CN108647791B - Multi-source automobile safety information processing method, device and system - Google Patents
Multi-source automobile safety information processing method, device and system Download PDFInfo
- Publication number
- CN108647791B CN108647791B CN201810290379.2A CN201810290379A CN108647791B CN 108647791 B CN108647791 B CN 108647791B CN 201810290379 A CN201810290379 A CN 201810290379A CN 108647791 B CN108647791 B CN 108647791B
- Authority
- CN
- China
- Prior art keywords
- information
- automobile
- vehicle
- fault
- safety
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
Abstract
The invention discloses a multi-source automobile safety information processing method, which comprises the steps of obtaining automobile safety information from multiple sources, including automobile owner complaint information and automobile safety related information, and determining an automobile fault label and a fault severity grade of each item of automobile safety information according to a preset automobile fault expert knowledge base; clustering the complaint information of each vehicle owner according to the complaint information of each vehicle owner and the corresponding label thereof to form a fault case of the vehicle; according to each item of vehicle safety associated information and the corresponding label thereof, the vehicle safety associated information is associated with the vehicle fault case to form a vehicle fault case knowledge map, and the vehicle fault case knowledge map can be used for vehicle safety risk level evaluation. Therefore, the reference information sources for the automobile safety risk assessment are enriched, and the reference value of the reference information for the automobile safety risk assessment is greatly improved.
Description
Technical Field
The invention relates to the field of automobile safety, in particular to a method, a device and a system for processing multi-source automobile safety information.
Background
In recent years, the sales of vehicles in China has been on the rise. In 2017, the automobile sales in China are 2800 more than ten thousand, and the defective automobiles are 2000 more than ten thousand recalled all year round. Therefore, personal and property safety of consumers can be effectively protected through the defective automobile recall. The automobile safety information analysis is a data basis for carrying out automobile product defect judgment, and all clues of recalls influenced by the survey of the quality supervision and management department from 2017 come from the automobile safety information analysis result.
However, the main source for analyzing the automobile safety information is the complaint information of the owner, so that the reference information for analyzing the automobile safety information has a single source and strong subjectivity, and the reference value provided for analyzing the automobile safety information is still to be improved.
Disclosure of Invention
In view of the above, the invention discloses a method, a device and a system for processing multi-source automobile safety information, which solve the problems that in the prior art, reference information for automobile safety information analysis is single in source, strong in subjectivity and low in reference value provided for automobile safety information analysis.
The embodiment of the invention discloses a method for processing multi-source automobile safety information, which comprises the following steps:
acquiring automobile safety information from various sources; the multiple sources of automotive safety information include: the vehicle owner complaint information and the vehicle safety correlation information;
determining a label of each item of automobile safety information according to a preset automobile fault expert knowledge base;
clustering the complaint information of the vehicle owners according to the complaint information of the vehicle owners and labels of the complaint information of the vehicle owners to form a fault case of the vehicle;
and associating the vehicle safety associated information with the automobile fault case according to each item of vehicle safety associated information and the label of the vehicle safety associated information to form an automobile fault case knowledge map.
Optionally, the vehicle safety related information includes:
producer filing information, producer complaint feedback information, automobile technical service bulletin, recall information and network public opinion information.
Optionally, the expert knowledge base of automobile faults includes: the vehicle failure label, the vehicle failure label key words and the vehicle failure mode severity level.
Optionally, the determining the label of each item of automobile safety information according to a preset automobile fault knowledge base includes:
determining a target field in each item of automobile safety information;
performing word segmentation processing on the target field to obtain word segmentation information;
matching the word segmentation information of each automobile safety information with automobile fault label keywords in an automobile fault expert knowledge base;
and if the automobile fault label key words are matched, recommending corresponding automobile fault labels, and determining the severity level of the automobile fault mode according to the recommended automobile fault labels.
Optionally, the method further includes:
if the tag is not matched, judging whether the automobile safety information which is not matched with the tag is effective information;
if the automobile safety information is valid information, forming a new expert knowledge item according to the automobile safety information which is not matched with the label;
and updating the automobile fault expert knowledge base according to the new expert knowledge items.
Optionally, according to the label of each item of vehicle owner complaint information and vehicle owner complaint information, cluster each item of vehicle owner complaint information, include:
acquiring basic information of the vehicle in the complaint information of the vehicle owner; the basic information includes: vehicle brand family and vehicle model;
clustering the complaint information of the vehicle owners according to the brand series of the vehicles;
clustering vehicles of each brand series according to the vehicle models;
and clustering the vehicles of each type according to the labels of the complaint information of the vehicle owners.
Optionally, the method further includes:
matching the automobile fault case with a historical automobile fault case;
if the automobile fault case is matched with a historical automobile fault case, updating the historical case according to the automobile fault case;
and if the fault case is not matched with the historical case, generating a new fault case.
Optionally, the associating the vehicle safety related information with the automobile fault case according to each item of vehicle safety related information and the label of the vehicle safety related information includes:
acquiring vehicle basic information and a label of each item of vehicle safety associated information;
according to the basic vehicle information of each vehicle safety related information, each vehicle safety related information is related to the automobile fault case;
and associating each piece of vehicle safety related information with the automobile fault case according to the label of each piece of vehicle safety related information.
Optionally, the method further includes:
and evaluating the safety risk level of the automobile according to the automobile fault case knowledge graph.
The embodiment of the invention also discloses a device for processing the multi-source automobile safety information, which comprises:
the data acquisition unit is used for acquiring automobile safety information from various sources; the multiple sources of automotive safety information include: the vehicle owner complaint information and the vehicle safety correlation information;
the tag determining unit is used for determining a tag of each item of automobile safety information according to a preset automobile fault expert knowledge base;
the clustering unit is used for clustering the complaint information of the vehicle owners according to the complaint information of the vehicle owners and the labels of the complaint information of the vehicle owners to form a fault case of the vehicle;
and the association unit is used for associating the vehicle safety associated information with the automobile fault case according to each item of vehicle safety associated information and the label of the vehicle safety associated information to form an automobile fault case knowledge map.
The embodiment of the invention also discloses a system for processing the multi-source automobile safety information, which comprises the following steps:
the data asset module is used for receiving automobile safety information uploaded by a user from various sources;
a data acquisition module for obtaining multiple sources of vehicle safety information from the data asset module, the multiple sources of vehicle safety information including: the vehicle owner complaint information and the vehicle safety correlation information;
the data cleaning module is used for cleaning and standardizing the automobile safety information;
the data processing module is used for determining the label of each automobile safety information according to a preset automobile fault expert knowledge base;
and the data analysis module is used for associating the vehicle safety associated information with the automobile fault case according to various vehicle safety associated information and the label of the vehicle safety associated information to form an automobile fault case knowledge map which is used as a basis for evaluating the automobile safety risk level.
The embodiment of the invention discloses a multi-source automobile safety information processing method, which is used for acquiring automobile safety information from multiple sources and comprises the following steps: the vehicle owner complaint information and the vehicle safety associated information, wherein the vehicle safety associated information may include: producer filing information, producer complaint feedback information, automobile technical service bulletin, recall information, network public opinion information and the like; determining a label of each item of automobile safety information according to a preset automobile fault expert knowledge base; the automobile fault expert knowledge base comprises: automobile fault labels, automobile fault label keywords, automobile fault mode severity levels and the like. Clustering the complaint information of the vehicle owners according to the complaint information of the vehicle owners and labels of the complaint information of the vehicle owners to form a fault case of the vehicle; according to various vehicle safety associated problem information and the labels of the vehicle safety associated information, the vehicle safety associated information is associated with the automobile fault cases to form an automobile fault case knowledge map, and the automobile fault case knowledge map can be used for automobile safety risk level evaluation. Therefore, the automobile safety information from various sources is obtained, some objective automobile safety related information is added besides the complaint information of the automobile owner, and the information is arranged into the knowledge map of the automobile fault case, so that the reference information sources for automobile safety risk assessment are enriched, and the reference value of the reference information for automobile safety risk assessment is greatly improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a method for processing multi-source automobile safety information according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a multi-source vehicle safety information processing device according to an embodiment of the present invention;
fig. 3 shows a schematic structural diagram of a processing system for multi-source automobile safety information according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a schematic flow chart of a method for processing multi-source automobile safety information according to an embodiment of the present invention is shown, where in this embodiment, the method includes:
s101: acquiring automobile safety information from various sources; the multiple sources of automotive safety information include: the vehicle owner complaint information and the vehicle safety correlation information;
in the prior art, the determination of the safety risk of the vehicle is generally performed only through the complaint information of the vehicle owner, that is, the source of the safety information of the vehicle only includes the complaint information of the vehicle owner. However, the subjective of the complaint information of the vehicle owner is strong, in order to provide more reliable reference information for determining the risk of the vehicle, some sources of objective vehicle safety information are added in the embodiment, which are collectively referred to as vehicle safety related information in the embodiment, specifically, the vehicle safety related information includes: the system comprises producer record information, producer complaint feedback information, automobile technical service bulletin, recall information and network public opinion information, wherein the recall information comprises domestic recall information and foreign recall information.
Wherein, the vehicle owner complaint information includes: basic information of the vehicle, use conditions, fault phenomena, traffic accident information, personal information of the owner of the vehicle and the like; wherein the vehicle basic information includes: vehicle brand series, model, etc.;
the producer record information comprises: vehicle brand series, model, configuration parameters, sales information, etc.;
the producer complaint feedback information includes: technical analysis report and maintenance scheme of vehicle owner complaint fault;
the technical service announcement of the automobile comprises the following steps: basic information of the vehicle, fault phenomena, fault reasons, whether the fault is a batch fault or not, possible consequences and a maintenance scheme;
domestic car recall information, including: basic information of the vehicle, fault phenomena, fault reasons, possible consequences and maintenance schemes;
foreign car recall information, including: basic information of the vehicle, frequent phenomenon, failure cause, possible consequences and maintenance scheme.
