CN116129551A - Automobile fault root cause analysis method, device, computer equipment and storage medium - Google Patents
Automobile fault root cause analysis method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN116129551A CN116129551A CN202211580383.5A CN202211580383A CN116129551A CN 116129551 A CN116129551 A CN 116129551A CN 202211580383 A CN202211580383 A CN 202211580383A CN 116129551 A CN116129551 A CN 116129551A
- Authority
- CN
- China
- Prior art keywords
- fault
- automobile
- information
- root cause
- phenomenon
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 90
- 238000000034 method Methods 0.000 claims abstract description 59
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 24
- 238000010801 machine learning Methods 0.000 claims abstract description 24
- 238000004364 calculation method Methods 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 18
- 230000015654 memory Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 10
- 230000004927 fusion Effects 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 9
- 238000012423 maintenance Methods 0.000 description 9
- 238000003745 diagnosis Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 7
- 230000002457 bidirectional effect Effects 0.000 description 6
- 230000006403 short-term memory Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000007787 long-term memory Effects 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 108010001267 Protein Subunits Proteins 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0808—Diagnosing performance data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Vehicle Cleaning, Maintenance, Repair, Refitting, And Outriggers (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application relates to an automobile fault root cause analysis method, an automobile fault root cause analysis device, computer equipment and a storage medium, wherein the automobile fault root cause analysis method comprises the following steps: the method comprises the steps of processing related documents of automobile fault information through a machine learning algorithm to obtain a triplet set corresponding to the related documents, constructing a knowledge graph corresponding to the automobile fault information based on the triplet set corresponding to the related documents, further generating a plurality of fault reason slot information corresponding to a target automobile fault phenomenon based on the knowledge graph, and carrying out knowledge calculation on the plurality of fault reason slot information to obtain a root cause analysis result corresponding to the target automobile fault phenomenon.
Description
Technical Field
The present disclosure relates to the field of automobile fault diagnosis technologies, and in particular, to an automobile fault root cause analysis method, an automobile fault root cause analysis device, a computer device, and a storage medium.
Background
With the rapid increase of the automobile maintenance quantity in each area, the number of various automobile faults is increased continuously, however, the existing automobile fault diagnosis process still has more problems, for example, the fault diagnosis process is excessively dependent on personal experience of a maintenance technician, sporadic fault data are difficult to obtain, and the like, which can cause that the automobile faults cannot be effectively processed, so that the automobile fault diagnosis process needs to be optimized.
According to the existing fault diagnosis method, vehicle type configuration information and fault codes of a vehicle are obtained through a vehicle fault diagnosis instrument, and fault reasons of the fault vehicle and automobile parts influenced by the fault reasons are obtained based on the fault codes.
Aiming at the problem that the deep analysis of the fault root causes cannot be carried out according to the actual fault conditions in the related technology, no effective solution is proposed at present.
Disclosure of Invention
In this embodiment, a method, an apparatus, a computer device, and a storage medium for analyzing a root cause of an automobile fault are provided, so as to solve the problem that in the related art, the root cause of the fault cannot be deeply analyzed according to an actual fault condition.
In a first aspect, in this embodiment, there is provided a method for analyzing a root cause of an automobile fault, the method including:
processing related documents of automobile fault information through a machine learning algorithm to obtain a triplet set corresponding to the related documents;
constructing a knowledge graph corresponding to the automobile fault information based on the triplet set corresponding to the related document;
and generating a plurality of fault reason slot position information corresponding to the fault phenomenon of the target automobile based on the knowledge graph, and performing knowledge calculation on the fault reason slot position information to obtain a root cause analysis result corresponding to the fault phenomenon of the target automobile.
In some embodiments, before the processing, by using a machine learning algorithm, the relevant document of the automobile fault information to obtain the triplet set corresponding to the relevant document, the method further includes:
and acquiring related documents of the automobile fault information, wherein the related documents comprise fault case documents corresponding to the automobile fault information.
In some embodiments, the processing, by a machine learning algorithm, the related document of the automobile fault information to obtain a triplet set corresponding to the related document includes:
The knowledge extraction is carried out on the related documents through the machine learning algorithm, so that a plurality of knowledge units corresponding to the related documents are obtained, wherein the knowledge units comprise text type automobile fault information, data type automobile fault information and threshold information of automobile part parameters;
and carrying out knowledge fusion on the plurality of knowledge units to obtain a triplet set corresponding to the related document.
In some embodiments, the constructing a knowledge graph corresponding to the automobile fault information based on the triplet set corresponding to the related document includes:
and storing the triplet set to a graph database based on a preset storage form, and generating a knowledge graph corresponding to the automobile fault information.
In some embodiments, before generating the plurality of fault cause slot information corresponding to the target automobile fault phenomenon based on the knowledge graph, the method further includes:
and acquiring the target automobile fault information based on an automobile fault retrieval page, wherein the target automobile fault information comprises a fault automobile type, a fault part and state information corresponding to the fault part.
In some embodiments, the performing knowledge calculation on the plurality of fault cause slot information to obtain a root cause analysis result corresponding to the target automobile fault phenomenon includes:
Performing word frequency statistics on the fault reason slot position information to obtain a plurality of word frequency statistics results corresponding to the fault phenomenon of the target automobile;
and carrying out path analysis on the plurality of fault cause slot position information through a hidden Markov model based on the plurality of word frequency statistical results to obtain root cause analysis results corresponding to the target automobile fault phenomenon.
In some embodiments, after the knowledge calculation is performed on the plurality of fault cause slot position information to obtain a root cause analysis result corresponding to the target automobile fault phenomenon, the method further includes:
counting fault data corresponding to the target automobile fault phenomenon, and comparing the counting result with threshold information of automobile part parameters corresponding to the automobile fault phenomenon;
and carrying out auxiliary analysis on root cause analysis results corresponding to the target automobile fault phenomenon based on the comparison results.
In a second aspect, in this embodiment, there is provided an apparatus for analyzing root cause of a failure of an automobile, the apparatus including:
the processing module is used for processing related documents of the automobile fault information through a machine learning algorithm to obtain a triplet set corresponding to the related documents;
The construction module is used for constructing a knowledge graph corresponding to the automobile fault information based on the triplet set corresponding to the related document;
and the analysis module is used for generating a plurality of fault reason slot position information corresponding to the fault phenomenon of the target automobile based on the knowledge graph, and carrying out knowledge calculation on the fault reason slot position information to obtain a root cause analysis result corresponding to the fault phenomenon of the target automobile.
In a third aspect, in this embodiment, there is provided a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the method for analyzing a root cause of a fault in an automobile according to the first aspect.
In a fourth aspect, in this embodiment, there is provided a storage medium having stored thereon a computer program which, when executed by a processor, implements the method for analyzing the root cause of a vehicle fault as described in the first aspect.
Compared with the related art, the method, the device, the computer equipment and the storage medium for analyzing the root cause of the automobile fault provided by the embodiment process related documents of the automobile fault information through a machine learning algorithm to obtain a triplet set corresponding to the related documents, construct a knowledge graph corresponding to the automobile fault information based on the triplet set corresponding to the related documents, further generate a plurality of fault cause slot information corresponding to the target automobile fault phenomenon based on the knowledge graph, and perform knowledge calculation on the plurality of fault cause slot information to obtain a root cause analysis result corresponding to the target automobile fault phenomenon, solve the problem that the root cause of the fault cannot be deeply analyzed according to the actual fault condition, improve the accuracy of the analysis result of the root cause of the fault, and effectively process the automobile fault.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the other features, objects, and advantages of the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:
fig. 1 is a hardware block diagram of a terminal device of an automobile fault root cause analysis method according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for analyzing root cause of an automobile fault according to an embodiment of the present application;
FIG. 3 is a knowledge extraction diagram of an automobile fault root cause analysis method according to an embodiment of the present application;
fig. 4 is a schematic diagram of a knowledge graph of an analysis method of a root cause of an automobile fault according to an embodiment of the present application;
FIG. 5 is a search page diagram of an automobile fault root cause analysis method according to an embodiment of the present application;
FIG. 6 is a path analysis chart of an automobile fault root cause analysis method according to an embodiment of the present application;
FIG. 7 is a flow chart of a method for analyzing root cause of an automobile fault according to an embodiment of the present application;
FIG. 8 is a preferred flow chart of a method for analyzing the root cause of an automobile fault provided in an embodiment of the present application;
fig. 9 is a block diagram of an apparatus for analyzing root cause of failure of an automobile according to an embodiment of the present application.
In the figure: 102. a processor; 104. a memory; 106. a transmission device; 108. an input-output device; 10. a processing module; 20. constructing a module; 30. and an analysis module.
Detailed Description
For a clearer understanding of the objects, technical solutions and advantages of the present application, the present application is described and illustrated below with reference to the accompanying drawings and examples.
Unless defined otherwise, technical or scientific terms used herein shall have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terms "a," "an," "the," "these," and the like in this application are not intended to be limiting in number, but rather are singular or plural. The terms "comprising," "including," "having," and any variations thereof, as used in the present application, are intended to cover a non-exclusive inclusion; for example, a process, method, and system, article, or apparatus that comprises a list of steps or modules (units) is not limited to the list of steps or modules (units), but may include other steps or modules (units) not listed or inherent to such process, method, article, or apparatus. The terms "connected," "coupled," and the like in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. Reference to "a plurality" in this application means two or more. "and/or" describes an association relationship of an association object, meaning that there may be three relationships, e.g., "a and/or B" may mean: a exists alone, A and B exist together, and B exists alone. Typically, the character "/" indicates that the associated object is an "or" relationship. The terms "first," "second," "third," and the like, as referred to in this application, merely distinguish similar objects and do not represent a particular ordering of objects.
The method embodiments provided in the present embodiment may be executed in a terminal, a computer, or similar computing device. For example, the method runs on a terminal, and fig. 1 is a block diagram of the hardware structure of the terminal of the method for analyzing the root cause of an automobile fault according to the present embodiment. As shown in fig. 1, the terminal may include one or more (only one is shown in fig. 1) processors 102 and a memory 104 for storing data, wherein the processors 102 may include, but are not limited to, a microprocessor MCU, a programmable logic device FPGA, or the like. The terminal may also include a transmission device 106 for communication functions and an input-output device 108. It will be appreciated by those skilled in the art that the structure shown in fig. 1 is merely illustrative and is not intended to limit the structure of the terminal. For example, the terminal may also include more or fewer components than shown in fig. 1, or have a different configuration than shown in fig. 1.
The memory 104 may be used to store computer programs, such as software programs of application software and modules, such as a computer program corresponding to the method of analyzing the root cause of an automobile fault in the present embodiment, and the processor 102 executes the computer program stored in the memory 104 to perform various functional applications and data processing, i.e., implement the method described above. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, which may be connected to the terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used to receive or transmit data via a network. The network includes a wireless network provided by a communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, simply referred to as NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is configured to communicate with the internet wirelessly.
