CN115345323A

CN115345323A - Vehicle fault detection method, device, equipment and storage medium

Info

Publication number: CN115345323A
Application number: CN202110467246.XA
Authority: CN
Inventors: 黄亮
Original assignee: Rainbow Wireless Beijing New Technology Co ltd
Current assignee: Rainbow Wireless Beijing New Technology Co ltd
Priority date: 2021-04-28
Filing date: 2021-04-28
Publication date: 2022-11-15

Abstract

The application provides a vehicle fault detection method, which comprises the following steps: key information related to the fault is analyzed according to the vehicle information of the vehicle to be detected; obtaining at least one fault reason according to the key information and the fault knowledge map for a user to confirm; performing sentiment analysis on the confirmation information of the user; and diagnosing the fault reason of the vehicle to be detected in at least one fault reason according to the emotion analysis result. Therefore, excessive dependence on maintenance personnel is reduced, fault reasons are intelligently searched, the accuracy of fault detection is improved, and the maintenance efficiency is improved.

Description

Vehicle fault detection method, device, equipment and storage medium

Technical Field

The present disclosure relates to the field of fault detection, and in particular, to a method, an apparatus, a device, and a storage medium for detecting a vehicle fault.

Background

With the popularization of automobiles, a certain time and labor are consumed in the process of troubleshooting in a maintenance place such as 4S, the detection process is combined with subjective detection of automobile faults, and due to the dependence on maintenance personnel, false detection or false detection often occurs in the process of troubleshooting.

Disclosure of Invention

The embodiment of the application provides a method, a device, equipment and a storage medium for detecting vehicle faults so as to solve the problems in the related art, and the technical scheme is as follows:

in a first aspect, an embodiment of the present application provides a method for detecting a vehicle fault, including:

analyzing key information related to the fault according to the vehicle information of the vehicle to be detected;

obtaining at least one fault reason according to the key information and the fault knowledge map for a user to confirm;

performing emotion analysis on the confirmation information of the user;

and diagnosing the fault reason of the vehicle to be detected in at least one fault reason according to the emotion analysis result.

In one embodiment, the key information related to the fault is analyzed according to the vehicle information of the vehicle to be detected, and the method comprises the following steps:

and performing word segmentation and word vector structuralization processing on the vehicle information of the vehicle to be detected to obtain key information related to the fault.

In one embodiment, the method further comprises:

constructing a basic physical part knowledge graph according to basic physical part information of a plurality of vehicle types;

constructing a triple including a fault phenomenon, an emotion analysis result and a fault keyword according to historical fault interaction data;

and associating the fault reason in the historical fault interaction data with the knowledge graph of the basic physical component according to the triples to obtain the fault knowledge graph.

In one embodiment, constructing a triple including a fault phenomenon, an emotion analysis result and a fault keyword according to historical fault interaction data comprises:

analyzing query data in historical fault interaction data through a named entity recognition model to obtain fault keywords;

analyzing reply data in the historical fault interaction data through an emotion analysis cyclic neural network to obtain an emotion analysis result;

and constructing a triple by using the fault keywords, the emotion analysis result and the fault phenomenon in the historical fault interaction data.

In one embodiment, associating the fault cause in the historical fault interaction data with the knowledge graph of the basic physical component according to the triples to obtain a fault knowledge graph, includes:

according to the fault keywords in the triples, the matched basic physical component information is searched in the basic physical component knowledge graph, and the fault phenomenon in the triples to which the fault keywords belong is associated with the matched basic physical component information;

and acquiring fault reasons corresponding to the phenomena from historical fault interaction data, and associating the acquired fault reasons with the fault phenomena to obtain a fault knowledge map.

In one embodiment, emotion analysis is performed on the confirmation information of the user, and the emotion analysis comprises the following steps:

and performing emotion analysis on the confirmation information of the user by using an emotion analysis recurrent neural network to determine the emotion type of the confirmation information.

In one embodiment, the diagnosing the fault cause of the vehicle to be detected in at least one fault cause according to the emotion analysis result comprises:

and when the user is determined to have positive emotion for one of the at least one fault reason according to emotion analysis, diagnosing the fault reason as the fault reason of the vehicle to be detected.

In one embodiment, the analyzing key information related to the fault according to the vehicle information of the vehicle to be detected comprises:

judging whether the vehicle information of the vehicle to be detected contains the fault code, and analyzing key information related to the fault from the vehicle information under the condition that the vehicle information does not contain the fault code.

In one embodiment, the method further comprises:

and prompting to perform manual diagnosis under the condition that at least one fault reason is determined not to be the fault reason of the vehicle to be detected according to emotion analysis, and updating the result of the manual diagnosis to a fault knowledge map.

In one embodiment, the method further comprises:

and determining a corresponding fault solution and providing the corresponding fault solution for a user according to the diagnosed fault reason of the vehicle to be detected.

In a second aspect, an embodiment of the present application provides a vehicle fault detection apparatus, including:

the analysis module is used for analyzing key information related to the fault according to the vehicle information of the vehicle to be detected;

the processing module is used for obtaining at least one fault reason according to the key information and the fault knowledge map for a user to confirm;

the analysis module is used for carrying out sentiment analysis on the confirmation information of the user;

and the fault detection module is used for diagnosing the fault reason of the vehicle to be detected in at least one fault reason according to the emotion analysis result.

In one embodiment, a parsing module includes:

and the first analysis unit is used for carrying out word segmentation and word vector structuralization on the vehicle information of the vehicle to be detected to obtain key information related to the fault.

In one embodiment, the above apparatus further comprises:

the basic physical part knowledge graph building module is used for building a basic physical part knowledge graph according to basic physical part information of a plurality of vehicle types;

the triple construction module is used for constructing a triple including a fault phenomenon, an emotion analysis result and a fault keyword according to historical fault interaction data;

and the fault knowledge map building module is used for associating the fault reason in the historical fault interaction data with the knowledge map of the basic physical component according to the triples to obtain the fault knowledge map.

In one embodiment, the triple construction module includes:

the second analysis unit is used for analyzing query data in the historical fault interaction data through the named entity identification model to obtain fault keywords;

the third analysis unit is used for analyzing reply data in the historical fault interaction data through the emotion analysis circulating neural network to obtain an emotion analysis result;

and the construction unit is used for constructing the triple by using the fault keywords, the emotion analysis result and the fault phenomenon in the historical fault interaction data.

In one embodiment, the fault knowledge graph building module comprises:

the first matching association unit is used for searching matched basic physical component information in the basic physical component knowledge graph according to the fault keyword in the triple, and associating the fault phenomenon in the triple to which the fault keyword belongs with the matched basic physical component information;

and the second matching and associating unit is used for acquiring the fault reason corresponding to the fault phenomenon from the historical fault interaction data and associating the acquired fault reason with the fault phenomenon to obtain a fault knowledge map.

In one embodiment, an analysis module comprises:

and the emotion analysis unit is used for carrying out emotion analysis on the confirmation information of the user by using the emotion analysis recurrent neural network and determining the emotion type of the confirmation information.

In one embodiment, a fault detection module includes:

and the sub-processing unit is used for diagnosing one of the at least one fault reason as the fault reason of the vehicle to be detected when the user is determined to be the positive emotion according to the emotion analysis.

In one embodiment, a parsing module includes:

and the judging unit is used for judging whether the vehicle information of the vehicle to be detected contains the fault code or not, and analyzing key information related to the fault from the vehicle information under the condition that the vehicle information does not contain the fault code.

In one embodiment, the apparatus further comprises:

and the manual diagnosis module is used for prompting manual diagnosis and updating the result of the manual diagnosis to the fault knowledge map under the condition that at least one fault reason is determined not to be the fault reason of the vehicle to be detected according to the emotion analysis.

In one embodiment, the above apparatus further comprises:

and the scheme determining module is used for determining a corresponding fault solution according to the diagnosed fault reason of the vehicle to be detected and providing the corresponding fault solution for a user.

In a third aspect, an embodiment of the present application provides a system for detecting a vehicle fault, where the apparatus includes: a memory and a processor. Wherein the memory and the processor are in communication with each other via an internal connection path, the memory is configured to store instructions, the processor is configured to execute the memory-stored instructions, and the processor is configured to cause the processor to perform the method of any of the above-described aspects when executing the memory-stored instructions.

In a fourth aspect, the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program runs on a computer, the method in any one of the above-described aspects is executed.

The advantages or beneficial effects in the above technical solution at least include: through analyzing key information in the vehicle information, at least one fault reason is obtained by combining the fault knowledge map for a user to confirm, and emotion analysis is carried out on the confirmation information of the user, so that the fault reason of the vehicle to be detected is diagnosed in the at least one fault reason according to an analysis result, excessive dependence on maintenance personnel is reduced, the fault reason is intelligently searched, the accuracy of fault detection is improved, and meanwhile, the maintenance efficiency is improved.

The foregoing summary is provided for the purpose of description only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the present application will be readily apparent by reference to the drawings and the following detailed description.

Drawings

In the drawings, like reference numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified. The figures are not necessarily to scale. It is appreciated that these drawings depict only some embodiments in accordance with the disclosure and are therefore not to be considered limiting of its scope.

FIG. 1 is a schematic flow diagram of a method of detecting a vehicle fault according to an embodiment of the present disclosure;

FIG. 2 is a schematic diagram of a fault knowledge-graph according to an embodiment of the present disclosure;

FIG. 3 is a flow diagram of a method of building a fault knowledge graph according to an embodiment of the present disclosure;

FIG. 4 is a flow chart diagram of a method of vehicle fault detection according to another embodiment of the present disclosure;

FIG. 5 is a flow chart diagram of a method of vehicle fault detection in an embodiment of the present disclosure;

FIG. 6 is a schematic block diagram of a vehicle fault detection apparatus according to an embodiment of the present disclosure;

FIG. 7 is a schematic block diagram of constructing a fault knowledge map in a vehicle fault detection apparatus according to an embodiment of the present disclosure;

FIG. 8 is a schematic block diagram of a vehicle fault detection apparatus according to an embodiment of the present disclosure;

FIG. 9 is a block diagram of a vehicle fault detection system used to implement embodiments of the present disclosure.

Detailed Description

In the following, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments may be modified in various different ways, all without departing from the spirit or scope of the present application. Accordingly, the drawings and description are to be regarded as illustrative in nature, and not as restrictive.

FIG. 1 is a flow chart of a method of vehicle fault detection according to an embodiment of the present application. As shown in fig. 1, the method for detecting a vehicle fault may include:

and S11, analyzing key information related to the fault according to the vehicle information of the vehicle to be detected.

It should be noted that the control end for detecting the vehicle fault is preferably a vehicle fault detection system (or even a cloud server). It will be appreciated that the vehicle fault detection system may be integrated into the vehicle control system (i.e., ECU) or may be independent of the vehicle control system. The detection system can be realized by software and/or hardware, and the detection system can be formed by two or more physical entities or one physical entity.

The vehicle information may be text information uploaded to the detection system by the user, or may be voice information uploaded to the detection system by the user, and the voice information is converted into text information, which is not limited herein. For example, the voice of the user may be collected by a sound collector on the vehicle, and then the voice is recognized as corresponding text information. For another example, the user collects the user voice through a microphone of a mobile phone and uploads the user voice to the detection system. It should be understood that the above are examples given in the present invention, and the present invention is not limited to the manner of sound collection and analysis, and all the manners of sound collection and analysis are within the scope of the present invention.

Illustratively, the vehicle information is a current vehicle fault phenomenon discovered by the user, for example, if the user says "the car is not on fire", the voice of the user is converted into words to be further analyzed, and the key information "the car is on fire" is obtained.

And S12, obtaining at least one fault reason according to the key information and the fault knowledge map for a user to confirm.

It should be noted that the fault obtains at least one fault reason according to the key information and the fault knowledge graph, so that the user can confirm that the knowledge graph includes a system, a component and a part corresponding to each vehicle type, and each part has a corresponding fault phenomenon corresponding to at least one fault reason. In this embodiment, a Match language may be used to index key information in the failure knowledge graph to find failed components and parts, and a manner similar to a decision tree or a binary tree algorithm may also be used to index key information to find failed components and parts. It can be understood that information such as vehicle models can be added for indexing, and fault reasons can be found more quickly.

Illustratively, when the key information is "fire not fired", because fire not fired belongs to a fault phenomenon, at least one fault reason corresponding to the fault phenomenon is searched in the fault knowledge map and sent to a user for confirmation. It can be understood that the voice question and answer can be performed with the user through the vehicle-mounted voice interaction system, and the voice question and answer can also be sent to the user in the form of short messages, mails and the like, which is not limited herein.

And S13, performing emotion analysis on the confirmation information of the user.

It should be noted that the confirmation information of the user may be fed back in a text form or in a voice form, which is not limited herein.

The emotion analysis is an analysis of the content of the confirmation information, and may be a positive emotion, a negative emotion, or another emotion. The emotion analysis may be performed by a neural network model, a self-attention mechanism model, or the like, and is not limited herein.

And S14, diagnosing the fault reason of the vehicle to be detected in at least one fault reason according to the emotion analysis result.

And further, when the user is determined to have positive emotion for one of the at least one fault reason according to emotion analysis, diagnosing the fault reason as the fault reason of the vehicle to be detected.

It can be understood that when the emotion analysis structure is negative emotion or other emotions, the current fault cause is not the fault cause of the vehicle to be detected.

Exemplarily, inquiring whether oil leakage of the oil tank is found or not, and if yes, indicating that the oil leakage of the oil tank is the fault reason of the vehicle to be detected; and when the user answers 'no', the fact that the oil leakage of the oil tank is not the fault reason of the vehicle to be detected is indicated.

In conclusion, by analyzing key information in the vehicle information, at least one fault reason is obtained by combining the fault knowledge map for the user to confirm, and emotion analysis is performed on the confirmation information of the user, so that the fault reason of the vehicle to be detected is diagnosed in the at least one fault reason according to an analysis result, excessive dependence on maintenance personnel is reduced, the fault reason is intelligently searched, the accuracy of fault detection is improved, and the maintenance efficiency is improved.

In one embodiment, the step S11 of analyzing key information related to the fault according to the vehicle information of the vehicle to be detected includes:

Specifically, word segmentation is performed on the vehicle information through Jieba to obtain corresponding word vectors, so that word segmentation of natural language is achieved, and some stop words (such as language words) are provided. For example, "engine damage of an automobile", the word cutting results in [ 'automobile', 'engine', 'damage' ].

Because natural language cannot be identified in the calculation process, the Word2vec is used for structuralizing to obtain key information, the non-structural Word vector is converted into the structuralized vector, and the natural language information can be reserved after the Word2vec is converted, so that the key information can be conveniently calculated in the follow-up process, and the original information cannot be lost. For example, word vector conversion preferentially performs one-hot encoding on a Word, word2vec randomly initializes a W weight matrix, performs inner product operation on the converted one-hot encoding, performs weighted average calculation on the result of the inner product to obtain θ, and finally adds a fully-connected network W to Word2vec, so that the Word vector = θ W.

In one embodiment, as shown in fig. 2-3, the method for detecting a vehicle fault further comprises:

and S31, constructing a basic physical part knowledge graph according to the basic physical part information of the plurality of vehicle types.

In this embodiment, the attributes and numbers of the respective systems, components, and parts in the same vehicle model are extracted. And (3) adopting Match creation statements to construct nodes for each system, component and part in the gallery, and then creating the relationship among the nodes according to the Match. For example, the knowledge graph of the basic physical part is constructed according to the composition of the vehicle, the vehicle type and the system under the vehicle type are in one relationship, each system and the component formed under the system are in another relationship, each component and the part under the component are in another relationship, and the knowledge graph of the basic physical part is constructed through the relationships. It should be noted that the Match language can perform operations of adding, deleting, and modifying the graph database. The gallery may be a Neo4J gallery, and may also be another gallery, which is not limited herein.

And S32, constructing a triple containing the fault phenomenon, the emotion analysis result and the fault keyword according to the historical fault interaction data.

In the embodiment, the historical fault interaction data refers to the question and answer content between the maintenance personnel and the user, and it can be understood that the fault reason of the vehicle can be determined by referring to the question and answer content between the maintenance personnel and the user. Therefore, the fault phenomenon, the fault keyword and the sentiment analysis result are extracted from historical fault interaction data, and the relation between the three is established, so that the fault cause and the original fault knowledge map can be quickly associated.

Illustratively, fault keywords such as "oil tank leak", "battery short", etc. The fault phenomenon is 'fire failure', and the emotion analysis result refers to 'yes', 'no', and the like. The triple contents can be that the fire is not fired, the storage battery is in power shortage, or the fire is not fired, the oil tank is not in oil leakage.

And S33, associating the fault reason in the historical fault interaction data with the knowledge graph of the basic physical component according to the triples to obtain the fault knowledge graph.

It should be noted that, since the triplet includes: the fault keywords and the fault phenomena can be associated with the fault reasons and the basic physical part knowledge map through the fault keywords, and can also be associated with the fault reasons and the basic physical part knowledge map through the fault phenomena, so that the fault knowledge map is obtained, a user can determine the fault reasons according to the fault knowledge map, and the dependency on maintenance personnel is reduced.

In one embodiment, step S20, constructing a triple including a fault phenomenon, an emotion analysis result, and a fault keyword according to historical fault interaction data includes:

analyzing query data in historical fault interaction data through a named entity identification model to obtain fault keywords;

It should be noted that the named entity recognition model may be a Bi-directional RNN structure combined CRF model, or a Bi-LSMT combined CRF model, in this embodiment, a Bi-LSMT combined CRF model is adopted, and the training process of the Bi-LSTM + CRF model includes converting query data of a serviceman into word vectors, manually labeling fault keywords, converting the word vectors and the fault keywords in the query data into numbers, and training the word vectors in the converted query data and the converted fault keywords through the Bi-LSTM + CRF model, so that the Bi-LSTM + CRF model can recognize the query data of the serviceman.

The training of the word vector by the Bi-LSMT considers the situation before and after the current moment, so that the effect on natural language processing is better, and the recognition error is reduced. The Bi-LSMT is combined with the CRF model in order to find the probability of labeling the sequence which is most likely to occur under the sequence under the condition of knowing the probability distribution of each word, and a hidden layer (N-dimensional vector) calculated by the Bi-LSTM is transmitted into the CRF model, so that the CRF model is utilized to process the problem of local normalization of the Bi-LSTM.

For illustrative purposes, reference may be made in particular to the following formulae:

in this embodiment, the emotion analysis cyclic neural network is an LSTM neural network, and the LSTM neural network is trained so that it can determine the emotion of the input sentence, such as a positive emotion, a negative emotion, and other emotions.

It should be noted that the emotion analysis recurrent neural network is trained by converting the reply data (i.e., the reply data of the user) into a word vector and manually identifying the meaning of the reply data, where 0 indicates yes, 1 indicates no, and 2 indicates others. And training the converted word vector and the meaning through an LSTM recurrent neural network so that the LSTM recurrent neural network can carry out emotion analysis.

In one embodiment, step S33, associating the fault cause in the historical fault interaction data with the knowledge graph of the basic physical component according to the triples to obtain a fault knowledge graph, includes:

according to the fault keywords in the triples, the matched basic physical piece information is searched in the basic physical piece knowledge map, and the fault phenomenon in the triples to which the fault keywords belong is associated with the matched basic physical piece information;

and acquiring fault reasons corresponding to the fault phenomena from historical fault interaction data, and associating the acquired fault reasons with the fault phenomena to obtain a fault knowledge map.

It should be noted that, in the historical fault interaction data, the fault cause corresponding to the fault phenomenon is determined according to the query data and the reply data. In this embodiment, the corresponding component or part is matched by the fault keyword, the Match creation statement is used to construct the fault phenomenon node, the fault phenomenon node is spliced to the matched component or part, and the Match creation statement is used to construct the fault cause node causing the fault phenomenon and spliced to the fault phenomenon.

In one embodiment, the step S13 of performing emotion analysis on the confirmation information of the user includes:

In this embodiment, the confirmation information of the user is input into the LSTM neural network, and the LSTM neural network analyzes the input information to determine the corresponding emotion type, and determines whether to continue to confirm the user according to the positive emotion, the negative emotion, or other emotions.

In one embodiment, step S14, diagnosing a fault cause of the vehicle to be detected from at least one fault cause according to the result of emotion analysis, includes:

In this embodiment, after a plurality of failure causes are determined according to the key information, the failure causes are sequentially queried to the user in a voice query manner, for example, the failure causes are converted into voice through the vehicle-mounted voice interaction system and are queried to the user. Judging the emotion type of the user according to the voice response of the user until the emotion type is a positive emotion, ending the inquiry, and determining the fault reason of the vehicle to be detected.

and judging whether the vehicle information of the vehicle to be detected contains the fault code, and analyzing key information related to the fault from the vehicle information under the condition that the vehicle information does not contain the fault code.

Specifically, the automobile fault code is a fault code reflected by the ECU analysis after the automobile has a fault. In this embodiment, if the vehicle information does not include the failure code, it means that the failure cannot be directly identified as the cause of the failure, and therefore, the vehicle information needs to be further analyzed to identify the cause of the failure.

Further, if the vehicle information of the vehicle to be detected contains the fault code, the corresponding fault reason is directly searched according to the fault code.

In this embodiment, a corresponding fault code is generally displayed on a dashboard or a console to prompt a user of a corresponding fault reason. Exemplarily, when a user sees a P0123 displayed on the console, the user may input "P0123" by voice or text and send it to the detection system, and the detection system searches for a failure cause corresponding to P0123 and then sends the failure cause to the client. For example, the OBD diagnosis system searches the fault reason corresponding to the fault code. For another example, the original data of the host factory system is extracted in advance, and a corresponding relationship between the fault code and the fault cause is created, so that the fault code can search for the corresponding fault cause through the corresponding relationship. When the vehicle information contains the fault code, the fault reason can be determined by inquiring the fault, so that the vehicle information does not need to be further analyzed, and the fault detection process is more intelligent.

Fig. 4 is a flowchart of a fault detection method of a vehicle according to another embodiment of the present disclosure. As shown in fig. 4-5, the method may include:

and S41, analyzing key information related to the fault according to the vehicle information of the vehicle to be detected.

And S42, obtaining at least one fault reason according to the key information and the fault knowledge map for the user to confirm.

And S43, emotion analysis is carried out on the confirmation information of the user.

And S44, under the condition that at least one fault reason is determined not to be the fault reason of the vehicle to be detected according to emotion analysis, prompting to carry out manual diagnosis, and updating the result of the manual diagnosis to a fault knowledge map.

In this embodiment, when the vehicle information does not include the fault code, the vehicle information is analyzed to obtain key information, at least one corresponding fault reason is searched in the fault knowledge graph according to the key information, the fault reasons are sequentially inquired for the user, and then confirmation information of the user is received, and when the confirmation information of the user is all non-positive emotions (i.e., negative emotions or other emotions), it is indicated that none of the searched fault reasons is a correct fault reason. Therefore, manual diagnosis is required. It should be noted that, if the cause of the fault of the vehicle to be detected cannot be determined, it is indicated that the fault knowledge graph does not have the fault of this type, interactive data (i.e., query data of a maintenance worker and reply data of a user) in the manual diagnosis process is obtained, the query data of the maintenance worker is analyzed through the named entity identification model to obtain fault keywords, the reply data is analyzed through the sentiment analysis recurrent neural network to obtain sentiment analysis results, and the three are combined into a triple and the fault knowledge graph is updated according to key information (i.e., fault phenomenon) determined by vehicle information input by the user. Therefore, the knowledge graph spectrum is continuously updated through the fault interaction data obtained through manual diagnosis, so that the vehicle fault detection is more accurate, the dependence on maintenance personnel is greatly reduced, and the fault detection accuracy is improved.

In one embodiment, the method of fault detection of a vehicle further comprises:

Specifically, a correspondence table between the failure cause and the failure solution may be stored in the failure detection system in advance, or a node for creating the failure solution in the failure knowledge graph may be created in advance and connected to the corresponding failure keyword node. Then, after the fault reason of the vehicle to be detected is determined, the corresponding fault solution is extracted and sent to the user in the modes of short messages, mails or voice broadcast and the like, so that the user can rapidly solve the fault according to the solution, and the user experience is improved.

Fig. 6 is a block diagram showing a configuration of a vehicle failure detection apparatus according to an embodiment of the present invention. As shown in fig. 6, the apparatus may include:

the analysis module 61 is used for analyzing key information related to the fault according to the vehicle information of the vehicle to be detected;

the processing module 62 is configured to obtain at least one fault reason according to the key information and the fault knowledge map, and allow a user to confirm the at least one fault reason;

the analysis module 63 is used for performing emotion analysis on the confirmation information of the user;

and the fault detection module 64 is used for diagnosing the fault reason of the vehicle to be detected from the at least one fault reason according to the emotion analysis result.

In one embodiment, the parsing module 61 includes:

In one embodiment, as shown in fig. 7, the apparatus further comprises:

the basic physical part knowledge graph building module 71 is used for building a basic physical part knowledge graph according to basic physical part information of a plurality of vehicle types;

the triple construction module 72 is used for constructing a triple containing a fault phenomenon, an emotion analysis result and a fault keyword according to historical fault interaction data;

and the fault knowledge map building module 73 is configured to associate the fault reason in the historical fault interaction data with the knowledge map of the basic physical component according to the triples to obtain the fault knowledge map.

In one embodiment, the triplet construction module 72 includes:

the third analysis unit is used for analyzing the reply data in the historical fault interaction data through the emotion analysis cyclic neural network to obtain an emotion analysis result;

In one embodiment, the fault knowledge map building module 73 includes:

In one embodiment, the analysis module 63 includes:

In one embodiment, the fault detection module 64 includes:

In one embodiment, the parsing module 61 includes:

In one embodiment, as shown in fig. 8, the apparatus further comprises:

and the manual diagnosis module 65 is used for prompting manual diagnosis and updating the result of the manual diagnosis to the fault knowledge map when determining that at least one fault reason is not the fault reason of the vehicle to be detected according to the emotion analysis.

In one embodiment, the apparatus further comprises:

Therefore, the device provided by the embodiment of the application can determine the fault reason of the vehicle to be detected by combining the key information and the fault knowledge map with the emotion analysis result of the user confirmation information.

The functions of each module in each apparatus in the embodiment of the present application may refer to corresponding descriptions in the above method, and are not described herein again.

Fig. 9 shows a block diagram of a vehicle failure detection system according to an embodiment of the present invention. As shown in fig. 9, the vehicle failure detection system includes: a memory 910 and a processor 920, the memory 910 having stored therein computer programs operable on the processor 920. The processor 920 implements the detection method of the vehicle failure in the above-described embodiment when executing the computer program. The number of the memory 910 and the processor 920 may be one or more.

The vehicle fault detection system further includes:

and a communication interface 930 for communicating with an external device to perform data interactive transmission.

If the memory 910, the processor 920 and the communication interface 930 are implemented independently, the memory 910, the processor 920 and the communication interface 930 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 9, but that does not indicate only one bus or one type of bus.

Optionally, in an implementation, if the memory 910, the processor 920 and the communication interface 930 are integrated on a chip, the memory 910, the processor 920 and the communication interface 930 may complete communication with each other through an internal interface.

Embodiments of the present invention provide a computer-readable storage medium, which stores a computer program, and when the program is executed by a processor, the computer program implements the method provided in the embodiments of the present application.

The embodiment of the present application further provides a chip, where the chip includes a processor, and is configured to call and execute the instruction stored in the memory from the memory, so that the communication device in which the chip is installed executes the method provided in the embodiment of the present application.

An embodiment of the present application further provides a chip, including: the system comprises an input interface, an output interface, a processor and a memory, wherein the input interface, the output interface, the processor and the memory are connected through an internal connection path, the processor is used for executing codes in the memory, and when the codes are executed, the processor is used for executing the method provided by the embodiment of the application.

It should be understood that the processor may be a Central Processing Unit (CPU), other general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or any conventional processor or the like. It is noted that the processor may be a processor supporting advanced reduced instruction set machine (ARM) architecture.

Further, optionally, the memory may include a read-only memory and a random access memory, and may further include a nonvolatile random access memory. The memory may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The non-volatile memory may include a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable EPROM (EEPROM), or a flash memory. Volatile memory can include Random Access Memory (RAM), which acts as external cache memory. By way of example, and not limitation, many forms of RAM are available. For example, static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), and direct bus RAM (DR RAM).

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The procedures or functions according to the present application are all or partially generated when the computer program instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium.

In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps in the process. And the scope of the preferred embodiments of the present application includes other implementations in which functions may be performed out of the order shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved.

The logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions.

It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. All or part of the steps of the method of the above embodiments may be implemented by hardware that is configured to be instructed to perform the relevant steps by a program, which may be stored in a computer-readable storage medium, and which, when executed, includes one or a combination of the steps of the method embodiments.

In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The above-described integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may also be stored in a computer-readable storage medium. The storage medium may be a read-only memory, a magnetic or optical disk, or the like.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various changes or substitutions within the technical scope of the present application, and these should be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method of detecting a vehicle fault, comprising:

performing emotion analysis on the confirmation information of the user;

and diagnosing the fault reason of the vehicle to be detected in the at least one fault reason according to the emotion analysis result.

2. The method according to claim 1, wherein the step of analyzing key information related to the fault according to the vehicle information of the vehicle to be detected comprises the following steps:

3. The method of claim 1, further comprising:

and associating the fault reasons in the historical fault interaction data with the knowledge graph of the basic physical component according to the triples to obtain the fault knowledge graph.

4. The method of claim 3, wherein constructing a triple including a fault phenomenon, an emotion analysis result and a fault keyword according to historical fault interaction data comprises:

analyzing the reply data in the historical fault interaction data through an emotion analysis cyclic neural network to obtain an emotion analysis result;

and constructing a triple by using the fault keyword, the emotion analysis result and the fault phenomenon in the historical fault interaction data.

5. The method of claim 3, wherein associating the fault cause in the historical fault interaction data with the underlying physical part knowledge graph according to the triples to obtain the fault knowledge graph comprises:

and acquiring a fault reason corresponding to the fault phenomenon from the historical fault interaction data, and associating the acquired fault reason with the fault phenomenon to obtain the fault knowledge map.

6. The method of claim 1, wherein performing sentiment analysis on the confirmation information of the user comprises:

and performing emotion analysis on the confirmation information of the user by using an emotion analysis recurrent neural network, and determining the emotion type of the confirmation information.

7. The method according to claim 1, wherein the diagnosing the fault cause of the vehicle to be detected among the at least one fault cause according to the result of the sentiment analysis comprises:

and when the user determines that one of the at least one fault reason is positive emotion according to the emotion analysis, diagnosing the fault reason as the fault reason of the vehicle to be detected.

8. The method according to claim 1, wherein the step of analyzing key information related to the fault according to the vehicle information of the vehicle to be detected comprises the following steps:

judging whether vehicle information of a vehicle to be detected contains a fault code, and analyzing key information related to the fault from the vehicle information under the condition that the vehicle information does not contain the fault code.

9. The method of claim 1, further comprising:

and prompting to perform manual diagnosis under the condition that the at least one fault reason is determined to be not the fault reason of the vehicle to be detected according to the emotion analysis, and updating the result of the manual diagnosis to the fault knowledge map.

10. The method of claim 1, further comprising:

and determining a corresponding fault solution according to the diagnosed fault reason of the vehicle to be detected and providing the corresponding fault solution for the user.

11. A vehicle malfunction detection device, characterized by comprising:

the analysis module is used for carrying out emotion analysis on the confirmation information of the user;

and the fault detection module is used for diagnosing the fault reason of the vehicle to be detected in the at least one fault reason according to the emotion analysis result.

12. The apparatus of claim 11, wherein the parsing module comprises:

and the first analysis unit is used for carrying out word segmentation and word vector structuralization processing on the vehicle information of the vehicle to be detected to obtain key information related to the fault.

13. The apparatus of claim 11, further comprising:

the triple construction module is used for constructing a triple containing a fault phenomenon, an emotion analysis result and a fault keyword according to historical fault interaction data;

and the fault knowledge map building module is used for associating the fault reasons in the historical fault interaction data with the knowledge map of the basic physical component according to the triples to obtain the fault knowledge map.

14. The apparatus of claim 13, wherein the triplet building module comprises:

the third analysis unit is used for analyzing the reply data in the historical fault interaction data through an emotion analysis cyclic neural network to obtain an emotion analysis result;

and the construction unit is used for constructing a triple by using the fault keyword, the emotion analysis result and the fault phenomenon in the historical fault interaction data.

15. The apparatus of claim 13, wherein the fault knowledge graph building module comprises:

the first matching association unit is used for associating the fault phenomenon in the triple to which the fault keyword belongs with the matched basic physical piece information;

and the second matching and associating unit is used for acquiring the fault reason corresponding to the fault phenomenon from the historical fault interaction data and associating the acquired fault reason with the fault phenomenon to obtain the fault knowledge map.

16. The apparatus of claim 11, wherein the analysis module comprises:

and the emotion analysis unit is used for carrying out emotion analysis on the confirmation information of the user by using an emotion analysis recurrent neural network and determining the emotion type of the confirmation information.

17. The apparatus of claim 11, wherein the fault detection module comprises:

18. The apparatus of claim 11, wherein the parsing module comprises:

the judging unit is used for judging whether the vehicle information of the vehicle to be detected contains the fault code or not, and analyzing key information related to the fault from the vehicle information under the condition that the vehicle information does not contain the fault code.

19. The apparatus of claim 11, further comprising:

and the manual diagnosis module is used for prompting manual diagnosis and updating the result of the manual diagnosis to the fault knowledge map under the condition that the at least one fault reason is determined not to be the fault reason of the vehicle to be detected according to the emotion analysis.

20. The apparatus of claim 11, further comprising:

and the scheme determining module is used for determining a corresponding fault solution according to the diagnosed fault reason of the vehicle to be detected and providing the corresponding fault solution to the user.

21. A vehicle fault detection system, comprising: a processor and a memory, the memory having stored therein instructions that are loaded and executed by the processor to implement the method of any of claims 1 to 10.

22. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-10.