification. And in order to make the above description and other purposes, features and advantages of the present invention more obvious and understandable, preferred embodiments are specifically given and described in detail as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] By reading the detailed description of the preferred embodiments below, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0026] Figure 1 is a flowchart of a method for evaluating the safety of an automotive NOA system provided by an embodiment of the present invention;

[0027] Figure 2 is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.

[0029] In the description of the present invention, unless otherwise clearly defined and limited, terms such as "installation", "connection", "connection", "fixation", etc. should be understood in a broad sense. For example, it can be a connection, a detachable connection, or integrated; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components or the interaction relationship between two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0030] Example 1

[0031] The present invention proposes a safety evaluation method for an automotive NOA system, which is applicable to the situation of evaluating the safety of an automotive NOA system in a single scenario. Different from the prior art method of comprehensively evaluating various scenarios, the present invention takes a single scenario as the evaluation basic unit and sets corresponding evaluation indicators for each single scenario, so as to realize the safety evaluation of a single scenario by using personalized evaluation indicators. Among them, a single scenario is a scenario of a certain driving condition, a certain weather scenario or a certain test scenario. For example, a lane keeping scenario, a rain avoidance scenario.

[0032] See Figure 1 , the method specifically includes the following steps:

[0033] S110. Obtain multiple safety evaluation indicators of the vehicle navigation and autonomous driving system, and multiple scenario factors of each evaluation indicator.

[0034] For example, in the lane keeping scenario, the multiple evaluation indicators include average speed, the distance between the vehicle and the center line of the lane, the distance between the vehicle and the yellow line, the occurrence times of acceleration and deceleration, and the average angle of the steering wheel.

[0035] Each evaluation indicator is affected by various scenario factors within a single scenario, and the scenario factors corresponding to different evaluation indicators can be the same or different. For example, the scenario factors of average speed include: road surface adhesion coefficient, traffic density, etc. The scenario factors of the average angle of the steering wheel include: weather, road curvature, etc.

[0036] S120. Using statistical methods, determine the static influence degree of the presence of each scenario factor on each evaluation index, and construct a first influence vector of multiple scenario factors on each evaluation index according to the static influence degree.

[0037] Statistics is a comprehensive science that uses means such as searching, sorting, analyzing, and describing data to infer the essence of the measured object and even predict the future of the object. In the present invention, the static influence degree of the presence of each scenario factor on each evaluation index can be collected from industry experts, and the average value of the same static influence degree is obtained, so as to obtain the static influence degree of the presence of each scenario factor on each evaluation index. In essence, it is a value that can be set within the range of -100 to 100. 0 indicates no influence, a negative value indicates that the scenario factor brings a negative impact on the evaluation index and will reduce the safety performance of the NOA system, and a positive value indicates that the scenario factor brings a positive impact on the evaluation index and will improve the safety performance of the NOA system. The higher the absolute value of the static influence degree, the greater the influence degree of the scenario factor. Suppose there are m scenario factors and n evaluation indexes. Both m and n are integers greater than or equal to 1.

[0038] Preferably, the present invention abandons the specific value of the influence degree and no longer considers the change range of the influence degree, and sets a first threshold (such as 10) and a second threshold (such as -10). The first threshold is greater than the second threshold.

[0039] If the static influence degree exceeds the first threshold, set the influence value of the evaluation index to a first value, such as 1. If the static influence degree exceeds the second threshold and does not exceed the first threshold, set the influence value of the evaluation index to a second value, such as 0. If the static influence degree does not exceed the second threshold, set the influence value of the evaluation index to a third value, such as -1. Construct a first influence vector of multiple scenario factors on each evaluation index according to the first value, the second value, and the third value. Exemplarily, suppose an evaluation index has 5 scenario factors, then the first scenario factor of this evaluation index is K = [-1, 0, -1, 1, 1], and each vector element in K is an influence value.

[0040] S130. Using experimental methods, determine the dynamic influence degree of each scenario factor on each evaluation index when fluctuating, and construct a second influence vector of multiple scenario factors on each evaluation index according to the dynamic influence degree.

