Vehicle safety risk assessment method and device

Abstract

The present invention provides a vehicle safety risk assessment method and device, the method comprising: performing risk assessment on each first node of an acquired target object to obtain a risk assessment result corresponding to each first node; wherein the first node is a bottom-level node of the target object; based on the risk assessment result of each first node and the target node of the target object acquired in advance, obtaining a risk assessment result of the target node; wherein the target node is a top-level node of the target object. The present invention performs risk assessment on the first node of the acquired target object, and then obtains the risk assessment result of the corresponding target object according to the risk assessment result obtained by the estimation, thereby improving the efficiency of risk assessment, and then improving the accuracy and reliability of risk assessment, so as to facilitate the subsequent determination of the corresponding risk solution according to the risk assessment result, and improve the efficiency and reliability of risk management.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a vehicle safety risk assessment method and device. Background Art

[0002] With the development of intelligent and connected cars, the cyber attacks faced by car terminals are becoming more and more numerous and complex. Cars are very sensitive to security attributes, so the network security protection of cars is a very important link. In the process of network security implementation, it is necessary to identify the targets that need to be protected, conduct risk analysis and assessment for the security targets that need to be protected, and determine the threat handling plan based on the assessment results.

[0003] At present, there are usually two ways to evaluate security targets that need to be protected. One method requires relevant professionals to conduct an assessment, and the change of evaluators will also lead to inconsistent assessment results. At the same time, there will be a large amount of historical data in security risk assessment, which are the best strategies verified by practice. However, most of these valuable data are not used after the project is completed. The other method is that there are some series of feature vectors and evaluation algorithms in the existing risk assessment methodology. When the feature list changes, it is necessary to re-study new evaluation methods or design new algorithms. Summary of the invention

[0004] The present invention provides a vehicle safety risk assessment method and device, which are used to solve the defect that the vehicle risk assessment method in the prior art has poor accuracy and thus has low safety of the target to be protected, improve the efficiency of risk estimation, and ensure the accuracy and reliability of risk estimation.

[0005] The present invention provides a vehicle safety risk assessment method, comprising: performing risk assessment on each first node of an acquired target object to obtain a risk prediction result corresponding to each first node; wherein the first node is a bottom-level node of the target object; based on the risk prediction result of each first node and a target node of the target object acquired in advance, obtaining a risk assessment result of the target node; wherein the target node is a top-level node of the target object.

[0006] According to a vehicle safety risk assessment method provided by the present invention, the risk assessment result of the target node is obtained based on the risk prediction result of each first node and the target node of the target object obtained in advance, including: obtaining at least two intermediate nodes corresponding to the target node based on the target node of the target object obtained in advance and the first node; wherein each of the intermediate nodes respectively includes a plurality of first nodes with the same logical relationship; based on the logical relationship between each of the first nodes and the risk prediction result of the first node, the risk prediction result of the corresponding intermediate node is obtained; based on the logical relationship between each of the intermediate nodes and the risk prediction result of the intermediate node, the risk assessment result of the target node is obtained.

[0007] According to a vehicle safety risk assessment method provided by the present invention, the logical relationship includes an AND relationship and an OR relationship, and the risk prediction result of each intermediate node is obtained, including: based on the logical relationship between each first node, sorting the values ​​of the risk estimation results corresponding to each first node with the same logical relationship; based on the AND relationship between each first node, selecting the minimum risk estimation result to obtain the risk prediction result of the intermediate node; based on the OR relationship between each first node, selecting the maximum risk estimation result to obtain the risk prediction result of the intermediate node.

[0008] According to a vehicle safety risk assessment method provided by the present invention, after obtaining the risk assessment result of the target node, it also includes: selecting corresponding mitigation measures according to the risk assessment result corresponding to the target node, and performing mitigation processing on the target object according to the mitigation measures.

[0009] According to a vehicle safety risk assessment method provided by the present invention, the risk assessment result is expressed as:

[0010] Y(threat A)=max(y(a 11 ),y(b 12 ),…,y(n 1N ))

[0011] Among them, Y(threat A) represents the risk assessment result of the target node, y(j 1i ) represents the risk assessment result of the intermediate node corresponding to the i-th first node j, i=1,2,..,N.

