CN110347843A - A kind of Chinese tour field Knowledge Service Platform construction method of knowledge based map - Google Patents
A kind of Chinese tour field Knowledge Service Platform construction method of knowledge based map Download PDFInfo
- Publication number
- CN110347843A CN110347843A CN201910621399.8A CN201910621399A CN110347843A CN 110347843 A CN110347843 A CN 110347843A CN 201910621399 A CN201910621399 A CN 201910621399A CN 110347843 A CN110347843 A CN 110347843A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- entity
- tour field
- attribute
- chinese
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 26
- 238000013507 mapping Methods 0.000 claims abstract description 38
- 230000004927 fusion Effects 0.000 claims abstract description 26
- 238000013135 deep learning Methods 0.000 claims abstract description 9
- 238000007619 statistical method Methods 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims description 46
- 230000008569 process Effects 0.000 claims description 7
- 230000003993 interaction Effects 0.000 claims description 6
- 230000009193 crawling Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000012800 visualization Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 2
- 238000013500 data storage Methods 0.000 claims description 2
- 238000005065 mining Methods 0.000 claims description 2
- 230000008439 repair process Effects 0.000 claims description 2
- 238000012706 support-vector machine Methods 0.000 claims description 2
- 239000002585 base Substances 0.000 description 15
- 230000008901 benefit Effects 0.000 description 3
- 235000013305 food Nutrition 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 241000209094 Oryza Species 0.000 description 2
- 235000007164 Oryza sativa Nutrition 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006698 induction Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 235000009566 rice Nutrition 0.000 description 2
- 238000013550 semantic technology Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000012458 free base Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
-
- 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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/14—Travel agencies
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Human Resources & Organizations (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
A kind of Chinese tour field Knowledge Service Platform construction method of knowledge based map, including obtaining structuring tourism knowledge from existing Chinese encyclopaedia class knowledge base, knowledge fusion, crawl tour site page data, knowledge completion is carried out to entity Infobox attribute by Custom Attributes matching rule, tour field ontology is constructed using Stamford ontology modeling tool Prot é g é, it combines the tourism ontology of building that data are switched to RDF triplet format using D2RQ and obtains tour field knowledge mapping, the Neo4j chart database store tasks for knowledge base of travelling, wherein knowledge fusion task includes completing entity using the semantic similarity between improved deep learning Knowledge Representation Model BERT computational entity to be aligned, attribute fusion is carried out based on principle and statistical method, using majority voting algorithm It carries out triple and merges subtask.The present invention facilitates tourist to obtain one-stop comprehensive sex service.
Description
Technical field
The invention belongs to computer information processing fields, and in particular to a kind of Chinese tour field of knowledge based map is known
Know service platform construction method, this method has merged cognition calculating, knowledge representation and reasoning, information retrieval and extraction, natural language
A variety of subjects such as speech processing and semantic web, data mining and machine learning, it is semantic by being added for internet mass tourism data
(knowledge) makes data generate wisdom, completes again to knowledge, the transition process of most Zhongdao Intelligent Application Platform from data to information,
To improve the Tourist Experience of user, realize from information service to knowledge services, propagate the targets such as tourist culture.
Background technique
Knowledge mapping describes concept in objective world, entity and its relationship in the form of structuring, by the information of internet
It is expressed as the form closer to the human cognitive world, one kind is provided and preferably organizes, manages and understand internet mass information
Ability.
Ontology is the representation of knowledge basis of knowledge mapping, can be O={ C, H, P, A, I } with formalization representation, C is concept set
It closes, as transactional concept and event genus, H is the context relation set of concept, also referred to as Taxonomy knowledge, and P is to belong to
Property set, describe concept possessed by feature, A is regular collection, describe domain-planning, I is example collection, for describing reality
Body-attribute-value.With using deep learning as representative indicate study development, the table towards entity in knowledge mapping and relationship
Dendrography habit also achieves important progress.Entity and relationship are expressed as dense low-dimensional vector by representation of knowledge study, are realized
The distributed of entity and relationship is indicated, efficiently entity and relationship can be calculated, alleviate that knowledge is sparse, facilitates reality
Existing knowledge fusion, becomes the important method of knowledge mapping knowledge fusion and knowledge completion.Knowledge mapping is divided into world knowledge figure
Spectrum and two class of domain knowledge map, world knowledge map include the WordNet for describing English glossary layer semantic relation, to construct this
The form of body carries out the DBPedia of tissue to knowledge entry, and concept hierarchy and the wikipedia for merging WordNet are largely real
The YAGO of volume data, the Freebase etc. that use groups intelligent method is established, the research of Universal Chinese character knowledge mapping can trace back to
The HowNet project constructed using human-edited's mode, industry have OpenKG.CN, and Baidu is intimate, and search dog is known cube etc., academic
Boundary includes that Tsinghua University, Shanghai Communications University and Fudan University are established using Baidupedia, interaction encyclopaedia and Chinese wikipedia
Extensive knowledge mapping XLore, Zhishi.me and CN-DBpedia.Google issues knowledge graph spectral term in May, 2012
Mesh, and next-generation intelligent search engine is constructed based on this, indicate extensive knowledge in internet semantic search
Successful application.
Compared with world knowledge map, the building research of domain knowledge map is relatively fewer, and domain knowledge map is called row
Industry knowledge mapping or vertical knowledge mapping can regard the domain knowledge based on semantic technology as towards a certain specific area
There is stringent and abundant data pattern in library, so depth, knowledge to the domain knowledge because it is constructed based on industry data
Accuracy has higher requirement.Britain's British Museum is semantic by combining semantic technology to carry out collection Various types of data resource
Tissue provides knowledge services by modes such as semanteme refinement, multimedia resource marks;British Broadcasting Corporation BBC [Kobilarov
Et al, 2009] ontologies are defined in plates such as its music, sport wild animals, converts news in machine readable letter
Breath source carries out Content Management and automatically generates with report.The utilization of domestic fields knowledge mapping technology has Shanghai Library to use for reference the U.S.
Congress number frame BibFrame [Kroeger et al, 2013] beats the resource constructions knowledge hierarchy such as family tree, famous person, manuscript
It makes family tree service platform and provides ancient books evidence-based service for researchers;The Chinese Academy of Agricultural Sciences then focuses on rice subdivision field, integration
The industry resources such as paper, patent, news construct rice knowledge mapping, provide industry professional knowledge service for researcher
Platform.
China's tourist industry informatization has had more than 30 years history, but is specific to the Chinese knowledge of tour field
Map also lacks very much, seriously hinders the development and succession of China's tourist culture.And existing Chinese domain knowledge map exists
Data pattern towards different field is different, and application demand is also different, instructs without a set of general standards and specifications
The problems such as building.
In conclusion there is an urgent need to construct knowledge based map Chinese tourism Knowledge Service Platform come tissue, management and
Using the magnanimity such as food, place, row, sightseeing, shopping and entertainment tourism knowledge data, tourist is facilitated to obtain one-stop comprehensive sex service, while also more
Tourist culture is propagated well, and tourist industry is finally made to move towards tourism knowledge services from travel information service.
Summary of the invention
It is an object of the invention to be directed to above-mentioned the problems of the prior art, a kind of Chinese trip of knowledge based map is provided
Domain knowledge service platform construction method is swum, structuring tourism knowledge, knowledge are obtained from existing Chinese encyclopaedia class knowledge base
It merges, crawl tour site page data, knowledge benefit is carried out to entity Infobox attribute by Custom Attributes matching rule
Entirely, combine the tourism ontology of building will using Stamford ontology modeling tool Prot é g é building tour field ontology, using D2RQ
Data switch to RDF triplet format and obtain the Neo4j chart database store tasks of tour field knowledge mapping, knowledge base of travelling.
To achieve the goals above, the technical solution adopted by the present invention the following steps are included:
S1, knowledge acquisition: structuring tourism knowledge is obtained from existing Chinese encyclopaedia class knowledge base;
S2, knowledge fusion: first complete using the semantic similarity between deep learning Knowledge Representation Model BERT computational entity
It is aligned at entity, then attribute fusion is carried out based on principle and statistical method, triple is finally carried out using majority voting algorithm and is melted
It closes;
S3, tour site page data is crawled, knowledge benefit is carried out to entity Infobox attribute by attributes match rule
Entirely;
S4, ontological construction: tour field ontology is constructed using Stamford ontology modeling tool Prot é g é;
S5, it data is switched into RDF triplet format using D2RQ combination tour field ontology obtains tour field knowledge graph
Spectrum;
S6, data storage: by the storage of tour field knowledge mapping into Neo4j chart database;
S7, building tourism Knowledge Service Platform.
The step S1 is completed especially by following procedure: being obtained under the classification of existing Chinese encyclopaedia class knowledge base
Entity structure knowledge, the Chinese encyclopaedia class knowledge base include Zhishi.me, CN-DBpedia, and classification includes " trip
Trip ", " sightseeing ", " playing ", entity structure knowledge includes sight spot, scenic spot, historic site, city, personage, historical relic, structural knowledge
Triple data in the middle include entity name, entity brief introduction, entity Infobox attribute, entity picture;
It is final define tour field entity attributes include Chinese, the open hour, foreign language title, ticket price,
Reason position, age, literary safeguarding grades not, duration of suggesting playing, be suitable for play season, affiliated city, value, name, date of birth, go
Generation time, nationality, nickname, achievement, works, age, nationality and native place.
The specific implementation procedure of three parts is as follows in the step S2:
1) entity alignment is completed using the semantic similarity between deep learning Knowledge Representation Model BERT computational entity
Step include: firstly, using Google issue BERT Chinese language model, by its fine-tuning finely tune the stage set
Set the layer second from the bottom acquisition entity term vector that parameter obtains output layer;Then, it is calculated according to the entity term vector of acquisition different
COS distance between entity, i.e. semantic similarity;Finally, reaching entity alignment according to semantic similarity by setting threshold value
Purpose;
2) two methods can be selected by carrying out attribute fusion based on principle and statistical method, and a kind of method is from existing Chinese
Tourist entity Infobox attribute is obtained in encyclopaedic knowledge library, is known by using Python redaction rule and statistics difference
Know the different names expression of the same attribute in library, it is final to determine entity Infobox property content;Another method is by entity
Triple relationship is regarded as with attribute, is classified as Relation extraction problem, and attribute is carried out by support vector machines, text mining algorithm and is melted
It closes;
3) when carrying out triple fusion using majority voting algorithm, after entity alignment, attribute fusion, to entity triple
In the data comprising same entity and attribute carry out triple fusion, each attribute is determined by majority voting algorithm unique
Attribute value.
The step S3 is completed by following procedure: crawling the tour site page and Baidupedia, interaction encyclopaedia, Chinese
Wikipedia data carry out knowledge completion to the part that attribute knowledge in entity lacks by attributes match rule.
The step S4 is completed by following procedure: being concluded to the entity in tour field data, attribute, relationship
Summarize, determine the related notion of tour field and the hierarchical structure of classification, define entity attribute and value range, and according to
Upper knowledge carries out modeling and summarizes tourism map schema model out, big using top-down body constructing method combination Stamford
Body constructing method is constructed using ontology modeling tool Prot é g é and completes tour field ontology.
The step S5 is completed by following procedure: the R2RML standard formulated according to the RDB2RDF work group of W3C,
The data in database are mapped on customized tour field ontology by editing and being arranged mapping ruler, use D2RQ work
Tourism data in relevant database, is converted into the data of RDF format, obtains tour field knowledge mapping by tool.
It combines the tour field ontology of building that data are switched to RDF triplet format using D2RQ, obtains tour field and know
Know map to realize by following procedure: firstly, the structuring that will acquire triple form is traveled, knowledge is corresponding by designing
Database table structure is stored into relevant database;Secondly, operation order generates the mapping text of default using D2RQ tool
Part modifies mapped file according to the tourism ontology of definition and completes the tour field ontology phase for database table being mapped to building completion
In the class answered;Finally, data are switched to RDF format to obtain tour field knowledge mapping by operation order using D2RQ tool.
The step S6 is completed by following procedure: being imported Neo4j chart database by downloading RDF and is extended jar packet, repairs
Change Neo4j configuration file and creation namespace prefix, is imported into the tour field knowledge mapping of RDF format using order line
Neo4j chart database is completed tour field knowledge mapping storage to the process in Neo4j chart database.
The step S7 tour field knowledge mapping store complete on the basis of, from the background using Java programming language and
Tourism knowledge is built using the visualization component of JSP dynamic web page technique and D3.js data-driven in SpringMVC framework, foreground
Service platform.
Compared with prior art, by the present invention in that with improved deep learning Knowledge Representation Model BERT computational entity
Between semantic similarity complete entity alignment, compare test with other Knowledge Representation Models, entity alignment accuracy rate is most
It is high.By carrying out induction and conclusion to the entity (concept) in tour field data, attribute, relationship, it is determined that the phase of tour field
The hierarchical structure for closing concept and classification defines entity attribute and value range, and carries out modeling according to the above knowledge and summarize
Tourism map schema model out, new classification relationship is defined in conjunction with tourism industry feature, using top-down ontology structure
The ontological construction " seven footworks " of construction method combination Stanford University is constructed using ontology modeling tool Prot é g é and completes tourism neck
Domain ontological construction is to current domain body building shortage system, general, engineering implementation method, codes and standards
Once benefit our pursuits.The present invention uses tour field knowledge base RDF triple Neo4j chart database storage scheme, Ke Yichong
The support of the more perfect figure query language and algorithm provided using primary knowledge store medium (Neo4j) itself is provided.It is based on
The tourism Knowledge Service Platform of this method building can be calculated in conjunction with figure excavation and knowledge reasoning is energized, and travel industry takes from information
Knowledge services are moved towards in business.
Detailed description of the invention
The flow diagram of Fig. 1 construction method of the present invention;
Fig. 2 knowledge fusion stage entity of the present invention is aligned implementation process schematic diagram;
Fig. 3 present invention tourism knowledge mapping knowledge Modeling schema model schematic.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and embodiments.
Referring to Fig. 1, the present invention is based on the Chinese tour field Knowledge Service Platform construction method of knowledge mapping, including it is following
Step:
S1: structuring tourism knowledge knowledge acquisition: is obtained from existing Chinese encyclopaedic knowledge class knowledge base;
From existing Chinese encyclopaedia class knowledge base Zhishi.me, CN-DBpedia, (its official website provides free RDF triple lattice
The downloading of formula data, data include Baidupedia, interaction encyclopaedia and Chinese wikipedia knowledge) " tourism ", " sightseeing ", " playing "
Obtaining entity structures knowledge, the structural knowledges such as sight spot, scenic spot, historic site, city, personage, historical relic under equal classification includes: entity
The triples data such as title, entity brief introduction (Abstracts), entity Infobox attribute, entity picture.
It is final define tour field entity attributes include: Chinese, the open hour, foreign language title, ticket price,
Reason position, age, literary safeguarding grades not, duration of suggesting playing, be suitable for play season, affiliated city, value, name, date of birth, go
Generation time, nationality, nickname, achievement, works, age, nationality, native place.
S2: knowledge fusion: knowledge fusion process includes three parts, is using improved deep learning knowledge table respectively
Semantic similarity between representation model BERT computational entity completes entity alignment, carries out attribute using based on principle and statistical method
It merges and carries out triple fusions based on most (Majority Voting) algorithms of voting using a kind of.
1. being completed using the semantic similarity between improved deep learning Knowledge Representation Model BERT computational entity real
Body alignment;
Entity alignment realization process of the present invention is as shown in Fig. 2, firstly, the entity got during S1 is arranged to text
Data set is constituted in document, and the BERT Chinese language model of Google publication is used under Linux platform Tensorflow environment
It is held as service (Server), obtains the layer second from the bottom of output layer in its fine tuning (fine-tuning) stage setting parameter,
The client (Client) of windows platform, which holds, obtains entity term vector;Secondly, calculating different realities according to the entity term vector of acquisition
COS distance between body, i.e. semantic similarity;Finally, achieving the purpose that entity is aligned according to semantic similarity.
2. carrying out attribute fusion based on principle and statistical method;
Tourist entity Infobox attribute is obtained from existing Chinese encyclopaedic knowledge library, is write by using Python
Same attribute in regular (regular expression) knowledge base different with statistics different names expression (such as: the date of birth with out
The raw time), it is final to determine entity Infobox property content.Such as: have for " geographical location " the attribute value description at " temple Ling Gu "
At about 1.5 kms, at 1.5 kilometers of the Nanjing Zhongshan Tomb east and Nanjing to the east of the Zhongshan Tomb, according to accuracy principle
With most of principles select second as attribute value.
3. carrying out triple fusion based on most ballot (Majority Voting) algorithms using a kind of;
Be aligned in above-mentioned entity, after attribute fusion, to include in entity triple same entity and attribute data into
The fusion of row triple determines unique attribute value to each attribute by majority ballot (Majority Voting) algorithm.Example
Such as: the attribute value of " building age " attribute in " Xi'an clock tower " entity is described in Baidupedia, interaction encyclopaedia, Chinese Wiki
In encyclopaedia be respectively bright Hong Wushi 7 years (1384), Ming Hongwu 17 years (1384), it is bright, according to majority voting algorithm, I
Finally determine unique triple data (Xi'an clock tower, build the age, Ming Hongwu 17 years (1384)).
S3: crawling tour site page data, is known by Custom Attributes matching rule entity Infobox attribute
Know completion.The tour site page and Baidupedia, interaction encyclopaedia, Chinese wikipedia text data are crawled, customized category is passed through
Property matching rule (regular expression) in entity attribute knowledge lack part carry out knowledge completion.Such as " to scenic spot
Reason position " attribute carry out completion when canonical matching template be " (be located at | be seated | be located at | position exists) [^, | ^.]+", to people
Canonical matching template when " nickname " attribute of object carries out completion be " (person | be commonly called as | original name | also known as | also name | also known as | pseudonym |
Assumed name) [^, | ^.]+".
S4: tour field ontology ontological construction: is constructed using Stamford ontology modeling tool Prot é g é
The present invention is by carrying out induction and conclusion to the entity (concept) in tour field data, attribute, relationship, it is determined that trip
The related notion in trip field and the hierarchical structure of classification, define entity attribute and value range, and according to the above knowledge into
Row modeling summarizes tourism map schema model out, then using top-down body constructing method combination Stanford University
Ontological construction " seven footworks " is constructed using ontology modeling tool Prot é g é and completes tour field ontology.Specific top layer is tourism,
Determine three big second level classifications: scenic spot, city, personage, second level class includes: to know, mode of transportation, scenic spot, drink food, shelter again now
Place, amusement, sightseeing, study;Attribute value type includes integer type (int), character string (string), date type (date) etc.;
Relationship between entity is in original four kinds of fundamental relations (part-of: part and whole relationship, kind-of: parent and son
Relationship, instance-of between class: relationship, attribute-of between class and example: the attribute of class, including object category
Property and data attribute) basis on, according to tour field ontology task need and specific feature define some other relationship, have
Body includes following situations:
1.birth-of: personage's date of birth is defined, can be used for age and the question and answer of reasoning personage;
2.time-of: duration of playing is suggested in definition, is tourist's one of problem the most deeply concerned;
3.specialties-of: it defines local featured delicious food and recommends, can be used for question and answer and diet semantic search;
4.accprice-of: defining lodging price, is equally tourist's one of problem the most deeply concerned.
Tourism map schema model of the invention is as shown in Figure 3, it is determined that tourist map composes the big second level classification of schema tri-:
Relationship between scenic spot, city, personage and three illustrates part attribute and attribute value datatype.
S5: it combines the tourism ontology of building that data are switched to RDF triplet format using D2RQ and obtains tourism knowledge mapping.
The acquisition of tour field knowledge mapping of the present invention is realized especially by following procedure:
According to the R2RML standard that the RDB2RDF work group of W3C formulates, by editing and being arranged mapping ruler data
Data in library are mapped on the tour field ontology of oneself definition.Table name in database corresponds to the concept in knowledge mapping,
Column name corresponds to attribute, and train value corresponds to attribute value, constrains corresponding relationship between table.Specifically used D2RQ tool, by relevant database
In tourism data be converted into the data of RDF format, to obtain tour field knowledge mapping.Wherein combined using D2RQ tool
The tourism ontology of building by data switch to RDF triplet format obtain tourism knowledge mapping by following procedure realization:
Firstly, the structuring tourism knowledge of (entity, attribute, the attribute value) triple form that will acquire passes through design pair
The database table structure answered is stored into relevant database;
Secondly, operation order generates the mapped file of default using D2RQ tool, reflected according to the modification of the tourism ontology of definition
File is penetrated to complete to be mapped to database table in the corresponding class of tour field ontology that building is completed;
Finally, data are switched to RDF format to obtain tour field knowledge mapping by operation order using D2RQ tool.
S6: by tourism knowledge base storage into Neo4j chart database.
Knowledge base of travelling in present invention storage is realized into Neo4j chart database especially by following procedure:
Neo4j chart database, which is imported, by downloading RDF extends jar packet, modification Neo4j configuration file and creation NameSpace
The tour field knowledge base of RDF format is imported into Neo4j chart database in Neo4j console operating instruction by prefix, and completing will
Knowledge base of travelling is stored to the process in Neo4j chart database.
S7: building tourism Knowledge Service Platform on the basis of knowledge base storage of travelling is completed.
The present invention building for Knowledge Service Platform of tourism is realized especially by following procedure:
Made from the background using Java programming language and SpringMVC framework, foreground on the basis of knowledge base storage of travelling is completed
Tourism Knowledge Service Platform is built with the visualization component of JSP dynamic web page technique and D3.js data-driven.
So far, a kind of Chinese tourism Knowledge Service Platform construction method of knowledge based map is fully completed.
By adding semantic (knowledge) for internet mass tourism data, so that data is generated wisdom, complete from data to letter
Breath arrives the transition process of knowledge, most Zhongdao Intelligent Application Platform again, realizes from information service to knowledge services, propagates tourist culture
Etc. targets.
It should be noted that a kind of Chinese tourism Knowledge Service Platform structure of knowledge based map provided by the above embodiment
Construction method, only just above-mentioned each functional steps are illustrated, and can according to need in practical application and carry out above-mentioned steps
Combination is rearranged to complete corresponding function, the purpose that details is introduced in specific embodiment is not the model for limiting claims
It encloses, and is to aid in and understands the method for the invention.Usual skill is all in spirit of the invention in technical field of the present invention
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (9)
1. a kind of Chinese tour field Knowledge Service Platform construction method of knowledge based map, which is characterized in that comprising steps of
S1, knowledge acquisition: structuring tourism knowledge is obtained from existing Chinese encyclopaedia class knowledge base;
S2, knowledge fusion: it is first completed using the semantic similarity between deep learning Knowledge Representation Model BERT computational entity real
Body alignment, then attribute fusion is carried out based on principle and statistical method, triple fusion is finally carried out using majority voting algorithm;
S3, tour site page data is crawled, knowledge completion is carried out to entity Infobox attribute by attributes match rule;
S4, ontological construction: tour field ontology is constructed using Stamford ontology modeling tool Prot é g é;
S5, it data is switched into RDF triplet format using D2RQ combination tour field ontology obtains tour field knowledge mapping;
S6, data storage: by the storage of tour field knowledge mapping into Neo4j chart database;
S7, building tourism Knowledge Service Platform.
2. the Chinese tour field Knowledge Service Platform construction method of knowledge based map according to claim 1, special
Sign is that the step S1 is completed especially by following procedure: obtaining under the classification of existing Chinese encyclopaedia class knowledge base
Entity structure knowledge, the Chinese encyclopaedia class knowledge base include Zhishi.me, CN-DBpedia, and classification includes " trip
Trip ", " sightseeing ", " playing ", entity structure knowledge includes sight spot, scenic spot, historic site, city, personage, historical relic, structural knowledge
Triple data in the middle include entity name, entity brief introduction, entity Infobox attribute, entity picture;
The final tour field entity attributes that define include Chinese, open hour, foreign language title, ticket price, geographical position
Set, the age, literary safeguarding grades not, duration of suggesting playing, be suitable for play season, affiliated city, value, name, date of birth, it is dead when
Between, nationality, nickname, achievement, works, age, nationality and native place.
3. the Chinese tour field Knowledge Service Platform construction method of knowledge based map according to claim 1, special
Sign is that the specific implementation procedure of three parts is as follows in the step S2:
1) the step of entity is aligned is completed using the semantic similarity between deep learning Knowledge Representation Model BERT computational entity
It include: firstly, the BERT Chinese language model issued using Google, is joined by finely tuning stage setting in its fine-tuning
The layer second from the bottom that number obtains output layer obtains entity term vector;Then, different entities are calculated according to the entity term vector of acquisition
Between COS distance, i.e. semantic similarity;Finally, reaching the mesh of entity alignment according to semantic similarity by setting threshold value
's;
2) two methods can be selected by carrying out attribute fusion based on principle and statistical method, and a kind of method is from existing Chinese encyclopaedia
Tourist entity Infobox attribute is obtained in knowledge base, by using Python redaction rule and the different knowledge bases of statistics
In same attribute different names expression, it is final to determine entity Infobox property content;Another method is by entity and category
Property regard triple relationship as, be classified as Relation extraction problem, pass through support vector machines, text mining algorithm carry out attribute fusion;
3) when carrying out triple fusion using majority voting algorithm, after entity alignment, attribute fusion, to being wrapped in entity triple
Triple fusion is carried out containing the data of same entity and attribute, unique attribute is determined to each attribute by majority voting algorithm
Value.
4. the Chinese tour field Knowledge Service Platform construction method of knowledge based map according to claim 1, special
Sign is that the step S3 is completed by following procedure: crawling the tour site page and Baidupedia, interaction encyclopaedia, Chinese
Wikipedia data carry out knowledge completion to the part that attribute knowledge in entity lacks by attributes match rule.
5. the Chinese tour field Knowledge Service Platform construction method of knowledge based map according to claim 1, special
Sign is that the step S4 is completed by following procedure: being concluded to the entity in tour field data, attribute, relationship
Summarize, determine the related notion of tour field and the hierarchical structure of classification, define entity attribute and value range, and according to
Upper knowledge carries out modeling and summarizes tourism map schema model out, big using top-down body constructing method combination Stamford
Body constructing method is constructed using ontology modeling tool Prot é g é and completes tour field ontology.
6. the Chinese tour field Knowledge Service Platform construction method of knowledge based map according to claim 1, special
Sign is that the step S5 is completed by following procedure: the R2RML standard formulated according to the RDB2RDF work group of W3C,
The data in database are mapped on customized tour field ontology by editing and being arranged mapping ruler, use D2RQ work
Tourism data in relevant database, is converted into the data of RDF format, obtains tour field knowledge mapping by tool.
7. the Chinese tour field Knowledge Service Platform construction method of knowledge based map according to claim 6, special
Sign is, combines the tour field ontology of building that data are switched to RDF triplet format using D2RQ, obtains tour field knowledge
Map is realized by following procedure: firstly, the structuring that will acquire triple form travels knowledge by designing corresponding number
According to database table structure storage into relevant database;Secondly, operation order generates the mapped file of default using D2RQ tool,
It is corresponding that the tour field ontology that database table is mapped to building completion by mapped file completion is modified according to the tourism ontology of definition
Class on;Finally, data are switched to RDF format to obtain tour field knowledge mapping by operation order using D2RQ tool.
8. the Chinese tour field Knowledge Service Platform construction method of knowledge based map according to claim 1, special
Sign is that the step S6 is completed by following procedure: importing Neo4j chart database by downloading RDF and extends jar packet, repairs
Change Neo4j configuration file and creation namespace prefix, is imported into the tour field knowledge mapping of RDF format using order line
Neo4j chart database is completed tour field knowledge mapping storage to the process in Neo4j chart database.
9. the Chinese tour field Knowledge Service Platform construction method of knowledge based map according to claim 1, special
Sign is that step S7 uses Java programming language and SpringMVC on the basis of tour field knowledge mapping stores completion from the background
Tourism Knowledge Service Platform is built using the visualization component of JSP dynamic web page technique and D3.js data-driven in framework, foreground.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910621399.8A CN110347843B (en) | 2019-07-10 | 2019-07-10 | Knowledge map-based Chinese tourism field knowledge service platform construction method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910621399.8A CN110347843B (en) | 2019-07-10 | 2019-07-10 | Knowledge map-based Chinese tourism field knowledge service platform construction method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110347843A true CN110347843A (en) | 2019-10-18 |
CN110347843B CN110347843B (en) | 2022-04-15 |
Family
ID=68175783
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910621399.8A Active CN110347843B (en) | 2019-07-10 | 2019-07-10 | Knowledge map-based Chinese tourism field knowledge service platform construction method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110347843B (en) |
Cited By (33)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110826316A (en) * | 2019-11-06 | 2020-02-21 | 北京交通大学 | Method for identifying sensitive information applied to referee document |
CN110928963A (en) * | 2019-11-28 | 2020-03-27 | 西安理工大学 | Column-level authority knowledge graph construction method for operation and maintenance service data table |
CN110990417A (en) * | 2019-12-13 | 2020-04-10 | 陕西师范大学 | Crowdsourcing-based Chinese tourism field knowledge service platform knowledge base updating method |
CN111191050A (en) * | 2020-01-03 | 2020-05-22 | 中国建设银行股份有限公司 | Method and device for constructing knowledge graph body model |
CN111241835A (en) * | 2019-11-15 | 2020-06-05 | 上海景域文化传播股份有限公司 | Tourist map-based one-player scenic spot tourist knowledge embedding method and device |
CN111291132A (en) * | 2020-01-14 | 2020-06-16 | 常州大学 | Cultural relic field ontology construction and analysis method for smart tourism |
CN111324691A (en) * | 2020-01-06 | 2020-06-23 | 大连民族大学 | Intelligent question-answering method for minority nationality field based on knowledge graph |
CN111538847A (en) * | 2020-04-16 | 2020-08-14 | 北方民族大学 | Ningxia rice knowledge graph construction method |
CN111753099A (en) * | 2020-06-28 | 2020-10-09 | 中国农业科学院农业信息研究所 | Method and system for enhancing file entity association degree based on knowledge graph |
CN111753100A (en) * | 2020-06-30 | 2020-10-09 | 广州小鹏车联网科技有限公司 | Knowledge graph generation method and server for vehicle-mounted application |
CN111832282A (en) * | 2020-07-16 | 2020-10-27 | 平安科技(深圳)有限公司 | External knowledge fused BERT model fine adjustment method and device and computer equipment |
CN112100395A (en) * | 2020-08-11 | 2020-12-18 | 淮阴工学院 | Expert cooperation feasibility analysis method |
CN112149423A (en) * | 2020-10-16 | 2020-12-29 | 中国农业科学院农业信息研究所 | Corpus labeling method and system for domain-oriented entity relationship joint extraction |
CN112182241A (en) * | 2020-09-24 | 2021-01-05 | 四川大学 | Automatic construction method of knowledge graph in field of air traffic control |
CN112199515A (en) * | 2020-11-17 | 2021-01-08 | 西安交通大学 | Polymorphic knowledge map driven knowledge service innovation method |
CN112612902A (en) * | 2020-12-23 | 2021-04-06 | 国网浙江省电力有限公司电力科学研究院 | Knowledge graph construction method and device for power grid main device |
CN112650855A (en) * | 2020-12-26 | 2021-04-13 | 曙光信息产业股份有限公司 | Knowledge graph engineering construction method and device, computer equipment and storage medium |
CN112650821A (en) * | 2021-01-20 | 2021-04-13 | 济南浪潮高新科技投资发展有限公司 | Entity alignment method fusing Wikidata |
CN112699248A (en) * | 2020-12-24 | 2021-04-23 | 厦门市美亚柏科信息股份有限公司 | Knowledge ontology construction method, terminal equipment and storage medium |
CN113065003A (en) * | 2021-04-22 | 2021-07-02 | 国际关系学院 | Knowledge graph generation method based on multiple indexes |
CN113190689A (en) * | 2021-05-25 | 2021-07-30 | 广东电网有限责任公司广州供电局 | Construction method, device, equipment and medium of electric power safety knowledge graph |
CN113204652A (en) * | 2021-07-05 | 2021-08-03 | 北京邮电大学 | Knowledge representation learning method and device |
CN113392220A (en) * | 2020-10-23 | 2021-09-14 | 腾讯科技(深圳)有限公司 | Knowledge graph generation method and device, computer equipment and storage medium |
CN113407688A (en) * | 2021-06-15 | 2021-09-17 | 西安理工大学 | Method for establishing knowledge graph-based survey standard intelligent question-answering system |
CN113468255A (en) * | 2021-06-25 | 2021-10-01 | 西安电子科技大学 | Knowledge graph-based data fusion method in social security comprehensive treatment field |
CN113535986A (en) * | 2021-09-02 | 2021-10-22 | 中国医学科学院医学信息研究所 | Data fusion method and device applied to medical knowledge graph |
CN113821647A (en) * | 2021-11-22 | 2021-12-21 | 山东捷瑞数字科技股份有限公司 | Construction method and system of knowledge graph in engineering machinery industry |
CN113901238A (en) * | 2021-12-07 | 2022-01-07 | 武大吉奥信息技术有限公司 | City physical examination index knowledge graph construction method and system |
CN114238653A (en) * | 2021-12-08 | 2022-03-25 | 华东师范大学 | Method for establishing, complementing and intelligently asking and answering knowledge graph of programming education |
CN114328980A (en) * | 2022-03-14 | 2022-04-12 | 来也科技(北京)有限公司 | Knowledge graph construction method and device combining RPA and AI, terminal and storage medium |
CN115269931A (en) * | 2022-09-28 | 2022-11-01 | 深圳技术大学 | Rail transit station data map system based on service drive and construction method thereof |
CN116304092A (en) * | 2023-03-02 | 2023-06-23 | 深圳今日人才信息科技有限公司 | Method for automatically acquiring job concepts and expanding map for recruitment field |
CN116304092B (en) * | 2023-03-02 | 2024-09-24 | 深圳今日人才信息科技有限公司 | Method for automatically acquiring job concepts and expanding map for recruitment field |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106777274A (en) * | 2016-06-16 | 2017-05-31 | 北京理工大学 | A kind of Chinese tour field knowledge mapping construction method and system |
CN109284394A (en) * | 2018-09-12 | 2019-01-29 | 青岛大学 | A method of Company Knowledge map is constructed from multi-source data integration visual angle |
-
2019
- 2019-07-10 CN CN201910621399.8A patent/CN110347843B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106777274A (en) * | 2016-06-16 | 2017-05-31 | 北京理工大学 | A kind of Chinese tour field knowledge mapping construction method and system |
CN109284394A (en) * | 2018-09-12 | 2019-01-29 | 青岛大学 | A method of Company Knowledge map is constructed from multi-source data integration visual angle |
Non-Patent Citations (1)
Title |
---|
贾中浩等: "旅游知识图谱特征学习的景点推荐", 《智能系统学报》 * |
Cited By (53)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110826316B (en) * | 2019-11-06 | 2021-08-10 | 北京交通大学 | Method for identifying sensitive information applied to referee document |
CN110826316A (en) * | 2019-11-06 | 2020-02-21 | 北京交通大学 | Method for identifying sensitive information applied to referee document |
CN111241835A (en) * | 2019-11-15 | 2020-06-05 | 上海景域文化传播股份有限公司 | Tourist map-based one-player scenic spot tourist knowledge embedding method and device |
CN111241835B (en) * | 2019-11-15 | 2021-12-14 | 上海景域文化传播股份有限公司 | Tourist map-based one-player scenic spot tourist knowledge embedding method and device |
CN110928963A (en) * | 2019-11-28 | 2020-03-27 | 西安理工大学 | Column-level authority knowledge graph construction method for operation and maintenance service data table |
CN110928963B (en) * | 2019-11-28 | 2023-10-24 | 西安理工大学 | Column-level authority knowledge graph construction method for operation and maintenance service data table |
CN110990417A (en) * | 2019-12-13 | 2020-04-10 | 陕西师范大学 | Crowdsourcing-based Chinese tourism field knowledge service platform knowledge base updating method |
CN111191050B (en) * | 2020-01-03 | 2023-07-04 | 中国建设银行股份有限公司 | Knowledge graph ontology model construction method and device |
CN111191050A (en) * | 2020-01-03 | 2020-05-22 | 中国建设银行股份有限公司 | Method and device for constructing knowledge graph body model |
CN111324691A (en) * | 2020-01-06 | 2020-06-23 | 大连民族大学 | Intelligent question-answering method for minority nationality field based on knowledge graph |
CN111291132A (en) * | 2020-01-14 | 2020-06-16 | 常州大学 | Cultural relic field ontology construction and analysis method for smart tourism |
CN111291132B (en) * | 2020-01-14 | 2024-04-02 | 常州大学 | Cultural relic field ontology construction and analysis method for intelligent travel |
CN111538847A (en) * | 2020-04-16 | 2020-08-14 | 北方民族大学 | Ningxia rice knowledge graph construction method |
CN111753099B (en) * | 2020-06-28 | 2023-11-21 | 中国农业科学院农业信息研究所 | Method and system for enhancing relevance of archive entity based on knowledge graph |
CN111753099A (en) * | 2020-06-28 | 2020-10-09 | 中国农业科学院农业信息研究所 | Method and system for enhancing file entity association degree based on knowledge graph |
CN111753100A (en) * | 2020-06-30 | 2020-10-09 | 广州小鹏车联网科技有限公司 | Knowledge graph generation method and server for vehicle-mounted application |
CN111832282A (en) * | 2020-07-16 | 2020-10-27 | 平安科技(深圳)有限公司 | External knowledge fused BERT model fine adjustment method and device and computer equipment |
CN112100395A (en) * | 2020-08-11 | 2020-12-18 | 淮阴工学院 | Expert cooperation feasibility analysis method |
CN112100395B (en) * | 2020-08-11 | 2024-03-29 | 淮阴工学院 | Expert cooperation feasibility analysis method |
CN112182241A (en) * | 2020-09-24 | 2021-01-05 | 四川大学 | Automatic construction method of knowledge graph in field of air traffic control |
CN112149423A (en) * | 2020-10-16 | 2020-12-29 | 中国农业科学院农业信息研究所 | Corpus labeling method and system for domain-oriented entity relationship joint extraction |
CN112149423B (en) * | 2020-10-16 | 2024-01-26 | 中国农业科学院农业信息研究所 | Corpus labeling method and system for domain entity relation joint extraction |
CN113392220B (en) * | 2020-10-23 | 2024-03-26 | 腾讯科技(深圳)有限公司 | Knowledge graph generation method and device, computer equipment and storage medium |
CN113392220A (en) * | 2020-10-23 | 2021-09-14 | 腾讯科技(深圳)有限公司 | Knowledge graph generation method and device, computer equipment and storage medium |
CN112199515B (en) * | 2020-11-17 | 2023-08-15 | 西安交通大学 | Knowledge service innovation method driven by polymorphic knowledge graph |
CN112199515A (en) * | 2020-11-17 | 2021-01-08 | 西安交通大学 | Polymorphic knowledge map driven knowledge service innovation method |
CN112612902B (en) * | 2020-12-23 | 2023-07-14 | 国网浙江省电力有限公司电力科学研究院 | Knowledge graph construction method and device for power grid main equipment |
CN112612902A (en) * | 2020-12-23 | 2021-04-06 | 国网浙江省电力有限公司电力科学研究院 | Knowledge graph construction method and device for power grid main device |
CN112699248B (en) * | 2020-12-24 | 2022-09-16 | 厦门市美亚柏科信息股份有限公司 | Knowledge ontology construction method, terminal equipment and storage medium |
CN112699248A (en) * | 2020-12-24 | 2021-04-23 | 厦门市美亚柏科信息股份有限公司 | Knowledge ontology construction method, terminal equipment and storage medium |
CN112650855B (en) * | 2020-12-26 | 2022-09-13 | 曙光信息产业股份有限公司 | Knowledge graph engineering construction method and device, computer equipment and storage medium |
CN112650855A (en) * | 2020-12-26 | 2021-04-13 | 曙光信息产业股份有限公司 | Knowledge graph engineering construction method and device, computer equipment and storage medium |
CN112650821A (en) * | 2021-01-20 | 2021-04-13 | 济南浪潮高新科技投资发展有限公司 | Entity alignment method fusing Wikidata |
CN113065003A (en) * | 2021-04-22 | 2021-07-02 | 国际关系学院 | Knowledge graph generation method based on multiple indexes |
CN113190689A (en) * | 2021-05-25 | 2021-07-30 | 广东电网有限责任公司广州供电局 | Construction method, device, equipment and medium of electric power safety knowledge graph |
CN113190689B (en) * | 2021-05-25 | 2023-04-18 | 广东电网有限责任公司广州供电局 | Construction method, device, equipment and medium of electric power safety knowledge graph |
CN113407688B (en) * | 2021-06-15 | 2022-09-16 | 西安理工大学 | Method for establishing knowledge graph-based survey standard intelligent question-answering system |
CN113407688A (en) * | 2021-06-15 | 2021-09-17 | 西安理工大学 | Method for establishing knowledge graph-based survey standard intelligent question-answering system |
CN113468255A (en) * | 2021-06-25 | 2021-10-01 | 西安电子科技大学 | Knowledge graph-based data fusion method in social security comprehensive treatment field |
CN113204652A (en) * | 2021-07-05 | 2021-08-03 | 北京邮电大学 | Knowledge representation learning method and device |
CN113204652B (en) * | 2021-07-05 | 2021-09-07 | 北京邮电大学 | Knowledge representation learning method and device |
CN113535986A (en) * | 2021-09-02 | 2021-10-22 | 中国医学科学院医学信息研究所 | Data fusion method and device applied to medical knowledge graph |
CN113535986B (en) * | 2021-09-02 | 2023-05-05 | 中国医学科学院医学信息研究所 | Data fusion method and device applied to medical knowledge graph |
CN113821647B (en) * | 2021-11-22 | 2022-02-22 | 山东捷瑞数字科技股份有限公司 | Construction method and system of knowledge graph in engineering machinery industry |
CN113821647A (en) * | 2021-11-22 | 2021-12-21 | 山东捷瑞数字科技股份有限公司 | Construction method and system of knowledge graph in engineering machinery industry |
CN113901238A (en) * | 2021-12-07 | 2022-01-07 | 武大吉奥信息技术有限公司 | City physical examination index knowledge graph construction method and system |
CN114238653A (en) * | 2021-12-08 | 2022-03-25 | 华东师范大学 | Method for establishing, complementing and intelligently asking and answering knowledge graph of programming education |
CN114238653B (en) * | 2021-12-08 | 2024-05-24 | 华东师范大学 | Method for constructing programming education knowledge graph, completing and intelligently asking and answering |
CN114328980A (en) * | 2022-03-14 | 2022-04-12 | 来也科技(北京)有限公司 | Knowledge graph construction method and device combining RPA and AI, terminal and storage medium |
CN115269931B (en) * | 2022-09-28 | 2022-11-29 | 深圳技术大学 | Rail transit station data map system based on service drive and construction method thereof |
CN115269931A (en) * | 2022-09-28 | 2022-11-01 | 深圳技术大学 | Rail transit station data map system based on service drive and construction method thereof |
CN116304092A (en) * | 2023-03-02 | 2023-06-23 | 深圳今日人才信息科技有限公司 | Method for automatically acquiring job concepts and expanding map for recruitment field |
CN116304092B (en) * | 2023-03-02 | 2024-09-24 | 深圳今日人才信息科技有限公司 | Method for automatically acquiring job concepts and expanding map for recruitment field |
Also Published As
Publication number | Publication date |
---|---|
CN110347843B (en) | 2022-04-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110347843A (en) | A kind of Chinese tour field Knowledge Service Platform construction method of knowledge based map | |
CN107679661B (en) | Personalized tour route planning method based on knowledge graph | |
Scheider et al. | Geo-analytical question-answering with GIS | |
Zeng et al. | Knowledge Organization Systems (KOS) in the Semantic Web: a multi-dimensional review | |
Syed et al. | Exploiting a web of semantic data for interpreting tables | |
Jabbar et al. | A methodology of real-time data fusion for localized big data analytics | |
CN110110173A (en) | Search result rank and presentation | |
CN104903886A (en) | Structured search queries based on social-graph information | |
Abdelmoty et al. | A critical evaluation of ontology languages for geographic information retrieval on the Internet | |
CN109949174B (en) | Heterogeneous social network user entity anchor link identification method | |
CN103412903B (en) | The Internet of Things real-time searching method and system predicted based on object of interest | |
Wang et al. | Bayesian intelligent semantic mashup for tourism | |
Xiong et al. | Affective impression: Sentiment-awareness POI suggestion via embedding in heterogeneous LBSNs | |
CN109086434A (en) | A kind of knowledge polymerizing method and system based on thematic map | |
CN107943810A (en) | The construction method of building information map | |
Fonseca et al. | Automatic representation of geographical data from a semantic point of view through a new ontology and classification techniques | |
Ding et al. | Integrating 3D city data through knowledge graphs | |
CN112069306B (en) | Paper partner recommendation method based on author writing tree and graph neural network | |
Liang | Intelligent Tourism Personalized Recommendation Based on Multi‐Fusion of Clustering Algorithms | |
Xie et al. | Construction of multimodal chinese tourism knowledge graph | |
CN116595139A (en) | Intelligent question-answering method based on multi-mode knowledge graph | |
Tang et al. | Visual and language semantic hybrid enhancement and complementary for video description | |
Zhao | A resource sharing system for music education using the entropy technology | |
Li et al. | Spatio-temporal data fusion techniques for modeling digital twin City | |
Fan et al. | CuPe-KG: Cultural perspective–based knowledge graph construction of tourism resources via pretrained language models |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |