Diagnostic method, device and equipment of new energy automobile and storage medium

Abstract

The invention discloses a new energy automobile diagnosis method, device and equipment and a storage medium, and belongs to the field of new energy automobiles. The method comprises the steps that a fault knowledge graph is acquired, the fault knowledge graph is constructed based on a triple in empirical data of the new energy automobile, and the triple is used for indicating the incidence relation between entities in the empirical data; identifying a first entity in a user inquiry statement and a first association relationship corresponding to an inquiry intention of the user inquiry statement; and generating reply content of the user inquiry statement according to a second entity, wherein the second entity comprises an entity having the first association relationship with the first entity in the fault knowledge graph.

Description

Technical Field

[0001] The present application relates to the field of new energy vehicles, and in particular to a diagnostic method, device, equipment and storage medium for new energy vehicles. Background Art

[0002] New energy vehicles are very different from traditional fuel vehicles in principle and structure. They have multiple controllers, which are connected by wiring harnesses and connectors. The connectors are composed of many pins. Damage to a single pin may cause the new energy vehicle to malfunction or even fail to work properly.

[0003] During maintenance, maintenance personnel need to find the cause of the fault based on the fault phenomenon and fault code, but there is a many-to-many relationship between the fault phenomenon and fault code and the fault cause, so it is extremely difficult to determine the cause of the fault. Summary of the invention

[0004] The present application provides a new energy vehicle diagnostic method, device, equipment and storage medium, which can enrich the diagnostic methods of new energy vehicles. The technical solution is as follows:

[0005] According to one aspect of the present application, a new energy vehicle diagnosis method is provided, the method comprising:

[0006] Acquire a fault knowledge graph, wherein the fault knowledge graph is constructed based on triples in the experience data of the new energy vehicle, and the triples are used to indicate association relationships between entities in the experience data;

[0007] Identify a first entity in a user query statement and a first association relationship corresponding to a query intent of the user query statement;

[0008] A reply content of the user query statement is generated according to a second entity, wherein the second entity includes an entity in the fault knowledge graph that has the first association relationship with the first entity.

[0009] According to another aspect of the present application, a diagnostic device for a new energy vehicle is provided, the device comprising:

[0010] A knowledge graph module, used to obtain a fault knowledge graph, wherein the fault knowledge graph is constructed based on triples in the experience data of the new energy vehicle, and the triples are used to indicate the association relationship between entities in the experience data;

[0011] An identification module, used to identify a first entity in a user query statement and a first association relationship corresponding to the query intention of the user query statement;

[0012] A generation module is used to generate a reply content of the user query statement according to a second entity, wherein the second entity includes an entity in the fault knowledge graph that has the first association relationship with the first entity.

[0013] According to another aspect of the present application, a computer device is provided, which includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set are loaded and executed by the processor to implement the diagnostic method for new energy vehicles as described above.

[0014] According to another aspect of the present application, a computer-readable storage medium is provided, in which at least one instruction, at least one program, a code set or an instruction set is stored. The at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement the diagnostic method for new energy vehicles as described above.

[0015] According to another aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the diagnostic method for a new energy vehicle provided in various optional implementations of the above aspects.

[0016] The beneficial effects of the technical solution provided by this application include at least:

[0017] Generate a fault knowledge graph based on the empirical data of new energy vehicle diagnosis. Use knowledge graph technology to extract knowledge from unstructured empirical data such as maintenance cases and make use of it. According to the maintenance personnel's query statements, the diagnosis system can quickly match the diagnosis results from the fault knowledge graph and feedback the diagnosis results to the maintenance personnel in various ways, so that the maintenance personnel can quickly determine the cause and solution of the fault, effectively assist the maintenance personnel in troubleshooting and maintenance work, and improve maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1is a schematic diagram of the structure of a computer system provided by an exemplary embodiment of the present application;

[0020] Figure 2 is a flow chart of a diagnostic method for a new energy vehicle provided by an exemplary embodiment of the present application;

[0021] Figure 3 is a schematic diagram of a fault knowledge graph provided by an exemplary embodiment of the present application;

[0022] Figure 4 is a schematic diagram of a fault knowledge graph provided by an exemplary embodiment of the present application;

[0023] Figure 5 is a schematic diagram of a diagnostic system provided by an exemplary embodiment of the present application;

[0024] Figure 6 is a flow chart of a diagnostic method for a new energy vehicle provided by an exemplary embodiment of the present application;

[0025] Figure 7 is a schematic diagram of an entity relationship extraction model provided by an exemplary embodiment of the present application;

[0026] Figure 8 is a schematic diagram of a matrix provided by an exemplary embodiment of the present application;

[0027] Fig. 9 is a schematic diagram of a diagnostic system provided by an exemplary embodiment of the present application;

[0028] Fig.10 is a schematic diagram of a diagnostic system provided by an exemplary embodiment of the present application;

[0029] Fig.11 is a schematic diagram of a reply knowledge graph provided by an exemplary embodiment of the present application;

[0030] Fig.12 is a flow chart of a diagnostic method for a new energy vehicle provided by an exemplary embodiment of the present application;

[0031] Fig.13 is a schematic diagram of an entity recognition model provided by an exemplary embodiment of the present application;

[0032] Fig.14 is a schematic diagram of a relationship classification model provided by an exemplary embodiment of the present application;

[0033] Fig.15 It is a structural schematic diagram of a diagnostic device for a new energy vehicle provided by an exemplary embodiment of the present application;

[0034] Fig.16It is a structural diagram of a computer device provided by an exemplary embodiment of the present application.

[0035] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application. DETAILED DESCRIPTION

[0036] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below with reference to the accompanying drawings.

[0037] Figure 1 A schematic diagram of a computer system provided by an exemplary embodiment of the present application is shown, and the computer system may include a terminal device 101 and a server 103 .

[0038] Exemplarily, the diagnostic method for new energy vehicles shown in the embodiment of the present application can be applied in a terminal device, and the terminal device 101 runs an application 102 that supports the fault diagnosis function of new energy vehicles. The terminal device may include a vehicle-mounted terminal, a mobile phone, a tablet computer, a notebook computer, a laptop computer, a desktop computer, an all-in-one computer, an Internet of Things device, an intelligent robot workstation, a television, a set-top box, smart glasses, a smart watch, a digital camera, an MP4 player, an MP5 player, a learning machine, a point-reading machine, an electronic paper book, an electronic dictionary, a virtual reality (VR) player or an augmented reality (AR) player, etc.

[0039] The terminal device 101 includes a first memory and a first processor. The first memory stores a diagnostic program for a new energy vehicle; the diagnostic program for the new energy vehicle is called and executed by the first processor to implement the diagnostic method for a new energy vehicle provided in the present application. The first memory may include but is not limited to the following: random access memory (RAM), read only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), and electrically erasable read-only memory (EEPROM).

[0040] The first processor may be composed of one or more integrated circuit chips. Optionally, the first processor may be a general-purpose processor, such as a central processing unit (CPU) or a network processor (NP). Optionally, the first processor may implement the diagnostic method for new energy vehicles provided in the present application by running a program or code.

[0041] In an optional embodiment, the terminal device 101 and the server 103 may be connected to each other via a wired or wireless network.

[0042] The server 103 is used to provide background services for the terminal device 101. Optionally, the server 103 undertakes the main computing work, and the terminal device 101 undertakes the secondary computing work; or, the server 103 undertakes the secondary computing work, and the terminal device 101 undertakes the main computing work; or, the server 103 and the terminal device 101 adopt a distributed computing architecture to perform collaborative computing.

[0043] The server 103 may be a single server, or a server cluster consisting of multiple servers, or a cloud computing service center.

[0044] Optionally, the server 103 includes a second memory and a second processor. The second memory stores a diagnostic program for new energy vehicles; the diagnostic program for new energy vehicles is called by the second processor to implement the diagnostic method for new energy vehicles provided in this application. Optionally, the second memory may include but is not limited to the following: RAM, ROM, PROM, EPROM, EEPROM. Optionally, the second processor may be a general-purpose processor, such as a CPU or NP.

[0045] Figure 2 FIG. 1 is a flow chart of a diagnostic method for a new energy vehicle provided by an exemplary embodiment of the present application. The method can be used for Figure 1 The terminal device shown in the figure. The method comprises the following steps.

[0046] Step 210: Obtain a fault knowledge graph, where the fault knowledge graph is constructed based on triples in the empirical data of new energy vehicles, where triples are used to indicate associations between entities in the empirical data.

[0047] The fault knowledge graph is a knowledge graph constructed using empirical data from the field of new energy vehicle maintenance. A knowledge graph is a structured knowledge base that stores and displays information about entities (such as automotive components, fault phenomena, causes of faults, vehicle models, vehicle brands, solutions, fault codes, meanings of fault codes, etc.) and their relationships. A knowledge graph is usually represented in the form of a graph, which contains nodes (representing entities) and edges (representing relationships between entities). The knowledge graph organizes information into a structure that is easier to understand and analyze.

[0048] The fault knowledge graph is constructed based on triples extracted from empirical data. A triple consists of three parts:

[0049] Subject: represents an entity, usually a node in the knowledge graph. The entity can be at least one of component unit, fault phenomenon, fault cause, vehicle model, vehicle brand, solution, fault code, and fault code meaning.

[0050] Predicate: describes the relationship between the subject and the object. In the knowledge graph, the predicate is usually represented as an association or attribute, such as "belongs to", "is located in", "leads to", etc. The predicate defines how the subject and the object are related.

[0051] Object: represents another entity or a specific attribute value. It is usually another node in the knowledge graph that is connected to the subject through a predicate, or a specific attribute value (such as a date, number, etc.).

[0052] The three parts together form a triple, which can be expressed as (subject, predicate, object). For example, in the fault knowledge graph, a triple representing the cause of a fault may be (power limit indicator light, fault cause, motor electric water pump fault), where "power limit indicator light" is the entity of the subject, "fault cause" is the association relationship of the predicate, and "motor electric water pump fault" is the entity of the object.

[0053] Therefore, a triplet extracted based on empirical data may include: a first entity, a second entity, and an association relationship between the first entity and the second entity; or a triplet may include: a first entity, an attribute of the first entity, and a specific attribute value of the attribute. This embodiment is only described by taking the example of a predicate including an association relationship.

[0054] The experience data is data related to the maintenance or diagnosis of new energy vehicles. For example, the experience data may include at least one of maintenance cases, relevant papers, expert experience, technical data, etc.

[0055] For example, for different systems of new energy vehicles, we can collect experience data corresponding to different systems, build fault knowledge graphs corresponding to each system, reduce the data volume of a single fault knowledge graph, and improve fault diagnosis efficiency. For example, we can collect maintenance cases of high-voltage systems of new energy vehicles, build fault knowledge graphs corresponding to high-voltage systems, and diagnose faults of high-voltage systems.

[0056] Of course, it is also possible to build a fault knowledge graph based on the empirical data of all systems of new energy vehicles. The fault knowledge graph can deeply analyze the mutual influence of faults between different systems, which helps to diagnose faults more accurately.

[0057] In an optional embodiment, the terminal device may also display an experience data reporting interface in the user interface of the diagnostic system, guide the user to fill in triples of experience data in the user interface, and update the fault knowledge graph in real time based on the triples filled in by the user.

[0058] In another optional embodiment, the terminal device may start collecting relevant data of the new energy vehicle, such as fault codes, detection data of various systems, and other information, after the diagnostic system alarms, and stop collecting relevant data of the energy vehicle after the alarm is resolved, and input the fault code and related data into the analysis model to obtain empirical data of the fault. The empirical data may include at least one of the above-mentioned entities and the association between entities.

[0059] Exemplarily, the experience data can be natural language text, chart data, or database data. The terminal device can perform natural language understanding on the experience data and extract triples from it; or the terminal device can call a neural network model to identify triples in the experience data and then build a fault knowledge graph based on the triples.

[0060] For example, Figure 3 As shown, the entities in the triplet may include at least one of the following entity types: vehicle brand 301, vehicle model 302, fault phenomenon 303, fault cause 304, solution 305, component unit 306, fault code 307, and fault code meaning 308. Each entity type may include at least one entity.

[0061] Among them, the vehicle brand may include at least one of the following: brand name, brand number, brand icon, brand abbreviation. The vehicle model refers to the vehicle model of the new energy vehicle, which may be a model name, model identification, model code, etc. The fault phenomenon is used to describe the abnormal performance of the new energy vehicle when a fault occurs. The fault phenomenon may be a text description or may include detection data. The cause of the fault is a description text of the cause of the fault phenomenon of the new energy vehicle. The solution is the repair measures or solutions taken for the fault phenomenon of the new energy vehicle or the cause of the fault; the solution may be a text description text. The component unit refers to the various components or systems that constitute the new energy vehicle. These component units include motors, battery packs, electronic control systems, charging systems, transmission systems, etc. The fault code is the fault information detected by the diagnostic system of the new energy vehicle, usually displayed in the form of a code, and the fault code may correspond to at least one of the fault location, fault cause, fault phenomenon, and solution. The meaning of the fault code is used to explain the fault code, describing at least one of the fault location, fault cause, fault phenomenon, and solution corresponding to the fault code.

[0062] The relationship includes at least one of the following relationship types:

[0063] The relationship between the vehicle model 302 and the vehicle brand 301; indicating the vehicle brand to which the vehicle model belongs, and the corresponding edge points from the vehicle model to the vehicle brand.

[0064] The occurrence relationship between the vehicle model 302 and the fault phenomenon 303 indicates the vehicle model where the fault phenomenon occurs, and the corresponding edge points from the vehicle model to the fault phenomenon.

[0065] The triggering relationship between the fault cause 304 and the fault phenomenon 303 indicates the fault cause that triggers the fault phenomenon, and the corresponding edge points from the fault cause to the fault phenomenon.

[0066] The causing relationship between the fault cause 304 and the fault cause 304; indicating the fault cause that causes the fault cause, for example, the motor fault causes the controller fault; its corresponding edge points from the fault cause to the fault cause.

[0067] The measure relationship between the fault cause 304 and the solution 305 indicates the solution corresponding to the fault cause, and the corresponding edge points from the fault cause to the solution.

[0068] The reporting relationship between the fault cause 304 and the fault code 307; indicating the fault code reported by the fault cause, and its corresponding edge points from the fault cause to the fault code.

[0069] The meaning relationship between the fault code 307 and the fault code meaning 308 indicates the fault code meaning corresponding to the fault code, and the corresponding edge points from the fault code to the fault code meaning.

[0070] The solution position relationship between the solution 305 and the component unit 306 indicates the firmware unit where the solution is located, and the corresponding edge points from the solution to the component unit.

[0071] The fault location relationship between the fault cause 304 and the component unit 306 indicates the component unit where the fault cause is located, and the corresponding edge points from the fault cause to the component unit.

[0072] The alias relationship between the component unit 306 and the component unit 306 indicates another alias (component unit) corresponding to the component unit, and the corresponding edge points from one component unit to another component unit.

[0073] The composition relationship between component units 306 and component units 306 indicates the composition relationship between component units, and the corresponding edge points from one component unit to another component unit.

[0074] For example, entities are used as nodes in the fault knowledge graph, and associations are used as edges in the fault knowledge graph. According to the triple (entity, association, entity), two nodes with associations are connected to construct the fault knowledge graph. Figure 4 As shown, the terminal device can display the user interface of the diagnostic system, and the constructed fault knowledge graph 309 is displayed in the user interface. The user can click on a node or edge in the indication graph to select the node or edge and view its detailed information and the information of the nodes or edges connected to it.

[0075] Exemplarily, in the fault knowledge graph, nodes of different entity types can be displayed in different styles, for example, different colors, different shapes, different sizes, etc.; edges of different association relationship types can also be displayed in different styles, for example, different colors, different types of lines, different thicknesses of lines, etc.

[0076] Step 220: Identify a first entity in the user query statement and a first association relationship corresponding to the query intention of the user query statement.

[0077] The terminal device receives a user query sentence input by the user. The user query sentence can be a query text input by the user, or a query text obtained by performing text recognition on the query voice input by the user. The user query sentence is a natural language for inquiring about new energy vehicle diagnostic knowledge.

[0078] Exemplarily, the user's query statement includes an entity and an association relationship. For example, the user asks why the motor fails, which includes the entity: motor failure, and the association relationship: the triggering relationship between the fault phenomenon and the fault cause. Based on the entity and the association relationship, the terminal device can query the entity "motor failure", the association relationship "triggering relationship", and the connected fault cause entity in the fault knowledge graph to obtain at least one fault cause that causes the motor failure.

[0079] The first entity may be any of the above entity types. Exemplarily, the entity name mentioned in the user query statement may not be exactly the same as the entity name stored in the fault knowledge graph. Therefore, the terminal device may first extract at least one query entity from the user query statement, and then semantically match the query entity with the candidate entity in the fault knowledge graph to obtain the entity corresponding to the query entity in the fault knowledge graph.

[0080] The number of the first entity may be at least one, the user query statement may include at least one entity, and the terminal device extracts these entities and the association relationship corresponding to each entity. That is, the terminal device extracts at least one set of entities and corresponding association relationships from the user query statement, so as to query another entity in the triple based on one entity and one association relationship.

[0081] The first association relationship may be any of the above-mentioned association relationship types. The terminal device performs semantic understanding on the user query statement and matches the association relationship corresponding to the query intention. For example, the terminal device may call a classification model to determine the association relationship type corresponding to the user query statement; or the terminal device may call a large language model to determine the association relationship type corresponding to the user query statement from at least one candidate association relationship type.

[0082] Step 230: Generate a reply content to the user query statement according to the second entity, where the second entity includes an entity in the fault knowledge graph that has a first association relationship with the first entity.

[0083] Exemplarily, the terminal device matches the corresponding second entity in the fault knowledge graph based on the first entity and the first association relationship, and the second entity is connected to the node corresponding to the first entity in the fault knowledge graph through the edge of the first association relationship. The first entity, the first association relationship and the second entity are a triple.

[0084] After obtaining the second entity, the terminal device generates a reply content to the user's inquiry statement based on the second entity. The reply content can be in various forms, for example, the reply content can be a reply text, a reply voice, a reply knowledge graph, etc. For example, the terminal device can call a large language model, use the second entity as the answer to the user's inquiry statement, and request the large language model to generate a reply text for the user's inquiry statement. The terminal device can also call speech synthesis technology to generate a reply voice based on the reply text. Alternatively, the terminal device can intercept the first entity, the first association relationship, and the second entity from the fault knowledge graph to obtain a reply knowledge graph to display to the user.

[0085] In an optional embodiment, the reply content includes a reply knowledge graph; the terminal device calls a query statement to query the first entity and the second entity corresponding to the first association relationship based on the fault knowledge graph; based on the first entity, the first association relationship, and the second entity, a reply knowledge graph is generated; the reply knowledge graph includes a first node corresponding to the first entity, a second node corresponding to the second entity, and a first edge corresponding to the first association relationship, and the first edge connects the first node and the second node.

[0086] Optionally, in response to receiving an operation to view the second node, the terminal device displays at least one third node connected to the second node in the reply knowledge graph; wherein the third node corresponds to a third entity; the third entity has an association relationship with the second entity, or the third entity has a first association relationship with the second entity.

[0087] In another optional embodiment, the reply content includes a reply text; the terminal device calls a query statement to query the first entity and the second entity corresponding to the first association relationship based on the fault knowledge graph; and calls a large language model to generate a reply text for the user's inquiry statement based on the second entity.

[0088] For example, Figure 5As shown, this embodiment provides a new energy vehicle diagnostic system, which includes a data acquisition module 401, a knowledge graph construction module 402, a knowledge graph question and answer module 403 and an application service module 404. The data acquisition module 401 is used to collect experience data, such as maintenance data, maintenance cases, expert information, technical information, etc. of new energy vehicles, and provide the experience data to the knowledge graph construction module to construct a fault indication graph. The knowledge graph construction module 402 is used to extract entities and associations from the experience data, merge similar entities, and generate a fault knowledge graph. The application service module 404 is used to display the diagnosis page of the new energy vehicle and display the fault knowledge graph. When the user enters a user query statement in the diagnosis page, the application service module 404 calls the knowledge graph question and answer module 403 to parse the user query statement and return the corresponding reply content. The knowledge graph question and answer module 403 is used to identify the entities and associations in the user query statement, and query the corresponding entity based on the fault knowledge graph constructed by the knowledge graph construction module 402, and generate a reply content based on the entity and return it to the application service module 404.

[0089] In summary, the method provided in this embodiment generates a fault knowledge graph based on the empirical data of new energy vehicle diagnosis. Knowledge is extracted and utilized from unstructured empirical data such as maintenance cases using knowledge graph technology. According to the query statements of the maintenance personnel, the diagnostic system can quickly match the diagnostic results from the fault knowledge graph and feedback the diagnostic results to the maintenance personnel in a variety of ways. For example, the knowledge graph is fed back to the maintenance personnel, and the diagnostic knowledge of new energy vehicles is intuitively displayed to the maintenance personnel in the form of a knowledge graph, which is convenient for the maintenance personnel to quickly determine the cause and solution of the fault, effectively assist the maintenance personnel in troubleshooting and maintenance work, and improve maintenance efficiency.

[0090] An exemplary embodiment of constructing a fault knowledge graph is given.

[0091] Figure 6 FIG. 1 is a flow chart of a diagnostic method for a new energy vehicle provided by an exemplary embodiment of the present application. The method can be used for Figure 1 The terminal device shown. Figure 2 In the illustrated embodiment, step 210 may include steps 211 to 213 .

[0092] Step 211: call the entity relationship extraction model to extract at least one triple from the empirical data; the triple includes two entities with an association relationship and the association relationship between the two entities.

[0093] In an optional embodiment, the terminal device can crawl the maintenance data, technical data and other empirical data of new energy vehicles; use regularization and manual assistance to screen the empirical data, retain the empirical data of the high-voltage system of new energy vehicles, and delete other irrelevant data. Then clean and organize the data to obtain a large amount of complete empirical data of the high-voltage system of new energy vehicles. Use pointers to mark the entities and associations in the empirical data. And divide the marked empirical data into training set, verification set and test set. Complete the training and testing of the entity relationship joint model based on the training set, verification set and test set.

[0094] The entity relationship extraction model is a neural network model that extracts triplets (entity, association relationship, entity) from input data (experience data).

[0095] For example, Figure 7 As shown in the figure, the entity relationship extraction model can adopt the network structure of RoBERTa-wwm-BiLSTM-GlobalPointer, that is, the entity relationship extraction model includes the RoBERTa-wwm network, BiLSTM network and GlobalPointer network connected in sequence. The entity relationship extraction model is trained using the training set and the validation set. The pre-trained language model RoBERTa-wwm is used to obtain the vector representation of the input text, and a dynamic character vector can be obtained by fine-tuning it with a small amount of annotated corpus. The BiLSTM network is used to further extract text features, and finally the GlobalPointer network is used to complete the decoding task.

[0096] In addition, the adversarial training mechanism is introduced to solve the problem of overfitting of the model on small sample data sets and improve the robustness and generalization ability of the model. Figure 7 As shown, in the adversarial training layer 804, interference is added to the output of the embedding layer, and the disturbed data is input into the feature extraction layer for feature extraction, so that the model outputs the disturbed prediction result, and the loss function is calculated based on the disturbed prediction result to train the model parameters to improve the robustness of the model.

[0097] Exemplarily, the empirical data is input into the entity relationship extraction model, and the entity relationship matrix 803 and the entity position matrix 802 are output. Figure 8As shown, in the entity position matrix 802, the starting and ending positions of each entity in the empirical data are marked. For example, if "Brand X" is an entity, the value in the first row and second column of the entity position matrix is 1. The first row represents the position of the first character of the entity in the empirical data (the first character), and the second column represents the position of the last character of the entity in the empirical data (the second character). Another example, if "Car A" is an entity, the value in the third row and fourth column of the entity position matrix is 1. The third row represents the position of the first character of the entity in the empirical data (the third character), and the fourth column represents the position of the last character of the entity in the empirical data (the fourth character).

[0098] As Figure 8 shown, in the entity relationship matrix 803, the subject and object of two entities with an associated relationship in the empirical data are marked. When the subject is in the front, a 1 is marked at the corresponding position in the upper right matrix of the entity relationship matrix 803; when the subject is in the back, a 1 is marked at the corresponding position in the lower left matrix of the entity relationship matrix 803. For example, Figure 8 there is a triple (Car A, belongs to, Brand X) in which Car A is the subject and Brand X is the object. In the empirical data "Brand X Car A appears unable to charge", the subject is after the object, so a 1 is marked at the third row and first column and a 1 is marked at the fourth row and second column in the entity relationship matrix 803. Marking a 1 at the third row and first column means the starting positions of the two entities are the first character and the third character respectively, and marking a 1 at the fourth row and second column means the ending positions of the two entities are the second character and the fourth character respectively. Since the two 1s are in the lower left matrix of the entity relationship matrix 803, it means the subject is after the object. However, from Figure 8 it can be seen that the entity relationship matrix 803 is extremely sparse, which will lead to memory waste. Therefore, the lower left matrix (lower triangular matrix) is mapped to the upper right matrix, and the position after mapping the value 1 is marked as 2, indicating that the subject is after the object, and thus the entity relationship matrix 803 as shown in Figure 8 can be obtained.

[0099] After training is completed, save the trained entity relationship extraction model; use the test set to test the trained entity relationship extraction model to ensure that the trained entity relationship extraction model can have good performance. Then, adopt the trained and tested entity relationship extraction model to extract the triples in the remaining empirical data to complete the extraction of all triples.

[0100] Step 212: Merge entities with similarity higher than the threshold in at least one triple to obtain a set of merged triples.

[0101] Taking at least one triple including a fourth entity and a fifth entity as an example; the terminal device calculates the text similarity between the fourth entity and the fifth entity; calculates the semantic similarity between the fourth entity and the fifth entity; calculates the weighted sum of the text similarity and the semantic similarity; when the weighted sum is higher than a threshold, merges the fourth entity and the fifth entity.

[0102] For example, cosine similarity is calculated as text similarity, and Jaccard similarity is calculated as semantic similarity. According to a preset threshold, entities with similarity greater than the threshold are merged, and the same entity is uniformly stored in the synonym entity library.

[0103] Exemplarily, the cosine similarity and Jaccard similarity of the fourth entity A and the fifth entity B are calculated respectively. The weight of the text similarity (cosine similarity) is set to 0.4, the weight of the semantic similarity (Jaccard similarity) is set to 0.6, and the two similarities are weighted to obtain the final entity similarity, which is calculated as follows: Sim(A, B) = 0.4*Simj(A, B) + 0.6*Simc(A, B).

[0104] Among them, Simj(A,B) is the Jaccard similarity, that is, the semantic similarity. Simc(A,B) is the cosine similarity, that is, the text similarity. Sim(A,B) is the final similarity.

[0105] The calculation method of cosine similarity is: Simc(A,B)=(A·B) / (||A||*||B||).

[0106] Among them, A and B are the word frequency vectors of the two texts, A·B is the dot product of the vectors, and ||A|| and ||B|| are the moduli (i.e., the lengths) of vectors A and B, respectively.

[0107] For example, A and B are: A: "The weather is great today, and it will be the same tomorrow"; B: "The weather is not bad today, and it will be the same tomorrow". After word segmentation, stop word removal and word frequency statistics, the word frequency vector is obtained:

[0108] A = [1, 2, 1, 1, 1, 0] (corresponding entries: today, weather, really good, tomorrow, also, the same, not bad);

[0109] B=[1,1,0,1,1,1,1].

[0110] Then calculate the dot product and modulus, and finally get cosine similarity = (1×1+2×1+1×0+1×1+1×1+1×1+0×1) / (√(12+12+12+02+12+12+12))=6 / (√10×√6)≈0.816. Since the cosine value is close to 1, it can be judged that A and B are similar.

[0111] The calculation method of Jaccard similarity is: Simj(A,B)=|A∩B| / |A∪B|.

[0112] Among them, A and B represent the word sets of two texts respectively, |A∩B| represents the size of the intersection of the two sets, and |A∪B| represents the size of the union of the two sets.

[0113] Suppose there are two texts: Text A: "The weather is great today"; Text B: "The weather will be great tomorrow too". After word segmentation and deduplication, we get the word set:

[0114] A = {Today, the weather is really nice};

[0115] B={Tomorrow, the weather will be good}.

[0116] Compute intersection and union:

[0117] A ∩ B = {weather} (common terms);

[0118] A ∪B = {Today, the weather is really good, tomorrow, it will be good too} (the merged set of entries).

[0119] Then Jaccard similarity = |A∩B| / |A∪B| = 1 / 5 = 0.2. Since the Jaccard correlation coefficient value is small, it can be judged that the similarity between text A and text B is low.

[0120] Step 213: Based on the triple set, the entities in the triples are used as nodes, and the association relationships are used as edges connecting the nodes to construct a fault knowledge graph.

[0121] Exemplarily, the triple set is imported into the Neo4j graph database to realize the construction of the fault knowledge graph of new energy vehicles.

[0122] In summary, the method provided in this embodiment can call the entity relationship extraction model to extract triples from the empirical data, merge the same entities in the triples based on similarity calculation, and construct a fault knowledge graph based on the merged triples. This facilitates maintenance personnel to quickly determine the cause and solution of the fault from the fault knowledge graph, effectively assists maintenance personnel in troubleshooting and maintenance work, and improves maintenance efficiency.

[0123] An exemplary embodiment of identifying entities and associated relationships from a user query sentence is given.

[0124] For example, an automatic question-answering function is constructed, which aims to convert the user's question into a query statement with the same semantics, query the fault knowledge graph and output the answer. Fig. 9As shown, the process includes entity recognition 501, entity matching 502 and intent classification 503.

[0125] Entity recognition 501 refers to identifying keywords (entities) from the user query sentence input by the user, such as fault phenomenon, fault code, etc. The obtained keywords are also called query entities. The entity recognition task must accurately identify the starting position and end position of the query entity (the position in the user query sentence), and also determine the entity category to which the query entity belongs.

[0126] Entity matching 502 aims to accurately match the query entity identified in the user query statement to the entity in the fault knowledge graph. Because the standard entity in the fault knowledge graph may have multiple aliases, the query entity may not necessarily be found in the fault knowledge graph. For example, the query entity "electric control" and the entity "motor controller" are expressed differently, but their semantics are the same. When the user query query entity "electric control" can be matched to the entity "motor controller" in the fault knowledge graph, and the relevant content of "motor controller" is returned, this is the significance of entity matching.

[0127] The purpose of intent classification 503 is to identify the intent of the user query sentence input by the user, that is, to classify the association relationship. After linking to the entity, the triple of the entity can be queried accordingly. However, there may be more than one triple related to the entity, so it is necessary to determine whether there is a triple that matches the user's intent. Figure 1 For example, there is a question sentence “Why does the instrument report that the EV function is limited?” The question answering system needs to obtain the intention of the question sentence through the intent classification 503 to query the fault cause of the entity “the instrument reports that the EV function is limited”.

[0128] For example, Fig.10 As shown, when the user query statement 504 is "Why is the power limit indicator light on the meter on?", the user query statement is subjected to entity recognition 501 and entity matching 502, and the query entity "power limit indicator light" is obtained in the fault knowledge graph corresponding to the entity "power limit indicator light". The user query statement 504 is subjected to intent classification 503, and its corresponding association relationship is obtained as the cause of the fault. Based on the identified entities and association relationships, a Cypher query statement 505 can be used to query the knowledge that the maintenance personnel expect to obtain from the fault knowledge graph, and the response content obtained is "motor electric water pump failure, motor failure". Optional, such as Fig.11As shown, the reply content can be displayed in the form of a knowledge graph, that is, the reply knowledge graph 506 is displayed. The reply knowledge graph can display the first entity at the visual focus position and radiate at least one second entity around the first entity. The user can click on a node or edge in the reply knowledge graph to view information related to the node or edge. For example, after clicking on the node corresponding to the second entity, a node corresponding to at least one entity connected to the second entity is displayed.

[0129] Fig.12 FIG. 1 is a flow chart of a diagnostic method for a new energy vehicle provided by an exemplary embodiment of the present application. The method can be used for Figure 1 The terminal device shown. Figure 2 In the illustrated embodiment, step 220 may include steps 221 to 224 .

[0130] Step 211: calling the entity recognition model to identify the query entity in the user query statement; the entity recognition model is used to output the entities contained in the user query statement, the entity type of the entity, and the location of the entity.

[0131] The entity recognition model is a neural network model that is trained to extract query entities from user query sentences. The entity recognition model can output the text of the query entity, the entity type it belongs to, the starting position of the query entity in the user query sentence, etc.

[0132] The model structure of the entity recognition model can be arbitrary. For example, the entity recognition model can be an ALBERT-GlobalPointer model, that is, the entity recognition model includes an ALBERT network and a GlobalPointer network.

[0133] Step 222: calling the relationship classification model to output the first association relationship corresponding to the user query statement; the relationship classification model is used to output the association relationship type corresponding to the query intention of the user query statement.

[0134] The relationship classification model is a neural network model that is trained to output the corresponding associated relationship type based on the query intent of the user query sentence. The model structure of the relationship classification model can be arbitrary. For example, the relationship classification model can be an ALBERT-TextCNN model, that is, the relationship classification model includes an ALBERT network and a TextCNN network.

[0135] Exemplarily, the training process of the entity recognition model and the relationship classification model is as follows. First, construct a training data set for the entity recognition model and the relationship classification model. Based on the entities and relationships in the triples extracted from the empirical data in step 210, generate part of the question corpus by imitating the way maintenance personnel ask questions, and expand the question corpus to obtain sufficient question corpus. Use the Python algorithm to further expand the question corpus by adding auxiliary verbs, attributives, and adjuncts, performing synonym replacement, and sentence reconstruction. Use the Python algorithm to annotate the entities and relationships in the question corpus to obtain a question entity recognition data set and a relationship classification data set.

[0136] Then, the entity recognition model and the relation classification model are trained. The question entity recognition dataset and the relation classification dataset are divided into training set, validation set and test set according to the ratio of 8:1:1. Fig.13 The ALBERT-GlobalPointer model shown in the figure is saved, and the trained and tested ALBERT-GlobalPointer model is saved to obtain an entity recognition model. The entity recognition model uses the ALBERT network to obtain an embedding representation 602 based on input data 601 (user query sentence), and uses the GlobalPointer network to output an entity prediction result 603 based on the embedding representation 602. The entity prediction result 603 includes the query entity contained in the user query sentence.

[0137] Use the relational classification dataset to train and test Fig.14 The ALBERT-TextCNN model shown in FIG. 1 is used to save the trained and tested ALBERT-TextCNN model to obtain a relation classification model. The relation classification model uses the ALBERT network to obtain an embedded representation based on the user query sentence, and then passes through a convolutional layer 701, a pooling layer 702, a fully connected layer 703 and a normalization function 704 to perform classification prediction based on the embedded representation to obtain the associated relationship type corresponding to the user query sentence.

[0138] Step 223: Calculate the similarity scores between the query entity and the candidate entities in the fault knowledge graph in sequence.

[0139] For each query entity in the user's query statement, the terminal device calculates the similarity score between the query entity and each candidate entity in the fault knowledge graph.

[0140] Exemplarily, the terminal device calculates the entity similarity score between the query entity and the candidate entity; calculates the sentence similarity score between the user query sentence and the candidate entity; and determines the weighted sum of the entity similarity score and the sentence similarity score as the similarity score. The entity similarity score is used to indicate the similarity between the query entity and the entity text of the candidate entity, and the sentence similarity score is used to indicate the similarity between the user query sentence and the candidate entity.

[0141] Step 224: Determine the first entity with the highest similarity score among the candidate entities as the entity corresponding to the query entity.

[0142] For example, the query entity is matched with the candidate entity in the fault knowledge graph in a word matching manner. score = α*(2|X∩Y| / (|X|+|Y|-|X∩Y|))+β*(2|X∩S| / (|X|+|S|-|X∩S|)).

[0143] Where X is the candidate entity, Y is the query entity, S is the user query sentence, α and β are parameters, which are 0.8 and 0.2 respectively, "a∩b" represents the common characters of a and b, and |*| represents the number of characters. (2|X∩Y| / (|X|+|Y|-|X∩Y|)) is the entity similarity score, and (2|X∩S| / (|X|+|S|-|X∩S|)) is the sentence similarity score.

[0144] Calculate the scores corresponding to the candidate entities and sort them in descending order, and select the candidate entity with the largest score as the entity that matches the query entity.

[0145] In summary, the method provided in this embodiment can perform entity recognition and relationship recognition on user query statements, extract entities and association relationships in user query statements, and query diagnostic results from the fault knowledge graph based on entities and association relationships. This facilitates maintenance personnel to quickly determine the cause and solution of the fault from the fault knowledge graph, effectively assists maintenance personnel in troubleshooting and maintenance work, and improves maintenance efficiency.

[0146] The embodiment of the present application provides a new energy vehicle auxiliary diagnosis method and system based on knowledge graph to solve the problem of difficulty in troubleshooting and repairing new energy vehicles. The method can make a basic fault cause judgment based on the fault phenomenon and fault code of the new energy vehicle; it can also provide automatic question-and-answer services and graph visualization functions with higher query accuracy during the fault diagnosis and repair process of maintenance personnel.

[0147] First, based on the reuse of ontology and expert knowledge in the field of automobile maintenance, a fault knowledge graph of new energy vehicles is constructed. This process can include the following steps:

[0148] S1. Obtain new energy vehicle maintenance cases, perform preprocessing and data annotation, obtain deep learning training corpus, and divide it into training set, validation set and test set;

[0149] S2. Complete the training and testing of the entity relationship extraction model based on the training set, validation set, and test set;

[0150] S3. After completing S1 and S2, the entity relationship joint extraction model completed by training and testing is used to extract triples in the remaining corpus, complete the extraction of all triples in the corpus, and obtain a triple set;

[0151] S4, combining cosine similarity and Jaccard correlation coefficient method to calculate text similarity and semantic similarity, pre-setting a threshold, merging entities whose similarity between entities is greater than the set threshold, and storing the same entity in a synonym entity library;

[0152] S5. Import the triple set obtained in S3 into the Neo4j graph database to build a knowledge graph of new energy vehicle faults.

[0153] Among them, the knowledge graph of new energy vehicle faults includes entities and associations, where entities include brand, model, fault phenomenon, fault cause, solution, fault code, fault code meaning and component unit. The associations include belonging to, occurrence phenomenon, triggering, causing, located, measures, reporting and meaning.

[0154] Secondly, an automatic question answering and graph visualization service is provided, and the method includes the following steps.

[0155] S6. Construct entity recognition model and relationship classification model training data set;

[0156] S7, training entity recognition model and relationship classification model;

[0157] S8, based on the synonym entity library obtained in S4, entity linking is realized by word matching;

[0158] S9, based on the entity recognition model and relationship classification model obtained in S7, and using the entity linking method proposed in S8, build an automatic question answering module;

[0159] S10. Build a new energy vehicle auxiliary diagnosis system based on knowledge graph.

[0160] Exemplarily, the embodiment of the present application adopts a method of entity-relationship joint extraction to realize one-step extraction of knowledge triples, which solves the problems of error accumulation and low degree of automation construction; it provides automatic question-answering and graph visualization functions, and maintenance personnel can interact with the auxiliary maintenance system through text and language, which improves work efficiency and reduces the difficulty of work for maintenance personnel.

[0161] It should be noted that before collecting relevant data of users and during the process of collecting relevant data of users, this application can display a prompt interface, pop-up window or output voice prompt information, and the prompt interface, pop-up window or voice prompt information is used to prompt the user that its relevant data is currently being collected, so that this application only starts to execute the relevant steps of obtaining relevant data of users after obtaining the confirmation operation issued by the user to the prompt interface or pop-up window, otherwise (that is, when the confirmation operation issued by the user to the prompt interface or pop-up window is not obtained), the relevant steps of obtaining relevant data of users are terminated, that is, the relevant data of users are not obtained. In other words, all user data collected by this application are collected with the consent and authorization of the user, and the collection, use and processing of relevant user data need to comply with the relevant laws, regulations and standards of relevant countries and regions.

[0162] It should be noted that the sequence of the method steps provided in the embodiments of the present application can be appropriately adjusted, and the steps can be increased or decreased accordingly according to the circumstances. Any technician familiar with the technical field can easily think of the changed methods within the technical scope disclosed in the present application, and they should be included in the protection scope of the present application, so they will not be repeated here.

[0163] Fig.15 This is a schematic diagram of a new energy vehicle diagnostic device provided by an exemplary embodiment of the present application. The device includes:

[0164] The knowledge graph module 1001 is used to obtain a fault knowledge graph, wherein the fault knowledge graph is constructed based on triples in the experience data of the new energy vehicle, and the triples are used to indicate the association relationship between entities in the experience data;

[0165] An identification module 1002 is used to identify a first entity in a user query statement and a first association relationship corresponding to the query intention of the user query statement;

[0166] The generation module 1003 is used to generate the reply content of the user query statement according to the second entity, and the second entity includes the entity in the fault knowledge graph that has the first association relationship with the first entity.

[0167] In an optional embodiment, the reply content includes a reply knowledge graph;

[0168] The generating module 1003 is used to call a query statement to query the first entity and the second entity corresponding to the first association relationship based on the fault knowledge graph;

[0169] The generation module 1003 is used to generate the reply knowledge graph based on the first entity, the first association relationship and the second entity; the reply knowledge graph includes a first node corresponding to the first entity, a second node corresponding to the second entity, and a first edge corresponding to the first association relationship, and the first edge connects the first node and the second node.

[0170] In an optional embodiment, the reply content includes a reply text;

[0171] The generating module 1003 is used to call a query statement to query the first entity and the second entity corresponding to the first association relationship based on the fault knowledge graph;

[0172] The generating module 1003 is used to call the large language model to generate a reply text of the user query sentence based on the second entity.

[0173] In an optional embodiment, the generating module 1003 is configured to display at least one third node connected to the second node in the reply knowledge graph in response to receiving an operation to view the second node;

[0174] The third node corresponds to a third entity; the third entity has an association relationship with the second entity, or the third entity has the first association relationship with the second entity.

[0175] In an optional embodiment, the entity includes at least one of the following entity types: vehicle brand, vehicle model, fault phenomenon, fault cause, solution, component unit, fault code, and fault code meaning.

[0176] In an optional embodiment, the association relationship includes at least one of the following association relationship types:

[0177] The relationship between vehicle models and vehicle brands;

[0178] The relationship between the vehicle type and the fault phenomenon;

[0179] The relationship between the cause of the fault and the fault phenomenon;

[0180] The fault cause and the relationship between the fault causes;

[0181] The relationship between the cause of the fault and the measures to solve it;

[0182] The reporting relationship between the fault cause and the fault code;

[0183] The semantic relationship between the fault code and the meaning of the fault code;

[0184] The solving position relationship between the solving device and the component unit;

[0185] The relationship between the fault cause and the fault position of the component unit;

[0186] The alias relationship between the component units;

[0187] The composition relationship between the component units.

[0188] In an optional embodiment, the knowledge graph module 1001 is used to call the entity relationship extraction model to extract at least one triple from the experience data; the triple includes two entities with an association relationship and the association relationship between the two entities;

[0189] The knowledge graph module 1001 is used to merge entities in the at least one triple whose similarity is higher than a threshold value to obtain a merged triple set;

[0190] The knowledge graph module 1001 is used to construct the fault knowledge graph based on the triple set, using the entities in the triples as nodes and the association relationships as edges connecting the nodes.

[0191] In an optional embodiment, the at least one triple includes a fourth entity and a fifth entity;

[0192] The knowledge graph module 1001 is used to calculate the text similarity between the fourth entity and the fifth entity;

[0193] The knowledge graph module 1001 is used to calculate the semantic similarity between the fourth entity and the fifth entity;

[0194] The knowledge graph module 1001 is used to calculate the weighted sum of the text similarity and the semantic similarity;

[0195] The knowledge graph module 1001 is used to merge the fourth entity and the fifth entity when the weighted sum is higher than a threshold.

[0196] In an optional embodiment, the identification module 1002 is used to call an entity recognition model to identify the query entity in the user query statement; the entity recognition model is used to output the entity contained in the user query statement, the entity type of the entity, and the location of the entity;

[0197] The identification module 1002 is used to call the relationship classification model to output the first association relationship corresponding to the user query statement; the relationship classification model is used to output the association relationship type corresponding to the query intention of the user query statement;

[0198] The identification module 1002 is used to sequentially calculate similarity scores between the query entity and the candidate entities in the fault knowledge graph;

[0199] The identification module 1002 is used to determine the first entity with the highest similarity score among the candidate entities as the entity corresponding to the query entity.

[0200] In an optional embodiment, the identification module 1002 is used to calculate an entity similarity score between the query entity and the candidate entity;

[0201] The recognition module 1002 is used to calculate the sentence similarity score between the user query sentence and the candidate entity;

[0202] The recognition module 1002 is configured to determine the similarity score as a weighted sum of the entity similarity score and the sentence similarity score.

[0203] It should be noted that the diagnostic device for new energy vehicles provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the diagnostic device for new energy vehicles provided in the above embodiment and the diagnostic method embodiment for new energy vehicles belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0204] The embodiment of the present application also provides a computer device, which includes: a processor and a memory, wherein at least one instruction, at least one program, code set or instruction set is stored in the memory, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by the processor to implement the diagnostic method of the new energy vehicle provided by the above-mentioned method embodiments. The computer device can be implemented as a terminal.

[0205] For example, Fig.16 It is a structural diagram of a computer device provided by an exemplary embodiment of the present application.

[0206] Typically, the computer device 1700 includes a processor 1701 and a memory 1702 .

[0207] The processor 1701 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 1701 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 1701 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 1701 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 1701 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0208] The memory 1702 may include one or more computer-readable storage media, which may be non-transitory. The memory 1702 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 1702 is used to store at least one instruction, which is used to be executed by the processor 1701 to implement the diagnostic method for new energy vehicles provided in the method embodiment of the present application.

[0209] In some embodiments, the computer device 1700 may also optionally include: a peripheral device interface 1703 and at least one peripheral device. The processor 1701, the memory 1702 and the peripheral device interface 1703 may be connected via a bus or a signal line. Each peripheral device may be connected to the peripheral device interface 1703 via a bus, a signal line or a circuit board. Specifically, the peripheral device includes: at least one of a radio frequency circuit 1704, a display screen 1705, a camera assembly 1706, an audio circuit 1707 and a power supply 1708.

[0210] The peripheral device interface 1703 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 1701 and the memory 1702. In some embodiments, the processor 1701, the memory 1702, and the peripheral device interface 1703 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 1701, the memory 1702, and the peripheral device interface 1703 may be implemented on a separate chip or circuit board, which is not limited in the embodiments of the present application.

[0211] The radio frequency circuit 1704 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 1704 communicates with the communication network and other communication devices through electromagnetic signals. The radio frequency circuit 1704 converts the electrical signal into an electromagnetic signal for transmission, or converts the received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 1704 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, and the like. The radio frequency circuit 1704 can communicate with other computer devices through at least one wireless communication protocol. The wireless communication protocol includes, but is not limited to: the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 1704 may also include circuits related to NFC (Near Field Communication), which is not limited in this application.

[0212] The display screen 1705 is used to display a UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 1705 is a touch display screen, the display screen 1705 also has the ability to collect touch signals on the surface or above the surface of the display screen 1705. The touch signal can be input to the processor 1701 as a control signal for processing. At this time, the display screen 1705 can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen 1705 can be one, and the front panel of the computer device 1700 is set; in other embodiments, the display screen 1705 can be at least two, which are respectively set on different surfaces of the computer device 1700 or are folded; in some other embodiments, the display screen 1705 can be a flexible display screen, which is set on the curved surface or folded surface of the computer device 1700. Even, the display screen 1705 can also be set to a non-rectangular irregular shape, that is, a special-shaped screen. The display screen 1705 can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).

[0213] The camera assembly 1706 is used to capture images or videos. Optionally, the camera assembly 1706 includes a front camera and a rear camera. Typically, the front camera is arranged on the front panel of the computer device 1700, and the rear camera is arranged on the back of the computer device. In some embodiments, there are at least two rear cameras, which are any one of a main camera, a depth of field camera, a wide-angle camera, and a telephoto camera, so as to realize the fusion of the main camera and the depth of field camera to realize the background blur function, the fusion of the main camera and the wide-angle camera to realize the panoramic shooting and VR (Virtual Reality) shooting function or other fusion shooting functions. In some embodiments, the camera assembly 1706 may also include a flash. The flash can be a monochrome temperature flash or a dual-color temperature flash. A dual-color temperature flash refers to a combination of a warm light flash and a cold light flash, which can be used for light compensation at different color temperatures.

[0214] The audio circuit 1707 may include a microphone and a speaker. The microphone is used to collect sound waves from the user and the environment, and convert the sound waves into electrical signals and input them into the processor 1701 for processing, or input them into the radio frequency circuit 1704 to achieve voice communication. For the purpose of stereo acquisition or noise reduction, there may be multiple microphones, which are respectively arranged at different parts of the computer device 1700. The microphone may also be an array microphone or an omnidirectional acquisition microphone. The speaker is used to convert the electrical signal from the processor 1701 or the radio frequency circuit 1704 into sound waves. The speaker may be a traditional film speaker or a piezoelectric ceramic speaker. When the speaker is a piezoelectric ceramic speaker, it can not only convert the electrical signal into sound waves audible to humans, but also convert the electrical signal into sound waves inaudible to humans for purposes such as ranging. In some embodiments, the audio circuit 1707 may also include a headphone jack.

[0215] The power supply 1708 is used to power various components in the computer device 1700. The power supply 1708 can be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 1708 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery that is charged through a wired line, and a wireless rechargeable battery is a battery that is charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0216] In some embodiments, the computer device 1700 further includes one or more sensors 1709 , including but not limited to: an acceleration sensor 1710 , a gyroscope sensor 1711 , a pressure sensor 1712 , an optical sensor 1713 , and a proximity sensor 1714 .

[0217] The acceleration sensor 1710 can detect the magnitude of acceleration on the three coordinate axes of the coordinate system established by the computer device 1700. For example, the acceleration sensor 1710 can be used to detect the components of gravity acceleration on the three coordinate axes. The processor 1701 can control the touch display screen 1705 to display the user interface in a horizontal view or a vertical view according to the gravity acceleration signal collected by the acceleration sensor 1710. The acceleration sensor 1710 can also be used to collect game or user motion data.

[0218] The gyro sensor 1711 can detect the body direction and rotation angle of the computer device 1700, and the gyro sensor 1711 can cooperate with the acceleration sensor 1710 to collect the user's 3D actions on the computer device 1700. The processor 1701 can implement the following functions based on the data collected by the gyro sensor 1711: motion sensing (such as changing the UI according to the user's tilt operation), image stabilization during shooting, game control, and inertial navigation.

