CN105975610A - Scene recognition method and device - Google Patents
Scene recognition method and device Download PDFInfo
- Publication number
- CN105975610A CN105975610A CN201610330812.1A CN201610330812A CN105975610A CN 105975610 A CN105975610 A CN 105975610A CN 201610330812 A CN201610330812 A CN 201610330812A CN 105975610 A CN105975610 A CN 105975610A
- Authority
- CN
- China
- Prior art keywords
- semantic
- minor structure
- user
- key word
- search key
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Machine Translation (AREA)
Abstract
The invention provides a scene recognition method and device. According to the embodiment of the scene recognition method and device, obtained search keywords provided by a user are subjected to semantic analysis so that at least one semantic substructure can be obtained, search intention is further obtained according to the at least one semantic substructure, and a scene of the user can be obtained according to the search intention and user attribute data of the user accordingly; as the position of the user is not completely depended on, scene recognition is carried out by combining the search intention obtained according to the search keywords, the scene recognition result is coincident with a practical scene, and the reliability of scene recognition is improved.
Description
[technical field]
The present invention relates to Internet technology, particularly relate to a kind of scene recognition method and device.
[background technology]
Along with the development of communication technology, terminal is integrated with increasing function, so that terminal is
System feature list contains more and more corresponding application program.Specified services in some application program
Some scene Recognition functions can be related to.Existing specified services is such as, it is recommended that services, predict in service etc.,
Corresponding scene can be identified based on the position at user place, and then it is relevant to provide the user this scene
Information on services.
But, the method for existing scene Recognition, it is completely dependent on the position at user place, may be such that
Scene Recognition result and actual scene deviation, therefore, can cause the reduction of the reliability of scene Recognition.
[summary of the invention]
The many aspects of the present invention provide a kind of scene recognition method and device, in order to improve scene Recognition
Reliability.
An aspect of of the present present invention, it is provided that a kind of scene recognition method, including:
Obtain the search key word that user provides;
Described search key word is carried out semantic analysis process, to obtain at least one semantic minor structure;
According at least one semantic minor structure described, it is thus achieved that search intention;
According to described search intention and the UAD of described user, it is thus achieved that the field at described user place
Scape.
Aspect as above and arbitrary possible implementation, it is further provided a kind of implementation, institute
State and described search key word is carried out semantic analysis process, to obtain at least one semantic minor structure, including:
Utilize semantic analysis technology, described search key word is carried out semantic analysis process;
To through semantic analysis process after search key word carry out contents extraction, with obtain described at least
One semantic minor structure.
Aspect as above and arbitrary possible implementation, it is further provided a kind of implementation, institute
State and described search key word is carried out semantic analysis process, to obtain at least one semantic minor structure, also wrap
Include:
It is modified processing at least one semantic minor structure described in being obtained, after obtaining and revising
At least one semantic minor structure described.
Aspect as above and arbitrary possible implementation, it is further provided a kind of implementation, institute
State according at least one semantic minor structure described, it is thus achieved that search intention, including:
According at least one semantic minor structure described, it is thus achieved that each language at least one semantic minor structure described
Structural relation between foster son's structure;
At least one semantic minor structure described and described structural relation are carried out Deep Semantics analysis, it is thus achieved that institute
State search intention.
Aspect as above and arbitrary possible implementation, it is further provided a kind of implementation, institute
State the UAD of user and include at least one in following data:
The position data of described user;And
User's portrait of described user.
Another aspect of the present invention, it is provided that a kind of scene Recognition device, including:
Acquiring unit, for obtaining the search key word that user provides;
Semantic primitive, for carrying out semantic analysis process to described search key word, to obtain at least one
Semantic minor structure;
It is intended to unit, for according at least one semantic minor structure described, it is thus achieved that search intention;
Recognition unit, for according to described search intention and the UAD of described user, it is thus achieved that institute
State the scene at user place.
Aspect as above and arbitrary possible implementation, it is further provided a kind of implementation, institute
Meaning elements, specifically for
Utilize semantic analysis technology, described search key word is carried out semantic analysis process;And
To through semantic analysis process after search key word carry out contents extraction, with obtain described at least
One semantic minor structure.
Aspect as above and arbitrary possible implementation, it is further provided a kind of implementation, institute
Meaning elements, is additionally operable to
It is modified processing at least one semantic minor structure described in being obtained, after obtaining and revising
At least one semantic minor structure described.
Aspect as above and arbitrary possible implementation, it is further provided a kind of implementation, institute
State intention unit, specifically for
According at least one semantic minor structure described, it is thus achieved that each language at least one semantic minor structure described
Structural relation between foster son's structure;And
At least one semantic minor structure described and described structural relation are carried out Deep Semantics analysis, it is thus achieved that institute
State search intention.
Aspect as above and arbitrary possible implementation, it is further provided a kind of implementation, institute
State the UAD of user and include at least one in following data:
The position data of described user;And
User's portrait of described user.
As shown from the above technical solution, the embodiment of the present invention is closed by the search providing acquired user
Keyword carries out semantic analysis process, to obtain at least one semantic minor structure, and then according to described at least one
Individual semantic minor structure, it is thus achieved that search intention, enabling according to described search intention and the use of described user
Family attribute data, it is thus achieved that the scene at described user place, owing to being no longer completely dependent on the position at user place,
But combine the search intention obtained according to search key word and carry out scene Recognition so that scene Recognition
Result is more consistent with actual scene, thus improves the reliability of scene Recognition.
It addition, use technical scheme provided by the present invention, it is possible to be effectively improved the experience of user.
[accompanying drawing explanation]
For the technical scheme being illustrated more clearly that in the embodiment of the present invention, below will be to embodiment or existing
In technology description, the required accompanying drawing used is briefly described, it should be apparent that, in describing below
Accompanying drawing is some embodiments of the present invention, for those of ordinary skill in the art, is not paying creation
On the premise of property is laborious, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
The schematic flow sheet of the scene recognition method that Fig. 1 provides for one embodiment of the invention;
The structural representation of the scene Recognition device that Fig. 2 provides for another embodiment of the present invention.
[detailed description of the invention]
For making the purpose of the embodiment of the present invention, technical scheme and advantage clearer, below in conjunction with this
Accompanying drawing in bright embodiment, is clearly and completely described the technical scheme in the embodiment of the present invention,
Obviously, described embodiment is a part of embodiment of the present invention rather than whole embodiments.Based on
Embodiment in the present invention, those of ordinary skill in the art are obtained under not making creative work premise
Other embodiments whole obtained, broadly fall into the scope of protection of the invention.
It should be noted that terminal involved in the embodiment of the present invention can include but not limited to mobile phone,
Personal digital assistant (Personal Digital Assistant, PDA), radio hand-held equipment, flat board electricity
Brain (Tablet Computer), PC (Personal Computer, PC), MP3 play
Device, MP4 player, wearable device (such as, intelligent glasses, intelligent watch, Intelligent bracelet etc.)
Deng.
It addition, the terms "and/or", a kind of incidence relation describing affiliated partner, represent
Three kinds of relations, such as, A and/or B can be there are, can represent: individualism A, there is A simultaneously
And B, individualism B these three situation.It addition, character "/" herein, typically represent forward-backward correlation pair
As if the relation of a kind of "or".
The schematic flow sheet of the scene recognition method that Fig. 1 provides for one embodiment of the invention, as shown in Figure 1.
101, the search key word that user provides is obtained.
102, described search key word is carried out semantic analysis process, to obtain at least one semantic minor structure.
103, according at least one semantic minor structure described, it is thus achieved that search intention.
104, according to described search intention and the UAD of described user, it is thus achieved that described user place
Scene.
It should be noted that the executive agent of 101~104 can be partly or entirely to be located locally terminal
Application, or can also be to be arranged in the plug-in unit in the application of local terminal or SDK
The functional units such as bag (Software Development Kit, SDK), or can also be for being positioned at network
Process engine in the server of side, or can also be the distributed system being positioned at network side, the present embodiment
This is not particularly limited.
It is understood that the local program (nativeApp) that described application can be mounted in terminal,
Or can also is that a web page program (webApp) of browser in terminal, the present embodiment is to this not
It is particularly limited.
