Vehicle fault diagnosis method and device, electronic equipment and storage medium

Abstract

The present disclosure relates to a vehicle fault diagnosis method and device, electronic equipment and storage medium. The method comprises: determining a target diagnosis result set according to a fault knowledge graph and a plurality of target fault codes, wherein the target diagnosis result set comprises a plurality of target diagnosis results, and the fault knowledge graph comprises a plurality of corresponding relationships between fault codes and diagnosis results; and generating a target diagnosis result sequence according to the correlation degree between each target diagnosis result in the target diagnosis result set and the target fault code. The method can comprehensively diagnose vehicle faults.

Description

Technical Field

[0001] This disclosure relates to the field of automotive technology, and more particularly to a vehicle fault diagnosis method, apparatus, electronic device, and storage medium. Background Technology

[0002] Currently, vehicle fault diagnosis methods mainly include the following: One is the manual diagnosis method, where repair personnel determine vehicle faults by sight, hearing, and smell, relying on their own repair experience and some simple tools for analysis. The other is the simple instrument diagnosis method, which, based on manual experience, uses simple instruments such as multimeters and oscilloscopes to determine the type of fault. Because both methods heavily rely on the experience and ability of the repair personnel, the diagnosis is time-consuming and the accuracy is relatively poor.

[0003] Based on this, an intelligent vehicle diagnostic system has emerged, which uses the vehicle controller to analyze data from automotive components and then displays the results on the vehicle screen or on a handheld diagnostic device, showing the location and time of the fault.

[0004] However, while on-board diagnostic systems can detect some obvious faults in a timely manner, they still cannot identify the root cause and potential problems of serious vehicle malfunctions. Summary of the Invention

[0005] This disclosure provides a vehicle fault diagnosis method, apparatus, electronic device, and storage medium capable of comprehensively diagnosing vehicle faults.

[0006] In a first aspect, this disclosure provides a vehicle fault diagnosis method, including:

[0007] Based on the fault knowledge graph and multiple target fault codes, a target diagnostic result set is determined. The target diagnostic result set includes multiple target diagnostic results, and the fault knowledge graph includes the correspondence between multiple fault codes and diagnostic results.

[0008] Based on the correlation between each target diagnostic result and the target fault code in the target diagnostic result set, a target diagnostic result sequence is generated.

[0009] Optionally, determining the target diagnostic result set based on the fault knowledge graph and multiple target fault codes includes:

[0010] For each target fault code, a set of diagnostic results is determined based on the fault knowledge graph, wherein the set of diagnostic results includes at least one diagnostic result;

[0011] The target diagnostic result set is determined based on the frequency of occurrence of each diagnostic result in the multiple diagnostic result sets of the multiple target fault codes.

[0012] Optionally, before generating the target diagnostic result sequence based on the correlation between each target diagnostic result in the target diagnostic result set and the target fault code, the method further includes:

[0013] Based on the frequency of each target diagnostic result in the target diagnostic result set, the correlation between each target diagnostic result and the target fault code is determined.

[0014] Optionally, before generating the target diagnostic result sequence based on the correlation between each target diagnostic result in the target diagnostic result set and the target fault code, the method further includes:

[0015] Based on the time sequence of the reported fault codes of each target, the correlation between the diagnostic results of each target and the fault codes of each target is determined.

[0016] Optionally, before determining the correlation between the diagnostic results of each target and the target fault code based on the reporting time sequence of each target fault code, the method further includes:

[0017] Based on the frequency of each diagnostic result in the multiple diagnostic result sets, it is determined that the frequency of each diagnostic result does not meet the preset condition.

[0018] Optionally, determining the target diagnostic result set based on the frequency of occurrence of each diagnostic result in the multiple diagnostic result sets of the multiple target fault codes includes:

[0019] If the frequency of each diagnostic result meets a preset condition, the union of the multiple diagnostic result sets is determined as the target diagnostic result set;

[0020] If the frequency of each diagnostic result does not meet the preset condition, the set of multiple diagnostic results is determined as the target diagnostic result set.

[0021] Optionally, the preset condition is that at least one frequency in the frequencies corresponding to each of the multiple diagnostic result sets is greater than or equal to a preset frequency.

[0022] Optionally, determining the target diagnostic result set based on the fault knowledge graph and multiple target fault codes includes:

[0023] For each target fault code, a set of diagnostic results for each target fault code is determined based on the fault knowledge graph and the priority of diagnostic results in the fault knowledge graph, wherein the set of diagnostic results includes at least one diagnostic result.

[0024] For each target fault code, the diagnostic result set is determined as the target diagnostic result set corresponding to each target fault code.

[0025] Optionally, before generating the target diagnostic result sequence based on the correlation between each target diagnostic result and the target fault code in the target diagnostic result set, the method further includes:

[0026] Based on the priority of all target diagnostic results within each target diagnostic result set, the correlation between each target diagnostic result in each target diagnostic result set and its corresponding target fault code is determined.

[0027] Optionally, the diagnostic results in the fault knowledge graph include at least one of the following: controller, fault setting conditions, fault recovery conditions, fault cause, and maintenance suggestions.

[0028] Optionally, the method further includes:

[0029] The multiple target fault codes are input into the trained model, and a diagnostic result sequence of the multiple target fault codes is output based on the trained model. The diagnostic results in the diagnostic result sequence are sorted according to their probability values.

