Fault processing method and device, computer device and readable storage medium

Abstract

The application relates to a fault processing method and device, computer equipment and a readable storage medium. The method comprises the following steps: in the case that a target vehicle is identified to be in a fault state, acquiring vehicle abnormal data of the target vehicle and a target fault code corresponding to the vehicle abnormal data; determining a target fault position of the target vehicle from vehicle fault positions associated with each candidate fault analysis dimension according to the target fault code and historical fault records associated with the target vehicle; and performing fault processing on the target vehicle according to the vehicle abnormal data and the target fault position. The method can improve the efficiency and accuracy of fault processing.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automobile diagnosis, and in particular to a fault processing method and device, computer equipment and a readable storage medium. BACKGROUND

[0002] With the rapid development of automobile technology, in order to ensure the safety of vehicle driving, it is necessary to process vehicle faults in a timely manner. The existing fault processing method is to analyze the fault code output by the vehicle by manual means, so as to process the vehicle fault.

[0003] However, using the existing fault processing method, only relying on manual experience to process vehicle faults will reduce the efficiency and accuracy of fault processing. SUMMARY

[0004] Therefore, it is necessary to provide a fault processing method, device, computer equipment and readable storage medium to improve the efficiency and accuracy of fault processing.

[0005] In a first aspect, the present application provides a fault processing method, comprising:

[0006] In the case where the target vehicle is identified to be in a fault state, vehicle abnormal data of the target vehicle and a target fault code corresponding to the vehicle abnormal data are obtained;

[0007] According to the target fault code and the historical fault record associated with the target vehicle, a target fault position of the target vehicle is determined from the vehicle fault positions associated with each candidate fault analysis dimension;

[0008] According to the vehicle abnormal data and the target fault position, the target vehicle is processed.

[0009] In one embodiment, according to the target fault code and the historical fault record associated with the target vehicle, the target fault position of the target vehicle is determined from the vehicle fault positions associated with each candidate fault analysis dimension, comprising:

[0010] From the historical fault record associated with the target vehicle, a target fault record containing the target fault code is extracted; according to the target fault record, a target dimension fault probability corresponding to each candidate fault analysis dimension is determined; according to the target dimension fault probability corresponding to each candidate fault analysis dimension and the position fault probability of the vehicle fault position associated with each candidate fault analysis dimension, the target fault position of the target vehicle is determined from the vehicle fault positions associated with each candidate fault analysis dimension.

[0011] In one embodiment, in the case of including at least two target fault codes, according to the target fault record, the target dimension fault probability corresponding to each candidate fault analysis dimension is determined, comprising:

[0012] For each target fault code, according to the occurrence times of each candidate fault analysis dimension in the target fault record associated with the target fault code, the initial dimension fault probability of each candidate fault analysis dimension under the target fault code is determined; the initial dimension fault probability of each candidate fault analysis dimension under the target fault code is optimized by using the correlation value between each target fault code, and the target dimension fault probability of each candidate fault analysis dimension under the target fault code is obtained.

[0013] In one of the embodiments, according to the occurrence times of each candidate fault analysis dimension in the target fault record associated with the target fault code, the initial dimension fault probability of each candidate fault analysis dimension under the target fault code is determined, which includes:

[0014] According to the occurrence times of each candidate fault analysis dimension in the target fault record associated with the target fault code, the original dimension fault probability of each candidate fault analysis dimension under the target fault code is determined; according to the correlation value between the target fault code and other fault codes contained in the historical fault record, and the target dimension fault probability of each candidate fault analysis dimension under the other fault codes, the probability adjustment parameter of each candidate fault analysis dimension under the target fault code is determined; the sum of the original dimension fault probability and the probability adjustment parameter of each candidate fault analysis dimension under the target fault code is taken as the initial dimension fault probability of each candidate fault analysis dimension under the target fault code.

[0015] In one of the embodiments, according to the target dimension fault probability corresponding to each candidate fault analysis dimension and the position fault probability of the vehicle fault position associated with each candidate fault analysis dimension, the target fault position of the target vehicle is determined from the vehicle fault positions associated with each candidate fault analysis dimension, which includes:

[0016] For each candidate fault analysis dimension, the position fault probability of each vehicle fault position associated with the candidate fault analysis dimension is weighted by using the target dimension fault probability corresponding to the candidate fault analysis dimension, and the weighted position fault probability of each vehicle fault position associated with the candidate fault analysis dimension is obtained; according to the relationship from large to small, the weighted position fault probability of each vehicle fault position associated with each candidate fault analysis dimension is sorted, and the vehicle fault positions corresponding to the pre-set number of weighted position fault probabilities in the front of the sorting are taken as the target fault positions of the target vehicle.

[0017] In one of the embodiments, according to the vehicle abnormal data and the target fault position, the target vehicle is processed for fault, which includes:

[0018] According to the vehicle abnormal data and the target fault position, the fault processing mode corresponding to the target vehicle is determined; the target vehicle is processed for fault by using the fault processing mode.

[0019] In one of the embodiments, according to the vehicle abnormal data and the target fault position, a fault handling mode corresponding to the target vehicle is determined, including:

[0020] The vehicle abnormal data and the target fault position are respectively vectorized and spliced to obtain a target fault vector; a fault similarity between the target fault vector and a standard fault vector corresponding to each candidate handling mode is determined; and the candidate handling mode with a fault similarity greater than a similarity threshold is taken as the fault handling mode corresponding to the target vehicle.

[0021] In a second aspect, the present application further provides a fault handling device, including:

[0022] A data acquisition module is configured to acquire vehicle abnormal data of a target vehicle and a target fault code corresponding to the vehicle abnormal data in a case where it is identified that the target vehicle is in a fault state.

[0023] A position determination module is configured to determine a target fault position of the target vehicle from vehicle fault positions associated with each candidate fault analysis dimension according to the target fault code and historical fault records associated with the target vehicle.

[0024] A fault handling module is configured to perform fault handling on the target vehicle according to the vehicle abnormal data and the target fault position.

[0025] In a third aspect, the present application further provides a computer device including a memory and a processor, wherein the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0026] In a case where it is identified that a target vehicle is in a fault state, vehicle abnormal data of the target vehicle and a target fault code corresponding to the vehicle abnormal data are acquired.

[0027] A target fault position of the target vehicle is determined from vehicle fault positions associated with each candidate fault analysis dimension according to the target fault code and historical fault records associated with the target vehicle.

[0028] Fault handling is performed on the target vehicle according to the vehicle abnormal data and the target fault position.

[0029] In a fourth aspect, the present application further provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the following steps:

[0030] In a case where it is identified that a target vehicle is in a fault state, vehicle abnormal data of the target vehicle and a target fault code corresponding to the vehicle abnormal data are acquired.

[0031] determine the target fault position of the target vehicle from vehicle fault positions associated with each candidate fault analysis dimension according to the target fault code and historical fault records associated with the target vehicle;

[0032] perform fault processing on the target vehicle according to the vehicle abnormal data and the target fault position.

[0033] In a fifth aspect, the present application provides a computer program product comprising a computer program which, when executed by a processor, implements the following steps:

[0034] In a case where it is identified that the target vehicle is in a fault state, obtain vehicle abnormal data of the target vehicle and a target fault code corresponding to the vehicle abnormal data;

[0035] determine the target fault position of the target vehicle from vehicle fault positions associated with each candidate fault analysis dimension according to the target fault code and historical fault records associated with the target vehicle;

[0036] perform fault processing on the target vehicle according to the vehicle abnormal data and the target fault position.

[0037] The fault processing method, device, computer device and readable storage medium described above, in a case where it is identified that the target vehicle is in a fault state, obtain vehicle abnormal data of the target vehicle and a target fault code corresponding to the vehicle abnormal data, determine the target fault position of the target vehicle from vehicle fault positions associated with each candidate fault analysis dimension according to the target fault code and historical fault records associated with the target vehicle, and perform fault processing on the target vehicle according to the vehicle abnormal data and the target fault position. Compared with the related art, in which fault codes output by a vehicle are processed by manual means, the above method can improve the efficiency and accuracy of fault processing by pre-dividing vehicle fault positions associated with each candidate fault analysis dimension and then determining the target fault position of the target vehicle from the vehicle fault positions based on historical fault records associated with the target vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other related drawings can also be obtained without creative labor.

[0039] Figure 1 An application environment diagram of the fault processing method in an embodiment;

[0040] Figure 2 A flowchart of the fault processing method in an embodiment;

[0041] Figure 3 Flowchart for determining target fault location in one embodiment;

[0042] Figure 4 Flowchart for determining target dimension fault probability in one embodiment;

[0043] Figure 5 Flowchart for determining initial dimension fault probability in one embodiment;

[0044] Figure 6 Flowchart for determining target fault location in another embodiment;

[0045] Figure 7 Flowchart for determining fault handling mode in one embodiment;

[0046] Figure 8 Flowchart for fault handling method in another embodiment;

[0047] Figure 9 Structural block diagram of fault handling apparatus in one embodiment;

[0048] Figure 10 Structural block diagram of fault handling apparatus in another embodiment;

[0049] Figure 11 Structural block diagram of fault handling apparatus in yet another embodiment;

[0050] Figure 12 Internal structural diagram of computer device in one embodiment. DETAILED DESCRIPTION

[0051] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not intended to limit the present application.

[0052] The fault handling method provided by the embodiments of the present application can be applied to, for example, Figure 1The application environment shown. Among them, the vehicle terminal 102 communicates with the server 104 through the network. For example, in the case of identifying that the target vehicle is in a fault state, the server 104 obtains the vehicle abnormal data of the target vehicle and the target fault code corresponding to the vehicle abnormal data through the vehicle terminal 102 in the target vehicle. The server 104 determines the target fault position of the target vehicle from the vehicle fault position associated with each candidate fault analysis dimension according to the target fault code and the historical fault record associated with the target vehicle, and performs fault processing on the target vehicle according to the vehicle abnormal data and the target fault position. Among them, the server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0053] With the rapid development of automobile technology, in order to ensure the safety of vehicle driving, it is necessary to perform fault processing on the vehicle from time to time. The existing fault processing method is to analyze the fault code output by the vehicle by manual method, so as to process the vehicle fault.

[0054] However, using the existing fault processing method, only relying on manual experience to process vehicle fault will reduce the efficiency and accuracy of fault processing.

[0055] Therefore, in an exemplary embodiment, a fault processing method is provided, which is applied to Figure 1 The server in the above method is taken as an example for illustration, as shown in Figure 2 The specific steps include the following steps:

[0056] S201, in the case of identifying that the target vehicle is in a fault state, obtaining the vehicle abnormal data of the target vehicle and the target fault code corresponding to the vehicle abnormal data.

[0057] Among them, the target vehicle refers to an intelligent vehicle with fault processing demand; the vehicle abnormal data refers to the vehicle data that exists abnormally when the vehicle is running; the target fault code refers to the fault identification that can represent the vehicle abnormal data.

[0058] Optionally, in the case of identifying that the target vehicle is in a fault state, the vehicle terminal in the target vehicle will immediately obtain the vehicle abnormal data of the target vehicle; then, the target fault code corresponding to the vehicle abnormal data can be determined according to the vehicle abnormal data and the fault code generation rule.

[0059] Further, after the vehicle terminal determines the vehicle abnormal data and the target fault code of the target vehicle, the vehicle abnormal data and the target fault code can be sent to the server for fault analysis.

[0060] S202, determining a target fault position of the target vehicle from vehicle fault positions associated with each candidate fault analysis dimension according to the target fault code and historical fault records associated with the target vehicle.

[0061] The historical fault records refer to fault records of the vehicle in a historical period, and can include fault codes and other information of the vehicle. The candidate fault analysis dimensions refer to preset dimensions for fault analysis of the vehicle, and can include hardware dimensions and software dimensions. The vehicle fault positions refer to specific positions where the vehicle can have faults in the candidate fault analysis dimensions. The target fault position refers to a specific position where the target vehicle has a fault.

[0062] It can be understood that, in order to facilitate vehicle fault analysis, each candidate fault analysis dimension can be determined in advance based on the structure of the vehicle. Then, for each candidate fault analysis dimension, the candidate fault analysis dimension can be further divided according to the structure of the vehicle and other factors to obtain each vehicle fault position in the candidate fault analysis dimension.

[0063] Optionally, the basic information of the target vehicle, such as the manufacturer, model, year, etc., can be queried according to the vehicle identification (e.g., vehicle identification code VIN) of the target vehicle. Then, the historical fault records associated with the target vehicle can be filtered from all vehicle fault records according to the basic information of the target vehicle. For example, the historical fault records associated with the target vehicle can be historical fault records of vehicles produced by the same manufacturer as the target vehicle.

[0064] Further, a position determination model can be constructed and trained based on the vehicle fault positions associated with each candidate fault analysis dimension. Correspondingly, the historical fault records associated with the target vehicle can be input into the trained position determination model, and the target fault position of the target vehicle can be output by the position determination model according to the historical fault records and model parameters.

[0065] S203, performing fault processing on the target vehicle according to the vehicle abnormal data and the target fault position.

[0066] Optionally, after the target fault position is determined, the target vehicle can be processed at the target fault position based on the analysis of the vehicle abnormal data. For example, the fault processing method corresponding to the target vehicle can be determined according to the vehicle abnormal data and the target fault position, and the target vehicle can be processed by using the fault processing method.

[0067] Optionally, the vehicle abnormal data can be input into the trained scheme generation model, and the fault solution method of the target vehicle can be output by the scheme generation model according to the vehicle abnormal data and model parameters. Then, the fault solution method can be used to process the fault at the target fault position.

[0068] In the fault processing method, in a case where it is identified that the target vehicle is in a fault state, vehicle abnormal data of the target vehicle and a target fault code corresponding to the vehicle abnormal data are acquired, a target fault position of the target vehicle is determined from vehicle fault positions associated with each candidate fault analysis dimension according to the target fault code and historical fault records associated with the target vehicle, and the target vehicle is processed according to the vehicle abnormal data and the target fault position. Compared with the related art in which a fault code output by a vehicle is processed in an artificial manner, the above method can improve the efficiency and accuracy of fault processing by pre-dividing vehicle fault positions associated with each candidate fault analysis dimension and then determining a target fault position of a target vehicle from the vehicle fault positions based on historical fault records associated with the target vehicle.

[0069] To ensure the accuracy of the fault position determination, on the basis of the above embodiment, in the present embodiment, an optional way of determining the target fault position is provided, as shown in the following steps. Figure 3 The method comprises the following steps:

[0070] S301, extracting a target fault record containing the target fault code from historical fault records associated with the target vehicle.

[0071] The target fault record refers to the historical fault record containing the target fault code.

[0072] Optionally, the target fault code can be used as an index to query each historical fault record associated with the target vehicle, and then the target fault record containing the target fault code is extracted from the historical fault record.

[0073] S302, determining a target dimension fault probability corresponding to each candidate fault analysis dimension according to the target fault record.

[0074] Optionally, the target fault record can be input into a trained probability determination model, and the probability determination model can output the target dimension fault probability corresponding to each candidate fault analysis dimension according to the target fault record and model parameters.

[0075] S303, determining the target fault position of the target vehicle from the vehicle fault positions associated with each candidate fault analysis dimension according to the target dimension fault probability corresponding to each candidate fault analysis dimension and the position fault probability of the vehicle fault position associated with each candidate fault analysis dimension.

[0076] Optionally, the position fault probability of each vehicle fault position under each candidate fault analysis dimension can be determined according to the historical fault record of the target vehicle; subsequently, after the target dimension fault probability corresponding to each candidate fault analysis dimension is determined, the target fault analysis dimension with greater fault possibility can be determined in advance based on the target dimension fault probability corresponding to each candidate fault analysis dimension.

[0077] Further, the vehicle fault position with a position fault probability greater than a preset threshold can be selected as the target fault position of the target vehicle from the vehicle fault positions associated with the target fault analysis dimension.

[0078] In the embodiments of the present application, the target fault position of the target vehicle is determined according to the target dimension fault probability of each candidate fault analysis dimension and the position fault probability of each vehicle fault position, which can ensure the accuracy of the determination of the fault position.

[0079] In order to ensure the accuracy of the determination of the target dimension fault probability, on the basis of the above-mentioned embodiments, in the case of including at least two target fault codes, in the present embodiment, an optional way of determining the target dimension fault probability is provided, as shown in Figure 4 The method comprises the following steps:

[0080] S401, for each target fault code, the initial dimension fault probability of each candidate fault analysis dimension under the target fault code is determined according to the number of occurrences of each candidate fault analysis dimension in the target fault record associated with the target fault code.

[0081] The initial dimension fault probability refers to the fault probability of each candidate fault analysis dimension based on the number of occurrences of each candidate fault analysis dimension.

[0082] Optionally, for each target fault code, the occurrence of each candidate fault analysis dimension can be analyzed based on the number of occurrences of each candidate fault analysis dimension in the target fault record associated with the target fault code, and then the initial dimension fault probability of each candidate fault analysis dimension under the target fault code is obtained.

[0083] S402, the initial dimension fault probability of each candidate fault analysis dimension under the target fault code is optimized by using the correlation value between each target fault code, and the target dimension fault probability of each candidate fault analysis dimension under the target fault code is obtained.

[0084] The correlation value refers to a numerical value that can represent the correlation degree between two target fault codes, and further, the greater the correlation value, the higher the correlation degree between the two target fault codes.

[0085] Optionally, the joint occurrence probability between each pair of the fault codes and the individual occurrence probability corresponding to each fault code can be obtained in advance by analyzing all the fault records; subsequently, the correlation value between each target fault code can be determined according to the joint occurrence probability between each pair of the target fault codes and the individual occurrence probability corresponding to each target fault code, with reference to the following formula (1).

[0086] (1)

[0087] wherein, represents the correlation value between C1 and C2; represents the joint occurrence probability between C1 and C2; represents the individual occurrence probability of C1; represents the individual occurrence probability of C2.

[0088] Further, for each target fault code, the correlation value between the target fault code and other target fault codes and the initial dimension fault probability of each candidate fault analysis dimension under the target fault code can be input into the trained probability optimization model, and the initial dimension fault probability is optimized by the probability optimization model according to the correlation values and the model parameters to obtain the target dimension fault probability of each candidate fault analysis dimension under the target fault code.

[0089] It can be understood that, since the correlation values between the target fault codes can reflect the diffusion range of the vehicle fault to a certain extent, after the correlation values between the target fault codes are determined, the initial dimension fault probability of each candidate fault analysis dimension under each target fault code can also be optimized based on the correlation values between the target fault codes to obtain the target dimension fault probability of each candidate fault analysis dimension under each target fault code.

[0090] In the embodiments of the present application, the correlation values between the target fault codes are introduced, and the initial dimension fault probability is optimized to obtain the target dimension fault probability by using the correlation values between the target fault codes, which can ensure the accuracy of the determination of the target dimension fault probability.

[0091] In order to ensure the accuracy of the determination of the initial dimension fault probability, on the basis of the above embodiments, in the present embodiment, an optional way of determining the initial dimension fault probability is provided, as shown in Figure 5 which specifically includes the following steps:

[0092] S501, determining the original dimension fault probability of each candidate fault analysis dimension under the target fault code according to the occurrence times of each candidate fault analysis dimension in the target fault records associated with the target fault code.

[0093] The original dimension fault probability is used to represent the occurrence probability of each candidate fault analysis dimension in the target fault record.

[0094] Optionally, for each target fault code, the original dimension fault probability of each candidate fault analysis dimension under the target fault code can be determined according to the occurrence times of each candidate fault analysis dimension in the target fault record associated with the target fault code, by referring to the following formula (2).

[0095] (2)

[0096] wherein, represents the candidate fault analysis dimension; represents the occurrence times of the candidate fault analysis dimension in the historical record of the fault code C; represents the total occurrence times of each candidate fault analysis dimension in the historical record of the fault code C; represents the weight of the candidate fault analysis dimension, which can be pre-set according to the importance and repair difficulty of the candidate fault analysis dimension and other factors; represents the original dimension fault probability of the candidate fault analysis dimension.

[0097] S502, according to the association value between the target fault code and other fault codes contained in the historical fault record, and the target dimension fault probability of each candidate fault analysis dimension under the other fault codes, determines the probability adjustment parameter of each candidate fault analysis dimension under the target fault code.

[0098] wherein, the probability adjustment parameter refers to a parameter capable of adjusting the original dimension fault probability.

[0099] It can be understood that, in order to consider the influence of the faults generated by the target vehicle in the historical period on the vehicle fault, the original dimension fault probability of each candidate fault analysis dimension can be adjusted.

[0100] Based on this, according to the association value between the target fault code and other fault codes contained in the historical fault record, and the target dimension fault probability of each candidate fault analysis dimension under the other fault codes, the probability adjustment parameter of each candidate fault analysis dimension under the target fault code is determined by referring to the following formula (3).

[0101] (3)

[0102] wherein, represents the probability adjustment parameter of the candidate fault analysis dimension in the target fault code C; History represents the historical fault code set of the vehicle. ​​​represents the associated value of the target fault code C and the historical fault code Ch in the historical fault record in the recent time, for example, can represent the associated value in the historical fault record in the previous 30 days starting from the current time; represents the number of times the historical fault code Ch appears in the historical fault record in the recent time; represents the associated value of the target fault code C and the historical fault code Ch in the total historical fault record. represents the number of times the historical fault code Ch appears in the total historical fault record. represents the target dimension fault probability of the fault analysis dimension selected when the historical fault code Ch appears.

[0103] S503, the sum of the original dimension fault probability of each candidate fault analysis dimension under the target fault code and the probability adjustment parameter is taken as the initial dimension fault probability of each candidate fault analysis dimension under the target fault code.

[0104] Optionally, after calculating the original dimension fault probability of each candidate fault analysis dimension and the probability adjustment parameter of each candidate fault analysis dimension, for each candidate fault analysis dimension, the sum of the original dimension fault probability of the candidate fault analysis dimension and the probability adjustment parameter is taken as the initial dimension fault probability of the candidate fault analysis dimension.

[0105] In the embodiments of the present application, the probability adjustment parameter is introduced, and the original dimension fault probability of the candidate fault analysis dimension is adjusted by using the probability adjustment parameter to obtain the initial dimension fault probability, which can ensure the accuracy of the initial dimension fault probability.

[0106] In order to ensure the accuracy of the determination of the target fault position, on the basis of the above-mentioned embodiments, in the present embodiment, another optional way of determining the target fault position is provided, as shown in Figure 6 The method comprises the following steps:

[0107] S601, for each candidate fault analysis dimension, the position fault probability of each vehicle fault position associated with the candidate fault analysis dimension is weighted by using the target dimension fault probability corresponding to the candidate fault analysis dimension to obtain the weighted position fault probability of each vehicle fault position associated with the candidate fault analysis dimension.

[0108] The weighted position fault probability refers to the fault probability obtained by weighting the position fault probability.

[0109] ​Optionally, for each candidate fault analysis dimension, the target dimension fault probability corresponding to the candidate fault analysis dimension is multiplied with the position fault probability of each vehicle fault position respectively to obtain the weighted position fault probability of each vehicle fault position associated with the candidate fault analysis dimension, according to formula (4) as follows.

[0110] (4)

[0111] wherein, represents the weighted position fault probability of the vehicle fault position ; represents the target dimension fault probability corresponding to the candidate fault analysis dimension ; represents the position fault probability of the vehicle fault position under the candidate fault analysis dimension .

[0112] It can be understood that there can be a same vehicle fault position under different candidate fault analysis dimensions, and therefore, in the above case, the sum of the weighted position fault probabilities of the vehicle fault position under different candidate fault analysis dimensions can be taken as the weighted position fault probability of the vehicle fault position under the overall analysis dimension, according to formula (5) as follows.

[0113] (5)

[0114] wherein, n represents the number of each candidate fault analysis dimension.

[0115] S602, the weighted position fault probabilities of each vehicle fault position associated with each candidate fault analysis dimension are sorted in descending order, and the vehicle fault positions corresponding to the preset number of weighted position fault probabilities in the front of the sorting are taken as the target fault positions of the target vehicle.

[0116] wherein, the preset number refers to the number of fault positions configured in advance.

[0117] Optionally, since the fault probability is used to represent the possibility of fault occurrence, the weighted position fault probabilities of each vehicle fault position associated with each candidate fault analysis dimension can be sorted in descending order to obtain a first sorting result, and then the vehicle fault positions corresponding to the preset number of weighted position fault probabilities in the front of the sorting are extracted from the first sorting result as the target fault positions of the target vehicle.

[0118] Alternatively, the weighted position fault probabilities of the vehicle fault positions in the overall analysis dimension can be sorted in descending order to obtain a second sorting result; subsequently, the vehicle fault positions corresponding to the preset number of weighted position fault probabilities in the first sorting result are extracted as the target fault positions of the target vehicle.

[0119] In the embodiments of the present application, by weighting the position fault probability with the target dimension fault probability to obtain the weighted position fault probability, and then determining the target fault position based on the size relationship between the weighted position fault probabilities, the accuracy of the target fault position determination can be ensured.

[0120] In order to ensure the accuracy of the fault processing mode determination, on the basis of the above embodiments, in the present embodiment, an optional way of determining the fault processing mode is provided, as shown in the following table: Figure 7 The specific steps include the following steps:

[0121] S701, the vehicle abnormal data and the target fault position are respectively vectorized and spliced to obtain a target fault vector.

[0122] The target fault vector refers to a vector value that can represent the vehicle abnormal data and the target fault position.

[0123] Optionally, the key features of the abnormal data, such as error code, fault description, occurrence time, device state, etc., can be extracted from the vehicle abnormal data based on the predicted data dimension, and the text data can be cleaned and preprocessed, such as removing stop words and extracting stems, etc., to obtain target abnormal data.

[0124] Further, the target abnormal data can be input into a vector model, and the vector model can output an abnormal data vector according to the target abnormal data and model parameters; the target fault position can be input into the vector model, and the vector model can output a fault position vector according to the target fault position and model parameters; subsequently, the abnormal data vector and the fault position vector are spliced to obtain the target fault vector.

[0125] S702, determine the fault similarity between the target fault vector and the standard fault vector corresponding to each candidate processing mode.

[0126] The candidate processing mode refers to a mode that can be used for fault processing; the standard fault vector refers to a vector corresponding to the vehicle fault condition to be solved by the candidate processing mode; the fault similarity refers to the similarity between the target fault vector and the standard fault vector, and further, the greater the fault similarity, the more similar the target fault vector and the standard fault vector.

[0127] Optionally, for each standard fault vector, a cosine similarity method can be used, i.e., formula (6) below, to calculate the fault similarity between the target fault vector and the standard fault vector based on the cosine value of the included angle between the target fault vector and the standard fault vector. The closer the fault similarity is to 1, the more similar the two vectors are, and the closer the fault similarity is to -1, the less similar they are.

[0128] (6)

[0129] Wherein, A represents the target fault vector; B represents the standard fault vector; A·B represents the dot product of the target fault vector A and the standard fault vector B (i.e., the sum of the corresponding position elements after multiplication); ||A|| and ||B|| represent the lengths of the target fault vector A and the standard fault vector B (i.e., the size or length of the vector, usually obtained by calculating the square root of the sum of the squares of the elements of the vector).

[0130] S703, the candidate processing mode with a fault similarity greater than the similarity threshold value is taken as the fault processing mode corresponding to the target vehicle.

[0131] Wherein, the similarity threshold value refers to a threshold value for measuring the degree of similarity. For example, the similarity threshold value can be determined according to the fault processing mode corresponding to the historical fault record. For example, the similarity threshold value can be set to 75%.

[0132] Optionally, for each fault similarity, the fault similarity can be compared with the similarity threshold value, if the fault similarity is greater than or equal to the similarity threshold value, the candidate processing mode corresponding to the fault similarity can be taken as the fault processing mode corresponding to the target vehicle; if the fault similarity is less than the similarity threshold value, the candidate processing mode corresponding to the fault similarity cannot solve the vehicle fault corresponding to the target vehicle.

[0133] It can be understood that in the case of multiple vehicle abnormal data, the fault similarity between each vehicle abnormal data and the standard fault vector corresponding to each candidate processing mode can be calculated respectively; then, a similarity matrix is constructed based on the fault similarity between each vehicle abnormal data and the standard fault vector corresponding to each candidate processing mode, and the fault processing mode corresponding to the target vehicle is determined based on the similarity matrix. Wherein, each row represents a piece of vehicle abnormal data, each column represents a candidate processing mode, and the value in the cell represents the similarity between them.

[0134] In the application embodiment, by determining the fault similarity between the target fault vector and the standard fault vector corresponding to each candidate processing mode, the target vehicle corresponding fault processing mode is selected from each candidate processing mode, which can ensure the accuracy of the fault processing mode determination.

[0135] Figure 8 For another embodiment of the flowchart of the fault handling method, on the basis of the above embodiment, the present embodiment provides an optional example of a fault handling method. In combination with Figure 8 , the specific implementation process is as follows:

[0136] S801, in the case of identifying that the target vehicle is in a fault state, obtaining vehicle abnormal data of the target vehicle and a target fault code corresponding to the vehicle abnormal data.

[0137] S802, extracting a target fault record containing the target fault code from the historical fault record associated with the target vehicle.

[0138] S803, determining the original dimension fault probability of each candidate fault analysis dimension under the target fault code according to the occurrence times of each candidate fault analysis dimension in the target fault record associated with the target fault code.

[0139] S804, determining the probability adjustment parameter of each candidate fault analysis dimension under the target fault code according to the correlation value between the target fault code and other fault codes contained in the historical fault record, and the target dimension fault probability of each candidate fault analysis dimension under the other fault codes.

[0140] S805, summing the original dimension fault probability and the probability adjustment parameter of each candidate fault analysis dimension under the target fault code as the initial dimension fault probability of each candidate fault analysis dimension under the target fault code.

[0141] S806, using the correlation value between each target fault code to optimize the initial dimension fault probability of each candidate fault analysis dimension under the target fault code, to obtain the target dimension fault probability of each candidate fault analysis dimension under the target fault code.

[0142] S807, for each candidate fault analysis dimension, using the target dimension fault probability corresponding to the candidate fault analysis dimension to perform weighted processing on the position fault probability of each vehicle fault position associated with the candidate fault analysis dimension, to obtain the weighted position fault probability of each vehicle fault position associated with the candidate fault analysis dimension.

[0143] S808, sorting the weighted position fault probability of each vehicle fault position associated with each candidate fault analysis dimension in descending order, and taking the vehicle fault positions corresponding to the top preset number of weighted position fault probabilities as the target fault positions of the target vehicle.

[0144] S809, splicing the vehicle abnormal data and the target fault position after vectorization processing to obtain a target fault vector.

[0145] S810, determine fault similarity between the target fault vector and the standard fault vector corresponding to each candidate processing mode.

[0146] S811, take the candidate processing mode with fault similarity greater than the similarity threshold value as the fault processing mode corresponding to the target vehicle.

[0147] S812, adopt the fault processing mode to process the fault of the target vehicle.

[0148] The specific process of S801-S812 can be referred to the description of the above method embodiments, which has similar implementation principles and technical effects, and will not be described here.

[0149] It should be understood that although each step in the flowchart involved in each of the above embodiments is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise stated herein, the execution of these steps has no strict sequence limitation, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each of the above embodiments can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be alternately executed with other steps or steps or stages in other steps.

[0150] Based on the same inventive concept, the embodiments of the present application also provide a fault processing device for implementing the above-mentioned fault processing method. The implementation scheme of the device for solving the problem is similar to the implementation scheme described in the above method, so the specific limitations in one or more fault processing device embodiments provided below can be referred to the limitations of the fault processing method in the above, which will not be described here.

[0151] In one exemplary embodiment, as shown in Figure 9 a fault processing device 1 is provided, comprising a data acquisition module 10, a position determination module 20 and a fault processing module 30, wherein:

[0152] The data acquisition module 10 is configured to acquire vehicle abnormal data of the target vehicle and a target fault code corresponding to the vehicle abnormal data when it is identified that the target vehicle is in a fault state.

[0153] The position determination module 20 is configured to determine a target fault position of the target vehicle from vehicle fault positions associated with each candidate fault analysis dimension according to the target fault code and historical fault records associated with the target vehicle.

[0154] The fault processing module 30 is configured to perform fault processing on the target vehicle according to the vehicle abnormal data and the target fault location.

[0155] In an exemplary embodiment, as shown in FIG. 1, the location determination module 20 includes: Figure 10

[0156] The record extraction unit 21 is configured to extract, from the historical fault records associated with the target vehicle, a target fault record containing the target fault code.

[0157] The probability determination unit 22 is configured to determine, according to the target fault record, a target dimension fault probability corresponding to each candidate fault analysis dimension.

[0158] The location determination unit 23 is configured to determine, according to the target dimension fault probability corresponding to each candidate fault analysis dimension and the location fault probability of the vehicle fault location associated with each candidate fault analysis dimension, the target fault location of the target vehicle from the vehicle fault locations associated with each candidate fault analysis dimension.

[0159] In an exemplary embodiment, in the case of including at least two target fault codes, the probability determination unit 22 includes:

[0160] The first sub-unit is configured to determine, for each target fault code, an initial dimension fault probability of each candidate fault analysis dimension under the target fault code according to the number of occurrences of each candidate fault analysis dimension in the target fault record associated with the target fault code.

[0161] The second sub-unit is configured to optimize the initial dimension fault probability of each candidate fault analysis dimension under the target fault code by using the association value between the target fault codes, to obtain the target dimension fault probability of each candidate fault analysis dimension under the target fault code.

[0162] In an exemplary embodiment, the first sub-unit is specifically configured to:

[0163] determine the original dimension fault probability of each candidate fault analysis dimension under the target fault code according to the number of occurrences of each candidate fault analysis dimension in the target fault record associated with the target fault code; determine a probability adjustment parameter of each candidate fault analysis dimension under the target fault code according to the association value between the target fault code and other fault codes contained in the historical fault record, and the target dimension fault probability of each candidate fault analysis dimension under the other fault codes; and take the sum of the original dimension fault probability and the probability adjustment parameter of each candidate fault analysis dimension under the target fault code as the initial dimension fault probability of each candidate fault analysis dimension under the target fault code.

[0164] In an exemplary embodiment, the location determination unit 23 is specifically configured to:

[0165] ​For each candidate fault analysis dimension, the position fault probabilities of each vehicle fault position associated with the candidate fault analysis dimension are weighted by the target dimension fault probability corresponding to the candidate fault analysis dimension to obtain weighted position fault probabilities of each vehicle fault position associated with the candidate fault analysis dimension.

[0166] The weighted position fault probabilities of each vehicle fault position associated with each candidate fault analysis dimension are sorted in descending order, and the vehicle fault positions corresponding to the top pre-set number of weighted position fault probabilities are taken as the target fault positions of the target vehicle.

[0167] In an exemplary embodiment, as shown in Figure 11 The fault processing module 30 includes:

[0168] A mode determination unit 31 is configured to determine a fault processing mode corresponding to the target vehicle according to the vehicle abnormal data and the target fault position.

[0169] A fault processing unit 32 is configured to perform fault processing on the target vehicle by using the fault processing mode.

[0170] In an exemplary embodiment, the mode determination unit 31 is specifically configured to:

[0171] The vehicle abnormal data and the target fault position are respectively vectorized and spliced to obtain a target fault vector; a fault similarity between the target fault vector and a standard fault vector corresponding to each candidate processing mode is determined; and the candidate processing mode with a fault similarity greater than a similarity threshold is taken as the fault processing mode corresponding to the target vehicle.

[0172] Each module in the above fault processing device can be realized by software, hardware, and a combination thereof, in whole or in part. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a memory in a computer device in software form, so as to be called and executed by a processor to perform the operations corresponding to each module.

[0173] In an exemplary embodiment, a computer device is provided, which can be a server, and an internal structure diagram thereof can be as shown in Figure 12As shown in the figure. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capability. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store historical failure record data. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through network connection. The computer program is executed by the processor to implement a fault processing method.

[0174] Those skilled in the art can understand that, Figure 12 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0175] In one embodiment, a computer device is also provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps in each of the method embodiments.

[0176] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps in each of the method embodiments.

[0177] In one embodiment, a computer program product is provided, including a computer program, and the computer program is executed by a processor to implement the steps in each of the method embodiments.

[0178] It should be noted that the data (including but not limited to historical failure records, etc.) involved in the present application are all data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data need to comply with relevant regulations.

[0179] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0180] The technical features of the above embodiments can be combined in any manner. To make the description concise, all possible combinations of the technical features in the above embodiments are not described, but as long as the combinations of the technical features do not exist, they should be considered as the scope of the present application.

[0181] The above-described embodiments are merely illustrative of several embodiments of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the scope of the patent. It should be noted that for those skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of protection of the present application should be subject to the appended claims.

Claims

1. A failure handling method characterized by, The method comprises: In the case of identifying that the target vehicle is in a fault state, obtaining vehicle abnormal data of the target vehicle and a target fault code corresponding to the vehicle abnormal data; According to the basic information of the target vehicle, screening historical fault records associated with the target vehicle from all vehicle fault records; From the historical fault records associated with the target vehicle, a target fault record containing the target fault code is extracted; According to the target fault record, the target dimension fault probability corresponding to each candidate fault analysis dimension is determined; wherein each candidate fault analysis dimension includes a hardware dimension and a software dimension; According to the target dimension fault probability corresponding to each candidate fault analysis dimension and the position fault probability of the vehicle fault position associated with each candidate fault analysis dimension, the target fault position of the target vehicle is determined from the vehicle fault position associated with each candidate fault analysis dimension; According to the vehicle abnormal data and the target fault position, the target vehicle is processed for fault.

2. The method of claim 1, wherein, In the case of including at least two target fault codes, the target dimension fault probability corresponding to each candidate fault analysis dimension is determined according to the target fault record, comprising: For each target fault code, the initial dimension fault probability of each candidate fault analysis dimension under the target fault code is determined according to the number of occurrences of each candidate fault analysis dimension in the target fault record associated with the target fault code; The initial dimension fault probability of each candidate fault analysis dimension under the target fault code is optimized by using the correlation value between each target fault code, to obtain the target dimension fault probability of each candidate fault analysis dimension under the target fault code.

3. The method of claim 2, wherein, The initial dimension fault probability of each candidate fault analysis dimension under the target fault code is determined according to the number of occurrences of each candidate fault analysis dimension in the target fault record associated with the target fault code, comprising: According to the number of occurrences of each candidate fault analysis dimension in the target fault record associated with the target fault code, the original dimension fault probability of each candidate fault analysis dimension under the target fault code is determined; According to the correlation value between the target fault code and other fault codes contained in the historical fault record, and the target dimension fault probability of each candidate fault analysis dimension under the other fault codes, the probability adjustment parameter of each candidate fault analysis dimension under the target fault code is determined; The sum of the original dimension fault probability and the probability adjustment parameter of each candidate fault analysis dimension under the target fault code is taken as the initial dimension fault probability of each candidate fault analysis dimension under the target fault code.

4. The method of claim 1, wherein, The target fault position of the target vehicle is determined from the vehicle fault position associated with each candidate fault analysis dimension according to the target dimension fault probability corresponding to each candidate fault analysis dimension and the position fault probability of the vehicle fault position associated with each candidate fault analysis dimension, comprising: For each candidate fault analysis dimension, the position fault probability of each vehicle fault position associated with the candidate fault analysis dimension is weighted by the target dimension fault probability corresponding to the candidate fault analysis dimension, to obtain a weighted position fault probability of each vehicle fault position associated with the candidate fault analysis dimension; The weighted position fault probabilities of each vehicle fault position associated with each candidate fault analysis dimension are sorted in descending order, and the vehicle fault positions corresponding to the top pre-set number of weighted position fault probabilities are taken as the target fault positions of the target vehicle.

5. The method of claim 1, wherein, The fault processing of the target vehicle according to the vehicle abnormal data and the target fault position comprises: Determining a fault processing mode corresponding to the target vehicle according to the vehicle abnormal data and the target fault position; Processing the target vehicle according to the fault processing mode.

6. The method of claim 5, wherein, The determination of the fault processing mode corresponding to the target vehicle according to the vehicle abnormal data and the target fault position comprises: Concatenating the vehicle abnormal data and the target fault position after vectorization processing to obtain a target fault vector; Determining the fault similarity between the target fault vector and the standard fault vector corresponding to each candidate processing mode; Taking the candidate processing mode with a fault similarity greater than a similarity threshold as the fault processing mode corresponding to the target vehicle.

7. A failure handling apparatus characterized by comprising: The device comprises: A data acquisition module configured to acquire vehicle abnormal data of a target vehicle and a target fault code corresponding to the vehicle abnormal data when the target vehicle is identified to be in a fault state; A position determination module configured to filter historical fault records associated with the target vehicle from all vehicle fault records according to basic information of the target vehicle, extract target fault records containing the target fault code from the historical fault records associated with the target vehicle, determine target dimension fault probabilities corresponding to each candidate fault analysis dimension according to the target fault records, and determine a target fault position of the target vehicle from vehicle fault positions associated with each candidate fault analysis dimension according to the target dimension fault probabilities corresponding to each candidate fault analysis dimension and the position fault probabilities of the vehicle fault positions associated with each candidate fault analysis dimension, wherein each candidate fault analysis dimension comprises a hardware dimension and a software dimension; A fault processing module configured to process the target vehicle according to the vehicle abnormal data and the target fault position.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the method of any one of claims 1 to 6.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

Images