[0041] In some examples, each scenario factor fluctuates within a threshold range to construct a first data sequence for each scenario factor; the first data sequence includes the fluctuation values of the scenario factor; the threshold range is determined according to the type of the scenario factor. For example, the threshold range of the road surface adhesion coefficient is 0.1 to 1. The first data sequence is determined in ascending order according to a set step size of 0.1: 0.1, 0.2, …, 0.9, 1. Each value in each data sequence is used as a test condition to test the automotive navigation and autonomous driving system, and a second data sequence of each evaluation index is obtained; the second data sequence includes the values of the evaluation index. For example, lane keeping tests are carried out under various adhesion coefficients, and the values of evaluation indexes such as average speed and distance from the center line of the lane are measured. Then, the variance of the second data sequence is calculated, and according to the magnitude relationship between the variance and the set threshold, the dynamic influence degree of each scenario factor on each evaluation index when fluctuating is determined. For example, multiple average speeds are obtained under different adhesion coefficients, and the variance of the average speed is calculated. If the variance is greater than the set threshold, it indicates that the average speed has obvious fluctuations and is greatly affected dynamically by the adhesion coefficient. If the evaluation index tends to be negative as the scenario factor gradually increases, that is, it is not conducive to the safety of the NOA system, then the negative value of the variance of the evaluation index is used as the dynamic influence degree; if the evaluation index tends to be positive as the scenario factor gradually increases, that is, it is conducive to the safety of the NOA system, then the positive value of the variance of the evaluation index is used as the dynamic influence degree. 0 in the dynamic influence degree indicates no influence, a negative value indicates that the fluctuation of the scenario factor brings a negative influence to the evaluation index and will reduce the safety performance of the NOA system, a positive value indicates that the scenario factor brings a positive influence to the evaluation index and will improve the safety performance of the NOA system, and the higher the absolute value of the dynamic influence degree, the greater the dynamic influence degree of the scenario factor.

[0042] Preferably, the present invention abandons the specific values of the influence degree and no longer considers the change range of the influence degree, and sets a third threshold (such as 5) and a fourth threshold (such as -5). The third threshold is greater than the fourth threshold.

[0043] If the dynamic influence degree exceeds the third threshold, the influence value of the evaluation index is set to a fourth value, such as 1. If the dynamic influence degree exceeds the fourth threshold and does not exceed the third threshold, the influence value of the evaluation index is set to a fifth value, such as 0. If the dynamic influence degree does not exceed the fourth threshold, the influence value of the evaluation index is set to a sixth value, such as -1. A second influence vector of multiple scenario factors on each evaluation index is constructed according to the fourth value, the fifth value, and the sixth value. Exemplarily, assuming that an evaluation index has 5 scenario factors, the second scenario factor of the evaluation index is T = [1, 0, -1, -1, -1], and each vector element in T is an influence value.

[0044] S140. Determine the influence value of each evaluation index according to the first influence vector and the second influence vector.

[0045] Average the influence values of the same evaluation index in the first influence vector and the second influence vector to obtain the influence value of each evaluation index. For example, if K = [-1, 0, -1, 1, 1] and T = [1, 0, -1, -1, -1], after averaging the influence values of the same scenario factor, the intermediate vector w = [0, 0, -2, 0, 0] is obtained; then add up all the influence values in w and divide by the number of scenario factors to get the influence value of the evaluation index weight = -0.4.

[0046] In some cases, a certain scenario factor may have a static positive influence and a dynamic negative influence on an evaluation index, which may be caused by experimental errors or unknown reasons. After averaging, the influence value is neutralized to 0, thus avoiding the influence of such situations on the final evaluation result.

[0047] S150. Synthesize the influence values of each evaluation index to obtain the initial weight of each evaluation index.

[0048] Take the influence value of each evaluation index as the numerator, and perform a weighted sum of the absolute values of the influence values of each evaluation index to obtain the denominator; divide the numerator by the denominator to obtain the initial weight of each evaluation index. Optionally, see the following formula:

[0049] ;

[0050] where, is the i-th initial weight, is the influence value of the i-th evaluation index, d can be determined according to the importance of the evaluation index and can be preset. n is the number of evaluation indexes.

[0051] The initial weight is obtained by combining statistical knowledge and experiments, and has a certain degree of accuracy, but there are still inaccurate situations, which may be caused by experimental errors. Therefore, the present invention selects the initial weights of those inaccurate evaluation indexes and continues to optimize them.

[0052] S160. Obtain the target evaluation index with inaccurate initial weight, and split the target evaluation index into multiple secondary indexes.