So, the search key word by providing acquired user carries out semantic analysis process, to obtain
Obtain at least one semantic minor structure, and then according at least one semantic minor structure described, it is thus achieved that search intention,
Make it possible to according to described search intention and the UAD of described user, it is thus achieved that described user place
Scene, owing to being no longer completely dependent on the position at user place, but combine according to search key word obtained
The search intention obtained carries out scene Recognition so that scene Recognition result is more consistent with actual scene, from
And improve the reliability of scene Recognition.
Alternatively, in a possible implementation of the present embodiment, in 101, specifically can adopt
The described search key word that collection user is provided.Specifically, specifically can be by searching that user is triggered
Rope order realizes.Specifically can use but be not limited to following several ways triggering search command:
Mode one:
User can be inputted described search key word on the page that current application is represented, then, logical
Cross the search button clicked on this page such as, using Baidu.com, to trigger search command, this search command
In comprise described search key word.Wherein, user inputs the order of described search key word can be any
Sequentially.So, after receiving this search command, then can parse described in included in it and search
Rope key word.
Mode two:
Use Asynchronous loading technology such as, Ajax Asynchronous loading or Jsonp Asynchronous loading etc., obtain in real time
The input content that user is inputted on the page that current application is represented, in order to carry out with search key word
Distinguishing, input content now is known as inputting key word.Wherein, user inputs described search pass
The order of keyword can be random order.Specifically, Ajax interface or Jsonp interface can specifically be provided
Deng interface, these interfaces can use Java, supertext pretreatment (Hypertext Preprocessor,
PHP) language such as language is write, and what it was concrete call can use Jquery, or primary
The language such as JavaScript are write.
Mode three: user can press the phonetic search button on the page that current application is represented by long,
Say the voice content wanting input, then, unclamp phonetic search button, to trigger search command, should
Search command comprises the search key word of the textual form changed according to the voice content said.So,
After receiving this search command, then can parse the described search key word included in it.
Mode four: user can by clicking on the phonetic search button on the page that represented of current application,
Say the voice content wanting input, treat that end says voice content a period of time such as, after 2 seconds,
Then trigger search command, this search command comprises the textual form according to the voice content conversion said
Search key word.So, after receiving this search command, then can parse included in it
Described search key word.
After getting described input key word, then can perform subsequent operation that is 102~104.
Alternatively, in a possible implementation of the present embodiment, in 102, specifically can be in order to
By semantic analysis technology, described search key word is carried out semantic analysis process, and then, then can be to warp
Cross the search key word after semantic analysis processes and carry out contents extraction, to obtain at least one semanteme described
Minor structure.
So-called semantic analysis processes, refer to become a sentences decomposition ingredient that some are little (as word,
Phrase etc.), and obtain the relation between these parts.In the present invention, can use of the prior art
Semantic analysis technology, carries out semantic analysis process to acquired search key word, and its result is permissible
As 103 and 104 perform basis.
It should be noted that there is the search key word of special construction for some, can be according to specifying rule
Then, carry out semantic analysis process, and contents extraction, such as, a kind of special construction for " or " draw
Playing the structure of Selective type, another kind is the structure that " XX's from XX is different " distinguish type, also one
Plant the structure for " noun from XX to XX " demand type.
In this implementation, it is possible to obtain at least one in the semantic minor structure of following structure:
Entity, attribute, property value, i.e. SPO;
Entity, attribute, i.e. SP;
Attribute, property value, i.e. PO;
Entity, adjective, object, i.e. SAO;
Entity, adjective, i.e. SA;
Adjective, object, i.e. AO;
Noun, modifies, i.e. NMOD;
Entity, predicate, object, i.e. SVO;
Entity, predicate, i.e. SV;
Predicate, object, i.e. VO;
Entity, predicate, object, the adverbial modifier, i.e. SVOP;
Entity, predicate, the adverbial modifier, i.e. SVP;
Predicate, object, the adverbial modifier, i.e. VOP;
Predicate, the adverbial modifier, i.e. VP;
Predicate, i.e. V;
Starting point, terminal, demand, i.e. SEI;And
Entity, entity, compares, i.e. EECOMP.
In this implementation, after obtaining at least one semantic minor structure described, it is also possible to further
Be modified processing at least one semantic minor structure described in being obtained, with obtain revise after described in
At least one semantic minor structure.
During a concrete implementation, can be according to part of speech, the mistake of correction dependency analysis, such as,
Fault processing that side by side word causes, describe that the fault processing that part of speech adverbial word causes, multiple predicate are (containing shape
Hold word) fault processing that causes of the fault processing caused, continuous verb, etc..
