Method, apparatus and storage medium for determining a fault resolution
By tagging vehicle SOA call chain faults and generating a set of highly similar solutions, the problem of single solutions in existing technologies is solved, and the diversity and effectiveness of fault handling are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GUOKE FOUNDATION STONE (CHONGQING) SOFTWARE CO LTD
- Filing Date
- 2022-12-30
- Publication Date
- 2026-07-21
AI Technical Summary
In existing technologies, when a vehicle SOA call chain fails, the default solution corresponding to the tag cannot adapt to the changing environmental factors, resulting in a single solution and an inability to quickly obtain an effective solution to the fault.
By labeling each SOA call chain failure with a corresponding tag, a tag set is constructed, and a solution set for each tag is generated based on tag similarity, including the preferred solution for that tag and solutions for other tags with high similarity, thus enriching the number and variety of solutions.
This improves the richness and diversity of solutions available to vehicles when SOA call chain failures occur, and enhances the fault handling capabilities of operations and maintenance personnel.
Smart Images
Figure CN116303637B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of vehicle fault analysis technology, and in particular to methods, apparatus, devices and storage media for determining fault solutions. Background Technology
[0002] During the operation of the vehicle, each function relies on one or more Service Oriented Architecture (SOA) systems to call each other. These one or more SOA systems call each other to form a call chain, which represents the call relationship between SOA services and the call relationship between functions within SOA services.
[0003] When the aforementioned call chain fails, the vehicle's related functions cannot be implemented. To prevent call chain failures from persisting for extended periods and impacting vehicle functionality, related technologies typically tagged vehicle faults to determine solutions. A default solution corresponding to each tag is stored in the vehicle's database. When an SOA call chain failure with a corresponding tag occurs, the vehicle displays the default solution for that tag to the user. However, in these technologies, each tag corresponds to only one solution. In many cases, due to environmental or other factors, the default solution for that tag cannot be applied. Therefore, to ensure users can quickly obtain available solutions to faults, it is necessary to expand the number of solutions corresponding to each tag. Summary of the Invention
[0004] To overcome the problems existing in related technologies, this disclosure provides a method, apparatus, device and storage medium for determining fault solutions.
[0005] According to a first aspect of the present disclosure, a method for determining a fault solution is provided, comprising:
[0006] Obtain a tag set, wherein the tags in the tag set are identification records of faults generated by the application architecture call chain on the vehicle;
[0007] Obtain the preferred solution for each tag in the tag set;
[0008] Based on the tag set and the preferred solutions corresponding to each tag in the tag set, determine the solution set corresponding to each tag in the tag set;
[0009] The solution set includes at least two solutions; the solution set corresponding to the first tag includes preferred solutions corresponding to at least two tags in the tag set, the at least two tags include the first tag and at least one second tag, the similarity between the second tag and the first tag is greater than a first preset threshold, the first preset threshold is greater than 0, and the first tag is any tag in the tag set.
[0010] As an optional embodiment, the tag set includes the first tag and N tags other than the first tag, where N is a positive integer;
[0011] The step of determining the solution set corresponding to each tag in the tag set based on the tag set and the preferred solutions corresponding to each tag in the tag set includes:
[0012] Obtain the vector corresponding to each tag in the tag set;
[0013] Using the vectors corresponding to the first label and the N labels, calculate the similarity between the first label and each of the N labels to obtain N similarity scores;
[0014] Based on the N similarities, the preferred solution corresponding to the first label, and the preferred solutions corresponding to the N labels, a solution set corresponding to the first label is determined.
[0015] As an optional embodiment, determining the solution set corresponding to the first tag based on the N similarities, the preferred solution corresponding to the first tag, and the preferred solutions corresponding to the N tags includes:
[0016] K second tags are determined from the N tags, wherein the similarity of the second tags is greater than a preset threshold, or the similarity of the second tags is the largest of the K similarity values among the N tags, where K is a positive integer less than or equal to N;
[0017] Generate a first solution set corresponding to the first tag, wherein the first solution set includes: the preferred solution corresponding to the second tag, and the preferred solution corresponding to the first tag.
[0018] As an optional embodiment, determining the solution set corresponding to each tag in the tag set based on the tag set and the preferred solutions corresponding to each tag in the tag set includes:
[0019] Based on the tag set and the preferred solutions corresponding to each tag in the tag set, determine the order of the solutions in the solution set corresponding to each tag in the tag set.
[0020] As an optional embodiment, the first solution set corresponding to the first tag includes the preferred solution corresponding to the first tag and K preferred solutions corresponding to the second tags, where K is a positive integer;
[0021] The step of determining the order of solutions in the solution set corresponding to each label in the label set, based on the label set and the preferred solutions corresponding to each label in the label set, includes:
[0022] The preferred solution corresponding to the first label is determined as the first position in the first solution set;
[0023] The preferred solutions corresponding to the K second labels are arranged in the first solution set in descending order of similarity between the K second labels and the first label.