[0053] Set a reasonable range of weights for each evaluation index through expert experience. If it exceeds this reasonable range, it means that the initial weight is incorrect. For example, in the scenario of vehicle obstacle avoidance, the reasonable range of the weight of the evaluation index of the distance between the vehicle and the obstacle is [0.8, 1]. If the initial weight is not within the reasonable range, it is considered that the distance between the vehicle and the obstacle is an inaccurate target evaluation index.

[0054] Multiple secondary indicators include severity indicators, exposure probability indicators, and controllability indicators. For example, the target evaluation indicator is the lane keeping function, which is broken down into severity indicator S: departure rate, object detection ability, and avoidance ability for sudden object intrusion; controllability indicator C: vehicle speed control, vehicle direction control; exposure probability indicator E: traffic signal visibility, density of road construction areas, pedestrian and bicycle flow.

[0055] S170. Determine the initial weight of each secondary indicator respectively, and synthesize the initial weights of multiple secondary indicators to obtain the latest weight of the target evaluation indicator.

[0056] Similar to the method for determining the initial weight of the evaluation indicator, the same method is also used to determine the initial weight for each secondary indicator (such as departure rate, object detection ability).

[0057] Specifically, use statistical methods to determine the static influence degree of the existence of each scenario factor on each secondary indicator, and construct a third influence vector of multiple scenario factors on each secondary indicator according to the static influence degree; use experimental methods to determine the dynamic influence degree of each scenario factor when fluctuating on each secondary indicator, and construct a fourth influence vector of multiple scenario factors on each secondary indicator according to the dynamic influence degree; determine the influence value of each secondary indicator according to the third influence vector and the fourth influence vector. Synthesize the influence values of each evaluation indicator under the target evaluation indicator to obtain the initial weight of each evaluation indicator. For details, refer to the process of determining the initial weight of the evaluation indicator, which will not be elaborated here.

[0058] Then, average the influence values of the same type of secondary indicators to obtain the influence value of each type of secondary indicator. For example, if the initial weight of the departure rate is 0.3, the initial weight of the object detection ability is 0.2, and the initial weight of the avoidance ability for sudden object intrusion is 0.1, then the influence value of the severity indicator S is (0.3 + 0.2 + 0.1) / 3 = 0.2

[0059] Next, according to the first weight of the severity indicator S, the second weight of the exposure probability indicator E, and the third weight of the controllability indicator C, perform a weighted sum of the influence values of each type of secondary indicator to obtain the latest weight of the target evaluation indicator. See the following formula, is the latest weight of the target evaluation indicator, is the first weight, is the second weight, is the third weight. S is the influence value of the severity indicator, E is the influence value of the exposure probability indicator, and C is the influence value of the controllability indicator.

[0060] ;

[0061] The security and controllability of the system are the aspects that need to be mainly focused on. Therefore, regarding the NOA security issue, the weights of S and C are increased, that is, the third weight > the first weight > the second weight, and the specific values can be set by oneself.

[0062] S180. Weighted sum is performed on each evaluation index according to the weight to obtain the security evaluation result of the automotive navigation and autonomous driving system.

[0063] Combined with the above description, for each evaluation index, if its initial weight is within a reasonable range, then take the initial weight as the final weight; if its initial weight is not within a reasonable range, calculate the latest weight by splitting the index, and take the latest weight as the final weight. The final weights of each evaluation index are used to perform weighted sum on each evaluation index to obtain the security evaluation result of the automotive navigation and autonomous driving system in a single scenario, that is, a numerical value of a security evaluation.

[0064] Compared with the prior art, the present invention has the following technical effects:

[0065] 1. The present invention uses statistical methods to obtain the static influence degree of the existence of scenario factors on evaluation indexes, and uses experimental methods to obtain the dynamic influence degree of the fluctuation of scenario factors on evaluation indexes. The influence values of each evaluation index are determined from both static and dynamic aspects, comprehensively evaluating the influence on evaluation indexes. By synthesizing the influence values of each evaluation index, the initial weight of each evaluation index is obtained, correlating different evaluation indexes, so that the initial weight can reflect the importance of each evaluation index among all evaluation indexes. The present invention also considers that when the initial weight is inaccurate, the initial weight is split into different types of secondary indexes, and the initial weights of the secondary indexes are synthesized to update the inaccurate initial weight.

[0066] 2. The present invention adopts a single-scenario analysis method to independently analyze the indexes corresponding to each scenario, so as to determine the weights of the corresponding evaluation indexes according to the characteristics of each scenario.

[0067] 3. The present invention introduces a judgment mechanism for whether the initial weight is accurate, and further improves the objectivity of determining the weights of the vehicle NOA system security evaluation indexes by splitting the indexes and setting the weights of different secondary indexes. Through this method, more accurate and objective weights of the vehicle NOA system security evaluation indexes can be obtained, so as to better evaluate the safety performance of the vehicle.

[0068] Embodiment 2

[0069] As Figure 2 shown, the embodiment of the present application provides an electronic device, including:

[0070] At least one processor; and

[0071] A memory communicatively connected to at least one of the processors; wherein,

[0072] The memory stores instructions executable by at least one of the processors, and the instructions are executed by at least one of the processors to enable at least one of the processors to execute the above method. At least one processor in this electronic device can execute the above method, and thus has at least the same advantages as the above method.

[0073] Optionally, the electronic device further includes an interface for connecting various components, including a high-speed interface and a low-speed interface. Each component is interconnected using different buses and can be mounted on a common motherboard or otherwise as needed. The processor can process instructions executed within the electronic device, including instructions for storing graphical information in the memory or on the memory to display a GUI (Graphical User Interface) on an external input / output device (such as a display device coupled to the interface). In other embodiments, if needed, multiple processors and multiple memories can be used together, and / or multiple buses and multiple memories can be used together. Similarly, multiple electronic devices can be connected (for example, as a server array, a set of blade servers, or a multi-processor system), and each device provides part of the necessary operations. Figure 2 Taking a processor 301 as an example.

[0074] The memory 302, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as program instructions / modules corresponding to the safety evaluation method of the vehicle NOA system in the embodiments of the present application. The processor 301 executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory 302, that is, implements the above safety evaluation method of the vehicle NOA system.

[0075] The memory 302 may mainly include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the electronic device, etc. In addition, the memory 302 can include high-speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some examples, the memory 302 can further include a memory remotely set relative to the processor 301, and these remote memories can be connected to the electronic device through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0076] The electronic device may further include: an input device 303 and an output device 304. The processor 301, the memory 302, the input device 303, and the output device 304 may be connected through a bus or other means. In the figure, the connection through the bus is taken as an example.

[0077] The input device 303 can receive input digital or character information. The output device 304 may include a display device, an auxiliary lighting device (e.g., an LED), a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light-emitting diode (LED) display, and a plasma display. In some embodiments, the display device may be a touch screen.

[0078] Embodiment 3

[0079] This embodiment provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to cause the computer to execute the above method. The computer instructions on the computer-readable storage medium are used to cause the computer to execute the above method, and thus have at least the same advantages as the above method.

[0080] The computer-readable storage medium in this application may adopt any combination of one or more computer-readable media. The medium may be a computer-readable signal medium or a computer-readable storage medium. The medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the medium (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the medium may be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.

[0081] The computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which computer-readable program code is carried. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium, and the computer-readable medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0082] The program code contained on a computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wire, optical fiber, RF (Radio Frequency), etc., or any suitable combination of the above.

[0083] The computer program code for performing the operations of the present application can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., by using an Internet service provider to connect through the Internet).

[0084] As described above, the above are only the preferred specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A safety evaluation method for an automobile NOA system, characterized in that: include: Obtain multiple safety evaluation indicators of the car navigation and autonomous driving system, as well as multiple scenario factors for each evaluation indicator; Using statistical methods, determine the static influence degree of each scenario factor on each evaluation index, and construct a first influence vector of multiple scenario factors on each evaluation index according to the static influence degree; Using an experimental method, determine the dynamic impact degree of each scenario factor on each evaluation index when it fluctuates, and construct a second impact vector of multiple scenario factors on each evaluation index according to the dynamic impact degree; Determine an influence value of each evaluation indicator according to the first influence vector and the second influence vector; The impact value of each evaluation indicator is combined to obtain the initial weight of each evaluation indicator; Obtaining the target evaluation index with inaccurate initial weight, and splitting the target evaluation index into multiple secondary indicators, wherein the multiple secondary indicators include a severity indicator, an exposure probability indicator, and a controllability indicator; Determine the initial weight of each secondary indicator separately, and combine the initial weights of multiple secondary indicators to obtain the latest weight of the target evaluation indicator; The weighted sum of each evaluation index is performed according to the weight to obtain the safety evaluation result of the vehicle navigation automatic driving system; Among them, the experimental method is used to determine the dynamic impact of each scenario factor on each evaluation indicator when it fluctuates, including: Fluctuate each scenario factor within a threshold range to construct a first data sequence for each scenario factor; the first data sequence includes a fluctuation value of the scenario factor; Using each value in each data sequence as a test condition, testing the vehicle navigation automatic driving system, and obtaining a second data sequence for each evaluation index; the second data sequence includes the value of the evaluation index; The variance of the second data sequence is calculated, and the dynamic influence of each scenario factor on each evaluation index when it fluctuates is determined according to the relationship between the variance and the set threshold.

2. The method according to claim 1, characterized in that Constructing a first influence vector of multiple scenario factors on each evaluation index according to the static influence degree, including: If the static influence degree exceeds a first threshold, setting the influence value of the evaluation index to a first value; If the static influence degree exceeds the second threshold value and does not exceed the first threshold value, setting the influence value of the evaluation index to a second value; If the static influence degree does not exceed the second threshold, setting the influence value of the evaluation index to a third value; Constructing a first influence vector of multiple scene factors on each evaluation index according to the first value, the second value and the third value; the first threshold value is greater than the second threshold value; Constructing a second impact vector of multiple scenario factors on each evaluation index according to the dynamic impact degree, including: If the dynamic impact degree exceeds a third threshold, setting the impact value of the evaluation index to a fourth value; If the dynamic impact degree exceeds the fourth threshold value and does not exceed the third threshold value, setting the impact value of the evaluation index to a fifth value; If the dynamic impact degree does not exceed the fourth threshold, setting the impact value of the evaluation index to a sixth value; A second influence vector of multiple scenario factors on each evaluation index is constructed according to the fourth value, the fifth value and the sixth value; and the third threshold is greater than the fourth threshold.

3. The method according to claim 1, characterized in that Determining the influence value of each evaluation indicator according to the first influence vector and the second influence vector includes: The influence values ​​of the same evaluation indicator in the first influence vector and the second influence vector are averaged to obtain the influence value of each evaluation indicator.

4. The method according to claim 1, characterized in that: The impact value of each evaluation indicator is combined to obtain the initial weight of each evaluation indicator, including: The influence value of each evaluation index is taken as the numerator, and the absolute value of the influence value of each evaluation index is weighted and summed to obtain the denominator; The numerator is divided by the denominator to obtain the initial weight of each evaluation indicator.

5. The method according to claim 1, characterized in that: Obtaining the target evaluation index for the inaccurate initial weight includes: Set a reasonable range of weights for each evaluation indicator; If the initial weight of an evaluation indicator exceeds the reasonable range, the evaluation indicator is used as the target evaluation indicator.

6. The method according to claim 1, characterized in that Determine the initial weight of each secondary indicator separately, including: Using statistical methods, determine the static influence degree of each scenario factor on each secondary indicator, and construct a third influence vector of multiple scenario factors on each secondary indicator according to the static influence degree; Using an experimental method, determine the dynamic impact degree of each scenario factor on each secondary indicator when it fluctuates, and construct a fourth impact vector of multiple scenario factors on each secondary indicator based on the dynamic impact degree; Determining an influence value of each secondary indicator according to the third influence vector and the fourth influence vector; The impact value of each evaluation indicator under the comprehensive target evaluation index is calculated to obtain the initial weight of each evaluation indicator.

7. The method according to claim 1, characterized in that The initial weights of various secondary indicators are combined to obtain the latest weights of the target evaluation indicators, including: The impact values ​​of the same secondary indicators are averaged to obtain the impact value of each secondary indicator; According to the first weight of the severity index, the second weight of the exposure probability index and the third weight of the controllability index, the impact value of each secondary index is weighted and summed to obtain the latest weight of the target evaluation index; Among them, the third weight>first weight>second weight.

8. An electronic device, characterized in that: include: at least one processor, and a memory communicatively coupled to at least one of the processors; The memory stores instructions executable by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the safety evaluation method for the automobile NOA system according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which can be executed by one or more processors to implement the safety evaluation method of the automobile NOA system according to any one of claims 1 to 7.

Images