During another concrete implementation, the mistake of dependency analysis, example according to sentence pattern, can be revised
As, the fault processing of the dependency analysis of the search key word at interrogative place, etc..
During another concrete implementation, the mistake of dependency analysis according to special construction, can be revised,
Such as, comprise serial verb construction, agent adverbial modifier's structure, word sentence structure, by word sentence structure, upside-down mounting
Sentence structure, noun parallel construction, continuous noun structure, etc..
During another concrete implementation, the adverbial modifier can be simplified process, for example, it is possible to enter
Subject or object that row is actual mark, and supplement for lacking subject or object, also may be used meanwhile
To carry out structure interpolation for special sentence pattern.Wherein, under described special sentence pattern can include but not limited to
At least one in row sentence pattern:
Relatively sentence pattern;
Select sentence pattern;
Nested sentence pattern;
Entity sentence pattern;
What sentence pattern;
How sentence pattern;
Why sentence pattern;
It it is non-sentence pattern;
Time question sentence sentence pattern;
Place question sentence sentence pattern;And
Quantity question sentence sentence pattern.
Alternatively, in a possible implementation of the present embodiment, in 103, specifically can root
According at least one semantic minor structure described, it is thus achieved that each semantic son knot at least one semantic minor structure described
Structural relation between structure, and then, then at least one semantic minor structure described and described structure can be closed
System carries out Deep Semantics analysis, it is thus achieved that described search intention.
Specifically, the structural relation between each semantic minor structure can include but not limited to following relationship
In at least one:
Choice relation;
Comparison;
Nest relation;
Coordination;
Or relation;
Conditional relationship;
Content relation;And
Core root relation (i.e. filiation).
Alternatively, in a possible implementation of the present embodiment, in 104, the institute of institute's foundation
State the UAD of user and can include but not limited at least one in following data:
The position data of described user;And
User's portrait of described user.
The position data of so-called user, the i.e. geographic position data of user position, specifically can adopt
With global positioning system (Global Positioning System, GPS) location technology, the wireless compatibility
Certification (Wireless Fidelity, Wi-Fi) location technology, architecture technology or sensor location technology
Etc. location technology, it is thus achieved that the geographic position data of user position.
User's portrait of so-called user, i.e. user profile labeling, it is simply that by collecting and analyzing user
Social property, living habit, the main information such as consuming behavior data after, take out a user
Business overall picture, can be regarded as applying the basic mode of big data technique.User's portrait provides enough
Information base, it is possible to help that to be quickly found out accurate user group and user's request etc. the most anti-
Feedforward information.
As such, it is possible to according to described search intention and the UAD of described user, it is thus achieved that described use
The scene at place, family, and then can provide, for this user, the clothes that this scene is relevant based on the scene obtained
Business information.
In the present embodiment, carry out semantic analysis process by the search key word that acquired user is provided,
To obtain at least one semantic minor structure, and then according at least one semantic minor structure described, it is thus achieved that search
It is intended to, enabling according to described search intention and the UAD of described user, it is thus achieved that described use
The scene at place, family, owing to being no longer completely dependent on the position at user place, but combines according to search key
The search intention that word is obtained is to carry out scene Recognition so that scene Recognition result and actual scene more
Cause, thus improve the reliability of scene Recognition.
It addition, use technical scheme provided by the present invention, it is possible to be effectively improved the experience of user.
It should be noted that for aforesaid each method embodiment, in order to be briefly described, therefore by its all table
Stating as a series of combination of actions, but those skilled in the art should know, the present invention is by being retouched
The restriction of the sequence of movement stated because according to the present invention, some step can use other orders or with
Shi Jinhang.Secondly, those skilled in the art also should know, embodiment described in this description all belongs to
In preferred embodiment, necessary to involved action and the module not necessarily present invention.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and does not has in certain embodiment
The part described in detail, may refer to the associated description of other embodiments.
The structural representation of the scene Recognition device that Fig. 2 provides for another embodiment of the present invention, such as Fig. 2 institute
Show.The scene Recognition device of the present embodiment can include acquiring unit 21, semantic primitive 22, be intended to unit
23 and recognition unit 24.Wherein, acquiring unit 21, for obtaining the search key word that user provides;
Semantic primitive 22, for carrying out semantic analysis process to described search key word, to obtain at least one language
Foster son's structure;It is intended to unit 23, for according at least one semantic minor structure described, it is thus achieved that search intention;
Recognition unit 24, for according to described search intention and the UAD of described user, it is thus achieved that described
The scene at user place.
It should be noted that the scene Recognition device that provided of the present embodiment can be partly or entirely position
In the application of local terminal, or it can also be the plug-in unit or soft being arranged in the application of local terminal
The functional units such as part development kit (Software Development Kit, SDK), or all right
For the process engine being positioned in network side server, or can also be the distributed system being positioned at network side,
This is not particularly limited by the present embodiment.
It is understood that the local program (nativeApp) that described application can be mounted in terminal,
Or can also is that a web page program (webApp) of browser in terminal, the present embodiment is to this not
It is particularly limited.
Alternatively, in a possible implementation of the present embodiment, institute's meaning elements 22, specifically
May be used for utilizing semantic analysis technology, described search key word is carried out semantic analysis process;And it is right
Search key word after semantic analysis processes carries out contents extraction, to obtain at least one language described
Foster son's structure.
Alternatively, in a possible implementation of the present embodiment, institute's meaning elements 22, also may be used
To be further used for being modified processing at least one semantic minor structure described in being obtained, repair to obtain
At least one semantic minor structure described after just.
Alternatively, in a possible implementation of the present embodiment, described intention unit 23, specifically
May be used for according at least one semantic minor structure described, it is thus achieved that every at least one semantic minor structure described
Structural relation between individual semantic minor structure;And to described at least one semantic minor structure and described structure
Relation carries out Deep Semantics analysis, it is thus achieved that described search intention.
Alternatively, in a possible implementation of the present embodiment, described recognition unit 24, depended on
According to the UAD of described user can include but not limited at least one in following data:
The position data of described user;And
User's portrait of described user.
It should be noted that method, the scene that can be provided by the present embodiment in embodiment corresponding to Fig. 1
Identification device realizes.Describe the related content that may refer in embodiment corresponding to Fig. 1 in detail, the most not
Repeat again.
In the present embodiment, the search key word user acquired in acquiring unit provided by semantic primitive
Carry out semantic analysis process, to obtain at least one semantic minor structure, and then by being intended to unit according to described
At least one semantic minor structure, it is thus achieved that search intention so that recognition unit can be according to described search intention
UAD with described user, it is thus achieved that the scene at described user place, owing to being no longer completely dependent on
The position at user place, but combine the search intention obtained according to search key word and carry out scene knowledge
Not so that scene Recognition result is more consistent with actual scene, thus improve the reliability of scene Recognition.
It addition, use technical scheme provided by the present invention, it is possible to be effectively improved the experience of user.
Those skilled in the art is it can be understood that arrive, and for convenience and simplicity of description, above-mentioned retouches
The specific works process of the system stated, device and unit, is referred to the correspondence in preceding method embodiment
Process, does not repeats them here.
In several embodiments provided by the present invention, it should be understood that disclosed system, device and
Method, can realize by another way.Such as, device embodiment described above is only shown
Meaning property, such as, the division of described unit, be only a kind of logic function and divide, actual can when realizing
There to be other dividing mode, such as, multiple unit or assembly can in conjunction with or be desirably integrated into another
Individual system, or some features can ignore, or do not perform.Another point, shown or discussed mutual it
Between coupling direct-coupling or communication connection can be the indirect coupling by some interfaces, device or unit
Close or communication connection, can be electrical, machinery or other form.
The described unit illustrated as separating component can be or may not be physically separate, makees
The parts shown for unit can be or may not be physical location, i.e. may be located at a place,
Or can also be distributed on multiple NE.Can select according to the actual needs part therein or
The whole unit of person realizes the purpose of the present embodiment scheme.
It addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit,
Can also be that unit is individually physically present, it is also possible to two or more unit are integrated in a list
In unit.Above-mentioned integrated unit both can realize to use the form of hardware, it would however also be possible to employ hardware adds software
The form of functional unit realizes.
The above-mentioned integrated unit realized with the form of SFU software functional unit, can be stored in a computer
In read/write memory medium.Above-mentioned SFU software functional unit is stored in a storage medium, including some fingers
Make with so that a computer installation (can be personal computer, server, or network equipment etc.)
Or processor (processor) performs the part steps of method described in each embodiment of the present invention.And it is aforementioned
Storage medium include: USB flash disk, portable hard drive, read only memory (Read-Only Memory, ROM),
Random access memory (Random Access Memory, RAM), magnetic disc or CD etc. are various
The medium of program code can be stored.
Last it is noted that above example is only in order to illustrate technical scheme, rather than to it
Limit;Although the present invention being described in detail with reference to previous embodiment, the ordinary skill of this area
Personnel it is understood that the technical scheme described in foregoing embodiments still can be modified by it, or
Person carries out equivalent to wherein portion of techniques feature;And these amendments or replacement, do not make corresponding skill
The essence of art scheme departs from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (10)
1. a scene recognition method, it is characterised in that including:
Obtain the search key word that user provides;
Described search key word is carried out semantic analysis process, to obtain at least one semantic minor structure;
According at least one semantic minor structure described, it is thus achieved that search intention;
According to described search intention and the UAD of described user, it is thus achieved that the field at described user place
Scape.
Method the most according to claim 1, it is characterised in that described described search key word is entered
Lang justice analyzes and processes, to obtain at least one semantic minor structure, including:
Utilize semantic analysis technology, described search key word is carried out semantic analysis process;
To through semantic analysis process after search key word carry out contents extraction, with obtain described at least
One semantic minor structure.
Method the most according to claim 2, it is characterised in that described described search key word is entered
Lang justice analyzes and processes, and to obtain at least one semantic minor structure, also includes:
It is modified processing at least one semantic minor structure described in being obtained, after obtaining and revising
At least one semantic minor structure described.
Method the most according to claim 1, it is characterised in that at least one language described in described basis
Foster son's structure, it is thus achieved that search intention, including:
According at least one semantic minor structure described, it is thus achieved that each language at least one semantic minor structure described
Structural relation between foster son's structure;
At least one semantic minor structure described and described structural relation are carried out Deep Semantics analysis, it is thus achieved that institute
State search intention.
5. according to the method described in Claims 1 to 4 any claim, it is characterised in that described user
UAD include at least one in following data:
The position data of described user;And
User's portrait of described user.
6. a scene Recognition device, it is characterised in that including:
Acquiring unit, for obtaining the search key word that user provides;
Semantic primitive, for carrying out semantic analysis process to described search key word, to obtain at least one
Semantic minor structure;
It is intended to unit, for according at least one semantic minor structure described, it is thus achieved that search intention;
Recognition unit, for according to described search intention and the UAD of described user, it is thus achieved that institute
State the scene at user place.
Device the most according to claim 6, it is characterised in that institute's meaning elements, specifically for
Utilize semantic analysis technology, described search key word is carried out semantic analysis process;And
To through semantic analysis process after search key word carry out contents extraction, with obtain described at least
One semantic minor structure.
Device the most according to claim 7, it is characterised in that institute's meaning elements, is additionally operable to
It is modified processing at least one semantic minor structure described in being obtained, after obtaining and revising
At least one semantic minor structure described.
Device the most according to claim 6, it is characterised in that described intention unit, specifically for
According at least one semantic minor structure described, it is thus achieved that each language at least one semantic minor structure described
Structural relation between foster son's structure;And
At least one semantic minor structure described and described structural relation are carried out Deep Semantics analysis, it is thus achieved that institute
State search intention.
10. according to the device described in claim 6~9 any claim, it is characterised in that described use
The UAD at family includes at least one in following data:
The position data of described user;And
User's portrait of described user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610330812.1A CN105975610A (en) | 2016-05-18 | 2016-05-18 | Scene recognition method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610330812.1A CN105975610A (en) | 2016-05-18 | 2016-05-18 | Scene recognition method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105975610A true CN105975610A (en) | 2016-09-28 |
Family
ID=56956960
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610330812.1A Pending CN105975610A (en) | 2016-05-18 | 2016-05-18 | Scene recognition method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105975610A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111506817A (en) * | 2020-04-21 | 2020-08-07 | 北京四维智联科技有限公司 | Method and system for determining search service |
CN111914133A (en) * | 2020-07-02 | 2020-11-10 | 海信视像科技股份有限公司 | Electronic equipment and query statement processing method |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104050176A (en) * | 2013-03-13 | 2014-09-17 | 电子科技大学 | Map-based information recommendation method |
CN104252533A (en) * | 2014-09-12 | 2014-12-31 | 百度在线网络技术(北京)有限公司 | Search method and search device |
CN104794122A (en) * | 2014-01-20 | 2015-07-22 | 腾讯科技(北京)有限公司 | Position information recommending method, device and system |
CN105069036A (en) * | 2015-07-22 | 2015-11-18 | 百度在线网络技术(北京)有限公司 | Information recommendation method and apparatus |
US9268818B1 (en) * | 2011-10-11 | 2016-02-23 | Google Inc. | Determining intent of a recommendation on a URL of a web page or advertisement |
CN105354199A (en) * | 2014-08-20 | 2016-02-24 | 北京羽扇智信息科技有限公司 | Scene information based entity meaning identification method and system |
-
2016
- 2016-05-18 CN CN201610330812.1A patent/CN105975610A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9268818B1 (en) * | 2011-10-11 | 2016-02-23 | Google Inc. | Determining intent of a recommendation on a URL of a web page or advertisement |
CN104050176A (en) * | 2013-03-13 | 2014-09-17 | 电子科技大学 | Map-based information recommendation method |
CN104794122A (en) * | 2014-01-20 | 2015-07-22 | 腾讯科技(北京)有限公司 | Position information recommending method, device and system |
CN105354199A (en) * | 2014-08-20 | 2016-02-24 | 北京羽扇智信息科技有限公司 | Scene information based entity meaning identification method and system |
CN104252533A (en) * | 2014-09-12 | 2014-12-31 | 百度在线网络技术(北京)有限公司 | Search method and search device |
CN105069036A (en) * | 2015-07-22 | 2015-11-18 | 百度在线网络技术(北京)有限公司 | Information recommendation method and apparatus |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111506817A (en) * | 2020-04-21 | 2020-08-07 | 北京四维智联科技有限公司 | Method and system for determining search service |
CN111914133A (en) * | 2020-07-02 | 2020-11-10 | 海信视像科技股份有限公司 | Electronic equipment and query statement processing method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110717339B (en) | Semantic representation model processing method and device, electronic equipment and storage medium | |
CN107480162B (en) | Search method, device and equipment based on artificial intelligence and computer readable storage medium | |
CN108287858B (en) | Semantic extraction method and device for natural language | |
CN113822067A (en) | Key information extraction method and device, computer equipment and storage medium | |
US10996931B1 (en) | Integrated programming framework for speech and text understanding with block and statement structure | |
US20170103061A1 (en) | Interaction apparatus and method | |
US20150286943A1 (en) | Decision Making and Planning/Prediction System for Human Intention Resolution | |
US11762926B2 (en) | Recommending web API's and associated endpoints | |
CN107102993B (en) | User appeal analysis method and device | |
CN112948534A (en) | Interaction method and system for intelligent man-machine conversation and electronic equipment | |
US20220414463A1 (en) | Automated troubleshooter | |
Zamanirad et al. | Programming bots by synthesizing natural language expressions into API invocations | |
EP3195308B1 (en) | Actions on digital document elements from voice | |
CN111783471B (en) | Semantic recognition method, device, equipment and storage medium for natural language | |
CN111767714B (en) | Text smoothness determination method, device, equipment and medium | |
CN105956181A (en) | Searching method and apparatus | |
CN112185361B (en) | Voice recognition model training method and device, electronic equipment and storage medium | |
CN111291551A (en) | Text processing method and device, electronic equipment and computer readable storage medium | |
CN105975610A (en) | Scene recognition method and device | |
CN105843849A (en) | Search method and device | |
CN106408115A (en) | Trip route recommending method and device | |
CN110580313B (en) | Data processing method a treatment method apparatus and apparatus for data processing | |
CN106021516A (en) | Search method and device | |
CN107729499A (en) | Information processing method, medium, system and electronic equipment | |
CN111243351B (en) | Foreign language spoken language training system based on word segmentation technology, client and server |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160928 |
|
RJ01 | Rejection of invention patent application after publication |