[0024] As an optional embodiment, the K second tags include a third tag and a fourth tag, wherein the third tag and the fourth tag have the same similarity to the first tag;
[0025] The label includes at least two fields.
[0026] After arranging the preferred solutions corresponding to the K second labels in the first solution set in descending order of similarity to the first label, the method further includes:
[0027] Compare the first tag and the third tag field by field to obtain the first field where the third tag differs from the first tag;
[0028] By comparing the first tag and the fourth tag field by field, a second field in which the four tags differ from the first tag is obtained;
[0029] Based on the arrangement of the first and second fields in the label, the order of the preferred solutions corresponding to the third and fourth labels in the first solution set is determined.
[0030] According to a second aspect of the present disclosure, an apparatus for determining a fault solution is provided, comprising:
[0031] The first acquisition module is used to acquire a tag set, wherein the tags in the tag set are tags for faults generated on the vehicle;
[0032] The second acquisition module is used to acquire the preferred solution corresponding to each tag in the tag set;
[0033] The determining module is used to determine the solution set corresponding to each tag in the tag set based on the tag set and the preferred solution corresponding to each tag in the tag set;
[0034] The solution set includes at least two solutions; the solution set corresponding to the first tag includes preferred solutions corresponding to at least two tags in the tag set, the at least two tags include the first tag and at least one second tag, the similarity between the second tag and the first tag is greater than a first preset threshold, the first preset threshold is greater than 0, and the first tag is any tag in the tag set.
[0035] According to a third aspect of the present disclosure, a computer program product is provided, which stores a set of instructions that are executed by the computer program product to implement the fault solution determination method provided by the fault solution determination aspect of the present disclosure.
[0036] According to a fourth aspect of the present disclosure, an electronic device is provided, comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement a fault solution determination method provided by the fault solution determination aspect of the present disclosure.
[0037] According to a fifth aspect of the present disclosure, a computer-readable storage medium is provided that stores computer program instructions thereon, which, when executed by a processor, implement the steps of a fault solution determination method provided by the fault solution determination aspect of the present disclosure.
[0038] The technical solutions provided by the embodiments of this disclosure can include the following beneficial effects: Since each SOA call chain failure has a corresponding preferred solution, each SOA call chain failure can be tagged accordingly, so that each tag corresponds to a preferred solution. Then, a tag set obtained by summarizing the above tags is obtained. Based on the tag set and the preferred solutions corresponding to each tag, a solution set corresponding to each tag is generated. The solution set corresponding to each tag not only includes the preferred solution corresponding to that tag, but also the solutions corresponding to tags with a similarity greater than a first preset threshold. In this way, when a vehicle's SOA call chain fails, a tag corresponding to the failure can be attached, and multiple solution sets corresponding to the failure can be queried through the tags. Compared with the prior art where one failure corresponds to one solution, the richness of the obtained solutions is improved.
[0039] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description
[0040] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.
[0041] Figure 1 This is a flowchart illustrating a method for determining a fault solution according to an exemplary embodiment.
[0042] Figure 2 This is a flowchart illustrating a method for determining a fault solution according to another exemplary embodiment.
[0043] Figure 3 This is a flowchart illustrating a method for determining a fault solution according to yet another exemplary embodiment.
[0044] Figure 4 This is a flowchart illustrating a method for determining a fault solution according to yet another exemplary embodiment.
[0045] Figure 5 This is a flowchart illustrating a method for determining a fault solution according to another exemplary embodiment.
[0046] Figure 6 This is a flowchart illustrating a method for determining a fault solution according to another exemplary embodiment.
[0047] Figure 7 This is a block diagram illustrating a fault solution determination apparatus according to an exemplary embodiment.
[0048] Figure 8 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation
[0049] The exemplary embodiments will now be described in detail with reference to the accompanying drawings.
[0050] It should be noted that the relevant embodiments and accompanying drawings are only for describing and illustrating exemplary embodiments provided by this disclosure, and not all embodiments of this disclosure, nor should this disclosure be understood to be limited to the relevant exemplary embodiments.
[0051] It should be noted that the terms "first," "second," etc., used in this disclosure are only used to distinguish different steps, devices, or modules. These terms do not represent any specific technical meaning, nor do they indicate any order or interdependence between them.
[0052] It should be noted that the terms “a,” “a plurality of,” and “at least one” used in this disclosure are illustrative rather than restrictive. Unless otherwise expressly indicated in the context, they should be understood as “one or more.”
[0053] It should be noted that the term "and / or" used in this disclosure is used to describe the relationship between related objects, and generally indicates that there are at least three relationships. For example, A and / or B can at least indicate: the existence of A alone, the existence of both A and B, and the existence of B alone.
[0054] It should be noted that the various steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Unless otherwise specified, the scope of this disclosure is not limited by the order in which the steps are described in the relevant embodiments.
[0055] It should be noted that all actions involving the acquisition of signals, information, or data in this disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with authorization from the owner of the relevant device.