[0012] According to a vehicle safety risk assessment method provided by the present invention, the risk assessment of each first node of the acquired target object includes: inputting each acquired first node into a risk assessment model to obtain a risk prediction result corresponding to each first node output by the risk assessment model, wherein the risk assessment model is trained based on a model training sample; or, performing a risk assessment on each acquired first node; and marking the results obtained by the risk assessment to obtain a risk prediction result corresponding to each first node.

[0013] The present invention also provides a vehicle safety risk assessment device, comprising: a first assessment module, performing risk assessment on each first node of the acquired target object to obtain a risk assessment result corresponding to each first node; wherein the first node is the bottom node of the target object; a second assessment module, based on the risk assessment result of each first node and the target node of the target object acquired in advance, obtains the risk assessment result of the target node; wherein the target node is the top node of the target object.

[0014] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-mentioned vehicle safety risk assessment methods are implemented.

[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above-mentioned vehicle safety risk assessment methods are implemented.

[0016] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the steps of any of the above-mentioned vehicle safety risk assessment methods are implemented.

[0017] The vehicle safety risk assessment method and device provided by the present invention perform risk estimation on the first node of the acquired target object, and then obtain the risk assessment result of the corresponding target object based on the estimated risk estimation result, thereby improving the efficiency of risk estimation, and then improving the accuracy and reliability of risk assessment, so as to facilitate the subsequent determination of the corresponding risk solution according to the risk assessment result, thereby improving the efficiency and reliability of risk management. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 It is a flow chart of the vehicle safety risk assessment method provided by the present invention;

[0020] Figure 2 It is one of the schematic diagrams of the architecture of the risk assessment model provided by the present invention;

[0021] Figure 3 This is the second schematic diagram of the architecture of the risk assessment model provided by the present invention;

[0022] Figure 4 It is a schematic diagram of the architecture of the vehicle safety risk assessment method provided by the present invention;

[0023] Figure 5 It is a flow chart of evaluating the effectiveness of the vehicle safety risk assessment method provided by the present invention;

[0024] Figure 6 It is a schematic diagram of the architecture for evaluating the effectiveness of the vehicle safety risk assessment method provided by the present invention;

[0025] Figure 7 It is a structural schematic diagram of a vehicle safety risk assessment device provided by the present invention;

[0026] Figure 8 is a schematic diagram of the structure of the effectiveness evaluation module provided by the present invention;

[0027] Fig. 9 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] Figure 1 A schematic flow chart of a vehicle safety risk assessment method of the present invention is shown, the method comprising:

[0030] S11, performing risk assessment on each first node of the acquired target object to obtain a risk estimation result corresponding to each first node; wherein the first node is a bottom-level node of the target object;

[0031] S12, based on the risk estimation results of each first node and the target node of the target object acquired in advance, obtain the risk assessment result of the target node; wherein the target node is the top-level node of the target object.

[0032] It should be noted that S1N in this manual does not represent the order of vehicle safety risk assessment methods. Figure 2-Figure 4 The vehicle safety risk assessment method of the present invention is described.

[0033] Step S11, performing risk assessment on each first node of the acquired target object to obtain a risk estimation result corresponding to each first node; wherein the first node is a bottom-level node of the target object.

[0034] In this embodiment, risk assessment is performed on each first node of the acquired target object, including: inputting each first node obtained into a risk assessment model, and obtaining risk estimation results corresponding to each first node output by the risk assessment model, wherein the risk assessment model is obtained based on model training samples. It should be noted that, for example, if there are first nodes a2, a3, b2, and b3, then corresponding to each first node a2, a3, b2, and b3, risk estimation results y(a2), y(a3), y(b2), and y(b3) are obtained respectively.

[0035] Specifically, refer to Figure 2 The risk assessment model includes: a feature extraction layer, which extracts features from each input first node to obtain a safety impact factor; a risk analysis layer, which performs risk analysis on the safety impact factor to obtain a risk estimation result corresponding to each first node.

