Vehicle fault tracing method, device and equipment, storage medium and program product

Abstract

The invention provides a vehicle fault tracing method, device and equipment, a storage medium and a program product, and the method comprises the steps: carrying out the word segmentation of fault description information, and obtaining a plurality of vocabularies corresponding to the fault description information; performing similarity calculation on each vocabulary in the work requirement ontology vector and each maintenance knowledge in a maintenance knowledge ontology vector in the knowledge graph to obtain a pre-pushed maintenance knowledge set; and filtering the maintenance knowledge in the pre-pushed maintenance knowledge set according to the maintenance knowledge model of the maintenance technician to obtain a pushed maintenance knowledge set. In other words, fault maintenance knowledge needed by maintenance technicians can be rapidly obtained according to the knowledge graph related to the vehicle faults, it is not needed to spend much time in the complex troubleshooting process, and the maintenance efficiency is improved to a certain degree.

Description

Technical Field

[0001] The present application relates to the technical field of vehicles, and specifically to a method, device, equipment, storage medium and program product for fault tracing of a vehicle. Background Art

[0002] The engine in a vehicle is the "heart" of the vehicle, which can convert the chemical energy of fuel into mechanical energy to drive the vehicle to run. The role of the engine determines that the number of components that make up the engine is numerous and the structure is complex. Therefore, the maintenance and repair of the engine are particularly important.

[0003] However, due to the complexity of the engine structure, during the process of fault repair of the engine, the repair technician may need to carry out a complex and cumbersome troubleshooting process, which takes a long time and the repair efficiency is low.

[0004] It should be noted that the information disclosed in the background art part of the present application is only intended to deepen the understanding of the general background art of the present application, and should not be regarded as an admission or any form of implication that this information constitutes the prior art known to those skilled in the art. Summary of the Invention

[0005] The present application provides a method, device, equipment, storage medium and program product for fault tracing of a vehicle, which is beneficial to solving the problem of low repair efficiency that may be caused by the long fault troubleshooting time in the prior art.

[0006] In a first aspect, an embodiment of the present application provides a method for fault tracing of a vehicle, including: Performing word segmentation processing on the fault description information to obtain a plurality of words corresponding to the fault description information, and the plurality of words are used to form a work requirement ontology vector; Calculating the similarity between each word in the work requirement ontology vector and each maintenance knowledge in the maintenance knowledge ontology vector in the knowledge graph to obtain a pre-pushed maintenance knowledge set, and the pre-pushed maintenance knowledge set includes the maintenance knowledge with the highest similarity to each word; Filtering the maintenance knowledge in the pre-pushed maintenance knowledge set according to the maintenance knowledge model of the repair technician to obtain a pushed maintenance knowledge set, and the maintenance knowledge in the pushed maintenance knowledge set matches the maintenance knowledge requirements of the maintenance knowledge model.

[0007] In a possible implementation manner, the performing word segmentation processing on the fault description information to obtain a plurality of words corresponding to the fault description information includes: Splitting the fault description information according to a preset splitting rule to obtain a plurality of maintenance sub-tasks; Perform word segmentation on each of the maintenance sub - tasks to obtain multiple words corresponding to each of the maintenance sub - tasks.

[0008] In a possible implementation manner, the splitting rules include at least one of the following rules: Special rule, where the special rule includes that no splitting process is required for maintenance work with special requirements; Specification rule, where the specification rule includes that no splitting process is required for maintenance work with specification requirements; Step rule, where the step rule includes splitting the maintenance work according to the maintenance steps; Non - splittable rule, where the non - splittable rule includes splitting the maintenance work into non - splittable maintenance sub - tasks.

[0009] In a possible implementation manner, the performing word segmentation on the fault description information to obtain multiple words corresponding to the fault description information includes: Perform word segmentation on the fault description information to obtain multiple pre - selected words corresponding to the fault description information; Perform semantic extension on each of the pre - selected words to obtain multiple words corresponding to the fault description information.

[0010] In a possible implementation manner, the filtering the maintenance knowledge in the pre - pushed maintenance knowledge set according to the maintenance knowledge model of the maintenance technician to obtain the pushed maintenance knowledge set includes: Calculate the similarity between each piece of maintenance knowledge in the pre - pushed maintenance knowledge set and the maintenance knowledge requirements in the maintenance knowledge model respectively to obtain the similarity calculation result corresponding to each piece of maintenance knowledge in the pre - pushed maintenance knowledge set; Determine the pushed maintenance knowledge set according to the similarity calculation result corresponding to each piece of maintenance knowledge in the pre - pushed maintenance knowledge set, where the similarity calculation result corresponding to each piece of maintenance knowledge in the pushed maintenance knowledge set is greater than or equal to a preset similarity threshold.

