CN108170708A - A kind of vehicle entity recognition method, electronic equipment, storage medium, system - Google Patents
A kind of vehicle entity recognition method, electronic equipment, storage medium, system Download PDFInfo
- Publication number
- CN108170708A CN108170708A CN201711185953.XA CN201711185953A CN108170708A CN 108170708 A CN108170708 A CN 108170708A CN 201711185953 A CN201711185953 A CN 201711185953A CN 108170708 A CN108170708 A CN 108170708A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- role
- entity
- sequence
- vehicle entity
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2452—Query translation
- G06F16/24522—Translation of natural language queries to structured queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/232—Orthographic correction, e.g. spell checking or vowelisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Character Discrimination (AREA)
- Machine Translation (AREA)
Abstract
A kind of vehicle entity recognition method of the present invention, including step generation role's set, role extracts, vehicle Entity recognition, update role's set, is gathered using the vehicle role creation vehicle role of draw standard vehicle library and vehicle corpus, vehicle role's extraction is carried out to original vehicle text according to vehicle role set, it is vehicle role's sequence by original vehicle role mapping, compares the vehicle entity character string of vehicle role's sequence and the vehicle entity in Standard of vehicle library, obtains the highest vehicle entity of similarity；The present invention relates to electronic equipment and readable storage medium storing program for executing, for performing a kind of vehicle entity recognition method；The invention further relates to a kind of vehicle entity recognition systems；The present invention is realized carries out accurate vehicle Entity recognition to original vehicle text input by user, and original vehicle update of role to vehicle role is gathered, greatly reduces the workload manually mapped, without manually formulating a large amount of rules, favorable expandability, accuracy rate is high, good compatibility.
Description
Technical field
The present invention relates to vehicle entity recognition techniques field more particularly to a kind of vehicle entity recognition method, electronic equipment,
Storage medium, system.
Background technology
In information of vehicles search, user inputs text message according to personal habits, and text input form is varied, such as
This kind of standard vehicle entity of " BMW ", " Audi " also includes input such as " BMW how much ", " Audi's A615 moneys " this kind of search and draws
It holds up the text that can not be handled or input includes the information of wrong word, such as " embracing horse ", " Australia's enlightening "；Under this application scenarios, need
Vehicle entity can be recognized accurately；But since vehicle entity does not have apparent boundary vocabulary, tradition name Entity recognition is led to
The mode of boundary word is over-scanned to trigger, such as name has surname as boundary, place name has the words such as institute, company, county, village work
For boundary, therefore traditional entity recognition method is difficult that vehicle entity is effectively identified；Text input by user both included
Chinese comes larger interference, existing method comprising english information and number, such as price, configuration of automobiles to vehicle entity extraction belt again
Compatibility it is poor.
Invention content
For overcome the deficiencies in the prior art, one of the objects of the present invention is to provide a kind of vehicle entity recognition method,
Gathered by extracting a small amount of vehicle role creation vehicle role, role is carried out to original vehicle text according to vehicle role set
It extracts, vehicle Entity recognition is carried out, and original vehicle update of role to vehicle role is gathered to the role of extraction, is greatly subtracted
The workload of artificial mapping is lacked, without manually formulating a large amount of rules, favorable expandability, accuracy rate is high, good compatibility.
The present invention provides a kind of vehicle entity recognition method, includes the following steps：
Role extracts, and carries out vehicle role's extraction to original vehicle text, several original vehicle roles is obtained, by several institutes
Original vehicle role mapping is stated as vehicle role's sequence；
Vehicle Entity recognition obtains the vehicle entity character string of the vehicle role sequence, the vehicle entity word
Symbol string and the vehicle entity in Standard of vehicle library, obtain the highest vehicle entity of similarity.
Further, step generation role set and step update role's set are further included, the step generates role set
It is combined into the vehicle role creation vehicle role set for extracting the Standard of vehicle library and vehicle corpus；The step more new role
Collection, which is combined into, gathers the original vehicle role added to the vehicle role.
Further, step generation role's set includes：Extract the Standard of vehicle library and the vehicle corpus
Vehicle entity role, vehicle component role, the role above of vehicle entity, vehicle entity hereafter role, according to institute
State vehicle entity role, vehicle component role, the role above of vehicle entity, vehicle entity hereafter role creation described in
Vehicle role gathers.
Further, the step role extracts and includes：Word segmentation processing is carried out to the original vehicle text, according to described
Vehicle role set word segmentation processing result is carried out vehicle entity role, vehicle component role, vehicle entity angle above
Role's extraction result is mapped as the vehicle role sequence by the hereafter role extraction of color, vehicle entity.
Further, the step vehicle Entity recognition includes：Judge whether the vehicle role sequence is real comprising vehicle
Body role is the vehicle entity role for extracting the vehicle role sequence, and by the vehicle entity of the vehicle role sequence
Role mapping is vehicle entity；Otherwise the vehicle role sequence with vehicle dictionary tree is matched, obtains the vehicle angle
The vehicle entity character string maps are vehicle entity text by the vehicle entity character string of color-sequential row, and the vehicle is real
Body text and the vehicle entity in the Standard of vehicle library, obtain the highest vehicle entity of similarity.
A kind of electronic equipment, including：Processor；
Memory；And program, wherein described program is stored in the memory, and is configured to by processor
It performs, described program includes performing a kind of vehicle entity recognition method.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
A kind of above-mentioned vehicle entity recognition method of row.
A kind of vehicle entity recognition system, including vehicle role abstraction module, vehicle Entity recognition module, the vehicle angle
Color abstraction module carries out vehicle role's extraction to original vehicle text, obtains several original vehicle roles, will be several described original
Vehicle role mapping is vehicle role's sequence；The vehicle Entity recognition module obtains the vehicle entity of the vehicle role sequence
Character string, the vehicle entity character string and the vehicle entity in Standard of vehicle library, obtain the highest vehicle entity of similarity.
Further, it further includes vehicle role set and closes generation module, the vehicle role set is closed described in generation module extraction
The vehicle role creation vehicle role of Standard of vehicle library and vehicle corpus gathers；The vehicle Entity recognition module further includes vehicle
Role gathers update module, and the vehicle role gathers update module and the original vehicle role is added to the vehicle angle
Color set.
Further, the vehicle role set closes generation module and extracts the Standard of vehicle library and the vehicle corpus
Vehicle entity role, vehicle component role, the role above of vehicle entity, vehicle entity hereafter role, and according to institute
State vehicle entity role, vehicle component role, the role above of vehicle entity, vehicle entity hereafter role creation described in
Vehicle role gathers.
Further, the vehicle role abstraction module further includes word-dividing mode, and the word-dividing mode is to the original car
Text carries out word segmentation processing, and the vehicle role abstraction module is gathered according to the vehicle role carries out word segmentation processing result
Vehicle entity role, the hereafter role extraction of vehicle component role, the role above of vehicle entity, vehicle entity, by angle
Color extracts result and is mapped as the vehicle role sequence.
Further, the vehicle role abstraction module further includes vehicle entity character string abstraction module and similarity-rough set
Module, the vehicle entity character string abstraction module match the vehicle role sequence with vehicle dictionary tree, obtain institute
The vehicle entity character string of vehicle role's sequence is stated, the vehicle entity character string maps are vehicle by the similarity-rough set module
Entity text, the vehicle entity text and the vehicle entity in the Standard of vehicle library, obtain the highest vehicle of similarity
Entity.
Compared with prior art, the beneficial effects of the present invention are：
The present invention is gathered by the vehicle role creation vehicle role of draw standard vehicle library and vehicle corpus, according to vehicle
Role set carries out vehicle role's extraction to original vehicle text, original vehicle role is obtained, by original vehicle role mapping
For vehicle role's sequence, the vehicle entity character string of vehicle role's sequence is obtained, compares vehicle entity character string and Standard of vehicle
The vehicle entity in library obtains the highest vehicle entity of similarity, original vehicle role is gathered added to vehicle role, greatly
Reduce the workload manually mapped, without manually formulating a large amount of rules, favorable expandability, accuracy rate is high, good compatibility.
Above description is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be implemented in accordance with the contents of the specification, below with presently preferred embodiments of the present invention and after attached drawing is coordinated to be described in detail such as.
The specific embodiment of the present invention is shown in detail by following embodiment and its attached drawing.