Network public opinion information, including: basic information of the vehicle, fault phenomena and network propagation influence indexes.
It should be noted that the car safety information includes the above-mentioned data information, but is not limited to the data information.
S102: determining a label of each item of automobile safety information according to a preset automobile fault expert knowledge base;
in this embodiment, the expert knowledge base of vehicle failure includes: automobile fault labels, automobile fault label keywords, automobile fault mode severity levels and the like.
Wherein, car trouble label includes: vehicle assembly and failure mode; the automobile assembly represents an integral body formed by a series of products, and a part system for realizing a specific function is generally called as follows: internal combustion engines, starters, oil pumps, etc. The failure mode represents the failure type of the automobile; the vehicle failure label that is a combination of the vehicle assembly and the failure mode may include, for example: engine water leakage, rear axle breakage, engine oil leakage, etc., and in addition, words indicating degrees such as engine oil leakage seriously, engine water leakage slightly, etc., may be included, wherein "serious" and "slight" are words indicating degrees.
The automobile fault label key words represent key words contained in automobile fault labels, comprise synonyms or similar words capable of representing relevant automobile assemblies, and represent synonyms or similar words capable of representing relevant faults. For example: assume that the car failure label is: engine oil leakage, wherein keywords regarding the automobile assembly engine include: internal combustion engines, power machines, engines, gas engines, and the like.
The automobile fault labels and the automobile fault mode severity levels have a one-to-one correspondence relationship, namely each automobile fault label corresponds to one automobile fault mode severity level.
In this embodiment, it is necessary to match each item of acquired automobile safety information with information in the expert knowledge base, and then determine a tag of each item of automobile safety information, specifically, S102 includes:
determining a target field in each item of automobile safety information;
performing word segmentation processing on the target field to obtain word segmentation information;
matching the word segmentation information of each automobile safety information with automobile fault label keywords in an automobile fault expert knowledge base;
and if the automobile fault label key words are matched, recommending corresponding automobile fault labels, and determining the severity level of the automobile fault mode according to the recommended automobile fault labels.
Wherein the target field represents a field for performing text analysis.
In this embodiment, the automobile safety information may include: the car owner complains information, producer records information, producer's complaint feedback information, car technical service bulletin, domestic recall information, foreign recall information and network public opinion information, to the car safety information of different information sources, and is specific, and the process of matching includes:
for vehicle owner complaint information:
the target field of the vehicle owner complaint information can be fault phenomenon description information in the vehicle owner complaint information, for example, the fault phenomenon description information in the vehicle owner complaint information is segmented and automatically matched with a vehicle fault label keyword in an expert knowledge base; and screening the fault label with the highest matching degree, and determining the severity level of the automobile fault mode in an expert knowledge base according to the determined automobile fault label.
For example, the following steps are carried out: the fault phenomenon description information in the vehicle owner complaint information comprises: the engine of a brand B model car is flooded when driving in the rain. After segmenting the vehicle owner complaint information, the obtained segmentation information may include: the automobile brand is A, the automobile model is B, the automobile is rainy, runs, an engine and water enters. Matching the word segmentation information with each automobile fault label keyword in the expert knowledge base, wherein the matched automobile fault label keywords are engine and water inflow, further the automobile fault label recommended for the automobile owner complaint information is engine water inflow, the automobile fault mode severity level preset for the engine water inflow in the expert knowledge base is one level, and therefore the fault distributed to the automobile owner complaint information is one level.
For the car technical service announcement:
the target field in the automobile technical service bulletin can be fault content, the fault content in the automobile technical service bulletin is subjected to word segmentation, automatic matching is carried out on the fault content and automobile fault label key words in a fault expert knowledge base, an accurate automobile fault label is determined, and the severity level of an automobile fault mode is determined in the expert fault knowledge base.
For recall information:
the target field in the recall information can be a fault phenomenon description field, the fault phenomenon field in the recall information (domestic recall information and/or foreign recall information) is segmented, automatic matching is carried out on the fault phenomenon field and automobile fault label key words in a fault expert knowledge base, an accurate automobile fault label is determined, and the severity level of an automobile fault mode is determined in the expert fault knowledge base.
Aiming at network public opinion information:
the target field in the internet public opinion information may include: and the related fault field or title field is used for segmenting a target field in the network public opinion information, automatically matching with the automobile fault label key word in the fault expert knowledge base, determining an accurate automobile fault label and determining the severity grade of the automobile fault mode in the expert fault knowledge base.
In this embodiment, the vehicle failure expert knowledge base is a database preset by a technician, and the vehicle failure expert knowledge base can be regularly updated, or when matching with the vehicle safety information through the expert knowledge base, if not matching to a suitable tag, the vehicle failure expert knowledge base can be updated according to the vehicle safety information, and the method specifically further includes:
if the tag is not matched, judging whether the automobile safety information which is not matched with the tag is effective information;
if the automobile safety information is valid information, forming a new expert knowledge item according to the automobile safety information which is not matched with the label;
and updating the automobile fault expert knowledge base according to the new expert knowledge items.
In this embodiment, the judgment of whether the vehicle owner complaint information is valid information may be performed manually by a technician or automatically by a related program. For example: if the complaint information of the vehicle owner comprises the related description information of the vehicle assembly and the description information of the vehicle fault and contains the basic information of the vehicle, the complaint information of the vehicle owner indicates that the vehicle fault information is effective information, an automobile expert knowledge item can be formed according to the field of the vehicle assembly, the description information of the vehicle fault and the basic information of the vehicle in the safety information of the vehicle, and an automobile fault expert knowledge base is updated according to the formed automobile expert knowledge item. In addition, the technician determines the severity level of the vehicle failure mode based on the vehicle expertise.
S103: clustering the complaint information of the vehicle owners according to the complaint information of the vehicle owners and labels of the complaint information of the vehicle owners to form a fault case of the vehicle;
in this embodiment, each item of vehicle owner complaint information is clustered, and clustering may be performed according to different clustering manners, for example, vehicles of the same brand series are divided into one type, or vehicles of the same model in the same brand series are divided into one type, or vehicles of the same model are divided into one type, or vehicle owner complaint information of the same brand series, the same model, and the same fault may also be divided into one type, specifically, S103 includes:
acquiring basic information of the vehicle in the complaint information of the vehicle owner; the basic information includes: vehicle brand family and vehicle model;
clustering the complaint information of the vehicle owners according to the brand series of the vehicles;
clustering vehicles of each brand series according to the vehicle models;
and clustering the vehicles of each type according to the labels of the complaint information of the vehicle owners.
In this embodiment, the label of the vehicle owner complaint information includes: the vehicle assembly + fault mode, therefore, the vehicle owner complaint information is clustered according to the label of the vehicle owner complaint information, and the same fault types in the vehicles of the same model can be classified into one type.
In this embodiment, any one or more clustering algorithms may be used to cluster the vehicle owner complaint information, which is not limited in this embodiment, and for example, a K-means algorithm, a fuzzy clustering algorithm, a semi-supervised clustering algorithm, and the like may be used.
In this embodiment, for a generated automobile fault case, if the historical automobile fault case includes the generated automobile fault case, the generated automobile fault case may be incorporated into the historical case, and if the historical automobile fault case does not include the generated automobile fault case, the generated automobile fault case is used as a new automobile fault case, which specifically includes:
matching the automobile fault case with a historical automobile fault case;
if the automobile fault case is matched with a historical automobile fault case, updating the historical case according to the automobile fault case;
and if the fault case is not matched with the historical case, generating a new fault case.
S104: according to the vehicle safety related information and the vehicle fault label of the vehicle safety related information, associating the vehicle safety related information with the vehicle fault case to form a vehicle fault case knowledge map;
in this embodiment, the automobile fault case and the vehicle safety related information may be linked by common information, for example, the vehicle safety related information may be related to the automobile fault case by the basic information of the vehicle and/or the fault tag of the vehicle, and specifically, S104 includes:
acquiring vehicle basic information and a label of each item of vehicle safety associated information;
the vehicle basic information according to each vehicle safety related information is related to the automobile fault case;
and associating the label according to each piece of vehicle safety associated information with the automobile fault case.
In this embodiment, the vehicle safety-related information includes: the system comprises a vehicle fault case, a manufacturer record information, a manufacturer complaint feedback information, a vehicle technical service announcement, a recall information, an internet public opinion information and the like, wherein the information can be associated with the vehicle fault case according to vehicle basic information and a matched vehicle fault label in the information.
In this embodiment, the knowledge graph of the automobile fault case includes automobile safety information from multiple sources, which provides a basis for determining whether the vehicle has a defect and evaluating a safety risk, and a technician can determine whether the vehicle has a safety problem according to the relevant information in the knowledge graph, thereby determining whether the vehicle has a defect.
Referring to fig. 2, a schematic structural diagram of a processing apparatus for multi-source vehicle safety information according to an embodiment of the present invention is shown, in this embodiment, the apparatus includes:
a data obtaining unit 201, configured to obtain automobile safety information from multiple sources; the multiple sources of automotive safety information include: the vehicle owner complaint information and the vehicle safety correlation information;
the tag determination unit 202 is configured to determine a tag of each item of automobile safety information according to a preset automobile failure expert knowledge base;
the clustering unit 203 is used for clustering the complaint information of the vehicle owners according to the complaint information of the vehicle owners and the labels of the complaint information of the vehicle owners to form a fault case of the vehicle;
the associating unit 204 is configured to associate the vehicle safety related information with the vehicle failure case according to each item of vehicle safety related information and the label of the vehicle safety related information, so as to form a vehicle failure case knowledge graph.
Optionally, the vehicle safety related information includes:
producer filing information, producer complaint feedback information, automobile technical service bulletin, recall information and network public opinion information.
Optionally, the expert knowledge base of automobile faults includes: automobile fault labels, automobile fault label keywords, automobile fault mode severity levels and the like. Optionally, the tag determining unit includes:
the target field determining subunit is used for determining a target field in each item of automobile safety information;
the word segmentation subunit is used for carrying out word segmentation processing on the target field to obtain word segmentation information;
the first matching subunit is used for matching the word segmentation information of each item of automobile safety information with automobile fault label keywords in an automobile fault expert knowledge base;
and the fault severity level determining subunit is used for recommending a corresponding automobile fault label if the automobile fault label key words are matched, and determining the severity level of the automobile fault mode according to the recommended automobile fault label.
Optionally, the method further includes:
the judging subunit is used for judging whether the automobile safety information which is not matched with the label is effective information or not if the label is not matched with the label;
the new expert knowledge item forming subunit is used for forming a new expert knowledge item according to the automobile safety information which is not matched with the label if the automobile safety information is effective information;
and the first updating subunit is used for updating the automobile fault expert knowledge base according to the new expert knowledge items.
Optionally, the clustering unit includes:
the first obtaining subunit is used for obtaining basic information of the vehicle in the complaint information of the vehicle owner; the basic information includes: vehicle brand family and vehicle model;
the first clustering subunit is used for clustering the complaint information of the vehicle owner according to the vehicle brand series;
the second clustering subunit is used for clustering vehicles of each brand series according to the vehicle models;
and the third clustering subunit is used for clustering vehicles of each type according to the labels of the complaint information of the vehicle owners.
Optionally, the method further includes:
the second matching subunit is used for matching the automobile fault case with the historical fault case;
the second updating subunit is used for updating the historical case according to the automobile fault case if the automobile fault case is matched with the historical automobile fault case;
and the generating subunit is used for generating a new automobile fault case if the automobile fault case is not matched with the historical case.
Optionally, the associating unit includes:
the second acquisition subunit is used for acquiring the vehicle basic information of each item of vehicle safety related information;
the first association subunit is used for associating each item of vehicle safety association information with the automobile fault case according to the vehicle basic information of each item of vehicle safety association information;
and the second association subunit is used for associating each item of vehicle safety associated information with the automobile fault case according to the label of each item of vehicle safety associated information.
Optionally, the method further includes:
and the analysis unit is used for evaluating the safety risk of the automobile according to the automobile fault case knowledge graph.
Through the device of the embodiment, the automobile safety information from various sources is obtained, some objective automobile safety related information is added besides the complaint information of the automobile owner, and the information is arranged into the automobile fault case knowledge map, so that the sources of the reference information for analyzing the automobile safety information are increased, and the reference value of the reference information for analyzing the automobile safety information is improved.
Referring to fig. 3, a schematic structural diagram of a system for processing multi-source vehicle safety information according to an embodiment of the present invention is shown, in this embodiment, the system includes:
the data asset module 301 is used for receiving automobile safety information uploaded by a user from various sources;
a data collection module 302 configured to obtain multiple sources of vehicle safety information from the data asset module, where the multiple sources of vehicle safety information include: the vehicle owner complaint information and the vehicle safety correlation information;
the data cleaning module 303 is used for cleaning the automobile safety information;
the data processing module 304 is used for determining a label of each item of automobile safety information according to a preset automobile fault expert knowledge base;
the data analysis module 305 is configured to associate the vehicle safety related information with the vehicle failure case according to each item of vehicle safety related information and the label of the vehicle safety related information, so as to form a vehicle failure case knowledge graph.
The data asset module is a system-oriented module, and a user can upload related data information through the module or automatically acquire the related data information through the module.
The HDFS distributed file system of Hadoop is used for storing the automobile manufacturer record information data in the data acquisition module, so that the expansibility and compatibility are improved; and importing the vehicle sales data stored by the HDFS into an Elasticissearch, and performing parallel computation on the large-scale data set by using MapReduce of Hadoop to improve the dynamic computation performance of the vehicle brand model sales data.
And the data cleaning module is used for processing the data ETL and finding recognizable errors in the data, including checking data consistency, processing invalid values and missing values. For example, whether the vehicle identification code in the vehicle owner complaint information is correct or not, whether the VIN of the sales vehicle in the producer record information is correct or repeated or not, and whether the vehicle model of the vehicle owner complaint information is recorded or not are checked;
and the data processing module is used for automatically segmenting the fault phenomenon description content in the multi-source information such as vehicle owner complaints and the like, automatically matching with the automobile fault label key words in the fault expert knowledge base, and intelligently recommending the automobile fault label with the highest matching degree and the severity grade thereof.
Through the system of the embodiment, the automobile safety information from various sources is obtained, some objective automobile safety related information is added besides the complaint information of the automobile owner, and the information is arranged into the automobile fault case knowledge map, so that the sources of the reference information for analyzing the automobile safety information are increased, and the reference value of the reference information for analyzing the automobile safety information is improved.
It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A multi-source automobile safety information processing method is characterized by comprising the following steps:
acquiring automobile safety information from various sources; the multiple sources of automotive safety information include: the vehicle owner complaint information and the vehicle safety correlation information;
determining a label of each item of automobile safety information according to a preset automobile fault expert knowledge base; wherein, according to the predetermined automobile fault knowledge base, the label of each item of automobile safety information is determined, including: determining a target field in each item of automobile safety information; performing word segmentation processing on the target field to obtain word segmentation information; matching the word segmentation information of each automobile safety information with automobile fault label keywords in an automobile fault expert knowledge base; if the automobile fault label key words are matched, recommending corresponding automobile fault labels, and determining the severity level of the automobile fault mode according to the recommended automobile fault labels; the automobile fault label key words represent key words contained in the automobile fault labels, and the automobile fault labels comprise: vehicle assembly and failure mode; the keywords contained in the automobile fault label represent synonyms or similar synonyms of the automobile assembly and represent synonyms or similar synonyms of the fault mode; the automobile assembly represents an integral formed by a series of products, a part system general name with a specific function is realized, the fault mode represents the fault type of an automobile, and the automobile fault label and the severity level of the automobile fault mode have a one-to-one correspondence relationship;
clustering the complaint information of the vehicle owners according to the complaint information of the vehicle owners and labels of the complaint information of the vehicle owners to form a fault case of the vehicle;
and associating the vehicle safety associated information with the automobile fault case according to each item of vehicle safety associated information and the label of the vehicle safety associated information to form an automobile fault case knowledge map.
2. The method of claim 1, wherein the vehicle safety association information comprises:
producer filing information, producer complaint feedback information, automobile technical service bulletin, recall information and network public opinion information.
3. The method of claim 1, wherein the vehicle fault expert knowledge base comprises: the vehicle failure label, the vehicle failure label key words and the vehicle failure mode severity level.
4. The method of claim 1, further comprising:
if the tag is not matched, judging whether the automobile safety information which is not matched with the tag is effective information;
if the automobile safety information is valid information, forming a new expert knowledge item according to the automobile safety information which is not matched with the label;
and updating the automobile fault expert knowledge base according to the new expert knowledge items.
5. The method of claim 1, wherein clustering the vehicle owner complaint information according to the vehicle owner complaint information and the label of the vehicle owner complaint information comprises:
acquiring basic information of the vehicle in the complaint information of the vehicle owner; the basic information includes: vehicle brand family and vehicle model;
clustering the complaint information of the vehicle owners according to the brand series of the vehicles;
clustering vehicles of each brand series according to the vehicle models;
and clustering the vehicles of each type according to the labels of the complaint information of the vehicle owners.
6. The method of claim 1, further comprising:
matching the automobile fault case with a historical automobile fault case;
if the automobile fault case is matched with a historical automobile fault case, updating the historical case according to the automobile fault case;
and if the fault case is not matched with the historical case, generating a new fault case.
7. The method of claim 1, wherein associating the vehicle safety-related information with the vehicle failure case according to the vehicle safety-related information and the label of the vehicle safety-related information comprises:
acquiring vehicle basic information and a label of each item of vehicle safety associated information;
according to the basic vehicle information of each vehicle safety related information, each vehicle safety related information is related to the automobile fault case;
and associating each piece of vehicle safety related information with the automobile fault case according to the label of each piece of vehicle safety related information.
8. The method of claim 1, further comprising:
and evaluating the safety risk level of the automobile according to the automobile fault case knowledge graph.
9. A multi-source automobile safety information processing device is characterized by comprising:
the data acquisition unit is used for acquiring automobile safety information from various sources; the multiple sources of automotive safety information include: the vehicle owner complaint information and the vehicle safety correlation information;
the tag determining unit is used for determining a tag of each item of automobile safety information according to a preset automobile fault expert knowledge base; the tag determination unit includes: the target field determining subunit is used for determining a target field in each item of automobile safety information; the word segmentation subunit is used for carrying out word segmentation processing on the target field to obtain word segmentation information; the first matching subunit is used for matching the word segmentation information of each item of automobile safety information with automobile fault label keywords in an automobile fault expert knowledge base; the fault severity level determining subunit is used for recommending a corresponding automobile fault label if the automobile fault label key word is matched, and determining the severity level of an automobile fault mode according to the recommended automobile fault label; the automobile fault label key words represent key words contained in the automobile fault labels, and the automobile fault labels comprise: vehicle assembly and failure mode; the keywords contained in the automobile fault label represent synonyms or similar synonyms of the automobile assembly and represent synonyms or similar synonyms of the fault mode; the automobile assembly represents an integral formed by a series of products, a part system general name with a specific function is realized, the fault mode represents the fault type of an automobile, and the automobile fault label and the severity level of the automobile fault mode have a one-to-one correspondence relationship;
the clustering unit is used for clustering the complaint information of the vehicle owners according to the complaint information of the vehicle owners and the labels of the complaint information of the vehicle owners to form a fault case of the vehicle;
and the association unit is used for associating the vehicle safety associated information with the automobile fault case according to each item of vehicle safety associated information and the label of the vehicle safety associated information to form an automobile fault case knowledge map.
