Vehicle part chart query method and device, electronic equipment and storage medium

Abstract

The invention is suitable for the technical field of computer application, and provides a vehicle part chart query method and device, electronic equipment and a storage medium, the method comprises the following steps: in response to a chart query instruction triggered by a user, determining first named entity information corresponding to the chart query instruction; performing vector coding processing on the first named entity information to generate a chart query vector corresponding to the first named entity information; according to the chart query vector and a preset chart vector library, determining a target component chart corresponding to the chart query instruction; and sending the target part chart to the user. Therefore, the named entity information in the user chart query instruction is extracted, the image query vector is generated according to the named entity information, and the component chart corresponding to the chart query instruction is queried through the image query vector, so that the component chart query efficiency and accuracy are improved, and the automobile maintenance efficiency and accuracy are improved.

Description

Technical Field

[0001] This application belongs to the field of computer application technology, and in particular relates to a method, device, electronic device, computer-readable storage medium, and computer program product for querying vehicle component diagrams. Background Technology

[0002] With the development of the social economy and the continuous improvement of people's living standards, automobiles have become an indispensable means of transportation in modern society, and their popularity continues to rise. With the rapid growth in car ownership and the increasing intelligence of vehicles, automobile maintenance has become a crucial link in ensuring road traffic safety, improving vehicle operating efficiency, and extending vehicle lifespan. Efficient and accurate maintenance services not only relate to the travel experience and property safety of car owners, but are also an important foundation for building a safe and efficient transportation system.

[0003] In related technologies, maintenance technicians frequently need to manually consult diagrams of various components across different vehicle models, such as circuit diagrams, terminal diagrams, and assembly diagrams, in their daily work to complete complex fault diagnosis and repair tasks. However, due to the large number of diagrams and the fact that the relationships between these scattered diagrams can only be judged through the experience of maintenance personnel, the efficiency and accuracy of component diagram lookup are low, seriously affecting the efficiency and accuracy of automotive repair. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, electronic device, and computer-readable storage medium for querying vehicle component diagrams, which can solve the problem in the related art that the large number of vehicle component diagrams and the fact that the correlation between the various scattered component diagrams can only be judged by the experience of maintenance personnel, resulting in low efficiency and accuracy of component diagram query, which seriously affects the efficiency and accuracy of automobile repair.

[0005] In a first aspect, embodiments of this application provide a method for querying vehicle component charts, comprising: responding to a chart query command triggered by a user, determining first named entity information corresponding to the chart query command; performing vector encoding processing on the first named entity information to generate a chart query vector corresponding to the first named entity information; determining a target component chart corresponding to the chart query command based on the chart query vector and a preset chart vector library; and sending the target component chart to the user.

[0006] In one possible implementation of the first aspect, after determining the first named entity information corresponding to the chart query command in response to a user-triggered chart query command, the method further includes: Based on the first named entity information, determine the instruction category corresponding to the chart query instruction, wherein the instruction category includes at least one of the following categories: vehicle attribute category and vehicle fault code category.

[0007] Optionally, in another possible implementation of the first aspect, the aforementioned preset chart vector library includes a first preset chart vector library and a second preset chart vector library. The determination of the target component chart corresponding to the chart query instruction based on the chart query vector and the preset chart vector library further includes: When the instruction category is vehicle attribute type, the target component chart is determined based on the chart query vector and the first preset chart vector library; When the instruction category is vehicle fault code, the target component chart is determined based on the chart query vector and the second preset chart vector library; When the instruction category is vehicle attribute type or vehicle fault code type, the first candidate component chart is determined according to the chart query vector and the first preset chart vector library; Based on the chart query vector and the second preset chart vector library, determine the second candidate component chart; The target component diagram is determined based on the first candidate component diagram and the second candidate component diagram.

[0008] Optionally, in another possible implementation of the first aspect, before determining the first named entity information corresponding to the chart query command in response to a user-triggered chart query command, the method further includes: Obtain a diagram of at least one component of at least one vehicle; A pre-defined chart vector library is built based on the charts of each component.

[0009] Optionally, in another possible implementation of the first aspect, the above-mentioned construction of a preset chart vector library based on the charts of each component includes: Named entities are extracted from the charts of each component to generate second named entity information corresponding to each component chart. Based on the second named entity information corresponding to each component chart, a knowledge graph is established for each component chart. The knowledge graph includes the association between each component chart and its corresponding second named entity information. The knowledge graph is vector-encoded to construct a pre-defined graph vector library.

[0010] Optionally, in another possible implementation of the first aspect, the second named entity information includes a second named entity and / or a third named entity, the first named entity includes at least one of brand, vehicle model, and component, the second named entity includes a fault code, and the knowledge graph of each component chart is established based on the second named entity information corresponding to each component chart, including: Based on the second named entity information, a first knowledge graph and a second knowledge graph are established. The first knowledge graph includes the association between each component graph and its corresponding second named entity, and the second knowledge graph includes the association between each component graph and its corresponding third named entity. The knowledge graph is vector-encoded to construct a pre-defined graph vector library, including: Vector encoding is performed on the first knowledge graph and the second knowledge graph respectively to construct the first preset graph vector library and the second preset graph vector library.

[0011] Secondly, this application also provides a device for querying vehicle component diagrams, comprising: a first determining module, configured to determine first named entity information corresponding to the diagram query command in response to a diagram query command triggered by a user; a first generating module, configured to perform vector encoding processing on the first named entity information to generate a diagram query vector corresponding to the first named entity information; a second determining module, configured to determine a target component diagram corresponding to the diagram query command based on the diagram query vector and a preset diagram vector library; and a sending module, configured to send the target component diagram to the user.

[0012] In one possible implementation of the second aspect, the vehicle component diagram query device further includes: The third determining module is used to determine the instruction category corresponding to the chart query instruction based on the first named entity information, wherein the instruction category includes at least one of the following categories: vehicle attribute category and vehicle fault code category.

[0013] Optionally, in another possible implementation of the second aspect, the aforementioned preset chart vector library includes a first preset chart vector library and a second preset chart vector library; correspondingly, the aforementioned second determining module further includes: The first determining unit is used to determine the target component chart based on the chart query vector and the first preset chart vector library when the instruction category is vehicle attribute type. The second determining unit is used to determine the target component chart based on the chart query vector and the second preset chart vector library when the instruction category is vehicle fault code; The third determining unit is used to determine the first candidate component chart based on the chart query vector and the first preset chart vector library when the instruction category is vehicle attribute type and vehicle fault code type. The fourth determining unit is used to determine the second candidate component chart based on the chart query vector and the second preset chart vector library; The fifth determining unit is used to determine the target component chart based on the first candidate component chart and the second candidate component chart.

[0014] Optionally, in another possible implementation of the second aspect, the vehicle component diagram query device further includes: The acquisition module is used to acquire a diagram of at least one component of at least one vehicle. The building module is used to construct a preset chart vector library based on the charts of each component.

[0015] Optionally, in another possible implementation of the second aspect, the aforementioned building module includes: The generation unit is used to extract named entities from the charts of each component and generate the second named entity information corresponding to each chart of each component. The first construction unit is used to build a knowledge graph of each component chart based on the second named entity information corresponding to each component chart. The knowledge graph includes the association between each component chart and the corresponding second named entity information. The second building unit is used to perform vector encoding on the knowledge graph in order to build a pre-defined graph vector library.

[0016] Optionally, in another possible implementation of the second aspect, the aforementioned first building unit is specifically used for: Based on the second named entity information, a first knowledge graph and a second knowledge graph are established. The first knowledge graph includes the association between each component graph and its corresponding second named entity, and the second knowledge graph includes the association between each component graph and its corresponding third named entity. The knowledge graph is vector-encoded to construct a pre-defined graph vector library, including: Vector encoding is performed on the first knowledge graph and the second knowledge graph respectively to construct the first preset graph vector library and the second preset graph vector library.

[0017] Thirdly, this application also provides an electronic device. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the computer program to implement any of the implementations of the first aspect described above.

[0018] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the method of any of the implementations of the first aspect described above.

[0019] Fifthly, this application also provides a computer program product that, when run on an electronic device, causes the electronic device to execute any of the implementation methods of the first aspect described above.

[0020] The beneficial effects of this application embodiment compared with the prior art are as follows: by extracting named entity information from the chart query command triggered by the user, and generating an image query vector based on the named entity information, the corresponding component chart can be queried in the preset chart vector library through the image query vector. This eliminates the need for repair personnel to select scattered component charts based on experience, thereby improving the efficiency and accuracy of component chart query, and thus improving the efficiency and accuracy of automobile repair. Attached Figure Description To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating a method for querying vehicle component diagrams according to an embodiment of this application; Figure 2 This is a schematic diagram of the process for constructing a preset chart vector library according to an embodiment of this application; Figure 3 This is a schematic diagram of the structure of the first knowledge graph provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of the second knowledge graph provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of the vehicle component chart query device provided in the embodiments of this application; Figure 6 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0022] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0023] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0024] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0025] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0026] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0027] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0028] The following description, with reference to the accompanying drawings, details the method, apparatus, electronic device, storage medium, and computer program for querying vehicle component diagrams provided in this application.

[0029] Figure 1 The illustration shows a flowchart of a method for querying vehicle component charts provided in an embodiment of this application.

[0030] Step 101: In response to the chart query command triggered by the user, determine the first named entity information corresponding to the chart query command.

[0031] It should be noted that the vehicle component chart query method of this application embodiment can be executed by the vehicle component chart query device of this application embodiment. The vehicle component chart query device of this application embodiment can be configured in any electronic device to execute the vehicle component chart query method of this application embodiment.

[0032] The chart query command can be triggered by the user or it can be used to query the chart of the target component.

[0033] The first named entity information can be entity words extracted from the chart query command.

[0034] In one possible implementation of this application, the system can receive chart query commands triggered by the user in various ways. For example, the user can enter a chart query command in a dialog box, select elements that make up the chart query command through drop-down menus, checkboxes, etc., and the system can assemble the various elements into a structured chart query command according to the user's selection. Alternatively, the user can ask a question by voice through a microphone, etc., and the system can convert the voice question into a text-type chart query command through voice recognition technology.

[0035] For example, the chart query command q1 can be "Please give me the engine-related charts for model B of brand A", or the chart query command q2 can be "Display all charts related to fault code P001", etc.

[0036] It should be noted that the chart query commands listed above are merely illustrative. In actual use, they can be determined according to actual usage needs and application scenarios. This application embodiment does not limit them in this regard.

[0037] As one possible implementation, in response to a user-triggered chart query command, named entities in the chart query command can be extracted according to preset extraction rules, and first named entity information can be generated based on the extracted named entities.

[0038] For example, the preset extraction rules can be to extract named entities such as brand, model, part, and fault code from the chart query command, but are not limited to this.

[0039] As an example, extraction can be performed using a pre-trained model, such as an "Enhanced Representation through Knowledge Integration (ERNIE) model" finely tuned using text from the automotive repair domain and pre-defined extraction rules.

[0040] As another example, named entity extraction can be performed using rule-based or dictionary-based methods. A dictionary of brands, models, parts, and fault codes can be built according to preset extraction rules, and extraction can be performed by string matching.

[0041] For example, if the chart query command q1 is "Please give me the engine-related charts for Brand A, Model B", the named entities are "Brand A", "Model B", and "Engine", and the first named entity information is "Brand A, Model B, Engine". If the chart query command q2 is "Display all charts related to fault code P001", the named entity is "P001", and the first named entity information is "P001". Optionally, after determining the first named entity information, the chart query instructions can be categorized based on the first named entity information. That is, in one possible implementation of this application, after step 101 above, the following may also be included: Based on the first named entity information, determine the instruction category corresponding to the chart query instruction.

[0042] The instruction category may include at least one of the following categories: vehicle attribute category, vehicle fault code category, but is not limited to these.

[0043] In one possible implementation of this application, the instruction category corresponding to the chart query instruction can be determined based on the named entity contained in the first named entity information.

[0044] As an example, if the first named entity information only contains named entities related to vehicle attributes such as brand, model, or component, then the instruction category of the chart query command can be determined to be the vehicle attribute category. If the first named entity information only contains named entities related to fault codes, then the instruction category of the chart query command can be determined to be the vehicle fault code category. If the first named entity information contains both named entities related to vehicle attributes and named entities of the fault code category, then the instruction category of the chart query command can be determined to be both the vehicle attribute category and the vehicle fault code category.

[0045] For example, if the chart query command q1 is "Please give me charts related to the engine of brand A, model B", and the first named entity information contains the named entities "Brand A", "Model B", and "Engine", all of which are vehicle attribute-related named entities, then the command type of chart query command q1 can be determined to be vehicle attribute type. If the chart query command q2 is "Display all charts related to fault code P001", and the first named entity information contains the named entity "P001", where "P001" is a fault code-related named entity, then the command type of chart query command q2 can be determined to be vehicle fault code type. If the chart query command q3 is "Please give me charts related to engine fault code P001 of brand A, model B", and the first named entity information contains the named entities "Brand A", "Model B", "Engine", and "P001", which includes both vehicle attribute-related named entities ("Brand A", "Model B", "Engine") and fault code-related named entities ("P001"), then the command type of chart query command q3 can be determined to be both vehicle attribute type and vehicle fault code type.

[0046] This allows for narrowing down the search scope of target component charts based on the command category of the chart query, thereby improving the efficiency of vehicle component chart queries.

[0047] Step 102: Perform vector encoding processing on the first named entity information to generate the chart query vector corresponding to the first named entity information.

[0048] As one possible implementation, the first named entity information can be vector-encoded using a pre-defined large model (such as an embedding model) to generate a graph query vector containing deep semantic information of the first named entity information.

[0049] Step 103: Determine the target component chart corresponding to the chart query command based on the chart query vector and the preset chart vector library.

[0050] The target component diagram can be a circuit diagram, terminal diagram, etc., but is not limited to these.

[0051] In one possible implementation of this application, the preset chart vector library may include each unique identifier corresponding to each component chart and the description information vector of each component chart corresponding to each unique identifier. The chart query vector can be matched with the description information vector of each component chart in the preset chart vector library, and the K unique identifiers corresponding to the top K (K is an integer greater than or equal to 1) description information vectors with the highest matching degree with the chart query vector can be determined, and the component charts corresponding to these K unique identifiers are determined as the target component charts.

[0052] In this way, not only can the most relevant component charts be retrieved, but also K-1 other charts related to the chart query command can be retrieved, improving the accuracy and efficiency of vehicle component chart queries.

[0053] In one possible implementation of this application, the preset chart vector library can be pre-built based on various charts for different vehicles. That is, in one possible implementation of this application, before step 101 above, the following may also be included: Step 201: Obtain a diagram of at least one component of at least one vehicle; Step 202: Construct a preset chart vector library based on the charts of each component.

[0054] One type of vehicle can be all vehicles of a single model under a single brand.

[0055] For example, all vehicles of brand A with model B are considered as one type of vehicle.

[0056] One possible implementation is to obtain a diagram of at least one component of at least one model of a vehicle under at least one brand. For example, this could be a circuit diagram or structural diagram of a component such as an engine or high-voltage battery pack for various models of vehicle brand A. However, this is not the only option.

[0057] In one possible implementation, a description information vector for each component chart can be generated based on the description information of each component chart, and a preset chart vector library can be constructed based on each description information vector.

[0058] For example, a pre-defined chart vector library can be constructed based on the knowledge graph of each component chart to make the semantic description of each component chart richer and more accurate, thereby improving the accuracy of vehicle component chart queries. That is, in one possible implementation of this application, step 202 above may include: Named entities are extracted from the charts of each component to generate second named entity information corresponding to each component chart. Based on the second named entity information corresponding to each component chart, a knowledge graph is established for each component chart. The knowledge graph includes the association between each component chart and its corresponding second named entity information. The knowledge graph is vector-encoded to construct a pre-defined graph vector library.

[0059] In one possible implementation of this application, firstly, named entities corresponding to each component chart can be extracted. For example, optical character recognition (OCR) can be used to identify the component charts, parse their metadata, and associate documents. Next, based on the extracted named entities, second named entity information for each component chart can be generated. The specific extraction method and the method for generating second named entity information based on the extracted named entities can be referred to the above description of the method for extracting chart query instructions and generating first named entity information; these details will not be repeated here.

[0060] In one possible implementation of this application, each component chart (which can be represented by a unique identifier corresponding to the component chart) and the named entities in the second named entity information of the component chart can be used as entity nodes of the knowledge graph. Based on the association between each named entity and the corresponding component chart configured by the user, edges connecting each component chart and the corresponding entity node in the knowledge graph are generated, thereby establishing the knowledge graph of each component chart.

[0061] For example, suppose the unique identifier of the component chart is chart-01 (hereinafter referred to as component chart chart-01), and the second named entity information is "XX1, 2025, headlight assembly, P020". Based on the association between each named entity configured by the user and the corresponding component chart, the following knowledge graph of component chart chart-01 represented by triples can be established: "(chart-01) - [Description of component] - (headlight assembly), (chart-01) - [belongs to brand] - (XX1), (chart-01) - [belongs to model] - (2025), (chart-01) - [fault code] - (P020)".

[0062] As one possible implementation, the knowledge graph can be vector-encoded. For example, the local network centered on each component graph (e.g., all nodes within one hop of the component graph) can be extracted from the knowledge graph. Based on the local network corresponding to each component graph, description information for each component graph can be generated. The description information can then be vector-encoded using a pre-defined large model (e.g., an embedding model) to generate description information vectors for each component graph. Based on the description information vectors for each component graph, a pre-defined graph vector library can be constructed. The pre-defined graph vector library can include each unique identifier of each component graph and its corresponding description information vector.

[0063] For example, based on the knowledge graph of the component chart with the unique identifier chart-01 listed above, the description information of component chart chart-01 can be generated as "Circuit diagram of the headlight assembly of XX1 brand 2025 model, fault code P020". Assuming that the description information vector of the above description information is [0.9, 0.1, 0.3], then in the preset chart vector library, the unique identifier and description information vector of this component chart can be represented as "chart-01: [0.9, 0.1, 0.3]".

[0064] In this way, a knowledge graph is constructed based on the second named entity information of each component chart, and then a description information vector is generated based on the knowledge graph. Each description information vector includes the relationship between each component chart and its corresponding named entity, thereby making the semantic description of each component chart richer and more accurate, and thus improving the accuracy of vehicle component chart queries.

[0065] Taking the second named entity information with the unique identifier chart-01 as an example, if a knowledge graph is not constructed and the second named entity information is directly vector-encoded, the semantics represented by "2025" cannot be determined. For example, "2025" may represent the vehicle model or the vehicle fault code, which may lead to an incorrect description of the component chart.

[0066] It should be noted that, in the embodiments of this application, the method for vector encoding of the description information can be the same as the method for vector encoding of the first named entity information, thereby improving the accuracy of determining the target component chart based on vector matching through the same vector encoding rules.

[0067] For example, the second named entity information may include a second named entity and / or a third named entity. The second named entity may include at least one of brand, vehicle model, and component. The third named entity may include a fault code. The above-mentioned knowledge graph of each component chart is established based on the second named entity information corresponding to each component chart, which may include: Based on the second named entity information, a first knowledge graph and a second knowledge graph are established. The first knowledge graph includes the association between each component graph and its corresponding second named entity, and the second knowledge graph includes the association between each component graph and its corresponding third named entity. The aforementioned vector encoding process for knowledge graphs to construct a pre-defined graph vector library may include: Vector encoding is performed on the first knowledge graph and the second knowledge graph respectively to construct the first preset graph vector library and the second preset graph vector library.

[0068] In one possible implementation of this application, based on the association between each second named entity configured by the user and the corresponding component chart, each component chart (which can be represented by the unique identifier corresponding to the component chart) and each second named entity in the second named entity information of the component chart are used as entity nodes of the knowledge graph to establish a knowledge graph for each component chart and generate a first knowledge graph. In the first knowledge graph, only the association between each component chart and second named entities such as brand, model, and component may be included, and the correspondence between component chart and fault code may not be included.

[0069] For example, assuming the second named entity information of component chart-02 is "XX2, 10, headlight, P030", then the second named entities corresponding to component chart-02 are "XX2", "10", and "headlight". The second named entity information of component chart-03 (a chart showing different fault causes for components of the same brand and model as component chart-02) is "XX2, 10, headlight, P040", then the second named entities corresponding to component chart-03 are also "XX2", "10", and "headlight". The second named entity information of component chart-04 is "XX2, 20, headlight, P050", then the second named entities corresponding to component chart-04 are "XX2", "20", and "headlight". The first knowledge graph constructed based on the second named entity information corresponding to component charts-02, chart-03, and chart-04 can be as follows: Figure 3 As shown.

[0070] It should be noted that, in the embodiments of this application, the second named entities corresponding to different component diagrams may be the same.

[0071] It should be noted that if the second named entity information of a component diagram does not include a second named entity, then the first knowledge graph may not include that component diagram.

[0072] In one possible implementation of this application, based on the association between each third named entity configured by the user and the corresponding component chart, each component chart (which can be represented by the unique identifier corresponding to the component chart) and each third named entity in the second named entity information of the component chart are used as entity nodes of the knowledge graph to establish a knowledge graph for each component chart and generate a second knowledge graph. In the second knowledge graph, only the association between each component chart and the fault code may be included, and the correspondence between the component chart and the brand, model and component may not be included.

[0073] For example, if the second named entity information corresponding to component charts -02, -03, and -04 is as shown above, and the second named entity information for chart -05 is "XX3, 50, engine, P050", then the third named entity corresponding to chart -02 is "P030", the third named entity corresponding to chart -03 is "P040", and the third named entity corresponding to chart -04 and chart -05 is "P050". The second knowledge graph constructed based on the second named entity information corresponding to chart -02, chart -03, chart -04, and chart -05 can be as follows: Figure 4 As shown.

[0074] It should be noted that in the embodiments of this application, the third named entities corresponding to different component diagrams may be the same.

[0075] In one possible implementation of this application, the first knowledge graph can be vector-encoded, and a first preset graph vector library can be constructed. The first preset graph vector library may include unique identifiers corresponding to one or more component graphs and descriptive information vectors for each component graph corresponding to each unique identifier. Similarly, the second knowledge graph can be vector-encoded, and a second preset graph vector library can be constructed. The second preset graph vector library may include unique identifiers corresponding to one or more component graphs and descriptive information vectors for each component graph corresponding to each unique identifier. Specific vector encoding methods and methods for constructing the first and second preset graph vector libraries can be found in the description of "vector encoding the knowledge graph to construct the preset graph vector library" in the above embodiments, and will not be repeated here.

