CN103488724A - Book-oriented reading field knowledge map construction method - Google Patents
Book-oriented reading field knowledge map construction method Download PDFInfo
- Publication number
- CN103488724A CN103488724A CN201310420375.9A CN201310420375A CN103488724A CN 103488724 A CN103488724 A CN 103488724A CN 201310420375 A CN201310420375 A CN 201310420375A CN 103488724 A CN103488724 A CN 103488724A
- Authority
- CN
- China
- Prior art keywords
- entity
- concept
- knowledge
- illustrative plates
- books
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to the technical field of Chinese knowledge base application, in particular to a book-oriented reading field knowledge map construction method. The method includes general knowledge map construction, namely acquiring knowledge on the internet, and integrating a general knowledge map; field knowledge map construction, namely combining with the general knowledge map and expending relative concepts and entities of books in an iterative manner, and extracting entity relation by combining with an entity Infobox table and traditional relation; and intelligent reading recommendation, namely marking core entities in electronic books from longer entities to shorter entities, and establishing links between the entities and a book knowledge map so as to realizing the intelligent reading recommendation. According to the method, by means of establishing the book-oriented reading field knowledge maps, the entities in the books can be explained or knowledge can be recommended, depth of knowledge is increased, facilitation, intelligentization and humanization of electronic reading are realized, and better user experiences are provided.
Description
Technical field
The invention belongs to Chinese knowledge base applied technical field, be specifically related to a kind of construction method of the domain knowledge of the reading towards books collection of illustrative plates.
Background technology
Along with the development of computer technology and popularizing of mobile device, deep change has occurred in people's reading method, and electronic reading replaces traditional paper reading to become one of main flow reading model gradually.Compare tradition and read, electronic reading has been avoided the waste environmental protection more of paper, and electronic reading can help reader to realize reading easily.Electronic reading becomes one of a kind of important channel of knowledge acquisition already, and the trend of the knowledge acquisition of leading is more arranged.
But the knowledge acquisition of current electronic reading all is limited to books itself, when running into strange vocabulary, knowledge point, the reader need to consult aid, as dictionary, encyclopedia etc., strange knowledge is made an explanation.This brings extra burden to reading, how the explanation of knowledge in books is showed intuitively the reader to become the bottleneck of current electronic reading, addresses this problem that electronic reading is more convenient by making, intelligence and hommization.
Current electronic reader is attempted the knowledge in books is made an explanation.The Kindle reader is linked to the word in e-book in wikipedia and is searched for, to produce the explanation of word.Having reading that word is linked to Chinese interactive encyclopaedia makes an explanation.These improve and have improved to a certain extent the intelligibility of e-book and the degree of depth of knowledge.Although knowledge and the content outside books expanded in these improvement, but still not carrying out intelligent knowledge arranges and recommends, the reader still need to arrange, select the knowledge needed, the knowledge that even these encyclopaedia pages do not exist the reader to want from the Search Results of word.So existing electronic reading is still intelligent not, can not screen automatically knowledge and knowledge and recommend.
Knowledge collection of illustrative plates (knowledge graph) refers to usings entity, concept as node, usings the semantic network of semantic relation as limit.The knowledge collection of illustrative plates makes knowledge acquisition more direct, so the knowledge collection of illustrative plates can provide for electronic reading the knowledge of semantic association, thereby realizes facilitation, intellectuality and the hommization of reading.But current Chinese knowledge collection of illustrative plates still belongs to the structure stage, and it is general knowledge collection of illustrative plates.Therefore, we need to build one for the each book nationality and read the domain knowledge collection of illustrative plates.
Summary of the invention
The present invention is directed to current electronic reading and have the problems such as knowledge hierarchy is shallow, the knowledge recommendation is intelligent not, propose a kind of in conjunction with the world knowledge collection of illustrative plates, structural surface is to the method for the domain knowledge collection of illustrative plates of books, for e-book structure knowledge network, thereby realize the explanation of books word and intelligent knowledge are recommended.
The domain knowledge of the reading towards the books map construction method that the present invention proposes, in conjunction with existing world knowledge collection of illustrative plates, kernel entity in books and concept are identified and marked, excavated the semantic relation between entity, concept, thus the domain knowledge collection of illustrative plates of structure books.When the kernel entity of readers' preference mark carries out knowledge query, the knowledge that reader will query semantics be relevant from the domain knowledge collection of illustrative plates is carried out intelligent knowledge and is recommended.The inventive method comprises three parts (i.e. three modules): world knowledge map construction, domain knowledge map construction and intelligence are read application, and the method Organization Chart is shown in shown in accompanying drawing 1.
one, world knowledge map construction
The knowledge collection of illustrative plates refers to the semantic network be comprised of the entity of magnanimity, concept and the semantic relation between them.The knowledge collection of illustrative plates can provide comprehensive, the most associated knowledge of entity and explanation, so we are that books build the domain knowledge collection of illustrative plates by the world knowledge collection of illustrative plates, thereby for making reasonable dismissal in word, knowledge point in books.
The Chinese knowledge collection of illustrative plates of current existence comprises that Google Chinese knowledge collection of illustrative plates, Baidu's knowledge collection of illustrative plates and search dog know cube.We utilize existing knowledge source as the knowledge source of realizing books domain knowledge map construction, by entity, concept and the relation of obtaining Baidupedia, interactive encyclopaedia and Chinese wikipedia, and in addition integratedly with cleaning, obtain high-quality Universal Chinese character knowledge collection of illustrative plates.
two, domain knowledge map construction
This module adopts alternative manner constantly to expand key concept and kernel entity in conjunction with the world knowledge collection of illustrative plates, then excavates the semantic relation between entity, thereby builds the domain knowledge collection of illustrative plates.This module is by step concept, Entity recognition and Relation extraction and realization.
concept, Entity recognition
The target of concept identification is to identify all concepts that are closely related with books, and the present invention realizes by the open classified information of entity in the world knowledge collection of illustrative plates.
the book keyword definition
At first, in order to identify the concept that books are relevant, the key word that needs a small amount of books of artificial definition to be closely related, book name can be selected in key word, also can select the key word in book name.This step can obtain set of keywords KEYWORD(definition: set of keywords is the set that relevant key word forms by book name).
the seed concept identification
The seed concept is directly to comprise the concept of keyword string in the knowledge collection of illustrative plates, and add classification seed concept set to close the SEEDCONCEPT(definition concept that comprises the key word word string in the knowledge collection of illustrative plates: classification seed concept set is closed the set formed for the concept that comprises the key word substring in set KEYWORD in the knowledge graph spectrum).
concept, the expansion of entity iteration
Concept, the expansion of entity iteration are according to the seed concept, expand all concepts relevant to books and entity from the world knowledge collection of illustrative plates.Implementation method is as follows, and the expansion process flow diagram is shown in accompanying drawing 2:
At first, from the set of seed concept, SEEDCONCEPT can obtain corresponding entity, and add kernel entity set COREENTITY(definition: the kernel entity set i.e. the set for being comprised of the entity under the seed concept).
Secondly, kernel entity in scanning COREENTITY, can produce the not concept in SEEDCONCEPT, be called candidate's concept, add candidate's concept set CANDIDATECONCEPT(definition: the set of candidate's concept be by under kernel entity and do not appear at the set that the concept in the key concept set forms).
Then, calculating candidate's concept in CANDIDATECONCEPT defines with key concept set CORECONCEPT(: the set that the key concept set is comprised of the closely-related concept of books, by the seed concept and and the larger concept of its similarity form) between semantic dependency.To be greater than given threshold value
(definition: semantic dependency threshold value.Think semantic relevant if concept is greater than this value to the semantic dependency of set) candidate's concept as related notion, add in key concept set CORECONCEPT.Wherein, candidate's concept c(means any candidate's concept) and the key concept set between CS(mean key concept set CORECONCEPT) semantic dependency be defined as:
Rel(c, cs).
Wherein,
mean to belong to the physical quantities of classification c and classification k simultaneously,
with
num (k)mean to belong to respectively classification
cor
kthe quantity of entity, c and k mean respectively the open classification of the entity in the knowledge collection of illustrative plates.
Finally, until there is no new concept or entity produces, so just obtain whole and books related notion and entity with the expansion CORECONCEPT of iterative manner increment and COREENTITY.
But, but may there be some more common and not strong entity and concepts of topic relativity in these entities and concept, therefore, need to be cleaned.Cleaning process realizes by the IDF value of computational entity or concept, and using the IDF value, lower entity or concept, as noise, are shown below:
nummean entity sum in the knowledge collection of illustrative plates,
mean in the knowledge collection of illustrative plates physical quantities that comprises link entity e,
num (c)mean the physical quantities that comprises the c that classifies in the knowledge collection of illustrative plates.E means the entity in the knowledge collection of illustrative plates, and c means the open classification of entity in the knowledge collection of illustrative plates.Entity or concept that versatility is larger be can punish like this, thereby maximally related entity and concept retained.
the entitative concept Relation extraction
The entitative concept Relation extraction is to be acquired entitative concept constructing semantic relation, is the important step of structure knowledge collection of illustrative plates.Entity relationship is expressed as tlv triple
, wherein source means source entity, target means target entity, relation presentation-entity relation, the set of r presentation-entity relationship description.The relation that books are relevant refers in tlv triple that source or target are in COREENTITY.The present invention mainly adopts two kinds of Relation extraction methods in conjunction with the world knowledge collection of illustrative plates: based on Infobox(, define: Infobox refers to the attribute list of entity in the knowledge collection of illustrative plates) the Relation extraction method and the Relation extraction method of Schema-based.
relation extraction method based on Infobox
Infobox is with the base attribute information of the formal description entity of form.The expression of Infobox (
) with entity relationship, mean identical,
entitycorresponding
source,
attributecorresponding
relation, valuecorresponding
target.Wherein
entitypresentation-entity,
attributethe presentation-entity attribute,
valuethe property value that presentation-entity is corresponding.At first, check the Infobox table, if
entityor
valuebelong to COREENTITY, this attribute is added to set R(definition: the set formed by the entity relationship tlv triple), and will
attributeadd entity relationship description collections r.
the Relation extraction method of Schema-based
Use Infobox can obtain entity relationship triplet sets R and entity relationship description collections r.In order to excavate more entity, the present invention adopts the Relation extraction method of Schema-based.
Challenge in entity relation extraction is the extraction of " relationship description ", and the method based on Infobox has obtained " relationship description " set r.Therefore, use the method for natural language processing here and, in conjunction with Chinese word segmentation identification entity, first find out the position of " relationship description " from a sentence, then find forward, backward respectively nearest kernel entity or noun entity.The Relation extraction pattern is:
, entity relationship words of description and its are forward, nearest entity forms one and concerns tlv triple backward.
For the extraction of character relation in books, adopt the decimation pattern in table 1 especially, the language material text is the business card introduction of entity, here r representative figure's set of relationship { as " father ", " husband ", " wife " etc. }:
Table 1. character relation decimation pattern
Annotate: * * means any word ,/nr, and/u ,/uj ,/v means the part-of-speech tagging after Chinese word segmentation, { r} is a relationship description word in relationship description set r.
entity refers to Relation extraction
In books, some entity has another name or special address, but all refers to same entity.Refer to entity in order to identify these, need to carry out entity and refer to judgement, be mainly to have utilized synonym in the synonym mapping table of the entity in the knowledge collection of illustrative plates and entity Infobox table to describe attribute (" another name ", " former name ", " formal name used at school ", " pseudonym " etc.) will refer to entity associated and arrive kernel entity.
three, intelligence is read application
This module fundamental purpose is the entity of mark in e-book and to complete the mapping of entity to knowledge in books domain knowledge collection of illustrative plates.During entity in the readers' preference books, from books domain knowledge collection of illustrative plates, select corresponding knowledge recommended and show.Comprise entity mark, entity explanation:
The entity mark is that the entity in kernel entity set COREENTITY is marked in e-book, and accuracy and speed in order to improve mark, sort entity according to length, then marks successively from long to short, the mistake mark caused to avoid entity to comprise;
Entity is explained the entity marked out in e-book is found to corresponding explanation in the knowledge collection of illustrative plates, when the user selects to need the entity of explanation, selects corresponding knowledge to be recommended.
In sum, use the collection of illustrative plates of the domain knowledge towards books of constructing in the present invention can accurately identify the extraction of entity, concept and entity relationship in e-book, and can mark accurately kernel entity, in conjunction with the knowledge collection of illustrative plates, the entity in e-book is done to accurate, intelligent knowledge and recommend, greatly improved convenience, the intelligibility of books.This is that existing electronic reading system does not all have the function realized.
According to foregoing, the domain knowledge of the reading towards books map construction method of the present invention is summarized as follows:
(1) for given e-book and world knowledge collection of illustrative plates, identify, extract the relevant knowledge that belongs to this e-book, so that being provided, intelligent knowledge recommends.These relevant knowledges comprise entity, concept and make an explanation and relevant semantic relation, form the relevant semantic network of books, i.e. books domain knowledge collection of illustrative plates.
(2) for the domain knowledge collection of illustrative plates and the e-book that build, generate intelligent reading system.Mark out the core vocabulary (entity in the knowledge collection of illustrative plates, concept) in e-book, and the glossary explanation in the knowledge collection of illustrative plates is linked in e-book.When the reader asks glossary explanation, from the domain knowledge collection of illustrative plates, select semantic relevant knowledge interpretation to be recommended.
The step of the method for books domain knowledge map construction described in step (1) is as follows:
(a) classified information in the world knowledge collection of illustrative plates is used in conceptual entity identification, at first defines book keyword, secondly tentatively obtains the seed concept that books are relevant, the then expansion concept of iteration and entity.By the correlativity between definition candidate's concept and key concept set
determine whether candidate's concept is added to the key concept set.Wherein
mean to belong to classification simultaneously
and classification
kphysical quantities,
num (c)with
num (k)mean to belong to respectively classification
cor
kthe quantity of lower entity.
Finally, by using the IDF index, clean entity, the concept obtained, obtain and the closely-related entity of books and concept.
(b) the entitative concept Relation extraction is used entity Infobox information in the world knowledge collection of illustrative plates, extracts and concerns tlv triple<source, relation, target > in description collections { relation} and the part entity relationship of relation.Then for the text of world knowledge collection of illustrative plates entity, use the Relation extraction method of Schema-based, extract more relation.
(c) entity refers to relation and mainly by the synonym information of entity in the world knowledge collection of illustrative plates and the synonym in the Infobox table, describes attribute, will refer to chain of entities and receive the kernel entity that it refers to.
Described in step (2), the step of intelligent reading system generation method is as follows:
(a) to need in order marking out in e-book the vocabulary of explaining, the entitative concept in books domain knowledge collection of illustrative plates to be sorted according to character length, then mated in e-book successively from long to short, mark.
(b) knowledge of books related entities, concept is taken out from the world knowledge collection of illustrative plates, be integrated into the domain knowledge collection of illustrative plates of books, complete the link of books vocabulary to relevant knowledge.
The accompanying drawing explanation
Fig. 1 is the Organization Chart towards books reading domain knowledge collection of illustrative plates.
Fig. 2 is the process flow diagram that concept, entity extract.
Fig. 3 is for carrying out entity mark and knowledge recommendation effect figure for the books Dream of the Red Mansion.
Fig. 4 shows for the A Dream of Red Mansions part personage graph of a relation that uses the Relation extraction method to obtain.
Embodiment
Below take the e-book Dream of the Red Mansion as example, further describe the present invention:
module one: world knowledge map construction
Use Baidu's Chinese knowledge collection of illustrative plates as knowledge source, use the knowledge source of interactive encyclopaedia and Chinese wikipedia as a supplement simultaneously.By crawling and resolve the encyclopaedia data, the encyclopaedia entity obtained is integrated and cleaned high-quality entity, concept and entity relationship.Thereby construct the world knowledge collection of illustrative plates.
module two: domain knowledge map construction
1. entity, concept extraction
At first, for the e-book Dream of the Red Mansion, the artificial key set KEYWORD{ " A Dream of Red Mansions " that sets }, then search the key concept set CORECONCEPT{ " A Dream of Red Mansions " that comprises " A Dream of Red Mansions " key word from knowledge collection of illustrative plates entity classification, " A Dream of Red Mansions personage ", " A Dream of Red Mansions dress ornament " ....Secondly, search the entity that belongs to key concept from the knowledge collection of illustrative plates, form kernel entity set COREENTITY{ " Jia Fu ", " precious jade ", " Lin Daiyu " ....The concept in CORECONCEPT under COREENTITY and is not added to CANDIDATECONCEPT.Calculate the semantic relevancy Rel (c, CS) between itself and CORECONCEPT for the concept in CANDIDATECONCEPT, select the degree of correlation to be greater than threshold value
concept add CORECPNCEPT.Finally, expansion COREENTITY and the CORECONCEPT of iteration, do not have new kernel entity and concept to add set until converge to, and obtains entity scale that books " A Dream of Red Mansions " are relevant in Table 2.
2. Relation extraction
At first, use the Relation extraction method based on Infobox to extract relation, judge Infobox table<entity, attribute, value > entity or value whether belong to the kernel entity set.If by entity relationship tlv triple<entity, attribute, value > add set R, relationship description attribute is added to relationship description set r simultaneously.As<Lin Daiyu, father, Lin Ruhai>can obtain relation "
lin Daiyu-father-Lin Ruhai" and relationship description "
father".
Secondly, use the Relation extraction method of Schema-based, the use pattern
expansion relation from text, as use relationship description "
father", can extract entity relationship "
jia Baoyu-father-Jia Zheng".
Then, use the pattern description in table 1 to extract the character relation in Dream of the Red Mansion from text, the character relation collection of illustrative plates scale obtained is in Table 2, and the character relation graphical effect centered by " Wang Xifeng ", " Lin Daiyu " is shown in accompanying drawing 4.
Finally, for the entity in books, refer to, as in Dream of the Red Mansion "
the phoenix elder sister", "
the phoenix spicy" all refer to "
wang Xifeng".Refer to entity in order to identify these, utilized synonym in the synonym mapping table of the entity in the knowledge collection of illustrative plates and entity Infobox table to describe attribute (" another name ", " former name ", " formal name used at school ", " pseudonym " etc.) and will refer to entity associated and arrive kernel entity.
Entity, the concept identification by this module, used, the knowledge collection of illustrative plates scale that the Relation extraction method builds is in Table 2.
The scale of table 2. A Dream of Red Mansions domain knowledge collection of illustrative plates
The scale of domain knowledge collection of illustrative plates | Physical quantities (individual) | Entity relationship quantity (individual) | Concept quantity (individual) |
A Dream of Red Mansions entity collection of illustrative plates | 1560 | 2731 | 85 |
A Dream of Red Mansions personage subgraph spectrum | 804 | 1530 | 2 |
module three: intelligence is read application
The Dream of the Red Mansion related entities that module two is obtained sorts from long to short according to physical length, then in the Dream of the Red Mansion e-book, marks out successively.The mistake that can avoid like this entity to comprise and cause improves accuracy and the efficiency marked simultaneously.Entity mark effect is shown in accompanying drawing 3, and in Dream of the Red Mansion, the related entities such as " precious jade ", " Lin Daiyu " is all accurately marked out.
The entity marked out in the Dream of the Red Mansion books is found to corresponding explanation in the knowledge collection of illustrative plates, when the user selects to need the entity of explanation, select corresponding knowledge to be recommended.Accompanying drawing 3 is shown as the explain information of entity in Dream of the Red Mansion " Lin Daiyu ".
Claims (3)
1. the domain knowledge of the reading towards a books map construction method, is characterized in that concrete steps are divided into: world knowledge map construction, domain knowledge map construction and intelligence reading application;
One, world knowledge map construction
The knowledge collection of illustrative plates refers to the semantic network be comprised of the entity of magnanimity, concept and the semantic relation between them; By the world knowledge collection of illustrative plates, be that books build the domain knowledge collection of illustrative plates, thereby for making reasonable dismissal in word, knowledge point in books; The world knowledge collection of illustrative plates is usingd the current Chinese knowledge collection of illustrative plates existed and is comprised that Google Chinese knowledge collection of illustrative plates, Baidu's knowledge collection of illustrative plates and search dog are known and cube build as existing knowledge source;
Two, domain knowledge map construction
In conjunction with the world knowledge collection of illustrative plates, adopt alternative manner constantly to expand key concept and kernel entity, then excavate the semantic relation between entity, thereby build the domain knowledge collection of illustrative plates; Comprise concept, Entity recognition and Relation extraction:
-2.1 concepts, Entity recognition
The target of concept identification is to identify all concepts that are closely related with books, and concept identification realizes by the open classified information of entity in the world knowledge collection of illustrative plates;
The definition of-2.1.1 book keyword
At first, in order to identify the concept that books are relevant, the key word be closely related by a small amount of books of artificial definition, book name selected in key word, or select the key word in book name; Obtain set of keywords KEYWORD by this step;
-2.1.2 seed concept identification
The seed concept is directly to comprise the concept of keyword string in the knowledge collection of illustrative plates, add classification seed concept set to close SEEDCONCEPT the concept that comprises the key word word string in the knowledge collection of illustrative plates, classification seed concept set is combined into the set that the concept that comprises the key word word string in set KEYWORD in the knowledge collection of illustrative plates forms;
-2.1.3 concept, the expansion of entity iteration
Concept, the expansion of entity iteration are according to the seed concept, expand all concepts relevant to books and entity from the world knowledge collection of illustrative plates; Concrete grammar is as follows:
At first, from the set of seed concept, SEEDCONCEPT obtains corresponding entity, adds kernel entity set COREENTITY, the set of kernel entity set for being comprised of the entity under the seed concept;
Secondly, kernel entity in scanning COREENTITY, produce the not concept in SEEDCONCEPT, be called candidate's concept, add candidate's concept set CANDIDATECONCEPT, candidate's concept set is combined into by under kernel entity and do not appear at the set that the concept in the key concept set forms;
Then, semantic dependency in calculating CANDIDATECONCEPT between candidate's concept and key concept set CORECONCEPT, the set that described key concept set is comprised of the closely-related concept of books, form by the seed concept with the larger concept of its similarity; To be greater than given threshold value
candidate's concept as related notion, add in key concept set CORECONCEPT; Wherein, between candidate's concept c and key concept set, the semantic dependency of CS is defined as: Re(c, cs);
Wherein,
mean to belong to the physical quantities of classification c and classification k simultaneously,
with
num (k)mean to belong to respectively classification
cor
kthe quantity of entity;
Finally, until there is no new concept or entity produces, so just obtain whole and books related notion and entity with the expansion CORECONCEPT of iterative manner increment and COREENTITY;
-2.2 entitative concept Relation extractions
The entitative concept Relation extraction is to be acquired entitative concept constructing semantic relation, and entity relationship is expressed as tlv triple
, wherein r presentation-entity relationship description set; The relation that books are relevant refers in tlv triple that source or target are in COREENTITY; Adopt two kinds of Relation extraction methods in conjunction with the world knowledge collection of illustrative plates: the Relation extraction method based on Infobox and the Relation extraction method of Schema-based;
The Relation extraction method of-2.2.1 based on Infobox
Infobox refers to the attribute list of entity, the base attribute information of the main formal description entity with form; The expression of Infobox
, with entity relationship, mean identical,
entitycorresponding
source,
attributecorresponding
relation, valuecorresponding
target; At first, check the Infobox table, if
entityor
valuebelong to COREENTITY, this attribute is added to set R, the set that R is comprised of the entity relationship tlv triple, will
attributeadd entity relationship description collections r;
The Relation extraction method of-2.2.2 Schema-based
The method of Infobox has obtained " relationship description " set r, the Relation extraction of Schema-based is used the method for natural language processing and identifies entity in conjunction with Chinese word segmentation, first find out the position of " relationship description " from a sentence, then find forward, backward respectively nearest kernel entity or noun entity; The Relation extraction pattern is:
;
-2.2.3 entity refers to Relation extraction
In books, some entity has another name or special address, but all refers to same entity; Refer to entity in order to identify these, need to carry out entity and refer to judgement, be mainly to have utilized synonym in the synonym mapping table of the entity in the knowledge collection of illustrative plates and entity Infobox table to describe attribute to comprise that " another name ", " former name ", " formal name used at school ", " pseudonym " will refer to entity associated and arrive kernel entity;
Three, intelligence is read application
Comprise entity mark, entity explanation:
The entity mark is that the entity in kernel entity set COREENTITY is marked in e-book, and accuracy and speed in order to improve mark, sort entity according to length, then marks successively from long to short, the mistake mark caused to avoid entity to comprise;
Entity is explained the entity marked out in e-book is found to corresponding explanation in the knowledge collection of illustrative plates, when the user selects to need the entity of explanation, selects corresponding knowledge to be recommended.
2. the domain knowledge of the reading towards books map construction method according to claim 1, it is characterized in that in concept, entity iteration spread step, but may there be some more common and not strong entity and concepts of topic relativity in entity and concept, therefore, need to be cleaned; Cleaning process realizes by the IDF value of computational entity or concept, and using the IDF value, lower entity or concept, as noise, are shown below:
nummean entity sum in the knowledge collection of illustrative plates,
mean in the knowledge collection of illustrative plates physical quantities that comprises link entity e,
num (c)mean the physical quantities that comprises the c that classifies in the knowledge collection of illustrative plates; Entity or concept that versatility is larger be can punish like this, thereby maximally related entity and concept retained.
3. the domain knowledge of the reading towards books map construction method according to claim 1, it is characterized in that in the Relation extraction of Schema-based, extraction for character relation in books, adopt the decimation pattern in table 1, the language material text is the business card introduction of entity, r representative figure's set of relationship here;
Table 1. character relation decimation pattern
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310420375.9A CN103488724B (en) | 2013-09-16 | 2013-09-16 | A kind of reading domain knowledge map construction method towards books |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310420375.9A CN103488724B (en) | 2013-09-16 | 2013-09-16 | A kind of reading domain knowledge map construction method towards books |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103488724A true CN103488724A (en) | 2014-01-01 |
CN103488724B CN103488724B (en) | 2016-09-28 |
Family
ID=49828950
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310420375.9A Expired - Fee Related CN103488724B (en) | 2013-09-16 | 2013-09-16 | A kind of reading domain knowledge map construction method towards books |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103488724B (en) |
Cited By (68)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104102713A (en) * | 2014-07-16 | 2014-10-15 | 百度在线网络技术(北京)有限公司 | Method and device for displaying recommendation results |
CN104133916A (en) * | 2014-08-14 | 2014-11-05 | 百度在线网络技术(北京)有限公司 | Search result information organizational method and device |
CN104408148A (en) * | 2014-12-03 | 2015-03-11 | 复旦大学 | Field encyclopedia establishment system based on general encyclopedia websites |
CN104462227A (en) * | 2014-11-13 | 2015-03-25 | 中国测绘科学研究院 | Automatic construction method of graphic knowledge genealogy |
CN105117115A (en) * | 2015-08-07 | 2015-12-02 | 小米科技有限责任公司 | Method and device for displaying electronic document |
CN105574098A (en) * | 2015-12-11 | 2016-05-11 | 百度在线网络技术(北京)有限公司 | Knowledge graph generation method and device and entity comparing method and device |
CN105824802A (en) * | 2016-03-31 | 2016-08-03 | 清华大学 | Method and device for acquiring knowledge graph vectoring expression |
CN105912656A (en) * | 2016-04-07 | 2016-08-31 | 桂林电子科技大学 | Construction method of commodity knowledge graph |
CN106095748A (en) * | 2016-06-06 | 2016-11-09 | 东软集团股份有限公司 | A kind of method and device generating event relation collection of illustrative plates |
CN106776564A (en) * | 2016-12-21 | 2017-05-31 | 张永成 | The method for recognizing semantics and system of a kind of knowledge based collection of illustrative plates |
CN106874378A (en) * | 2017-01-05 | 2017-06-20 | 北京工商大学 | The entity of rule-based model extracts the method that knowledge mapping is built with relation excavation |
CN106875014A (en) * | 2017-03-02 | 2017-06-20 | 上海交通大学 | The automation of the soft project knowledge base based on semi-supervised learning builds implementation method |
CN106933806A (en) * | 2017-03-15 | 2017-07-07 | 北京大数医达科技有限公司 | The determination method and apparatus of medical synonym |
CN106934032A (en) * | 2017-03-14 | 2017-07-07 | 软通动力信息技术(集团)有限公司 | A kind of city knowledge mapping construction method and device |
CN106951526A (en) * | 2017-03-21 | 2017-07-14 | 北京邮电大学 | A kind of entity set extended method and device |
CN107038261A (en) * | 2017-05-28 | 2017-08-11 | 海南大学 | A kind of processing framework resource based on data collection of illustrative plates, Information Atlas and knowledge mapping can Dynamic and Abstract Semantic Modeling Method |
CN107103100A (en) * | 2017-06-10 | 2017-08-29 | 海南大学 | A kind of fault-tolerant intelligent semantic searching method based on data collection of illustrative plates, Information Atlas and knowledge mapping framework for putting into driving |
CN107330125A (en) * | 2017-07-20 | 2017-11-07 | 云南电网有限责任公司电力科学研究院 | The unstructured distribution data integrated approach of magnanimity of knowledge based graphical spectrum technology |
CN107391512A (en) * | 2016-05-17 | 2017-11-24 | 北京邮电大学 | The method and apparatus of knowledge mapping prediction |
CN107609052A (en) * | 2017-08-23 | 2018-01-19 | 中国科学院软件研究所 | A kind of generation method and device of the domain knowledge collection of illustrative plates based on semantic triangle |
CN107704637A (en) * | 2017-11-20 | 2018-02-16 | 中国人民解放军国防科技大学 | Knowledge graph construction method for emergency |
CN107894884A (en) * | 2016-09-30 | 2018-04-10 | 中国电子科技集团公司信息科学研究院 | Object representation device and its description method |
CN108052576A (en) * | 2017-12-08 | 2018-05-18 | 国家计算机网络与信息安全管理中心 | A kind of reason knowledge mapping construction method and system |
CN108073587A (en) * | 2016-11-09 | 2018-05-25 | 阿里巴巴集团控股有限公司 | A kind of automatic question-answering method, device and electronic equipment |
CN108171213A (en) * | 2018-01-22 | 2018-06-15 | 北京邮电大学 | A kind of Relation extraction method for being applicable in picture and text knowledge mapping |
CN108182245A (en) * | 2017-12-28 | 2018-06-19 | 北京锐安科技有限公司 | The construction method and device of people's object properties classificating knowledge collection of illustrative plates |
CN108415971A (en) * | 2018-02-08 | 2018-08-17 | 兰州智豆信息科技有限公司 | Recommend the method and apparatus of supply-demand information using knowledge mapping |
CN108463818A (en) * | 2016-10-31 | 2018-08-28 | 微软技术许可有限责任公司 | Establish and update connection segment collection of illustrative plates |
CN108694177A (en) * | 2017-04-06 | 2018-10-23 | 北大方正集团有限公司 | Knowledge mapping construction method and system |
CN108710695A (en) * | 2018-05-23 | 2018-10-26 | 掌阅科技股份有限公司 | Mind map generation method based on e-book and electronic equipment |
CN108829865A (en) * | 2018-06-22 | 2018-11-16 | 海信集团有限公司 | Information retrieval method and device |
CN108920527A (en) * | 2018-06-07 | 2018-11-30 | 桂林电子科技大学 | A kind of personalized recommendation method of knowledge based map |
CN108959242A (en) * | 2018-05-08 | 2018-12-07 | 中国科学院信息工程研究所 | A kind of target entity recognition methods and device based on Chinese character part of speech feature |
CN109189942A (en) * | 2018-09-12 | 2019-01-11 | 山东大学 | A kind of construction method and device of patent data knowledge mapping |
CN109241289A (en) * | 2017-07-04 | 2019-01-18 | 北京国双科技有限公司 | Entity information map extending method and device |
CN109522551A (en) * | 2018-11-09 | 2019-03-26 | 天津新开心生活科技有限公司 | Entity link method, apparatus, storage medium and electronic equipment |
CN109597895A (en) * | 2018-11-09 | 2019-04-09 | 中电科大数据研究院有限公司 | A kind of archives search method of knowledge based map |
CN109710748A (en) * | 2019-01-17 | 2019-05-03 | 北京光年无限科技有限公司 | It is a kind of to draw this reading exchange method and system towards intelligent robot |
CN109726298A (en) * | 2019-01-08 | 2019-05-07 | 上海市研发公共服务平台管理中心 | Knowledge mapping construction method, system, terminal and medium suitable for scientific and technical literature |
CN109739994A (en) * | 2018-12-14 | 2019-05-10 | 复旦大学 | A kind of API knowledge mapping construction method based on reference documents |