10. A system for processing multi-source automotive safety information, comprising:
the data asset module is used for receiving automobile safety information uploaded by a user from various sources;
a data acquisition module for obtaining multiple sources of vehicle safety information from the data asset module, the multiple sources of vehicle safety information including: the vehicle owner complaint information and the vehicle safety correlation information;
the data cleaning module is used for cleaning and standardizing the automobile safety information;
the data processing module is used for determining the label of each automobile safety information according to a preset automobile fault expert knowledge base; the data processing module is specifically used for determining a target field in each item of automobile safety information; performing word segmentation processing on the target field to obtain word segmentation information; matching the word segmentation information of each automobile safety information with automobile fault label keywords in an automobile fault expert knowledge base; if the automobile fault label key words are matched, recommending corresponding automobile fault labels, and determining the severity level of the automobile fault mode according to the recommended automobile fault labels; the automobile fault label key words represent key words contained in the automobile fault labels, and the automobile fault labels comprise: vehicle assembly and failure mode; the keywords contained in the automobile fault label represent synonyms or similar synonyms of the automobile assembly and represent synonyms or similar synonyms of the fault mode; the automobile assembly represents an integral formed by a series of products, a part system general name with a specific function is realized, the fault mode represents the fault type of an automobile, and the automobile fault label and the severity level of the automobile fault mode have a one-to-one correspondence relationship;
and the data analysis module is used for associating the vehicle safety associated information with the automobile fault case according to various vehicle safety associated information and the label of the vehicle safety associated information to form an automobile fault case knowledge map which is used as a basis for evaluating the automobile safety risk level.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810290379.2A CN108647791B (en) | 2018-03-30 | 2018-03-30 | Multi-source automobile safety information processing method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810290379.2A CN108647791B (en) | 2018-03-30 | 2018-03-30 | Multi-source automobile safety information processing method, device and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108647791A CN108647791A (en) | 2018-10-12 |
| CN108647791B true CN108647791B (en) | 2020-12-29 |
Family
ID=63745570
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810290379.2A Active CN108647791B (en) | 2018-03-30 | 2018-03-30 | Multi-source automobile safety information processing method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108647791B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111159500A (en) * | 2018-11-07 | 2020-05-15 | 上海博泰悦臻网络技术服务有限公司 | Vehicle, vehicle networking knowledge map platform, vehicle networking knowledge question and answer method and system |
| CN109460010B (en) * | 2018-12-18 | 2020-11-17 | 彩虹无线（北京）新技术有限公司 | Vehicle fault detection method and device based on knowledge graph and storage medium |
| CN111435366A (en) * | 2019-01-14 | 2020-07-21 | 阿里巴巴集团控股有限公司 | Equipment fault diagnosis method and device and electronic equipment |
| CN110008288B (en) * | 2019-02-19 | 2021-06-29 | 武汉烽火技术服务有限公司 | Construction method and application of knowledge map library for network fault analysis |
| CN110362660B (en) * | 2019-07-23 | 2023-06-09 | 重庆邮电大学 | Electronic product quality automatic detection method based on knowledge graph |
| CN111127071A (en) * | 2019-11-11 | 2020-05-08 | 深圳市元征科技股份有限公司 | Vehicle information management method, device, server and storage medium |
| CN111209472B (en) * | 2019-12-24 | 2023-08-18 | 中国铁道科学研究院集团有限公司电子计算技术研究所 | Railway accident fault association and accident fault cause analysis method and system |
| CN111414477B (en) * | 2020-03-11 | 2024-02-13 | 科大讯飞股份有限公司 | Automatic vehicle fault diagnosis method, device and equipment |
| CN113326349A (en) * | 2021-05-28 | 2021-08-31 | 中国标准化研究院 | Automobile product defect identification method and device based on case reasoning |
| CN116932921B (en) * | 2023-09-18 | 2023-12-12 | 湘江实验室 | Personalized recommendation method and related equipment for automobiles |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107153914A (en) * | 2017-04-18 | 2017-09-12 | 交通运输部公路科学研究所 | A kind of evaluation system and method for automobilism risk |
