Fault analysis method and device based on graph database

Abstract

The invention discloses a fault analysis method and device based on a graph database, and relates to the field of big data, and the method comprises the steps: a big data platform constructs a graph database according to the maintenance data of a vehicle; the maintenance data comprises three dimensions of a fault phenomenon, a diagnosis conclusion and parts; nodes of the graph database are the maintenance data, and edges of the graph database are association relationships among different dimension nodes; the big data platform automatically traverses the graph database according to the fault phenomenon of the vehicle to obtain a plurality of fault links; each fault link comprises a diagnosis conclusion associated with the fault phenomenon and a part. According to the method, more comprehensive fault analysis can be given for the fault phenomenon, so that a maintenance technician can find potential faults, and the technical problem that the fault analysis result is not comprehensive enough in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of big data, and specifically to a fault analysis method and device based on a graph database. Background Art

[0002] Automobile fault analysis is a very important technology that can help OEMs and maintenance stations to promptly detect and locate faults and improve vehicle operating efficiency. There are already some methods for automobile fault analysis on the market, most of which use relational databases for direct analysis. The relational database stores historical faults and corresponding processing methods. When a fault phenomenon occurs, the relational database is directly searched to see if the fault phenomenon has occurred before, and then the corresponding maintenance method for the fault phenomenon is found. Although this method is simple, it lacks the function of association analysis. It can only find the maintenance method corresponding to the fault phenomenon stored in the relational database, and cannot find potential faults. The results of the fault analysis are not comprehensive enough. Summary of the invention

[0003] The present application provides a fault analysis method and device based on a graph database, which can solve the technical problems existing in the prior art that potential faults cannot be discovered and the fault analysis results are not comprehensive enough.

[0004] In a first aspect, an embodiment of the present application provides a fault analysis method based on a graph database, the fault analysis method comprising:

[0005] The big data platform constructs a graph database based on the vehicle maintenance data; the maintenance data includes three dimensions: fault phenomenon, diagnosis conclusion, and parts; the nodes of the graph database are the maintenance data, and the edges are the associations between nodes of different dimensions;

[0006] The big data platform automatically traverses the graph database according to the fault phenomenon of the vehicle to obtain multiple fault links; each fault link includes a diagnostic conclusion and a component associated with the fault phenomenon.

[0007] In this embodiment, the fault phenomenon is used as the root node in the graph database. Based on the association relationship, nodes of other dimensions associated with the root node are obtained, thereby obtaining multiple fault links. A more comprehensive fault analysis can be given for the fault phenomenon, so that maintenance technicians can discover potential faults and solve the technical problem that the fault analysis results in the prior art are not comprehensive enough.

[0008] In combination with the first aspect, in one implementation, the big data platform constructs a graph database based on vehicle maintenance data, further comprising:

[0009] Preset the weight of the edge between two nodes according to the different sources of maintenance data;

[0010] The maintenance data includes historical maintenance data of vehicle failures and preset regular maintenance data;

[0011] The source of the historical maintenance data is a maintenance technician, and the source of the preset rule maintenance data includes a user manual.

[0012] In this embodiment, weights are set when constructing the graph database based on the sources of maintenance data. The weight values ​​can be set in advance so that the graph database can adapt to more application environments when it is constructed. Setting weights for association relationships improves the distinction between association relationships between different nodes in the graph database, and can obtain association relationships of different degrees, thereby distinguishing the importance of subsequent output fault links.

[0013] In combination with the first aspect, in one implementation, the maintenance technicians are divided into at least one level, and when there are multiple levels, each level corresponds to a preset weight.

[0014] In this embodiment, maintenance technicians are classified and weights are differentiated more finely based on actual conditions, so as to ensure that the total weight of the fault link obtained in the graph database can be more accurate and adapt to more usage environments.

[0015] In combination with the first aspect, in one implementation, the big data platform traverses the graph database, obtains multiple fault links, automatically calculates the total weight of each fault link, and arranges the multiple fault links in a specified order, where the total weight is the product of the weights of the edges of the fault link.

[0016] In this embodiment, multiple link failures obtained from the search graph database are sorted according to the total weight, so that the closest analysis results can be obtained more clearly, providing options for maintenance technicians, and the sorting of faulty links obtained according to the analysis is verified in turn, which improves the accuracy and reduces the time for fault handling.