CN109766444A (en) * | 2018-12-10 | 2019-05-17 | 北京百度网讯科技有限公司 | The application database generation method and its device of knowledge mapping |
CN109885660A (en) * | 2019-02-22 | 2019-06-14 | 上海乐言信息科技有限公司 | A kind of question answering system and method based on information retrieval that knowledge mapping is energized |
CN110008354A (en) * | 2019-04-10 | 2019-07-12 | 华侨大学 | A kind of construction method of the external Chinese studying content of knowledge based map |
CN110162640A (en) * | 2019-04-28 | 2019-08-23 | 北京百度网讯科技有限公司 | Novel entities method for digging, device, computer equipment and storage medium |
CN110245239A (en) * | 2019-05-13 | 2019-09-17 | 吉林大学 | A kind of construction method and system towards automotive field knowledge mapping |
CN110275966A (en) * | 2019-07-01 | 2019-09-24 | 科大讯飞(苏州)科技有限公司 | A kind of Knowledge Extraction Method and device |
CN110489032A (en) * | 2019-08-14 | 2019-11-22 | 掌阅科技股份有限公司 | Dictionaries query method and electronic equipment for e-book |
CN110532399A (en) * | 2019-08-07 | 2019-12-03 | 广州多益网络股份有限公司 | Knowledge mapping update method, system and the device of object game question answering system |
CN110598002A (en) * | 2019-08-14 | 2019-12-20 | 广州视源电子科技股份有限公司 | Knowledge graph library construction method and device, computer storage medium and electronic equipment |
US10579689B2 (en) | 2017-02-08 | 2020-03-03 | International Business Machines Corporation | Visualization and augmentation of human knowledge construction during material consumption |
CN111091006A (en) * | 2019-12-20 | 2020-05-01 | 北京百度网讯科技有限公司 | Entity intention system establishing method, device, equipment and medium |
CN111209407A (en) * | 2018-11-21 | 2020-05-29 | 北京嘀嘀无限科技发展有限公司 | Data processing method and device, electronic equipment and computer readable storage medium |
CN111274812A (en) * | 2018-12-03 | 2020-06-12 | 阿里巴巴集团控股有限公司 | Character relation recognition method, device and storage medium |
WO2020143319A1 (en) * | 2019-01-08 | 2020-07-16 | 平安科技(深圳)有限公司 | Knowledge graph completion method and apparatus, computer device and storage medium |
CN111581376A (en) * | 2020-04-17 | 2020-08-25 | 中国船舶重工集团公司第七一四研究所 | Automatic knowledge graph construction system and method |
CN111708892A (en) * | 2020-04-24 | 2020-09-25 | 陆洋 | Database system based on depth knowledge graph |
CN112100396A (en) * | 2020-08-28 | 2020-12-18 | 泰康保险集团股份有限公司 | Data processing method and device |
CN112256835A (en) * | 2020-10-29 | 2021-01-22 | 东南大学 | Subgraph extraction method for accurately describing element semantics in knowledge graph |
CN112463980A (en) * | 2020-11-25 | 2021-03-09 | 南京摄星智能科技有限公司 | Intelligent plan recommendation method based on knowledge graph |
CN112487212A (en) * | 2020-12-18 | 2021-03-12 | 清华大学 | Method and device for constructing domain knowledge graph |
CN112597285A (en) * | 2020-12-10 | 2021-04-02 | 太极计算机股份有限公司 | Man-machine interaction method and system based on knowledge graph |
CN112632226A (en) * | 2020-12-29 | 2021-04-09 | 天津汇智星源信息技术有限公司 | Semantic search method and device based on legal knowledge graph and electronic equipment |
WO2021073254A1 (en) * | 2019-10-18 | 2021-04-22 | 平安科技(深圳)有限公司 | Knowledge graph-based entity linking method and apparatus, device, and storage medium |
CN112749284A (en) * | 2020-12-31 | 2021-05-04 | 平安科技(深圳)有限公司 | Knowledge graph construction method, device, equipment and storage medium |
CN112823332A (en) * | 2018-10-10 | 2021-05-18 | N3有限责任公司 | Semantic industry terminology |
CN113297347A (en) * | 2021-06-29 | 2021-08-24 | 中国人民解放军国防科技大学 | Intelligent auxiliary method, system and storage medium for professional document reading |
CN113326697A (en) * | 2021-05-31 | 2021-08-31 | 云南电网有限责任公司电力科学研究院 | Knowledge graph-based electric power text entity semantic understanding method |
TWI747220B (en) * | 2020-03-31 | 2021-11-21 | 股感生活金融科技股份有限公司 | Knowledge graph association search method and system |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107423820B (en) * | 2016-05-24 | 2020-09-29 | 清华大学 | Knowledge graph representation learning method combined with entity hierarchy categories |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6408302B1 (en) * | 1999-06-28 | 2002-06-18 | Davox Corporation | System and method of mapping database fields to a knowledge base using a graphical user interface |
CN1448863A (en) * | 2002-04-04 | 2003-10-15 | 迪吉科技有限公司 | Establishing, editing, searching of knowledge map and editing method of corresponding network information content |
CN1466046A (en) * | 2002-07-01 | 2004-01-07 | 财团法人资讯工业策进会 | Knowledge pattern system and method using ontologics as basis |
US20060277176A1 (en) * | 2005-06-01 | 2006-12-07 | Mydrew Inc. | System, method and apparatus of constructing user knowledge base for the purpose of creating an electronic marketplace over a public network |
-
2013
- 2013-09-16 CN CN201310420375.9A patent/CN103488724B/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6408302B1 (en) * | 1999-06-28 | 2002-06-18 | Davox Corporation | System and method of mapping database fields to a knowledge base using a graphical user interface |
CN1448863A (en) * | 2002-04-04 | 2003-10-15 | 迪吉科技有限公司 | Establishing, editing, searching of knowledge map and editing method of corresponding network information content |
CN1466046A (en) * | 2002-07-01 | 2004-01-07 | 财团法人资讯工业策进会 | Knowledge pattern system and method using ontologics as basis |
US20060277176A1 (en) * | 2005-06-01 | 2006-12-07 | Mydrew Inc. | System, method and apparatus of constructing user knowledge base for the purpose of creating an electronic marketplace over a public network |
Cited By (99)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104102713A (en) * | 2014-07-16 | 2014-10-15 | 百度在线网络技术(北京)有限公司 | Method and device for displaying recommendation results |
CN104102713B (en) * | 2014-07-16 | 2018-01-19 | 百度在线网络技术(北京)有限公司 | Recommendation results show method and apparatus |
CN104133916A (en) * | 2014-08-14 | 2014-11-05 | 百度在线网络技术(北京)有限公司 | Search result information organizational method and device |
CN104462227A (en) * | 2014-11-13 | 2015-03-25 | 中国测绘科学研究院 | Automatic construction method of graphic knowledge genealogy |
CN104408148A (en) * | 2014-12-03 | 2015-03-11 | 复旦大学 | Field encyclopedia establishment system based on general encyclopedia websites |
CN104408148B (en) * | 2014-12-03 | 2017-12-01 | 复旦大学 | A kind of field encyclopaedia constructing system based on general encyclopaedia website |
CN105117115A (en) * | 2015-08-07 | 2015-12-02 | 小米科技有限责任公司 | Method and device for displaying electronic document |
CN105117115B (en) * | 2015-08-07 | 2018-05-08 | 小米科技有限责任公司 | A kind of method and apparatus for showing electronic document |
CN105574098A (en) * | 2015-12-11 | 2016-05-11 | 百度在线网络技术(北京)有限公司 | Knowledge graph generation method and device and entity comparing method and device |
CN105574098B (en) * | 2015-12-11 | 2019-02-12 | 百度在线网络技术(北京)有限公司 | The generation method and device of knowledge mapping, entity control methods and device |
CN105824802A (en) * | 2016-03-31 | 2016-08-03 | 清华大学 | Method and device for acquiring knowledge graph vectoring expression |
CN105824802B (en) * | 2016-03-31 | 2018-10-30 | 清华大学 | It is a kind of to obtain the method and device that knowledge mapping vectorization indicates |
CN105912656A (en) * | 2016-04-07 | 2016-08-31 | 桂林电子科技大学 | Construction method of commodity knowledge graph |
CN105912656B (en) * | 2016-04-07 | 2020-03-17 | 桂林电子科技大学 | Method for constructing commodity knowledge graph |
CN107391512B (en) * | 2016-05-17 | 2021-05-11 | 北京邮电大学 | Method and device for predicting knowledge graph |
CN107391512A (en) * | 2016-05-17 | 2017-11-24 | 北京邮电大学 | The method and apparatus of knowledge mapping prediction |
CN106095748A (en) * | 2016-06-06 | 2016-11-09 | 东软集团股份有限公司 | A kind of method and device generating event relation collection of illustrative plates |
CN107894884A (en) * | 2016-09-30 | 2018-04-10 | 中国电子科技集团公司信息科学研究院 | Object representation device and its description method |
CN108463818A (en) * | 2016-10-31 | 2018-08-28 | 微软技术许可有限责任公司 | Establish and update connection segment collection of illustrative plates |
CN108073587A (en) * | 2016-11-09 | 2018-05-25 | 阿里巴巴集团控股有限公司 | A kind of automatic question-answering method, device and electronic equipment |
CN106776564A (en) * | 2016-12-21 | 2017-05-31 | 张永成 | The method for recognizing semantics and system of a kind of knowledge based collection of illustrative plates |
CN106874378B (en) * | 2017-01-05 | 2020-06-02 | 北京工商大学 | Method for constructing knowledge graph based on entity extraction and relation mining of rule model |
CN106874378A (en) * | 2017-01-05 | 2017-06-20 | 北京工商大学 | The entity of rule-based model extracts the method that knowledge mapping is built with relation excavation |
US10579689B2 (en) | 2017-02-08 | 2020-03-03 | International Business Machines Corporation | Visualization and augmentation of human knowledge construction during material consumption |
US11250086B2 (en) | 2017-02-08 | 2022-02-15 | International Business Machines Corporation | Visualization and augmentation of human knowledge construction during material consumption |
CN106875014A (en) * | 2017-03-02 | 2017-06-20 | 上海交通大学 | The automation of the soft project knowledge base based on semi-supervised learning builds implementation method |
CN106934032A (en) * | 2017-03-14 | 2017-07-07 | 软通动力信息技术(集团)有限公司 | A kind of city knowledge mapping construction method and device |
CN106934032B (en) * | 2017-03-14 | 2019-10-18 | 北京软通智城科技有限公司 | A kind of city knowledge mapping construction method and device |
CN106933806A (en) * | 2017-03-15 | 2017-07-07 | 北京大数医达科技有限公司 | The determination method and apparatus of medical synonym |
CN106951526B (en) * | 2017-03-21 | 2020-08-07 | 北京邮电大学 | Entity set extension method and device |
CN106951526A (en) * | 2017-03-21 | 2017-07-14 | 北京邮电大学 | A kind of entity set extended method and device |
CN108694177A (en) * | 2017-04-06 | 2018-10-23 | 北大方正集团有限公司 | Knowledge mapping construction method and system |
CN107038261A (en) * | 2017-05-28 | 2017-08-11 | 海南大学 | A kind of processing framework resource based on data collection of illustrative plates, Information Atlas and knowledge mapping can Dynamic and Abstract Semantic Modeling Method |
CN107103100A (en) * | 2017-06-10 | 2017-08-29 | 海南大学 | A kind of fault-tolerant intelligent semantic searching method based on data collection of illustrative plates, Information Atlas and knowledge mapping framework for putting into driving |
CN109241289A (en) * | 2017-07-04 | 2019-01-18 | 北京国双科技有限公司 | Entity information map extending method and device |
CN107330125A (en) * | 2017-07-20 | 2017-11-07 | 云南电网有限责任公司电力科学研究院 | The unstructured distribution data integrated approach of magnanimity of knowledge based graphical spectrum technology |
CN107330125B (en) * | 2017-07-20 | 2020-06-30 | 云南电网有限责任公司电力科学研究院 | Mass unstructured distribution network data integration method based on knowledge graph technology |
CN107609052B (en) * | 2017-08-23 | 2019-09-24 | 中国科学院软件研究所 | A kind of generation method and device of the domain knowledge map based on semantic triangle |
CN107609052A (en) * | 2017-08-23 | 2018-01-19 | 中国科学院软件研究所 | A kind of generation method and device of the domain knowledge collection of illustrative plates based on semantic triangle |
CN107704637B (en) * | 2017-11-20 | 2019-12-13 | 中国人民解放军国防科技大学 | knowledge graph construction method for emergency |
CN107704637A (en) * | 2017-11-20 | 2018-02-16 | 中国人民解放军国防科技大学 | Knowledge graph construction method for emergency |
CN108052576B (en) * | 2017-12-08 | 2021-04-23 | 国家计算机网络与信息安全管理中心 | Method and system for constructing affair knowledge graph |
CN108052576A (en) * | 2017-12-08 | 2018-05-18 | 国家计算机网络与信息安全管理中心 | A kind of reason knowledge mapping construction method and system |
CN108182245A (en) * | 2017-12-28 | 2018-06-19 | 北京锐安科技有限公司 | The construction method and device of people's object properties classificating knowledge collection of illustrative plates |
CN108171213A (en) * | 2018-01-22 | 2018-06-15 | 北京邮电大学 | A kind of Relation extraction method for being applicable in picture and text knowledge mapping |
CN108415971B (en) * | 2018-02-08 | 2021-07-23 | 兰州智豆信息科技有限公司 | Method and device for recommending supply and demand information by using knowledge graph |
CN108415971A (en) * | 2018-02-08 | 2018-08-17 | 兰州智豆信息科技有限公司 | Recommend the method and apparatus of supply-demand information using knowledge mapping |
CN108959242A (en) * | 2018-05-08 | 2018-12-07 | 中国科学院信息工程研究所 | A kind of target entity recognition methods and device based on Chinese character part of speech feature |
CN108710695A (en) * | 2018-05-23 | 2018-10-26 | 掌阅科技股份有限公司 | Mind map generation method based on e-book and electronic equipment |
CN108710695B (en) * | 2018-05-23 | 2019-08-06 | 掌阅科技股份有限公司 | Mind map generation method and electronic equipment based on e-book |
CN108920527A (en) * | 2018-06-07 | 2018-11-30 | 桂林电子科技大学 | A kind of personalized recommendation method of knowledge based map |
CN108829865A (en) * | 2018-06-22 | 2018-11-16 | 海信集团有限公司 | Information retrieval method and device |
CN109189942A (en) * | 2018-09-12 | 2019-01-11 | 山东大学 | A kind of construction method and device of patent data knowledge mapping |
CN112823332A (en) * | 2018-10-10 | 2021-05-18 | N3有限责任公司 | Semantic industry terminology |
CN109597895B (en) * | 2018-11-09 | 2021-10-22 | 中电科大数据研究院有限公司 | Knowledge graph-based official document searching method |
CN109522551B (en) * | 2018-11-09 | 2024-02-20 | 天津新开心生活科技有限公司 | Entity linking method and device, storage medium and electronic equipment |
CN109597895A (en) * | 2018-11-09 | 2019-04-09 | 中电科大数据研究院有限公司 | A kind of archives search method of knowledge based map |
CN109522551A (en) * | 2018-11-09 | 2019-03-26 | 天津新开心生活科技有限公司 | Entity link method, apparatus, storage medium and electronic equipment |
CN111209407B (en) * | 2018-11-21 | 2023-06-16 | 北京嘀嘀无限科技发展有限公司 | Data processing method, device, electronic equipment and computer readable storage medium |
CN111209407A (en) * | 2018-11-21 | 2020-05-29 | 北京嘀嘀无限科技发展有限公司 | Data processing method and device, electronic equipment and computer readable storage medium |
CN111274812B (en) * | 2018-12-03 | 2023-04-18 | 阿里巴巴集团控股有限公司 | Figure relation recognition method, equipment and storage medium |
CN111274812A (en) * | 2018-12-03 | 2020-06-12 | 阿里巴巴集团控股有限公司 | Character relation recognition method, device and storage medium |
CN109766444A (en) * | 2018-12-10 | 2019-05-17 | 北京百度网讯科技有限公司 | The application database generation method and its device of knowledge mapping |
CN109739994A (en) * | 2018-12-14 | 2019-05-10 | 复旦大学 | A kind of API knowledge mapping construction method based on reference documents |
CN109739994B (en) * | 2018-12-14 | 2023-05-02 | 复旦大学 | API knowledge graph construction method based on reference document |
CN109726298A (en) * | 2019-01-08 | 2019-05-07 | 上海市研发公共服务平台管理中心 | Knowledge mapping construction method, system, terminal and medium suitable for scientific and technical literature |
WO2020143319A1 (en) * | 2019-01-08 | 2020-07-16 | 平安科技(深圳)有限公司 | Knowledge graph completion method and apparatus, computer device and storage medium |
CN109710748A (en) * | 2019-01-17 | 2019-05-03 | 北京光年无限科技有限公司 | It is a kind of to draw this reading exchange method and system towards intelligent robot |
CN109710748B (en) * | 2019-01-17 | 2021-04-27 | 北京光年无限科技有限公司 | Intelligent robot-oriented picture book reading interaction method and system |
CN109885660A (en) * | 2019-02-22 | 2019-06-14 | 上海乐言信息科技有限公司 | A kind of question answering system and method based on information retrieval that knowledge mapping is energized |
CN110008354A (en) * | 2019-04-10 | 2019-07-12 | 华侨大学 | A kind of construction method of the external Chinese studying content of knowledge based map |
CN110008354B (en) * | 2019-04-10 | 2022-06-07 | 华侨大学 | Method for constructing foreign Chinese learning content based on knowledge graph |
CN110162640A (en) * | 2019-04-28 | 2019-08-23 | 北京百度网讯科技有限公司 | Novel entities method for digging, device, computer equipment and storage medium |
CN110245239A (en) * | 2019-05-13 | 2019-09-17 | 吉林大学 | A kind of construction method and system towards automotive field knowledge mapping |
CN110275966A (en) * | 2019-07-01 | 2019-09-24 | 科大讯飞(苏州)科技有限公司 | A kind of Knowledge Extraction Method and device |
CN110532399A (en) * | 2019-08-07 | 2019-12-03 | 广州多益网络股份有限公司 | Knowledge mapping update method, system and the device of object game question answering system |
CN110489032B (en) * | 2019-08-14 | 2021-08-24 | 掌阅科技股份有限公司 | Dictionary query method for electronic book and electronic equipment |
CN110489032A (en) * | 2019-08-14 | 2019-11-22 | 掌阅科技股份有限公司 | Dictionaries query method and electronic equipment for e-book |
CN110598002A (en) * | 2019-08-14 | 2019-12-20 | 广州视源电子科技股份有限公司 | Knowledge graph library construction method and device, computer storage medium and electronic equipment |
WO2021073254A1 (en) * | 2019-10-18 | 2021-04-22 | 平安科技(深圳)有限公司 | Knowledge graph-based entity linking method and apparatus, device, and storage medium |
CN111091006A (en) * | 2019-12-20 | 2020-05-01 | 北京百度网讯科技有限公司 | Entity intention system establishing method, device, equipment and medium |
CN111091006B (en) * | 2019-12-20 | 2023-08-29 | 北京百度网讯科技有限公司 | Method, device, equipment and medium for establishing entity intention system |
TWI747220B (en) * | 2020-03-31 | 2021-11-21 | 股感生活金融科技股份有限公司 | Knowledge graph association search method and system |
CN111581376A (en) * | 2020-04-17 | 2020-08-25 | 中国船舶重工集团公司第七一四研究所 | Automatic knowledge graph construction system and method |
CN111581376B (en) * | 2020-04-17 | 2024-04-19 | 中国船舶重工集团公司第七一四研究所 | Automatic knowledge graph construction system and method |
CN111708892B (en) * | 2020-04-24 | 2021-08-03 | 陆洋 | Database system based on depth knowledge graph |
CN111708892A (en) * | 2020-04-24 | 2020-09-25 | 陆洋 | Database system based on depth knowledge graph |
CN112100396A (en) * | 2020-08-28 | 2020-12-18 | 泰康保险集团股份有限公司 | Data processing method and device |
CN112100396B (en) * | 2020-08-28 | 2023-10-27 | 泰康保险集团股份有限公司 | Data processing method and device |
CN112256835A (en) * | 2020-10-29 | 2021-01-22 | 东南大学 | Subgraph extraction method for accurately describing element semantics in knowledge graph |
CN112463980A (en) * | 2020-11-25 | 2021-03-09 | 南京摄星智能科技有限公司 | Intelligent plan recommendation method based on knowledge graph |
CN112597285A (en) * | 2020-12-10 | 2021-04-02 | 太极计算机股份有限公司 | Man-machine interaction method and system based on knowledge graph |
CN112487212A (en) * | 2020-12-18 | 2021-03-12 | 清华大学 | Method and device for constructing domain knowledge graph |
CN112632226B (en) * | 2020-12-29 | 2021-10-26 | 天津汇智星源信息技术有限公司 | Semantic search method and device based on legal knowledge graph and electronic equipment |
CN112632226A (en) * | 2020-12-29 | 2021-04-09 | 天津汇智星源信息技术有限公司 | Semantic search method and device based on legal knowledge graph and electronic equipment |
CN112749284A (en) * | 2020-12-31 | 2021-05-04 | 平安科技(深圳)有限公司 | Knowledge graph construction method, device, equipment and storage medium |
CN112749284B (en) * | 2020-12-31 | 2021-12-17 | 平安科技(深圳)有限公司 | Knowledge graph construction method, device, equipment and storage medium |
CN113326697A (en) * | 2021-05-31 | 2021-08-31 | 云南电网有限责任公司电力科学研究院 | Knowledge graph-based electric power text entity semantic understanding method |
CN113297347A (en) * | 2021-06-29 | 2021-08-24 | 中国人民解放军国防科技大学 | Intelligent auxiliary method, system and storage medium for professional document reading |
Also Published As
Publication number | Publication date |
---|---|
CN103488724B (en) | 2016-09-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103488724B (en) | A kind of reading domain knowledge map construction method towards books | |
CN110633409B (en) | Automobile news event extraction method integrating rules and deep learning | |
CN106776711B (en) | Chinese medical knowledge map construction method based on deep learning | |
CN109492077B (en) | Knowledge graph-based petrochemical field question-answering method and system | |
CN107957991B (en) | Entity attribute information extraction method and device based on syntax dependence | |
CN101593200B (en) | Method for classifying Chinese webpages based on keyword frequency analysis | |
CN104391942B (en) | Short essay eigen extended method based on semantic collection of illustrative plates | |
Liu et al. | An adaptive graph model for automatic image annotation | |
CN108280114B (en) | Deep learning-based user literature reading interest analysis method | |
CN105528437B (en) | A kind of question answering system construction method extracted based on structured text knowledge | |
CN107832229A (en) | A kind of system testing case automatic generating method based on NLP | |
CN105930362B (en) | Search for target identification method, device and terminal | |
CN106537370A (en) | Method and system for robust tagging of named entities in the presence of source or translation errors | |
CN105706078A (en) | Automatic definition of entity collections | |
CN106354844B (en) | Service combination package recommendation system and method based on text mining | |
CN106649666A (en) | Left-right recursion-based new word discovery method | |
CN106021392A (en) | News key information extraction method and system | |
CN111104801B (en) | Text word segmentation method, system, equipment and medium based on website domain name | |
CN109597895B (en) | Knowledge graph-based official document searching method | |
CN110888991A (en) | Sectional semantic annotation method in weak annotation environment | |
CN107656921A (en) | A kind of short text dependency analysis method based on deep learning | |
CN104268283A (en) | Method for automatically analyzing Internet web page | |
CN107145497A (en) | The method of the image of metadata selected and content matching based on image and content | |
CN114090861A (en) | Education field search engine construction method based on knowledge graph | |
Nesi et al. | Ge (o) Lo (cator): Geographic information extraction from unstructured text data and Web documents |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
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: 20160928 Termination date: 20190916 |