[0011] In a possible implementation manner, the maintenance knowledge model includes: The first maintenance knowledge requirement, which is used to represent the maintenance knowledge requirements of high - efficiency and rapidity; The second maintenance knowledge requirement, which is used to represent the long - term maintenance knowledge requirements.

[0012] In a possible implementation manner, the similarity calculation formula includes: Where R is the maintenance knowledge model; d jThe j-th maintenance knowledge in the pre-pushed maintenance knowledge set; Sim(d j , R) is the similarity between the maintenance knowledge d j and the maintenance knowledge requirements in the maintenance knowledge model R; W j (C k ) is the proportion of the k-th ontology concept C k in the j-th maintenance knowledge; W R (C k ) is the proportion of the ontology concept C k in the maintenance knowledge model R; q is the number of ontology concepts in the maintenance knowledge d j .

[0013] Second, an embodiment of the present application provides a fault tracing device for a vehicle, including: A word segmentation module, configured to perform word segmentation processing on the fault description information to obtain a plurality of words corresponding to the fault description information, and the plurality of words are used to form a work requirement ontology vector; A pre-pushed maintenance knowledge set acquisition module, configured to calculate the similarity between each word in the work requirement ontology vector and each maintenance knowledge in the maintenance knowledge ontology vector in the knowledge graph, and obtain a pre-pushed maintenance knowledge set, where the pre-pushed maintenance knowledge set includes the maintenance knowledge with the highest similarity to each word; A pushed maintenance knowledge set acquisition module, configured to filter the maintenance knowledge in the pre-pushed maintenance knowledge set according to the maintenance knowledge model of the maintenance technician, and obtain a pushed maintenance knowledge set, where the maintenance knowledge in the pushed maintenance knowledge set matches the maintenance knowledge requirements of the maintenance knowledge model.

[0014] Third, an embodiment of the present application provides an electronic device, including: A processor; A memory; And a computer program, where the computer program is stored in the memory, and when the computer program is executed by the processor, the electronic device is caused to execute the method according to any one of the first aspects.

[0015] Fourth, an embodiment of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of the first aspects is implemented.

[0016] Fifth, an embodiment of the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, the method according to any one of the first aspects is implemented.

[0017] In the embodiments of the present application, fault repair knowledge required by maintenance technicians can be quickly obtained according to the knowledge graph related to vehicle faults, without spending a lot of time on complex and cumbersome troubleshooting processes, which improves the repair efficiency to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0019] Figure 1 It is a schematic flow chart of a fault tracing method for a vehicle provided by an embodiment of the present application.

[0020] Figure 2 It is a schematic diagram of the interface of a vehicle fault tracing system provided by an embodiment of the present application.

[0021] Figure 3 It is a schematic flow chart of another fault tracing method for a vehicle provided by an embodiment of the present application.

[0022] Figure 4 It is a schematic flow chart of a method for constructing a knowledge graph provided by an embodiment of the present application.

[0023] Figure 5 It is a schematic diagram of another interface of a vehicle fault tracing system provided by an embodiment of the present application.

[0024] Figure 6 It is a schematic diagram of another interface of a vehicle fault tracing system provided by an embodiment of the present application.

[0025] Figure 7 It is a schematic structural diagram of a vehicle fault tracing device provided by an embodiment of the present application.

[0026] Figure 8 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] In order to better understand the technical solutions of the present application, the embodiments of the present application will be described in detail below with reference to the drawings.

[0028] It should be clear that the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application.

[0029] The terms used in the embodiments of the present application are for the purpose of describing specific embodiments only and are not intended to limit the present application. The singular forms "a", "the" and "said" used in the embodiments of the present application and the appended claims are also intended to include the plural forms unless the context clearly dictates otherwise.

[0030] It should be understood that the term "and / or" used herein is merely an associative relationship describing associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " herein generally represents an "or" relationship between the associated objects before and after.

[0031] The engine in a vehicle is the "heart" of the vehicle, which can convert the chemical energy of fuel into mechanical energy to drive the vehicle. The function of the engine determines that the engine consists of a large number of components with a complex structure. Therefore, the maintenance and repair of the engine are particularly important.

[0032] However, due to the complexity of the engine structure, during the process of fault repair of the engine, the repair technician may need to carry out a complex and cumbersome troubleshooting process, which takes a long time and results in low repair efficiency.

[0033] To address the above problems, in the embodiments of the present application, according to the knowledge graph related to vehicle faults, the fault repair knowledge required by the repair technician can be quickly obtained, without spending a lot of time on a complex and cumbersome troubleshooting process, thereby improving the repair efficiency to a certain extent.

[0034] Specifically, it will be described in detail below in conjunction with the drawings and specific embodiments.

[0035] See Figure 1 , which is a schematic flowchart of a vehicle fault tracing method provided by an embodiment of the present application. As Figure 1 shown, the method specifically includes the following steps.

[0036] Step S101: Perform word segmentation on the fault description information to obtain a plurality of words corresponding to the fault description information.

[0037] In the embodiments of the present application, the fault description information is the content input by the repair technician through the display interface. For example, [gasoline engine] or [the engine shakes severely after stepping on the accelerator pedal hard when going uphill], etc. Of course, the repair technician can input the fault description information in other ways, and the embodiments of the present application do not make specific limitations thereto.

[0038] In practical applications, when the fault description information is relatively complex, it may lead to inaccurate semantic understanding, and further may result in inaccurate maintenance knowledge output. Therefore, in the embodiments of the present application, the fault description information can be segmented to obtain multiple words corresponding to the fault description information.

[0039] Specifically, the fault description information is segmented according to a preset segmentation rule to obtain multiple maintenance sub-tasks; each maintenance sub-task is segmented to obtain multiple words corresponding to each maintenance sub-task.

[0040] In the embodiments of the present application, the segmentation rules include at least one of the following rules: special rule, the special rule includes that there is no need to segment the maintenance work with special requirements; specification rule, the specification rule includes that there is no need to segment the maintenance work with specification requirements; step rule, the step rule includes segmenting the maintenance work according to the maintenance steps; non-segmentable rule, the non-segmentable rule includes segmenting the maintenance work into non-segmentable maintenance sub-tasks.

[0041] In addition, each maintenance sub-task can be segmented using parts of speech, and the weights corresponding to the subject, predicate, and object are determined for each separated word. The obtained words can be expressed as: {(subject, weight), (predicate, weight), (object, weight)} = {(a, aw), (b, bw), (c, cw)}, and it is necessary to satisfy aw + bw + cw = 1. Among them, nouns and verbs mostly represent the semantics of the subject, predicate, and object. Otherwise, the corresponding weight is set to null.

[0042] In practical applications, the fault description information may include fuzzy or simplified expressions. Through segmenting the fault description information, the multiple words obtained may not be able to more accurately match the maintenance knowledge in the knowledge graph. In addition, the same word may have multiple representation methods in the knowledge graph. Only matching the maintenance knowledge based on the multiple words after segmentation may result in not being able to obtain all the maintenance knowledge corresponding to the fault description information.

[0043] In a possible implementation manner, segmenting the fault description information to obtain multiple words corresponding to the fault description information includes: segmenting the fault description information to obtain multiple preselected words corresponding to the fault description information; extending the meaning of each preselected word to obtain multiple words corresponding to the fault description information.

[0044] It can be understood that extending the meaning of a word refers to enhancing semantic understanding by expanding the meaning of the word or introducing related words. By extending the meaning of the preselected words after segmenting the fault description information, the vocabulary can be expanded and enriched, the query intention corresponding to the fault description information can be better understood, and the maintenance knowledge in the knowledge graph can be more accurately matched.

[0045] In the embodiments of the present application, multiple words are used to form a work requirement ontology vector. It can be understood that the words are represented by ontology vectors, and the work requirement ontology vector X = {X 1 , X 2 , …, X n}, where X i is the ontology vector corresponding to the i-th word, 1 ≤ i ≤ n, and n is the number of words.

[0046] Step S102: Calculate the similarity between each word in the work requirement ontology vector and each maintenance knowledge in the maintenance knowledge ontology vector in the knowledge graph to obtain a pre-pushed maintenance knowledge set.

[0047] It can be understood that the maintenance knowledge ontology vector Y = {Y 1 , Y 2 , …, Y m} in the knowledge graph, where Y l is the ontology vector corresponding to the l-th maintenance knowledge in the maintenance knowledge ontology vector in the knowledge graph, 1 ≤ l ≤ m, and m is the number of maintenance knowledge in the knowledge graph.

[0048] In the embodiments of the present application, a knowledge graph about vehicle faults is constructed and visualized in the vehicle fault tracing system. The specific content about "knowledge graph and vehicle fault tracing system" will be described below and will not be elaborated here.

[0049] In the embodiments of the present application, a similarity matrix of the work requirement ontology vector X and the maintenance knowledge ontology vector Y in the knowledge graph can be constructed to calculate the similarity between each word in the work requirement ontology vector and each maintenance knowledge in the maintenance knowledge ontology vector. The similarity matrix is: .

[0050] Among them, X i Y l represents the similarity between X i and Y l . For the convenience of description, e is used to represent X i and f is used to represent Y l in the following text.

[0051] Specifically, the similarity Sim(X i , Y l ) between X i and Y l can be expressed as Sim(e, f): .

[0052] Among them, the set E of the inherent properties of e is E = {Te 1 , Te 2 , …, Te s}, and the set F of the inherent properties of f is F = {Tf 1 , Tf 2 , …, Tf s}; |E∩F| represents the number of inherent properties that e and f have in common; |E - F| represents the number of inherent properties that only e has and f does not have; |F - E| represents the number of inherent properties that only f has and e does not have; Len(e, f) represents the depth between e and f, that is, the ratio of the number of inherent properties that e and f both have to the sum of all inherent properties of e and f.

[0053] As described above, according to the similarity matrix of the ontology vector X of the work requirements and the ontology vector Y of the maintenance knowledge in the knowledge graph, the similarity between each vocabulary in the ontology vector of the work requirements and each piece of maintenance knowledge in the ontology vector of the maintenance knowledge in the knowledge graph can be obtained. For each vocabulary in the ontology vector of the work requirements, by selecting the piece of maintenance knowledge corresponding to the maximum similarity value, the maintenance knowledge corresponding to each vocabulary can be obtained, and thus the pre-push maintenance knowledge set can be obtained.

[0054] It can be understood that the pre-push maintenance knowledge set includes the piece of maintenance knowledge with the highest similarity to each vocabulary. In the embodiment of the present application, the pre-push maintenance knowledge set is represented as D = {d 1 , d 2 , …, d n’}, which is marked through the feature vector space T = {t 1 , t 2 , …, t m’}. At this time, the j-th piece of maintenance knowledge d j in the pre-push maintenance knowledge set = {W 1j , W 2j , …, W m’j}, 1 ≤ j ≤ n’, where n’ is the number of pieces of maintenance knowledge. Among them, W pj is the proportion of the j-th piece of maintenance knowledge d j to the p-th feature word t p in the feature vector space, 1 ≤ p ≤ m’, and m’ is the number of feature words.

[0055] Furthermore, the feature words in the feature vector space T = {t1, t2, …, t m’} are matched with the ontology in the knowledge graph. At this time, T = {t 1 , t 2 , …, t m’} can be changed into the set C of ontology concepts = {C 1 , C 2, …, C q}。Then, taking the ontology concept as the retrieval keyword, a corresponding semantic vector is generated in the maintenance knowledge vector space. The k-th ontology concept C k in the maintenance knowledge d j has a proportional value W j (C k ), where 1 ≤ k ≤ q and q is the number of ontology concepts. At this time, the semantic vector of the maintenance knowledge d j is {W j (C 1 ), W j (C 2 ), …, W j (C q )}.

[0056] Among them, , freq(C kj ) is the total number of times the ontology concept C k is indexed in the maintenance knowledge d j , is the maximum value of the total number of times the ontology concept is indexed in the maintenance knowledge d j , that is, the total number of times the ontology concept C r is indexed in the maintenance knowledge d j freq(C rj ), where 1 ≤ r ≤ q, and n(C k ) is the number of times the ontology concept C k appears in all maintenance knowledge.

[0057] Step S103: Filter the maintenance knowledge in the pre-pushed maintenance knowledge set according to the maintenance knowledge model of the maintenance technician to obtain the pushed maintenance knowledge set.

[0058] In practical applications, different maintenance technicians may have different maintenance knowledge requirements. If each maintenance technician only repairs vehicle faults based on the pre-pushed maintenance knowledge set, it may not meet the needs of the maintenance technician. Therefore, the maintenance knowledge in the pre-pushed maintenance knowledge set can be filtered according to the maintenance knowledge requirements of the maintenance technician, so as to obtain the maintenance knowledge that can meet the needs of the maintenance technician.

[0059] In the embodiment of the present application, a login interface is set in the vehicle fault tracing system, and each maintenance technician corresponds to an account. The vehicle fault tracing system can establish a maintenance knowledge model of the maintenance technician corresponding to the account.

[0060] See Figure 2 , which is a schematic diagram of an interface of a vehicle fault tracing system provided by an embodiment of the present application. As Figure 2As shown, the login interface of the vehicle fault tracing system includes an input module for account and password, a module for selecting the identity of the login person, and modules for login button and registration button. When a maintenance technician needs to repair a vehicle, the technician inputs the account, password, and the identity of the login person in the input module for account and password and the module for selecting the identity of the login person respectively, and clicks the login button to enter the system interface of the vehicle fault tracing system. If the maintenance technician has not registered an account, the technician can click the registration button to register an account. The specific content of the "system interface of the vehicle fault tracing system" will be described below and will not be elaborated here.

[0061] In the embodiment of the present application, the maintenance knowledge model includes: a first maintenance knowledge requirement, which is used to represent efficient and rapid maintenance knowledge requirements; a second maintenance knowledge requirement, which is used to represent long-term maintenance knowledge requirements.

[0062] It can be understood that the efficient and rapid maintenance knowledge requirements can enable the maintenance technician to meet the requirements by searching examples, viewing historical maintenance steps, and paying attention to the matters specially prompted by the vehicle fault tracing system. The long-term maintenance knowledge requirements include the efficient and rapid maintenance knowledge requirements, and can become long-term requirements with the introduction, promotion of new technologies and the passage of time.

[0063] It should be noted that the maintenance knowledge in the pushed maintenance knowledge set matches the maintenance knowledge requirements of the maintenance knowledge model.

[0064] See Figure 3 , which is a schematic flowchart of another vehicle fault tracing method provided by the embodiment of the present application. As Figure 3 shown, based on the embodiment shown in Figure 1 , step S103 specifically includes the following steps.

[0065] Step S1031: Calculate the similarity between each maintenance knowledge in the pre-pushed maintenance knowledge set and the maintenance knowledge requirements in the maintenance knowledge model respectively, and obtain the similarity calculation result corresponding to each maintenance knowledge in the pre-pushed maintenance knowledge set.

[0066] In the embodiment of the present application, the similarity calculation formula between maintenance knowledge and maintenance knowledge requirements is: where R is the maintenance knowledge model; d j is the jth maintenance knowledge in the pre-pushed maintenance knowledge set; Sim(d j , R) is the similarity between the maintenance knowledge d j and the maintenance knowledge requirements in the maintenance knowledge model R; W j (C k)(j) is the proportion of the k-th ontology concept C in the j-th maintenance knowledge k ; W R (C k ) is the proportion of the ontology concept C in the maintenance knowledge model R k ; q is the number of ontology concepts in the maintenance knowledge d j .

[0067] Step S1032: Determine the push maintenance knowledge set according to the similarity calculation results corresponding to each maintenance knowledge in the pre-push maintenance knowledge set.

[0068] In the embodiment of the present application, the similarity calculation results corresponding to each maintenance knowledge in the push maintenance knowledge set are greater than or equal to a preset similarity threshold.

[0069] It can be understood that after obtaining the similarity calculation results corresponding to each maintenance knowledge in the pre-push maintenance knowledge set according to the above similarity calculation formula of the maintenance knowledge and the maintenance knowledge requirements, it is determined whether the similarity calculation results corresponding to each maintenance knowledge are greater than or equal to a preset similarity threshold. If the similarity calculation result corresponding to the maintenance knowledge is greater than or equal to the preset similarity threshold, then push the maintenance knowledge.

[0070] In the embodiment of the present application, by calculating the similarity between the maintenance knowledge and the maintenance knowledge requirements, the maintenance knowledge with a higher similarity to the maintenance knowledge requirements can be accurately determined, and then the maintenance knowledge that meets the needs of the maintenance technician can be recommended to the maintenance technician.

[0071] In the embodiment of the present application, the fault maintenance knowledge required by the maintenance technician can be quickly obtained according to the knowledge graph related to the vehicle fault, without spending a lot of time on a complex and cumbersome troubleshooting process, which improves the maintenance efficiency to a certain extent.

[0072] In practical applications, before obtaining the push maintenance knowledge set through the knowledge graph, it is necessary to first construct a knowledge graph of vehicle faults.

[0073] See Figure 4 , which is a schematic flowchart of a process for constructing a knowledge graph provided by an embodiment of the present application. As shown in Figure 4, it specifically includes the following steps.

[0074] Step S401: Collect fault maintenance cases.

[0075] In the embodiments of the present application, in order to construct a knowledge graph of vehicle faults, it is necessary to first collect vehicle fault repair cases. The fault repair cases generally include but are not limited to fault phenomena, fault troubleshooting steps, fault cause location, repair technicians, repair tools, repair locations, repair methods, and repair effects, etc. After collecting the fault repair cases, it is necessary to analyze the fault repair cases and label the key information, for example, fault phenomena, fault troubleshooting steps, fault cause location, repair technicians, repair tools, repair locations, repair methods, and repair effects, etc.

[0076] Step S402: Perform knowledge extraction.

[0077] In the embodiments of the present application, after collecting and analyzing the fault repair cases, the repair knowledge can be extracted through a deep learning network model. The extracted repair knowledge includes entities, attributes, and relationships. The extracted repair knowledge is usually saved in the form of triples, for example, (entity - relationship - entity), etc.

[0078] Step S403: Perform knowledge fusion.

[0079] In practical applications, there may be duplicate repair knowledge in the repair knowledge obtained by performing knowledge extraction on the fault repair cases. In addition, fault repair cases from different sources may provide inconsistent descriptions of the same repair knowledge, which may lead to inconsistencies in the repair knowledge.

[0080] In the embodiments of the present application, after performing knowledge extraction on the fault repair cases, the entity linking technology is used to perform knowledge fusion on the extracted repair knowledge to eliminate contradictions and ambiguities and make the repair knowledge more standardized.

[0081] Step S404: Perform knowledge processing.

[0082] In practical applications, in the repair knowledge after performing knowledge fusion, there may be missing associations between entities, which may in turn lead to an incomplete knowledge graph.

[0083] In the embodiments of the present application, for the repair knowledge after performing knowledge fusion, through computer reasoning, new associations between entities are established to expand and enrich the knowledge graph.