[0219] The pressure sensor 1712 can be set on the side frame of the computer device 1700 and / or the lower layer of the touch display screen 1705. When the pressure sensor 1712 is set on the side frame of the computer device 1700, it can detect the user's grip signal of the computer device 1700, and the processor 1701 performs left and right hand recognition or shortcut operations according to the grip signal collected by the pressure sensor 1712. When the pressure sensor 1712 is set on the lower layer of the touch display screen 1705, the processor 1701 controls the operability controls on the UI interface according to the user's pressure operation on the touch display screen 1705. The operability controls include at least one of a button control, a scroll bar control, an icon control, and a menu control.

[0220] The optical sensor 1713 is used to collect the ambient light intensity. In one embodiment, the processor 1701 can control the display brightness of the touch display screen 1705 according to the ambient light intensity collected by the optical sensor 1713. Specifically, when the ambient light intensity is high, the display brightness of the touch display screen 1705 is increased; when the ambient light intensity is low, the display brightness of the touch display screen 1705 is reduced. In another embodiment, the processor 1701 can also dynamically adjust the shooting parameters of the camera assembly 1706 according to the ambient light intensity collected by the optical sensor 1713.

[0221] The proximity sensor 1714, also called a distance sensor, is usually arranged on the front panel of the computer device 1700. The proximity sensor 1714 is used to collect the distance between the user and the front of the computer device 1700. In one embodiment, when the proximity sensor 1714 detects that the distance between the user and the front of the computer device 1700 is gradually decreasing, the processor 1701 controls the touch display screen 1705 to switch from the screen-on state to the screen-off state; when the proximity sensor 1714 detects that the distance between the user and the front of the computer device 1700 is gradually increasing, the processor 1701 controls the touch display screen 1705 to switch from the screen-off state to the screen-on state.

[0222] Those skilled in the art will understand that Fig.16 The structure shown in the figure does not constitute a limitation on the computer device 1700, and the computer device 1700 may include more or less components than shown in the figure, or combine some components, or adopt a different arrangement of components.

[0223] A computer-readable storage medium is also provided in an embodiment of the present application, in which at least one instruction, at least one program, code set or instruction set is stored. When the at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor of a computer device, the diagnostic method for new energy vehicles provided by the above-mentioned method embodiments is implemented.

[0224] The present application also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the diagnostic method for a new energy vehicle provided by each of the above method embodiments.

[0225] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned readable storage medium may be a read-only memory, a disk or an optical disk, etc.

[0226] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent switching, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A diagnostic method for new energy vehicles, characterized in that: The method comprises: Acquire a fault knowledge graph, wherein the fault knowledge graph is constructed based on triples in the experience data of the new energy vehicle, and the triples are used to indicate association relationships between entities in the experience data; Identify a first entity in a user query statement and a first association relationship corresponding to a query intent of the user query statement; A reply content of the user query statement is generated according to a second entity, wherein the second entity includes an entity in the fault knowledge graph that has the first association relationship with the first entity.

2. The method according to claim 1, characterized in that The reply content includes a reply knowledge graph; The generating the reply content of the user query statement according to the second entity includes: Calling a query statement to query the first entity and the second entity corresponding to the first association relationship based on the fault knowledge graph; The reply knowledge graph is generated based on the first entity, the first association relationship and the second entity; the reply knowledge graph includes a first node corresponding to the first entity, a second node corresponding to the second entity, and a first edge corresponding to the first association relationship, and the first edge connects the first node and the second node.

3. The method according to claim 1, characterized in that The reply content includes a reply text; The generating the reply content of the user query statement according to the second entity includes: Calling a query statement to query the first entity and the second entity corresponding to the first association relationship based on the fault knowledge graph; The large language model is called to generate a reply text of the user query sentence based on the second entity.

4. The method according to claim 2, characterized in that: The method further comprises: In response to receiving an operation to view the second node, displaying at least one third node connected to the second node in the reply knowledge graph; The third node corresponds to a third entity; the third entity has an association relationship with the second entity, or the third entity has the first association relationship with the second entity.

5. The method according to any one of claims 1 to 4, characterized in that: The entity includes at least one of the following entity types: vehicle brand, vehicle model, fault phenomenon, fault cause, solution, component unit, fault code, and fault code meaning.

6. The method according to any one of claims 1 to 4, characterized in that: The association relationship includes at least one of the following association relationship types: The relationship between vehicle models and vehicle brands; The relationship between the vehicle type and the fault phenomenon; The relationship between the cause of the fault and the fault phenomenon; The fault cause and the relationship between the fault causes; The relationship between the causes of the failure and the measures to solve them; The reporting relationship between the fault cause and the fault code; The semantic relationship between the fault code and the meaning of the fault code; The relationship between the solution and the solution position of the component unit; The relationship between the fault cause and the fault position of the component unit; The alias relationship between the component units; The composition relationship between the component units.

7. The method according to any one of claims 1 to 4, characterized in that: The obtaining of the fault knowledge graph includes: Invoking an entity relationship extraction model to extract at least one triple from the empirical data; the triple includes two entities having an association relationship and the association relationship between the two entities; Merging entities in the at least one triple whose similarity is higher than a threshold value to obtain a merged triple set; Based on the triple set, the entities in the triples are used as nodes, and the association relationships are used as edges connecting the nodes to construct the fault knowledge graph.

8. The method according to claim 7, characterized in that The at least one triple includes a fourth entity and a fifth entity; The merging of entities in the at least one triplet with a similarity higher than a threshold comprises: Calculating text similarity between the fourth entity and the fifth entity; Calculating the semantic similarity between the fourth entity and the fifth entity; Calculating a weighted sum of the text similarity and the semantic similarity; In case the weighted sum is higher than a threshold, the fourth entity and the fifth entity are merged.

9. The method according to any one of claims 1 to 4, characterized in that: The identifying a first entity in a user query statement and a first association relationship corresponding to a query intention of the user query statement includes: Calling an entity recognition model to identify a query entity in the user query statement; the entity recognition model is used to output the entity contained in the user query statement, the entity type of the entity, and the location of the entity; The relationship classification model is called to output the first association relationship corresponding to the user query statement; the relationship classification model is used to output the association relationship type corresponding to the query intention of the user query statement; Calculating the similarity scores between the query entity and the candidate entities in the fault knowledge graph in sequence; The first entity with the highest similarity score among the candidate entities is determined as the entity corresponding to the query entity.

10. The method according to claim 9, characterized in that The calculating the similarity score between the query entity and the candidate entity in the fault knowledge graph includes: Calculating entity similarity scores between the query entity and the candidate entity; Calculating a sentence similarity score between the user query sentence and the candidate entity; A weighted sum of the entity similarity score and the sentence similarity score is determined as the similarity score.

11. A diagnostic device for new energy vehicles, characterized in that: The device comprises: A knowledge graph module, used to obtain a fault knowledge graph, wherein the fault knowledge graph is constructed based on triples in the experience data of the new energy vehicle, and the triples are used to indicate the association relationship between entities in the experience data; An identification module, used to identify a first entity in a user query statement and a first association relationship corresponding to the query intention of the user query statement; A generation module is used to generate a reply content of the user query statement according to a second entity, wherein the second entity includes an entity in the fault knowledge graph that has the first association relationship with the first entity.

12. A computer device, characterized in that: The computer device includes a processor and a memory, wherein the memory stores at least one program, and the at least one program is loaded and executed by the processor to implement the diagnostic method for new energy vehicles as described in any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that: The readable storage medium stores at least one program, and the at least one program is loaded and executed by the processor to implement the diagnostic method for new energy vehicles as described in any one of claims 1 to 10.

14. A computer program product, characterized in that The computer program product includes computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the diagnostic method for a new energy vehicle as described in any one of claims 1 to 10.

Images