[0036] In an optional embodiment, each first node obtained is input into a risk assessment model to obtain a risk assessment result corresponding to each first node output by the risk assessment model. The specific structure of the risk assessment model can be referred to Figure 3 Specifically:

[0037] First, each risk feature of the first node is input into the feature extraction layer. The feature extraction layer divides the risk features into two dimensional risks according to their harmfulness and the possibility of attack, and extracts features from them respectively to obtain the security impact factors corresponding to the risks of each dimension. For example, the risk features include {x1, x2, x3, t1, t2, t3, t4, t5, t6}, and the two dimensional risks are the first risk dimension {x1, x2, x3} and the second risk dimension {t1, t2, t3, t4, t5, t6}. The features of the two dimensional risks are extracted to obtain the security impact factor H1 corresponding to the first risk dimension {x1, x2, x3} and the security impact factor H2 corresponding to the second risk dimension {t1, t2, t3, t4, t5, t6}.

[0038] It should be noted that the safety impact factor may be a safety impact factor such as life hazard, dangerous exposure, etc. In addition, x iIt can be at least one of the functional safety level, data sensitivity and vehicle damage level, i=1,2,3,t j It can be at least one of the cost of implementing the attack, the skill level requirement of the attacker, the difficulty of purchasing attack auxiliary equipment, whether the attack method is replicable, the affected scope and the vehicle contact requirement, j = 1, 2, 3, 4, 5, 6.

[0039] In this embodiment, the safety impact factor H1 and the safety impact factor H2 are respectively expressed as:

[0040]

[0041]

[0042] Among them, H1 represents the safety impact factor of the first risk dimension {x1, x2, x3}, and x i represents the i-th risk feature of the first risk dimension, w i Represents the corresponding risk characteristic x i weight, i = 1, 2; H1 represents the safety impact factor of the corresponding dimensional risks {t1, t2, t3, t4, t5, t6}, t j The second risk dimension j risk characteristics, u j Represents the corresponding risk characteristic t j The weights are j=1,2,3,4,5,6.

[0043] Secondly, the safety impact factor is input into the risk analysis layer to obtain the risk estimation result corresponding to each first node output by the risk analysis layer. The risk estimation result is expressed as:

[0044]

[0045] Among them, s represents the risk estimation result, p k It represents the weight corresponding to the kth safety impact factor H1, k = 1, 2. It should be added that s represents the sub-neuron value, which is used to evaluate the hazard ratio obtained by the neuron, and p represents the training parameters of the neural network, which can be used to dynamically adjust the training.

[0046] In another optional embodiment, performing risk assessment on each first node of the acquired target object includes: performing risk assessment on each first node acquired; marking the results obtained through the risk assessment to obtain risk estimation results corresponding to each first node.

[0047] Step S12, based on the risk estimation results of each first node and the target node of the target object acquired in advance, obtain the risk assessment result of the target node; wherein the target node is the top-level node of the target object.

[0048] In this embodiment, based on the risk prediction results of each first node and the target node of the target object obtained in advance, the risk assessment result of the target node is obtained, including: based on the target node of the target object obtained in advance and the first node, at least two intermediate nodes corresponding to the target node are obtained; wherein each intermediate node respectively includes multiple first nodes with the same logical relationship; based on the logical relationship between each first node and the risk prediction result of the first node, the risk prediction result of the corresponding intermediate node is obtained; based on the logical relationship between each intermediate node and the risk prediction result of the intermediate node, the risk assessment result of the target node is obtained.

[0049] Specifically, first, based on the target node and the first node of the target object obtained in advance, at least two intermediate nodes corresponding to the target node are obtained; wherein each intermediate node includes a plurality of first nodes having the same logical relationship. It should be noted that the subordinate relationship represents dependency and subordination. In this embodiment, the first node forms a component of the intermediate node, and the intermediate node forms a component of the target node.

[0050] Secondly, based on the logical relationship between each first node and the risk prediction result of the first node, the risk prediction result of the corresponding intermediate node is obtained. In this embodiment, the logical relationship between the first nodes includes an AND relationship and an OR relationship, and the risk prediction result of the intermediate node is obtained, including: based on the logical relationship between each first node, the values ​​of the risk prediction results corresponding to each first node with the same logical relationship are sorted; based on the AND relationship between each first node, the minimum risk prediction result is selected to obtain the risk prediction result of the intermediate node; based on the OR relationship between each first node, the maximum risk prediction result is selected to obtain the risk prediction result of the corresponding intermediate node.