[0030] Secondly, this disclosure provides a vehicle fault diagnosis device, comprising:

[0031] The determination module is used to determine a set of target diagnostic results based on a fault knowledge graph and multiple target fault codes. The set of target diagnostic results includes multiple target diagnostic results, and the fault knowledge graph includes the correspondence between multiple fault codes and diagnostic results.

[0032] The sequence generation module is used to generate a sequence of target diagnostic results based on the correlation between each target diagnostic result and the target fault code in the target diagnostic result set.

[0033] Thirdly, this disclosure provides an electronic device, including: a processor, the processor being configured to execute a computer program stored in a memory, the computer program being executed by the processor to implement the steps of any of the methods provided in the first aspect.

[0034] Fourthly, this disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods provided in the first aspect.

[0035] In the technical solution provided in this disclosure, a set of target diagnostic results is determined based on a fault knowledge graph and multiple target fault codes. The set of target diagnostic results includes multiple target diagnostic results, and the fault knowledge graph includes the correspondence between multiple fault codes and diagnostic results. Based on the correlation between each target diagnostic result and the target fault code in the set of target diagnostic results, a sequence of target diagnostic results is generated. In this way, based on multiple fault codes generated by vehicle faults, the direct diagnostic results and related diagnostic results corresponding to multiple fault codes can be quickly obtained, that is, the direct diagnostic results and related diagnostic results of the current vehicle fault, thereby enabling a comprehensive diagnosis of vehicle faults. Attached Figure Description

[0036] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0037] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0038] Figure 1 A schematic diagram illustrating one application scenario provided in this disclosure;

[0039] Figure 2 This is a flowchart illustrating a vehicle fault diagnosis method provided in this disclosure;

[0040] Figure 3 This is a flowchart illustrating another vehicle fault diagnosis method provided in this disclosure;

[0041] Figure 4 This is a flowchart illustrating yet another vehicle fault diagnosis method provided in this disclosure;

[0042] Figure 5 This is a flowchart illustrating yet another vehicle fault diagnosis method provided in this disclosure;

[0043] Figure 6 This is a flowchart illustrating yet another vehicle fault diagnosis method provided in this disclosure;

[0044] Figure 7 This is a flowchart illustrating yet another vehicle fault diagnosis method provided in this disclosure;

[0045] Figure 8 This is a flowchart illustrating yet another vehicle fault diagnosis method provided in this disclosure;

[0046] Figure 9This is a flowchart illustrating yet another vehicle fault diagnosis method provided in this disclosure;

[0047] Figure 10 This is a flowchart illustrating yet another vehicle fault diagnosis method provided in this disclosure;

[0048] Figure 11 This is a flowchart illustrating yet another vehicle fault diagnosis method provided in this disclosure;

[0049] Figure 12 This is a schematic diagram of the structure of a vehicle fault diagnosis device provided in this disclosure. Detailed Implementation

[0050] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0051] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0052] This disclosure applies to vehicles. Figure 1 This is a schematic diagram illustrating one application scenario provided in this disclosure, such as... Figure 1 As shown, it includes: vehicle 110 and cloud server 120. Vehicle 110 is communicatively connected to cloud server 120. Cloud server 120 periodically sends fault code requests to vehicle 110. Based on the received fault code requests, vehicle 110 returns a fault code to cloud server 120 when a fault exists. Cloud server 120 diagnoses vehicle faults based on the received fault codes.

[0053] Continue as Figure 1 As shown, the application scenario can also include: vehicle fault diagnostic instrument 130. When vehicle 110 has a fault, the vehicle fault diagnostic instrument 130 and vehicle 110 are connected. After connection, the vehicle fault diagnostic instrument 130 sends a fault code request to vehicle 110. Based on the received fault code request, vehicle 110 returns the fault code generated under the current fault to the vehicle fault diagnostic instrument 130. The vehicle fault diagnostic instrument 130 diagnoses the current fault of the vehicle based on the received fault code.

[0054] When a vehicle malfunctions, a corresponding fault code is generated. Each vehicle malfunction may generate at least one fault code, especially when a serious malfunction occurs, which may generate multiple fault codes. A fault code is a string that begins with a letter and is followed by a set of numbers. The first letter identifies the type of fault code, and the set of numbers indicates at least one of the following: the cause of the current malfunction, repair recommendations, and malfunction recovery conditions.

[0055] The technical solution disclosed herein can be applied to the vehicle fault diagnostic instrument 130 and / or cloud server 120 in the above scenario. By determining a target diagnostic result set based on a fault knowledge graph and multiple target fault codes, the target diagnostic result set includes multiple target diagnostic results, and the fault knowledge graph includes the correspondence between multiple fault codes and diagnostic results. Based on the correlation between each target diagnostic result and the target fault code in the target diagnostic result set, a target diagnostic result sequence is generated. In this way, based on multiple fault codes generated by the vehicle fault, the direct diagnostic results and related diagnostic results corresponding to multiple fault codes can be quickly obtained, that is, the direct diagnostic results and related diagnostic results of the current vehicle fault, thereby enabling a comprehensive diagnosis of the vehicle fault.

[0056] The technical solutions of this disclosure will be explained in detail below through several specific embodiments.

[0057] Figure 2 This is a flowchart illustrating a vehicle fault diagnosis method provided in this disclosure, such as... Figure 2 As shown, it includes:

[0058] S101, based on the fault knowledge graph and multiple target fault codes, determine the target diagnostic result set.

[0059] The target diagnostic result set includes multiple target diagnostic results, and the fault knowledge graph includes multiple correspondences between fault codes and diagnostic results.

[0060] Figure 3 This is a schematic diagram of a fault knowledge graph provided in this disclosure, such as... Figure 3 As shown, the fault knowledge graph includes various types of nodes, including fault code node 1, fault cause node 2, maintenance suggestion node 3, fault setting condition node 4, fault recovery condition node 5, and controller node 6. Nodes can be connected by connecting lines, and there is a corresponding relationship between the nodes at both ends of the connecting line. For example, ... Figure 3 As shown, the two ends of the connecting line can be fault code node 1 and fault cause node 2, or the two ends of the connecting line can be fault code node 1 and maintenance suggestion node 3.

[0061] For example, the fault knowledge graph includes 6449 nodes, of which there are 36 controller nodes 6, 1099 fault cause nodes 2, 2066 fault code nodes 1, 580 fault recovery condition nodes 5, 839 maintenance suggestion nodes 3, and 1879 fault setting condition nodes 4.

[0062] Based on the above embodiments, the diagnostic results in the fault knowledge graph can be at least one of the following: fault cause, maintenance suggestion, fault setting conditions, fault recovery conditions, and controller. The fault knowledge graph includes the correspondence between multiple fault codes and diagnostic results. It should be noted that the same fault code may correspond to multiple diagnostic results, and different fault codes may correspond to one diagnostic result. The correspondence between these diagnostic results and fault codes is determined based on historical investigation results.

[0063] When a vehicle experiences a serious malfunction, multiple target fault codes may be generated. Each target fault code is one of all fault codes in the fault knowledge graph. Based on these multiple target fault codes, the corresponding set of diagnostic results is retrieved from the fault knowledge graph for each code. For example, if a vehicle experiences a serious malfunction and generates target fault codes B1, B2, and B3, then target fault code B1 in the fault knowledge graph corresponds to diagnostic results A1 and A3, target fault code B2 corresponds to diagnostic results A1, A2, and A3, and target fault code B3 corresponds to diagnostic result A1. Therefore, the diagnostic result set 1 for target fault code B1 is {diagnostic result A1, diagnostic result A3}, the diagnostic result set 2 for target fault code B2 is {diagnostic result A1, diagnostic result A2, diagnostic result A3}, and the diagnostic result set 3 for target fault code B3 is {diagnostic result A1}.

[0064] A target diagnostic result set is determined based on the diagnostic result set of each target fault code. This target diagnostic result set includes multiple target diagnostic results. A target diagnostic result can be one of the diagnostic result sets mentioned above, or it can be one of the aforementioned diagnostic result sets. The target diagnostic result set can be singular, meaning multiple target fault codes determine one target diagnostic result set; or it can be multiple, meaning one target diagnostic result set is determined for each target fault code. This embodiment does not impose specific limitations on the number of target diagnostic result sets corresponding to multiple target fault codes, or on the type of target diagnostic result in each target diagnostic result set.

[0065] S103, Generate a target diagnosis result sequence based on the correlation between each target diagnosis result and the target fault code in the target diagnosis result set.

[0066] For example, if multiple target fault codes correspond to a target diagnostic result set, and one target diagnostic result in the target diagnostic result set constitutes a diagnostic result set, based on the correlation between the diagnostic result set and all target fault codes, the diagnostic result sets in the target diagnostic result set are arranged in descending order of correlation to generate a target diagnostic result sequence. For instance, based on the above embodiment, the target diagnostic result sets corresponding to target fault codes B1, B2, and B3 are {diagnostic result set 1, diagnostic result set 2, diagnostic result set 3}, where the correlation between diagnostic result set 1 and all target fault codes is greater than that between diagnostic result set 2 and all target fault codes, and the correlation between diagnostic result set 3 and all target fault codes is greater than that between diagnostic result set 1 and all target fault codes. Therefore, the generated target diagnostic result sequence is {diagnostic result set 3, diagnostic result set 1, diagnostic result set 2}.

[0067] For example, if multiple target fault codes correspond to a target diagnostic result set, and each target diagnostic result in the target diagnostic result set is a single diagnostic result, the diagnostic results in the target diagnostic result set are arranged in descending order of relevance based on the correlation between the diagnostic results and all target fault codes, thus generating a target diagnostic result sequence. For instance, based on the above embodiment, the target diagnostic result set corresponding to target fault codes B1, B2, and B3 is {diagnostic result A1, diagnostic result A2, diagnostic result A3}, where the correlation between diagnostic result A1 and all target fault codes is greater than that between diagnostic result A3 and all target fault codes, and the correlation between diagnostic result A3 and all target fault codes is greater than that between diagnostic result A2 and all target fault codes. Therefore, the generated target diagnostic result sequence is {diagnostic result A1, diagnostic result A3, diagnostic result A2}.

[0068] For example, if multiple target fault codes correspond to multiple target diagnostic result sets, then a target diagnostic result set is a diagnostic result set. Based on the correlation between the diagnostic results in each diagnostic result set and the corresponding target fault codes, the diagnostic results in each diagnostic result set are arranged in descending order of correlation to generate a target diagnostic result sequence corresponding to each target fault code. For example, based on the above implementation, the target diagnostic result sets corresponding to target fault codes B1, B2, and B3 are {diagnostic result set 1}, {diagnostic result set 2}, and {diagnostic result set 3}, respectively. In diagnostic result set 1, the correlation between diagnostic result A1 and target fault code B1 is greater than the correlation between diagnostic result A3 and target fault code B1. In diagnostic result set 2, the correlation between diagnostic result A1 and target fault code B2 is greater than the correlation between diagnostic result A3 and target fault code B2. The correlation between diagnostic result A3 and target fault code B2 is greater than the correlation between diagnostic result A2 and target fault code B2. Therefore, the generated target diagnostic result sequence for target fault code B1 is {diagnostic result A1, diagnostic result A3}, the generated target diagnostic result sequence for target fault code B2 is {diagnostic result A1, diagnostic result A3, diagnostic result A2}, and the generated target diagnostic result sequence for target fault code B3 is {diagnostic result A1}.

[0069] In this embodiment, a target diagnostic result set is determined based on a fault knowledge graph and multiple target fault codes. The target diagnostic result set includes multiple target diagnostic results, and the fault knowledge graph includes the correspondence between multiple fault codes and diagnostic results. Based on the correlation between each target diagnostic result and the target fault code in the target diagnostic result set, a target diagnostic result sequence is generated. In this way, based on multiple fault codes generated by the vehicle fault, the direct diagnostic results and related diagnostic results corresponding to multiple fault codes can be quickly obtained, that is, the direct diagnostic results and related diagnostic results of the current vehicle fault, thereby enabling a comprehensive diagnosis of the vehicle fault.

[0070] Figure 4 This is a schematic diagram of another vehicle fault diagnosis process provided in this disclosure. Figure 4 for Figure 2 Based on the illustrated embodiment, a specific description of a possible implementation of S101 is as follows:

[0071] S1011, For each target fault code, determine the set of diagnostic results based on the fault knowledge graph.

[0072] The set of diagnostic results includes at least one diagnostic result.

[0073] The target fault code can be a non-circuit-related target fault code, used to represent faults in non-communication bus systems. The first letter of a non-circuit-related target fault code is not the character "U"; for example, the first letter could be "B," "C," or "P." The fault knowledge graph includes the correspondence between target fault codes and diagnostic results. Based on each received target fault code, at least one corresponding diagnostic result is found from the fault knowledge graph, thus obtaining a diagnostic result set for each target fault code, and this set includes at least one diagnostic result.

[0074] For example, upon receiving target fault codes C1, C2, and C3, the fault knowledge graph shows that target fault code C1 corresponds to diagnostic results A1 and A3, target fault code C2 corresponds to diagnostic results A1, A2, and A3, and target fault code C3 corresponds to diagnostic result A1. Therefore, for target fault code C1, the determined set of diagnostic results is {diagnostic result A1, diagnostic result A3}; for target fault code C2, the determined set of diagnostic results is {diagnostic result A1, diagnostic result A2, diagnostic result A3}; and for target fault code C3, the determined set of diagnostic results is {diagnostic result A1}.

[0075] S1012, determine the target diagnostic result set based on the frequency of occurrence of each diagnostic result in the multiple diagnostic result sets of the multiple target fault codes.

[0076] Based on all diagnostic results in the entire set of diagnostic results for all target fault codes, determine the frequency of each diagnostic result among all diagnostic results. For example, based on the above embodiment, the entire set of diagnostic results includes: {diagnostic result A1, diagnostic result A3}, {diagnostic result A1, diagnostic result A2, diagnostic result A3}, and {diagnostic result A1}. The entire set of diagnostic results includes three diagnostic results: diagnostic result A1, diagnostic result A2, and diagnostic result A3. Diagnostic result A1 appears 3 times in the entire set of diagnostic results, diagnostic result A2 appears once in the entire set of diagnostic results, and diagnostic result A3 appears twice in the entire set of diagnostic results.

[0077] The target diagnostic result set is determined based on whether the frequency of each diagnostic result among all diagnostic results meets the preset conditions. The target diagnostic results in the target diagnostic result set can be either a set of diagnostic results or a single diagnostic result, which will be analyzed in detail later.

[0078] As a specific description of one possible implementation method when executing S1012, such as Figure 5 As shown:

[0079] S201, determine whether the frequency of each diagnostic result meets the preset conditions.

[0080] If yes, execute S202; otherwise, execute S203.

[0081] Optionally, the preset condition can be that at least one frequency among all diagnostic results in multiple diagnostic result sets is greater than or equal to a preset frequency. If the preset condition is met, it means that at least one diagnostic result among all diagnostic results has a frequency greater than or equal to the preset frequency. If the preset condition is not met, it means that no diagnostic result among all diagnostic results has a frequency greater than or equal to the preset frequency, that is, the frequency of each diagnostic result is less than the preset frequency.

[0082] S202, determine the union of the multiple sets of diagnostic results as the target set of diagnostic results.

[0083] If at least one diagnostic result among all diagnostic results has a frequency greater than or equal to a preset frequency, the union of the multiple diagnostic result sets is determined as the target diagnostic result set. For example, the preset frequency can be 3. Based on the above embodiment, if the frequency of diagnostic result A1 in all diagnostic result sets is equal to the preset frequency, that is, the preset condition is met, the union of the diagnostic result sets {diagnostic result A1, diagnostic result A3}, {diagnostic result A1, diagnostic result A2, diagnostic result A3}, and {diagnostic result A1} can be determined as the target diagnostic result set.

[0084] S203, determine the plurality of diagnostic result sets as the target diagnostic result set.

[0085] If the frequency of each diagnostic result is less than the preset frequency, then each set of diagnostic results can be considered as a target diagnostic result, and all sets of diagnostic results can form a target diagnostic result set. For example, the preset frequency can be 3, and all sets of diagnostic results include: {diagnostic result A1, diagnostic result A2}, {diagnostic result A1, diagnostic result A3}, and {diagnostic result A2}. Each set contains three diagnostic results. Diagnostic results A1 and A2 each appear twice in all sets, while diagnostic result A3 appears once. Since both frequencies are less than the preset frequency, the preset condition is not met. Therefore, the target diagnostic result set can be determined based on time series as {{diagnostic result A1, diagnostic result A2}, {diagnostic result A1, diagnostic result A3}, {diagnostic result A2}}, meaning that the time of {diagnostic result A1, diagnostic result A2} is earlier than that of {diagnostic result A1, diagnostic result A3}, and the time of {diagnostic result A1, diagnostic result A3} is earlier than that of {diagnostic result A2}.

[0086] Figure 6This is a flowchart illustrating yet another vehicle fault diagnosis method provided in this disclosure. Figure 6 for Figure 4 Based on the illustrated embodiment, before executing S103, the following steps are also included:

[0087] S102, determine the correlation between each target diagnosis result and the target fault code based on the frequency corresponding to each target diagnosis result in the target diagnosis result set.

[0088] If the target diagnostic results in the target diagnostic result set are diagnostic results, the higher the frequency of the target diagnostic results in the target diagnostic result set, the higher the correlation between the target diagnostic results and the target fault codes. Thus, based on the frequency of each target diagnostic result, the order of the correlation between the target diagnostic results can be determined.

[0089] For example, based on the above embodiment, the target diagnostic result set is {diagnostic result A1, diagnostic result A2, diagnostic result A3}. The frequency of diagnostic result A1 is 3 times, the frequency of diagnostic result A2 is 1 time, and the frequency of diagnostic result A3 is 2 times. Therefore, diagnostic result A1 has the highest correlation with the target fault code, followed by diagnostic result A3, and finally diagnostic result A2. Thus, the generated target diagnostic result sequence is {diagnostic result A1, diagnostic result A3, diagnostic result A2}.

[0090] In this embodiment, by determining the correlation between each target diagnostic result and the target fault code based on the frequency of each target diagnostic result in the target diagnostic result set, the diagnostic results of the current vehicle fault can be sorted based on the frequency of the target diagnostic results, thereby obtaining the direct and indirect diagnostic results of the current vehicle fault.

[0091] Figure 7 This is a flowchart illustrating yet another vehicle fault diagnosis method provided in this disclosure. Figure 7 for Figure 4 Based on the illustrated embodiment, before executing S103, the following steps are also included:

[0092] S102', determine the correlation between the diagnostic results of each target and the target fault code based on the time sequence of their reporting.

[0093] If the target diagnostic results in the target diagnostic results set is a set of diagnostic results, obtain the reporting time of each target fault code. If the reporting time of the target fault code is earlier, the correlation between the diagnostic results set corresponding to the target fault code and the target fault code is higher. Thus, based on the reporting time order of each target fault code, the correlation order between the diagnostic results set and the target fault code can be determined.

[0094] For example, based on the above embodiment, the target diagnostic result set is {{diagnostic result A1, diagnostic result A2}, {diagnostic result A1, diagnostic result A3}, {diagnostic result A2}}, and the target fault code C1 was reported at 13:21, the target fault code C2 was reported at 13:23, and the target fault code C3 was reported at 13:20. Then, the target diagnostic result {diagnostic result A2} has the highest correlation with the target fault code, followed by the target diagnostic result {diagnostic result A1, diagnostic result A2}, and finally the target diagnostic result {diagnostic result A1, diagnostic result A3}. Thus, the generated target diagnostic result sequence is {{diagnostic result A2}, {diagnostic result A1, diagnostic result A2}, {diagnostic result A1, diagnostic result A3}}.

[0095] In this embodiment, by determining the correlation between each target diagnostic result and the target fault code based on the reporting time order of each target fault code, the diagnostic results of the current vehicle fault can be sorted based on the reporting time of the target fault code, so that the direct and indirect diagnostic results of the current vehicle fault can be obtained.

[0096] Figure 8 This is a flowchart illustrating yet another vehicle fault diagnosis method provided in this disclosure. Figure 8 for Figure 7 Based on the illustrated embodiment, before executing S102', the following is also included:

[0097] S1013, Based on the frequency of each diagnostic result in the multiple diagnostic result sets, determine that the frequency of each diagnostic result does not meet the preset condition.

[0098] Optionally, the preset condition can be that at least one frequency among all diagnostic results in multiple diagnostic result sets is greater than or equal to a preset frequency. If the preset condition is met, it means that at least one diagnostic result among all diagnostic results has a frequency greater than or equal to the preset frequency. If the preset condition is not met, it means that no diagnostic result among all diagnostic results has a frequency greater than or equal to the preset frequency, that is, the frequency of each diagnostic result is less than the preset frequency.

[0099] If the preset conditions are not met, the correlation between each target diagnosis result and the target fault code is determined based on the time sequence of each target fault code report; if the preset conditions are met, the correlation between each target diagnosis result and the target fault code is determined based on the frequency of each target diagnosis result in the target diagnosis result set.

[0100] Figure 9 This is a flowchart illustrating yet another vehicle fault diagnosis method provided in this disclosure. Figure 9 for Figure 2Based on the illustrated embodiment, another possible implementation of S101 is described in detail below:

[0101] S301, for each target fault code, determine the set of diagnostic results for each target fault code based on the fault knowledge graph and the priority of the diagnostic results in the fault knowledge graph.

[0102] The set of diagnostic results includes at least one diagnostic result.

[0103] The target fault code can be a circuit-type target fault code, used to indicate faults in the communication bus system. Circuit-type target fault codes begin with the character "U". The diagnostic nodes in the fault knowledge graph include the correspondence between target fault codes and diagnostic results. Diagnostic results can include at least one of three levels: Level 1, Level 2, and Level 3. Level 1 diagnostic results have higher priority than Level 2, and Level 2 diagnostic results have higher priority than Level 3. For example, a Level 1 diagnostic result could be a bus diagnostic result, a Level 2 diagnostic result could be a child node diagnostic result, and a Level 3 diagnostic result could be a leaf node diagnostic result.

[0104] Based on prior knowledge of the circuit topology, the priority of diagnostic results in the fault knowledge graph is determined. According to each target fault code, the first-level diagnostic result corresponding to the target fault code is first determined in the fault knowledge graph. After determining the first-level diagnostic result, the second-level diagnostic result corresponding to the target fault code is determined in the fault knowledge graph. After determining the second-level diagnostic result, the third-level diagnostic result corresponding to the target fault code is finally determined in the fault knowledge graph. In this way, the set of diagnostic results for the target fault code can be determined, and the set of diagnostic results may include at least one of the first-level, second-level, and third-level diagnostic results.

[0105] For example, the diagnostic result set for target fault code U1 is {diagnostic result L2, diagnostic result L3}, the diagnostic result set for target fault code U2 is {diagnostic result L1, diagnostic result L2, diagnostic result L3}, and the diagnostic result set for target fault code U3 is {diagnostic result L3}. Here, diagnostic result L1 is a first-level diagnostic result, diagnostic result L2 is a second-level diagnostic result, and diagnostic result L3 is a third-level diagnostic result.

[0106] S302, for each target fault code, determine the diagnostic result set as the target diagnostic result set corresponding to each target fault code.

[0107] Each target fault code corresponds to a set of diagnostic results. This set of diagnostic results can be used as the target diagnostic result set for each target fault code. In this way, multiple target diagnostic result sets can be determined for multiple target fault codes. Each target diagnostic result set includes at least one target diagnostic result, which is the diagnostic result.

[0108] For example, based on the above embodiments, the target diagnostic result set for target fault code U1 is {target diagnostic result L2, target diagnostic result L3}, the target diagnostic result set for target fault code U2 is {target diagnostic result L1, target diagnostic result L2, target diagnostic result L3}, and the target diagnostic result set for target fault code U3 is {target diagnostic result L3}.

[0109] In this embodiment, for each target fault code, a set of diagnostic results is determined based on the fault knowledge graph and the priority of diagnostic results in the fault knowledge graph. The set of diagnostic results includes at least one diagnostic result. For each target fault code, a set of diagnostic results is determined as the target diagnostic result set corresponding to each target fault code. In this way, the target diagnostic result set of each target fault code is determined based on the priority of diagnostic results. This not only determines the direct diagnostic result of the vehicle fault, but also the related diagnostic results, thereby enabling a comprehensive diagnosis of the vehicle fault.

[0110] Figure 10 This is a flowchart illustrating yet another vehicle fault diagnosis method provided in this disclosure. Figure 10 for Figure 9 Based on the illustrated embodiment, before executing S103, the following steps are also included:

[0111] S102” determines the correlation between each target diagnosis result and its corresponding target fault code in each target diagnosis result set based on the priority of all target diagnosis results in each target diagnosis result set.

[0112] The target diagnostic result set is the diagnostic result set, and the target diagnostic results within the target diagnostic result set are the diagnostic results within the diagnostic result set. The priority of the target diagnostic results is the priority of the diagnostic results within the aforementioned diagnostic result set. Based on the order in which the diagnostic results in the target diagnostic result set are determined, the relevance of each target diagnostic result in the target diagnostic result set to its corresponding target fault code can be determined. As mentioned above, the first-level diagnostic results are determined first, followed by the second-level diagnostic results, and finally the third-level diagnostic results. Therefore, based on the order in which the diagnostic results are determined, the relevance ranking of each target diagnostic result in the target diagnostic result set can be determined.

[0113] For example, based on the above embodiments, in the target diagnostic result set {target diagnostic result L2, target diagnostic result L3}, target diagnostic result L2 is determined first, then target diagnostic result L3 is determined. In the target diagnostic result set {target diagnostic result L1, target diagnostic result L2, target diagnostic result L3}, target diagnostic result L1 is determined first, then target diagnostic result L2 is determined, and finally target diagnostic result L3 is determined. The target diagnostic result set {target diagnostic result L3} only determines one target diagnostic result L3. Therefore, it can be determined that in the target diagnostic result set for target fault code U1, the correlation between target diagnostic result L2 and target fault code U1 is greater than the correlation between target diagnostic result L3 and target fault code U1; in the target diagnostic result set for target fault code U2, the correlation between target diagnostic result L1 and target fault code U2 is greater than the correlation between target diagnostic result L2 and target fault code U2, and the correlation between target diagnostic result L2 and target fault code U2 is greater than the correlation between target diagnostic result L3 and target fault code U2. Thus, the target diagnostic result sequence corresponding to the determined target fault code U1 is {target diagnostic result L2, target diagnostic result L3}, the target diagnostic result sequence corresponding to the target fault code U2 is {target diagnostic result L1, target diagnostic result L2, target diagnostic result L3}, and the target diagnostic result sequence corresponding to the target fault code U3 is {target diagnostic result L3}.

[0114] In this embodiment, by determining the correlation between each target diagnostic result and its corresponding target fault code in each target diagnostic result set according to the priority of all target diagnostic results in each target diagnostic result set, it is possible to sort each target diagnostic result in all target diagnostic result sets based on the priority of the target diagnostic results, so as to obtain the direct and indirect diagnostic results of the current vehicle fault.

[0115] Figure 11 This is a flowchart illustrating yet another vehicle fault diagnosis method provided in this disclosure. Figure 11 for Figure 2 Based on the illustrated embodiment, it also includes:

[0116] S104, input the multiple target fault codes into the trained model, and output the diagnostic result sequence of the multiple target fault codes based on the trained model.

[0117] The diagnostic results in the diagnostic result sequence are sorted according to their probability values.

[0118] The model has three layers: an input layer, a hidden layer, and an output layer. The number of neurons in the input layer is equal to the total number of fault codes, the number of neurons in the output layer is equal to the total number of diagnostic results, and the number of neurons in the hidden layer is 256. Diagnostic results from the fault knowledge graph are used as labels, and fault codes from the fault knowledge graph are used as training features. The dimension vector L representing the number of neurons in the input layer is initialized to 0. Based on a numerical dictionary, both the input fault codes and diagnostic results are numerically processed, and the corresponding positions in L are changed from 0 to 1, resulting in the final vector L1. This vector is then used to train the model, resulting in the trained model.

[0119] Multiple target fault codes are input into the trained model, which can output multiple diagnostic results. Each diagnostic result corresponds to a different probability value. Based on the order of probability values ​​from largest to smallest, a sequence of multiple diagnostic results can be determined. The diagnostic result ranked first in the sequence is the direct diagnostic result and related diagnostic results of the current vehicle fault.

[0120] In this embodiment, by inputting multiple target fault codes into a trained model, and outputting a sequence of diagnostic results for multiple target fault codes based on the trained model, the diagnostic results in the sequence are sorted according to probability values, thereby obtaining the direct diagnostic results of the current vehicle fault and related diagnostic results, and verifying the target diagnostic result sequence obtained in the above embodiment.

[0121] This disclosure also provides a vehicle fault diagnosis device. Figure 12 This is a schematic diagram of the structure of a vehicle fault diagnosis device provided in this disclosure, such as... Figure 12 As shown, the vehicle fault diagnosis device includes:

[0122] The determination module 210 is used to determine a target diagnostic result set based on a fault knowledge graph and multiple target fault codes. The target diagnostic result set includes multiple target diagnostic results, and the fault knowledge graph includes the correspondence between multiple fault codes and diagnostic results.

[0123] The sequence generation module 220 is used to generate a target diagnosis result sequence based on the correlation between each target diagnosis result and the target fault code in the target diagnosis result set.

[0124] Optionally, the determining module 210 is further configured to, for each target fault code, determine a set of diagnostic results based on the fault knowledge graph, wherein the set of diagnostic results includes at least one diagnostic result; and determine the target diagnostic result set based on the frequency of occurrence of each diagnostic result in the multiple sets of diagnostic results for the multiple target fault codes.

[0125] Optionally, the determining module 210 is further configured to determine the correlation between each target diagnostic result and the target fault code based on the frequency corresponding to each target diagnostic result in the target diagnostic result set.

[0126] Optionally, the determining module 210 is further configured to determine the correlation between the diagnostic results of each target and the target fault code based on the time sequence of the reporting of each target fault code.

[0127] Optionally, the determining module 210 is further configured to determine, based on the frequency of each diagnostic result in the plurality of diagnostic result sets, that the frequency of each diagnostic result does not meet a preset condition.

[0128] Optionally, the determining module 210 is further configured to determine the union of the multiple diagnostic result sets as the target diagnostic result set if the frequency of each diagnostic result meets a preset condition; and to determine the multiple diagnostic result sets as the target diagnostic result set if the frequency of each diagnostic result does not meet the preset condition.

[0129] Optionally, the preset condition is that at least one frequency in the frequencies corresponding to each of the multiple diagnostic result sets is greater than or equal to a preset frequency.

[0130] Optionally, the determining module 210 is further configured to, for each target fault code, determine a set of diagnostic results for each target fault code based on the fault knowledge graph and the priority of diagnostic results in the fault knowledge graph, wherein the set of diagnostic results includes at least one diagnostic result; and for each target fault code, determine the set of diagnostic results as the target diagnostic result set corresponding to each target fault code.

[0131] Optionally, the determining module 210 is further configured to determine the correlation between each target diagnostic result in each target diagnostic result set and the corresponding target fault code based on the priority of all target diagnostic results in each target diagnostic result set.

[0132] Optionally, the diagnostic results in the fault knowledge graph include at least one of the following: controller, fault setting conditions, fault recovery conditions, fault cause, and maintenance suggestions.

[0133] Optionally, the vehicle fault diagnosis device may also include:

[0134] The result sequence module is used to input the multiple target fault codes into the trained model, and output a diagnostic result sequence of the multiple target fault codes based on the trained model. The diagnostic results in the diagnostic result sequence are sorted according to their probability values.

[0135] The vehicle fault diagnosis device provided in this disclosure can be used to perform the steps of the above method embodiments. Its implementation principle and technical effect are similar, and will not be repeated here.

[0136] This disclosure also provides an electronic device, including: a processor, the processor being configured to execute a computer program stored in a memory, the computer program being executed by the processor to implement the steps of the above method embodiments.

[0137] This disclosure also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method embodiments.

[0138] This disclosure also provides a computer program product that, when run on a computer, causes the computer to perform the steps of the above-described method embodiments.

[0139] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0140] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A vehicle fault diagnosis method, characterized in that, include: For each target fault code, a set of diagnostic results is determined based on the fault knowledge graph. The set of diagnostic results includes at least one diagnostic result, and the fault knowledge graph includes the correspondence between multiple fault codes and diagnostic results. A target diagnostic result set is determined based on the frequency of occurrence of each diagnostic result in multiple diagnostic result sets of multiple target fault codes, wherein the target diagnostic result set includes multiple target diagnostic results; Based on the frequency of each target diagnostic result in the target diagnostic result set, the correlation between each target diagnostic result and the target fault code is determined; Based on the correlation between each target diagnostic result and the target fault code, a target diagnostic result sequence is generated.

2. The method according to claim 1, characterized in that, Before generating the target diagnostic result sequence based on the correlation between each target diagnostic result and the target fault code in the target diagnostic result set, the method further includes: Based on the time sequence of the reported fault codes of each target, the correlation between the diagnostic results of each target and the fault codes of each target is determined.

3. The method according to claim 2, characterized in that, Before determining the correlation between the diagnostic results of each target and the target fault code based on the reporting time sequence of each target fault code, the method further includes: Based on the frequency of each diagnostic result in the multiple diagnostic result sets, it is determined that the frequency of each diagnostic result does not meet the preset condition.

4. The method according to claim 1, characterized in that, The step of determining the target diagnostic result set based on the frequency of occurrence of each diagnostic result in the multiple diagnostic result sets of the multiple target fault codes includes: If the frequency of each diagnostic result meets a preset condition, the union of the multiple diagnostic result sets is determined as the target diagnostic result set; If the frequency of each diagnostic result does not meet the preset condition, the set of multiple diagnostic results is determined as the target diagnostic result set.

5. The method according to claim 3 or 4, characterized in that, The preset condition is that at least one frequency in the frequency corresponding to each of the multiple diagnostic result sets is greater than or equal to the preset frequency.

6. The method according to claim 1, characterized in that, The step of determining the target diagnostic result set based on the fault knowledge graph and multiple target fault codes includes: For each target fault code, a set of diagnostic results for each target fault code is determined based on the fault knowledge graph and the priority of diagnostic results in the fault knowledge graph, wherein the set of diagnostic results includes at least one diagnostic result. For each target fault code, the diagnostic result set is determined as the target diagnostic result set corresponding to each target fault code.

7. The method according to claim 6, characterized in that, Before generating the target diagnostic result sequence based on the correlation between each target diagnostic result and the target fault code in the target diagnostic result set, the following steps are also included: Based on the priority of all target diagnostic results within each target diagnostic result set, the correlation between each target diagnostic result in each target diagnostic result set and its corresponding target fault code is determined.

8. The method according to claim 1, characterized in that, The diagnostic results in the fault knowledge graph include at least one of the following: controller, fault setting conditions, fault recovery conditions, fault cause, and maintenance suggestions.

9. The method according to claim 1, characterized in that, Also includes: The multiple target fault codes are input into the trained model, and a diagnostic result sequence of the multiple target fault codes is output based on the trained model. The diagnostic results in the diagnostic result sequence are sorted according to their probability values.

10. A vehicle fault diagnosis device, characterized in that, include: The determination module is used to, for each target fault code, determine a set of diagnostic results based on a fault knowledge graph, wherein the set of diagnostic results includes at least one diagnostic result, and the fault knowledge graph includes the correspondence between multiple fault codes and diagnostic results; determine a set of target diagnostic results based on the frequency of occurrence of each diagnostic result in multiple sets of diagnostic results for multiple target fault codes, wherein the set of target diagnostic results includes multiple target diagnostic results; and determine the correlation between each target diagnostic result and the target fault code based on the frequency corresponding to each target diagnostic result in the set of target diagnostic results. The sequence generation module is used to generate a sequence of target diagnostic results based on the correlation between each target diagnostic result and the target fault code.

11. An electronic device, characterized in that, include: A processor for executing a computer program stored in a memory, wherein the computer program, when executed by the processor, implements the steps of the method according to any one of claims 1-9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-9.

Images