CN110008354A - A kind of construction method of the external Chinese studying content of knowledge based map - Google Patents
A kind of construction method of the external Chinese studying content of knowledge based map Download PDFInfo
- Publication number
- CN110008354A CN110008354A CN201910284590.8A CN201910284590A CN110008354A CN 110008354 A CN110008354 A CN 110008354A CN 201910284590 A CN201910284590 A CN 201910284590A CN 110008354 A CN110008354 A CN 110008354A
- Authority
- CN
- China
- Prior art keywords
- concept
- entity
- knowledge
- chinese
- external 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
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a kind of construction methods of the external Chinese studying content of knowledge based map, comprising: the concept set towards external Chinese studying field is designed, and emphasizes the form expression of concept and conceptual relation;Entity and Relation extraction are carried out for external Chinese studying corpus according to concept set, is stored in the form of triple, to obtain final external Chinese studying knowledge mapping;Association knowledge intelligent recommendation and association knowledge multi-angle profound level reasoning, which are shown, to be realized to Chinese terms to what user chose.It is excavated based on the knowledge point in teaching Chinese as a foreign language resource and knowledge mapping constructs, overseas Chinese studying person will be helped effectively to carry out Chinese terms study, promote interactivity, intelligence and the personalization of the practice of Chinese studying word.
Description
Technical field
The present invention relates to Chinese knowledge base applied technical fields, more particularly to a kind of external Chinese of knowledge based map
The construction method of learning Content.
Background technique
With the promotion of Chinese international status and influence power, the Chinese as economy and culture carrier has obtained more and more
Attention, the number of countries in the world learning Chinese is also being increasing.Chinese studying can not only promote communication exchange, can also make outer
Compatriots are better understood by the thick and heavy geography carried under language and lexical system, history, cultural connotation, reinforce them to China
The acceptance of culture.
Word teaching is most basic one of the task of Chinese teaching, always through teaching Chinese as a foreign language.It can actually teach
In, word teaching is chronically at weak link, and the sensibility for causing many students to pay close attention to word is inadequate, comes to realize the ability of word
It is not strong, drastically influence the promotion of the language abilities such as their reading, writing, oral expression.It is the artificial of support with big data
The mode of intelligence+education, just by the concern of various circles of society.In order to help overseas Chinese studying person to better grasp Chinese word
Language, is excavated based on the knowledge point in teaching Chinese as a foreign language resource and knowledge mapping constructs, and overseas Chinese studying person will be helped effective
Chinese terms study is carried out, by the pass of the information inquiry and profound level of the good Structure of Knowledge Representation of knowledge mapping, high speed
The advantages that being reasoning, guidance student experience word affection, experience word emotion, come into the perceptual world of word, realize word exists
Expression in special context is intended to, and holds the deepmeaning of word, so that Chinese studying word practices more convenient, intelligence and people
Property.
Summary of the invention
The present invention is lacked for the association knowledge that there is learned word in the study of current Chinese terms, and association knowledge can not be high
Efficiency Inquiry and association knowledge can not profound reasoning the problems such as showing, propose a kind of combination world knowledge map, construction towards
The method of external Chinese studying domain knowledge map constructs knowledge network for external Chinese studying, to realize to Chinese terms
The association knowledge intelligent recommendation of study and association knowledge multi-angle profound level reasoning are shown.
The technical solution adopted by the present invention to solve the technical problems is:
A kind of construction method of the external Chinese studying content of knowledge based map of the present invention, comprising the following steps:
S1, conceptual level design
S11, construct seed concept set, including level Four concept: level-one concept (i.e. root node) is " Chinese " teaching material, second level
Concept is word and word;Three-level concept includes phrase, example sentence, the communication dialogue based on the word, the teaching material where word under word concept
Cardon, group word, example sentence, the communication dialogue based on the word, the teaching material position letter where word are write under location information and word concept
Breath, level Four concept be the picture for example sentence, phrase etc., video, audio multimedia;
S12 obtains corresponding entity from seed concept set based on world knowledge map, kernel entity set, core is added
Heart entity sets are to gather as composed by the entity under seed concept;
S13 scans kernel entity, generates the not concept in seed concept set, referred to as candidate concepts, is added candidate general
Read set.Candidate concepts set is as belonging to kernel entity and not appear in collection composed by the concept in key concept set
It closes;
S14 calculates the semantic dependency in candidate concepts set between candidate concepts and key concept set, the core
Concept set is the set as composed by the concept closely related with external Chinese studying field, by seed concept and similar to its
Property biggish concept composition;
S15 will be greater than the candidate concepts of given threshold value as related notion, be added in key concept set;
S16, iteratively incrementally extended core concept set just obtains whole until not new concept generates
Concept set relevant to external Chinese studying;
S17, according to step S16 obtain concept set further progress concept clean, by by calculate concept IDF value come
Concept some more common but not strong with external Chinese topic relativity is deleted.
S18, concept fusion will carry out concept alignment with the reference concept of alias or special address, will utilize general
Synonym in the synonyms map and knowledge base Infobox table of knowledge mapping describes attribute, including " alias ", " once used
Name ", " scientific name ", " pseudonym " etc. are concept related to key concept concentration will refer to;
S19, the conceptual relation based on Infobox are excavated.Check that Baidupedia, interaction encyclopaedia, Chinese wikipedia etc. are known
The Infobox in library is known, if the concept in key concept set falls into Infobox, by the concept in the Infobox with three
Tuple form is extracted, and conceptual level set C is added.
S2, instance layer study
S21 constructs external Chinese data, based on " Chinese " teaching material, and include " external Chinese education introduction ",
The teaching materials such as " external Chinese everyday expressions comparative example is released ", " the big paradise of Chinese culture ", " it is spoken to develop Chinese middle rank ", and fitting
The question-answer sentence of overseas Chinese studying person's real life is Chinese studying corpus;
S22 identifies entity using the method and combination Chinese word segmentation of natural language processing, i.e., first finds out from a sentence
Nearest kernel entity or noun entity are then found in the position of " relationship " respectively forwardly, backward;
S23, according to step S22 obtain entity set further progress entity clean, by by the IDF value of computational entity come
Entity some more common but not strong with external Chinese topic relativity is deleted;
S24, entity fusion will carry out entity alignment with the reference entity of alias or special address, will utilize general
Synonym in the synonyms map and knowledge base Infobox table of knowledge mapping describes attribute, including " alias ", " once used
Name ", " scientific name ", " pseudonym " etc. will refer to entity associated into entity set;
Entity, relationship and entity triple are added in instance layer E S25.The instance layer is counted according to conceptual level
According to instantiation as a result, being made of the triple closely related with external Chinese studying field;
S26, the triple store that step S25 is obtained form external Chinese language knowledge map in Neo4j chart database;
S3, intelligent learning system application;Association knowledge intelligent recommendation and association are realized to Chinese terms to what user chose
Knowledge multi-angle profound level reasoning is shown;
S31 receives the external Chinese language text that user chooses;
S32 extracts knowledge mapping feature, extraly uses the context substance feature of an entity;
S33 carries out Text character extraction based on convolutional neural networks: subvector, term vector entity context vector are made
For multiple channels, merged under the frame of CNN;
S34 is carried out the historical interest fusion of user based on attention mechanism: judging user to the interest of current knowledge point
When, using attention network, different weights is distributed to user's history record;
S35 carries out relevant knowledge point retrieval by weight descending according to S34;
S36, using S35's as a result, completing association knowledge intelligent recommendation and association knowledge multi-angle profound level reasoning displaying.
By the above-mentioned description of this invention it is found that compared with prior art, the invention has the following beneficial effects:
Overseas Chinese studying person is helped effectively to carry out Chinese terms study, by the good representation of knowledge knot of knowledge mapping
The advantages that relation inference of structure, the information inquiry of high speed and profound level, guidance student experiences word affection, experiences word emotion,
The perceptual world for coming into word realizes to obtain expression intention of the word in special context, holds the deepmeaning of word, make Chinese Language
It practises word and practices more convenient, intelligence and hommization.
Invention is further described in detail with reference to the accompanying drawings and embodiments;But a kind of knowledge based figure of the invention
The external Chinese studying systems construction method of spectrum is not limited to the embodiment.
Detailed description of the invention
Fig. 1 is the general frame figure of the method for the present invention.
Specific embodiment
Present invention will be further explained below with reference to specific examples.It should be understood that these embodiments are merely to illustrate the present invention
Rather than it limits the scope of the invention.In addition, it should also be understood that, after reading the content taught by the present invention, those skilled in the art
Member can make various changes or modifications the present invention, and such equivalent forms equally fall within the application the appended claims and limited
Range.
It is shown in Figure 1, a kind of construction method of the external Chinese studying content of knowledge based map of the invention, including
Following steps: (1) conceptual level designs;(2) instance layer learns;(3) intelligent learning system application.
Step S1, conceptual level design.
S11, by inquiry OpenKG.CN platform (Open Chinese knowledge mapping) etc. world knowledges map with Chinese study
Relevant classification information detailed outline table constructs the concept set of word and word, and wherein the concept set of word includes writing cardon, phonetic, portion
Head, stroke, the five-element, traditional font, five, basic paraphrase, detailed paraphrase, relevant group word, nearly antonym, translator of English, related words;Word
Concept set include basic paraphrase, detailed paraphrase, nearly antonym, translator of English, related term.
S12 obtains corresponding entity from seed concept set based on world knowledge map, kernel entity set is added, with
For " grass " this word concept, obtains it and write cardon, phonetic (c ǎ o), radical (Lv), stroke (9), five-element's (wood), five
(AJJ), basic paraphrase (the herbal general designation in higher plant other than cultivated plant), detailed paraphrase are (herbal total
Claim, refer to the hay as fuel, feed, the wasteland ... that do not opened up wasteland), (flowers and plants rapid style of writing is small carelessly former to be risen carelessly relevant group word
The careless green grass thick grass of ground weeds draft vegetation hay grass green hundred), translator of English (variant of Fuck;manuscript;straw;
CL:, pinch, strain, root;Variant of grass, draft (of a document);careless;rough;Grass), related words
(Lao Kuanjing Man Fangcang);It include that basic paraphrase (dips in the change of upper phosphorus or sulphur with tiny batten by taking " match " this word concept as an example
Close the thing got fire made of object.Existing frequently-used is safety match), (dried firewood to make a fire, one end are moistened with phosphorus or sulphur for detailed paraphrase
Compound, draw the tiny wooden stick ... got fire to wipe), near synonym (match), translator of English (match (for lighting
fire));
S13 scans kernel entity, generates the not concept in seed concept set, referred to as candidate concepts, is added candidate general
Set is read, the concept set including wherein word includes the multimedias such as communication dialogue, example sentence, picture and text sound;The concept set of word include phrase,
The multimedias such as communication dialogue, example sentence, picture and text sound.Candidate concepts set is as belonging to kernel entity and not appear in key concept
Set composed by concept in set;
S14 calculates the semantic dependency in candidate concepts set between candidate concepts and key concept set, the core
Concept set is the set as composed by the concept closely related with external Chinese studying field, by seed concept and similar to its
Property biggish concept composition;
S15 will be greater than the candidate concepts of given threshold value as related notion, be added in key concept set;
S16, iteratively incrementally extended core concept set just obtains whole until not new concept generates
Concept set relevant to external Chinese studying, the specially concept set of word and word, wherein the concept set of word include write cardon,
Phonetic, radical, stroke, the five-element, traditional font, five, basic paraphrase, detailed paraphrase, relevant group word, nearly antonym, translator of English, phase
Close the multimedias such as word, communication dialogue, example sentence, picture and text sound;The concept set of word includes basic paraphrase, detailed paraphrase, nearly antonym, English
The multimedias such as literary translation, related term, phrase, communication dialogue, example sentence, picture and text sound;
S17, according to step S16 obtain concept set further progress concept clean, by by calculate concept IDF value come
Concept some more common but not strong with external Chinese topic relativity is deleted, as in word concept set radical, the five-element,
Five, detailed paraphrase;The detailed paraphrase that word concept is concentrated;
S18, concept fusion will carry out concept alignment with the reference concept of alias or special address, will utilize general
Synonym in the synonyms map and knowledge base Infobox table of knowledge mapping describes attribute, including " alias ", " once used
Name ", " scientific name ", " pseudonym " etc. are concept related to key concept concentration will refer to, such as A Dream of Red Mansions, stone note, feelings monk record, wind and moon-scene
Treasured mirror, Nanjing Shi Erchai;
S19, the conceptual relation based on Infobox are excavated.Check that Baidupedia, interaction encyclopaedia, Chinese wikipedia etc. are known
The Infobox in library is known, if the concept in key concept set falls into Infobox, by the concept in the Infobox with three
Tuple form is extracted, and the conceptual level set is added, such as<China, capital, and Beijing>;
S2, instance layer study.
S21 constructs external Chinese data, based on " Chinese " teaching material, and include " external Chinese education introduction ",
The teaching materials such as " external Chinese everyday expressions comparative example is released ", " the big paradise of Chinese culture ", " it is spoken to develop Chinese middle rank ", and fitting
The question-answer sentence of overseas Chinese studying person's real life is Chinese studying corpus;
S22 identifies entity using the method and combination Chinese word segmentation of natural language processing, i.e., first finds out from a sentence
Nearest kernel entity or noun entity are then found in the position of " relationship " respectively forwardly, backward, and such as " " thinker " is one
The sculpture of a greatness ", finds out relative "Yes", finds out entity " thinker " and " sculpture " backward forward;
S23 is cleaned according to the entity set further progress entity that step S22 is obtained, and will pass through the IDF value of computational entity
(TF-IDF (term frequency-inverse document frequency) is a kind of for information retrieval and data digging
The common weighting technique of pick.TF means word frequency (Term Frequency), and IDF means inverse document frequency (Inverse
Document Frequency).TF-IDF is a kind of statistical method, to assess a words for a file set or a language
Expect the significance level of a copy of it file in library.The importance of words is with the directly proportional increasing of number that it occurs hereof
The frequency that adds, but can occur in corpus with it simultaneously is inversely proportional decline.Therefore, the IDF of a certain particular words, Ke Yiyou
General act number divided by the file comprising the word number, then take denary logarithm to obtain the obtained quotient) come one
A little more common but not strong with external Chinese topic relativity entities are deleted, such as " sandwich ";
S24, entity fusion will carry out entity alignment with the reference entity of alias or special address, will utilize general
Synonym in the synonyms map and knowledge base Infobox table of knowledge mapping describes attribute, including " alias ", " once used
Name ", " scientific name ", " pseudonym " etc. will refer to entity associated into entity set, as the Dragon Boat Festival, the Dragon Boat Festival, noon day section, the Dragon Boat Festival,
Ai Jie, end five, weight noon, noon day, Xia Jie;
Entity, relationship and entity triple are added in instance layer S25.The instance layer is counted according to conceptual level
According to instantiation as a result, be made of the triple closely related with external Chinese studying field, such as < thinker, works form,
Sculpture >;
S26: the triple store that step S25 is obtained forms external Chinese language knowledge map in Neo4j chart database.
Step S3, instance layer study (by taking knowledge expands module as an example).
S31, receives the external Chinese language text that user chooses, and the knowledge of such as entitled " surname, the general knowledge being named " is expanded
Text;
S32 is extracted knowledge mapping feature (surname is named), extraly uses the context substance feature of an entity;
S33 carries out Text character extraction based on convolutional neural networks: subvector, term vector entity context vector are made
For multiple channels, merged under the frame of CNN;
S34 is carried out the historical interest fusion of user based on attention mechanism: judging user to the interest of current knowledge point
When (such as entertaining story), using attention network, different weights is distributed to user's history record;
S35, according to S34 by weight descending carry out relevant knowledge point retrieval, as it is above-mentioned it is entitled " surname, being named
General knowledge " knowledge expand text, after carrying out a series of text-processings and analysis, " LI Si guang is named for the article recommended
Story ";
S36, using S35's as a result, article " being named story of LI Si guang " is recommended user with visual means, and
This recommending data is recorded in knowledge mapping.
A kind of external Chinese language knowledge map tool of construction method of the external Chinese studying content of knowledge based map of the present invention
There are the information inquiry and profound relation inference of good Structure of Knowledge Representation, high speed, so that Chinese studying word
Practice more convenient, intelligence and hommization.
The above is only a specific embodiment of the present invention, but the design concept of the present invention is not limited to this, all to utilize this
Design makes a non-material change to the present invention, and should all belong to behavior that violates the scope of protection of the present invention.
Claims (1)
1. a kind of construction method of the external Chinese studying content of knowledge based map, which comprises the following steps:
S1, the concept set towards external Chinese studying field are designed, and obtain the form expression of concept and conceptual relation, packet
It includes:
S11 constructs seed concept set by classification information detailed outline table relevant to Chinese study in world knowledge map;
S12 obtains corresponding entity from seed concept set based on world knowledge map, kernel entity set is added, and core is real
Body set is to gather as composed by the entity under seed concept;
S13 scans kernel entity, generates the not concept in seed concept set, referred to as candidate concepts, and candidate concepts collection is added
It closes;Candidate concepts set is as belonging to kernel entity and not appear in set composed by the concept in key concept set;
S14 calculates the semantic dependency in candidate concepts set between candidate concepts and key concept set, the key concept
Set is the set as composed by the concept closely related with external Chinese studying field, by seed concept and with its similitude compared with
Big concept composition;
S15 will be greater than the candidate concepts of given threshold value as related notion, be added in key concept set;
S16, iteratively incrementally extended core concept set, until not new concept generates, just obtain it is whole with
The relevant concept set of external Chinese studying;
S17 is cleaned according to the concept set further progress concept that step S16 is obtained, and will be deleted by the IDF value for calculating concept
Fall general but not strong with external Chinese topic relativity concept;
S18, concept fusion will carry out concept alignment with the reference concept of alias or special address, will utilize world knowledge
Synonym in the synonyms map and knowledge base Infobox table of map describes attribute, will refer to concept related general to core
It reads and concentrates;
S19, the conceptual relation based on Infobox are excavated;The Infobox in knowledge base is checked, if in key concept set
Concept falls into Infobox, then extracts the concept in the Infobox with triple form, and the conceptual level set is added
C;
S2 is carried out entity and Relation extraction for external Chinese studying corpus according to concept set, is stored, obtained in the form of triple
To final external Chinese studying knowledge mapping, comprising:
S21 constructs external Chinese data;
S22 identifies entity using the method and combination Chinese word segmentation of natural language processing, first finds out " relationship " from a sentence
Position, then find nearest kernel entity or noun entity respectively forwardly, backward;
S23 is cleaned according to the entity set further progress entity that step S22 is obtained, will be deleted by the IDF value of computational entity
Fall general but not strong with external Chinese topic relativity concept;
S24, entity fusion will carry out entity alignment with the reference entity of alias or special address, will utilize world knowledge
Synonym in the synonyms map and knowledge base Infobox table of map describes attribute, will refer to entity associated to entity set
In;
Entity, relationship and entity triple are added in instance layer E S25;The instance layer is that data reality is carried out according to conceptual level
Exampleization as a result, being made of the triple closely related with external Chinese studying field;
S26, the triple store that step S25 is obtained form external Chinese language knowledge map in Neo4j chart database;
S3 realizes association knowledge intelligent recommendation and association knowledge multi-angle profound level reasoning to the external Chinese terms that user chooses
It shows, comprising:
S31 receives the external Chinese language text that user chooses;
S32 extracts knowledge mapping feature, extraly uses the context substance feature of an entity;
S33 carries out Text character extraction based on convolutional neural networks: using subvector, term vector entity context vector as more
A channel is merged under the frame of CNN;
S34 carries out the historical interest fusion of user based on attention mechanism: when judging interest of the user to current knowledge point,
Using attention network, different weights is distributed to user's history record;
S35 carries out relevant knowledge point retrieval by weight descending according to S34;
S36, using S35's as a result, completing association knowledge intelligent recommendation and displaying.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910284590.8A CN110008354B (en) | 2019-04-10 | 2019-04-10 | Method for constructing foreign Chinese learning content based on knowledge graph |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910284590.8A CN110008354B (en) | 2019-04-10 | 2019-04-10 | Method for constructing foreign Chinese learning content based on knowledge graph |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110008354A true CN110008354A (en) | 2019-07-12 |
CN110008354B CN110008354B (en) | 2022-06-07 |
Family
ID=67170715
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910284590.8A Active CN110008354B (en) | 2019-04-10 | 2019-04-10 | Method for constructing foreign Chinese learning content based on knowledge graph |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110008354B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110704522A (en) * | 2019-09-04 | 2020-01-17 | 南京航空航天大学 | Concept data model automatic conversion method based on semantic analysis |
CN110750652A (en) * | 2019-10-21 | 2020-02-04 | 广西大学 | Story ending generation method combining context entity words and knowledge |
CN111401066A (en) * | 2020-03-12 | 2020-07-10 | 腾讯科技(深圳)有限公司 | Artificial intelligence-based word classification model training method, word processing method and device |
CN111522964A (en) * | 2020-04-17 | 2020-08-11 | 电子科技大学 | Tibetan medicine literature core concept mining method |
CN111797244A (en) * | 2020-07-20 | 2020-10-20 | 华侨大学 | Intelligent situation teaching method and system based on knowledge graph and conversation robot |
CN112182239A (en) * | 2020-09-22 | 2021-01-05 | 中国建设银行股份有限公司 | Information retrieval method and device |
CN113051379A (en) * | 2021-02-24 | 2021-06-29 | 南京审计大学 | Knowledge point recommendation method and device, electronic equipment and storage medium |
CN113139036A (en) * | 2020-01-20 | 2021-07-20 | 海信视像科技股份有限公司 | Information interaction method and equipment |
CN113204651A (en) * | 2021-05-28 | 2021-08-03 | 华侨大学 | Multi-source knowledge graph fusion method and device in Chinese education field |
CN114547346A (en) * | 2022-04-22 | 2022-05-27 | 浙江太美医疗科技股份有限公司 | Knowledge graph construction method and device, electronic equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103488724A (en) * | 2013-09-16 | 2014-01-01 | 复旦大学 | Book-oriented reading field knowledge map construction method |
CN106776711A (en) * | 2016-11-14 | 2017-05-31 | 浙江大学 | A kind of Chinese medical knowledge mapping construction method based on deep learning |
CN106874261A (en) * | 2017-03-17 | 2017-06-20 | 中国科学院软件研究所 | A kind of domain knowledge collection of illustrative plates and querying method based on semantic triangle |
CN108182262A (en) * | 2018-01-04 | 2018-06-19 | 华侨大学 | Intelligent Answer System construction method and system based on deep learning and knowledge mapping |
US20180218127A1 (en) * | 2017-01-31 | 2018-08-02 | Pager, Inc. | Generating a Knowledge Graph for Determining Patient Symptoms and Medical Recommendations Based on Medical Information |
CN109062939A (en) * | 2018-06-20 | 2018-12-21 | 广东外语外贸大学 | A kind of intelligence towards Chinese international education leads method |
-
2019
- 2019-04-10 CN CN201910284590.8A patent/CN110008354B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103488724A (en) * | 2013-09-16 | 2014-01-01 | 复旦大学 | Book-oriented reading field knowledge map construction method |
CN106776711A (en) * | 2016-11-14 | 2017-05-31 | 浙江大学 | A kind of Chinese medical knowledge mapping construction method based on deep learning |
US20180218127A1 (en) * | 2017-01-31 | 2018-08-02 | Pager, Inc. | Generating a Knowledge Graph for Determining Patient Symptoms and Medical Recommendations Based on Medical Information |
CN106874261A (en) * | 2017-03-17 | 2017-06-20 | 中国科学院软件研究所 | A kind of domain knowledge collection of illustrative plates and querying method based on semantic triangle |
CN108182262A (en) * | 2018-01-04 | 2018-06-19 | 华侨大学 | Intelligent Answer System construction method and system based on deep learning and knowledge mapping |
CN109062939A (en) * | 2018-06-20 | 2018-12-21 | 广东外语外贸大学 | A kind of intelligence towards Chinese international education leads method |
Non-Patent Citations (1)
Title |
---|
化立志: "基于知识图谱的领域知识库管理系统的设计与实现", 《中国优秀博硕士学位论文全文数据库(硕士)—信息科技辑》 * |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110704522A (en) * | 2019-09-04 | 2020-01-17 | 南京航空航天大学 | Concept data model automatic conversion method based on semantic analysis |
CN110704522B (en) * | 2019-09-04 | 2023-04-07 | 南京航空航天大学 | Concept data model automatic conversion method based on semantic analysis |
CN110750652A (en) * | 2019-10-21 | 2020-02-04 | 广西大学 | Story ending generation method combining context entity words and knowledge |
CN113139036A (en) * | 2020-01-20 | 2021-07-20 | 海信视像科技股份有限公司 | Information interaction method and equipment |
CN113139036B (en) * | 2020-01-20 | 2022-07-01 | 海信视像科技股份有限公司 | Information interaction method and equipment |
CN111401066A (en) * | 2020-03-12 | 2020-07-10 | 腾讯科技(深圳)有限公司 | Artificial intelligence-based word classification model training method, word processing method and device |
CN111401066B (en) * | 2020-03-12 | 2022-04-12 | 腾讯科技(深圳)有限公司 | Artificial intelligence-based word classification model training method, word processing method and device |
CN111522964A (en) * | 2020-04-17 | 2020-08-11 | 电子科技大学 | Tibetan medicine literature core concept mining method |
CN111797244B (en) * | 2020-07-20 | 2022-06-07 | 华侨大学 | Intelligent situation teaching method and system based on knowledge graph and conversation robot |
CN111797244A (en) * | 2020-07-20 | 2020-10-20 | 华侨大学 | Intelligent situation teaching method and system based on knowledge graph and conversation robot |
CN112182239A (en) * | 2020-09-22 | 2021-01-05 | 中国建设银行股份有限公司 | Information retrieval method and device |
CN113051379A (en) * | 2021-02-24 | 2021-06-29 | 南京审计大学 | Knowledge point recommendation method and device, electronic equipment and storage medium |
CN113051379B (en) * | 2021-02-24 | 2023-08-04 | 南京审计大学 | Knowledge point recommendation method and device, electronic equipment and storage medium |
CN113204651A (en) * | 2021-05-28 | 2021-08-03 | 华侨大学 | Multi-source knowledge graph fusion method and device in Chinese education field |
CN114547346A (en) * | 2022-04-22 | 2022-05-27 | 浙江太美医疗科技股份有限公司 | Knowledge graph construction method and device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110008354B (en) | 2022-06-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110008354A (en) | A kind of construction method of the external Chinese studying content of knowledge based map | |
Wilks | Machine translation: Its scope and limits | |
Preziosi | Architecture, language and meaning: the origins of the built world and its semiotic organization | |
Gouws | Learning, unlearning and innovation in the planning of electronic dictionaries | |
CN109960786A (en) | Chinese Measurement of word similarity based on convergence strategy | |
Goddard | Natural semantic metalanguage | |
Maxwell | Modelling search and stopping in interactive information retrieval | |
Ali et al. | Gender representation in primary level English and Urdu textbooks in Pakistan | |
Fiormonte | Taxation against overrepresentation? The consequences of monolingualism for digital humanities | |
Abduvoitov | THE HERMENEUTIC CONCEPT OF THE TRANSLATION OF PROSE AND NOVELS | |
Wang | Proposing a new oceanic culture-based creative product design method to construct and deconstruct products of the austronesian aborigines | |
Bao et al. | AEG: Argumentative essay generation via a dual-decoder model with content planning | |
Giskin et al. | An introduction to Chinese culture through the family | |
Aytac et al. | Emerging trends in knowledge organization and information organization course curriculum | |
CN103218353B (en) | Mother tongue personage learns the artificial intelligence implementation method with other Languages text | |
Kelly | An analysis of Spanish use in award-winning children’s picturebooks | |
Levisen | The cultural semantics of untranslatables: Linguistic worldview and the Danish language of laughter | |
CN112115722A (en) | Human brain-simulated Chinese analysis method and intelligent interaction system | |
Melliana et al. | translation equivalence and strategies in “laut bercerita (the sea speaks his name)” novel by Leila S. Chudori | |
Ochilova | ANALYSIS OF THE TRANSLATION OF ANTHROPONYMS IN CHILDRENS LITERATURE (ON THE EXAMPLE OF ENGLISH AND UZBEK FOLK TALES). | |
Febriana et al. | An Analysis of Students’ Collocation Translation in EFL Classroom | |
Saputra et al. | The reception of acehnese on hadih maja in the formation of children’s character values in Aceh | |
Saeed et al. | Sense and feel: the missing elements in Faiz Ahmad Faiz’s translated poetry | |
Khaleghi Zavareh | Translation of Culture-Specific Items from English into Persian: A Case Study of The Secret Garden | |
Xu et al. | Sentiment Analysis of Film Reviews Based on Semantic Rules and Extended Domain Sentiment Dictionary |
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 |