In this embodiment, a method for analyzing a root cause of an automobile fault is provided, and fig. 2 is a flowchart of the method for analyzing a root cause of an automobile fault according to this embodiment, as shown in fig. 2, where the flowchart includes the following steps:
step S210, processing related documents of the automobile fault information through a machine learning algorithm to obtain a triplet set corresponding to the related documents.
Step S220, based on the triplet set corresponding to the related document, a knowledge graph corresponding to the automobile fault information is constructed.
Step S230, based on the knowledge graph, generating a plurality of fault reason slot information corresponding to the fault phenomenon of the target automobile, and performing knowledge calculation on the plurality of fault reason slot information to obtain a root cause analysis result corresponding to the fault phenomenon of the target automobile.
The method is characterized in that the fault root cause corresponding to the fault phenomenon of the target automobile is queried together through knowledge reasoning, knowledge calculation and data analysis, wherein the knowledge reasoning comprises intention recognition and slot extraction; the knowledge calculation comprises word frequency statistics and path analysis, wherein the word frequency statistics is used for acquiring the occurrence frequency of a corresponding fault phenomenon under the occurrence condition of a certain fault cause; the data analysis includes statistical analysis and threshold comparison.
Specifically, description information of a target automobile fault phenomenon is obtained from an automobile fault retrieval page, the description information is analyzed to obtain a retrieval intention of the user, the retrieval intention of the user is converted into a graph database query language Cypher, and then a plurality of fault cause slot position information corresponding to the target automobile fault phenomenon is queried according to the graph database query language.
Further, after the root cause analysis result corresponding to the fault phenomenon of the target automobile is obtained, inquiring corresponding fault maintenance measures in a knowledge graph according to the fault root cause, and sending the fault root cause and the fault maintenance measures to users corresponding to the fault phenomenon of the target automobile.
According to the existing fault diagnosis method, vehicle type configuration information and fault codes of a vehicle are obtained through a vehicle fault diagnosis instrument, and fault reasons of the fault vehicle and automobile parts influenced by the fault reasons are obtained based on the fault codes. On the basis of the prior art, a complete knowledge graph is constructed based on fault information and corresponding fault reasons, further, fault phenomena can be deeply analyzed based on the knowledge graph to obtain accurate fault causes, specifically, relevant documents of automobile fault information are processed through a machine learning algorithm to obtain a triplet set corresponding to the relevant documents, the knowledge graph corresponding to the automobile fault information is constructed based on the triplet set corresponding to the relevant documents, further, a plurality of fault cause slot position information corresponding to a target automobile fault phenomenon is generated based on the knowledge graph, knowledge calculation is conducted on the plurality of fault cause slot position information to obtain root cause analysis results corresponding to the target automobile fault phenomenon, the problem that the fault causes cannot be deeply analyzed according to actual fault conditions is solved, accuracy of the fault root cause analysis results is improved, and accordingly, effective processing of automobile faults can be achieved.
In some embodiments, the processing, by a machine learning algorithm, the relevant document of the automobile fault information, before obtaining the triplet set corresponding to the relevant document, further includes the following steps:
step S201, obtaining related documents of automobile fault information, wherein the related documents comprise fault case documents corresponding to the automobile fault information.
Specifically, relevant documents of automobile fault information are collected from automobile relevant departments such as automobile part manufacturers, whole automobile manufacturers, automobile 4S shops, after-sales centers, automobile maintenance management centers and the like, wherein the relevant documents comprise fault classical case documents corresponding to the automobile fault information.
It should be appreciated that the above-mentioned related documents store information in various structures, wherein the various structures of the documents include structured data, such as controller area network bus data, car driving data, and the like; semi-structured data such as user behavior portraits, failure modes, impact analysis reports, etc.; documents of unstructured data, such as fault plans, troubleshooting manuals, fault cases, and fault analysis reports, etc.
According to the method and the device for obtaining the automobile fault information, the related documents of the automobile fault information are obtained, and the related documents comprise fault case documents corresponding to the automobile fault information, so that a classical fault case is added in the fault information, and the automobile fault information is more complete.
In some embodiments, the processing, by a machine learning algorithm, the relevant document of the automobile fault information to obtain the triplet set corresponding to the relevant document includes the following steps:
step S211, carrying out knowledge extraction on the related documents through a machine learning algorithm to obtain a plurality of knowledge units corresponding to the related documents, wherein the knowledge units comprise text type automobile fault information, data type automobile fault information and threshold information of automobile part parameters;
and S212, carrying out knowledge fusion on the knowledge units to obtain a triplet set corresponding to the related document.
Specifically, as shown in fig. 3, the automobile fault related corpus is labeled in sequence, and is divided into a training set, a verification set and a test set according to proportion, related documents are converted into word vectors through a bidirectional encoder representation technology (Bidirectional Encoder Representations from Transformers, abbreviated as BERT) based on a converter to represent characteristic information of texts in the related documents, the converted word vectors are transmitted to a bidirectional long and short Term Memory network (Bidirectional Long Short-Term Memory, abbreviated as BiLSTM) to learn context characteristics of the texts to obtain semantic dependency relations among texts with a larger distance, an output result of the bidirectional long and short Term Memory network is transmitted to a conditional random field (Conditional Random Field, abbreviated as CRF) to obtain labeling information of the texts to confirm entities in the related documents, an output result of the bidirectional long and short Term Memory network is transmitted to a Self-Attention mechanism (Self-Attention), and the weights of words in the texts are calculated to obtain global characteristic vector results in the texts to confirm the relations in the related documents.
It should be noted that, the knowledge extracted in this embodiment includes text type information of text type related to the automobile fault, data type information of numerical value type such as driving behavior parameters, environmental parameters and automobile state parameters in the running process of the automobile, and threshold information for maintaining normal running of the automobile.