Description of the drawings
Attached drawing described herein is used to provide further understanding of the present invention, and forms the part of the application, this hair
Bright illustrative embodiments and their description do not constitute improper limitations of the present invention for explaining the present invention.In the accompanying drawings：
Fig. 1 is a kind of vehicle entity recognition method flow chart of the present invention；
Fig. 2 is a kind of vehicle entity recognition system structure diagram of the present invention；
Fig. 3 is a kind of vehicle entity recognition system schematic diagram of the present invention.
Specific embodiment
In the following, with reference to attached drawing and specific embodiment, the present invention is described further, it should be noted that not
Under the premise of conflicting, new implementation can be formed between various embodiments described below or between each technical characteristic in any combination
Example.
A kind of vehicle entity recognition method, as shown in Figure 1, including the following steps：
Generate the vehicle role creation vehicle role set of role's set, draw standard vehicle library and vehicle corpus, mark
Quasi- vehicle library storage standard vehicle entity, such as " benz ", " BMW ", " Audi ", vehicle language material library storage user input data,
Such as " consideration start with BMW ", " Audi's price "；Preferably, step generation role set includes：Draw standard vehicle library and vehicle
The vehicle entity role of corpus, vehicle component role, the role above of vehicle entity, vehicle entity hereafter angle
Color, the role above of vehicle entity is the role before vehicle entity in vehicle text, and the hereafter role of vehicle entity is vehicle
Role in text after vehicle entity, according to vehicle entity role, vehicle component role, vehicle entity angle above
The hereafter role creation vehicle role set of color, vehicle entity, only need to count a small amount of vehicle role, other vehicles in this step
Role, which by step updates role's set and extends to role, to be gathered, and the workload manually mapped is greatly reduced, without people
Work formulates a large amount of rules, and the vehicle entity in Standard of vehicle library added to role is gathered, improves the knowledge of vehicle entity by favorable expandability
Other accuracy rate and recognition efficiency.
In one embodiment, the vehicle entity role of extraction is encoded to " C ", such as benz, BMW, Audi, vehicle composition member
Plain role is encoded to " D ", such as run quickly, enlightening, Austria, the role above of vehicle entity is encoded to " K ", such as consider, displacement, inquiry, vehicle
The hereafter role of entity is encoded to " L ", and such as price is stated a price, other roles other than above-mentioned role are encoded to " A ".
Role extracts, and carries out vehicle role's extraction to original vehicle text according to vehicle role set, obtains several original
Several original vehicle role mappings are vehicle role's sequence by vehicle role；Preferably, step role extracts and includes：To original
Vehicle text carries out word segmentation processing, carries out vehicle entity role to word segmentation processing result according to vehicle role set, vehicle forms
Role's extraction result is mapped as vehicle angle by element role, the hereafter role extraction of the role above of vehicle entity, vehicle entity
Color-sequential arranges.
Vehicle Entity recognition obtains the vehicle entity character string of vehicle role's sequence, compares vehicle entity character string and mark
The vehicle entity in quasi- vehicle library obtains the highest vehicle entity of similarity；Preferably, step vehicle Entity recognition includes：Judge
Whether vehicle role sequence is the vehicle entity role for extracting vehicle role's sequence comprising vehicle entity role, and by vehicle
The vehicle entity role of role's sequence is mapped as vehicle entity；Otherwise by the vehicle role sequence and the progress of vehicle dictionary tree
Match, obtain the vehicle entity character string of vehicle role's sequence, be vehicle entity text by vehicle entity character string maps, compare vehicle
Entity text and the vehicle entity in Standard of vehicle library, obtain the highest vehicle entity of similarity.
Role's set is updated, original vehicle role is gathered added to vehicle role, when vehicle role sequence includes vehicle
During entity role, the role above of vehicle entity and the hereafter role of vehicle entity are gathered added to vehicle role；Work as vehicle
When role's sequence does not include vehicle entity role, original vehicle role added to vehicle role is gathered, only need to count a small amount of
Vehicle role creation vehicle role gathers, and constantly gathers new vehicle role added to vehicle role, realizes vehicle role
The extension of set obtains the vehicle role set of high quality, greatly reduces human cost.
In one embodiment, the vehicle entity role " BMW " of vehicle entity " BMW " and vehicle in draw standard vehicle library
Component role " treasured " and " horse " are gathered added to vehicle role, and vehicle entity role " BMW " is encoded to " C ", vehicle composition
Element role " treasured " and " horse " are encoded to " D ", and original vehicle text input by user is " consulting BMW price ", to " consulting
BMW price " carry out word segmentation processing be " consulting/BMW/price ", according to vehicle role set to " consulting/BMW/price " into
Row role extracts, and role's extraction result is mapped as vehicle role's sequence, vehicle role sequence is classified as " ACA ", because of vehicle role sequence
It arranges in " ACA " comprising vehicle entity role " C ", extracts the vehicle entity role " C " of vehicle role sequence " ACA ", and by vehicle
The vehicle entity role " C " of role's sequence " ACA " is mapped as vehicle entity " BMW "；By the role above " consulting " of vehicle entity
Vehicle entity is upper in gathering with the hereafter role " price " of vehicle entity added to vehicle role set, and calculating vehicle role
Literary role and the frequency of use of the hereafter role of vehicle entity, role's frequency of use are used for the vehicle entity that filtering is of little use
Literary role and the hereafter role of vehicle entity.
In one embodiment, original vehicle text input by user is " considering to embrace horse 300,000 ", to " considering to embrace horse 300,000 "
Word segmentation processing is carried out as " considering/embrace/horse/3,0/0,000 ", role is carried out to " considering/embrace/horse/3,0/0,000 " according to vehicle role set
It extracts, role's extraction result is mapped as vehicle role's sequence, vehicle role sequence is classified as " KADAA ", and vehicle role's sequence is not wrapped
The role of entity containing vehicle carries out max model matching, specially using trie by existing entity word dictionary to sequence " KADAA "
Content is built into vehicle dictionary tree, and sequence " KADAA " is matched with vehicle dictionary tree, obtains vehicle entity character string
Vehicle entity character string " KAD " is mapped as vehicle entity text " considering to embrace horse ", vehicle entity text " is considered to embrace by " KAD "
Horse " and the vehicle entity in Standard of vehicle library do similarity calculation, and similarity is defeated more than the vehicle entity headed by threshold value and ranking
Go out, similarity highest of the result for vehicle entity text " considering to embrace horse " and the vehicle entity " BMW " in Standard of vehicle library, vehicle
Entity recognition result is " BMW ", by new vehicle component role " embracing " added to vehicle role set, when there is new original
Beginning vehicle text, if user is accidentally defeated into " embrace and " by " Bora ", system can automatically identify vehicle entity as " Bora ", vehicle
The update of role's set greatly reduces the workload manually mapped, favorable expandability, good compatibility.
A kind of electronic equipment, including：Processor；Memory；And program, Program are stored in memory, and
And be configured to be performed by processor, program includes performing a kind of vehicle entity recognition method；One kind is computer-readable to deposit
Storage media is stored thereon with computer program, it is characterised in that：Computer program is executed by processor a kind of above-mentioned vehicle entity
Recognition methods.
A kind of vehicle entity recognition system, as shown in Fig. 2, including vehicle role abstraction module, vehicle Entity recognition module,
Vehicle role abstraction module carries out vehicle role's extraction to original vehicle text, several original vehicle roles is obtained, by several originals
Beginning vehicle role mapping is vehicle role's sequence；Vehicle Entity recognition module obtains the vehicle entity character of vehicle role's sequence
String compares the vehicle entity of vehicle entity character string and Standard of vehicle library, obtains the highest vehicle entity of similarity.
In one embodiment, as shown in Fig. 2-Fig. 3, it is preferable that further include vehicle role set and close generation module, vehicle role
Gather the vehicle role creation vehicle role set of generation module draw standard vehicle library and vehicle corpus；Vehicle Entity recognition
Module further includes vehicle role and gathers update module, and vehicle role gathers update module and original vehicle role is added to vehicle angle
Color set.
In one embodiment, it is preferable that vehicle role set closes generation module draw standard vehicle library and vehicle corpus
Vehicle entity role, vehicle component role, the role above of vehicle entity, vehicle entity hereafter role, and according to vehicle
Entity role, vehicle component role, the role above of vehicle entity, vehicle entity hereafter role creation vehicle role
Set.
In one embodiment, as shown in Fig. 2-Fig. 3, it is preferable that vehicle role's abstraction module further includes word-dividing mode, participle
Module carries out original vehicle text word segmentation processing, and vehicle role abstraction module is gathered according to vehicle role to word segmentation processing result
The hereafter role extraction of vehicle entity role, vehicle component role, the role above of vehicle entity, vehicle entity are carried out,
Role's extraction result is mapped as vehicle role's sequence.
In one embodiment, as shown in Fig. 2-Fig. 3, it is preferable that vehicle role's abstraction module further includes vehicle entity character
Go here and there abstraction module and similarity-rough set module, vehicle entity character string abstraction module by vehicle role sequence and vehicle dictionary tree into
Row matching, obtains the vehicle entity character string of vehicle role's sequence, and vehicle entity character string maps are by similarity-rough set module
Vehicle entity text compares the vehicle entity of vehicle entity text and Standard of vehicle library, obtains the highest vehicle entity of similarity.
In one embodiment, when vehicle role sequence includes vehicle entity role, role gathers update module by vehicle
The role above of entity and the hereafter role of vehicle entity gather added to vehicle role；When vehicle role sequence does not include vehicle
During entity role, role gathers update module and gathers original vehicle role added to vehicle role.
The present invention is gathered by the vehicle role creation vehicle role of draw standard vehicle library and vehicle corpus, according to vehicle
Role set carries out vehicle role's extraction to original vehicle text, original vehicle role is obtained, by original vehicle role mapping
For vehicle role's sequence, the vehicle entity character string of vehicle role's sequence is obtained, compares vehicle entity character string and Standard of vehicle
The vehicle entity in library obtains the highest vehicle entity of similarity, original vehicle role is gathered added to vehicle role, greatly
Reduce the workload manually mapped, without manually formulating a large amount of rules, favorable expandability, accuracy rate is high, good compatibility.
More than, only presently preferred embodiments of the present invention not makees the present invention limitation in any form；All one's own professions
The those of ordinary skill of industry can swimmingly implement the present invention shown in by specification attached drawing and above；But all to be familiar with sheet special
The technical staff of industry without departing from the scope of the present invention, is made a little using disclosed above technology contents
The equivalent variations of variation, modification and evolution are the equivalent embodiment of the present invention；Meanwhile all substantial technologicals according to the present invention
Variation, modification and evolution of any equivalent variations made to above example etc., still fall within technical scheme of the present invention
Within protection domain.
Claims (12)
1. a kind of vehicle entity recognition method, it is characterised in that include the following steps：
Role extracts, and carries out vehicle role's extraction to original vehicle text, several original vehicle roles is obtained, by several originals
Beginning vehicle role mapping is vehicle role's sequence；
Vehicle Entity recognition obtains the vehicle entity character string of the vehicle role sequence, the vehicle entity character string
With the vehicle entity in Standard of vehicle library, the highest vehicle entity of similarity is obtained.
2. a kind of vehicle entity recognition method as described in claim 1, it is characterised in that：Further include step generation role's set
With step update role's set, the step generation role set is combined into the vehicle for extracting the Standard of vehicle library and vehicle corpus
Role creation vehicle role gathers；The step update role set is combined into is added to the vehicle angle by the original vehicle role
Color set.
3. a kind of vehicle entity recognition method as claimed in claim 2, which is characterized in that the step generation role gathers packet
It includes：Extract the vehicle entity role, vehicle component role, vehicle entity in the Standard of vehicle library and the vehicle corpus
Role above, vehicle entity hereafter role, according to the vehicle entity role, vehicle component role, vehicle entity
Role above, vehicle entity hereafter role creation described in vehicle role set.
4. a kind of vehicle entity recognition method as claimed in claim 3, which is characterized in that the step role, which extracts, to be included：
Word segmentation processing is carried out to the original vehicle text, vehicle entity is carried out to word segmentation processing result according to vehicle role set
Role, the hereafter role extraction of vehicle component role, the role above of vehicle entity, vehicle entity, role is extracted and is tied
Fruit is mapped as the vehicle role sequence.
A kind of 5. vehicle entity recognition method as claimed in claim 4, which is characterized in that the step vehicle Entity recognition packet
It includes：Judge that the vehicle role sequence is the vehicle reality for extracting the vehicle role sequence whether comprising vehicle entity role
Body role, and the vehicle entity role of the vehicle role sequence is mapped as vehicle entity；Otherwise by the vehicle role sequence
Row are matched with vehicle dictionary tree, the vehicle entity character string of the vehicle role sequence are obtained, by the vehicle entity word
Symbol string is mapped as vehicle entity text, the vehicle entity text and the vehicle entity in the Standard of vehicle library, obtains phase
Like the highest vehicle entity of degree.
6. a kind of electronic equipment, it is characterised in that including：Processor；
Memory；And program, wherein described program is stored in the memory, and is configured to be held by processor
Row, described program include the method for performing as described in claim 1-5 any one.
7. a kind of computer readable storage medium, is stored thereon with computer program, it is characterised in that：The computer program quilt
Processor performs the method as described in claim 1-5 any one.
8. a kind of vehicle entity recognition system, it is characterised in that：Including vehicle role abstraction module, vehicle Entity recognition module,
The vehicle role abstraction module carries out vehicle role's extraction to original vehicle text, obtains several original vehicle roles, if will
It is vehicle role's sequence to do the original vehicle role mapping；The vehicle Entity recognition module obtains the vehicle role sequence
Vehicle entity character string, the vehicle entity in the vehicle entity character string and Standard of vehicle library obtains similarity highest
Vehicle entity.
9. a kind of vehicle entity recognition system as claimed in claim 8, it is characterised in that：Further include the symphysis of vehicle role set into
Module, the vehicle role set close the vehicle role creation vehicle that generation module extracts the Standard of vehicle library and vehicle corpus
Role gathers；The vehicle Entity recognition module further includes vehicle role and gathers update module, and the vehicle role gathers update
Module gathers the original vehicle role added to the vehicle role.
10. a kind of vehicle entity recognition system as claimed in claim 9, it is characterised in that：The vehicle role set symphysis into
The vehicle entity role, vehicle component role, vehicle that module extracts the Standard of vehicle library and the vehicle corpus are real
The role above of body, the hereafter role of vehicle entity, and according to the vehicle entity role, vehicle component role, vehicle
Vehicle role described in the role above of entity, the hereafter role creation of vehicle entity gathers.
11. a kind of vehicle entity recognition system as claimed in claim 10, it is characterised in that：The vehicle role abstraction module
Word-dividing mode is further included, the word-dividing mode carries out the original vehicle text word segmentation processing, and the vehicle role extracts mould
Root tuber is gathered according to the vehicle role carries out word segmentation processing result vehicle entity role, vehicle component role, vehicle reality
The role above of body, the hereafter role of vehicle entity extract, and role's extraction result is mapped as the vehicle role sequence.
12. a kind of vehicle entity recognition system as claimed in claim 11, it is characterised in that：The vehicle role abstraction module
Vehicle entity character string abstraction module and similarity-rough set module are further included, the vehicle entity character string abstraction module is by described in
Vehicle role sequence is matched with vehicle dictionary tree, obtains the vehicle entity character string of the vehicle role sequence, the phase
Like degree comparison module by the vehicle entity character string maps be vehicle entity text, the vehicle entity text with it is described
The vehicle entity in Standard of vehicle library obtains the highest vehicle entity of similarity.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711185953.XA CN108170708B (en) | 2017-11-23 | 2017-11-23 | Vehicle entity identification method, electronic equipment, storage medium and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711185953.XA CN108170708B (en) | 2017-11-23 | 2017-11-23 | Vehicle entity identification method, electronic equipment, storage medium and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108170708A true CN108170708A (en) | 2018-06-15 |
| CN108170708B CN108170708B (en) | 2021-03-30 |
Family
ID=62527603
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711185953.XA Active CN108170708B (en) | 2017-11-23 | 2017-11-23 | Vehicle entity identification method, electronic equipment, storage medium and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108170708B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109389064A (en) * | 2018-09-27 | 2019-02-26 | 东软睿驰汽车技术（沈阳）有限公司 | A kind of vehicle characteristics acquisition methods and device |
| CN111612015A (en) * | 2020-05-26 | 2020-09-01 | 创新奇智(西安)科技有限公司 | Vehicle identification method and device and electronic equipment |
| CN111930775A (en) * | 2020-08-26 | 2020-11-13 | 明觉科技（北京）有限公司 | Vehicle information identification method, device, terminal and computer readable storage medium |
| CN113886385A (en) * | 2021-09-18 | 2022-01-04 | 中国银行保险信息技术管理有限公司 | New energy automobile insurance identification method and device based on rule engine |
| CN115759097A (en) * | 2022-11-08 | 2023-03-07 | 广东数鼎科技有限公司 | Vehicle type name recognition method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102033879A (en) * | 2009-09-27 | 2011-04-27 | 腾讯科技（深圳）有限公司 | Method and device for identifying Chinese name |
| CN103268339A (en) * | 2013-05-17 | 2013-08-28 | 中国科学院计算技术研究所 | Recognition method and system of named entities in microblog messages |
-
2017
- 2017-11-23 CN CN201711185953.XA patent/CN108170708B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102033879A (en) * | 2009-09-27 | 2011-04-27 | 腾讯科技（深圳）有限公司 | Method and device for identifying Chinese name |
| CN103268339A (en) * | 2013-05-17 | 2013-08-28 | 中国科学院计算技术研究所 | Recognition method and system of named entities in microblog messages |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109389064A (en) * | 2018-09-27 | 2019-02-26 | 东软睿驰汽车技术（沈阳）有限公司 | A kind of vehicle characteristics acquisition methods and device |
| CN111612015A (en) * | 2020-05-26 | 2020-09-01 | 创新奇智(西安)科技有限公司 | Vehicle identification method and device and electronic equipment |
| CN111612015B (en) * | 2020-05-26 | 2023-10-31 | 创新奇智(西安)科技有限公司 | Vehicle identification method and device and electronic equipment |
| CN111930775A (en) * | 2020-08-26 | 2020-11-13 | 明觉科技（北京）有限公司 | Vehicle information identification method, device, terminal and computer readable storage medium |
| CN113886385A (en) * | 2021-09-18 | 2022-01-04 | 中国银行保险信息技术管理有限公司 | New energy automobile insurance identification method and device based on rule engine |
| CN115759097A (en) * | 2022-11-08 | 2023-03-07 | 广东数鼎科技有限公司 | Vehicle type name recognition method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108170708B (en) | 2021-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108170708A (en) | A kind of vehicle entity recognition method, electronic equipment, storage medium, system | |
| CN110909548B (en) | Chinese named entity recognition method, device and computer readable storage medium | |
| WO2018032937A1 (en) | Method and apparatus for classifying text information | |
| CN105843965B (en) | A kind of Deep Web Crawler form filling method and apparatus based on URL subject classification | |
| CN102289522B (en) | Method of intelligently classifying texts | |
| CN103559175B (en) | A kind of Spam Filtering System based on cluster and method | |
| CN106096609B (en) | A kind of merchandise query keyword automatic generation method based on OCR | |
| CN107229731B (en) | Method and apparatus for classifying data | |
| CN107729900A (en) | It is a kind of that the method and apparatus for completing typing information completion is extracted using picture attribute | |
| CN106339479A (en) | Picture naming method and terminal | |
| CN106815208A (en) | The analysis method and device of law judgement document | |
| CN107861944A (en) | A kind of text label extracting method and device based on Word2Vec | |
| JP2013238991A (en) | Information processing apparatus, information processing method, and program | |
| CN107943514A (en) | The method for digging and system of core code element in a kind of software document | |
| CN106127222B (en) | A kind of the similarity of character string calculation method and similitude judgment method of view-based access control model | |
| CN103236261A (en) | Speaker-dependent voice recognizing method | |
| CN106815193A (en) | Model training method and device and wrong word recognition methods and device | |
| CN110321549A (en) | Based on the new concept method for digging for serializing study, relation excavation, Time-Series analysis | |
| CN107402916A (en) | The segmenting method and device of Chinese text | |
| CN110443174A (en) | A kind of pedestrian's recognition methods again based on decoupling self-adaptive identification feature learning | |
| CN108845992B (en) | Computer readable storage medium and question-answer interaction method | |
| CN106844412A (en) | A kind of human face data collection method and device | |
| CN110674313B (en) | Method for dynamically updating knowledge graph based on user log | |
| CN103425648B (en) | The disposal route of relation loop and system | |
| CN114037886A (en) | Image recognition method and device, electronic equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 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 |