CN104572906B - The acquisition methods and equipment of a kind of affair character - Google Patents
The acquisition methods and equipment of a kind of affair character Download PDFInfo
- Publication number
- CN104572906B CN104572906B CN201410828598.3A CN201410828598A CN104572906B CN 104572906 B CN104572906 B CN 104572906B CN 201410828598 A CN201410828598 A CN 201410828598A CN 104572906 B CN104572906 B CN 104572906B
- Authority
- CN
- China
- Prior art keywords
- feature
- words
- object event
- attribute
- word
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 76
- 238000000605 extraction Methods 0.000 claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims description 19
- 238000007621 cluster analysis Methods 0.000 claims description 8
- 230000000052 comparative effect Effects 0.000 claims description 7
- 239000000284 extract Substances 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 12
- 238000012545 processing Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000003860 storage Methods 0.000 description 4
- 206010037660 Pyrexia Diseases 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 206010034719 Personality change Diseases 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000001727 in vivo Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses the acquisition methods and equipment of a kind of affair character, including：Acquisition includes multiple Feature Words for describing the feature set of words of object event in feature set of words；From the feature set of words of acquisition, determine to describe at least one Feature Words of the attribute of object event；For each definite Feature Words, in residue character word from feature set of words in addition to for describing the Feature Words of object event attribute, at least one Feature Words of the particular content for the attribute that this feature word is identified are extracted, and establish the correspondence between definite this feature word and at least one Feature Words of extraction；According at least one set of correspondence is obtained, the feature of object event is obtained, in this way, helping to fully understand the object event, the precision for obtaining object event customized information is improved, lays the foundation subsequently quickly to position the object event.
Description
Technical field
The present invention relates to field of computer technology more particularly to the acquisition methods and equipment of a kind of affair character.
Background technology
In today of Internet technology fast development, user generates substantial amounts of data at application internet.In face of interconnection
The mass data generated on the net, it is desirable to oneself interested event is obtained from mass data.
However, each event possesses customized information, can be distinguished by the customized information of event different
Event.The customized information of event generally comprises the corresponding particular content of attribute of the attribute and event of event.
When handling mass data, by manual identified mode, determine to describe the extraction template of event,
Mass data is matched using definite extraction template, obtains the customized information of interested event.
Wherein, extraction template is the extraction rule for referring to extract the attribute particular content corresponding with the attribute of description event
Then.
But since extraction template used in current is determined by manual type, with the development of event, for
The new feature that event occurs, can not determine the corresponding extraction template of the new feature, cause to handle to mass data in time
When, it obtains that the customized information of interested event is inaccurate, affects judgement of the people to the event.
The content of the invention
In view of this, an embodiment of the present invention provides the acquisition methods and equipment of a kind of affair character, for solving right
When mass data is handled, obtain interested event customized information it is inaccurate the problem of.
In a first aspect, a kind of acquisition methods of affair character are provided, including：
It obtains to describe the feature set of words of object event, wherein, multiple Feature Words are included in the feature set of words；
From the feature set of words of acquisition, determine to describe at least one feature of the attribute of the object event
Word；
For each definite Feature Words, remove to describe the attribute of the object event from the feature set of words
Feature Words outside residue character word in, extract at least one feature of the particular content for the attribute that this feature word is identified
Word, and establish the correspondence between definite this feature word and at least one Feature Words of extraction；
According at least one set of correspondence is obtained, the feature of the object event is obtained.
With reference to first aspect, in the first possible implementation, the method further includes：
The mapping relations that the feature of the object event is established between obtained at least one set of correspondence.
The possible realization method of with reference to first aspect or with reference to first aspect the first, in second of possible reality
In existing mode, from the multiple Feature Words of acquisition, determine to describe at least one spy of the attribute of the object event
Word is levied, including：
For the feature set of words of acquisition, following operation is performed, until determining in the feature set of words all
For describing the Feature Words of the attribute of the object event：
Select any one Feature Words；
Determine context of this feature word of selection in original document；And according to the context, judge
Whether this feature word is for describing the Feature Words of the attribute of the object event；
If this feature word that judging result is selection is for describing the Feature Words of the attribute of the object event, should
Feature Words are labeled as describing the Feature Words of the attribute of the object event, and select next Feature Words, continue to execute
State operation；
If this feature word that judging result is selection is not intended to describe the Feature Words of the attribute of the object event, select
Next Feature Words are selected, continue to execute aforesaid operations.
Second of possible realization method with reference to first aspect, in the third possible realization method, according to described
Context, judge this feature word whether be for describing the Feature Words of the attribute of the object event, including：
According to the context, by syntactic analysis and syntactic analysis, determine whether this feature word is above and below described
The centre word of literary content；
If it is determined that this feature word is the centre word of the context, it is determined that this feature word is for describing the mesh
The Feature Words of the attribute of mark event；
If it is determined that this feature word is not the centre word of the context, it is determined that this feature word is not for for describing
State the Feature Words of the attribute of object event.
Second of possible realization method with reference to first aspect or the third possible realization with reference to first aspect
Mode in the 4th kind of possible realization method, is completely used for describing the target thing in the feature set of words is determined
After the Feature Words of the attribute of part, the method further includes：
Judgement is determined to be completely used in the feature set of words
It is no that there are synonyms；
In judging result there are during synonym, from meeting the multiple for describing the categories of the object event of synonym condition
Property Feature Words in select a Feature Words, as the described object event of multiple Feature Words for meeting synonym condition
Attribute Feature Words.
The possible realization method of with reference to first aspect either with reference to first aspect the first or with reference to first aspect
Second of possible realization method the third possible realization method either with reference to first aspect or with reference to first party
The 4th kind of possible realization method in face in the 5th kind of possible realization method, removes to retouch from the feature set of words
It states in the residue character word outside the Feature Words of the attribute of the object event, extracts the tool for the attribute that this feature word is identified
At least one Feature Words held in vivo, including：
Residue character from the feature set of words in addition to for describing the Feature Words of the attribute of the object event
In word, a Feature Words are selected；
For definite one for describing the Feature Words of the attribute of the object event, according to semantic rules, judge to select
This feature word selected whether be the definite Feature Words hyponym；
If hyponym, it is determined that this feature word selected is the described object event of the definite Feature Words
The particular content of attribute.
The possible realization method of with reference to first aspect either with reference to first aspect the first or with reference to first aspect
Second of possible realization method the third possible realization method either with reference to first aspect or with reference to first party
The 4th kind of possible realization method in face or the 5th kind of possible realization method with reference to first aspect, in the 6th kind of possibility
Realization method in, obtain to describe the feature set of words of object event, including：
When handling mass data, obtain from mass data to describe target thing by cluster analysis mode
Multiple Feature Words of part；
Obtained multiple feature word combinations are obtained describing to the feature set of words of object event.
The possible realization method of with reference to first aspect either with reference to first aspect the first or with reference to first aspect
Second of possible realization method the third possible realization method either with reference to first aspect or with reference to first party
The 4th kind of possible realization method in face the 5th kind of possible realization method either with reference to first aspect or with reference to first
In the 7th kind of possible realization method, at least one set of corresponding pass is obtained in basis for 6th kind of possible realization method of aspect
After system obtains the feature of the object event, the method further includes：
The feature of the object event compared and the feature of the default object event；
According to comparative result, determine to include in the feature of the obtained object event for describing object event
Attribute in, the different category of attribute with including to describe object event in the feature of the default object event
Property；
Using the different attribute determined as the newly-increased attribute of the object event.
Second aspect provides a kind of acquisition equipment of affair character, including：
Acquisition module, for obtaining to describe the feature set of words of object event, wherein, it is wrapped in the feature set of words
Containing multiple Feature Words；
Determining module, for from the feature set of words of acquisition, determining to describe the attribute of the object event
At least one Feature Words；
Abstraction module for being directed to each definite Feature Words, removes to describe described from the feature set of words
In residue character word outside the Feature Words of the attribute of object event, the particular content for the attribute that this feature word is identified is extracted
At least one Feature Words, and establish the correspondence between definite this feature word and at least one Feature Words of extraction；Root
According at least one set of correspondence is obtained, the feature of the object event is obtained.
With reference to second aspect, in the first possible implementation, the acquisition equipment further includes：
Module is established, for the mapping between at least one set of correspondence for establishing the feature of the object event and obtaining
Relation.
With reference to the first possible realization method of second aspect or combination second aspect, in second of possible reality
In existing mode, the determining module specifically for being directed to the feature set of words of acquisition, performs following operation, until determining
Go out in the feature set of words to be completely used for describing the Feature Words of the attribute of the object event：
Select any one Feature Words；
Determine context of this feature word of selection in original document；And according to the context, judge
Whether this feature word is for describing the Feature Words of the attribute of the object event；
If this feature word that judging result is selection is for describing the Feature Words of the attribute of the object event, should
Feature Words are labeled as describing the Feature Words of the attribute of the object event, and select next Feature Words, continue to execute
State operation；
If this feature word that judging result is selection is not intended to describe the Feature Words of the attribute of the object event, select
Next Feature Words are selected, continue to execute aforesaid operations.
It is described to determine in the third possible realization method with reference to second of possible realization method of second aspect
Module, specifically for according to the context, by syntactic analysis and syntactic analysis, determining whether this feature word is described
The centre word of context；
If it is determined that this feature word is the centre word of the context, it is determined that this feature word is for describing the mesh
The Feature Words of the attribute of mark event；
If it is determined that this feature word is not the centre word of the context, it is determined that this feature word is not for for describing
State the Feature Words of the attribute of object event.
With reference to second of possible realization method of second aspect or the third possible realization of combination second aspect
Mode, in the 4th kind of possible realization method, the acquisition equipment further includes：Judgment module, wherein：
The judgment module, for being completely used for describing the category of the object event in the feature set of words is determined
Property Feature Words after, judgement determine to be completely used for describing the feature of the attribute of the object event in the feature set of words
It whether there is synonym in word；
In judging result there are during synonym, from meeting the multiple for describing the categories of the object event of synonym condition
Property Feature Words in select a Feature Words, as the described object event of multiple Feature Words for meeting synonym condition
Attribute Feature Words.
The first possible realization method of second aspect is either combined with reference to second aspect or with reference to second aspect
Second of possible realization method either combine second aspect the third possible realization method or with reference to second party
The 4th kind of possible realization method in face, in the 5th kind of possible realization method, the abstraction module, specifically for from described
In residue character word in feature set of words in addition to for describing the Feature Words of the attribute of the object event, a spy is selected
Levy word；
For definite one for describing the Feature Words of the attribute of the object event, according to semantic rules, judge to select
This feature word selected whether be the definite Feature Words hyponym；
If hyponym, it is determined that this feature word selected is the described object event of the definite Feature Words
The particular content of attribute.
The first possible realization method of second aspect is either combined with reference to second aspect or with reference to second aspect
Second of possible realization method either combine second aspect the third possible realization method or with reference to second party
The 4th kind of possible realization method in face or the 5th kind of possible realization method for combining second aspect, in the 6th kind of possibility
Realization method in, the acquisition module, specifically for when handling mass data, by cluster analysis mode from sea
It measures and the multiple Feature Words for describing object event is obtained in data；
Obtained multiple feature word combinations are obtained describing to the feature set of words of object event.
The first possible realization method of second aspect is either combined with reference to second aspect or with reference to second aspect
Second of possible realization method either combine second aspect the third possible realization method or with reference to second party
The 4th kind of possible realization method in face either combines the 5th kind of possible realization method of second aspect or with reference to second
6th kind of possible realization method of aspect, in the 7th kind of possible realization method, the acquisition equipment further includes：Compare mould
Block, wherein：
The comparison module, for according to obtain at least one set of correspondence obtain the object event feature it
Afterwards, the feature of the object event compared and the feature of the default object event；
According to comparative result, determine to include in the feature of the obtained object event for describing object event
Attribute in, the different category of attribute with including to describe object event in the feature of the default object event
Property；
Using the different attribute determined as the newly-increased attribute of the object event.
The present invention has the beneficial effect that：
The embodiment of the present invention obtains to describe the feature set of words of object event, is included in the feature set of words multiple
Feature Words；From the feature set of words of acquisition, determine to describe at least one feature of the attribute of the object event
Word；For each definite Feature Words, remove to describe the feature of the object event attribute from the feature set of words
In residue character word outside word, at least one Feature Words of the particular content for the attribute that this feature word is identified are extracted, and
Establish the correspondence between definite this feature word and at least one Feature Words of extraction；It is closed according at least one set of correspond to is obtained
System, obtains the feature of the object event, in this way, for magnanimity for describing multiple Feature Words of any one event, dynamically
The Feature Words for describing the attribute of the event and the Feature Words for describing the particular content of the attribute of the event are determined, and
Establish the Feature Words for the attribute for determining to describe the event and the feature for describing the particular content of the attribute of the event
Correspondence between word by obtained multigroup correspondence, determines the feature of object event, helps to fully understand the mesh
Mark event improves the precision for obtaining object event customized information, lays the foundation subsequently quickly to position the object event.
Description of the drawings
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly introduced, it should be apparent that, the accompanying drawings in the following description is only some embodiments of the present invention, for this
For the those of ordinary skill in field, without having to pay creative labor, it can also be obtained according to these attached drawings
His attached drawing.
Fig. 1 is a kind of flow diagram of the acquisition methods of affair character provided in an embodiment of the present invention；
Fig. 2 is a kind of structure diagram of the acquisition equipment of affair character provided in an embodiment of the present invention；
Fig. 3 is a kind of structure diagram of the acquisition equipment of affair character provided in an embodiment of the present invention.
Specific embodiment
In order to achieve the object of the present invention, an embodiment of the present invention provides the acquisition methods and equipment of a kind of affair character,
Acquisition includes multiple Feature Words for describing the feature set of words of object event in the feature set of words；From described in acquisition
In feature set of words, determine to describe at least one Feature Words of the attribute of the object event；For each definite
Feature Words, the residue character word from the feature set of words in addition to for describing the Feature Words of the object event attribute
In, at least one Feature Words of the particular content for the attribute that this feature word is identified are extracted, and establish definite this feature word
Correspondence between at least one Feature Words of extraction；According at least one set of correspondence is obtained, the target thing is obtained
The feature of part, in this way, dynamically determining to describe the event for describing multiple Feature Words of any one event for magnanimity
Attribute Feature Words and Feature Words for describing the particular content of the attribute of the event, and establish and determine to describe this
Feature Words of the attribute of event and for describing the correspondence between the Feature Words of the particular content of the attribute of the event, lead to
The multigroup correspondence crossed determines the feature of object event, helps to fully understand the object event, improves acquisition mesh
The precision of mark event customized information lays the foundation subsequently quickly to position the object event.
The each embodiment of the present invention is described in further detail with reference to Figure of description.Obviously, it is described
Embodiment is only part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, this field
All other embodiment that those of ordinary skill is obtained without making creative work, belongs to protection of the present invention
Scope.
Fig. 1 is a kind of flow diagram of the acquisition methods of affair character provided in an embodiment of the present invention.The method can
With as described below.
Step 101：It obtains to describe the feature set of words of object event.
Wherein, multiple Feature Words are included in the feature set of words.
In a step 101, when handling mass data, by way of cluster analysis, obtained from mass data
It takes in multiple Feature Words of description object event；Obtained multiple feature word combinations are obtained describing to the spy of object event
Levy set of words.
Wherein, the mode of cluster analysis includes at least：Clustering algorithm (English based on distance：K-Means algorithms), it is implicit
Di Li Crays distribution (English：Latent Dirichlet Allocation；Abbreviation：LDA it is a kind of in).
Alternatively, according to the written material of description event, the multiple features for describing the event are sorted out from the written material
The multiple feature word combinations sorted out are obtained describing the feature set of words of the event by word.
It should be noted that the Feature Words that feature set of words includes can be participle, the participle is by segmenting software (example
Such as：Chinese lexical analysis system (English：Institute of Computing Technology Chinese Lexical
Analysis System；Abbreviation：ICTCLAS) etc.) processing obtains；Can be phrase, the phrase to text by passing through shallow-layer
Semantic analysis, chunk parsing obtain；It can also be name entity, such as：Except the mechanism name of traditional name Entity recognition,
Name, name etc. are named outside entity, the name entity being also included in restriction field, song title, singer, concert name etc..
Such as：The feature set of words for obtaining describing singing event is：Music, program, China, Liu Dehua, song,
Film, performance, next life edge, singer, performance, art, model, performer, participation, youth, satellite TV, dancing, contest, party, idol,
Sing, hold, Beijing, the world, the age, creation, the lyrics, concert, the U.S., the birthday, great master, represent, hold, theme, Hong Kong,
Welcome guest, broadcast, artist, attraction, glamour, nationality, broadcast, classics, guitar, singing, moulding, the popular feeling, making, epoch }.
The feature set of words for obtaining describing mobile phone is：{ perfection, water-proof function, IP degree of protection, IP55, brand, behaviour
Make system, screen, battery, continuation of the journey, price, appearance, performance, take pictures, is tonequality, lovely, compact, very comfortable, beautiful, comfortable, clear
Clear, durable, economical, external form, it is quick, very cheap, simple, intact, very big, fine and smooth, bright, ultra-thin, not all right, fever, it is sharp.
Step 102：From the feature set of words of acquisition, determine to describe the attribute of the object event at least
One Feature Words.
In a step 102, for the feature set of words of acquisition, following operation is performed, until determining the feature
It is completely used for describing the Feature Words of the attribute of the object event in set of words：
Select any one Feature Words；
Determine context of this feature word of selection in original document；And according to the context, judge
Whether this feature word is for describing the Feature Words of the attribute of the object event；
If this feature word that judging result is selection is for describing the Feature Words of the attribute of the object event, should
Feature Words are labeled as describing the Feature Words of the attribute of the object event, and select next Feature Words, continue to execute
State operation；
If this feature word that judging result is selection is not intended to describe the Feature Words of the attribute of the object event, select
Next Feature Words are selected, continue to execute aforesaid operations.
Specifically, according to the context, judge whether this feature word is for describing the category of the object event
The Feature Words of property, including：
According to the context, by syntactic analysis and syntactic analysis, determine whether this feature word is above and below described
The centre word of literary content；
If it is determined that this feature word is the centre word of the context, it is determined that this feature word is for describing the mesh
The Feature Words of the attribute of mark event；
If it is determined that this feature word is not the centre word of the context, it is determined that this feature word is not for for describing
State the Feature Words of the attribute of object event.
Specifically, according to the context where the phrase, the syntactic analysis to context and syntax point are passed through
Analysis, judge the phrase whether centered on word, if word centered on obtained phrase, then determine that the phrase belongs to describe event
Attribute Feature Words.
Such as：For the Feature Words " singer " for being used to describe in the feature set of words of singing event, from the upper of original document
Hereafter " in Pekinese's concert, there is the singer from Hong-Kong, wherein there is everybody very favorite song：Next life edge "
In, phrase " singer of Hong-Kong " is analyzed as noun phrase, " singer " is modified in " Hong-Kong " in phrase, that
" singer " is the centre word of phrase, and therefore, " singer " is for describing the Feature Words of the attribute of singing event；Analyze qualifier
Word centered on " song " behind " liking ", therefore, " song " are for describing the feature of the attribute of singing event
Word；…….
In the same way, for the Feature Words for being used to describe in the feature set of words of mobile phone, obtain describing hand
The Feature Words of machine attribute include at least：Price, appearance, screen, battery etc..
Optionally, it is completely used for describing the Feature Words of the attribute of the object event in the feature set of words is determined
When, the method further includes：
Judgement is determined to be completely used in the feature set of words
It is no that there are synonyms；
The spy for being completely used for describing the attribute of the object event in the feature set of words is to determine out in judging result
It levies in word there are during synonym, from the multiple Feature Words for the attribute for describing the object event for meeting synonym condition
Select a Feature Words, the feature of the attribute as the described object event of multiple Feature Words for meeting synonym condition
Word.
For the Feature Words for being used to describe in the feature set of words of singing event, obtain describing the attribute of singing event
Feature Words include at least：Program, song, performer, artist, singer.
Wherein, performer, artist, singer meet synonym condition, then a feature is selected from performer, artist, singer
Word, such as：Performer, then the Feature Words for obtaining describing the attribute of singing event include at least：Program, song, performer.
Step 103：For each definite Feature Words, remove to describe the target thing from the feature set of words
In residue character word outside the Feature Words of the attribute of part, the particular content for the attribute that this feature word is identified is extracted at least
One Feature Words, and establish the correspondence between definite this feature word and at least one Feature Words of extraction.
In step 103, from the feature set of words remove for describe the object event attribute Feature Words it
In outer residue character word, a Feature Words are selected；
For definite one for describing the Feature Words of the attribute of the object event, according to semantic rules, judge to select
This feature word selected whether be the definite Feature Words hyponym；
If hyponym, it is determined that this feature word selected is the described object event of the definite Feature Words
The particular content of attribute.
Specifically, this feature word for judging to select whether for this be used for describe the object event attribute Feature Words
Subordinate concept when can by semantic knowledge-base (such as：WordNet or HowNet) judged.Such as：It is led in music
In domain, the title of song is the subordinate concept of song.
Except the Feature Words of the attribute that is used to describe singing event in feature set of words for being used to describe singing event
Outside residue character word in, it is corresponding for describing singing event for describing the Feature Words of the attribute of singing event " song "
Attribute particular content Feature Words be " next life edge "；It is corresponding for describing the Feature Words of the attribute of singing event " program "
For describing the Feature Words of the particular content of the attribute of singing event as " concert "；For describing the spy of the attribute of singing event
The Feature Words of the particular content of the corresponding attribute for being used to describe singing event of sign word " performer " are " XXX ".
Again for example：In feature set of words for being used to describe mobile phone in addition to being used to describe the Feature Words of mobile phone attribute
Residue character word in, for describe the Feature Words of the attribute of mobile phone " price " it is corresponding for describe mobile phone attribute it is specific
The Feature Words of content are " cheap "；For describing the corresponding attribute for being used to describe mobile phone of the Feature Words of the attribute of mobile phone " appearance "
Particular content Feature Words be " beautiful, ultra-thin "；For describing, the Feature Words of the attribute of mobile phone " screen " are corresponding to be used to retouch
The Feature Words for stating the particular content of the attribute of mobile phone are " bright "；For describing the corresponding use of the Feature Words of the attribute of mobile phone " battery "
In description mobile phone attribute particular content Feature Words be " fever "；For describing the Feature Words of the attribute of mobile phone " waterproof work(
The Feature Words of the particular content of the corresponding attribute for being used to describe mobile phone of energy " are " IP55 "；For describing the spy of the attribute of mobile phone
The Feature Words of the particular content of the corresponding attribute for being used to describe mobile phone of sign word " taking pictures " are " sharp ".
The Feature Words of attribute obtaining each for describing the object event are corresponding to be used to describe the target
During at least one Feature Words of the particular content of the attribute of event, establish to describe the Feature Words of the attribute of the object event
With for describing the correspondence between at least one Feature Words of the particular content of the attribute of the object event.
Step 104：According at least one set of correspondence is obtained, the feature of the object event is obtained.
At step 104, when obtaining the feature of the object event, establish the feature of the object event and obtain
Mapping relations between at least one set of correspondence.
Optionally, when according to obtaining at least one set of correspondence and obtaining the feature of the object event, the method is also
Including：
The feature of the object event compared and the feature of the default object event；
According to comparative result, determine to include in the feature of the obtained object event for describing object event
Attribute in, the different category of attribute with including to describe object event in the feature of the default object event
Property；
Using the different attribute determined as the newly-increased attribute of the object event.
After correspondence between the attribute and the particular content of attribute for obtaining object event, sent out when receiving user
During the searching request sent, the event identifier to be searched and the attribute of the event to be searched that are included in being asked according to described search, profit
With the correspondence between the attribute of the event of storage and the particular content of attribute, determine event to be searched attribute it is specific
Content, and the particular content of the attribute of definite event to be searched is sent to user so that user can quickly understand the thing
Part.
By the scheme of the embodiment of the present invention, obtain to describe the feature set of words of object event, the feature word set
Multiple Feature Words are included in conjunction；From the feature set of words of acquisition, determine to describe the attribute of the object event
At least one Feature Words；For each definite Feature Words, remove to describe the target thing from the feature set of words
In residue character word outside the Feature Words of part attribute, at least the one of the particular content for the attribute that this feature word is identified is extracted
A Feature Words, and establish the correspondence between definite this feature word and at least one Feature Words of extraction；According to obtain to
Few one group of correspondence, obtains the feature of the object event, in this way, the multiple spies for being used to describe any one event for magnanimity
Word is levied, dynamically determines to describe the Feature Words of the attribute of the event and the particular content for describing the attribute of the event
Feature Words, and establish determine to describe the event attribute Feature Words and for describing the specific of the attribute of the event
Correspondence between the Feature Words of content by obtained multigroup correspondence, determines the feature of object event, contributes to complete
Face understands the object event, improves the precision for obtaining object event customized information, subsequently quickly to position the object event
It lays the foundation.
Fig. 2 is a kind of structure diagram of the acquisition equipment of affair character provided in an embodiment of the present invention.The acquisition is set
It is standby to include：Acquisition module 21, determining module 22 and abstraction module 23, wherein：
Acquisition module 21, for obtaining to describe the feature set of words of object event, wherein, in the feature set of words
Include multiple Feature Words；
Determining module 22, for from the feature set of words of acquisition, determining to describe the category of the object event
At least one Feature Words of property；
Abstraction module 23 for being directed to each definite Feature Words, is removed from the feature set of words for describing
It states in the residue character word outside the Feature Words of the attribute of object event, extracts the specific interior of the attribute that this feature word is identified
At least one Feature Words held, and establish the correspondence between definite this feature word and at least one Feature Words of extraction；
According at least one set of correspondence is obtained, the feature of the object event is obtained.
Optionally, the acquisition equipment further includes：Module 24 is established, wherein：
Module 24 is established, for reflecting between at least one set of correspondence for establishing the feature of the object event and obtaining
Penetrate relation.
Specifically, the determining module 22, specifically for being directed to the feature set of words of acquisition, execution is following to be operated,
Until determining to be completely used for describing the Feature Words of the attribute of the object event in the feature set of words：
Select any one Feature Words；
Determine context of this feature word of selection in original document；And according to the context, judge
Whether this feature word is for describing the Feature Words of the attribute of the object event；
If this feature word that judging result is selection is for describing the Feature Words of the attribute of the object event, should
Feature Words are labeled as describing the Feature Words of the attribute of the object event, and select next Feature Words, continue to execute
State operation；
If this feature word that judging result is selection is not intended to describe the Feature Words of the attribute of the object event, select
Next Feature Words are selected, continue to execute aforesaid operations.
Specifically, the determining module 22, specifically for according to the context, passing through syntactic analysis and syntax point
Analysis, determine this feature word whether be the context centre word；
If it is determined that this feature word is the centre word of the context, it is determined that this feature word is for describing the mesh
The Feature Words of the attribute of mark event；
If it is determined that this feature word is not the centre word of the context, it is determined that this feature word is not for for describing
State the Feature Words of the attribute of object event.
Specifically, the acquisition equipment further includes：Judgment module 25, wherein：
The judgment module 25, for being completely used for describing the object event in the feature set of words is determined
After the Feature Words of attribute, judgement is determined to be completely used for describing the spy of the attribute of the object event in the feature set of words
It levies and whether there is synonym in word；
In judging result there are during synonym, from meeting the multiple for describing the categories of the object event of synonym condition
Property Feature Words in select a Feature Words, as the described object event of multiple Feature Words for meeting synonym condition
Attribute Feature Words.
Specifically, the abstraction module 23, specifically for removing to describe the target thing from the feature set of words
In residue character word outside the Feature Words of the attribute of part, a Feature Words are selected；
For definite one for describing the Feature Words of the attribute of the object event, according to semantic rules, judge to select
This feature word selected whether be the definite Feature Words hyponym；
If hyponym, it is determined that this feature word selected is the described object event of the definite Feature Words
The particular content of attribute.
Specifically, the acquisition module 21, specifically for when handling mass data, passing through cluster analysis mode
It obtains to describe multiple Feature Words of object event from mass data；
Obtained multiple feature word combinations are obtained describing to the feature set of words of object event.
Optionally, the acquisition equipment further includes：Comparison module 26, wherein：
The comparison module 26, for according to obtain at least one set of correspondence obtain the object event feature it
Afterwards, the feature of the object event compared and the feature of the default object event；
According to comparative result, determine to include in the feature of the obtained object event for describing object event
Attribute in, the different category of attribute with including to describe object event in the feature of the default object event
Property；
Using the different attribute determined as the newly-increased attribute of the object event.
Acquisition equipment described in the embodiment of the present invention, can be realized by hardware mode, can also be real by software mode
It is existing.For magnanimity for describing multiple Feature Words of any one event, dynamically determine to describe the spy of the attribute of the event
Word and the Feature Words for describing the particular content of the attribute of the event are levied, and establishes and determines to describe the attribute of the event
Feature Words and for describing the correspondence between the Feature Words of the particular content of the attribute of the event, it is more by what is obtained
Group correspondence, determines the feature of object event, helps to fully understand the object event, improves and obtains object event individual character
Change the precision of information, lay the foundation subsequently quickly to position the object event.
Fig. 3 is a kind of structure diagram of the acquisition equipment of affair character provided in an embodiment of the present invention.The acquisition is set
The standby function of possessing foregoing description, may be employed universal computer architecture.The acquisition equipment includes processor 31,32 and of interface
Memory 33.Processor 31 and network interface 32 connect, and are connected with memory 33.Such as bus connection processing can be passed through
Device 31, interface 32 and memory 33.Wherein：
Processor 31 can be central processing unit (English：Central processing unit, abbreviation：CPU) or
It is the combination of CPU and hardware chip.
Interface 32 can be one or more of：Network interface controller (the English of wireline interface is provided：network
Interface controller, abbreviation：NIC), such as Ethernet NIC, the Ethernet NIC can provide copper wire and/or optical fiber
Interface；The NIC of wireless interface, such as WLAN (English are provided：Wireless local area network, abbreviation：
WLAN)NIC。
For storing program code, the processor 31 from memory obtains the program code of storage, presses memory 33
Programmatic agent execution according to acquisition is correspondingly handled.
Memory 33 can be volatile memory (English：Volatile memory), such as random access memory
(English：Random-access memory, abbreviation：RAM)；Or nonvolatile memory (English：non-volatile
Memory), such as read-only memory is (English：Read-only memory, abbreviation：ROM), flash memory (English：flash
Memory), hard disk (English：Hard disk drive, abbreviation：HDD) or solid state disk is (English：Solid-state drive,
Abbreviation：SSD)；Or the combination of the memory of mentioned kind.Memory 33 can also include Content Addressable Memory (English：
Content-addressable memory, abbreviation：CAM).
Specifically, the processor 31 performs the program stored in the memory 33, performs following operation：
It obtains to describe the feature set of words of object event, wherein, multiple Feature Words are included in the feature set of words；
From the feature set of words of acquisition, determine to describe at least one feature of the attribute of the object event
Word；
For each definite Feature Words, remove to describe the attribute of the object event from the feature set of words
Feature Words outside residue character word in, extract at least one feature of the particular content for the attribute that this feature word is identified
Word, and establish the correspondence between definite this feature word and at least one Feature Words of extraction；
According at least one set of correspondence is obtained, the feature of the object event is obtained.
Optionally, the processor 31, is additionally operable to perform：
The mapping relations that the feature of the object event is established between obtained at least one set of correspondence.
Specifically, the processor 31 determines to describe the object event from the multiple Feature Words of acquisition
Attribute at least one Feature Words, including：
For the feature set of words of acquisition, following operation is performed, until determining in the feature set of words all
For describing the Feature Words of the attribute of the object event：
Select any one Feature Words；
Determine context of this feature word of selection in original document；And according to the context, judge
Whether this feature word is for describing the Feature Words of the attribute of the object event；
If this feature word that judging result is selection is for describing the Feature Words of the attribute of the object event, should
Feature Words are labeled as describing the Feature Words of the attribute of the object event, and select next Feature Words, continue to execute
State operation；
If this feature word that judging result is selection is not intended to describe the Feature Words of the attribute of the object event, select
Next Feature Words are selected, continue to execute aforesaid operations.
Specifically, the processor 31 judges whether this feature word is described for describing according to the context
The Feature Words of the attribute of object event, including：
According to the context, by syntactic analysis and syntactic analysis, determine whether this feature word is above and below described
The centre word of literary content；
If it is determined that this feature word is the centre word of the context, it is determined that this feature word is for describing the mesh
The Feature Words of the attribute of mark event；
If it is determined that this feature word is not the centre word of the context, it is determined that this feature word is not for for describing
State the Feature Words of the attribute of object event.
Specifically, the processor 31 is completely used for describing the object event in the feature set of words is determined
After the Feature Words of attribute, the method further includes：
Judgement is determined to be completely used in the feature set of words
It is no that there are synonyms；
In judging result there are during synonym, from meeting the multiple for describing the categories of the object event of synonym condition
Property Feature Words in select a Feature Words, as the described object event of multiple Feature Words for meeting synonym condition
Attribute Feature Words.
Specifically, the processor 31 removes to describe the spy of the attribute of the object event from the feature set of words
It levies in the residue character word outside word, extracts at least one Feature Words of the particular content for the attribute that this feature word is identified,
Including：
Residue character from the feature set of words in addition to for describing the Feature Words of the attribute of the object event
In word, a Feature Words are selected；
For definite one for describing the Feature Words of the attribute of the object event, according to semantic rules, judge to select
This feature word selected whether be the definite Feature Words hyponym；
If hyponym, it is determined that this feature word selected is the described object event of the definite Feature Words
The particular content of attribute.
Specifically, the processor 31 obtains to describe the feature set of words of object event, including：
When handling mass data, obtain from mass data to describe target thing by cluster analysis mode
Multiple Feature Words of part；
Obtained multiple feature word combinations are obtained describing to the feature set of words of object event.
Specifically, the processor 31 according to obtain at least one set of correspondence obtain the object event feature it
Afterwards, the method further includes：
The feature of the object event compared and the feature of the default object event；
According to comparative result, determine to include in the feature of the obtained object event for describing object event
Attribute in, the different category of attribute with including to describe object event in the feature of the default object event
Property；
Using the different attribute determined as the newly-increased attribute of the object event.
It will be understood by those skilled in the art that the embodiment of the present invention can be provided as method, apparatus (equipment) or computer
Program product.Therefore, in terms of the present invention can be used complete hardware embodiment, complete software embodiment or combine software and hardware
Embodiment form.Moreover, the meter for wherein including computer usable program code in one or more can be used in the present invention
The computer journey that calculation machine usable storage medium is implemented on (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of sequence product.
The present invention be with reference to according to the method for the embodiment of the present invention, the flow chart of device (equipment) and computer program product
And/or block diagram describes.It should be understood that each flow in flowchart and/or the block diagram can be realized by computer program instructions
And/or the flow in box and flowchart and/or the block diagram and/or the combination of box.These computer programs can be provided to refer to
The processor of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices is made to generate
One machine so that the instruction generation performed by computer or the processor of other programmable data processing devices is used to implement
The device for the function of being specified in one flow of flow chart or multiple flows and/or one box of block diagram or multiple boxes.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction generation being stored in the computer-readable memory includes referring to
Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or
The function of being specified in multiple boxes.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that counted
Series of operation steps is performed on calculation machine or other programmable devices to generate computer implemented processing, so as in computer or
The instruction offer performed on other programmable devices is used to implement in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although preferred embodiments of the present invention have been described, but those skilled in the art once know basic creation
Property concept, then can make these embodiments other change and modification.So appended claims be intended to be construed to include it is excellent
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
God and scope.In this way, if these modifications and changes of the present invention belongs to the scope of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to comprising including these modification and variations.
Claims (16)
1. a kind of acquisition methods of affair character, which is characterized in that including：
It obtains to describe the feature set of words of object event, wherein, multiple Feature Words are included in the feature set of words；
From the feature set of words of acquisition, determine to describe at least one Feature Words of the attribute of the object event；
For each definite Feature Words, remove to describe the spy of the attribute of the object event from the feature set of words
It levies in the residue character word outside word, extracts at least one Feature Words of the particular content for the attribute that this feature word is identified,
And establish the correspondence between definite this feature word and at least one Feature Words of extraction；
According at least one set of correspondence is obtained, the feature of the object event is obtained.
2. acquisition methods as described in claim 1, which is characterized in that the method further includes：
The mapping relations that the feature of the object event is established between obtained at least one set of correspondence.
3. acquisition methods as claimed in claim 1 or 2, which is characterized in that from the multiple Feature Words of acquisition, determine to use
In at least one Feature Words for the attribute for describing the object event, including：
For the feature set of words of acquisition, following operation is performed, until determining to be completely used in the feature set of words
The Feature Words of the attribute of the object event are described：
Select any one Feature Words；
Determine context of this feature word of selection in original document；And according to the context, judge the spy
Levy whether word is for describing the Feature Words of the attribute of the object event；
If this feature word that judging result is selection is for describing the Feature Words of the attribute of the object event, by this feature
Word is labeled as describing the Feature Words of the attribute of the object event, and selects next Feature Words, continues to execute above-mentioned behaviour
Make；
If this feature word that judging result is selection is not intended to describe the Feature Words of the attribute of the object event, under selection
One Feature Words, continues to execute aforesaid operations.
4. acquisition methods as claimed in claim 3, which is characterized in that according to the context, judge that this feature word is
It is no be for describe the object event attribute Feature Words, including：
According to the context, by syntactic analysis and syntactic analysis, determine whether this feature word is in the context
The centre word of appearance；
If it is determined that this feature word is the centre word of the context, it is determined that this feature word is for describing the target thing
The Feature Words of the attribute of part；
If it is determined that this feature word is not the centre word of the context, it is determined that this feature word is not for describing the mesh
The Feature Words of the attribute of mark event.
5. acquisition methods as claimed in claim 3, which is characterized in that be completely used for retouching in the feature set of words is determined
After the Feature Words for stating the attribute of the object event, the method further includes：
Whether judgement is determined to be completely used in the feature set of words to deposit in the Feature Words for describing the attribute of the object event
In synonym；
In judging result there are during synonym, from meeting the multiple for describing the attributes of the object event of synonym condition
A Feature Words, the category as the described object event of multiple Feature Words for meeting synonym condition are selected in Feature Words
The Feature Words of property.
6. the acquisition methods as described in any in claim 1,2,4 and 5, which is characterized in that removed from the feature set of words
For describing in the residue character word outside the Feature Words of the attribute of the object event, the category that this feature word is identified is extracted
At least one Feature Words of the particular content of property, including：
In residue character word from the feature set of words in addition to for describing the Feature Words of the attribute of the object event,
Select a Feature Words；
For definite one for describing the Feature Words of the attribute of the object event, according to semantic rules, selection is judged
This feature word whether be the definite Feature Words hyponym；
If hyponym, it is determined that this feature word selected for the described object event of the definite Feature Words attribute
Particular content.
7. the acquisition methods as described in claim 1,2,4 and 5 are any, which is characterized in that obtain to describe object event
Feature set of words, including：
When handling mass data, obtain from mass data to describe object event by cluster analysis mode
Multiple Feature Words；
Obtained multiple feature word combinations are obtained describing to the feature set of words of object event.
8. the acquisition methods as described in claim 1,2,4 and 5 are any, which is characterized in that obtain at least one set of correspondence in basis
After relation obtains the feature of the object event, the method further includes：
The feature of the object event compared and the feature of the default object event；
According to comparative result, that determines to include in the feature of the obtained object event is used to describe the category of object event
Property in, the different attribute of attribute with including to describe object event in the feature of the default object event；
Using the different attribute determined as the newly-increased attribute of the object event.
9. a kind of acquisition equipment of affair character, which is characterized in that including：
Acquisition module, for obtaining to describe the feature set of words of object event, wherein, comprising more in the feature set of words
A Feature Words；
Determining module, for from the feature set of words of acquisition, determining to describe the attribute of the object event extremely
Few Feature Words；
Abstraction module for being directed to each definite Feature Words, removes to describe the target from the feature set of words
In residue character word outside the Feature Words of the attribute of event, the particular content for the attribute that this feature word is identified is extracted extremely
Few Feature Words, and establish the correspondence between definite this feature word and at least one Feature Words of extraction；According to
To at least one set of correspondence, the feature of the object event is obtained.
10. equipment is obtained as claimed in claim 9, which is characterized in that the acquisition equipment further includes：
Module is established, is closed for the mapping between at least one set of correspondence for establishing the feature of the object event and obtaining
System.
11. the acquisition equipment as described in claim 9 or 10, which is characterized in that
The determining module specifically for being directed to the feature set of words of acquisition, performs following operation, until determining described
It is completely used for describing the Feature Words of the attribute of the object event in feature set of words：
Select any one Feature Words；
Determine context of this feature word of selection in original document；And according to the context, judge the spy
Levy whether word is for describing the Feature Words of the attribute of the object event；
If this feature word that judging result is selection is for describing the Feature Words of the attribute of the object event, by this feature
Word is labeled as describing the Feature Words of the attribute of the object event, and selects next Feature Words, continues to execute above-mentioned behaviour
Make；
If this feature word that judging result is selection is not intended to describe the Feature Words of the attribute of the object event, under selection
One Feature Words, continues to execute aforesaid operations.
12. equipment is obtained as claimed in claim 11, which is characterized in that
The determining module, specifically for according to the context, by syntactic analysis and syntactic analysis, determining this feature
Word whether be the context centre word；
If it is determined that this feature word is the centre word of the context, it is determined that this feature word is for describing the target thing
The Feature Words of the attribute of part；
If it is determined that this feature word is not the centre word of the context, it is determined that this feature word is not for describing the mesh
The Feature Words of the attribute of mark event.
13. equipment is obtained as claimed in claim 11, which is characterized in that the acquisition equipment further includes：Judgment module,
In：
The judgment module, for being completely used for describing the attribute of the object event in the feature set of words is determined
After Feature Words, judgement is determined to be completely used in the feature set of words in the Feature Words for describing the attribute of the object event
With the presence or absence of synonym；
In judging result there are during synonym, from meeting the multiple for describing the attributes of the object event of synonym condition
A Feature Words, the category as the described object event of multiple Feature Words for meeting synonym condition are selected in Feature Words
The Feature Words of property.
14. the acquisition equipment as described in any in claim 9,10,12 and 13, which is characterized in that
The abstraction module, specifically for from the feature set of words remove for describe the object event attribute feature
In residue character word outside word, a Feature Words are selected；
For definite one for describing the Feature Words of the attribute of the object event, according to semantic rules, selection is judged
This feature word whether be the definite Feature Words hyponym；
If hyponym, it is determined that this feature word selected for the described object event of the definite Feature Words attribute
Particular content.
15. the acquisition equipment as described in any in claim 9,10,12 and 13, which is characterized in that
The acquisition module, specifically for when handling mass data, by cluster analysis mode from mass data
It obtains to describe multiple Feature Words of object event；
Obtained multiple feature word combinations are obtained describing to the feature set of words of object event.
16. the acquisition equipment as described in any in claim 9,10,12 and 13, which is characterized in that the acquisition equipment is also wrapped
It includes：Comparison module, wherein：
The comparison module, for according to obtaining after at least one set of correspondence obtains the feature of the object event, than
The feature of the object event relatively obtained and the feature of the default object event；
According to comparative result, that determines to include in the feature of the obtained object event is used to describe the category of object event
Property in, the different attribute of attribute with including to describe object event in the feature of the default object event；
Using the different attribute determined as the newly-increased attribute of the object event.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410828598.3A CN104572906B (en) | 2014-12-26 | 2014-12-26 | The acquisition methods and equipment of a kind of affair character |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410828598.3A CN104572906B (en) | 2014-12-26 | 2014-12-26 | The acquisition methods and equipment of a kind of affair character |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104572906A CN104572906A (en) | 2015-04-29 |
| CN104572906B true CN104572906B (en) | 2018-05-18 |
Family
ID=53088968
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410828598.3A Expired - Fee Related CN104572906B (en) | 2014-12-26 | 2014-12-26 | The acquisition methods and equipment of a kind of affair character |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104572906B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106294476B (en) * | 2015-06-05 | 2020-10-16 | 北京搜狗科技发展有限公司 | Feature word relation obtaining method and device |
| CN105589950B (en) * | 2015-12-18 | 2018-12-25 | 百度在线网络技术（北京）有限公司 | Event attribute sentence is determining and is based on event attribute sentence method for early warning and device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1407483A (en) * | 2001-09-04 | 2003-04-02 | 优网通国际资讯股份有限公司 | Text expression method and system and text translation method and system |
| CN101853298A (en) * | 2010-05-26 | 2010-10-06 | 上海大学 | Event-oriented query expansion method |
| JP2014191550A (en) * | 2013-03-27 | 2014-10-06 | Intelligent Wave Inc | Content search server, content search device, and content search method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8301633B2 (en) * | 2007-10-01 | 2012-10-30 | Palo Alto Research Center Incorporated | System and method for semantic search |
| US9244924B2 (en) * | 2012-04-23 | 2016-01-26 | Sri International | Classification, search, and retrieval of complex video events |
-
2014
- 2014-12-26 CN CN201410828598.3A patent/CN104572906B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1407483A (en) * | 2001-09-04 | 2003-04-02 | 优网通国际资讯股份有限公司 | Text expression method and system and text translation method and system |
| CN101853298A (en) * | 2010-05-26 | 2010-10-06 | 上海大学 | Event-oriented query expansion method |
| JP2014191550A (en) * | 2013-03-27 | 2014-10-06 | Intelligent Wave Inc | Content search server, content search device, and content search method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104572906A (en) | 2015-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110543574B (en) | Knowledge graph construction method, device, equipment and medium | |
| CN107423363B (en) | Artificial intelligence based word generation method, device, equipment and storage medium | |
| CN104484411B (en) | A kind of construction method of the semantic knowledge-base based on dictionary | |
| Jo et al. | Aspect and sentiment unification model for online review analysis | |
| KR20210116379A (en) | Method, apparatus for text generation, device and storage medium | |
| US20200151277A1 (en) | Generating three-dimensional digital content from natural language requests | |
| Chang et al. | The prompt artists | |
| CN110097085A (en) | Lyrics document creation method, training method, device, server and storage medium | |
| CN104866511B (en) | A kind of method and apparatus of addition multimedia file | |
| WO2020232796A1 (en) | Multimedia data matching method and device, and storage medium | |
| CN107992585A (en) | Universal tag method for digging, device, server and medium | |
| CN109410913B (en) | Voice synthesis method, device, equipment and storage medium | |
| CN101840414A (en) | Create the equipment and the method for animation from network text | |
| CN108334601A (en) | Song recommendations method, apparatus and storage medium based on label topic model | |
| CN104978332B (en) | User-generated content label data generation method, device and correlation technique and device | |
| CN107092605A (en) | A kind of entity link method and device | |
| CN112836487A (en) | Automatic comment method and device, computer equipment and storage medium | |
| CN110472043A (en) | A kind of clustering method and device for comment text | |
| CN106528538A (en) | Method and device for intelligent emotion recognition | |
| CN106021234A (en) | Label extraction method and system | |
| CN109472008A (en) | A kind of Text similarity computing method, apparatus and electronic equipment | |
| CN110210038A (en) | Kernel entity determines method and its system, server and computer-readable medium | |
| CN108170845A (en) | Multimedia data processing method, device and storage medium | |
| CN104572906B (en) | The acquisition methods and equipment of a kind of affair character | |
| CN106502987B (en) | A kind of method and apparatus that the sentence template based on seed sentence is recalled |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180518 |