CN106095748A - A kind of method and device generating event relation collection of illustrative plates - Google Patents
A kind of method and device generating event relation collection of illustrative plates Download PDFInfo
- Publication number
- CN106095748A CN106095748A CN201610394465.9A CN201610394465A CN106095748A CN 106095748 A CN106095748 A CN 106095748A CN 201610394465 A CN201610394465 A CN 201610394465A CN 106095748 A CN106095748 A CN 106095748A
- Authority
- CN
- China
- Prior art keywords
- name
- statement
- personage
- role
- relation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/211—Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
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 provides a kind of method and device generating event relation collection of illustrative plates, and wherein method includes: according to default punctuation mark, manuscript is split as statement;Extract the personage in the statement after splitting, filter out the statement comprising described personage as standby statement;Described personage includes at least one in name, role and personal pronoun;Utilize the syntactic analysis treebank being obtained ahead of time that described standby statement is carried out syntactic analysis, generate the incidence relation between described personage;Described personage and described incidence relation is utilized to generate event relation collection of illustrative plates.Utilize this method can check event between personage intuitively, it is possible to make user utilize relatively short period of time to understand the purport of event, save reading time.
Description
Technical field
The present invention relates to Internet technical field, particularly relate to a kind of method and device generating event relation collection of illustrative plates.
Background technology
Along with developing rapidly of the Internet, people are to check event by the Internet.But on the Internet all kinds of too
Many, it is unfavorable for that user's fast browsing is watched.More particularly with the personage in event, when relation is intricate, user need by
Entire chapter reads the complete main contents that could understand.Some content complexity, also it is difficult to understand the purport of event by summary.
Therefore, those skilled in the art need to provide a kind of method, it is possible to make user utilize relatively short period of time to understand event
Purport, save reading time.
Summary of the invention
In order to solve above technical problem present in prior art, the present invention provides a kind of event relation collection of illustrative plates that generates
Method and device, it is possible to make user utilize relatively short period of time to understand the purport of event, save reading time.
The present invention provides a kind of method generating event relation collection of illustrative plates, including:
Manuscript is split as statement according to default punctuation mark;
Extract the personage in the statement after splitting, filter out the statement comprising described personage as standby statement;Described people
Thing includes at least one in name, role and personal pronoun;
Utilize the syntactic analysis treebank being obtained ahead of time that described standby statement is carried out syntactic analysis, generate between described personage
Incidence relation;
Described personage and described incidence relation is utilized to generate event relation collection of illustrative plates.
Preferably, before utilizing the syntactic analysis treebank being obtained ahead of time that described standby statement is carried out syntactic analysis, also
Including:
When the described name in manuscript exists corresponding role, extract the role that described name is corresponding, record described people
Corresponding relation between name and role;According to the corresponding relation between described name and role, it is corresponding by described role transforming
Name;
When personal pronoun occurs in the described name in manuscript, extracting the personal pronoun that described name is corresponding, record is described
Corresponding relation between name and personal pronoun;According to the corresponding relation between described name and personal pronoun, by described person
Pronoun is converted to the name of correspondence.
Preferably, the personage in the described statement extracted after splitting, specifically include:
Utilize natural language processing technique that the statement after splitting is carried out the vocabulary after participle obtains participle;
The personage in described vocabulary is extracted according to part of speech.
Preferably, described extract the personage in described vocabulary according to part of speech after, also include:
When described personage includes name and role and when described role is adjacent with described name, record this name and role
Between corresponding relation;
The personage presented in described event relation collection of illustrative plates includes described name and role, and described role is as described name
Attribute.
Preferably, the syntactic analysis treebank that described utilization is obtained ahead of time carries out syntactic analysis to described standby statement, specifically
For:
Utilize the syntactic analysis treebank being obtained ahead of time based on maximum entropy algorithm, condition random field algorithm or neural network algorithm
Described standby statement is carried out syntactic analysis.
The embodiment of the present invention also provides for a kind of device generating event relation collection of illustrative plates, including: statement splits module, standby language
Sentence screening module, incidence relation generation module and relation map generation module;
Described statement splits module, for manuscript is split as statement according to default punctuation mark;
Described standby statement screening module, the personage in statement after extracting fractionation, filter out and comprise described personage
Standby statement;Described personage includes at least one in name, role and personal pronoun;
Described incidence relation generation module, for utilizing the syntactic analysis treebank being obtained ahead of time to carry out described standby statement
Syntactic analysis, generates the incidence relation between described personage;
Described relation map generation module, is used for utilizing described personage and described incidence relation to generate event relation collection of illustrative plates.
Preferably, also include: corresponding relation the first logging modle, corresponding relation the second logging modle, the first modular converter
With the second modular converter;
Described corresponding relation the first logging modle, for when the described name in manuscript exists corresponding role, extracting
The role that described name is corresponding, records the corresponding relation between described name and role;
Described first modular converter, for according to the corresponding relation between described name and role, by described role transforming
For corresponding name;
Described corresponding relation the second logging modle, for when personal pronoun occurs in the described name in manuscript, extracts institute
State the personal pronoun that name is corresponding, record the corresponding relation between described name and personal pronoun;
Described second modular converter, for according to the corresponding relation between described name and personal pronoun, by described person
Pronoun is converted to the name of correspondence.
Preferably, described standby statement screening module includes splitting submodule and extracting submodule;
Described fractionation submodule, obtains participle for utilizing natural language processing technique that the statement after splitting is carried out participle
After vocabulary;
Described extraction submodule, for extracting the personage in described vocabulary according to part of speech.
Preferably, also include: attribute modify module, for when described personage includes name and role and described role with
When described name is adjacent, record the corresponding relation between this name and role;The personage's bag presented in described event relation collection of illustrative plates
Including described name and role, described role is as the attribute of described name.
Preferably, described relation map generation module is specifically for utilizing the syntactic analysis treebank being obtained ahead of time based on maximum
Entropy algorithm, condition random field algorithm or neural network algorithm carry out syntactic analysis to described standby statement.
Compared with prior art, the present invention at least has the advantage that
Manuscript is split as statement according to default punctuation mark, then extracts the personage in the statement after splitting, filter out
Comprise the statement of described personage as standby statement;Utilize the syntactic analysis treebank being obtained ahead of time that described standby statement is carried out sentence
Method is analyzed, it is thus achieved that the incidence relation between described personage;Described personage and described incidence relation is utilized to generate event relation collection of illustrative plates.
Utilize this method can check event between personage intuitively, it is possible to make user utilize relatively short period of time to understand event
Purport, saves reading time.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present application 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 only this
Some embodiments described in application, for those of ordinary skill in the art, on the premise of not paying creative work,
Other accompanying drawing can also be obtained according to these accompanying drawings.
Embodiment of the method one flow chart generating event relation collection of illustrative plates that Fig. 1 provides for the present invention;
A kind of relation map embodiment that Fig. 2 provides for the present invention;
Embodiment of the method two flow chart generating event relation collection of illustrative plates that Fig. 3 provides for the present invention;
The another kind of relation map embodiment that Fig. 4 provides for the present invention;
Device embodiment one schematic diagram generating event relation collection of illustrative plates that Fig. 5 provides for the present invention;
Device embodiment two schematic diagram generating event relation collection of illustrative plates that Fig. 6 provides for the present invention.
Detailed description of the invention
In order to make those skilled in the art be more fully understood that the present invention program, below in conjunction with in the embodiment of the present invention
Accompanying drawing, is clearly and completely described the technical scheme in the embodiment of the present invention, it is clear that described embodiment is only this
Invent a part of embodiment rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art exist
Do not make the every other embodiment obtained under creative work premise, broadly fall into the scope of protection of the invention.
Embodiment of the method one:
Seeing Fig. 1, this figure is embodiment of the method one flow chart generating event relation collection of illustrative plates that the present invention provides.
The method generating event relation collection of illustrative plates that the present embodiment provides, including:
S101: manuscript is split as statement according to default punctuation mark;
It should be noted that the method that the present embodiment provides is to be split as long sentence for the disassembly principle of manuscript, i.e. for
Punctuation mark is that the sentence of comma, colon, pause mark etc. does not splits.Such as, default punctuation mark may include that fullstop, sense
Exclamation, question mark and branch.Occur that the statement acquiescence presetting punctuation mark is a complete long sentence, can split.
S102: extract the personage in the statement after splitting, filter out the statement comprising described personage as standby statement;Institute
State personage and include at least one in name, role and personal pronoun;
Can extract personage therein for the statement after each fractionation, personage is probably with name appearance, it is also possible to
Occur with role, it is also possible to personal pronoun occurs.Such as, name occurs that: king so-and-so, Zhang etc.;Role
Occur that: judge, police, manager etc..Personal pronoun occurs that: he, she, it etc..As long as statement includes of the above
At least one then illustrates that guarantor comprises personage, then screened by such statement.
It is understood that what the relation map of event presented is personage and event, therefore, for not including the language of personage
Sentence can be rejected, and only retains the statement comprising personage.
S103: utilize the syntactic analysis treebank being obtained ahead of time that described standby statement is carried out syntactic analysis, generate described people
Incidence relation between thing;
It should be noted that carry out, for statement, the technology that syntactic analysis is comparative maturity based on syntactic analysis treebank,
This repeats no more.
Syntactic analysis treebank includes three kinds at present, respectively Harbin Institute of Technology, Tsing-Hua University and Binzhou syntactic analysis treebank, it is possible to use
Any one in these three.
Utilize the syntactic analysis treebank being obtained ahead of time based on maximum entropy algorithm, condition random field algorithm or neural network algorithm
Described standby statement is carried out syntactic analysis.
It is understood that the incidence relation between personage is primarily to extract verb.
S104: utilize described personage and described incidence relation to generate event relation collection of illustrative plates.
Such as: the statement after fractionation is: certain company manager king so-and-so bribe judge's Zhang N ten thousand RMB.Public procurator Zhao
So-and-so reports that Zhang accepts bribes.
The personage occurred in this statement is: king so-and-so, Zhang and Zhao so-and-so;
Incidence relation between personage is: bribes, accept bribes, report.
Event relation collection of illustrative plates according to personage and incidence relation generation is as shown in Figure 2.
The method that the present embodiment provides, is split as statement to manuscript according to default punctuation mark, then extracts after splitting
Personage in statement, filters out the statement comprising described personage as standby statement;Utilize the syntactic analysis treebank being obtained ahead of time
Described standby statement is carried out syntactic analysis, it is thus achieved that the incidence relation between described personage;Utilize described personage and described association
Relation generates event relation collection of illustrative plates.Utilize this method can check event between personage intuitively, it is possible to make user's profit
Understand the purport of event by relatively short period of time, save reading time.
Embodiment of the method two:
Seeing Fig. 3, this figure is embodiment of the method two flow chart generating event relation collection of illustrative plates that the present invention provides.
It should be noted that in order to name, role and personal pronoun are merged duplicate removal, the present embodiment also includes from manuscript
Role that middle extraction name is corresponding and personal pronoun.
It addition, for the relation making reader be more fully understood that between personage and role, the present invention is generating event relation figure
Time spectrum, added role before name, will role as the attribute of name, such as, judge Zhang.Judge is Zhang
Attribute.
In the present embodiment, S201 with S101 is identical, does not repeats them here.
S202: utilize natural language processing technique that the statement after splitting is carried out the vocabulary after participle obtains participle;According to
Part of speech extracts the personage in described vocabulary;Filter out the statement comprising described personage as standby statement;
It is understood that utilize natural language processing technique to carry out participle belong to prior art, specifically the most superfluous at this
State.
Such as, so-and-so and king of Lee so-and-so meet with robbery at the train station.After participle be: Lee so-and-so, and, king so-and-so, at, train
Stand, meet with, plunder.
The classification of part of speech includes: name, conjunction, verb, noun and preposition etc..
Such as, so-and-so and king of Lee so-and-so be all name.
As long as it is understood that the statement that screening comprises personage refers to comprise in this statement one as standby statement
Personage just screens as standby statement, is not the statement comprising all personages.I.e. filter out and protect at least one personage's
Statement is as standby statement.
S203: when the described name in manuscript exists corresponding role, extract the role that described name is corresponding, record institute
State the corresponding relation between name and role;According to the corresponding relation between described name and role, by described role transforming it is
Corresponding name;
Such as, public procurator Zhao so-and-so, wherein public procurator is the role of this personage of Zhao.
This step records the corresponding relation between name and role, partly in order to merge duplicate removal, due to a literary composition
In original text, the address for same personage may be different.Sometimes use role, sometimes use name, sometimes use personal pronoun.For
Accurately present event relation collection of illustrative plates, need the address of same personage is merged duplicate removal.
Such as: judge king so-and-so point out ...;Judge points out ...;Role is converted into name.
On the other hand, set up the corresponding relation between name and role, also for when presenting event relation collection of illustrative plates, people
Add the role of correspondence before Ming, be so conducive to the role of user's intuitivism apprehension name.
S204: when personal pronoun occurs in the described name in manuscript, extract the personal pronoun that described name is corresponding, record
Corresponding relation between described name and personal pronoun;According to the corresponding relation between described name and personal pronoun, by described
Personal pronoun is converted to the name of correspondence.
Such as, judge king so-and-so because ...;He is described during accepting bribes according to him ...;Therefore can be by personal pronoun
" he " is converted to " king so-and-so ", it is achieved merge duplicate removal.
When implementing, when finding statement exists personal pronoun, find adjacent statement up or down, according to semanteme
Relation, obtain upper one or in next occur name, and personal pronoun is converted to correspondence name.
S205-S206 is identical with S103-S104 respectively, does not repeats them here.
In order to make those skilled in the art be more fully understood that the method that the present embodiment is introduced, it is exemplified below.
Manuscript example:
In evening March 18, above-mentioned 4 people drive black Cadillac SUV, knock 7 years old boy near the Guo Dian of Jinan on road away
Little family grinds, and escapes after child is thrown into the street greenbelt.Accident driver is that the student enrollment of 20 years old pacifies certain, discards child person
Big for car owner Zhang, two people system friendss.At that time, separately there is 8 years old child in accident car, and it is shocking: incident
Second day, 4 people in car, also with 8 years old child of this name, went to the Ou Lebao recreation ground being positioned at Qihe to play calmly.
First, first participle, judge personage according to part of speech after participle, including name, role's (position).
(7 years old) boy, little family grinds, (child), and (student enrollment) pacifies certain, and (car owner) Zhang is big, (8 years old) child.
Second, screen standby statement according to personage, from standby statement, obtain the incidence relation between personage;
Pacify certain-> and knock 7 years old boy of-> away;
Pacify certain-> to knock the little family of-> away and grind;
Big-the > of Zhang discards-> child;
Pacify certain-> friend-> Zhang big;
XX-> is with-> (8 years old) child.
3rd, merge duplicate removal, be name by role transforming, personal pronoun is converted to name;
Pacify certain-> to knock-> (7 years old boy) little family away and grind;
Big-the > of Zhang discards-> (child) (7 years old boy) little family and grinds;
Pacify certain-> friend-> Zhang big;
XX-> is with-> (8 years old) child.
4th, generate event relation collection of illustrative plates, specifically may refer to Fig. 4.
It should be noted that second and the 3rd sequencing can overturn, i.e. can first merge duplicate removal, reentry personage
Between incidence relation.Can also first obtain the incidence relation between personage, remerge duplicate removal.
It is understood that the method that above example provides, in order to accurately present relation map, personage is closed
And duplicate removal.Further, the method is applicable not only to news report manuscript, but also is applicable to public security class notes, court judgment meeting
Record etc..
A kind of method generating event relation collection of illustrative plates provided based on above example, the present invention also provides for a kind of generation thing
The device of part relation map, is described in detail below in conjunction with the accompanying drawings.
Device embodiment one:
Seeing Fig. 5, this figure is device embodiment one schematic diagram generating event relation collection of illustrative plates that the present invention provides.
The device generating event relation collection of illustrative plates that the present embodiment provides, including: statement splits module 501, standby statement sieve
Modeling block 502, incidence relation generation module 503 and relation map generation module 504;
Described statement splits module 501, for manuscript is split as statement according to default punctuation mark;
It should be noted that the method that the present embodiment provides is to be split as long sentence for the disassembly principle of manuscript, i.e. for
Punctuation mark is that the sentence of comma, colon, pause mark etc. does not splits.Such as, default punctuation mark may include that fullstop, sense
Exclamation, question mark and branch.Occur that the statement acquiescence presetting punctuation mark is a complete long sentence, can split.
Described standby statement screening module 502, the personage in statement after extracting fractionation, filter out and comprise described people
The standby statement of thing;Described personage includes at least one in name, role and personal pronoun;
Personage therein can be extracted for the statement after each fractionation,.Statement containing personage is screened.
It is understood that what the relation map of event presented is personage and event, therefore, for not including the language of personage
Sentence can be rejected, and only retains the statement comprising personage.
Described incidence relation generation module 503, for utilizing the syntactic analysis treebank being obtained ahead of time to described standby statement
Carry out syntactic analysis, generate the incidence relation between described personage;
It should be noted that carry out, for statement, the technology that syntactic analysis is comparative maturity based on syntactic analysis treebank,
This repeats no more.
Syntactic analysis treebank includes three kinds at present, respectively Harbin Institute of Technology, Tsing-Hua University and Binzhou syntactic analysis treebank, it is possible to use
Any one in these three.
Utilize the syntactic analysis treebank being obtained ahead of time based on maximum entropy algorithm, condition random field algorithm or neural network algorithm
Described standby statement is carried out syntactic analysis.
It is understood that the incidence relation between personage is primarily to extract verb.
Described relation map generation module 504, is used for utilizing described personage and described incidence relation to generate event relation figure
Spectrum.
Such as: the statement after fractionation is: certain company manager king so-and-so bribe judge's Zhang N ten thousand RMB.Public procurator Zhao
So-and-so reports that Zhang accepts bribes.
The personage occurred in this statement is: king so-and-so, Zhang and Zhao so-and-so;
Incidence relation between personage is: bribes, accept bribes, report.
Event relation collection of illustrative plates according to personage and incidence relation generation is as shown in Figure 2.
The device that the present embodiment provides, is split as statement to manuscript according to default punctuation mark, then extracts after splitting
Personage in statement, filters out the statement comprising described personage as standby statement;Utilize the syntactic analysis treebank being obtained ahead of time
Described standby statement is carried out syntactic analysis, it is thus achieved that the incidence relation between described personage;Utilize described personage and described association
Relation generates event relation collection of illustrative plates.Utilize this method can check event between personage intuitively, it is possible to make user's profit
Understand the purport of event by relatively short period of time, save reading time.
Device embodiment two:
Seeing Fig. 6, this figure is device embodiment two schematic diagram generating event relation collection of illustrative plates that the present invention provides.
It should be noted that in order to name, role and personal pronoun are merged duplicate removal, the present embodiment also includes from manuscript
Role that middle extraction name is corresponding and personal pronoun.
It addition, for the relation making reader be more fully understood that between name and role, the present invention is generating event relation figure
Time spectrum, added role before name, will role as the attribute of name, such as, judge Zhang.Judge is Zhang
Attribute.
The device generating event relation collection of illustrative plates that the embodiment of the present invention provides, also includes: corresponding relation the first logging modle
601, the first modular converter 602, corresponding relation the second logging modle 603 and the second modular converter 604;
Described corresponding relation the first logging modle 601, for when the described name in manuscript exists corresponding role, carrying
Take the role that described name is corresponding, record the corresponding relation between described name and role;
Described first modular converter 602, for according to the corresponding relation between described name and role, turns described role
It is changed to the name of correspondence;
Described corresponding relation the second logging modle 603, for when personal pronoun occurs in the described name in manuscript, extracts
The personal pronoun that described name is corresponding, records the corresponding relation between described name and personal pronoun;
Described second modular converter 604, for according to the corresponding relation between described name and personal pronoun, by described people
Pronoun is claimed to be converted to the name of correspondence.
It is understood that utilize natural language processing technique to carry out participle belong to prior art, specifically the most superfluous at this
State.
Such as, so-and-so and king of Lee so-and-so meet with robbery at the train station.After participle be: Lee so-and-so, and, king so-and-so, at, train
Stand, meet with, plunder.
The classification of part of speech includes: name, conjunction, verb, noun and preposition etc..
Such as, so-and-so and king of Lee so-and-so be all name.
As long as it is understood that the statement that screening comprises personage refers to comprise in this statement one as standby statement
Personage just screens as standby statement, is not the statement comprising all personages.I.e. filter out and include at least one personage's
Statement is as standby statement.
Such as, public procurator Zhao so-and-so, wherein public procurator is the role of this personage of Zhao.
This step records the corresponding relation between name and role, partly in order to merge duplicate removal, due to a literary composition
In original text, the address for same personage may be different.Sometimes with role, sometimes with name, personal pronoun is sometimes used.For essence
Really present event relation collection of illustrative plates, need the address of same personage is merged duplicate removal.
Such as: judge king so-and-so point out ...;Judge points out ...;Role is converted into name.
On the other hand, set up the corresponding relation between name and role, also for when presenting event relation collection of illustrative plates, people
Add the role of correspondence before Ming, be so conducive to the role that user's intuitivism apprehension name is corresponding.
Wherein, described standby statement screening module includes splitting submodule 502a and extracting submodule 502b;
Described fractionation submodule 502a, obtains for utilizing natural language processing technique that the statement after splitting is carried out participle
Vocabulary after participle;
Described extraction submodule 502b, for extracting the personage in described vocabulary according to part of speech.
The present embodiment also includes: module 605 modified in attribute, is used for when described personage includes name and role and described angle
When color is adjacent with described name, record the corresponding relation between this name and role;The people presented in described event relation collection of illustrative plates
Thing includes described name and role, and described role is as the attribute of described name.
Described relation map generation module 504 is calculated based on maximum entropy specifically for utilizing the syntactic analysis treebank being obtained ahead of time
Method, condition random field algorithm or neural network algorithm carry out syntactic analysis to described standby statement.
The device that the present embodiment provides, in order to accurately present relation map, has carried out merging duplicate removal to personage.Further, should
Method is applicable not only to news manuscript, but also is applicable to public security class notes, court judgment minutes etc..
The above, be only presently preferred embodiments of the present invention, and the present invention not makees any pro forma restriction.Though
So the present invention is disclosed above with preferred embodiment, but is not limited to the present invention.Any it is familiar with those skilled in the art
Member, without departing under technical solution of the present invention ambit, may utilize the method for the disclosure above and technology contents to the present invention
Technical scheme makes many possible variations and modification, or is revised as the Equivalent embodiments of equivalent variations.Therefore, every without departing from
The content of technical solution of the present invention, the technical spirit of the foundation present invention is to any simple modification made for any of the above embodiments, equivalent
Change and modification, all still fall within the range of technical solution of the present invention protection.
Claims (10)
1. the method generating event relation collection of illustrative plates, it is characterised in that including:
Manuscript is split as statement according to default punctuation mark;
Extract the personage in the statement after splitting, filter out the statement comprising described personage as standby statement;Described personage wraps
Include at least one in name, role and personal pronoun;
Utilize the syntactic analysis treebank being obtained ahead of time that described standby statement is carried out syntactic analysis, generate the pass between described personage
Connection relation;
Described personage and described incidence relation is utilized to generate event relation collection of illustrative plates.
The method of generation event relation collection of illustrative plates the most according to claim 1, it is characterised in that at the sentence that utilization is obtained ahead of time
Before method analysis treebank carries out syntactic analysis to described standby statement, also include:
When the described name in manuscript exists corresponding role, extract the role that described name is corresponding, record described name with
Corresponding relation between role;According to the corresponding relation between described name and role, it is corresponding people by described role transforming
Name;
When personal pronoun occurs in the described name in manuscript, extract the personal pronoun that described name is corresponding, record described name
And the corresponding relation between personal pronoun;According to the corresponding relation between described name and personal pronoun, by described personal pronoun
Be converted to the name of correspondence.
The method of generation event relation collection of illustrative plates the most according to claim 1, it is characterised in that the language after described extraction fractionation
Personage in Ju, specifically includes:
Utilize natural language processing technique that the statement after splitting is carried out the vocabulary after participle obtains participle;
The personage in described vocabulary is extracted according to part of speech.
The method of generation event relation collection of illustrative plates the most according to claim 3, it is characterised in that extract according to part of speech described
After personage in described vocabulary, also include:
When described personage includes name and role and when described role is adjacent with described name, record between this name and role
Corresponding relation;
The personage presented in described event relation collection of illustrative plates includes that described name and role, described role determine as described name
Language.
The method of generation event relation collection of illustrative plates the most according to claim 1, it is characterised in that described utilization is obtained ahead of time
Syntactic analysis treebank carries out syntactic analysis to described standby statement, particularly as follows:
Utilize the syntactic analysis treebank being obtained ahead of time based on maximum entropy algorithm, condition random field algorithm or neural network algorithm to institute
State standby statement and carry out syntactic analysis.
6. the device generating event relation collection of illustrative plates, it is characterised in that including: statement splits module, standby statement screening mould
Block, incidence relation generation module and relation map generation module;
Described statement splits module, for manuscript is split as statement according to default punctuation mark;
Described standby statement screening module, the personage in statement after extracting fractionation, filter out and comprise the standby of described personage
Use statement;Described personage includes at least one in name, role and personal pronoun;
Described incidence relation generation module, for utilizing the syntactic analysis treebank being obtained ahead of time that described standby statement is carried out syntax
Analyze, generate the incidence relation between described personage;
Described relation map generation module, is used for utilizing described personage and described incidence relation to generate event relation collection of illustrative plates.
The device of generation event relation collection of illustrative plates the most according to claim 6, it is characterised in that also include: corresponding relation
One logging modle, corresponding relation the second logging modle, the first modular converter and the second modular converter;
Described corresponding relation the first logging modle, for when the described name in manuscript exists corresponding role, extracts described
The role that name is corresponding, records the corresponding relation between described name and role;
Described first modular converter, is used for according to the corresponding relation between described name and role, is right by described role transforming
The name answered;
Described corresponding relation the second logging modle, for when personal pronoun occurs in the described name in manuscript, extracts described people
The personal pronoun that name is corresponding, records the corresponding relation between described name and personal pronoun;
Described second modular converter, for according to the corresponding relation between described name and personal pronoun, by described personal pronoun
Be converted to the name of correspondence.
The device of generation event relation collection of illustrative plates the most according to claim 6, it is characterised in that described standby statement screening mould
Block includes splitting submodule and extracting submodule;
Described fractionation submodule, after for utilizing natural language processing technique to carry out the statement after splitting, participle obtains participle
Vocabulary;
Described extraction submodule, for extracting the personage in described vocabulary according to part of speech.
The device of generation event relation collection of illustrative plates the most according to claim 8, it is characterised in that also include: mould modified in attribute
Block, for when described personage includes name and role and when described role is adjacent with described name, records this name and role
Between corresponding relation;The personage presented in described event relation collection of illustrative plates includes described name and role, and described role is as institute
State the attribute of name.
The device of generation event relation collection of illustrative plates the most according to claim 6, it is characterised in that described relation map generates
Module is specifically for utilizing the syntactic analysis treebank being obtained ahead of time based on maximum entropy algorithm, condition random field algorithm or neutral net
Algorithm carries out syntactic analysis to described standby statement.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610394465.9A CN106095748B (en) | 2016-06-06 | 2016-06-06 | A kind of method and device generating event relation map |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610394465.9A CN106095748B (en) | 2016-06-06 | 2016-06-06 | A kind of method and device generating event relation map |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106095748A true CN106095748A (en) | 2016-11-09 |
CN106095748B CN106095748B (en) | 2019-08-27 |
Family
ID=57447276
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610394465.9A Active CN106095748B (en) | 2016-06-06 | 2016-06-06 | A kind of method and device generating event relation map |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106095748B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106776544A (en) * | 2016-11-24 | 2017-05-31 | 四川无声信息技术有限公司 | Character relation recognition methods and device and segmenting method |
CN107507093A (en) * | 2017-08-22 | 2017-12-22 | 深圳市慧择保险经纪有限公司 | The data processing method and device of domestic customers demand for insurance |
CN107526722A (en) * | 2017-07-31 | 2017-12-29 | 努比亚技术有限公司 | A kind of character relation analysis method and terminal |
CN109657073A (en) * | 2018-12-21 | 2019-04-19 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
CN110309311A (en) * | 2018-03-09 | 2019-10-08 | 北京国双科技有限公司 | A kind of event handling strategy determines method and device |
CN111008022A (en) * | 2019-12-04 | 2020-04-14 | 浙江大搜车软件技术有限公司 | Relationship graph generation method and device, computer equipment and storage medium |
CN111859970A (en) * | 2020-07-23 | 2020-10-30 | 北京字节跳动网络技术有限公司 | Method, apparatus, device and medium for processing information |
CN112241461A (en) * | 2020-09-15 | 2021-01-19 | 上海连尚网络科技有限公司 | Method and equipment for generating character relation graph of book |
CN112579786A (en) * | 2019-09-30 | 2021-03-30 | 北京国双科技有限公司 | Construction method and device of atlas based on record, storage medium and equipment |
CN112714253A (en) * | 2020-12-28 | 2021-04-27 | 维沃移动通信有限公司 | Video recording method and device, electronic equipment and readable storage medium |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101604312A (en) * | 2007-12-07 | 2009-12-16 | 宗刚 | The method and system of the searching, managing and communicating of information |
CN101706794A (en) * | 2009-11-24 | 2010-05-12 | 上海显智信息科技有限公司 | Information browsing and retrieval method based on semantic entity-relationship model and visualized recommendation |
CN102214186A (en) * | 2010-04-07 | 2011-10-12 | 腾讯科技(深圳)有限公司 | Method and system for displaying object relation |
CN102693219A (en) * | 2012-06-05 | 2012-09-26 | 苏州大学 | Method and system for extracting Chinese event |
CN103488724A (en) * | 2013-09-16 | 2014-01-01 | 复旦大学 | Book-oriented reading field knowledge map construction method |
CN103617280A (en) * | 2013-12-09 | 2014-03-05 | 苏州大学 | Method and system for mining Chinese event information |
CN104462508A (en) * | 2014-12-19 | 2015-03-25 | 北京奇虎科技有限公司 | Character relation search method and device based on knowledge graph |
CN104615783A (en) * | 2015-03-02 | 2015-05-13 | 百度在线网络技术(北京)有限公司 | Information searching method and device |
CN105302794A (en) * | 2015-10-30 | 2016-02-03 | 苏州大学 | Chinese homodigital event recognition method and system |
CN105468605A (en) * | 2014-08-25 | 2016-04-06 | 济南中林信息科技有限公司 | Entity information map generation method and device |
CN105573977A (en) * | 2015-10-23 | 2016-05-11 | 苏州大学 | Method and system for identifying Chinese event sequential relationship |
-
2016
- 2016-06-06 CN CN201610394465.9A patent/CN106095748B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101604312A (en) * | 2007-12-07 | 2009-12-16 | 宗刚 | The method and system of the searching, managing and communicating of information |
CN101706794A (en) * | 2009-11-24 | 2010-05-12 | 上海显智信息科技有限公司 | Information browsing and retrieval method based on semantic entity-relationship model and visualized recommendation |
CN102214186A (en) * | 2010-04-07 | 2011-10-12 | 腾讯科技(深圳)有限公司 | Method and system for displaying object relation |
CN102693219A (en) * | 2012-06-05 | 2012-09-26 | 苏州大学 | Method and system for extracting Chinese event |
CN103488724A (en) * | 2013-09-16 | 2014-01-01 | 复旦大学 | Book-oriented reading field knowledge map construction method |
CN103617280A (en) * | 2013-12-09 | 2014-03-05 | 苏州大学 | Method and system for mining Chinese event information |
CN105468605A (en) * | 2014-08-25 | 2016-04-06 | 济南中林信息科技有限公司 | Entity information map generation method and device |
CN104462508A (en) * | 2014-12-19 | 2015-03-25 | 北京奇虎科技有限公司 | Character relation search method and device based on knowledge graph |
CN104615783A (en) * | 2015-03-02 | 2015-05-13 | 百度在线网络技术(北京)有限公司 | Information searching method and device |
CN105573977A (en) * | 2015-10-23 | 2016-05-11 | 苏州大学 | Method and system for identifying Chinese event sequential relationship |
CN105302794A (en) * | 2015-10-30 | 2016-02-03 | 苏州大学 | Chinese homodigital event recognition method and system |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106776544A (en) * | 2016-11-24 | 2017-05-31 | 四川无声信息技术有限公司 | Character relation recognition methods and device and segmenting method |
CN107526722A (en) * | 2017-07-31 | 2017-12-29 | 努比亚技术有限公司 | A kind of character relation analysis method and terminal |
CN107507093A (en) * | 2017-08-22 | 2017-12-22 | 深圳市慧择保险经纪有限公司 | The data processing method and device of domestic customers demand for insurance |
CN110309311A (en) * | 2018-03-09 | 2019-10-08 | 北京国双科技有限公司 | A kind of event handling strategy determines method and device |
CN109657073A (en) * | 2018-12-21 | 2019-04-19 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
CN112579786A (en) * | 2019-09-30 | 2021-03-30 | 北京国双科技有限公司 | Construction method and device of atlas based on record, storage medium and equipment |
WO2021063077A1 (en) * | 2019-09-30 | 2021-04-08 | 北京国双科技有限公司 | Method and apparatus for constructing record-based map, and storage medium and device |
CN111008022A (en) * | 2019-12-04 | 2020-04-14 | 浙江大搜车软件技术有限公司 | Relationship graph generation method and device, computer equipment and storage medium |
CN111008022B (en) * | 2019-12-04 | 2023-12-12 | 浙江大搜车软件技术有限公司 | Relationship diagram generation method, device, computer equipment and storage medium |
CN111859970A (en) * | 2020-07-23 | 2020-10-30 | 北京字节跳动网络技术有限公司 | Method, apparatus, device and medium for processing information |
CN111859970B (en) * | 2020-07-23 | 2022-05-17 | 北京字节跳动网络技术有限公司 | Method, apparatus, device and medium for processing information |
CN112241461A (en) * | 2020-09-15 | 2021-01-19 | 上海连尚网络科技有限公司 | Method and equipment for generating character relation graph of book |
WO2022057788A1 (en) * | 2020-09-15 | 2022-03-24 | 上海连尚网络科技有限公司 | Method and device for generating character relation map of book |
CN112241461B (en) * | 2020-09-15 | 2023-08-18 | 上海连尚网络科技有限公司 | Method and equipment for generating character relation graph of book |
CN112714253A (en) * | 2020-12-28 | 2021-04-27 | 维沃移动通信有限公司 | Video recording method and device, electronic equipment and readable storage medium |
CN112714253B (en) * | 2020-12-28 | 2022-08-26 | 维沃移动通信有限公司 | Video recording method and device, electronic equipment and readable storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN106095748B (en) | 2019-08-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106095748A (en) | A kind of method and device generating event relation collection of illustrative plates | |
CN107092596B (en) | Text emotion analysis method based on attention CNNs and CCR | |
CN110619568A (en) | Risk assessment report generation method, device, equipment and storage medium | |
Crespy | Analysing European Discourses | |
CN106503049A (en) | A kind of microblog emotional sorting technique for merging multiple affection resources based on SVM | |
CN106484904A (en) | Patent retrieval analysis system and its analysis method | |
Zhang et al. | Effects of mobile phone use on pedestrian crossing behavior and safety at unsignalized intersections | |
CN103077207B (en) | A kind of microblogging happy index analysis method and system | |
Armbrust | A history of new media in the Arab Middle East | |
WO2006023622A3 (en) | Automated extraction of semantic content and generation of a structured document from speech | |
CN103631859A (en) | Intelligent review expert recommending method for science and technology projects | |
CN102096680A (en) | Method and device for analyzing information validity | |
CN104063521A (en) | Method and device for achieving searching service | |
CN103942191A (en) | Horrific text recognizing method based on content | |
CN104731873A (en) | Evaluation information generation method and device | |
CN107341399A (en) | Assess the method and device of code file security | |
Williams | 14 Changes in the verb phrase in legislative language in English | |
CN104268134A (en) | Subjective and objective classifier building method and system | |
CN112037468A (en) | Safety early warning method and device and electronic equipment | |
CN105631015A (en) | Intelligent multimedia player | |
Matthews et al. | Fracturing debate? A review of research on media coverage of “fracking” | |
CN110110325A (en) | It is a kind of to repeat case lookup method and device, computer readable storage medium | |
CN104268203A (en) | Mobile terminal and junk information effectively filtering method and device thereof | |
Rigaud et al. | What do we expect from comic panel extraction? | |
CN103577557A (en) | Device and method for determining capturing frequency of network resource point |
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 |