[0076] For example, a preset chart vector library matching the chart query command can be determined based on the command category of the chart query command. That is, in one possible implementation of this application, the preset chart vector library includes a first preset chart vector library and a second preset chart vector library, and step 103 may include: When the instruction category is vehicle attribute type, the target component chart is determined based on the chart query vector and the first preset chart vector library; When the instruction category is vehicle fault code, the target component chart is determined based on the chart query vector and the second preset chart vector library; When the instruction category is vehicle attribute type or vehicle fault code type, the first candidate component chart is determined according to the chart query vector and the first preset chart vector library; Based on the chart query vector and the second preset chart vector library, determine the second candidate component chart; The target component diagram is determined based on the first candidate component diagram and the second candidate component diagram.

[0077] In one possible implementation of this application, when the instruction category of the chart query vector is a vehicle attribute class, the chart query vector can be matched with the description information vectors of each component chart in the first preset chart vector library, and the K unique identifiers corresponding to the top K description information vectors with the highest matching degree with the chart query vector can be determined, and the component charts corresponding to these K unique identifiers can be determined as the target component charts.

[0078] For example, K is 2, assuming the first preset chart vector library is based on, for example, Figure 3 The first knowledge graph shown includes the description information vectors corresponding to the unique identifiers chart-02, chart-03, and chart-04 of the component charts. If the chart query instruction is "Hello, please help me query the headlight related charts for model 10 of XX2" (the chart query instruction only includes named entities of the vehicle attribute class, and the instruction category is vehicle attribute class), it can be determined that the target component charts are the component charts corresponding to the unique identifier "chart-02" and the component charts corresponding to the unique identifier "chart-03".

[0079] In one possible implementation of this application, when the instruction category of the chart query vector is a vehicle fault code, the chart query vector can be matched with the description information vectors of each component chart in the second preset chart vector library, and the K unique identifiers corresponding to the top K description information vectors with the highest matching degree with the chart query vector can be determined, and the component charts corresponding to these K unique identifiers can be determined as the target component charts.

[0080] For example, K is 2, assuming the second preset chart vector library is based on, for example, Figure 4 The second knowledge graph shown includes description information vectors corresponding to the unique identifiers chart-02, chart-03, chart-04, and chart-05. If the chart query command is "Hello, please help me query the charts related to fault code P050" (the chart query command only includes named entities of the vehicle fault code class, and the command category is vehicle fault code class), the target component charts can be determined to be the component charts corresponding to the unique identifier "chart-04" and the component charts corresponding to the unique identifier "chart-05".

[0081] In one possible implementation of this application, when the instruction category of the chart query vector is a vehicle attribute class or a vehicle fault code class, the chart query vector can be matched with the description information vectors of each component chart in the first preset chart vector library and the second preset chart vector library, respectively. K unique identifiers corresponding to the top K description information vectors with the highest matching degree to the chart query vector in the first preset chart vector library can be determined, and the component charts corresponding to these K unique identifiers are identified as first candidate component charts. Similarly, K unique identifiers corresponding to the top K description information vectors with the highest matching degree to the chart query vector in the second preset chart vector library can be determined, and the component charts corresponding to these K unique identifiers are identified as second candidate component charts. The intersection of the first candidate component charts and the second candidate component charts can be identified as the target component chart.

[0082] For example, if K is 2, and the chart query command is "Hello, please help me query the headlight chart for vehicle model XX2 of vehicle type 10 with fault code P050" (the chart query command includes named entities of vehicle attribute class and vehicle fault code class, and the command category is vehicle attribute class and vehicle fault code class), then the first candidate component chart can be determined as the component chart corresponding to the unique identifiers "chart-04" and "chart-02 (or chart-03)", and the second candidate component chart is the component chart corresponding to the unique identifiers "chart-04" and "chart-05". The intersection of the first and second candidate component charts is the component chart corresponding to the unique identifier "chart-04", so the component chart corresponding to the unique identifier "chart-04" can be determined as the target component chart.

[0083] In this way, different preset chart vector libraries and chart query vectors can be selected for matching according to different instruction categories, thereby improving the efficiency and accuracy of vehicle component chart queries.

[0084] Step 104: Send the target component diagram to the user.

[0085] In one possible implementation, K target component charts can be sent to the user who triggers the corresponding chart query command.

[0086] The vehicle component chart query method provided in this application extracts named entity information from the chart query command triggered by the user and generates an image query vector based on the named entity information. The corresponding component chart is then queried from a preset chart vector library using the image query vector. This eliminates the need for repair personnel to select from scattered component charts based on experience, thereby improving the efficiency and accuracy of component chart query and ultimately enhancing the efficiency and accuracy of automobile repair.

[0087] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0088] Corresponding to the vehicle component chart query method described in the above embodiments, Figure 5 A structural block diagram of a vehicle component chart query device provided in an embodiment of this application is shown. For ease of explanation, only the parts related to the embodiment of this application are shown.

[0089] Reference Figure 5 The device 50 includes: The first determining module 51 is used to determine the first named entity information corresponding to the chart query command in response to the chart query command triggered by the user. The first generation module 52 is used to perform vector encoding processing on the first named entity information to generate a chart query vector corresponding to the first named entity information. The second determining module 53 is used to determine the target component chart corresponding to the chart query command based on the chart query vector and the preset chart vector library; Sending module 54 is used to send the target component diagram to the user.

[0090] In practical use, the vehicle component chart query device provided in this application embodiment can be configured in any electronic device to execute the aforementioned vehicle component chart query method.

[0091] The vehicle component chart query device provided in this application extracts named entity information from the chart query command triggered by the user and generates an image query vector based on the named entity information. The corresponding component chart is then queried from a preset chart vector library using the image query vector. This eliminates the need for repair personnel to select from scattered component charts based on experience, thereby improving the efficiency and accuracy of component chart queries and ultimately improving the efficiency and accuracy of automobile repair.

[0092] In one possible implementation of this application, the vehicle component diagram query device 50 further includes: The third determining module is used to determine the instruction category corresponding to the chart query instruction based on the first named entity information, wherein the instruction category includes at least one of the following categories: vehicle attribute category and vehicle fault code category.

[0093] Optionally, in another possible implementation of this application, the aforementioned preset chart vector library includes a first preset chart vector library and a second preset chart vector library; correspondingly, the aforementioned second determining module 53 further includes: The first determining unit is used to determine the target component chart based on the chart query vector and the first preset chart vector library when the instruction category is vehicle attribute type. The second determining unit is used to determine the target component chart based on the chart query vector and the second preset chart vector library when the instruction category is vehicle fault code; The third determining unit is used to determine the first candidate component chart based on the chart query vector and the first preset chart vector library when the instruction category is vehicle attribute type and vehicle fault code type. The fourth determining unit is used to determine the second candidate component chart based on the chart query vector and the second preset chart vector library; The fifth determining unit is used to determine the target component chart based on the first candidate component chart and the second candidate component chart.

[0094] Optionally, in another possible implementation of this application, the vehicle component diagram query device 50 further includes: The acquisition module is used to acquire a diagram of at least one component of at least one vehicle. The building module is used to construct a preset chart vector library based on the charts of each component.

[0095] Optionally, in one possible implementation of this application, the above-mentioned building module includes: The generation unit is used to extract named entities from the charts of each component and generate the second named entity information corresponding to each chart of each component. The first construction unit is used to build a knowledge graph of each component chart based on the second named entity information corresponding to each component chart. The knowledge graph includes the association between each component chart and the corresponding second named entity information. The second building unit is used to perform vector encoding on the knowledge graph in order to build a pre-defined graph vector library.

[0096] Optionally, in another possible implementation of this application, the first building unit described above is specifically used for: Based on the second named entity information, a first knowledge graph and a second knowledge graph are established. The first knowledge graph includes the association between each component graph and its corresponding second named entity, and the second knowledge graph includes the association between each component graph and its corresponding third named entity. The knowledge graph is vector-encoded to construct a pre-defined graph vector library, including: Vector encoding is performed on the first knowledge graph and the second knowledge graph respectively to construct the first preset graph vector library and the second preset graph vector library.

[0097] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0098] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0099] To implement the above embodiments, this application also proposes an electronic device.

[0100] Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application.

[0101] like Figure 6 As shown, the above-mentioned electronic device 200 includes: The system includes a memory 210 and at least one processor 220, and a bus 230 connecting different components (including the memory 210 and the processor 220). The memory 210 stores a computer program, which, when executed by the processor 220, implements the vehicle component chart query method described in this application embodiment.

[0102] Bus 230 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0103] Electronic device 200 typically includes a variety of electronic device readable media. These media can be any available media that can be accessed by electronic device 200, including volatile and non-volatile media, removable and non-removable media.

[0104] Memory 210 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 240 and / or cache memory 250. Electronic device 200 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 260 may be used to read and write non-removable, non-volatile magnetic media (… Figure 6 Not shown; usually referred to as a "hard drive"). Although Figure 6 As not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 230 via one or more data media interfaces. Memory 210 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0105] A program / utility 280 having a set (at least one) of program modules 270 may be stored in, for example, memory 210. Such program modules 270 include—but are not limited to—an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 270 typically perform the functions and / or methods described in the embodiments of this application.

[0106] Electronic device 200 can also communicate with one or more external devices 290 (e.g., keyboard, pointing device, display 291, etc.), and with one or more devices that enable a user to interact with electronic device 200, and / or with any device that enables electronic device 200 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 292. Furthermore, electronic device 200 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 293. As shown, network adapter 293 communicates with other modules of electronic device 200 via bus 230. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0107] The processor 220 performs various functional applications and data processing by running programs stored in the memory 210.

[0108] It should be noted that the implementation process and technical principles of the electronic device in this embodiment are explained in the foregoing description of the method for querying vehicle component diagrams in this application embodiment, and will not be repeated here.

[0109] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0110] This application provides a computer program product that, when run on an electronic device, enables the electronic device to perform the steps described in the various method embodiments above.

[0111] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a photographic device / electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0112] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0113] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0114] In the embodiments provided in this application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings or direct couplings or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0115] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0116] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for querying vehicle component diagrams, characterized in that, include: In response to a chart query command triggered by a user, determine the first named entity information corresponding to the chart query command; The first named entity information is vector encoded to generate a chart query vector corresponding to the first named entity information; Based on the chart query vector and the preset chart vector library, determine the target component chart corresponding to the chart query command; Send the target component diagram to the user.

2. The method as described in claim 1, characterized in that, After determining the first named entity information corresponding to the chart query command triggered by the user, the method further includes: Based on the first named entity information, the instruction category corresponding to the chart query instruction is determined, wherein the instruction category includes at least one of the following categories: vehicle attribute category and vehicle fault code category.

3. The method as described in claim 2, characterized in that, The preset chart vector library includes a first preset chart vector library and a second preset chart vector library. The step of determining the target component chart corresponding to the chart query instruction based on the chart query vector and the preset chart vector library includes: When the instruction category is the vehicle attribute category, the target component chart is determined according to the chart query vector and the first preset chart vector library; When the instruction category is the vehicle fault code category, the target component chart is determined according to the chart query vector and the second preset chart vector library; When the instruction category is the vehicle attribute category and the vehicle fault code category, the first candidate component chart is determined according to the chart query vector and the first preset chart vector library; Based on the chart query vector and the second preset chart vector library, determine the second candidate component chart; The target component chart is determined based on the first candidate component chart and the second candidate component chart.

4. The method according to any one of claims 1-3, characterized in that, Before determining the first named entity information corresponding to the chart query command triggered by the user, the method further includes: Obtain a diagram of at least one component of at least one vehicle; Based on the diagrams of each component, construct the preset diagram vector library.

5. The method as described in claim 4, characterized in that, The step of constructing the preset chart vector library based on the charts of each component includes: Named entities are extracted from each of the component charts to generate second named entity information corresponding to each of the component charts. Based on the second named entity information corresponding to each component chart, a knowledge graph is established for each component chart, wherein the knowledge graph includes the association between each component chart and the corresponding second named entity information; The knowledge graph is vector encoded to construct the preset graph vector library.

6. The method as described in claim 5, characterized in that, The second named entity information includes a second named entity and / or a third named entity. The first named entity includes at least one of brand, vehicle model, and component. The second named entity includes a fault code. The step of establishing a knowledge graph for each component chart based on the second named entity information corresponding to each component chart includes: Based on the second named entity information, a first knowledge graph and a second knowledge graph are established, wherein the first knowledge graph includes the association between each component graph and the corresponding second named entity, and the second knowledge graph includes the association between each component graph and the corresponding third named entity. The step of performing vector encoding processing on the knowledge graph to construct the preset graph vector library includes: The first knowledge graph and the second knowledge graph are respectively subjected to vector encoding processing to construct the first preset chart vector library and the second preset chart vector library.

7. A device for querying vehicle component diagrams, characterized in that, include: The first determining module is used to determine the first named entity information corresponding to the chart query command in response to the chart query command triggered by the user. The first generation module is used to perform vector encoding processing on the first named entity information to generate a chart query vector corresponding to the first named entity information. The second determining module is used to determine the target component chart corresponding to the chart query instruction based on the chart query vector and the preset chart vector library; The sending module is used to send the target component chart to the user.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it causes the electronic device to implement the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by an electronic device, it implements the method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes a computer program that, when run on an electronic device, causes the electronic device to perform the method as described in any one of claims 1-6.

Images