CN106202038A - Synonym method for digging based on iteration and device - Google Patents
Synonym method for digging based on iteration and device Download PDFInfo
- Publication number
- CN106202038A CN106202038A CN201610498013.5A CN201610498013A CN106202038A CN 106202038 A CN106202038 A CN 106202038A CN 201610498013 A CN201610498013 A CN 201610498013A CN 106202038 A CN106202038 A CN 106202038A
- Authority
- CN
- China
- Prior art keywords
- synonym
- candidate
- language material
- group
- pair
- 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
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/247—Thesauruses; Synonyms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
The present invention relates to a kind of synonym method for digging based on iteration and device, wherein, described method includes: according to the problem language material acquisition synonym pair for obtaining answer of user's input;One-to-one relationship according to described synonym centering word obtains the first candidate synonym group;The second candidate synonym group is extracted from more described synonym centering iteration according to described first candidate synonym group;The alignment result in synonymicon is updated according to described first candidate synonym group and described second candidate synonym group.The present invention obtains the first candidate synonym group according to the one-to-one relationship of synonym centering word, to extract the second candidate synonym group according to the first candidate synonym group from more synonym centering iteration, and then the alignment result in renewal synonymicon, it is not needed upon template, VSM or semantic vector synonym word is excavated, synon excavation quantity can be effectively increased, and then promote accuracy rate and the recall rate of semantic matches.
Description
Technical field
The present invention relates to technical field of data processing, particularly relate to a kind of synonym method for digging based on iteration and dress
Put.
Background technology
Along with development and the progress of society of science and technology, intelligent terminal is increasingly becoming for mobile phone, panel computer, intelligent robot etc.
Indispensable instrument in people's study and work.Being searched the content wanted alternately by question and answer is the important of intelligent terminal
One of function.
When user is in the problem of description, in order to the synonym that (including voice mode) query will be inputted with user
The result matched is also contained in interaction feedback recalls, and can use and extend based on the synon request of searching (query), i.e. in profit
Also the synonym of query is utilized to scan for while scanning for query.In order to the mutual middle application at intelligent answer should
Technology, synon excavation is very important element task.
Existing synonym excavates mode and carries out synonym by the dependent probability calculating in corpus between each word
Excavating, but this mode needs to calculate the word in corpus two-by-two, efficiency is the lowest.Additionally, excavation based on template
Mode needs human configuration template, and the synonym accuracy rate of excavation is low;Based on VSM (Vector Space Model, vector space
Model) excavation mode previous work amount big, and Result accuracy rate is low;Excavation mode based on semantic vector needs in a large number
Data and artificial experience.
Summary of the invention
For existing based on template, based on existing for VSM or based on semantic vector synonym method for digging above-mentioned lack
Falling into, the present invention proposes following technical scheme:
A kind of synonym method for digging based on iteration, including:
The problem language material acquisition synonym pair for obtaining answer according to user's input;Wherein, described synonym to for
There is the statement combination that the statement of identical semanteme is constituted;
One-to-one relationship according to described synonym centering word obtains the first candidate synonym group;
The second candidate synonym group is extracted from more described synonym centering iteration according to described first candidate synonym group;
The alignment in synonymicon is updated according to described first candidate synonym group and described second candidate synonym group
Result.
Alternatively, the described problem language material acquisition synonym pair for obtaining answer according to user's input, including:
Described problem corpus expansion is become vector, and problem language material corresponding for the described vector with identical dimensional is determined
For synonym pair;Wherein, the dimension of described vector is the answer of described problem language material.
Alternatively, described by vectorial for described problem corpus expansion one-tenth, including:
According to word-vector word2vec treatment technology or hownet lexical knowledge bank described problem corpus expansion become to
Amount.
Alternatively, the described problem language material acquisition synonym pair for obtaining answer according to user's input, including:
Synonym pair is obtained according to the different problem language materials that user inputs continuously for obtaining answer interested.
Alternatively, the described different problem language materials inputted continuously for obtaining answer interested according to user obtain same
Justice language pair, including:
Overlapping words proportion, grammatical structure similarity and/or problem target according to described different problem language materials are divided
Class result obtains synonym pair from described different problem language materials.
Alternatively, the described problem language material acquisition synonym pair for obtaining answer according to user's input, including:
Input described user carries out pattern recognition, with the knot according to pattern recognition for obtaining the problem language material of answer
Described for the difference with logicality problem language material is defined as synonym pair by fruit.
Alternatively, described described user is inputted carry out pattern recognition for obtaining the problem language material of answer, also include:
Judge whether described problem language material is summarized in a closed set.
Alternatively, described according to described first candidate synonym group and described second candidate synonym group update in dictionary with
The alignment result of justice word, including:
By newly generated synonym to adding described dictionary, and it is that the described unjustified word of sentence of same meaning centering builds alignment
Relation.
A kind of synonym excavating gear based on iteration, including:
Synonym is to acquiring unit, for the problem language material acquisition synonym for obtaining answer according to user's input
Right;Wherein, described synonym is to by having the statement combination that the statement of identical semanteme is constituted;
First phrase acquiring unit, for obtaining the first candidate according to the one-to-one relationship of described synonym centering word
Synonym phrase;
Second phrase acquiring unit, is used for according to described first candidate synonym group from more described synonym centering iteration
Extract the second candidate synonym group;
Alignment result updating block, for according to described first candidate synonym group and described second candidate synonym group more
Alignment result in new synonymicon.
Alternatively, acquiring unit is further used for by described synonym:
Described problem corpus expansion is become vector, and problem language material corresponding for the described vector with identical dimensional is determined
For synonym pair;Wherein, the dimension of described vector is the answer of described problem language material;Or,
Synonym pair is obtained according to the different problem language materials that user inputs continuously for obtaining answer interested;Or,
Input described user carries out pattern recognition, with the knot according to pattern recognition for obtaining the problem language material of answer
Described for the difference with logicality problem language material is defined as synonym pair by fruit.
The synonym method for digging based on iteration of the present invention and device, input problem language material according to user and obtain synonym
Right, and obtain the first candidate synonym group according to the one-to-one relationship of described synonym centering word, with according to described first
Candidate synonym group extracts the second candidate synonym group from more described synonym centering iteration, and then according to described first candidate
Synonym phrase and described second candidate synonym group update the alignment in synonymicon result it is not necessary to based on template, VSM or
Synonym word is excavated by semantic vector, can be effectively increased synon excavation quantity, and then promote the standard of semantic matches
Really rate and recall rate.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
In having technology to describe, the required accompanying drawing used is briefly described, it should be apparent that, the accompanying drawing in describing below is the present invention
Some embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to according to
These accompanying drawings obtain other accompanying drawing.
Fig. 1 is the schematic flow sheet of the synonym method for digging based on iteration of one embodiment of the invention;
Fig. 2 is the structural representation of the synonym excavating gear based on iteration of one embodiment of the 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 the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is explicitly described, it is clear that described embodiment is the present invention
A part of embodiment rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not having
Make the every other embodiment obtained under creative work premise, broadly fall into the scope of protection of the invention.
Fig. 1 is the schematic flow sheet of the synonym method for digging based on iteration of one embodiment of the invention;Such as Fig. 1 institute
Showing, the method includes:
S1: according to the problem language material acquisition synonym pair for obtaining answer of user's input;Wherein, described synonym pair
By having the statement combination that the statement of identical semanteme is constituted;
For example, such as user's input is " Beijing Taxi Industry lease ", " Beijing for obtaining the problem language material of answer
Taxi is leased ";
On this basis, the problem language material inputted according to above-mentioned user obtains the synonym pair with identical semanteme.
S2: obtain the first candidate synonym group according to the one-to-one relationship of described synonym centering word;
Specifically, by by the synonym of above-mentioned acquisition to carrying out aliging the most one to one, will above-mentioned sentence to entering
After row word segmentation processing, former sentence and the target sentence of sentence centering are carried out correspondence, and by a both sides remaining unjustified word respectively
Language aligns.Such as, by former sentence " Beijing Taxi Industry lease " and target sentence " Beijing taxi rent of above-mentioned sentence of same meaning centering
Rent " carry out word segmentation processing acquired results for " Beijing/taxi/lease ", " Beijing/taxi/lease ";And then, by this former sentence and
Target sentence carries out correspondence, then a both sides remaining unjustified word respectively is " taxi " and " taxi ", by the two word
Alignment (i.e. building alignment relation), to obtain the first candidate synonym group.
If it is understood that higher to synon prescription, it is also possible to according to the alignment frequency of synonym phrase or
Extraction context optimizes above-mentioned synonym phrase.
S3: extract the second candidate synonym from more described synonym centering iteration according to described first candidate synonym group
Group;
It is understood that be " taxi-taxi " according to the confirmable first candidate synonym group of above-mentioned steps S2;
Thus can be according to the above-mentioned first same phrase of candidate from more synonyms pair, such as " Beijing Taxi Industry lease " and " north
Capital taxi is hired out " in iteration extract the second candidate synonym group;I.e. the corresponding relation of basis " taxi-taxi " is to above-mentioned synonym
Language, to carrying out word segmentation processing with correspondence, can be drawn into the second candidate synonym group " lease-hire out ".
S4: according to described first candidate synonym group and described second candidate synonym group update in synonymicon right
Neat result.
It is understood that after often performing an above-mentioned steps, wait according to above-mentioned first candidate synonym group and second
Select the acquisition result of synonym phrase, be updated the alignment result in synonymicon processing, it is possible to circulation performs above-mentioned
Step S2 is to many times of step S4, until no longer there is new alignment result.
The synonym method for digging based on iteration of the present embodiment, inputs problem language material according to user and obtains synonym pair,
And obtain the first candidate synonym group according to the one-to-one relationship of described synonym centering word, with according to described first candidate
Synonym phrase extracts the second candidate synonym group from more described synonym centering iteration, and then according to described first candidate's synonym
Phrase and described second candidate synonym group update the alignment in synonymicon result it is not necessary to based on template, VSM or semanteme
Synonym word is excavated by vector, can be effectively increased synon excavation quantity, and then promote the accuracy rate of semantic matches
And recall rate.
As another preferred embodiment, in step S1, the problem language material being used for obtaining answer according to user's input obtains
Synonym pair, can farther include:
S11: described problem corpus expansion is become vector, and will there is the problem language material of the described vector correspondence of identical dimensional
It is defined as synonym pair;Wherein, the dimension of described vector is the answer of described problem language material;
Further, preferred as the present embodiment, above-mentioned become vector specifically to may include that described problem corpus expansion
According to word-vector word2vec treatment technology or hownet lexical knowledge bank described problem corpus expansion become to
Amount.
Preferred as another embodiment, the problem language material for obtaining answer according to user's input described in step S1
Obtain synonym pair, including:
S12: obtain synonym pair according to the different problem language materials that user inputs continuously for obtaining answer interested.
Specifically, if user's search answer to getting dare not interest (the most dissatisfied) time, it will usually by search
Problem statement carries out converting (such as change sentence pattern, summarize semanteme etc.) according to semanteme, thus can be by original the asking of user's input
Problem statement after topic statement and conversion is as synonym pair.
Further, preferred as the present embodiment, above-mentioned according to user for obtaining answer interested and the most defeated
The different problem language materials entered obtain synonym pair, may include that
Overlapping words proportion, grammatical structure similarity and/or problem target according to described different problem language materials are divided
Class result obtains synonym pair from described different problem language materials.
The problem statement " where the native place of Liu Dehua is " that such as inputs continuously according to user, " which the local of Liu Dehua is
In ", can calculate overlapping words " Liu Dehua ", " ", "Yes", " where ";The structure of grammer is identical (is title owner
Pronoun+noun+verb+query pronoun);The target classification of problem is identical (being location category inquiry);Can be according to above-mentioned interior
Acquisition synonym pair is screened in any one or multinomial combination in appearance further.
Preferred as another embodiment, the problem language material for obtaining answer according to user's input described in step S1
Obtain synonym pair, including:
S13: input described user carries out pattern recognition, with according to pattern recognition for obtaining the problem language material of answer
Result the described problem language material of the difference with logicality is defined as synonym pair.
Further, preferred as the present embodiment, the above-mentioned problem language for obtaining answer that described user is inputted
Material carries out pattern recognition, it is also possible to including:
Judge whether described problem language material is summarized in a closed set.
Specifically, the part scene in reality, there is logicality between the different problems of user's search, and
These problems may be summarized in a closed set (i.e. the problematic amount corresponding to same answer is limited).By this
Characteristic, the different problem of didactic extraction in the sequence have same problem, and then it is right to extract synonym office.
It should be noted that above-mentioned sequence includes but not limited to the search journal file of storage in system, and then above-mentioned
The different problem of didactic extraction can be carried out based on historical statistics result, Heuristics etc..
Further, on the basis of above-mentioned each method embodiment, according to described first candidate's synonym described in step S2
In phrase and described second candidate synonym group renewal dictionary, synon alignment is as a result, it is possible to include:
S21: by newly generated synonym to adding described dictionary, and be that the described unjustified word of sentence of same meaning centering builds
Alignment relation.
Fig. 2 is the structural representation of the synonym excavating gear based on iteration of one embodiment of the invention;Such as Fig. 2 institute
Showing, this device includes that synonym is to acquiring unit the 10, first phrase acquiring unit the 20, second phrase acquiring unit 30 and alignment
Result updating block 40, wherein:
Synonym obtains synonym to acquiring unit 10 for the problem language material being used for obtaining answer according to user's input
Right;Wherein, described synonym is to by having the statement combination that the statement of identical semanteme is constituted;
First phrase acquiring unit 20 obtains the first time for the one-to-one relationship according to described synonym centering word
Select synonym phrase;
Second phrase acquiring unit 30 is for according to described first candidate synonym group from more described synonym centerings repeatedly
Generation extraction the second candidate synonym group;
Alignment result updating block 40 is for according to described first candidate synonym group and described second candidate synonym group
Update the alignment result in synonymicon.
Specifically, the problem language material that synonym is used for obtaining answer to acquiring unit 10 according to user's input obtains synonym
Language pair;First phrase acquiring unit 20 obtains the first candidate synonym according to the one-to-one relationship of described synonym centering word
Group;Second phrase acquiring unit 30 extracts second according to described first candidate synonym group from more described synonym centering iteration
Candidate synonym group;Alignment result updating block 40 is according to described first candidate synonym group and described second candidate synonym group
Update the alignment result in synonymicon.
The synonym excavating gear based on iteration of the present embodiment, inputs problem language material according to user and obtains synonym pair,
And obtain the first candidate synonym group according to the one-to-one relationship of described synonym centering word, with according to described first candidate
Synonym phrase extracts the second candidate synonym group from more described synonym centering iteration, and then according to described first candidate's synonym
Phrase and described second candidate synonym group update the alignment in synonymicon result it is not necessary to based on template, VSM or semanteme
Synonym word is excavated by vector, can be effectively increased synon excavation quantity, and then promote the accuracy rate of semantic matches
And recall rate.
Further, preferred as said apparatus embodiment, acquiring unit 10 be can be used for by synonym:
Described problem corpus expansion is become vector, and problem language material corresponding for the described vector with identical dimensional is determined
For synonym pair;Wherein, the dimension of described vector is the answer of described problem language material;Or,
Synonym pair is obtained according to the different problem language materials that user inputs continuously for obtaining answer interested;Or,
Input described user carries out pattern recognition, with the knot according to pattern recognition for obtaining the problem language material of answer
Described for the difference with logicality problem language material is defined as synonym pair by fruit.
Device described in the present embodiment may be used for performing said method embodiment, and its principle is similar with technique effect, this
Place repeats no more.
Device embodiment described above is only schematically, and the wherein said unit illustrated as separating component can
To be or to may not be physically separate, the parts shown as unit can be or may not be physics list
Unit, i.e. may be located at a place, or can also be distributed on multiple NE.Can be selected it according to the actual needs
In some or all of module realize the purpose of the present embodiment scheme.Those of ordinary skill in the art are not paying creativeness
Work in the case of, be i.e. appreciated that and implement.
Through the above description of the embodiments, those skilled in the art it can be understood that to each embodiment can
The mode adding required general hardware platform by software realizes, naturally it is also possible to pass through hardware.Based on such understanding, on
State the part that prior art contributes by technical scheme the most in other words to embody with the form of software product, should
Computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD etc., including some fingers
Make with so that a computer equipment (can be personal computer, server, or the network equipment etc.) performs each and implements
The method described in some part of example or embodiment.
Last it is noted that above example is only in order to illustrate technical scheme, it is not intended to limit;Although
With reference to previous embodiment, the present invention is described in detail, it will be understood by those within the art that: it still may be used
So that the technical scheme described in foregoing embodiments to be modified, or wherein portion of techniques feature is carried out equivalent;
And these amendment or replace, do not make appropriate technical solution essence depart from various embodiments of the present invention technical scheme spirit and
Scope.
Claims (10)
1. a synonym method for digging based on iteration, it is characterised in that including:
The problem language material acquisition synonym pair for obtaining answer according to user's input;Wherein, described synonym is to for having
The statement combination that the statement of identical semanteme is constituted;
One-to-one relationship according to described synonym centering word obtains the first candidate synonym group;
The second candidate synonym group is extracted from more described synonym centering iteration according to described first candidate synonym group;
The alignment result in synonymicon is updated according to described first candidate synonym group and described second candidate synonym group.
Method the most according to claim 1, it is characterised in that the described problem being used for obtaining answer according to user's input
Language material obtains synonym pair, including:
Described problem corpus expansion is become vector, and problem language material corresponding for the described vector with identical dimensional is defined as same
Justice language pair;Wherein, the dimension of described vector is the answer of described problem language material.
Method the most according to claim 2, it is characterised in that described by vectorial for described problem corpus expansion one-tenth, including:
According to word-vector word2vec treatment technology or hownet lexical knowledge bank, described problem corpus expansion is become vector.
Method the most according to claim 1, it is characterised in that the described problem being used for obtaining answer according to user's input
Language material obtains synonym pair, including:
Synonym pair is obtained according to the different problem language materials that user inputs continuously for obtaining answer interested.
Method the most according to claim 4, it is characterised in that described according to user for obtaining answer interested and company
The different problem language materials of continuous input obtain synonym pair, including:
According to the described different overlapping words proportions of problem language material, grammatical structure similarity and/or problem target classification knot
Fruit obtains synonym pair from described different problem language materials.
Method the most according to claim 1, it is characterised in that the described problem being used for obtaining answer according to user's input
Language material obtains synonym pair, including:
Input described user carries out pattern recognition for obtaining the problem language material of answer, will with the result according to pattern recognition
The difference described problem language material with logicality is defined as synonym pair.
Method the most according to claim 6, it is characterised in that described described user is inputted for obtaining asking of answer
Topic language material carries out pattern recognition, also includes:
Judge whether described problem language material is summarized in a closed set.
8. according to the method according to any one of claim 1-7, it is characterised in that described according to described first candidate synonym
Group and described second candidate synonym group update synon alignment result in dictionary, including:
By newly generated synonym to adding described dictionary, and it is that the described unjustified word of sentence of same meaning centering builds alignment pass
System.
9. a synonym excavating gear based on iteration, it is characterised in that including:
Synonym is to acquiring unit, for the problem language material acquisition synonym pair for obtaining answer according to user's input;Its
In, described synonym is to by having the statement combination that the statement of identical semanteme is constituted;
First phrase acquiring unit, for obtaining first candidate's synonym according to the one-to-one relationship of described synonym centering word
Phrase;
Second phrase acquiring unit, for extracting from more described synonym centering iteration according to described first candidate synonym group
Second candidate synonym group;
Alignment result updating block, for updating same according to described first candidate synonym group and described second candidate synonym group
Alignment result in justice word dictionary.
Device the most according to claim 9, it is characterised in that acquiring unit is further used for by described synonym:
Described problem corpus expansion is become vector, and problem language material corresponding for the described vector with identical dimensional is defined as same
Justice language pair;Wherein, the dimension of described vector is the answer of described problem language material;Or,
Synonym pair is obtained according to the different problem language materials that user inputs continuously for obtaining answer interested;Or,
Input described user carries out pattern recognition for obtaining the problem language material of answer, will with the result according to pattern recognition
The difference described problem language material with logicality is defined as synonym pair.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610498013.5A CN106202038A (en) | 2016-06-29 | 2016-06-29 | Synonym method for digging based on iteration and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610498013.5A CN106202038A (en) | 2016-06-29 | 2016-06-29 | Synonym method for digging based on iteration and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106202038A true CN106202038A (en) | 2016-12-07 |
Family
ID=57463495
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610498013.5A Pending CN106202038A (en) | 2016-06-29 | 2016-06-29 | Synonym method for digging based on iteration and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106202038A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106844571A (en) * | 2017-01-03 | 2017-06-13 | 北京齐尔布莱特科技有限公司 | Recognize method, device and the computing device of synonym |
CN109102809A (en) * | 2018-06-22 | 2018-12-28 | 北京光年无限科技有限公司 | A kind of dialogue method and system for intelligent robot |
CN110532547A (en) * | 2019-07-31 | 2019-12-03 | 厦门快商通科技股份有限公司 | Building of corpus method, apparatus, electronic equipment and medium |
CN111488735A (en) * | 2020-04-09 | 2020-08-04 | 中国银行股份有限公司 | Test corpus generation method and device and electronic equipment |
CN112395867A (en) * | 2020-11-16 | 2021-02-23 | 中国平安人寿保险股份有限公司 | Synonym mining method, synonym mining device, synonym mining storage medium and computer equipment |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090182755A1 (en) * | 2008-01-10 | 2009-07-16 | International Business Machines Corporation | Method and system for discovery and modification of data cluster and synonyms |
CN102760134A (en) * | 2011-04-28 | 2012-10-31 | 北京百度网讯科技有限公司 | Method and device for mining synonyms |
CN102999495A (en) * | 2011-09-09 | 2013-03-27 | 北京百度网讯科技有限公司 | Method and device for determining synonym semantics mapping relations |
CN103942339A (en) * | 2014-05-08 | 2014-07-23 | 深圳市宜搜科技发展有限公司 | Synonym mining method and device |
US20150193428A1 (en) * | 2014-01-08 | 2015-07-09 | Electronics And Telecommunications Research Institute | Semantic frame operating method based on text big-data and electronic device supporting the same |
CN105095204A (en) * | 2014-04-17 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Method and device for obtaining synonym |
CN105630938A (en) * | 2015-12-23 | 2016-06-01 | 深圳市智客网络科技有限公司 | Intelligent question-answering system |
-
2016
- 2016-06-29 CN CN201610498013.5A patent/CN106202038A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090182755A1 (en) * | 2008-01-10 | 2009-07-16 | International Business Machines Corporation | Method and system for discovery and modification of data cluster and synonyms |
CN102760134A (en) * | 2011-04-28 | 2012-10-31 | 北京百度网讯科技有限公司 | Method and device for mining synonyms |
CN102999495A (en) * | 2011-09-09 | 2013-03-27 | 北京百度网讯科技有限公司 | Method and device for determining synonym semantics mapping relations |
US20150193428A1 (en) * | 2014-01-08 | 2015-07-09 | Electronics And Telecommunications Research Institute | Semantic frame operating method based on text big-data and electronic device supporting the same |
CN105095204A (en) * | 2014-04-17 | 2015-11-25 | 阿里巴巴集团控股有限公司 | Method and device for obtaining synonym |
CN103942339A (en) * | 2014-05-08 | 2014-07-23 | 深圳市宜搜科技发展有限公司 | Synonym mining method and device |
CN105630938A (en) * | 2015-12-23 | 2016-06-01 | 深圳市智客网络科技有限公司 | Intelligent question-answering system |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106844571A (en) * | 2017-01-03 | 2017-06-13 | 北京齐尔布莱特科技有限公司 | Recognize method, device and the computing device of synonym |
CN106844571B (en) * | 2017-01-03 | 2020-04-07 | 北京齐尔布莱特科技有限公司 | Method and device for identifying synonyms and computing equipment |
CN109102809A (en) * | 2018-06-22 | 2018-12-28 | 北京光年无限科技有限公司 | A kind of dialogue method and system for intelligent robot |
CN110532547A (en) * | 2019-07-31 | 2019-12-03 | 厦门快商通科技股份有限公司 | Building of corpus method, apparatus, electronic equipment and medium |
CN111488735A (en) * | 2020-04-09 | 2020-08-04 | 中国银行股份有限公司 | Test corpus generation method and device and electronic equipment |
CN111488735B (en) * | 2020-04-09 | 2023-10-27 | 中国银行股份有限公司 | Test corpus generation method and device and electronic equipment |
CN112395867A (en) * | 2020-11-16 | 2021-02-23 | 中国平安人寿保险股份有限公司 | Synonym mining method, synonym mining device, synonym mining storage medium and computer equipment |
CN112395867B (en) * | 2020-11-16 | 2023-08-08 | 中国平安人寿保险股份有限公司 | Synonym mining method and device, storage medium and computer equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108874878B (en) | Knowledge graph construction system and method | |
CN106649818B (en) | Application search intention identification method and device, application search method and server | |
CN106202038A (en) | Synonym method for digging based on iteration and device | |
CN106951438A (en) | A kind of event extraction system and method towards open field | |
CN111460798A (en) | Method and device for pushing similar meaning words, electronic equipment and medium | |
CN109325040B (en) | FAQ question-answer library generalization method, device and equipment | |
CN111797214A (en) | FAQ database-based problem screening method and device, computer equipment and medium | |
CN108073568A (en) | keyword extracting method and device | |
CN109947952B (en) | Retrieval method, device, equipment and storage medium based on English knowledge graph | |
CN107168991B (en) | Search result display method and device | |
CN110162768B (en) | Method and device for acquiring entity relationship, computer readable medium and electronic equipment | |
CN103678576A (en) | Full-text retrieval system based on dynamic semantic analysis | |
CN105787134B (en) | Intelligent answer method, apparatus and system | |
CN111414763A (en) | Semantic disambiguation method, device, equipment and storage device for sign language calculation | |
CN105512316A (en) | Knowledge service system combining mobile terminal | |
CN104679731B (en) | Extract the method and device of keyword in the page | |
CN106844571A (en) | Recognize method, device and the computing device of synonym | |
CN103324700A (en) | Noumenon concept attribute learning method based on Web information | |
CN105512347A (en) | Information processing method based on geographic topic model | |
CN107844493A (en) | A kind of file association method and system | |
CN105608075A (en) | Related knowledge point acquisition method and system | |
CN112148886A (en) | Method and system for constructing content knowledge graph | |
CN107480197B (en) | Entity word recognition method and device | |
CN105653576A (en) | Information searching method and apparatus, manual position service method and system | |
CN103076894A (en) | Method and equipment for building input entries for object identity information according to object identity information |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161207 |