Further, since there are texts with the same meaning but different expression modes, it is necessary to calculate the similarity between different knowledge, unify and fuse the knowledge with high similarity, and use different entities A i And B i For example, the specific calculation process is as follows:
(1) And (3) performing cosine similarity calculation on the text attribute, wherein the concrete formula is as follows:
(2) And (3) performing Jacquard similarity calculation on the collection attributes, wherein the specific formula is as follows:
(3) And calculating the numerical similarity of the numerical class attribute, wherein the specific formula is as follows:
(4) And (3) carrying out weighted calculation on the similarity of the text class, the collection class and the numerical value class attribute, fusing the similarity of the three attributes into the similarity between two entities, and comparing, if the three attributes of the two entities are very similar, merging the three attributes into one entity to eliminate ambiguity, wherein the specific formula is as follows:
where α+β+γ=1, sim (a i ,B i ) Is the similarity between two entities.
According to the method, knowledge extraction is carried out on the relevant documents through a machine learning algorithm to obtain a plurality of knowledge units corresponding to the relevant documents, the knowledge units comprise text type automobile fault information, data type automobile fault information and threshold information of automobile part parameters, knowledge fusion is carried out on the plurality of knowledge units to obtain a triplet set corresponding to the relevant documents, and therefore accurate and comprehensive automobile fault knowledge can be obtained.
In some embodiments, a knowledge graph corresponding to the automobile fault information is constructed based on a triplet set corresponding to the related document, and the method comprises the following steps:
step S221, based on a preset storage form, storing the triplet set into a graph database, and generating a knowledge graph corresponding to the automobile fault information.
It is to be noted that the triplet set obtained by fusing the knowledge is stored in a graph database in the storage forms of entity-relationship-entity, entity-attribute, relationship-attribute and the like, so as to generate a knowledge graph corresponding to the automobile fault information.
Specifically, as shown in fig. 4, a "vehicle type" is taken as a root node, a "vehicle type-part" triplet is constructed, after the "part" node, the next division is performed according to specific working conditions, so as to connect different "working condition" nodes, text attributes of the parts, threshold range of parameters of each part and other information are added in the attributes of the "working condition" node, after the "working condition" node, nodes such as "classical fault case", "fault phenomenon", "fault cause", "fault mechanism", "maintenance scheme" and the like are connected, and meanwhile, a relation is established with corresponding nodes such as "specific phenomenon", "specific cause", "specific mechanism", "specific scheme", "specific result", "specific measure" and the like.
Further, adding the attribute which is the same as the working condition corresponding to the component into the attribute of the 'failure phenomenon' node, wherein a specific attribute value is filled in according to the actual failure phenomenon, and adding the 'occurrence number' attribute into the 'failure phenomenon' node so as to record the historical occurrence number of the failure phenomenon.
In the process of storing the value class information, the type of the value is specified, and the specific type of the value comprises a floating point type or integer type and the like.
According to the embodiment, based on a preset storage form, the triplet set is stored in the graph database, and the knowledge graph corresponding to the automobile fault information is generated, so that the accuracy of the generated knowledge graph is improved.
In some embodiments, before generating the plurality of fault cause slot information corresponding to the fault phenomenon of the target automobile based on the knowledge graph, the method further includes the following steps:
and acquiring target automobile fault information based on the automobile fault retrieval page, wherein the target automobile fault information comprises a fault automobile type, fault parts and state information corresponding to the fault parts.
Specifically, as shown in fig. 5, in the automobile fault search page, filling options such as a fault vehicle type AND a fault part are set, AND the state of the fault part is described through information such as parameters, values AND units, AND since accurate fault judgment can be performed on the part only by using a plurality of parameters, the plurality of parts AND the parameters thereof can be connected through logic symbols in the search page, wherein the logic symbols include "AND", "OR", AND "NOT", AND the like.
Further, an additional description frame of the automobile fault is added in the automobile fault retrieval page and is used for supplementing automobile fault information which cannot be represented in page options, so that the automobile fault information is more complete.
According to the embodiment, the target automobile fault information is obtained based on the automobile fault retrieval page, and the target automobile fault information comprises a fault automobile type, fault parts and state information corresponding to the fault parts, so that complete target automobile fault information can be obtained.
In some embodiments, knowledge calculation is performed on a plurality of fault cause slot position information to obtain root cause analysis results corresponding to a target automobile fault phenomenon, including the following steps:
step S231, word frequency statistics is carried out on the slot position information of a plurality of fault reasons, and a plurality of word frequency statistics results corresponding to the fault phenomenon of the target automobile are obtained;
step S232, based on the word frequency statistical results, path analysis is carried out on the fault reason slot position information through a hidden Markov model to obtain root cause analysis results corresponding to the fault phenomenon of the target automobile.
It should be noted that, in the knowledge graph, there are classical fault cases of the automobile, so there are multiple pairs of fault phenomena and fault reasons corresponding to each other, however, each fault reason is not only a reason corresponding to a single fault phenomenon, but also can be used as a fault phenomenon corresponding to a fault reason of a previous layer, so the path analysis is performed on the fault phenomenon of the target automobile through the hidden markov model, and the root cause analysis result corresponding to the fault phenomenon of the target automobile is obtained.
Specifically, in the knowledge graph, generating a plurality of fault cause slot information corresponding to the fault phenomenon of the target automobile, performing word frequency statistics on the plurality of fault cause slot information to obtain a plurality of word frequency statistics results corresponding to the fault phenomenon of the target automobile, for example, that a fault existsThe phenomenon is F x And the failure cause is F y N represents the occurrence number of faults stored in the fault knowledge graph, then at F y Under the condition, the fault phenomenon F occurs x Frequency P (F) x |F y ) Can be expressed as:
wherein, the liquid crystal display device comprises a liquid crystal display device,
indicating the cause of failure F y Cause failure phenomenon F x The number of occurrences of occurrence, < >>
Indicating the cause of failure F y Path analysis is performed on the plurality of fault cause slot information through a hidden markov model to obtain a root cause analysis result corresponding to the fault phenomenon of the target automobile, for example, as shown in fig. 6, based on the hidden markov chain method, the probability P (F (i, j) i a of the fault phenomenon a occurring under the condition of the fault cause F (i, j) is expressed by the following formula:
P(F(i,j)|A)＝P(F(i,j)|F(i-1,k))×P(F(i-1,k)|F(i-2,r))×……×P(F(1,h)|A)；
wherein A is a fault phenomenon, i is a fault cause layer, and F (i, j) represents a j-th fault cause of the i fault cause layer.
Further, the occurrence probabilities of all fault reasons corresponding to the fault phenomenon are calculated according to the hidden Markov chain method, and comparison is carried out, so that the fault reason with the largest occurrence probability is taken as the fault root cause corresponding to the fault phenomenon.
According to the embodiment, word frequency statistics is carried out on the plurality of fault cause slot information to obtain a plurality of word frequency statistics results corresponding to the fault phenomenon of the target automobile, and path analysis is carried out on the plurality of fault cause slot information through a hidden Markov model based on the plurality of word frequency statistics results to obtain root cause analysis results corresponding to the fault phenomenon of the target automobile.
In some embodiments, knowledge calculation is performed on the plurality of fault cause slot position information to obtain root cause analysis results corresponding to the fault phenomenon of the target automobile, and then the method further comprises the following steps:
step S241, statistics of fault data corresponding to the fault phenomenon of the target automobile is carried out, and the statistical result is compared with threshold information of automobile part parameters corresponding to the fault phenomenon of the automobile;
step S242, based on the comparison result, performing auxiliary analysis on the root cause analysis result corresponding to the target automobile fault phenomenon.
Specifically, the numerical information in the fault phenomenon of the target automobile is subjected to statistical analysis, the fault data result obtained through statistics is compared with the corresponding fault threshold information in the knowledge graph, and based on the comparison result, the root cause analysis result corresponding to the fault phenomenon of the target automobile is judged in an auxiliary mode.
It is to be understood that the knowledge graph of the automobile fault is constructed based on text fault knowledge, numerical fault knowledge and threshold information of the component parameters, and when the text description of the automobile fault phenomenon is analyzed, the automobile fault can be further analyzed according to the running parameters and the state parameters of the automobile.
According to the method and the device for analyzing the root cause of the automobile, fault data corresponding to the fault phenomenon of the target automobile are counted, the counted result is compared with threshold information of automobile part parameters corresponding to the fault phenomenon of the automobile, and based on the comparison result, auxiliary analysis is conducted on root cause analysis results corresponding to the fault phenomenon of the target automobile, so that corresponding fault root causes are further analyzed according to running parameters and state parameters of the automobile, and accuracy of the fault root causes is improved.
Fig. 7 is a flow chart of an automobile fault root cause analysis method according to the present embodiment, and as shown in fig. 7, the specific process of the automobile fault root cause analysis method is as follows:
relevant documents of automobile fault information are collected from automobile relevant departments such as automobile part manufacturers, whole automobile manufacturers, automobile 4S shops, automobile after-sales centers, automobile maintenance management centers and the like, knowledge extraction is conducted on the relevant documents through a machine learning algorithm to obtain a plurality of knowledge units corresponding to the relevant documents, the knowledge units comprise text type automobile fault information, data type automobile fault information and threshold information of automobile part parameters, knowledge fusion is conducted on the knowledge units to obtain a triplet set corresponding to the relevant documents, and the triplet set is stored in a graph database based on a preset storage mode to construct an automobile fault knowledge map.
Setting target automobile fault information in a pull-down prompt menu of an automobile fault search page, carrying out intention recognition on the target automobile fault information, further obtaining a plurality of fault reason slot information corresponding to the target automobile fault phenomenon, carrying out word frequency statistics on the plurality of fault reason slot information to obtain a plurality of word frequency statistical results corresponding to the target automobile fault phenomenon, carrying out path analysis on the plurality of fault reason slot information through a hidden Markov model based on the plurality of word frequency statistical results to obtain root cause analysis results corresponding to the target automobile fault phenomenon, further, carrying out statistics on fault data corresponding to the target automobile fault phenomenon, comparing the statistical results with threshold information of automobile part parameters corresponding to the automobile fault phenomenon, and carrying out auxiliary analysis on the root cause analysis results corresponding to the target automobile fault phenomenon based on the comparison results.
And inquiring corresponding fault maintenance measures in the knowledge graph according to the fault root cause, and sending the fault root cause and the fault maintenance measures to users corresponding to the fault phenomenon of the target automobile.
The present embodiment is described and illustrated below by way of preferred embodiments.
Fig. 8 is a preferred flowchart of the automobile fault root analysis method of the present embodiment, as shown in fig. 8, comprising the steps of:
Step S810, acquiring related documents of automobile fault information, wherein the related documents comprise fault case documents corresponding to the automobile fault information;
step S820, carrying out knowledge extraction on the related documents through a machine learning algorithm to obtain a plurality of knowledge units corresponding to the related documents, wherein the knowledge units comprise text type automobile fault information, data type automobile fault information and threshold information of automobile part parameters;
step S830, carrying out knowledge fusion on a plurality of knowledge units to obtain a triplet set corresponding to the related document;
step S840, based on a preset storage form, storing the triplet set into a graph database to generate a knowledge graph corresponding to the automobile fault information;
step S850, acquiring target automobile fault information based on the automobile fault retrieval page, wherein the target automobile fault information comprises fault automobile types, fault parts and state information corresponding to the fault parts;
step S860, based on the knowledge graph, generating a plurality of fault cause slot information corresponding to the fault phenomenon of the target automobile, and performing word frequency statistics on the plurality of fault cause slot information to obtain a plurality of word frequency statistics results corresponding to the fault phenomenon of the target automobile;
step S870, carrying out path analysis on the plurality of fault reason slot position information through a hidden Markov model based on a plurality of word frequency statistical results to obtain root cause analysis results corresponding to the fault phenomenon of the target automobile;
Step S880, counting fault data corresponding to the fault phenomenon of the target automobile, and comparing the counted result with threshold information of automobile part parameters corresponding to the fault phenomenon of the automobile;
step S890, based on the comparison result, performing auxiliary analysis on the root cause analysis result corresponding to the target automobile fault phenomenon.
According to the method, related documents of automobile fault information are obtained, knowledge extraction is conducted on the related documents through a machine learning algorithm, a plurality of knowledge units corresponding to the related documents are obtained, and the knowledge units comprise text type automobile fault information, data type automobile fault information and threshold information of automobile part parameters; carrying out knowledge fusion on a plurality of knowledge units to obtain a triplet set corresponding to a related document, storing the triplet set into a graph database based on a preset storage form, and generating a knowledge graph corresponding to automobile fault information so as to construct an automobile fault knowledge graph with complete information; further, based on an automobile fault retrieval page, acquiring target automobile fault information, acquiring a plurality of fault cause slot position information corresponding to a target automobile fault phenomenon based on a knowledge graph, performing word frequency statistics on the plurality of fault cause slot position information to obtain a plurality of word frequency statistics results corresponding to the target automobile fault phenomenon, and further performing path analysis on the plurality of fault cause slot position information through a hidden Markov model to obtain a root cause analysis result corresponding to the target automobile fault phenomenon; the fault data corresponding to the target automobile fault phenomenon are counted, and the counted result is compared with the threshold value information of the automobile part parameters corresponding to the automobile fault phenomenon, so that the root cause analysis result corresponding to the target automobile fault phenomenon can be subjected to auxiliary analysis through the comparison result, the problem that the fault root cause cannot be subjected to deep analysis according to the actual fault condition is solved, the accuracy of the fault root cause analysis result is improved, and the automobile fault can be effectively processed.
It should be noted that the steps illustrated in the above-described flow or flow diagrams of the figures may be performed in a computer system, such as a set of computer-executable instructions, and that, although a logical order is illustrated in the flow diagrams, in some cases, the steps illustrated or described may be performed in an order other than that illustrated herein.
The embodiment also provides an apparatus for analyzing the root cause of the automobile fault, which is used for implementing the foregoing embodiments and preferred embodiments, and is not described in detail. The terms "module," "unit," "sub-unit," and the like as used below may refer to a combination of software and/or hardware that performs a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementations in hardware, or a combination of software and hardware, are also possible and contemplated.
Fig. 9 is a block diagram showing the configuration of an automobile fault root cause analysis device according to the present embodiment, and as shown in fig. 9, the device includes: a processing module 10, a construction module 20 and an analysis module 30;
the processing module 10 processes related documents of the automobile fault information through a machine learning algorithm to obtain a triplet set corresponding to the related documents;
The construction module 20 constructs a knowledge graph corresponding to the automobile fault information based on the triplet set corresponding to the related document;
the analysis module 30 generates a plurality of fault reason slot information corresponding to the fault phenomenon of the target automobile based on the knowledge graph, and performs knowledge calculation on the plurality of fault reason slot information to obtain a root cause analysis result corresponding to the fault phenomenon of the target automobile.
According to the device provided by the embodiment, the relevant documents of the automobile fault information are processed through the machine learning algorithm to obtain the triplet set corresponding to the relevant documents, the knowledge graph corresponding to the automobile fault information is constructed based on the triplet set corresponding to the relevant documents, further, based on the knowledge graph, a plurality of fault reason slot information corresponding to the target automobile fault phenomenon is generated, knowledge calculation is conducted on the plurality of fault reason slot information to obtain the root cause analysis result corresponding to the target automobile fault phenomenon, the problem that deep analysis cannot be conducted on the fault root cause according to the actual fault condition is solved, the accuracy of the fault root cause analysis result is improved, and therefore the automobile fault can be effectively processed.
In some embodiments, on the basis of fig. 9, the apparatus further includes an obtaining module, configured to obtain a relevant document of the automobile fault information, where the relevant document includes a fault case document corresponding to the automobile fault information.
In some embodiments, on the basis of fig. 9, the device further includes an extraction module, configured to extract knowledge from the relevant document by using a machine learning algorithm, to obtain a plurality of knowledge units corresponding to the relevant document, where the knowledge units include text-type automobile fault information, data-type automobile fault information, and threshold information of automobile part parameters; and carrying out knowledge fusion on the plurality of knowledge units to obtain a triplet set corresponding to the related document.
In some embodiments, on the basis of fig. 9, the apparatus further includes a generating module, configured to store the triplet set in a graph database based on a preset storage form, and generate a knowledge graph corresponding to the automobile fault information.