| CN107742162A (en) * | 2017-10-24 | 2018-02-27 | 国网江苏省电力公司南京供电公司 | A kind of multidimensional characteristic association analysis method based on auxiliary tone monitoring information |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4284800B2 (en) * | 1999-12-20 | 2009-06-24 | Ｊｆｅスチール株式会社 | Rolling method setting method |
| CN104133818A (en) * | 2013-05-04 | 2014-11-05 | 白银博德信通科技有限公司 | Automobile historical data analysis method and automobile historical data analysis system based on Internet of vehicles |
| CN103473409B (en) * | 2013-08-25 | 2016-06-01 | 浙江大学 | The FPGA automatic fault diagnosis method in a kind of knowledge based storehouse |
| TW201527756A (en) * | 2014-01-10 | 2015-07-16 | Nat Univ Tsing Hua | Method, computer program product, system for providing food safety map |
| EP2940672B1 (en) * | 2014-04-29 | 2018-03-07 | Fujitsu Limited | Vehicular safety system |
| CN105712140A (en) * | 2014-12-05 | 2016-06-29 | 华夏视清数字技术(北京)有限公司 | Monitoring and early-warning device and method |
| KR20170010930A (en) * | 2015-07-20 | 2017-02-02 | 대원항업 주식회사 | Smart safety helper service method by cctv |
| CN106651714A (en) * | 2016-09-09 | 2017-05-10 | 浙江大学 | Intelligent factory security situation and emergency command information visualization system |
| CN107490485A (en) * | 2016-11-15 | 2017-12-19 | 宝沃汽车（中国）有限公司 | Vehicle health degree detection method, device and vehicle |
| CN106933994B (en) * | 2017-02-27 | 2020-07-31 | 广东省中医院 | Traditional Chinese medicine knowledge graph-based core disease and syndrome relation construction method |
| CN107103363B (en) * | 2017-03-13 | 2018-06-01 | 北京航空航天大学 | A kind of construction method of the software fault expert system based on LDA |
| CN107562034A (en) * | 2017-07-14 | 2018-01-09 | 宝沃汽车（中国）有限公司 | Fault handling method and processing system on line |
| CN107644269B (en) * | 2017-09-11 | 2020-05-22 | 国网江西省电力公司南昌供电分公司 | Electric power public opinion prediction method and device supporting risk assessment |
-
2018
- 2018-03-30 CN CN201810290379.2A patent/CN108647791B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107153914A (en) * | 2017-04-18 | 2017-09-12 | 交通运输部公路科学研究所 | A kind of evaluation system and method for automobilism risk |
| CN107742162A (en) * | 2017-10-24 | 2018-02-27 | 国网江苏省电力公司南京供电公司 | A kind of multidimensional characteristic association analysis method based on auxiliary tone monitoring information |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108647791A (en) | 2018-10-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108647791B (en) | Multi-source automobile safety information processing method, device and system | |
| CN107085768B (en) | Method for evaluating automobile use reliability | |
| US11443567B2 (en) | Methods and systems for providing a vehicle repair tip | |
| US8930305B2 (en) | Adaptive information processing systems, methods, and media for updating product documentation and knowledge base | |
| CN111414477A (en) | Vehicle fault automatic diagnosis method, device and equipment | |
| US11521182B2 (en) | Methods and systems for clustering of repair orders based on inferences gathered from repair orders | |
| US10504071B2 (en) | Methods and systems for clustering of repair orders based on multiple repair indicators | |
| US20110225096A1 (en) | Method And System For Providing Diagnostic Feedback Based On Diagnostic Data | |
| CN108648011B (en) | Method and system for generating and identifying car insurance buying intention of customer by using model | |
| WO2015171666A1 (en) | Methods and systems for providing an auto-generated repair-hint to a vehicle repair tool | |
| CN112925287B (en) | Big data intelligent system for accurately diagnosing automobile fault | |
| WO2015020831A2 (en) | Methods and systems for generating baselines regarding vehicle service request data | |
| CN107924494B (en) | Method and system for clustering repair orders based on alternative repair indicators | |
| CN116720852B (en) | New energy automobile maintenance data analysis management system based on artificial intelligence | |
| US11550806B2 (en) | Analyzing vehicles based on common circuit elements | |
| CN113505932A (en) | Power battery capacity algorithm based on big data technology evaluation | |
| CN110119891B (en) | Traffic safety influence factor identification method suitable for big data | |
| US20180357614A1 (en) | System And Method For Detecting Spikes In Automotive Repairs | |
| CN112634066A (en) | Method and device for analyzing sales vehicle type through vehicle identification number | |
| KR102629504B1 (en) | System for vehicle maintenance service intermediation | |
| CN115759358A (en) | Resource reproducibility probability evaluation method and system based on automobile disassembled part | |
| US20180032942A1 (en) | Methods and Systems for Tracking Labor Efficiency |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |