CN106779817A - Intension recognizing method and system based on various dimensions information - Google Patents
Intension recognizing method and system based on various dimensions information Download PDFInfo
- Publication number
- CN106779817A CN106779817A CN201611075074.7A CN201611075074A CN106779817A CN 106779817 A CN106779817 A CN 106779817A CN 201611075074 A CN201611075074 A CN 201611075074A CN 106779817 A CN106779817 A CN 106779817A
- Authority
- CN
- China
- Prior art keywords
- information
- carried out
- text message
- user
- history
- 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 OR CALCULATING; 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Machine Translation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to intention assessment technical field, there is provided a kind of intension recognizing method based on various dimensions information and system, the method includes obtaining text message, user's history operation information and the external information of user, information extraction and/or identification are carried out to text message, obtain characteristic information, according to characteristic information, user's history operation information and external information, intention assessment is carried out, obtain user in predicting and be intended to.Intension recognizing method and system of the present invention based on various dimensions information, it is possible to increase the precision and data-handling efficiency of intention assessment, prevent Intention Anticipation distortion, strengthen Consumer's Experience.
Description
Technical field
The present invention relates to intention assessment technical field, and in particular to a kind of intension recognizing method based on various dimensions information and
System.
Background technology
At present, it is that the platform, the when and where in equipment that are used based on user etc. are outer that the identification of existing user view is mostly
The daily information in portion, for example：When stop and click on webpage, click location on APP etc. predicts user's
It is intended to and preference.But, lack the literal information of user language, cause the result distortion of prediction, poor accuracy.Also, it is existing
Some user view identification does not possess individualized inference capabilities, poor user experience.
The precision and data-handling efficiency of intention assessment are how improved, Intention Anticipation distortion is prevented, strengthen Consumer's Experience,
It is the problem of those skilled in the art's urgent need to resolve.
The content of the invention
For defect of the prior art, the present invention provides a kind of intension recognizing method based on various dimensions information and is
System, it is possible to increase the precision and data-handling efficiency of intention assessment, prevents Intention Anticipation distortion, strengthens Consumer's Experience.
In a first aspect, the present invention provides a kind of intension recognizing method based on various dimensions information, the method includes：Obtain and use
The text message at family, user's history operation information and external information；
Information extraction and/or identification are carried out to text message, characteristic information is obtained；
According to characteristic information, user's history operation information and external information, intention assessment is carried out, obtain user in predicting meaning
Figure.
Further, information extraction and/or identification are carried out to text message, characteristic information is obtained, is specifically included：To text
Information carries out information extraction, obtains extraction information；
Topic detection is carried out to text message, topic detection information is obtained；
Emotion identification is carried out to text message, emotional state information is obtained；
Language performance identification is carried out to text message, language performance information is obtained, characteristic information includes extraction information, topic
Identification information, emotional state information and language performance information；
According to characteristic information, user's history operation information and external information, intention assessment is carried out, specifically included：
According to the information of extraction, topic detection information, emotional state information and language performance information, and user's history operation
Information and external information, carry out intention assessment.
Further, information extraction is carried out to text message, extraction information is obtained, is specifically included：
Word, the meaning of one's words are carried out to text message to extract, and obtain extraction information；
After extraction information is obtained, before carrying out intention assessment, the method also includes：Believed according to text message and extraction
Breath, review text information.
Based on above-mentioned any intension recognizing method embodiment based on various dimensions information, further, text message is entered
Row information is extracted and/or recognized, obtains characteristic information, is specifically included：Topic detection is carried out to current text information, obtains current
Topic information；
Topic detection is carried out to history text information, historical topic information is obtained, text message includes current text information
With history text information, characteristic information include actualite information and historical topic information；
According to characteristic information, user's history operation information and external information, intention assessment is carried out, specifically included：
According to actualite information, historical topic information, user's history operation information and external information, intention knowledge is carried out
Not.
Further, information extraction and/or identification are carried out to text message, characteristic information is obtained, is specifically included：To current
Text message carries out Emotion identification, obtains current emotional information；
Emotion identification is carried out to history text information, history emotional information is obtained, text message includes current text information
With history text information, characteristic information include current emotional information and history emotional information；
According to characteristic information, user's history operation information and external information, intention assessment is carried out, specifically included：
According to current emotional information, history emotional information, user's history operation information and external information, intention knowledge is carried out
Not.
Second aspect, the present invention provides a kind of intention assessment system based on various dimensions information, and the system is obtained including information
Take subsystem, characteristic information and determine subsystem and Intention Anticipation subsystem, information acquisition subsystem is used to obtain the text of user
Information, user's history operation information and external information；Characteristic information determines subsystem for carrying out information extraction to text message
And/or identification, obtain characteristic information；Intention Anticipation subsystem is used for according to characteristic information, user's history operation information and outside
Information, carries out intention assessment, obtains user in predicting and is intended to.
Further, characteristic information determine subsystem specifically for：Information extraction is carried out to text message, is obtained and is extracted letter
Breath；Topic detection is carried out to text message, topic detection information is obtained；Emotion identification is carried out to text message, mood shape is obtained
State information；Language performance identification is carried out to text message, language performance information is obtained, characteristic information includes extraction information, topic
Identification information, emotional state information and language performance information；
Intention Anticipation subsystem specifically for：According to the information of extraction, topic detection information, emotional state information and language row
It is information, and user's history operation information and external information, carry out intention assessment.
Further, characteristic information determines that subsystem is carrying out information extraction to text message, when obtaining extraction information, tool
Body is used for：Word, the meaning of one's words are carried out to text message to extract, and obtain extraction information；The system also includes text amendment subsystem, uses
According to text message and extraction information, review text information.
Based on above-mentioned any intention assessment system embodiment based on various dimensions information, further, characteristic information determines
Subsystem specifically for：Topic detection is carried out to current text information, actualite information is obtained；History text information is carried out
Topic detection, obtains historical topic information, and text message includes current text information and history text information, and characteristic information includes
Actualite information and historical topic information；
Intention Anticipation subsystem specifically for：According to actualite information, historical topic information, user's history operation information
And external information, carry out intention assessment.
Further, characteristic information determine subsystem specifically for：Emotion identification is carried out to current text information, is obtained and is worked as
Preceding emotional information；Emotion identification is carried out to history text information, history emotional information is obtained, text message is believed including current text
Breath and history text information, characteristic information include current emotional information and history emotional information；
Intention Anticipation subsystem specifically for：According to current emotional information, history emotional information, user's history operation information
And external information, carry out intention assessment.
As shown from the above technical solution, intension recognizing method and system of the present invention based on various dimensions information, can pass through
The text message of user is extracted or recognized, obtains characteristic information.Characteristic information and user's history operation letter according to user
Breath, with reference to external information, is identified, it is possible to increase the precision of intention assessment to user view.Also, the method is combined to be used
Family historical operation information, according to the personalized use state of user, it is intended that identification is accurate, reliable, and data-handling efficiency is high, helps
In raising Consumer's Experience.
Therefore, the present invention based on various dimensions information intension recognizing method and system, it is possible to increase intention assessment it is accurate
Degree and data-handling efficiency, prevent Intention Anticipation distortion, strengthen Consumer's Experience.
Brief description of the drawings
In order to illustrate more clearly of the specific embodiment of the invention or technical scheme of the prior art, below will be to specific
The accompanying drawing to be used needed for implementation method or description of the prior art is briefly described.In all of the figs, similar element
Or the general reference by being similar in part is identified.In accompanying drawing, each element or part might not draw according to actual ratio.
Fig. 1 shows a kind of intension recognizing method flow chart based on various dimensions information provided by the present invention；
Fig. 2 shows a kind of intention assessment system structure diagram based on various dimensions information provided by the present invention；
Fig. 3 shows another intention assessment system structure diagram based on various dimensions information provided by the present invention.
Specific embodiment
The embodiment of technical solution of the present invention is described in detail below in conjunction with accompanying drawing.Following examples are only used for
Technical scheme is clearly illustrated, therefore is intended only as example, and protection of the invention can not be limited with this
Scope.
It should be noted that unless otherwise indicated, technical term used in this application or scientific terminology should be this hair
The ordinary meaning that bright one of ordinary skill in the art are understood.
In a first aspect, the embodiment of the present invention provides a kind of intension recognizing method based on various dimensions information, and with reference to Fig. 1, should
Method includes：
Step S1, obtains text message, user's history operation information and the external information of user, wherein, text message can
To be the text sentence of user input, user's history operation information is operate interface, facility information or mobile phone, the computer of user
Etc. the use habit information in operative, external information is use time, place to use or current hot issue, news etc.；
Step S2, information extraction and/or identification are carried out to text message, obtain characteristic information；
Step S3, according to characteristic information, user's history operation information and external information, carries out intention assessment, obtains user
Prediction is intended to.
As shown from the above technical solution, the present embodiment is based on the intension recognizing method of various dimensions information, can be by user
Text message extracted or recognized, obtain characteristic information.Characteristic information and user's history operation information according to user, knot
External information is closed, user view is identified, it is possible to increase the precision of intention assessment.Also, the method combination user go through
History operation information, according to the personalized use state of user, it is intended that identification is accurate, reliable, and data-handling efficiency is high, helps to carry
Consumer's Experience high.
Therefore, the present embodiment be based on various dimensions information intension recognizing method, it is possible to increase the precision of intention assessment and
Data-handling efficiency, prevents Intention Anticipation distortion, strengthens Consumer's Experience.
Specifically, when characteristic information is obtained, it is as follows that the method implements process：
Information extraction is carried out to the text message, extraction information is obtained, here, the meaning of one's words according to text message carries out letter
Breath is extracted；
Topic detection is carried out to text message, topic detection information is obtained, here, the topic according to text message is known
Not, the staple of conversation, secondary topic are such as recognized；
Emotion identification is carried out to text message, emotional state information is obtained；
Language performance identification is carried out to text message, language performance information, such as sentence pattern of text message, the tone is obtained,
Characteristic information includes extraction information, topic detection information, emotional state information and language performance information；
According to characteristic information, user's history operation information and external information, intention assessment is carried out, specifically included：According to carrying
Win the confidence breath, topic detection information, emotional state information and language performance information, and user's history operation information and outside believe
Breath, carries out intention assessment.Meanwhile, the present embodiment be based on various dimensions information intension recognizing method can also according to extract information,
At least one in topic detection information, four kinds of information of emotional state information and language performance information, and combine user's history behaviour
Make information and external information, carry out intention assessment.
Here, the present embodiment be based on various dimensions information intension recognizing method, be capable of identify that or extract user the meaning of one's words,
Many information such as topic, mood and language performance, for intention assessment provides comprehensive, effective Informational support, helps to carry
The degree of accuracy of intention assessment high, prevents Intention Anticipation distortion.
Specifically, when extraction information is obtained, the intension recognizing method that the present embodiment is based on various dimensions information can be directed to
Word, the meaning of one's words are extracted, i.e., word, the meaning of one's words are carried out to text message and is extracted, and obtain extraction information, i.e., with reference to text message
The meaning of one's words is extracted, meanwhile, can also extract keyword, proper noun etc..Obtain extraction information after, carry out intention assessment it
Before, the method also includes：According to text message and extraction information, review text information, i.e., with reference to the context text of text message
Meaning and original statement, the original statement of text message is modified or rewritten, and to be conducive to intention assessment and prediction, reduces meaning
The data processing complex degree of figure identification process.
In order to further improve the accuracy of intention assessment, the method can also be identified to history text information, such as
When carrying out topic detection, the method to implement process as follows：
Topic detection is carried out to current text information, actualite information, such as current staple of conversation, current secondary words is obtained
Topic, current hot issue etc.；
Carry out topic detection to history text information, obtain historical topic information, such as the staple of conversation, current secondary topic,
Topic, hobby topic etc. are often chatted, history text information includes current text information and history text information, and characteristic information includes working as
Preceding topic information and historical topic information；
According to characteristic information, user's history operation information and external information, intention assessment is carried out, specifically included：According to work as
Preceding topic information, historical topic information, user's history operation information and external information, carry out intention assessment.Here, the method energy
The historical topic information of user is enough taken into account, with reference to personalized behaviour in service of the user when different topics are discussed, user's meaning is carried out
Figure identification, helps to strengthen the accuracy of intention assessment.
When such as carrying out Emotion identification, the method to implement process as follows：
Emotion identification is carried out to current text information, current emotional information is obtained；
Emotion identification is carried out to history text information, history emotional information, such as main emotional state of user's history, use is obtained
Secondary emotional state of family history etc., text message includes current text information and history text information, and characteristic information includes current
Emotional information and history emotional information；
According to characteristic information, user's history operation information and external information, intention assessment is carried out, specifically included：According to work as
Preceding emotional information, history emotional information, user's history operation information and external information, carry out intention assessment.Here, the method energy
The history emotional information of user is enough taken into account, the personalized behaviour in service with reference to user under different moods carries out user view knowledge
Not, contribute to strengthen the accuracy of intention assessment.
Specifically, state in realization in processing procedure, the method mainly uses logic rules or machine learning scheduling algorithm, come
The intention of inference user.In the training stage, the method enters row information knowledge through the text message of each user for collecting in advance
Not, extract, obtain extraction information, topic detection information, emotional state information and the language performance information of the user, and the use
The historical operation information and external information at family, intention feedback is carried out to every kind of information, to update ALU number, sequence
Mode or Machine Learning Parameter.For example, actual intention situation according to each user in the training stage and experiment feedback be intended into
Row contrast, if comparing result is inconsistent, updates ALU number, sortord or Machine Learning Parameter, and repeat
It is iterated, when actual intention situation and experiment feedback are intended to uniformity reaches highest, then constitution iteration, and training is completed.
In test phase, when user is input into this paper sentence, we can be trained by passing data and carry out inference.
Second aspect, the embodiment of the present invention provides a kind of intention assessment system based on various dimensions information, with reference to Fig. 2, should
System determines subsystem 2 and Intention Anticipation subsystem 3, information acquisition subsystem 1 including information acquisition subsystem 1, characteristic information
Text message, user's history operation information and external information for obtaining user；Characteristic information determines subsystem 2 for text
This information carries out information extraction and/or identification, obtains characteristic information；Intention Anticipation subsystem 3 is used for according to characteristic information, user
Historical operation information and external information, carry out intention assessment, obtain user in predicting and are intended to.
As shown from the above technical solution, the present embodiment is based on the intention assessment system of various dimensions information, can be by user
Text message extracted or recognized, obtain characteristic information.Characteristic information and user's history operation information according to user, knot
External information is closed, user view is identified, it is possible to increase the precision of intention assessment.Also, system combination user goes through
History operation information, according to the personalized use state of user, it is intended that identification is accurate, reliable, and data-handling efficiency is high, helps to carry
Consumer's Experience high.
Therefore, the present embodiment be based on various dimensions information intention assessment system, it is possible to increase the precision of intention assessment and
Data-handling efficiency, prevents Intention Anticipation distortion, strengthens Consumer's Experience.
It is special with reference to Fig. 3 in order to further improve the accuracy that the present embodiment is based on the intention assessment system of various dimensions information
Reference breath determines that subsystem 2 is capable of identify that many information, and characteristic information determines that subsystem 2 includes information extraction modules, words
Topic identification module, Emotion identification module and language performance identification module, wherein, information extraction modules enter row information to text message
Extract, obtain extraction information；Topic detection module carries out topic detection to text message, obtains topic detection information；Mood is known
Other module carries out Emotion identification to text message, obtains emotional state information；Language performance identification module is carried out to text message
Language performance recognizes that obtain language performance information, characteristic information includes extraction information, topic detection information, emotional state information
With language performance information；Intention Anticipation subsystem 3 specifically for：According to the information of extraction, topic detection information, emotional state information
With language performance information, and user's history operation information and external information, intention assessment is carried out.Here, characteristic information determines
Subsystem 2 is capable of identify that or extracts many information such as the meaning of one's words, topic, mood and the language performance of user, to be intended to know
Comprehensive, effective Informational support is indescribably supplied, contributes to Intention Anticipation subsystem 3 to improve the degree of accuracy of intention assessment, prevent from being intended to
Predicted distortion.
Characteristic information determines that subsystem 2 is carrying out information extraction to text message, when obtaining extraction information, specifically for：
Word, the meaning of one's words are carried out to text message to extract, and obtain extraction information；The system also includes text amendment subsystem, for basis
Text message and extraction information, review text information, to be conducive to intention assessment and prediction, reduce the data of intention assessment process
Treatment complexity.
When topic detection is carried out, characteristic information determine the topic identification module of subsystem 2 specifically for：To current text
Information carries out topic detection, obtains actualite information；Topic detection is carried out to history text information, historical topic letter is obtained
Breath, text message includes current text information and history text information, and characteristic information includes actualite information and historical topic
Information；Intention Anticipation subsystem 3 specifically for：According to actualite information, historical topic information, user's history operation information and
External information, carries out intention assessment.Here, characteristic information determines that subsystem 2 can take into account the historical topic information of user, it is meaning
Figure predicting subsystem 3 provides user the personalized behaviour in service when different topics are discussed, to carry out user view identification, helps
In the accuracy of enhancing intention assessment.
When Emotion identification is carried out, characteristic information determine the Emotion identification module of subsystem 2 specifically for：To current text
Information carries out Emotion identification, obtains current emotional information；Emotion identification is carried out to history text information, history mood letter is obtained
Breath, text message includes current text information and history text information, and characteristic information includes current emotional information and history mood
Information；Intention Anticipation subsystem 3 specifically for：According to current emotional information, history emotional information, user's history operation information and
External information, carries out intention assessment.Here, characteristic information determines that subsystem 2 can take into account the emotional status of user, it is pre- to be intended to
Survey subsystem 3 and user is provided the personalized behaviour in service in different moods, to carry out user view identification, contribute to enhancing to anticipate
Scheme the accuracy of identification.
Finally it should be noted that：Various embodiments above is merely illustrative of the technical solution of the present invention, rather than its limitations；To the greatest extent
Pipe has been described in detail with reference to foregoing embodiments to the present invention, it will be understood by those within the art that：Its according to
The technical scheme described in foregoing embodiments can so be modified, or which part or all technical characteristic are entered
Row equivalent；And these modifications or replacement, the essence of appropriate technical solution is departed from various embodiments of the present invention technology
The scope of scheme, it all should cover in the middle of the scope of claim of the invention and specification.
Claims (10)
1. a kind of intension recognizing method based on various dimensions information, it is characterised in that including：
Obtain text message, user's history operation information and the external information of user；
Information extraction and/or identification are carried out to the text message, characteristic information is obtained；
According to the characteristic information, the user's history operation information and the external information, intention assessment is carried out, obtain user
Prediction is intended to.
2. the intension recognizing method of various dimensions information is based on according to claim 1, it is characterised in that
Information extraction and/or identification are carried out to the text message, characteristic information is obtained, specifically included：
Information extraction is carried out to the text message, extraction information is obtained；
Topic detection is carried out to the text message, topic detection information is obtained；
Emotion identification is carried out to the text message, emotional state information is obtained；
Language performance identification is carried out to the text message, language performance information is obtained, the characteristic information includes the extraction
Information, the topic detection information, the emotional state information and the language performance information；
According to the characteristic information, the user's history operation information and the external information, intention assessment is carried out, specific bag
Include：
According to the extraction information, the topic detection information, the emotional state information and the language performance information, and
The user's history operation information and the external information, carry out intention assessment.
3. the intension recognizing method of various dimensions information is based on according to claim 2, it is characterised in that
Information extraction is carried out to the text message, extraction information is obtained, specifically included：
Word, the meaning of one's words are carried out to the text message to extract, and obtain the extraction information；
After the extraction information is obtained, before carrying out intention assessment, the method also includes：According to the text message and institute
Extraction information is stated, the text message is corrected.
4. the intension recognizing method of various dimensions information is based on according to claim 1, it is characterised in that
Information extraction and/or identification are carried out to the text message, characteristic information is obtained, specifically included：
Topic detection is carried out to current text information, actualite information is obtained；
Topic detection is carried out to history text information, historical topic information is obtained, the text message includes the current text
Information and the history text information, the characteristic information include the actualite information and the historical topic information；
According to the characteristic information, the user's history operation information and the external information, intention assessment is carried out, specific bag
Include：
According to the actualite information, the historical topic information, the user's history operation information and the external information,
Carry out intention assessment.
5. the intension recognizing method of various dimensions information is based on according to claim 1, it is characterised in that
Information extraction and/or identification are carried out to the text message, characteristic information is obtained, specifically included：
Emotion identification is carried out to current text information, current emotional information is obtained；
Emotion identification is carried out to history text information, history emotional information is obtained, the text message includes the current text
Information and the history text information, the characteristic information include the current emotional information and the history emotional information；
According to the characteristic information, the user's history operation information and the external information, intention assessment is carried out, specific bag
Include：
According to the current emotional information, the history emotional information, the user's history operation information and the external information,
Carry out intention assessment.
6. a kind of intention assessment system based on various dimensions information, it is characterised in that including：
Information acquisition subsystem, text message, user's history operation information and external information for obtaining user；
Characteristic information determines subsystem, for carrying out information extraction and/or identification to the text message, obtains characteristic information；
Intention Anticipation subsystem, for according to the characteristic information, the user's history operation information and the external information, entering
Row intention assessment, obtains user in predicting and is intended to.
7. the intention assessment system of various dimensions information is based on according to claim 6, it is characterised in that
The characteristic information determine subsystem specifically for：Information extraction is carried out to the text message, extraction information is obtained；It is right
The text message carries out topic detection, obtains topic detection information；Emotion identification is carried out to the text message, mood is obtained
Status information；Language performance identification is carried out to the text message, language performance information is obtained, the characteristic information includes described
Extraction information, the topic detection information, the emotional state information and the language performance information；
The Intention Anticipation subsystem specifically for：According to the extraction information, the topic detection information, the emotional state
Information and the language performance information, and the user's history operation information and the external information, carry out intention assessment.
8. the intention assessment system of various dimensions information is based on according to claim 7, it is characterised in that
The characteristic information determines that subsystem is carrying out information extraction to the text message, specific to use when obtaining extraction information
In：Word, the meaning of one's words are carried out to the text message to extract, and obtain the extraction information；The system also includes text amendment subsystem
System, for according to the text message and the extraction information, correcting the text message.
9. the intention assessment system of various dimensions information is based on according to claim 6, it is characterised in that
The characteristic information determine subsystem specifically for：Topic detection is carried out to current text information, actualite letter is obtained
Breath；Topic detection is carried out to history text information, historical topic information is obtained, the text message is believed including the current text
Breath and the history text information, the characteristic information include the actualite information and the historical topic information；
The Intention Anticipation subsystem specifically for：According to the actualite information, the historical topic information, the user
Historical operation information and the external information, carry out intention assessment.
10. the intention assessment system of various dimensions information is based on according to claim 6, it is characterised in that the characteristic information
Determine subsystem specifically for：Emotion identification is carried out to current text information, current emotional information is obtained；To history text information
Emotion identification is carried out, history emotional information is obtained, the text message includes the current text information and the history text
Information, the characteristic information includes the current emotional information and the history emotional information；
The Intention Anticipation subsystem specifically for：According to the current emotional information, the history emotional information, the user
Historical operation information and the external information, carry out intention assessment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611075074.7A CN106779817A (en) | 2016-11-29 | 2016-11-29 | Intension recognizing method and system based on various dimensions information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611075074.7A CN106779817A (en) | 2016-11-29 | 2016-11-29 | Intension recognizing method and system based on various dimensions information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106779817A true CN106779817A (en) | 2017-05-31 |
Family
ID=58898442
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611075074.7A Pending CN106779817A (en) | 2016-11-29 | 2016-11-29 | Intension recognizing method and system based on various dimensions information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106779817A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109785681A (en) * | 2019-03-22 | 2019-05-21 | 邱洵 | A kind of English language tutoring system and teaching application method |
| CN109800354A (en) * | 2019-01-09 | 2019-05-24 | 考拉征信服务有限公司 | A kind of resume modification intension recognizing method and system based on the storage of block chain |
| CN109918602A (en) * | 2019-02-26 | 2019-06-21 | 南威软件股份有限公司 | A kind of web data preloading method and system |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS63106042A (en) * | 1986-10-23 | 1988-05-11 | Nippon Telegr & Teleph Corp <Ntt> | Method for recognizing intention of conversation text |
| CN1757030A (en) * | 2002-06-27 | 2006-04-05 | 国际商业机器公司 | Context searchable communications |
| US20120179467A1 (en) * | 2008-12-01 | 2012-07-12 | At&T Intellectual Property I, L. P. | User intention based on n-best list of recognition hypotheses for utterances in a dialog |
| CN102880723A (en) * | 2012-10-22 | 2013-01-16 | 深圳市宜搜科技发展有限公司 | Searching method and system for identifying user retrieval intention |
| CN104951428A (en) * | 2014-03-26 | 2015-09-30 | 阿里巴巴集团控股有限公司 | User intention recognition method and device |
| CN104951433A (en) * | 2015-06-24 | 2015-09-30 | 北京京东尚科信息技术有限公司 | Method and system for intention recognition based on context |
| CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and system based on artificial intelligence |
| CN105183848A (en) * | 2015-09-07 | 2015-12-23 | 百度在线网络技术（北京）有限公司 | Human-computer chatting method and device based on artificial intelligence |
| CN105474166A (en) * | 2013-03-15 | 2016-04-06 | 先进元素科技公司 | Method and system for purposeful computing |
| CN105830118A (en) * | 2013-08-10 | 2016-08-03 | 格林伊登美国控股有限责任公司 | Conversation-like method and apparatus for determining the outcome of an online conversation and through analysis of emotional expressions during the conversation |
| CN106095746A (en) * | 2016-06-01 | 2016-11-09 | 竹间智能科技（上海）有限公司 | Word emotion identification system and method |
-
2016
- 2016-11-29 CN CN201611075074.7A patent/CN106779817A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS63106042A (en) * | 1986-10-23 | 1988-05-11 | Nippon Telegr & Teleph Corp <Ntt> | Method for recognizing intention of conversation text |
| CN1757030A (en) * | 2002-06-27 | 2006-04-05 | 国际商业机器公司 | Context searchable communications |
| US20120179467A1 (en) * | 2008-12-01 | 2012-07-12 | At&T Intellectual Property I, L. P. | User intention based on n-best list of recognition hypotheses for utterances in a dialog |
| CN102880723A (en) * | 2012-10-22 | 2013-01-16 | 深圳市宜搜科技发展有限公司 | Searching method and system for identifying user retrieval intention |
| CN105474166A (en) * | 2013-03-15 | 2016-04-06 | 先进元素科技公司 | Method and system for purposeful computing |
| CN105830118A (en) * | 2013-08-10 | 2016-08-03 | 格林伊登美国控股有限责任公司 | Conversation-like method and apparatus for determining the outcome of an online conversation and through analysis of emotional expressions during the conversation |
| CN104951428A (en) * | 2014-03-26 | 2015-09-30 | 阿里巴巴集团控股有限公司 | User intention recognition method and device |
| CN104951433A (en) * | 2015-06-24 | 2015-09-30 | 北京京东尚科信息技术有限公司 | Method and system for intention recognition based on context |
| CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and system based on artificial intelligence |
| CN105183848A (en) * | 2015-09-07 | 2015-12-23 | 百度在线网络技术（北京）有限公司 | Human-computer chatting method and device based on artificial intelligence |
| CN106095746A (en) * | 2016-06-01 | 2016-11-09 | 竹间智能科技（上海）有限公司 | Word emotion identification system and method |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109800354A (en) * | 2019-01-09 | 2019-05-24 | 考拉征信服务有限公司 | A kind of resume modification intension recognizing method and system based on the storage of block chain |
| CN109918602A (en) * | 2019-02-26 | 2019-06-21 | 南威软件股份有限公司 | A kind of web data preloading method and system |
| CN109785681A (en) * | 2019-03-22 | 2019-05-21 | 邱洵 | A kind of English language tutoring system and teaching application method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7346610B2 (en) | Deriving multiple semantic representations for utterances in a natural language understanding framework | |
| US11663409B2 (en) | Systems and methods for training machine learning models using active learning | |
| US20210406473A1 (en) | System and method for building chatbot providing intelligent conversational service | |
| Fowler et al. | Effects of language modeling and its personalization on touchscreen typing performance | |
| CN106202059B (en) | Machine translation method and machine translation device | |
| US20190180196A1 (en) | Systems and methods for generating and updating machine hybrid deep learning models | |
| CN106649825B (en) | Voice interaction system and creation method and device thereof | |
| US20190179903A1 (en) | Systems and methods for multi language automated action response | |
| WO2019113122A1 (en) | Systems and methods for improved machine learning for conversations | |
| US20160163314A1 (en) | Dialog management system and dialog management method | |
| CN109753560B (en) | Information processing method and device of intelligent question-answering system | |
| CN108255805A (en) | The analysis of public opinion method and device, storage medium, electronic equipment | |
| CN111400340B (en) | Natural language processing method, device, computer equipment and storage medium | |
| CN104679733B (en) | A kind of voice dialogue interpretation method, apparatus and system | |
| CN113901837A (en) | Intention understanding method, device, equipment and storage medium | |
| KR102718809B1 (en) | Counseling Type Classification System | |
| CN106777073A (en) | The automatic method for correcting of wrong word and server in a kind of search engine | |
| CN109977398A (en) | A kind of speech recognition text error correction method of specific area | |
| US20160239470A1 (en) | Context sensitive input tools | |
| CN110060674A (en) | Form management method, apparatus, terminal and storage medium | |
| CN108304424A (en) | Text key word extracting method and text key word extraction element | |
| JP2016157407A (en) | Prior construction method of vocabulary semantic pattern for text analysis and response system | |
| US11562137B2 (en) | System to correct model drift for natural language understanding | |
| CN108280173A (en) | A kind of key message method for digging, medium and the equipment of non-structured text | |
| CN106779817A (en) | Intension recognizing method and system based on various dimensions information |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170531 |
|
| RJ01 | Rejection of invention patent application after publication |