CN108509420A - Gu spectrum and ancient culture knowledge mapping natural language processing method - Google Patents
Gu spectrum and ancient culture knowledge mapping natural language processing method Download PDFInfo
- Publication number
- CN108509420A CN108509420A CN201810269797.3A CN201810269797A CN108509420A CN 108509420 A CN108509420 A CN 108509420A CN 201810269797 A CN201810269797 A CN 201810269797A CN 108509420 A CN108509420 A CN 108509420A
- Authority
- CN
- China
- Prior art keywords
- ancient
- spectrum
- data
- knowledge
- knowledge mapping
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/58—Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
The present invention provides a kind of ancient spectrum and ancient culture knowledge mapping natural language processing methods, including：According to Gu spectrum and ancient culture professional knowledge, the pattern of the knowledge mapping of ancient spectrum and ancient culture is created；Obtain data and Extracting Information；Merge knowledge, including link entity and merging knowledge；Integrated ancient spectrum and ancient culture knowledge base pattern and data, solve the conflict of pattern and data.The present invention uses natural language processing technique and knowledge mapping technology in Gu spectrum research field, it is graphically displayed ancient spectrum knowledge development process and structural relation, Gu spectrum knowledge resource and its carrier, excavation, analysis, structure and drafting explicit knowledge and connecting each other between them are described with visualization technique.It can show nuclear structure, developing history and overall architecture, reach Multidisciplinary Integration, valuable reference is provided for Gu spectrum disciplinary study.
Description
Technical field
The present invention relates to a kind of knowledge mapping generation method more particularly to a kind of ancient spectrum and ancient culture knowledge mapping nature languages
Say processing method.
Background technology
Knowledge mapping is a kind of novel the mass knowledge management and service mode generated under the historical background of big data.
It is huge, networking the knowledge system to be got up for framework construction with " semantic network ", can capture and field concept is presented
Between semantic relation.Domestic and international Internet company releases knowledge mapping to promote service quality one after another, as Google's knowledge mapping,
" know cube " of Baidu " intimate " and search dog.However, composing research field in Gu, there is presently no be capable of providing knowing for similar functions
Know collection of illustrative plates.Universal now ancient spectrum research concentrates in the research of single composition, fails to extend it using knowledge mapping technology and grind
Study carefully direction, Gu spectrum is combined with ancient culture.
Invention content
It is existed in the prior art or potential shortcoming in view of above-mentioned, the present invention provides a kind of knowledge mapping generation sides
Method generates ancient spectrum and ancient culture knowledge mapping using big data treatment technology and natural language processing method, is carried to Gu spectrum research
For technical support.
To achieve the above object, the present invention provides a kind of ancient spectrum and ancient culture knowledge mapping natural language processing method,
It includes：
Create the pattern of the knowledge mapping of ancient spectrum and ancient culture：Knowledge mapping G is by ideograph Gs, datagram GdAnd the two
Between relationship R composition, be expressed as G=<GS, Gd, R>；Ideograph Gs=<NS, PS, ES>, wherein NSIndicate the class node in figure,
PSIndicate attribute side, ESIndicate the relationship between two classes connected by multiple summits；Datagram Gd=<Nd, Pd, Ed>, NdIndicate real
Example node and character nodes, PdIndicate attribute side, EdIndicate the relationship between two nodes of multiple summits connection；Each edge and
The node on side both sides indicates subject, predicate and object；
Obtain data and Extracting Information：From on existing picture and word and internet picture concerned and word obtain
Gu spectrum and ancient culture data；For image content, optical character identification OCR (Optical Character can be taken
Recognition) identification sampling is carried out with Object Detection (Object identifying) technology；For lteral data, can pass through
Data are cut and are sub-divided into as unit of a word by the function of Chinese vocabulary table and segmenter, are based on directed acyclic graph (DAG)
It is handled with using Viterbi algorithm to apply mechanically HMM model；It is (general to extract entity from various types of data sources for Extracting Information
Read), the correlation between attribute and entity, form the knowledge representation of ontological on this basis；Extracting Information firstly the need of
Entity extraction is carried out, extracts name entity automatically mainly from a large amount of lteral datas, is needed to extract in fact between entity
Incidence relation finally also needs to the attribute information for obtaining special entity, to obtain complete data information；
Merge knowledge：After obtaining entity, relationship and entity attribute information, for eliminate concept ambiguity, avoid redundancy and
Error message needs to realize that entity link, entity disambiguate (entity disambiguation) method and be used in solution reality of the same name
The problem of body produces ambiguity；Coreference resolution (Coreference Resolution) is for solving multiple denotion items corresponding to same
The problem of entity object；Structural data in existing relevant database is dissolved into knowledge mapping, resource can be used
Describing framework RDF is expressed as data model by the data conversion of relevant database at the triple data of RDF<It is main
Language, predicate, object>Such structure；Data are extracted from multi-source data and will appear Data duplication or collision problem, to data source
Confidence level scoring is carried out, the frequency occurred based on data source and in separate sources is ranked up data item, is supplemented to
In respective attributes value field, it will be stored in the index data base of knowledge mapping after data source normalization；And
Integrated ancient spectrum and ancient culture knowledge base pattern and data：Based on above step, structuring and networking can be obtained
Knowledge hierarchy；During establishment model, when data collision occur, or can not confirm data source quality, by Gu spectrum and Gu
Cultural expert manually evaluates, and determines final result.
Using above-mentioned technical proposal, the present invention uses natural language processing technique and knowledge mapping skill in Gu spectrum research field
Art is graphically displayed ancient spectrum knowledge development process and structural relation, and ancient spectrum knowledge resource and its carrier are described with visualization technique,
It excavates, analysis, build and draw explicit knowledge and connecting each other between them.Can show nuclear structure, developing history with
And overall architecture, reach Multidisciplinary Integration, valuable reference is provided for Gu spectrum disciplinary study.
In some possible designs, in the pattern of the knowledge mapping of the ancient spectrum and ancient culture of establishment, the datagram
Data compose library and ancient culture library from ancient times.
In some possible designs, in the pattern of the knowledge mapping of the ancient spectrum and ancient culture of establishment, including ancient spectrum is general
The attribute of the attribute of thought, the specifically attribute and ancient culture concept of each first music score..
In some possible designs, the attribute of the ancient spectrum concept includes ancient spectrum title, classification, compiles author, age, version
Sheet, print process, now hide and the key to exercises in it is one or more.
In some possible designs, the attribute of the specific a certain music score includes spectrum name, classification, passes spectrum people, copies spectrum year
Generation, tune, material and printing, specification, now hide and the key to exercises in it is one or more.
In some possible designs, the attribute of the ancient culture concept includes one or more in type and dynasty.
In some possible designs, the Extracting Information the step of in, data source includes existing picture and word
And the picture concerned on internet and word.
In some possible designs, the method further includes：On the basis for establishing ancient spectrum and ancient culture knowledge mapping
Afterwards, ancient spectrum and ancient culture knowledge feedback are established, solution pattern conflicts with data.
In some possible designs, participle, the template of knowledge based collection of illustrative plates are carried out using the question and answer exchange architecture
Match and the translation of template executes.
Description of the drawings
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, other are can also be obtained according to these attached drawings
Attached drawing.
Fig. 1 is the flow chart of the ancient spectrum of structure and ancient culture knowledge mapping of the embodiment of the present invention.
Fig. 2 is the schematic diagram of the datagram of knowledge mapping in the embodiment of the present invention.
Fig. 3 is the schematic diagram of the Ming Dynasty's Gu spectrum and ancient culture knowledge mapping in the embodiment of the present invention.
Fig. 4 is the schematic diagram of the question and answer exchange architecture based on ancient spectrum and ancient culture knowledge mapping in the embodiment of the present invention.
Specific implementation mode
Illustrate that embodiments of the present invention, those skilled in the art can be by this specification below by way of specific specific example
Disclosed content understands other advantages and effect of the present invention easily.The present invention can also pass through in addition different specific realities
The mode of applying is embodied or practiced, the various details in this specification can also be based on different viewpoints with application, without departing from
Various modifications or alterations are carried out under the spirit of the present invention.
Invention broadly provides a kind of ancient spectrum and ancient culture knowledge mapping based on natural language processing, are related to one kind and know
Know collection of illustrative plates generation method, using big data treatment technology and natural language processing method, generate ancient spectrum and ancient culture knowledge mapping,
Research is composed to Gu, technical support is provided.
Knowledge mapping, the structure of knowledge mapping can be established using natural language processing technique and knowledge mapping relevant knowledge
Flow is including the use of entity extraction, text extraction, relation data conversion, data fusion, integrated knowledge database pattern and data.Mesh
Before, in Gu spectrum is studied, natural language processing technique and knowledge mapping, the present invention is not applied to be introduced certainly in Gu spectrum research
Right language processing techniques and knowledge mapping, are converted to digital information and intelligible figure by human cognitive information, utilize computer
Processing method and internet the relevant technologies provide new idea and method for Gu spectrum research.In the following with reference to the drawings and specific embodiments
To be described in further details to the present invention.
As shown in fig.1, in figure paraphrase ancient spectrum of the invention and ancient culture knowledge mapping natural language processing method one
Kind realization method includes mainly following steps：1, the pattern of the knowledge mapping of ancient spectrum and ancient culture is created；2, number is obtained
According to and Extracting Information；3, knowledge is merged；4, ancient spectrum and ancient culture knowledge base pattern and data are integrated.
Expansion explanation is carried out to each step below.
1, professional knowledge is composed according to Gu, creates the pattern of the knowledge mapping of ancient spectrum and ancient culture：
The ancient spectrum knowledge mapping G of definition is by ancient spectral model figure Gs, ancient modal data figure GdAnd the two (GsAnd Gd) between relationship
R is formed, i.e. G=<GS, Gd, R>；Ideograph Gs=<NS, PS, ES>, wherein NSIndicate the class node in figure, PSIndicate attribute side, ES
Indicate the relationship between two classes connected by multiple summits；Datagram Gd=<Nd, Pd, Ed>, NdIndicate instant node and character section
Point, PdIt indicates attribute side, uses EdIndicate the relationship between two nodes connected by multiple summits.The section of each edge and side both sides
Point all indicates subject, predicate and object.
The attribute of ancient spectrum concept has ancient spectrum title, classification, compiles author, age, version, print process, now Tibetan and the key to exercises；
The attribute of specific a certain music score has spectrum name, classification, passes spectrum people, copy spectrum age, tune, material and printing, is specification, existing
Tibetan and the key to exercises；
The attribute of ancient culture concept includes such as type and dynasty.
Datagram：Knowledge mapping includes ancient spectrum library and ancient culture library at present, the two libraries are highly relevant, utilize knowledge graph
Spectrum, can establish the association between data, and supporting function is provided for Gu spectrum research.Fig. 2 describes the example of a datagram, figure
3 describe the example of the Ming Dynasty Gu spectrum and ancient culture knowledge mapping.
2, data and Extracting Information are obtained：
There are two aspects, existing picture and the picture concerned on word and internet and word in ancient modal data source.It is right
In image content, optical character identification OCR (Optical Character Recognition) and Object can be taken
Detection (Object identifying) technology carries out identification sampling.For lteral data, the work(of Chinese vocabulary table and segmenter can be passed through
Data can be cut and be sub-divided into as unit of a word, be based on directed acyclic graph (DAG, Database Availability
Group it) and using Viterbi (Viterbi) algorithm applies mechanically at HMM (hidden Markov, Hidden Markov Model) model
Reason.
It is to obtain vocabulary from Gu spectrum and the relevant text information of ancient culture that text, which extracts target, and specific implementation process includes
Following steps：
Gu spectrum and ancient culture related text are divided into manageable segment by the first step first with sentence iterator.
Infinite in length system of the sentence iterator to processing text.
Second step, after sentence iterator exports text fragments, using segmenter (Tokenizer) by the further cutting of text
For word,
Third walks, and is every part of document structure tree vocabulary based on the word after cutting.Important word and its statistical information is all deposited
Storage is in vocabulary table cache.Distinguishing the basic ideas of important and insignificant word is：Only occur primary or occurs being less than five times
Word relatively find it difficult to learn habit, be regarded as unhelpful noise signal.Needed for the methods of the in store Word2vec of vocabulary table cache and bag of words
Metadata.Word2vec generates the vector expression of word, also known as neural term vector.Term vector can be grown to comprising hundreds of
Number, and these coefficients help probability of occurrence of one word of neural network prediction in any special context, such as in another spy
The probability occurred after fixed word.
Extracting Information, i.e., it is mutual between entity (concept), attribute and entity from being extracted in various types of data sources
Relationship forms the knowledge representation of ontological on this basis.Extracting Information is also name entity firstly the need of entity extraction is carried out
It identifies (Named entity recognition, and translate " proper name identification "), is mainly extracted automatically from a large amount of lteral datas
It is the part of most critical and basis in information extraction, the acquisition efficiency of the meeting follow-up knowledge of extreme influence to name entity, Entity recognition
And quality.After extracting entity, it is also necessary to extract the incidence relation between entity, can just obtain semantic information, while also needing
The attribute information for obtaining special entity, to obtain complete data information.
3, knowledge is merged：It links entity and merges knowledge
After obtaining entity, relationship and entity attribute information, to eliminate concept ambiguity, avoiding redundancy and error message,
It needs to realize that entity link, entity disambiguate (entity disambiguation) method and be used in solution entity generation discrimination of the same name
The problem of justice.
Coreference resolution (Coreference Resolution) corresponds to same entity object for solving multiple denotion items
The problem of.For example the happy bright pleasure of Wei Shi music score, Wei Shi refers both to identical concept, that is, refers to Wei Shi music score, is that a kind of jade of end of the Ming Dynasty maritime business Wei will
After some melodies of the Ming Dynasty pass to Japan, by the white poem music score externally taught and edited and publish of its four generation Sun Wei.
When building knowledge mapping, need to obtain knowledge input from the own database of enterprise or mechanism.By structuring
Data are dissolved into knowledge mapping, and resource description framework RDF (Resource Description Framework) works can be used
For data model, by the data conversion of relevant database at the triple data of RDF.It can be used what W3C was released in 2012
Mapping language standard Direct Mapping, are directly output as RDF graph, in RDF graph by relation database table structure and data
It is used for indicate class and predicate belong to in relational database table name and field name be consistent.
Data are extracted from multi-source data and will appear Data duplication or collision problem, to solve the problems, such as this, using to data
The mode of source confidence level scoring.Score the frequency occurred based on data source and in separate sources, the elder generation of sorting data item
Sequence afterwards, is supplemented in respective attributes value field.After final all data sources can be all normalized in deposit index data base.
4, integrated knowledge database pattern and data：
Above step obtains true expression, the pattern of knowledge based collection of illustrative plates, so that it may to obtain structuring and networking
Knowledge hierarchy.During establishment model, when there is data collision, or can not confirm data source quality, by Gu spectrum and
Ancient culture expert manually evaluates, and determines final result.
It further regards to shown in Fig. 4, the present invention further relates to after completing the structure of above-mentioned ancient spectrum and ancient culture knowledge mapping
The knowledge mapping engine of ancient spectrum and ancient culture is established in application to the ancient spectrum and ancient culture knowledge mapping established.
Specifically：
5, the knowledge mapping engine of ancient spectrum and ancient culture is established.
The application of knowledge mapping, as shown in figure 4, input natural language, exportable corresponding answer.Semantic question and answer are realized
With lower part：
The participle of first, knowledge based collection of illustrative plates；
Second, template matches；
The third, the translation of template executes.
Participle and Entity recognition are realized using HMM (hidden Markov algorithm), while determining the type of word, that is, judges that word is
Concept, entity or attribute.The semantic template of ancient spectrum and ancient culture field based on definition, matches question and answer and target.Template is " real
Body+attribute " indicates a node and a line for knowledge mapping.
Template matches process：
1) matched candidate template is determined according to the entity of parsing and type；
2) judge whether candidate template constitutes the subgraph of knowledge mapping with candidate entity, found in multiple candidate templates
With the highest template of rate, after determining template, translation template is the standard query language SPARQL on semantic network, in diagram data
It is executed on library.
It is as follows to match example：
Entity+attribute：
Which the version of Wei Shi music score hasWhich tune Wei Shi music score includesWei Shi music score melodies are any property
Concept+attribute：Which classification is Gu spectrum have
Attribute value+concept：
Which the ancient spectrum of the entitled Dao Gong of the mode of ancient Chinese music and double angles tune has
【It is multiple】(attribute+attribute value)+concept；
The entitled peaceful tune of the mode of ancient Chinese music plays an instrument as Chinese lute, and the ancient spectrum that print process is block-printed copy, version is minister's hall version has
Which
(attribute+attribute value)+or+(attribute+attribute value)+concept；
Which the ancient spectrum of the entitled positive Heibei provincial opera of the mode of ancient Chinese music or double tune has
(attribute+attribute value)+without+(attribute+attribute value)：
The entitled positive Heibei provincial opera of the mode of ancient Chinese music and play an instrument that not to be the ancient spectrum of Chinese lute have which
The present invention uses natural language processing technique and knowledge mapping technology in Gu spectrum research field, is graphically displayed ancient spectrum
Knowledge development process and structural relation describe ancient spectrum knowledge resource and its carrier with visualization technique, excavate, analysis, structure and
Draw explicit knowledge and connecting each other between them.It can show nuclear structure, developing history and overall architecture, reach more
Subject convergence provides valuable reference for Gu spectrum disciplinary study.
Universal now ancient spectrum research concentrates in the research of single composition, fails to extend it using knowledge mapping technology and grind
Study carefully direction, Gu spectrum is combined with ancient culture, the present invention utilizes natural language processing technique and knowledge mapping, and composing research to Gu provides
Technical support has also opened up the application field of knowledge mapping.
It should be noted that structure, ratio, size etc. depicted in this specification institute accompanying drawings, only coordinating
The bright revealed content of book is not limited to the enforceable limit of the present invention so that those skilled in the art understands and reads
Fixed condition, therefore do not have technical essential meaning, the modification of any structure, the change of proportionate relationship or the adjustment of size, not
It influences under the effect of present invention can be generated and the purpose that can reach, should all still fall and be obtained in disclosed technology contents
In the range of capable of covering.Meanwhile it is cited such as "upper", "lower", "left", "right", " centre " and " one " in this specification
Term is merely convenient to being illustrated for narration, rather than to limit the scope of the invention, the change of relativeness or tune
It is whole, in the case where changing technology contents without essence, when being also considered as the enforceable scope of the present invention.
The above is only presently preferred embodiments of the present invention, not does limitation in any form to the present invention, though
So the present invention has been disclosed as a preferred embodiment, and however, it is not intended to limit the invention, any technology people for being familiar with this profession
Member, in the range of not departing from technical solution of the present invention, when the technology contents using the disclosure above make a little change or repair
Decorations are the equivalent embodiment of equivalent variations, as long as being the content without departing from technical solution of the present invention, technology according to the present invention is real
Any simple modification, equivalent change and modification made by confrontation above example still fall within the range of technical solution of the present invention
It is interior.
Claims (8)
1. a kind of ancient spectrum and ancient culture knowledge mapping natural language processing method, which is characterized in that including step：
Create the pattern of the knowledge mapping of ancient spectrum and ancient culture：Knowledge mapping G is by ideograph Gs, datagram GdAnd between the two
Relationship R composition, be expressed as G=<GS, Gd, R>；Ideograph Gs=<NS, PS, ES>, wherein NSIndicate the class node in figure, PSTable
Show attribute side, ESIndicate the relationship between two classes connected by multiple summits；Datagram Gd=<Nd, Pd, Ed>, NdIndicate example section
Point and character nodes, PdIndicate attribute side, EdIndicate the relationship between two nodes connected by multiple summits；Each edge and side two
The node on side indicates subject, predicate and object；
Obtain data and Extracting Information：From the picture concerned and the ancient spectrum of word acquisition on existing picture and word and internet
And ancient culture data；For image content, optical character identification OCR is taken to carry out identification sampling with Identifying Technique of Object；For
Data are cut by the function of Chinese vocabulary table and segmenter and are sub-divided into as unit of a word, based on having by lteral data
HMM model processing is applied mechanically to acyclic figure and using Viterbi algorithm；Extracting Information is extracted from various types of data sources
Correlation between entity, attribute and entity forms the knowledge representation of ontological on this basis；Extracting Information carries out first
Entity extracts, and extracts name entity automatically from lteral data, next extracts the incidence relation between entity, finally obtains special
Entity attributes information is determined, to obtain complete data information；
Merge knowledge：After obtaining entity, incidence relation and entity attributes information, to eliminate concept ambiguity, avoiding redundancy
And error message, entity link is realized, using entity disambiguation method for solving the problems, such as that entity of the same name produces ambiguity；Refer to altogether and disappears
Solution is for solving the problems, such as that multiple denotion items correspond to same entity object；By the structuring number in existing relevant database
According to being dissolved into knowledge mapping, using resource description framework RDF as data model, by the data conversion of relevant database at
The triple data of RDF, are expressed as<Subject, predicate, object>Such structure；Data, which are extracted, from multi-source data will appear data
Repetition or collision problem carry out confidence level scoring, the frequency occurred based on data source and in separate sources to data source
Degree, is ranked up data item, is supplemented in respective attributes value field, and the index of knowledge mapping will be stored in after data source normalization
In database；And
Integrated ancient spectrum and ancient culture knowledge base pattern and data：Based on above step, the knowledge body of structuring and networking is obtained
System；During establishment model, when data collision occur, or can not confirm data source quality, by Gu spectrum and ancient culture expert
Artificial evaluation, determines final result.
2. ancient spectrum as described in claim 1 and ancient culture knowledge mapping natural language processing method, it is characterised in that：It is creating
Ancient spectrum and ancient culture knowledge mapping pattern in, the data of the datagram compose library and ancient culture library from ancient times.
3. ancient spectrum as described in claim 1 and ancient culture knowledge mapping natural language processing method, it is characterised in that：It is creating
Ancient spectrum and ancient culture knowledge mapping pattern in, the attribute comprising ancient spectrum concept, specific each head music score attribute and Gu
The attribute of cultural concept.
4. ancient spectrum as claimed in claim 3 and ancient culture knowledge mapping natural language processing method, it is characterised in that：The Gu
The attribute of spectrum concept includes ancient spectrum title, classification, compiles author, age, version, print process, now Tibetan and one kind in the key to exercises or more
Kind.
5. ancient spectrum as claimed in claim 3 and ancient culture knowledge mapping natural language processing method, it is characterised in that：The tool
The attribute of each first music score of body includes spectrum name, classification, passes spectrum people, copies spectrum age, tune, material and printing, specification, now hides and inscribe
It is one or more in solution.
6. ancient spectrum as claimed in claim 3 and ancient culture knowledge mapping natural language processing method, it is characterised in that：The Gu
The attribute of cultural concept includes one or more in type and dynasty.
7. ancient spectrum as described in claim 1 and ancient culture knowledge mapping natural language processing method, it is characterised in that：Also wrap
It includes：After establishing the basis of ancient spectrum and ancient culture knowledge mapping, the question and answer engine of the knowledge mapping of ancient spectrum and ancient culture is established
Framework.
8. ancient spectrum as claimed in claim 7 and ancient culture knowledge mapping natural language processing method, which is characterized in that utilize institute
State the translation execution that question and answer exchange architecture carries out the participle, template matches and template of knowledge based collection of illustrative plates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810269797.3A CN108509420A (en) | 2018-03-29 | 2018-03-29 | Gu spectrum and ancient culture knowledge mapping natural language processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810269797.3A CN108509420A (en) | 2018-03-29 | 2018-03-29 | Gu spectrum and ancient culture knowledge mapping natural language processing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108509420A true CN108509420A (en) | 2018-09-07 |
Family
ID=63379179
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810269797.3A Pending CN108509420A (en) | 2018-03-29 | 2018-03-29 | Gu spectrum and ancient culture knowledge mapping natural language processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108509420A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109271530A (en) * | 2018-10-17 | 2019-01-25 | 长沙瀚云信息科技有限公司 | A kind of disease knowledge map construction method and plateform system, equipment, storage medium |
| CN109471948A (en) * | 2018-11-08 | 2019-03-15 | 威海天鑫现代服务技术研究院有限公司 | A kind of the elder's health domain knowledge question answering system construction method |
| CN109508383A (en) * | 2018-10-30 | 2019-03-22 | 北京国双科技有限公司 | The construction method and device of knowledge mapping |
| CN109597855A (en) * | 2018-11-29 | 2019-04-09 | 北京邮电大学 | Domain knowledge map construction method and system based on big data driving |
| CN109657069A (en) * | 2018-12-11 | 2019-04-19 | 北京百度网讯科技有限公司 | The generation method and its device of knowledge mapping |
| CN109815340A (en) * | 2019-01-17 | 2019-05-28 | 云南师范大学 | A kind of construction method of national culture information resources knowledge mapping |
| CN110096573A (en) * | 2019-04-22 | 2019-08-06 | 腾讯科技（深圳）有限公司 | A kind of text resolution method and relevant device |
| CN110162637A (en) * | 2019-02-14 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Information Atlas construction method, device and equipment |
| CN110347736A (en) * | 2019-06-21 | 2019-10-18 | 厦门美域中央信息科技有限公司 | A kind of data self mapping method towards RDF triple |
| CN110413793A (en) * | 2019-06-11 | 2019-11-05 | 福建奇点时空数字科技有限公司 | A kind of knowledge mapping substance feature method for digging based on translation model |
| CN110472226A (en) * | 2019-07-03 | 2019-11-19 | 五邑大学 | A kind of network security situation prediction method and device of knowledge based map |
| CN110991149A (en) * | 2019-11-12 | 2020-04-10 | 广州爱学信息科技有限公司 | Multi-mode entity linking method and entity linking system |
| CN111159356A (en) * | 2019-12-31 | 2020-05-15 | 重庆和贯科技有限公司 | Knowledge graph construction method based on teaching content |
| CN111753095A (en) * | 2019-03-29 | 2020-10-09 | 富士通株式会社 | Method and device for generating knowledge base |
| CN114153992A (en) * | 2021-12-28 | 2022-03-08 | 安徽富驰信息技术有限公司 | Domain knowledge graph construction equipment and method |
| CN115017335A (en) * | 2022-06-16 | 2022-09-06 | 特赞（上海）信息科技有限公司 | Knowledge graph construction method and system |
| CN116070643A (en) * | 2023-04-03 | 2023-05-05 | 武昌理工学院 | Fixed style translation method and system from ancient text to English |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103729402A (en) * | 2013-11-22 | 2014-04-16 | 浙江大学 | Method for establishing mapping knowledge domain based on book catalogue |
| CN104462506A (en) * | 2014-12-19 | 2015-03-25 | 北京奇虎科技有限公司 | Method and device for establishing knowledge graph based on user annotation information |
| CN106815307A (en) * | 2016-12-16 | 2017-06-09 | 中国科学院自动化研究所 | Public Culture knowledge mapping platform and its use method |
| WO2018034902A1 (en) * | 2016-08-16 | 2018-02-22 | Ebay Inc. | Knowledge graph construction for online personal assistant |
-
2018
- 2018-03-29 CN CN201810269797.3A patent/CN108509420A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103729402A (en) * | 2013-11-22 | 2014-04-16 | 浙江大学 | Method for establishing mapping knowledge domain based on book catalogue |
| CN104462506A (en) * | 2014-12-19 | 2015-03-25 | 北京奇虎科技有限公司 | Method and device for establishing knowledge graph based on user annotation information |
| WO2018034902A1 (en) * | 2016-08-16 | 2018-02-22 | Ebay Inc. | Knowledge graph construction for online personal assistant |
| CN106815307A (en) * | 2016-12-16 | 2017-06-09 | 中国科学院自动化研究所 | Public Culture knowledge mapping platform and its use method |
Non-Patent Citations (4)
| Title |
|---|
| HAN XIAO 等: ""TransG: A Generative Mixture Model for knowledge Graph Embedding"", 《WWW.ARXIV.ORG》 * |
| WEIYU CHEN 等: ""Research on space-time evolution model of Xiangshan Culture Knowledge graph based on named graph"", 《2017 IEEE 2ND ADVANCED INFORMATION TECHNOLOGY，ELECTRONIC AND AUTOMATION CONTROL CONFERENCE》 * |
| 王立妹 等: ""国外非物质文化遗产旅游知识图谱分析"", 《淮南师范学院学报》 * |
| 阮彤 等: ""中医药知识图谱构建与应用"", 《医学信息学杂志》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109271530A (en) * | 2018-10-17 | 2019-01-25 | 长沙瀚云信息科技有限公司 | A kind of disease knowledge map construction method and plateform system, equipment, storage medium |
| CN109508383A (en) * | 2018-10-30 | 2019-03-22 | 北京国双科技有限公司 | The construction method and device of knowledge mapping |
| CN109471948A (en) * | 2018-11-08 | 2019-03-15 | 威海天鑫现代服务技术研究院有限公司 | A kind of the elder's health domain knowledge question answering system construction method |
| CN109597855A (en) * | 2018-11-29 | 2019-04-09 | 北京邮电大学 | Domain knowledge map construction method and system based on big data driving |
| CN109657069A (en) * | 2018-12-11 | 2019-04-19 | 北京百度网讯科技有限公司 | The generation method and its device of knowledge mapping |
| CN109815340A (en) * | 2019-01-17 | 2019-05-28 | 云南师范大学 | A kind of construction method of national culture information resources knowledge mapping |
| CN110162637A (en) * | 2019-02-14 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Information Atlas construction method, device and equipment |
| CN110162637B (en) * | 2019-02-14 | 2023-06-20 | 腾讯科技（深圳）有限公司 | Information map construction method, device and equipment |
| CN111753095A (en) * | 2019-03-29 | 2020-10-09 | 富士通株式会社 | Method and device for generating knowledge base |
| CN110096573A (en) * | 2019-04-22 | 2019-08-06 | 腾讯科技（深圳）有限公司 | A kind of text resolution method and relevant device |
| CN110096573B (en) * | 2019-04-22 | 2022-12-27 | 腾讯科技（深圳）有限公司 | Text parsing method and device |
| CN110413793A (en) * | 2019-06-11 | 2019-11-05 | 福建奇点时空数字科技有限公司 | A kind of knowledge mapping substance feature method for digging based on translation model |
| CN110347736A (en) * | 2019-06-21 | 2019-10-18 | 厦门美域中央信息科技有限公司 | A kind of data self mapping method towards RDF triple |
| CN110472226A (en) * | 2019-07-03 | 2019-11-19 | 五邑大学 | A kind of network security situation prediction method and device of knowledge based map |
| CN110991149A (en) * | 2019-11-12 | 2020-04-10 | 广州爱学信息科技有限公司 | Multi-mode entity linking method and entity linking system |
| CN111159356A (en) * | 2019-12-31 | 2020-05-15 | 重庆和贯科技有限公司 | Knowledge graph construction method based on teaching content |
| CN114153992A (en) * | 2021-12-28 | 2022-03-08 | 安徽富驰信息技术有限公司 | Domain knowledge graph construction equipment and method |
| CN115017335A (en) * | 2022-06-16 | 2022-09-06 | 特赞（上海）信息科技有限公司 | Knowledge graph construction method and system |
| CN116070643A (en) * | 2023-04-03 | 2023-05-05 | 武昌理工学院 | Fixed style translation method and system from ancient text to English |
| CN116070643B (en) * | 2023-04-03 | 2023-08-15 | 武昌理工学院 | Fixed style translation method and system from ancient text to English |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108509420A (en) | Gu spectrum and ancient culture knowledge mapping natural language processing method | |
| Khan et al. | A novel natural language processing (NLP)–based machine translation model for English to Pakistan sign language translation | |
| Elnagar et al. | Systematic literature review of dialectal Arabic: identification and detection | |
| CN110609983B (en) | Structured decomposition method for policy file | |
| Das et al. | A novel system for generating simple sentences from complex and compound sentences | |
| JP7297458B2 (en) | Interactive content creation support method | |
| Jänicke et al. | Interactive visual alignment of medieval text versions | |
| Sahala | Contributions to computational assyriology | |
| Mengliev et al. | Rule-based syntactic analysis for Uzbek language: an alternative approach to overcome data scarcity and enhance interpretability | |
| Ali et al. | SiNER: A large dataset for Sindhi named entity recognition | |
| Kapitanov et al. | Slovo: Russian Sign Language Dataset | |
| Silva et al. | Xte: Explainable text entailment | |
| Yáñez-Bouza | Methodological approaches to the study of codification, prescription, and prescriptivism | |
| KR950013128B1 (en) | Apparatus and method of machine translation | |
| Lapesa et al. | Analysis of political debates through newspaper reports: methods and outcomes | |
| O’Donnell | Interactions between natural–language processing and systemic functional linguistics | |
| Mahlaza | Foundations for reusable and maintainable surface realisers for isiXhosa and isiZulu | |
| Wanjawa et al. | Model for semantic network generation from low resource languages as applied to question answering–case of swahili | |
| Barros et al. | HanaNLG: a flexible hybrid approach for natural language generation | |
| Nurgazina et al. | Research of semantic aspects of the Kazakh language when translating into the Kazakh sign language. | |
| Kupiyalova et al. | Semantic search using Natural Language Processing | |
| Worke | INFORMATION EXTRACTION MODEL FROM GE’EZ TEXTS | |
| Medrano | Toward a Khipu Transcription" Insistence": a Corpus-Based Study of the Textos Andinos | |
| Fan | Exploring English Translation Strategies Oriented by Big Data Technology | |
| JP7312354B2 (en) | Intention information extraction program, intention information extraction device, and intention information extraction method |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20181010 Address after: 200031 Fenyang Road 20 Xuhui District, Shanghai Applicant after: SHANGHAI CONSERVATORY OF MUSIC Address before: 200040 7 D, 2 Lane 568 lane, Julu Road, Jingan District, Shanghai. Applicant before: Zhao Weiping Applicant before: Sun Ning |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180907 |