[0084] Step S405: Perform knowledge storage.

[0085] In the embodiments of the present application, after the fault repair cases of the vehicle are subjected to knowledge extraction, knowledge fusion, and knowledge processing to obtain repair knowledge, the repair knowledge is stored in a graph database and stored in the form of a knowledge graph. Specifically, the repair knowledge is stored in the Neo4j graph database, and in the Neo4j graph database, the constructed knowledge graph can be converted into a JSON file format to facilitate the visualization of the knowledge graph. For the sake of easy understanding, the knowledge graph in the vehicle fault tracing system is shown below.

[0086] It should be noted that when downloading the JSON file, it is necessary to first select a node or relationship to run, and then use the run command to run a second time to download.

[0087] See Figure 5 , which is a schematic diagram of another vehicle fault tracing system interface provided by the embodiments of the present application. As Figure 5 shown, the system interface of the vehicle fault tracing system includes a function module on the left and a display module on the right. Among them, the function module includes a knowledge graph and fault tracing. The function corresponding to the knowledge graph is to display the knowledge graph related to vehicle faults, and the function corresponding to fault tracing is the semantic search function based on the knowledge graph, and semantic search for fault tracing can be performed in the search window under fault tracing. There are 2D knowledge graph and 3D knowledge graph on the upper side of the display module, and maintenance technicians can select different visualization methods to display the knowledge graph.

[0088] In the embodiments of the present application, when a maintenance technician clicks on the knowledge graph in the function module, the display module can display the corresponding visualization information of the knowledge graph. The visualized knowledge graph usually includes nodes corresponding to information such as vehicle fault phenomena, fault causes, and solutions, and the relationships between the nodes (for example, reasons, solutions, and cases, etc.). In addition, it also includes information such as the attribute labels of the nodes. The attribute labels can define the size and color of the nodes, etc. The same type of nodes can use the same attribute labels. As Figure 5 shown, the same type of nodes are distinguished by the same color. The light purple nodes represent fault phenomena, for example, engine shaking, unable to open the throttle valve, gasoline engine fault code... etc.; the light green nodes represent fault causes, for example, ignition wire burning, electronic control system, unable to open normally, sensors, and read with a diagnostic instrument... etc.; the dark green nodes represent solutions, for example, replace the throttle valve, detect the intake system..., remove the spark plug... and check the intake camshaft, etc.; the light pink nodes represent cases, for example, exhaust system blockage, intake system air leakage, and intake camshaft... etc. Of course, the relationships between the nodes can also have attribute labels, which are used to define the size and color of the connections between the nodes, etc.

[0089] It should be noted that the knowledge graph may also include other information, such as fault types, repair tools, etc., which are not specifically elaborated in the embodiments of the present application. In addition, the knowledge graph described in the embodiments of the present application is only a specific implementation manner, and those skilled in the art can set other types of knowledge graphs according to actual needs, and the embodiments of the present application do not make specific limitations thereto.

[0090] In the embodiments of the present application, when a maintenance technician clicks on fault tracing in the function module, a search window is displayed in the display module, and the maintenance technician can enter fault description information in the search window to query the repair knowledge corresponding to the fault description information.

[0091] See Figure 6 , which is a schematic diagram of another vehicle fault tracing system interface provided by the embodiments of the present application. As Figure 6 shown, a text search and a search window are displayed in the display module. When a maintenance technician wants to retrieve repair knowledge related to "gasoline engine", they can enter "gasoline engine" in the search window, and the vehicle fault tracing system will retrieve the repair knowledge related to "gasoline engine" according to the Figure 1 method of the embodiment shown. At this time, the nodes related to "gasoline engine" in the knowledge graph will be displayed more brightly, such as Figure 6 the nodes circled in yellow in, while other nodes are relatively dim. In addition, the specific information of the repair knowledge related to "gasoline engine", "It may be the intake cam position..., so it is decided to replace the intake camshaft", will be displayed in the display module.

[0092] As described above, the vehicle fault tracing system can display the knowledge graph and retrieve the repair knowledge required by the maintenance technician. In practical applications, in order to implement functions such as displaying the knowledge graph and retrieving repair knowledge, a vehicle fault tracing system can be developed.

[0093] In the embodiments of the present application, a vehicle fault tracing system can be constructed based on the Windows interface framework WPF. WPF consists of an editing framework and an engine, and supports a unified language, programming model, and framework. In addition, WPF has a brand-new multimedia interactive user graphical interface, page dynamicization, and strong support for vector graphics, and is also compatible with 3D controls, 2D drawing, and events.

[0094] When building a project for an application, WPF can automatically generate directory files. Among them, App.xaml is the initial file and resource for setting up the application. App.xaml.cs, as the background file of App.xaml, can be edited. Inheriting from System.Windows.Application, it can be compatible with all WPF applications. MainWindow.xaml includes the WPF application interface and the XAML design file. MainWindow.xaml.cs, as the background code file, is used to control MainWindow.xaml. To efficiently arrange classes, through the XAML namespace, the development language can encapsulate functions in the form of classes, and the compiler can accurately distinguish classes with the same name. Among them, the difference between xmlns and xmlns:x is that x is presented in the form of a prefix during use. xmlns is a default namespace, not marked with a prefix. Usually, each xaml file only corresponds to one corresponding default namespace. A complete xaml file must have two namespaces; xmlns:x is an optional corresponding prefix = "namespace description".

[0095] In the embodiment of the present application, first, the XAML language is used to construct the login interface and the system interface, and the login interface and the system interface are designed and laid out; then, the JSON file corresponding to the knowledge graph is imported into Visual StudioCode, the content of the JSON file is read and the corresponding website is generated and run, and this website is embedded in the system interface of the vehicle fault tracing system, so that the visualization display graph can be presented in the vehicle fault tracing system; finally, when a maintenance technician wants to search for the maintenance knowledge he needs, the search content is input at the front end of the vehicle fault tracing system. After the vehicle fault tracing system detects the data input from the front end, the required maintenance knowledge will be returned to the front end.

[0096] Corresponding to the above embodiment, the embodiment of the present application also provides a vehicle fault tracing device.

[0097] See Figure 7 , which is a schematic structural diagram of a vehicle fault tracing device provided by the embodiment of the present application. As Figure 7 shown, the vehicle fault tracing device 700 includes a word segmentation module 701, a pre-push maintenance knowledge set acquisition module 702, and a push maintenance knowledge set acquisition module 703.

[0098] Specifically, the word segmentation module 701 is used to perform word segmentation on the fault description information to obtain multiple words corresponding to the fault description information, and the multiple words are used to form the work requirement ontology vector; the pre-push maintenance knowledge set acquisition module 702 is used to calculate the similarity between each word in the work requirement ontology vector and each maintenance knowledge in the maintenance knowledge ontology vector in the knowledge graph to obtain the pre-push maintenance knowledge set, and the pre-push maintenance knowledge set includes the maintenance knowledge with the highest similarity to each word; the push maintenance knowledge set acquisition module 703 is used to filter the maintenance knowledge in the pre-push maintenance knowledge set according to the maintenance knowledge model of the maintenance technician to obtain the push maintenance knowledge set, and the maintenance knowledge in the push maintenance knowledge set matches the maintenance knowledge requirements of the maintenance knowledge model.

[0099] For the specific content involved in the embodiments of the present application, reference may be made to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0100] Corresponding to the above embodiments, the embodiments of the present application also provide an electronic device.

[0101] See Figure 8 , which is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 8 shown, the electronic device 800 may include: a processor 801, a memory 802, and a communication unit 803. These components communicate through one or more buses. Those skilled in the art can understand that the structure of the electronic device shown in the figure does not constitute a limitation on the embodiments of the present application. It can be a bus structure, a star structure, and can also include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0102] Among them, the communication unit 803 is used to establish a communication channel so that the electronic device can communicate with other devices.

[0103] The processor 801 is the control center of the electronic device, connecting various parts of the entire electronic device through various interfaces and lines, and by running or executing software programs and / or modules stored in the memory 802, and calling data stored in the memory, to execute various functions of the electronic device and / or process data. The processor may be composed of an integrated circuit (IC), for example, it may be composed of a single packaged IC, or may be composed of multiple packaged ICs with the same or different functions connected. For example, the processor 801 may only include a central processing unit (CPU). In the embodiment of the present application, the CPU may be a single computing core or may include multiple computing cores.

[0104] A memory 802 for storing execution instructions of a processor 801. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disc.

[0105] When the execution instructions in the memory 802 are executed by the processor 801, the electronic device 800 is enabled to execute some or all of the steps in the above method embodiments.

[0106] Corresponding to the above embodiments, an embodiment of the present application further provides a computer-readable storage medium. The computer-readable storage medium can store a program. When the program runs, it can control the device where the computer-readable storage medium is located to execute some or all of the steps in the above method embodiments. Specifically, the computer-readable storage medium can be a magnetic disk, an optical disc, a read-only memory (ROM), a random access memory (RAM), etc.

[0107] Corresponding to the above embodiments, an embodiment of the present application further provides a computer program product. The computer program product includes executable instructions. When the executable instructions are executed on a computer, the computer is enabled to execute some or all of the steps in the above method embodiments.

[0108] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships can exist. For example, A and / or B can represent the cases of A existing alone, A and B existing simultaneously, and B existing alone. Where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one of the following" and its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, and c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0109] Those of ordinary skill in the art can realize that the various units and algorithm steps described in the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0110] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0111] In several embodiments provided in this application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The foregoing storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM for short), random access memories (RAM for short), magnetic disks, or optical discs.

[0112] The above are only the specific implementation manners of this application. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application and should be covered by the protection scope of this application. The protection scope of this application shall be subject to the protection scope of the claims.

Claims

1. A vehicle fault tracing method, characterized in that: include: Performing word segmentation processing on the fault description information to obtain a plurality of words corresponding to the fault description information, wherein the plurality of words are used to form a work requirement ontology vector; Calculate the similarity between each of the words in the work requirement ontology vector and each of the maintenance knowledge in the maintenance knowledge ontology vector in the knowledge graph to obtain a pre-pushed maintenance knowledge set, wherein the pre-pushed maintenance knowledge set includes maintenance knowledge with the highest similarity to each of the words; The maintenance knowledge in the pre-pushed maintenance knowledge set is filtered according to the maintenance knowledge model of the maintenance technician to obtain a pushed maintenance knowledge set, wherein the maintenance knowledge in the pushed maintenance knowledge set matches the maintenance knowledge requirement of the maintenance knowledge model.

2. The method according to claim 1, characterized in that: The word segmentation processing is performed on the fault description information to obtain a plurality of words corresponding to the fault description information, including: Splitting the fault description information according to a preset splitting rule to obtain multiple maintenance sub-tasks; Perform word segmentation processing on each of the maintenance sub-tasks to obtain multiple words corresponding to each of the maintenance sub-tasks.

3. The method according to claim 2, characterized in that The splitting rule includes at least one of the following rules: Special rules, including that special requirements for maintenance work do not require split processing; Regulatory rules, including that there is no need to separate maintenance work that has regulatory requirements; Step rules, wherein the step rules include splitting the maintenance work according to the maintenance steps; The indivisibility rule includes splitting the maintenance work into indivisible maintenance sub-works.

4. The method according to claim 1, characterized in that: The word segmentation processing is performed on the fault description information to obtain a plurality of words corresponding to the fault description information, including: Performing word segmentation processing on the fault description information to obtain a plurality of pre-selected words corresponding to the fault description information; The meaning of each of the pre-selected words is extended to obtain a plurality of words corresponding to the fault description information.

5. The method according to claim 1, characterized in that The filtering of the maintenance knowledge in the pre-pushed maintenance knowledge set according to the maintenance knowledge model of the maintenance technician to obtain the pushed maintenance knowledge set includes: Calculate the similarity between each maintenance knowledge in the pre-pushed maintenance knowledge set and the maintenance knowledge requirements in the maintenance knowledge model, and obtain a similarity calculation result corresponding to each maintenance knowledge in the pre-pushed maintenance knowledge set; The pushed maintenance knowledge set is determined according to the similarity calculation result corresponding to each maintenance knowledge in the pre-pushed maintenance knowledge set, wherein the similarity calculation result corresponding to each maintenance knowledge in the pushed maintenance knowledge set is greater than or equal to a preset similarity threshold.

6. The method according to claim 5, characterized in that The maintenance knowledge model includes: a first maintenance knowledge requirement, wherein the first maintenance knowledge requirement is used to represent an efficient and fast maintenance knowledge requirement; The second maintenance knowledge requirement is used to represent a long-term maintenance knowledge requirement.

7. The method according to claim 5, characterized in that The similarity calculation formula includes: Wherein, R is the maintenance knowledge model; d j is the jth maintenance knowledge in the pre-pushed maintenance knowledge set; Sim (d j , R) is maintenance knowledge d j The similarity with the maintenance knowledge requirements in the maintenance knowledge model R; W j (C k ) is the kth ontology concept C in the jth maintenance knowledge k The proportion of R (C k ) is the ontology concept C in the maintenance knowledge model R k The proportion of; q is the maintenance knowledge d j The number of concepts in the ontology.

8. A vehicle fault tracing device, characterized in that: include: A word segmentation module, used to perform word segmentation processing on the fault description information to obtain a plurality of words corresponding to the fault description information, wherein the plurality of words are used to form a work requirement ontology vector; A pre-push maintenance knowledge set acquisition module is used to calculate the similarity between each of the words in the work requirement ontology vector and each of the maintenance knowledge in the maintenance knowledge ontology vector in the knowledge graph to obtain a pre-push maintenance knowledge set, wherein the pre-push maintenance knowledge set includes the maintenance knowledge with the highest similarity to each of the words; The push maintenance knowledge set acquisition module is used to filter the maintenance knowledge in the pre-push maintenance knowledge set according to the maintenance knowledge model of the maintenance technician to obtain the push maintenance knowledge set, wherein the maintenance knowledge in the push maintenance knowledge set matches the maintenance knowledge requirements of the maintenance knowledge model.

9. An electronic device, characterized in that: include: processor; Memory; And a computer program, wherein the computer program is stored in the memory, and when the computer program is executed by the processor, the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

11. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images