[0017] In combination with the first aspect, in one implementation, the big data platform receives fault codes from the vehicle controller, matches the maintenance data according to the preset rules, and if the match is successful, adds the matched rule maintenance data to the graph database, and updates the graph database weight.

[0018] In this embodiment, by receiving the fault code in real time, matching it with the fault phenomenon corresponding to the fault code, and then updating the database to update the weight, the association relationship between the nodes in the graph database can be continuously improved, so that the obtained fault link is more reliable and more accurate.

[0019] In combination with the first aspect, in one implementation, in the graph database, each time an association relationship appears, the weight of the corresponding edge is accumulated once.

[0020] In this embodiment, the weights of the edges in the graph database are adjusted in a timely manner so that the graph database is continuously updated, the dynamics and real-time performance of the graph database are increased, and the fault analysis capability of the graph database is improved.

[0021] In combination with the first aspect, in one implementation, maintenance data is collected periodically, and the big data platform updates the graph database based on the collected maintenance data.

[0022] In this embodiment, periodically updating the graph database can continuously enrich the nodes and relationships in the graph database, so that the samples in the graph database continue to increase, improve the graph database's ability to analyze faults, improve the comprehensiveness of the obtained fault links, and improve the reliability of the weight ranking of fault links.

[0023] In a second aspect, an embodiment of the present application provides a fault analysis device based on any of the above-mentioned fault analysis methods based on a graph database, wherein the fault analysis device is arranged on a big data platform, and includes:

[0024] A construction module, which is used to construct a graph database based on the maintenance data of the vehicle; the maintenance data includes three dimensions: fault phenomenon, diagnosis conclusion, and parts;

[0025] A graph database, which is used to store the maintenance data, wherein the nodes of the graph database are the maintenance data, and the edges are the associations between nodes of different dimensions;

[0026] The analysis module is used to automatically traverse the graph database according to the fault phenomenon of the vehicle to obtain multiple fault links; each fault link includes a diagnosis conclusion and a component associated with the fault phenomenon.

[0027] In conjunction with the second aspect, in one implementation, the construction module is further used to preset the weight of the edge between two nodes according to different sources of the maintenance data;

[0028] The maintenance data includes historical maintenance data of vehicle failures and preset regular maintenance data;

[0029] The source of the historical maintenance data is a maintenance technician, and the source of the preset rule maintenance data includes a user manual.

[0030] In combination with the second aspect, in one embodiment, the fault analysis device also includes a calculation module, which is used to automatically calculate the total weight of each fault link after the analysis module automatically traverses the graph database to obtain multiple fault links, and arrange the multiple fault links in a specified order.

[0031] The beneficial effects brought by the technical solution provided by the embodiments of the present application include:

[0032] By constructing a graph database based on the vehicle's maintenance data, the maintenance data includes three dimensions: fault phenomenon, diagnostic conclusion, and parts; the nodes of the graph database are maintenance data, and the edges are the associations between nodes of different dimensions; the big data platform automatically traverses the graph database based on the vehicle's fault phenomenon. The graph database takes the fault phenomenon as the root node, and based on the association, nodes of other dimensions associated with the root node are obtained, thus obtaining multiple fault links, and a more comprehensive fault analysis can be given for the fault phenomenon, so that maintenance technicians can discover potential faults and solve the technical problem that the fault analysis results in the prior art are not comprehensive enough. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 This is a flow chart of an embodiment of a fault analysis method based on a graph database of the present application;

[0034] Figure 2 This is a schematic diagram of a map database in an embodiment of the present application;

[0035] Figure 3 This is a schematic diagram of a fault analysis device according to an embodiment of the present application;

[0036] Figure 4 This is a flow chart of an embodiment of a fault analysis method in combination with a fault analysis device of the present application. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0038] First, some technical terms in the present application are explained to facilitate those skilled in the art to understand the present application.

[0039] Graph Database: A graph database is a data management system that uses nodes and edges as basic storage units and is designed to efficiently store and query graph data. A graph is a set of nodes and edges, where "nodes" represent entities and "edges" represent relationships between entities. In a graph database, the relationships between data are as important as the data itself, and they are stored as part of the data. This architecture enables the graph database to quickly respond to complex association queries because the relationships between entities have been stored in the database in advance.

[0040] Big data platform: The big data platform in this application refers to the automotive big data application platform, which is a system that integrates data collection, storage, analysis and application. It collects various data generated by vehicles, such as driving data, vehicle condition data, user data, etc., processes and analyzes these data, and provides data services and solutions in various scenarios for automobile manufacturers, service providers and users. The automotive big data application platform can monitor and analyze the vehicle condition data in real time and detect vehicle failures and abnormal conditions in a timely manner. By analyzing a large amount of vehicle fault data, a reliable fault diagnosis and prediction model can be established, providing accurate repair and maintenance recommendations, reducing vehicle repair costs and improving vehicle reliability.

[0041] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0042] In a first aspect, an embodiment of the present application provides a fault analysis method based on a graph database.

[0043] In one embodiment, referring to Figure 1 , Figure 1 This is a flow chart of an embodiment of the fault analysis method of the present application.

[0044] like Figure 1 As shown, the fault analysis method includes:

[0045] S11: The big data platform builds a graph database based on the vehicle maintenance data. The maintenance data includes three dimensions: fault phenomenon, diagnosis conclusion, and parts. The nodes of the graph database are maintenance data, and the edges are the associations between nodes of different dimensions.

[0046] In this embodiment, the maintenance data is transmitted to the big data platform in advance, and the big data platform constructs a graph database based on all the maintenance data it receives. The maintenance data includes the fault phenomenon, the diagnosis conclusion for the fault phenomenon, and the parts corresponding to the diagnosis conclusion.

[0047] Among them, the fault phenomenon adopts a standardized description of the phenomenon of the fault, such as "the second and third gear double cone synchronizer assembly is damaged". The diagnostic conclusion is the conclusion of each fault phenomenon. Different maintenance data may have different diagnostic conclusions for the same fault phenomenon. The diagnostic conclusion is, for example, "the oil leakage is found at the welding part of the rear axle housing sleeve. There are no oil leaking parts around the outside of the axle housing. It is caused by cracks in the welding part of the axle housing, and the cracks are invisible to the naked eye." The parts are the final fault location determined based on the diagnostic conclusion, such as "the axle housing half-shaft oil seal."

[0048] S12: The big data platform automatically traverses the graph database according to the vehicle fault phenomenon to obtain multiple fault links. Specifically, each fault link includes a diagnosis conclusion and a component associated with the fault phenomenon, and the fault links are presented in the form of: fault phenomenon → diagnosis conclusion → component.

[0049] In this embodiment, a graph database is established based on maintenance data, with maintenance data as nodes and edges as associations between nodes of different dimensions. According to the fault phenomenon of the vehicle, the graph database is automatically traversed to obtain nodes of other dimensions associated with the root node, thereby obtaining multiple fault links. A more comprehensive fault analysis can be given for the fault phenomenon, potential faults can be discovered, and the technical problem that the fault analysis results in the prior art are not comprehensive enough can be solved.

[0050] Furthermore, in one embodiment, the big data platform in S11 constructs a graph database based on the vehicle maintenance data, and further includes: when initially setting the weights in the graph database, presetting the weights of the edges between two nodes based on the different sources of the maintenance data. Figure 2 As shown in Figure 1, it is a schematic diagram of a graph database. Figure 2 The fault phenomena, diagnostic conclusions and components in the system are all presented as nodes. The line between two nodes is an edge, and the number on the edge represents the weight of the edge. The edge represents the relationship between two connected nodes of different dimensions. Figure 2 The number on the middle line represents the weight of the edge. The larger the number, the higher the weight, which means the stronger the association between the nodes at both ends of the edge.

[0051] In this embodiment, the above maintenance data includes: historical maintenance data of vehicle failures and preset rule maintenance data. The source of historical maintenance data is maintenance technicians, and a large amount of historical maintenance data provided by maintenance technicians is collected and transmitted to the big data platform. The source of preset rule maintenance data includes user manuals. Developers transmit rule maintenance data obtained according to user manuals to the big data platform, listing the diagnosis conclusions of the fault phenomena and parts.

[0052] In the maintenance data obtained from the big data platform, there may be the same fault phenomenon, but the corresponding diagnostic conclusions and / or parts are different. This situation will be reflected in the association relationship of the graph database. Therefore, in the constructed graph database, each time the association relationship appears, the weight of the corresponding edge is accumulated once.

[0053] In the above step S12, the big data platform traverses the graph database, obtains multiple fault links, automatically calculates the total weight of each link, and arranges the multiple fault links in a specified order. Preferably, the specified order can be in descending order of total weight, which can more clearly display the fault link with the highest correlation.

[0054] like Figure 2 As shown in Figure 1, when fault 5 occurs, the big data platform traverses the graph database and obtains 3 fault links. It then automatically calculates the total weight of each fault link, which is the product of the weights of the edges of the fault link. The total weight is then arranged in descending order according to the total weight, as shown in Table 1.

[0055] Table 1

[0056] Faulty link Total weight Fault phenomenon 5 → Diagnosis conclusion 4 → Component 5 11*17＝181 Fault phenomenon 5 → Diagnosis conclusion 5 → Components 6 11*14＝154 Fault phenomenon 5 → Diagnosis conclusion 5 → Component 4 18*9＝72

[0057] In this embodiment, by setting the weight of each edge in the graph database, the closest fault link can be given in the fault analysis, the optimal fault analysis can be given, and the fault can be checked step by step according to the size of the weight. The possible cause of the vehicle failure can be quickly located, helping maintenance technicians to locate the fault location more quickly, and improving the speed and quality of maintenance services.

[0058] Furthermore, in one embodiment, maintenance technicians are divided into at least one level. When there are multiple levels, each level corresponds to a preset weight.

[0059] Furthermore, in one embodiment, the big data platform receives the fault code from the vehicle controller and matches it according to the preset rule maintenance data. Specifically, the fault code corresponds to the fault phenomenon. If the fault phenomenon can match the preset rule maintenance data, then the matching rule maintenance data is added to the graph database and the graph database is updated to achieve the purpose of updating the weight. If the fault phenomenon does not match the preset rule maintenance data, then the developer can perform subsequent manual processing on the fault phenomenon, generate rule maintenance data after processing, update the graph database according to the generated rule maintenance data, update the nodes and associations in the graph database, and the generated rule maintenance data is TSP data, and the weight can also be preset according to the TSP data.

[0060] As shown in Table 2, an embodiment of weights of different maintenance data sources is provided. The data sources in Table 2 include user manuals, TSP data and maintenance technicians. Maintenance technicians are divided into different levels, for example: experienced maintenance technicians, maintenance technicians with certain experience and maintenance technicians with inexperience. The distinction between different levels can be set according to different environments.

[0061] Table 2

[0062] Data Source Weight User Manual 0.8 TSP Data 0.8 Experienced maintenance technicians 2 Experienced maintenance technicians 1.5 Inexperienced maintenance technicians 1.0

[0063] Furthermore, maintenance data can be collected periodically, and the big data platform can periodically update the graph database based on the collected maintenance data.

[0064] In this embodiment, different weights are preset according to different maintenance data sources, which can increase the level of fault analysis. The update of the graph database can continuously increase the maintenance data in the graph database, making the coverage of fault analysis wider, the analysis more complete, and the analysis results (i.e., fault links) more accurate.

[0065] In a second aspect, the present application also provides a fault analysis device, based on any embodiment of the fault analysis method of the graph database. Figure 3 As shown, in this embodiment, the fault analysis device is arranged on a big data platform, including a construction module, a graph database and an analysis module.

[0066] Among them, the construction module is used to construct a graph database based on the vehicle's maintenance data; the maintenance data includes three dimensions: fault phenomenon, diagnosis conclusion, and parts.

[0067] The graph database is used to store maintenance data. The nodes of the graph database are the above maintenance data, and the edges are the associations between nodes of different dimensions.

[0068] The analysis module is used to automatically traverse the graph database according to the vehicle's fault phenomenon to obtain multiple fault links; each fault link includes a diagnostic conclusion and a component associated with the fault phenomenon.

[0069] Furthermore, the construction module is also used to preset the weight of the edge between two nodes according to different sources of maintenance data; the maintenance data includes historical maintenance data of vehicle failures and preset rule maintenance data; the source of historical maintenance data is maintenance technicians, and the source of preset rule maintenance data includes user manuals.

[0070] Furthermore, the fault analysis device also includes a calculation module, which is used to automatically calculate the total weight of each link after the analysis module automatically traverses the graph database to obtain multiple faulty links, and arrange the multiple faulty links in a specified order. The arrangement form is shown in Table 1.

[0071] Among them, the functional implementation of each module in the above-mentioned fault analysis device corresponds to each step in the above-mentioned fault analysis method embodiment, and its functions and implementation processes are no longer repeated here.

[0072] A specific embodiment of a fault analysis method is given below in conjunction with a fault analysis device.

[0073] like Figure 4 As shown, in this embodiment, the fault analysis method includes:

[0074] a101: The construction module constructs a graph database based on the vehicle maintenance data; the maintenance data includes three dimensions: fault phenomenon, diagnosis conclusion, and parts. The maintenance data includes historical maintenance data of vehicle failures and preset rule maintenance data. The source of historical maintenance data is maintenance technicians; the source of preset rule maintenance data includes user manuals.

[0075] In the constructed graph database, fault phenomena, diagnostic conclusions, and parts are represented by different nodes. The edges of the graph database are the associations between nodes of different dimensions, and each edge has a corresponding weight. When the graph database is established, the weight of each edge is preset according to the different sources of maintenance data. See Table 2. The weight corresponding to the user manual is 0.8, so the weight of the edge formed by the preset rule maintenance data is 0.8. The larger the weight number, the higher the weight, indicating that the association between the nodes at both ends of the edge is stronger.

[0076] In addition, in the graph database, each time an association relationship appears, the weight of the corresponding edge is accumulated. For example, if new regular maintenance data is added to the graph database, and the association relationship of a certain edge is increased once, then in this embodiment, the weight of this edge is increased by 0.8 based on the previous weight.

[0077] a201: When a vehicle failure occurs, the big data platform will receive the vehicle failure phenomenon uploaded by the user. At this time, the analysis module automatically traverses the graph database according to the vehicle failure phenomenon and obtains multiple failure links, where each failure link includes a diagnostic conclusion and a component associated with the failure phenomenon.

[0078] a301: After the analysis module automatically traverses the graph database to obtain multiple faulty links, the calculation module automatically calculates the total weight of each link and arranges the multiple faulty links in a specified order. The arrangement is shown in Table 1.

[0079] Specifically, the total weight of each link = the weight of the edge between the fault phenomenon and the diagnosis conclusion * the weight of the edge between the diagnosis conclusion and the component. Figure 2As shown, the first fault link is: fault phenomenon 5→diagnosis conclusion 5→component 6, the weight of the edge between fault phenomenon 5 and diagnosis conclusion 5 is 11, and the weight of the edge between diagnosis conclusion 5 and component 6 is 14, so the total weight of this link = 11*14=154. For another example, the second fault link is: fault phenomenon 5→diagnosis conclusion 4→component 5, the weight of the edge between fault phenomenon 5 and diagnosis conclusion 4 is 8, and the weight of the edge between diagnosis conclusion 41 and component 5 is 9, so the total weight of this link = 8*9=72. For another example, the third fault link is: fault phenomenon 5→diagnosis conclusion 5→component 4, the weight of the edge between fault phenomenon 5 and diagnosis conclusion 5 is 11, and the weight of the edge between diagnosis conclusion 5 and component 4 is 17, so the total weight of this link = 11*17=181.

[0080] According to the total weight of each fault link, they are sorted in descending order: the third fault link, the first fault link, and the second fault link. In other words, the fault analysis obtains all potential fault links corresponding to the fault phenomenon, and the fault analysis is more comprehensive. The sorting of total weight further gives the order of fault possibility from strong to weak, which is provided to maintenance technicians for reference. The fault link with the largest total weight is the optimal result. Maintenance technicians can start with the fault link with the largest total weight, gradually eliminate the fault, save time, and improve the speed and quality of maintenance services.

[0081] Furthermore, in the steps of the above embodiment, the big data platform will receive fault codes sent from different vehicle controllers, and update the graph database according to the fault phenomena corresponding to the fault codes, thereby improving the reliability of the graph database and keeping the graph database dynamically updated in real time.

[0082] Specifically, the vehicle controller can collect vehicle driving status data, including vehicle speed, engine speed, brake pedal switch status, elevation, battery voltage, etc., and analyze these status data. When a fault occurs, the fault code is transmitted to the big data platform through the on-board TBOX.

[0083] The big data platform also includes a matching module. After receiving the fault code, the matching module matches the fault phenomenon corresponding to the fault code with the preset rule maintenance data. Specifically, the matching module searches the preset rule maintenance data to see whether the fault phenomenon corresponding to the fault code can be found. If it is found, the fault link corresponding to the fault phenomenon can be obtained. The construction module updates the graph database according to the fault link to update the weight of the corresponding edge in the graph database. If the matching module does not find the fault phenomenon corresponding to the fault code in the preset rule maintenance data, the graph database will not be updated at this time. The subsequent maintenance technician will manually analyze the fault code and add it to the graph database after obtaining the corresponding fault link.

[0084] In this embodiment, by receiving the fault code in real time, matching it with the fault phenomenon corresponding to the fault code, and then updating the database to update the weight, the association relationship between the nodes in the graph database can be continuously improved, so that the obtained fault link is more reliable and more accurate.

[0085] Furthermore, in the steps of the above embodiment, a step of updating the graph database periodically may be included. The big data platform periodically collects historical maintenance data newly transmitted by maintenance technicians, and may also periodically collect rule maintenance data transmitted by developers. In this application, developers refer to personnel who design and debug vehicles before they break down, and maintenance technicians refer to personnel who repair vehicles after they break down. Then, the big data platform periodically updates the graph database based on the collected historical maintenance data and rule maintenance data. New nodes and / or associations may be added to the graph database, and the weights of the edges may also change.

[0086] In this embodiment, periodically updating the graph database can continuously enrich the nodes and relationships in the graph database, so that the samples in the graph database continue to increase, improve the graph database's ability to analyze faults, improve the comprehensiveness of the obtained fault links, and improve the reliability of the weight ranking of fault links.

[0087] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0088] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.

[0089] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "for example" or "for example" is intended to present related concepts in a specific way.

[0090] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0091] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0092] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0093] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A fault analysis method based on a graph database, characterized in that: The fault analysis method comprises: The big data platform constructs a graph database based on the vehicle maintenance data; the maintenance data includes three dimensions: fault phenomenon, diagnosis conclusion, and parts; the nodes of the graph database are the maintenance data, and the edges are the associations between nodes of different dimensions; The big data platform automatically traverses the graph database according to the fault phenomenon of the vehicle to obtain multiple fault links; each fault link includes a diagnostic conclusion and a component associated with the fault phenomenon.

2. The fault analysis method based on graph database according to claim 1, characterized in that: The big data platform builds a graph database based on vehicle maintenance data, which also includes: Preset the weight of the edge between two nodes according to the different sources of maintenance data; The maintenance data includes historical maintenance data of vehicle failures and preset regular maintenance data; The source of the historical maintenance data is a maintenance technician, and the source of the preset rule maintenance data includes a user manual.

3. The fault analysis method based on graph database according to claim 2, characterized in that: The maintenance technicians are divided into at least one level. When there are multiple levels, each level corresponds to a preset weight.

4. The fault analysis method based on graph database according to claim 2, characterized in that: The big data platform traverses the graph database, obtains multiple fault links, automatically calculates the total weight of each fault link, and arranges the multiple fault links in a specified order, where the total weight is the product of the weights of the edges of the fault link.

5. The fault analysis method based on graph database according to claim 2, characterized in that: The big data platform receives the fault code from the vehicle controller and matches it with the preset rule maintenance data. If the match is successful, the matched rule maintenance data is added to the graph database and the graph database weight is updated.

6. The fault analysis method based on graph database according to claim 2, characterized in that: In the graph database, each time an association relationship appears, the weight of the corresponding edge is accumulated once.

7. The fault analysis method based on graph database according to claim 1, characterized in that: Maintenance data is collected periodically, and the big data platform updates the graph database according to the collected maintenance data.

8. A fault analysis device based on the fault analysis method based on a graph database according to any one of claims 1 to 7, characterized in that: The fault analysis device is arranged on a big data platform and includes: A construction module, which is used to construct a graph database based on the maintenance data of the vehicle; the maintenance data includes three dimensions: fault phenomenon, diagnosis conclusion, and parts; A graph database, which is used to store the maintenance data, wherein the nodes of the graph database are the maintenance data, and the edges are the associations between nodes of different dimensions; The analysis module is used to automatically traverse the graph database according to the fault phenomenon of the vehicle to obtain multiple fault links; each fault link includes a diagnosis conclusion and a component associated with the fault phenomenon.

9. The fault analysis device according to claim 8, characterized in that: The construction module is also used to preset the weight of the edge between two nodes according to different sources of maintenance data; The maintenance data includes historical maintenance data of vehicle failures and preset regular maintenance data; The source of the historical maintenance data is a maintenance technician, and the source of the preset rule maintenance data includes a user manual.

10. The fault analysis device according to claim 9, characterized in that: The fault analysis device also includes a calculation module, which is used to automatically calculate the total weight of each fault link after the analysis module automatically traverses the graph database to obtain multiple fault links, and arrange the multiple fault links in a specified order.

Images