[0056] Exemplary methods
[0057] Figure 1 This is a flowchart illustrating a method for determining a fault solution according to an exemplary embodiment, such as... Figure 1 As shown, the method for determining a fault solution is used in the determination of a fault solution and includes the following steps.
[0058] In step S110, a tag set is obtained, wherein the tags in the tag set are identification records of faults generated by the application architecture call chain on the vehicle.
[0059] In this embodiment, the tag set is a collection of tags, where each tag represents a fault generated by the Service-Oriented Architecture (SOA) call chain on the vehicle. The vehicle-side SOA call chain represents a function (e.g., opening a car door) implemented through mutual calls between one or more SOA services, forming an SOA call chain of service invocations. Tags can be assigned to all possible SOA call chain faults on the vehicle, and these tags can be aggregated to obtain the tag set.
[0060] This embodiment introduces a tagging mechanism into the SOA call chain on the vehicle side, so that each SOA call chain fault corresponds to a tag, giving the SOA call chain faults characteristic attributes, and then recommending fault solutions based on the tags corresponding to the faults.
[0061] In the face of scenarios with numerous devices and diverse faults in SOA service systems, the introduction of a tagging mechanism can help users quickly locate faults and receive recommended solutions, enabling them to promptly utilize past experience to troubleshoot problems.
[0062] For example, the tags can be a tag tree in the form of a tree diagram, with the car manufacturer as the root node of the tag tree, the vehicle model as the child node of the car manufacturer, and specific fault-related tags such as faulty equipment, fault point, and fault cause as child nodes of the vehicle model.
[0063] In step S120, the preferred solutions corresponding to each tag in the tag set are obtained.
[0064] In this embodiment, each tag has a corresponding preferred solution. This preferred solution is pre-set by the user based on past experience and stored in the vehicle's database.
[0065] In step S130, based on the tag set and the preferred solutions corresponding to each tag in the tag set, a solution set corresponding to each tag in the tag set is determined;
[0066] The solution set includes at least two solutions; the solution set corresponding to the first tag includes preferred solutions corresponding to at least two tags in the tag set, the at least two tags include the first tag and at least one second tag, the similarity between the second tag and the first tag is greater than a first preset threshold, the first preset threshold is greater than 0, and the first tag is any tag in the tag set.
[0067] In this embodiment, each label has only one corresponding inherent preferred solution. However, when users match solutions for each fault, they usually want to obtain as many effective solutions as possible, even if some solutions are not as effective as the preferred solution.
[0068] Based on this, we can construct a solution set for each tag. Each solution set includes at least two solutions. The solutions in a solution set can be determined by the tag set and the preferred solutions corresponding to each tag in the tag set.
[0069] In one embodiment, SOA call chain failures exhibit certain similarities, and correspondingly, the tags also show some similarity. Therefore, for each tag, preferred solutions corresponding to other tags with high similarity to that tag can be obtained, and then these preferred solutions corresponding to other tags are added to the solution set of the original solution.
[0070] Taking the first label as an example, the solution set corresponding to the first label includes the preferred solution corresponding to the first label and at least one preferred solution corresponding to other labels. The preferred solution corresponding to the first label is the solution with higher priority in the solution set.
[0071] In this disclosure, since each SOA call chain failure has a corresponding preferred solution, each SOA call chain failure can be tagged, so that each tag corresponds to a preferred solution. Then, a tag set obtained by aggregating the tags is obtained. Based on the tag set and the preferred solutions corresponding to each tag, a solution set corresponding to each tag is generated. The solution set corresponding to each tag includes not only the preferred solution corresponding to that tag, but also solutions corresponding to tags with a similarity greater than a first preset threshold. In this way, when a vehicle's SOA call chain fails, a tag corresponding to the failure can be attached, and multiple solution sets corresponding to the failure can be queried through the tags. Compared with the prior art where one failure corresponds to one solution, the richness of the obtained solutions is improved.
[0072] As an optional embodiment, the tag set includes the first tag and N tags other than the first tag, where N is a positive integer, such as... Figure 2 As shown, the above S130 may include:
[0073] In step S210, the vector corresponding to each tag in the tag set is obtained;
[0074] In this embodiment, since similar faults exist in the SOA call chain within the vehicle, there are varying degrees of similarity between the tags. The similarity between tags can be numerically represented by vectorizing each tag and calculating the cosine similarity between the vectorized tags. For example, tags can be vectorized using one-hot encoding.
[0075] In step S220, using the vectors corresponding to the first label and the N labels, the similarity between the first label and each of the N labels is calculated to obtain N similarity scores.
[0076] In this embodiment, taking the first label as an example, the label set contains N+1 labels. First, these N+1 labels can be converted into corresponding vectors. Then, for any first label, the N similarities between the first label and the other N labels can be determined by calculating the cosine similarity between the vectors. Then, based on these N similarities, the preferred solutions corresponding to some of the N labels are selected, and together with the preferred solutions corresponding to the first label, they form the solution set for the first label.
[0077] If two tags are independent of each other, then the similarity between the two tags is 0. If two tags are completely identical, then the similarity between the two tags is 1. If two tags have some degree of similarity, then the higher the similarity between the two tags, the larger the similarity value between 0 and 1.
[0078] In step S230, a solution set corresponding to the first label is determined based on the N similarities, the preferred solution corresponding to the first label, and the preferred solutions corresponding to the N labels.
[0079] In this embodiment, solutions to similar faults can be shared to a certain extent. Therefore, a solution set for a tag can be constructed based on the similarity between tags. Taking the first tag as an example, tags with high similarity to the first tag can be selected from N tags, and the preferred solutions corresponding to these tags, together with the preferred solutions corresponding to the first tag, can form the solution set corresponding to the first tag.
[0080] For example, tags with a similarity greater than 0.6 to the first tag can be obtained, and the preferred solutions corresponding to these tags, together with the solutions of the first tag, can be determined as the solution set corresponding to the first tag.
[0081] This application calculates the similarity between a first label and other labels in the label set, and then selects labels with high similarity to the first label, adding the preferred solutions corresponding to these labels to the solution set of the first label. This enriches the number of solutions corresponding to the first label.
[0082] As an optional embodiment, such as Figure 3 As shown, determining the solution set corresponding to the first label based on the N similarities, the preferred solution corresponding to the first label, and the preferred solutions corresponding to the N labels includes:
[0083] In step S310, the tag with a similarity greater than a second preset threshold among the N tags is determined as the second tag, wherein the second preset threshold is greater than or equal to the first preset threshold;
[0084] In this embodiment, for any first tag in the tag set, after determining the N similarities between the first tag and the other N tags in the tag set, K second tags with high similarity to the first tag can be selected from the N tags based on the N similarities. The preferred solutions corresponding to these K second tags are then added to the solution set of the first tag. Specifically, the second tags can be selected by setting a similarity threshold.
[0085] Specifically, in one embodiment, a second preset threshold for similarity can be set. If the similarity between two tags is greater than the second preset threshold, it can be considered that the preferred solutions corresponding to these two tags can be shared. Therefore, tags with a similarity greater than the second preset threshold to the first tag can be identified as second tags, and the preferred solutions corresponding to all second tags can be added to the first solution set of the first tag. For example, the second preset threshold can be 0.5 or 0.25.
[0086] In step S320, a first solution set corresponding to the first tag is generated, wherein the first solution set includes: the preferred solution corresponding to the second tag, and the preferred solution corresponding to the first tag.
[0087] In this embodiment, a second tag with a high similarity to the first tag is selected, and the preferred solutions corresponding to the second tag and the preferred solutions corresponding to the first tag are combined to form a first solution set. This allows each tag to correspond to more solutions, providing operations and maintenance personnel with a wider range of options when facing SOA call chain failures.
[0088] As an optional embodiment, determining the solution set corresponding to the first tag based on the N similarities, the preferred solution corresponding to the first tag, and the preferred solutions corresponding to the N tags includes:
[0089] The labels corresponding to the K largest similarities among the N similarities are determined as the second label, where K is a positive integer less than or equal to N;
[0090] Generate a first solution set corresponding to the first tag, wherein the first solution set includes: the preferred solution corresponding to the second tag, and the preferred solution corresponding to the first tag.
[0091] In this embodiment, after determining the N similarities between the other N tags in the tag set and the first tag, K second tags with high similarity to the first tag can be selected from the N tags based on the N similarities. The preferred solutions corresponding to these K second tags are then added to the solution set of the first tag. Specifically, the second tags can be selected by setting a threshold for the number of second tags.
[0092] In one embodiment, the N similarities can be sorted in descending order, and a positive integer K less than or equal to N can be determined. Then, the K largest similarities are selected from the N similarities, and the K labels corresponding to these K similarities are determined as second labels. The preferred solutions corresponding to the K second labels are added to the solution set corresponding to the first label. For example, k can be N / 2 or N / 4.
[0093] As an optional embodiment, the above S130 may include:
[0094] Based on the tag set and the preferred solutions corresponding to each tag in the tag set, determine the order of the solutions in the solution set corresponding to each tag in the tag set.
[0095] In this embodiment, for each tag, after determining the solutions included in the solution set corresponding to that tag, it is also necessary to further determine the order of these solutions within the solution set. In the solution set corresponding to a tag, the stronger the effect of a solution on the fault identified by the tag, the higher its ranking. Therefore, after determining the solutions included in the solution set corresponding to a tag, the order of the solutions in the solution set can be determined based on the effectiveness of these solutions on the fault identified by the tag.
[0096] As an optional embodiment, such as Figure 4 As shown, the first solution set corresponding to the first label includes the preferred solution corresponding to the first label and K preferred solutions corresponding to the second labels, where K is a positive integer;
[0097] The step of determining the order of solutions in the solution set corresponding to each label in the label set, based on the label set and the preferred solutions corresponding to each label in the label set, includes:
[0098] In step S410, the preferred solution corresponding to the first tag is determined as the first position in the first solution set;
[0099] In this embodiment, taking the first label as an example, in the first solution set, the stronger the effect of the solution on the fault identified by the first label, the higher the ranking order of the solution in the first solution set.
[0100] Since the preferred solution corresponding to the first label is a solution specifically for the first label, it has the strongest effect when applied to the fault identified by the first label, and therefore ranks first in the set of first solutions.
[0101] In step S420, the preferred solutions corresponding to the K second tags are arranged in the first solution set in descending order of similarity between the K second tags and the first tag.
[0102] In this embodiment, the first solution set includes not only the preferred solution corresponding to the first label, but also K preferred solutions corresponding to the second labels. The higher the similarity between the second label and the first label, the stronger the effect of the preferred solution corresponding to the second label on the fault identified by the first label. Therefore, the order of the solutions in the first solution set can be determined by comparing the similarity between each second label and the first label.
[0103] Specifically, the first solution set corresponding to the first label includes not only the preferred solution corresponding to the first label, but also K preferred solutions corresponding to the second labels. Since the preferred solution corresponding to the first label is most effective in addressing the fault identified by the first label, it can be ranked first in the first solution set.
[0104] For each second label, the higher its similarity to the first label, the stronger the effect of the optimal solution corresponding to the second label on the fault identified by the first label. Therefore, the optimal solution corresponding to the second label should be ranked higher in the first solution set. That is, the optimal solutions corresponding to the K second labels can be arranged in the first solution set in descending order of their similarity to the first label, in order from first to last.
[0105] For example, K is 3, and the three second labels are label A, label B, and label C. The similarity between label A and the first label is 0.75, the similarity between label B and the first label is 0.68, and the similarity between label C and the first label is 0.6. Therefore, there are four solutions in the first solution set. The solutions, arranged from first to last, are: the preferred solution corresponding to the first label, the preferred solution corresponding to label A, the preferred solution corresponding to label B, and the preferred solution corresponding to label C.
[0106] Using the above method, solutions in the solution set can be ranked based on their effectiveness in addressing the faults identified by the tags. This allows users to more easily select solutions from the set after retrieving the corresponding tag to address the fault.
[0107] As an optional embodiment, the K second tags include a third tag and a fourth tag, and the third tag and the fourth tag have the same similarity to the first tag;
[0108] The label includes at least two fields.
[0109] After arranging the preferred solutions corresponding to the K second labels in the first solution set in descending order of similarity to the first label, the method further includes:
[0110] Compare the first tag and the third tag field by field to obtain the first field where the third tag differs from the first tag;
[0111] By comparing the first tag and the fourth tag field by field, a second field in which the four tags differ from the first tag is obtained;
[0112] Based on the arrangement of the first and second fields in the label, the order of the preferred solutions corresponding to the third and fourth labels in the first solution set is determined.
[0113] In this embodiment, taking the first label as an example, if the similarity between the K second labels in the first solution set and the first label is different, the preferred solutions corresponding to the K second labels can be arranged in the first solution set in descending order of their similarity to the first label.
[0114] However, one possibility is that there are at least two second tags with the same similarity to the first tag. In this case, other strategies would be needed to rank the preferred solutions corresponding to these at least two second tags.
[0115] Specifically, in this embodiment, the labels are in the form of a tree diagram, where each node in the label tree is a field, and a label includes at least two fields.
[0116] In one embodiment, the vehicle manufacturer can be used as the root node of the tag tree, the vehicle model can be used as a child node of the vehicle manufacturer, the specific faulty device can be used as a child node of the vehicle model, the more specific fault point can be used as a child node of the faulty device, and the cause of the fault point can be used as a child node of the fault point. A path formed by these five nodes can be regarded as a tag.
[0117] Clearly, based on the above tagging method, car manufacturers and models can be categorized into the upper virtual classification layer. These are not directly related to the fault and can exist independently. In contrast, faulty equipment, fault location, and fault cause are related to the fault and are not independent. Therefore, the later fields in the tags best reflect the characteristic attributes of the fault.
[0118] If at least two second labels exist that have the same similarity to the first label, but differ in the position of their differing fields, then the second label with the differing field appearing earlier in the list of second labels will have a better solution for the fault identified by the first label.
[0119] For example, the second label includes a third label and a fourth label, and the third and fourth labels have the same similarity to the first label. Starting from the root node of the label, the first and third labels are compared field by field to obtain the first field where the third label differs from the first label. Similarly, the first and fourth labels are compared field by field to obtain the second field where the fourth label differs from the first label. If the first field appears earlier in the label list, the preferred solution corresponding to the third label can be ranked before the preferred solution corresponding to the fourth label in the first solution set. Similarly, if the second field appears earlier in the label list, the preferred solution corresponding to the fourth label can be ranked before the preferred solution corresponding to the third label in the first solution set.
[0120] As an optional embodiment, the label representing the fault uses 8 bytes, i.e., an unsigned 64-bit integer. The vehicle manufacturer occupies the high 2 bytes, the middle 3 bytes, and the specific fault-related content occupies the low 3 bytes. The first label is: Vehicle Manufacturer 1 -- Model 1 -- BCM -- Door Motor 1 -- Error Code 001; the third label is: Vehicle Manufacturer 1 -- Model 1 -- BCM -- Door Motor 1 -- Error Code 002; the fourth label is: Vehicle Manufacturer 1 -- Model 2 -- BCM -- Door Motor 1 -- Error Code 001.
[0121] The first and third labels have the same similarity, but the causes of failure for the first and third labels are different, and the vehicle models for the first and fourth labels are different. Obviously, the fourth label is closer to the first label. Therefore, in the first solution set, the preferred solution corresponding to the fourth label can be ranked before the preferred solution corresponding to the third label.
[0122] Based on the above scheme, by sorting the solutions in the solution set, a batch of better fault solutions can be quickly matched using a single label.
[0123] As an optional embodiment, the above solution can be set up under the vehicle-cloud integrated system, that is, the relational database management system (MySQL) database can be deployed in the cloud, and the MySQL database stores the tag set and the solution set corresponding to each tag in the tag set.
[0124] like Figure 5As shown, the vehicle-cloud integrated system consists of two service sets: online and offline. The online system provides developers or operations personnel with a real-time online query service based on vehicle-side SOA call chain fault tags. Specifically, developers or operations personnel input SOA call chain fault tags on the vehicle side, which then sends the tags to a MySQL database in the cloud. The MySQL database retrieves the corresponding solution set for each tag and returns it to the vehicle side. The offline service provides the online service with a tag set based on combinations of vehicle-side SOA call chain fault tags. This tag set, along with its corresponding solution set, is stored in a database for use by the online service.
[0125] Among them, the online service can improve the HTTP(S) interface to obtain fault labels for the vehicle-side SOA call chain and respond with the solution set of the request.
[0126] After obtaining the solution set corresponding to the tag from the online service, the solution set can be displayed on the vehicle, and the solution set can be displayed in pages on the display interface.
[0127] As an alternative embodiment, such as Figure 6 As shown, a specific vehicle-side SOA call chain fault label set can be defined according to a preset labeling mechanism, the label set can be stored in a MySQL database, the label set can be retrieved from the MySQL database, and each label in the label set can be quantified using the ONE-HOT encoding method.
[0128] For each label in the label set, the Cartesian product can be used to calculate the cosine similarity between the label and every other label in the label set through its quantized vector. Then, the optimal solutions for the other labels are arranged in descending order of cosine similarity.
[0129] When there are at least two tags with the same similarity to the tag, the preferred solutions corresponding to the at least two tags are sorted by comparing the tag with the other at least two tags field by field and based on the position of the fields where the tag differs from the other at least two tags.
[0130] After sorting the preferred solutions for all tags, the preferred solution set for each tag is obtained by filtering according to the sorting, and each tag and its corresponding solution set are stored in the MySQL database.
[0131] Exemplary device
[0132] Figure 7 This is a block diagram of a fault solution determination apparatus 700 according to an exemplary embodiment. (Refer to...) Figure 7The device 700 includes a first acquisition module 710, a second acquisition module 720, and a determination module 730.
[0133] The first acquisition module 710 is used to acquire a tag set, wherein the tags in the tag set are tags for faults generated on the vehicle;
[0134] The second acquisition module 720 is used to acquire the preferred solution corresponding to each tag in the tag set;
[0135] The determining module 730 is used to determine the solution set corresponding to each tag in the tag set based on the tag set and the preferred solution corresponding to each tag in the tag set;
[0136] The solution set includes at least two solutions; the solution set corresponding to the first tag includes preferred solutions corresponding to at least two tags in the tag set, the at least two tags include the first tag and at least one second tag, the similarity between the second tag and the first tag is greater than a first preset threshold, the first preset threshold is greater than 0, and the first tag is any tag in the tag set.
[0137] As an optional embodiment, the tag set includes the first tag and N tags other than the first tag, where N is a positive integer. The determining module 730 is further configured to:
[0138] Obtain the vector corresponding to each tag in the tag set;
[0139] Using the vectors corresponding to the first label and the N labels, calculate the similarity between the first label and each of the N labels to obtain N similarity scores;
[0140] Based on the N similarities, the preferred solution corresponding to the first label, and the preferred solutions corresponding to the N labels, a solution set corresponding to the first label is determined.
[0141] As an optional embodiment, the determining module 730 is further configured to:
[0142] K second tags are determined from the N tags, wherein the similarity of the second tags is greater than a preset threshold, or the similarity of the second tags is the largest of the K similarity values among the N tags, where K is a positive integer less than or equal to N;
[0143] The second tag is determined from the N tags whose similarity is greater than a second preset threshold, wherein the second preset threshold is greater than or equal to the first preset threshold;
[0144] Generate a first solution set corresponding to the first tag, wherein the first solution set includes: the preferred solution corresponding to the second tag, and the preferred solution corresponding to the first tag.
[0145] As an optional embodiment, the determining module 730 is further configured to:
[0146] The labels corresponding to the K largest similarities among the N similarities are determined as the second label, where K is a positive integer less than or equal to N;
[0147] Generate a first solution set corresponding to the first tag, wherein the first solution set includes: the preferred solution corresponding to the second tag, and the preferred solution corresponding to the first tag.
[0148] As an optional embodiment, the determining module 730 is further configured to:
[0149] Based on the tag set and the preferred solutions corresponding to each tag in the tag set, determine the order of the solutions in the solution set corresponding to each tag in the tag set.
[0150] As an optional embodiment, the determining module 730 is further configured to:
[0151] The preferred solution corresponding to the first label is determined as the first position in the first solution set;
[0152] The preferred solutions corresponding to the K second labels are arranged in the first solution set in descending order of similarity between the K second labels and the first label.
[0153] As an optional embodiment, the determining module 730 is further configured to:
[0154] Compare the first tag and the third tag field by field to obtain the first field where the third tag differs from the first tag;
[0155] By comparing the first tag and the fourth tag field by field, a second field in which the four tags differ from the first tag is obtained;
[0156] Based on the arrangement of the first and second fields in the label, the order of the preferred solutions corresponding to the third and fourth labels in the first solution set is determined.
[0157] The fault solution determination device provided in this embodiment of the invention can implement the steps in the above method embodiments, and will not be repeated here to avoid repetition.
[0158] Exemplary electronic devices
[0159] Figure 8 This is a block diagram illustrating an electronic device 800 according to an exemplary embodiment. The electronic device 800 may be a vehicle controller, an in-vehicle terminal, an in-vehicle computer, or other types of electronic devices.
[0160] Reference Figure 8 The electronic device 800 may include at least one processor 810 and a memory 820. The processor 810 can execute instructions stored in the memory 820. The processor 810 is communicatively connected to the memory 820 via a data bus. In addition to the memory 820, the processor 810 can also be communicatively connected to an input device 830, an output device 840, and a communication device 850 via the data bus.
[0161] The processor 810 can be any conventional processor, such as a commercially available CPU. The processor may also include, for example, a Graphics Processing Unit (GPU), a Field Programmable Gate Array (FPGA), a System-on-Chip (SOC), an Application-Specific Integrated Circuit (ASIC), or a combination thereof.
[0162] The memory 820 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 storage, flash memory, magnetic disk or optical disk.
[0163] In this embodiment of the present disclosure, the memory 820 stores executable instructions, and the processor 810 can read the executable instructions from the memory 820 and execute the instructions to implement all or part of the steps of the fault solution determination method described in any of the exemplary embodiments above.
[0164] Exemplary computer-readable storage media
[0165] In addition to the methods and apparatus described above, exemplary embodiments of this disclosure may also be a computer program product or a computer-readable storage medium storing the computer program product. The computer product includes computer program instructions that can be executed by a processor to perform all or part of the steps described in any of the methods in the exemplary embodiments described above.
[0166] The computer program product can be written in any combination of one or more programming languages to perform the operations of the embodiments of this disclosure. These programming languages include object-oriented programming languages such as Java and C++, as well as conventional procedural programming languages such as C or similar languages, and scripting languages (e.g., Python). The program code can be executed entirely on a user's computing device, partially on a user's computing device, as a standalone software package, partially on a user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.
[0167] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media include: static random access memory (SRAM) having one or more electrically connected wires, electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk, or any suitable combination thereof.
[0168] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of this disclosure. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.
[0169] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.
Claims
1. A method for determining a fault solution, characterized in that, include: Obtain a tag set, wherein the tags in the tag set are identification records of faults generated by the application architecture call chain on the vehicle; Obtain the preferred solution for each tag in the tag set; Based on the tag set and the preferred solutions corresponding to each tag in the tag set, determine the solution set corresponding to each tag in the tag set; The solution set includes at least two solutions; the solution set corresponding to the first tag includes preferred solutions corresponding to at least two tags in the tag set, the at least two tags include the first tag and at least one second tag, the similarity between the second tag and the first tag is greater than a first preset threshold, the first preset threshold is greater than 0, and the first tag is any tag in the tag set; The first solution set corresponding to the first label includes the preferred solution corresponding to the first label and K preferred solutions corresponding to the second labels, where K is a positive integer; the K second labels include a third label and a fourth label, and the third label and the fourth label have the same similarity to the first label; the labels are a label tree in the form of a tree diagram, where each node in the label tree is a field, and a label includes at least two fields, with the car manufacturer as the root node of the label tree, the vehicle model as the child node of the car manufacturer, the specific faulty device as the child node of the vehicle model, the more specific fault point as the child node of the faulty device, and the cause of the fault point as the child node of the fault point; The step of determining the solution set corresponding to each tag in the tag set based on the tag set and the preferred solutions corresponding to each tag in the tag set includes: The preferred solution corresponding to the first label is determined as the first position in the first solution set; According to the order of similarity between the K second tags and the first tag from largest to smallest, the preferred solutions corresponding to the K second tags are arranged in the first solution set in order from first to last. Compare the first tag and the third tag field by field to obtain the first field where the third tag differs from the first tag; By comparing the first tag and the fourth tag field by field, a second field in which the fourth tag differs from the first tag is obtained; Based on the arrangement positions of the first field and the second field in the label, determine the arrangement order of the preferred solutions corresponding to the third label and the fourth label in the first solution set; The tag set includes the first tag and N tags other than the first tag, where N is a positive integer; The step of determining the solution set corresponding to each tag in the tag set based on the tag set and the preferred solutions corresponding to each tag in the tag set includes: The tags in the tag set are vectorized using one-hot encoding to obtain the vector corresponding to each tag in the tag set; Using the vectors corresponding to the first label and the N labels, the similarity between the first label and each of the N labels is calculated to obtain N similarity scores, where the similarity score of each label is a cosine similarity score. Based on the N similarities, the preferred solution corresponding to the first label, and the preferred solutions corresponding to the N labels, a solution set corresponding to the first label is determined.
2. The method for determining a fault solution according to claim 1, characterized in that, The step of determining the solution set corresponding to the first label based on the N similarities, the preferred solution corresponding to the first label, and the preferred solutions corresponding to the N labels includes: The second tag is determined from the N tags whose similarity is greater than a second preset threshold, wherein the second preset threshold is greater than or equal to the first preset threshold; Generate a first solution set corresponding to the first tag, wherein the first solution set includes: the preferred solution corresponding to the second tag, and the preferred solution corresponding to the first tag.
3. The method for determining a fault solution according to claim 1, characterized in that, The step of determining the solution set corresponding to the first label based on the N similarities, the preferred solution corresponding to the first label, and the preferred solutions corresponding to the N labels includes: The labels corresponding to the K largest similarities among the N similarities are determined as the second label, where K is a positive integer less than or equal to N; Generate a first solution set corresponding to the first tag, wherein the first solution set includes: the preferred solution corresponding to the second tag, and the preferred solution corresponding to the first tag.
4. A device for determining a fault solution, characterized in that, include: The first acquisition module is used to acquire a tag set, wherein the tags in the tag set are tags for faults generated on the vehicle; The second acquisition module is used to acquire the preferred solution corresponding to each tag in the tag set; The determining module is used to determine the solution set corresponding to each tag in the tag set based on the tag set and the preferred solution corresponding to each tag in the tag set; The solution set includes at least two solutions; the solution set corresponding to the first tag includes preferred solutions corresponding to at least two tags in the tag set, the at least two tags include the first tag and at least one second tag, the similarity between the second tag and the first tag is greater than a first preset threshold, the first preset threshold is greater than 0, and the first tag is any tag in the tag set; The first solution set corresponding to the first label includes the preferred solution corresponding to the first label and K preferred solutions corresponding to the second labels, where K is a positive integer; the K second labels include a third label and a fourth label, and the third label and the fourth label have the same similarity to the first label; the labels are a label tree in the form of a tree diagram, where each node in the label tree is a field, and a label includes at least two fields, with the car manufacturer as the root node of the label tree, the vehicle model as the child node of the car manufacturer, the specific faulty device as the child node of the vehicle model, the more specific fault point as the child node of the faulty device, and the cause of the fault point as the child node of the fault point; The determining module is also used for: The preferred solution corresponding to the first label is determined as the first position in the first solution set; According to the order of similarity between the K second tags and the first tag from largest to smallest, the preferred solutions corresponding to the K second tags are arranged in the first solution set in order from first to last. Compare the first tag and the third tag field by field to obtain the first field where the third tag differs from the first tag; By comparing the first tag and the fourth tag field by field, a second field in which the fourth tag differs from the first tag is obtained; Based on the arrangement positions of the first field and the second field in the label, determine the arrangement order of the preferred solutions corresponding to the third label and the fourth label in the first solution set; The tag set includes the first tag and N tags other than the first tag, where N is a positive integer; the determining module is further configured to: The tags in the tag set are vectorized using one-hot encoding to obtain the vector corresponding to each tag in the tag set; Using the vectors corresponding to the first label and the N labels, the similarity between the first label and each of the N labels is calculated to obtain N similarity scores, where the similarity score of each label is a cosine similarity score. Based on the N similarities, the preferred solution corresponding to the first label, and the preferred solutions corresponding to the N labels, a solution set corresponding to the first label is determined.
5. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the fault solution determination method according to any one of claims 1-3.
6. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the program instructions are executed by the processor, they implement the steps of the method for determining a fault solution as described in any one of claims 1-3.