[0051] For example, refer to Figure 4 , assuming that there are four first nodes a2, a3, b2 and b3, if the logical relationship between a2 and a3 is a sum relationship, then according to the sum relationship between a2 and a3, the risk prediction result y(a1)=min(y(a2),y(a3)) corresponding to the intermediate node a1 is obtained. Similarly, if the logical relationship between b2 and b3 is an or relationship, then according to the or relationship between b2 and b3, the risk prediction result y(b1)=max(y(b2),y(b3)) corresponding to the intermediate node b1 is obtained.

[0052] Finally, based on the logical relationship between each intermediate node and the risk prediction result of the intermediate node, the risk assessment result of the target node is obtained. Specifically, the risk assessment result of the target node is obtained by: sorting the risk prediction results corresponding to each intermediate node according to the value size; based on the logical relationship between each intermediate node, selecting the maximum risk prediction result from the sorting results as the risk assessment result of the target node. For example, continue to refer to Figure 3 , there are intermediate nodes a1 and b1, and the logical relationship between a1 and b1 is an OR relationship, then the risk assessment result of the corresponding target node is Y(threatA)=max(y(a1),y(b1)).

[0053] In this embodiment, the risk assessment result is expressed as:

[0054] Y(threat A)=max(y(a 11 ),y(b 12 ),…,y(n 1N ))

[0055] Among them, Y(threat A) represents the risk assessment result of the target node, y(j 1i ) represents the risk assessment result of the intermediate node corresponding to the i-th first node j, i=1,2,..,N.

[0056] In an optional embodiment, after obtaining the risk assessment result of the target node, the method further includes: selecting a corresponding mitigation measure according to the risk assessment result corresponding to the target node, and performing mitigation processing on the target object according to the mitigation measure.

[0057] It should be noted that when implementing mitigation measures, the risks of the corresponding target nodes can be determined based on the risk assessment results of the corresponding target nodes, so that corresponding measures can be taken to mitigate or eliminate the potential risks of the target objects. In other words, if the risk assessment results indicate that the corresponding target nodes are at risk of data leakage, the mitigation measures can encrypt the data of the target nodes to eliminate or mitigate the potential data leakage risks of the target objects.

[0058] refer to Figure 5 In an optional embodiment, in order to evaluate the effectiveness of the above vehicle safety risk assessment method, it is also necessary to:

[0059] S51, based on a predetermined node, select a corresponding first node from all first nodes to implement a mitigation measure, to obtain a first evaluation node, wherein the first evaluation node includes a first node that has been mitigated and a first node that has not been mitigated;

[0060] S52, performing risk assessment on all first assessment nodes to obtain first risk assessment results corresponding to the first assessment nodes;

[0061] S53, obtaining a first risk assessment result of the target node based on the risk assessment result of the first assessment node and the subordinate relationship between the first node and the target node;

[0062] S54, obtaining a validity assessment result based on the first risk assessment result and the risk assessment result.

[0063] It should be noted that in step S51, when implementing mitigation measures, the existing risks can be determined based on the risk estimation results of the corresponding first nodes obtained in advance, and corresponding measures can be taken to mitigate or remove the risks existing in the specific first nodes. For example, Figure 6 , mitigation measures are implemented for specific first nodes a3 and first node b3 according to the risk assessment results corresponding to each first node.

[0064] In addition, obtaining the first risk estimation result corresponding to the first evaluation node and obtaining the first risk assessment result of the target node can refer to the above description and will not be repeated here.

[0065] It should be noted that in step S53, the first risk assessment result is expressed as:

[0066] Y(threat A')=max(y(a 11 '),y(b 12 '),…,y(n 1N '))

[0067] Among them, Y(threat A') represents the risk assessment result of the target node, y(j 1i ') represents the risk estimation result of the intermediate node corresponding to the i-th first evaluation node j, i = 1, 2, .., N.

[0068] In step S44, the effectiveness evaluation result The effectiveness evaluation results The larger it is, the more effective the mitigation measures are.

[0069] To sum up, the embodiment of the present invention performs risk estimation on the first node of the acquired target object, and then obtains the risk assessment result of the corresponding target object based on the estimated risk estimation result, thereby improving the efficiency of risk estimation, and then improving the accuracy and reliability of risk assessment, so as to facilitate the subsequent determination of the corresponding risk solution according to the risk assessment result, thereby improving the efficiency and reliability of risk management.

[0070] The vehicle safety risk assessment device provided by the present invention is described below. The vehicle safety risk assessment device described below and the vehicle safety risk assessment method described above can be referenced to each other.

[0071] Figure 7 A schematic diagram of the structure of a vehicle safety risk assessment device is shown, the device comprising:

[0072] The first evaluation module 71 performs risk evaluation on each first node of the acquired target object to obtain a risk estimation result corresponding to each first node; wherein the first node is a bottom-level node of the target object;

[0073] The second evaluation module 72 obtains a risk evaluation result of the target node based on the risk evaluation results of each first node and the target node of the target object obtained in advance; wherein the target node is the top-level node of the target object.

[0074] In this embodiment, the first evaluation module 71 includes: a data input unit, which inputs the acquired first nodes into the risk assessment model unit; the risk assessment model unit, which performs risk assessment on the input first nodes to obtain risk prediction results corresponding to the first nodes; and a data output unit, which outputs the risk prediction results of the first nodes obtained by the risk assessment model, wherein the risk assessment model is obtained based on model training sample training.

[0075] Specifically, the risk assessment model unit includes: a feature extraction subunit, which extracts features from each input first node to obtain a safety impact factor; and a risk analysis subunit, which performs risk analysis on the safety impact factor to obtain a risk estimation result corresponding to each first node.

[0076] In another optional embodiment, the first evaluation module 71 further includes: a first evaluation unit, which performs risk evaluation on each acquired first node; and a labeling unit, which labels the results obtained through the risk evaluation to obtain risk estimation results corresponding to each first node.

[0077] The second evaluation module 72 includes: a node acquisition unit, which obtains at least two intermediate nodes corresponding to the target node based on the target node and the first node of the target object obtained in advance; wherein each intermediate node includes multiple first nodes with the same logical relationship; a risk prediction unit, which obtains the risk prediction result of the corresponding intermediate node based on the logical relationship between each first node and the risk prediction result of the first node; and a risk assessment unit, which obtains the risk assessment result of the target node based on the logical relationship between each intermediate node and the risk prediction result of the intermediate node.

[0078] Specifically, the risk prediction unit includes: a first sorting subunit, which sorts the values ​​of the risk prediction results corresponding to the first nodes with the same logical relationship based on the logical relationship between the first nodes; a first selection subunit, which obtains the risk prediction results of the corresponding intermediate nodes based on the logical relationship between the first nodes. It should be noted that the logical relationship between the first nodes includes an AND relationship and an OR relationship. If the first nodes are in an AND relationship, the minimum risk prediction result is selected as the risk prediction result of the intermediate node; if the first nodes are in an OR relationship, the maximum risk prediction result is selected as the risk prediction result of the intermediate node.

[0079] In one possible implementation, the risk assessment unit includes: a second sorting subunit, which sorts the risk prediction results corresponding to each intermediate node according to their values; and a second selection subunit, which selects the maximum risk prediction result from the sorting results as the risk assessment result of the target node based on the OR logical relationship between the intermediate nodes.

[0080] In an optional embodiment, the device further includes: a mitigation processing module, which is used to select corresponding mitigation measures to be taken according to the risk assessment result corresponding to the target node, and perform mitigation processing on the target object according to the mitigation measures.

[0081] It should be noted that when implementing mitigation measures, the risks of the corresponding target nodes can be determined based on the risk assessment results of the corresponding target nodes, so that corresponding measures can be taken to mitigate or eliminate the potential risks of the target objects. In other words, if the risk assessment results indicate that the corresponding target nodes are at risk of data leakage, the mitigation measures can encrypt the data of the target nodes to eliminate or mitigate the potential data leakage risks of the target objects.

[0082] refer to Figure 8 In an optional embodiment, the device further includes a validity evaluation module for evaluating the validity of the risk evaluation result of the target node. The validity evaluation module specifically includes:

[0083] A mitigation unit 81 selects a mitigation measure for a corresponding first node from all first nodes based on a predetermined node to obtain a first evaluation node, wherein the first evaluation node includes a first node that has been mitigated and a first node that has not been mitigated;

[0084] A first risk assessment unit 82 performs risk assessment on all first assessment nodes to obtain first risk assessment results corresponding to the first assessment nodes;

[0085] A second risk assessment unit 83 obtains a first risk assessment result of the target node based on the risk pre-estimation result of the first assessment node and the subordinate relationship between the first node and the target node;

[0086] The effectiveness evaluation unit 84 obtains an effectiveness evaluation result based on the first risk evaluation result and the risk evaluation result.

[0087] It should be noted that when the mitigation unit 81 implements mitigation measures, it can determine the existing risks based on the risk assessment results of the corresponding first node obtained in advance, and take corresponding measures to mitigate or eliminate the risks existing in the specific first node. For example, if there is a data leakage, corresponding measures can be taken to encrypt the data to eliminate the risk.

[0088] In addition, the first risk assessment unit 82 may be configured with reference to the first assessment module described above, and the second risk assessment unit 83 may be configured with reference to the second assessment module described above, which will not be described in detail herein.

[0089] The effectiveness evaluation unit 84 includes: an evaluation subunit, which obtains the effectiveness evaluation result based on the first risk evaluation result and the risk evaluation result. Among them, Y(threat A) represents the risk assessment result, and Y(threat A') represents the first risk assessment result. The larger it is, the more effective the mitigation measures are.

[0090] Fig. 9 An example of a physical structure diagram of an electronic device is shown in FIG. Fig. 9 As shown, the electronic device may include: a processor 91, a communication interface 92, a memory 93 and a communication bus 94, wherein the processor 91, the communication interface 92 and the memory 93 communicate with each other through the communication bus 94. The processor 91 may call the logic instructions in the memory 93 to execute the vehicle safety risk assessment method, which includes: performing risk assessment on each first node of the acquired target object to obtain a risk assessment result corresponding to each first node; wherein the first node is a bottom node of the target object; based on the risk assessment result of each first node and the target node of the target object acquired in advance, obtaining a risk assessment result of the target node; wherein the target node is a top node of the target object.

[0091] In addition, the logic instructions in the above-mentioned memory 93 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk, etc., which can store program codes.

[0092] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the vehicle safety risk assessment method provided by the above method, which includes: performing a risk assessment on each first node of the acquired target object to obtain a risk prediction result corresponding to each first node; wherein the first node is the bottom node of the target object; based on the risk prediction result of each first node and the target node of the target object acquired in advance, obtaining a risk assessment result of the target node; wherein the target node is the top node of the target object.

[0093] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the vehicle safety risk assessment method provided by the above method. The method includes: performing a risk assessment on each first node of the acquired target object to obtain a risk prediction result corresponding to each first node; wherein the first node is a bottom-level node of the target object; based on the risk prediction result of each first node and the target node of the target object acquired in advance, obtaining a risk assessment result of the target node; wherein the target node is a top-level node of the target object.

[0094] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0095] Through the description of the above implementation methods, those skilled in the art can clearly understand that the implementation methods can be implemented by means of software plus a necessary general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution can essentially or in other words be embodied in the form of a software product that contributes to the prior art. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the method described in an embodiment or some parts of the embodiment.

[0096] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vehicle safety risk assessment method, characterized in that: include: Performing risk assessment on each first node of the acquired target object to obtain a risk estimation result corresponding to each first node; wherein the first node is a bottom-level node of the target object; Based on the risk estimation results of each of the first nodes and the pre-acquired target node of the target object, a risk assessment result of the target node is obtained; wherein the target node is the top-level node of the target object; The step of obtaining a risk assessment result of the target node based on the risk assessment result of each of the first nodes and the pre-acquired target node of the target object includes: Based on the pre-acquired target node of the target object and the first node, at least two intermediate nodes corresponding to the target node are obtained; wherein each of the intermediate nodes includes a plurality of first nodes having the same logical relationship; Based on the logical relationship between the first nodes and the risk estimation results of the first nodes, a risk prediction result of the corresponding intermediate node is obtained; Based on the logical relationship between the intermediate nodes and the risk prediction results of the intermediate nodes, a risk assessment result of the target node is obtained; The logical relationship includes an AND relationship and an OR relationship, and obtaining the risk prediction result corresponding to the intermediate node includes: Based on the logical relationship between the first nodes, the values ​​of the risk estimation results corresponding to the first nodes having the same logical relationship are sorted respectively; Based on the sum relationship between the first nodes, a minimum risk estimation result is selected to obtain a risk prediction result of an intermediate node; Based on the OR relationship between the first nodes, select the maximum risk estimation result to obtain the risk prediction result of the corresponding intermediate node; Based on the logical relationship between the intermediate nodes and the risk prediction results of the intermediate nodes, a risk assessment result of the target node is obtained, including: Sorting the risk prediction results corresponding to the intermediate nodes according to their values; Based on the OR logical relationship between the intermediate nodes, the maximum risk prediction result is selected from the sorting results as the risk assessment result of the target node.

2. The vehicle safety risk assessment method according to claim 1, characterized in that: After obtaining the risk assessment result of the target node, the method further includes: According to the risk assessment result corresponding to the target node, a corresponding mitigation measure is selected, and mitigation processing is performed on the target object according to the mitigation measure.

3. The vehicle safety risk assessment method according to claim 1, characterized in that: The risk assessment results are expressed as: Y(threat A)=max(y(a 11 ),y(b 12 ),…,y(n 1N )) Among them, Y(threat A) represents the risk assessment result of the target node, y(j 1i ) represents the risk assessment result of the intermediate node corresponding to the i-th first node j, i=1,2,..,N.

4. The vehicle safety risk assessment method according to claim 1, characterized in that: The performing risk assessment on each first node of the acquired target object includes: Inputting each first node obtained into a risk assessment model to obtain a risk estimation result corresponding to each first node output by the risk assessment model, wherein the risk assessment model is obtained by training based on a model training sample; or Performing risk assessment on each of the obtained first nodes; The results obtained through the risk assessment are marked to obtain risk estimation results corresponding to each of the first nodes.

5. A vehicle safety risk assessment device, characterized in that: include: A first assessment module performs risk assessment on each first node of the acquired target object to obtain a risk estimation result corresponding to each first node; wherein the first node is a bottom-level node of the target object; A second evaluation module, based on the risk evaluation results of each of the first nodes and the pre-acquired target node of the target object, obtains a risk evaluation result of the target node; wherein the target node is a top-level node of the target object; The second evaluation module comprises: A node acquisition unit, based on the pre-acquired target node of the target object and the first node, obtains at least two intermediate nodes corresponding to the target node; wherein each of the intermediate nodes includes a plurality of first nodes having the same logical relationship; A risk prediction unit, which obtains a risk prediction result of a corresponding intermediate node based on the logical relationship between the first nodes and the risk estimation result of the first nodes; A risk assessment unit, which obtains a risk assessment result of the target node based on the logical relationship between the intermediate nodes and the risk prediction results of the intermediate nodes; The risk prediction unit comprises: A first sorting subunit, based on the logical relationship between the first nodes, sorts the values ​​of the risk estimation results corresponding to the first nodes having the same logical relationship; A first selection subunit selects a minimum risk prediction result based on the sum relationship between the first nodes to obtain a risk prediction result of an intermediate node; and selects a maximum risk prediction result based on the or relationship between the first nodes to obtain a risk prediction result of a corresponding intermediate node; The risk assessment unit comprises: A second sorting subunit sorts the risk prediction results corresponding to the intermediate nodes according to their values; The second selection subunit selects the maximum risk prediction result from the sorting results based on the OR logical relationship between the intermediate nodes as the risk assessment result of the target node.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the vehicle safety risk assessment method according to any one of claims 1 to 4 are implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the vehicle safety risk assessment method according to any one of claims 1 to 4 are implemented.

8. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the vehicle safety risk assessment method according to any one of claims 1 to 4 are implemented.

Images