In some embodiments, on the basis of fig. 9, the apparatus further includes a search module, configured to obtain, based on the automobile fault search page, target automobile fault information, where the target automobile fault information includes a fault automobile type, a fault component, and status information corresponding to the fault component.
In some embodiments, on the basis of fig. 9, the apparatus further includes a statistics module, configured to perform word frequency statistics on the plurality of fault cause slot information, so as to obtain a plurality of word frequency statistics results corresponding to the fault phenomenon of the target automobile; and carrying out path analysis on the plurality of fault cause slot position information through a hidden Markov model based on the plurality of word frequency statistical results to obtain root cause analysis results corresponding to the fault phenomenon of the target automobile.
In some embodiments, on the basis of fig. 9, the apparatus further includes an auxiliary module, configured to count fault data corresponding to a target automobile fault phenomenon, and compare the counted result with threshold information of automobile part parameters corresponding to the automobile fault phenomenon; and carrying out auxiliary analysis on root cause analysis results corresponding to the fault phenomenon of the target automobile based on the comparison results.
The above-described respective modules may be functional modules or program modules, and may be implemented by software or hardware. For modules implemented in hardware, the various modules described above may be located in the same processor; or the above modules may be located in different processors in any combination.
There is also provided in this embodiment a computer device comprising a memory in which a computer program is stored and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.
Optionally, the computer device may further include a transmission device and an input/output device, where the transmission device is connected to the processor, and the input/output device is connected to the processor.
It should be noted that, specific examples in this embodiment may refer to examples described in the foregoing embodiments and alternative implementations, and are not described in detail in this embodiment.
In addition, in combination with the method for analyzing the root cause of the automobile fault provided in the above embodiment, a storage medium may be provided in this embodiment. The storage medium has a computer program stored thereon; the computer program, when executed by a processor, implements any of the automobile fault root cause analysis methods of the above embodiments.
It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to be limiting. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present application, are within the scope of the present application in light of the embodiments provided herein.
It is evident that the drawings are only examples or embodiments of the present application, from which the present application can also be adapted to other similar situations by a person skilled in the art without the inventive effort. In addition, it should be appreciated that while the development effort might be complex and lengthy, it would nevertheless be a routine undertaking of design, fabrication, or manufacture for those of ordinary skill having the benefit of this disclosure, and thus should not be construed as an admission of insufficient detail.
The term "embodiment" in this application means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive. It will be clear or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the patent. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. A method for analyzing root cause of an automobile fault, the method comprising:
processing related documents of automobile fault information through a machine learning algorithm to obtain a triplet set corresponding to the related documents;
Constructing a knowledge graph corresponding to the automobile fault information based on the triplet set corresponding to the related document;
and generating a plurality of fault reason slot position information corresponding to the fault phenomenon of the target automobile based on the knowledge graph, and performing knowledge calculation on the fault reason slot position information to obtain a root cause analysis result corresponding to the fault phenomenon of the target automobile.
2. The method for analyzing the root cause of the automobile fault according to claim 1, wherein before the related document of the automobile fault information is processed by a machine learning algorithm to obtain the triplet set corresponding to the related document, the method further comprises:
and acquiring related documents of the automobile fault information, wherein the related documents comprise fault case documents corresponding to the automobile fault information.
3. The method for analyzing the root cause of the automobile fault according to claim 1, wherein the processing the related document of the automobile fault information by the machine learning algorithm to obtain the triplet set corresponding to the related document comprises:
the knowledge extraction is carried out on the related documents through the machine learning algorithm, so that a plurality of knowledge units corresponding to the related documents are obtained, wherein the knowledge units comprise text type automobile fault information, data type automobile fault information and threshold information of automobile part parameters;
And carrying out knowledge fusion on the plurality of knowledge units to obtain a triplet set corresponding to the related document.
4. The method for analyzing the root cause of an automobile fault according to claim 3, wherein the constructing a knowledge graph corresponding to the automobile fault information based on the triplet set corresponding to the relevant document includes:
and storing the triplet set to a graph database based on a preset storage form, and generating a knowledge graph corresponding to the automobile fault information.
5. The method for analyzing the root cause of a fault in an automobile according to claim 1, wherein before generating the plurality of fault cause slot information corresponding to the fault phenomenon of the target automobile based on the knowledge graph, the method further comprises:
and acquiring the target automobile fault information based on an automobile fault retrieval page, wherein the target automobile fault information comprises a fault automobile type, a fault part and state information corresponding to the fault part.
6. The method for analyzing root cause of failure of an automobile according to claim 1, wherein the performing knowledge calculation on the plurality of failure cause slot information to obtain root cause analysis results corresponding to the failure phenomenon of the target automobile includes:
Performing word frequency statistics on the fault reason slot position information to obtain a plurality of word frequency statistics results corresponding to the fault phenomenon of the target automobile;
and carrying out path analysis on the plurality of fault cause slot position information through a hidden Markov model based on the plurality of word frequency statistical results to obtain root cause analysis results corresponding to the target automobile fault phenomenon.
7. The method for analyzing the root cause of the failure of the automobile according to claim 6, wherein after performing knowledge calculation on the plurality of failure cause slot information to obtain the root cause analysis result corresponding to the failure phenomenon of the target automobile, further comprises:
counting fault data corresponding to the target automobile fault phenomenon, and comparing the counting result with threshold information of automobile part parameters corresponding to the automobile fault phenomenon;
and carrying out auxiliary analysis on root cause analysis results corresponding to the target automobile fault phenomenon based on the comparison results.
8. An automotive fault root cause analysis device, the device comprising:
the processing module is used for processing related documents of the automobile fault information through a machine learning algorithm to obtain a triplet set corresponding to the related documents;
The construction module is used for constructing a knowledge graph corresponding to the automobile fault information based on the triplet set corresponding to the related document;
and the analysis module is used for generating a plurality of fault reason slot position information corresponding to the fault phenomenon of the target automobile based on the knowledge graph, and carrying out knowledge calculation on the fault reason slot position information to obtain a root cause analysis result corresponding to the fault phenomenon of the target automobile.
9. A computer device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to run the computer program to perform the steps of the method for root cause analysis of an automobile fault as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the automobile fault root analysis method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211580383.5A CN116129551A (en) | 2022-12-09 | 2022-12-09 | Automobile fault root cause analysis method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211580383.5A CN116129551A (en) | 2022-12-09 | 2022-12-09 | Automobile fault root cause analysis method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116129551A true CN116129551A (en) | 2023-05-16 |
Family
ID=86299939
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211580383.5A Pending CN116129551A (en) | 2022-12-09 | 2022-12-09 | Automobile fault root cause analysis method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116129551A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113094512A (en) * | 2021-04-08 | 2021-07-09 | 达而观信息科技（上海）有限公司 | Fault analysis system and method in industrial production and manufacturing |
| CN113868427A (en) * | 2020-06-30 | 2021-12-31 | 中国移动通信集团天津有限公司 | Data processing method and device and electronic equipment |
| CN113918726A (en) * | 2021-09-06 | 2022-01-11 | 国网河北省电力有限公司电力科学研究院 | Retrieval method and system for fault knowledge of electric power main transformer equipment |
| WO2022135419A1 (en) * | 2020-12-21 | 2022-06-30 | 广州橙行智动汽车科技有限公司 | Voice interaction method and apparatus |
| CN115034409A (en) * | 2022-05-31 | 2022-09-09 | 中国第一汽车股份有限公司 | Vehicle maintenance scheme determination method, device, equipment and storage medium |
| CN115033679A (en) * | 2022-08-10 | 2022-09-09 | 深圳联友科技有限公司 | Method for searching automobile maintenance data based on knowledge graph |
-
2022
- 2022-12-09 CN CN202211580383.5A patent/CN116129551A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113868427A (en) * | 2020-06-30 | 2021-12-31 | 中国移动通信集团天津有限公司 | Data processing method and device and electronic equipment |
| WO2022135419A1 (en) * | 2020-12-21 | 2022-06-30 | 广州橙行智动汽车科技有限公司 | Voice interaction method and apparatus |
| CN113094512A (en) * | 2021-04-08 | 2021-07-09 | 达而观信息科技（上海）有限公司 | Fault analysis system and method in industrial production and manufacturing |
| CN113918726A (en) * | 2021-09-06 | 2022-01-11 | 国网河北省电力有限公司电力科学研究院 | Retrieval method and system for fault knowledge of electric power main transformer equipment |
| CN115034409A (en) * | 2022-05-31 | 2022-09-09 | 中国第一汽车股份有限公司 | Vehicle maintenance scheme determination method, device, equipment and storage medium |
| CN115033679A (en) * | 2022-08-10 | 2022-09-09 | 深圳联友科技有限公司 | Method for searching automobile maintenance data based on knowledge graph |
Non-Patent Citations (2)
| Title |
|---|
| 李德毅 等: "《人工智能导论》", 30 September 2018, 中国科学技术出版社, pages: 177 - 181 * |
| 韩力群: "《机器智能与智能机器人》", 31 March 2022, 国防工业出版社, pages: 71 - 74 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109033068B (en) | Method and device for reading and understanding based on attention mechanism and electronic equipment | |
| CN112527998A (en) | Reply recommendation method, reply recommendation device and intelligent device | |
| US20220092416A1 (en) | Neural architecture search through a graph search space | |
| CN112100529A (en) | Search content ordering method and device, storage medium and electronic equipment | |
| CN116186200B (en) | Model training method, device, electronic equipment and storage medium | |
| CN112487173A (en) | Man-machine conversation method, device and storage medium | |
| CN112632224B (en) | Case recommendation method and device based on case knowledge graph and electronic equipment | |
| CN103389979A (en) | System, device and method for recommending classification lexicon in input method | |
| US20200364216A1 (en) | Method, apparatus and storage medium for updating model parameter | |
| US12001494B2 (en) | Content processing method and apparatus, computer-readable storage medium and computer device | |
| US20230094730A1 (en) | Model training method and method for human-machine interaction | |
| CN114186076A (en) | Knowledge graph construction method, device, equipment and computer readable storage medium | |
| CN111324705B (en) | System and method for adaptively adjusting associated search terms | |
| CN115221332A (en) | Construction method and system of dangerous chemical accident event map | |
| CN117112916A (en) | Financial information query method, device and storage medium based on Internet of vehicles | |
| CN111651577B (en) | Cross-media data association analysis model training and data association analysis method and system | |
| CN116129551A (en) | Automobile fault root cause analysis method, device, computer equipment and storage medium | |
| CN110569030B (en) | Code recommendation method and device | |
| CN108255808B (en) | Text division method and device, storage medium and electronic equipment | |
| CN115563242A (en) | Automobile information screening method and device, electronic equipment and storage medium | |
| CN115391500A (en) | Dialogue type information retrieval method based on pre-training language model | |
| CN115062126A (en) | Statement analysis method and device, electronic equipment and readable storage medium | |
| CN114756774A (en) | Travel scheme recommendation method, travel scheme recommendation device, model training equipment and storage medium | |
| CN112883735A (en) | Form image structured processing method, device, equipment and storage medium | |
| TWI603320B (en) | Global spoken dialogue system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |