CN108694177A - Knowledge mapping construction method and system - Google Patents

Knowledge mapping construction method and system Download PDF

Info

Publication number
CN108694177A
CN108694177A CN201710220269.4A CN201710220269A CN108694177A CN 108694177 A CN108694177 A CN 108694177A CN 201710220269 A CN201710220269 A CN 201710220269A CN 108694177 A CN108694177 A CN 108694177A
Authority
CN
China
Prior art keywords
knowledge
instance
meta
content
text segment
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
Application number
CN201710220269.4A
Other languages
Chinese (zh)
Other versions
CN108694177B (en
Inventor
百华睿
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
New Founder Holdings Development Co ltd
Beijing Founder Electronics Co Ltd
Original Assignee
Peking University Founder Group Co Ltd
Beijing Founder Electronics Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Peking University Founder Group Co Ltd, Beijing Founder Electronics Co Ltd filed Critical Peking University Founder Group Co Ltd
Priority to CN201710220269.4A priority Critical patent/CN108694177B/en
Publication of CN108694177A publication Critical patent/CN108694177A/en
Application granted granted Critical
Publication of CN108694177B publication Critical patent/CN108694177B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00Computing arrangements using knowledge-based models
    • G06N5/02Knowledge representation; Symbolic representation
    • G06N5/022Knowledge engineering; Knowledge acquisition
    • G06N5/025Extracting rules from data

Abstract

A kind of knowledge mapping construction method of present invention offer and system, wherein method include:Obtain the corpus information at least one field of knowledge mapping to be built;Participle and part-of-speech tagging are carried out to the knowledge content of text segment that corpus information includes, obtain keyword therein;Keyword is matched according to default rule with domain body, the knowledge meta-instance in acquisition knowledge content of text segment, the incidence relation between the attribute and knowledge meta-instance of knowledge meta-instance;Domain body includes:Field theme, at least one model that field theme includes, the incidence relation between the attribute and model of model;Model includes at least one knowledge meta-instance;Knowledge mapping is built according to the incidence relation between the attribute and knowledge meta-instance of knowledge meta-instance, knowledge meta-instance in multiple knowledge content of text segments.The present invention realizes automation structure knowledge mapping, reduces the construction cost of knowledge mapping, improves the structure efficiency and accuracy rate of knowledge mapping.

Description

Knowledge mapping construction method and system
Technical field
The present invention relates to pro digital publishing area more particularly to a kind of knowledge mapping construction method and systems.
Background technology
Knowledge services are the hot spots that pro digital publishing area is pursued for a period of time recently, and country is a large amount of in this respect to be provided Gold input also accelerates the time that knowledge services are landed in publisher.But the domestic Knowledge Service System built is general at present For be still traditional document rank knowledge services, traditional full-text search mode is provided, is also in terms of resource associations Interrelational form between document and bibliography.
In order to realize real knowledge retrieval, build as knowledge retrieval base support various types of knowledge hierarchies just At key, current part society of commercial press leading in terms of knowledge hierarchy structure has conveniently had in field thesaurus Certain accumulation, but for knowledge retrieval, build domain body and knowledge mapping is only optimal target.
However, for professional domain, it is desirable to be able to which the expert being well understood by this profession could be qualified next manual Knowledge mapping is built, has put into a large amount of input of artificial and time, the efficiency for building knowledge mapping is too low, and cost is too high, accurately Rate is too low.
Invention content
The present invention provides a kind of knowledge mapping construction method and system, for solve in the prior art structure knowledge mapping at This height, the low problem of efficiency.
The first aspect of the invention is to provide a kind of knowledge mapping construction method, including:
The corpus information at least one field of knowledge mapping to be built is obtained, the corpus information includes:Multiple knowledge Content of text segment;
Participle and part-of-speech tagging are carried out to the knowledge content of text segment, obtained in the knowledge content of text segment Keyword;
The keyword is matched according to default rule with domain body, the knowledge content of text segment is obtained In knowledge meta-instance, the knowledge meta-instance attribute and the knowledge meta-instance between incidence relation;The field Ontology includes:Field theme, at least one model that field theme includes, the association between the attribute and model of model are closed System;The model includes at least one knowledge meta-instance;
According to the attribute of knowledge meta-instance, the knowledge meta-instance in the multiple knowledge content of text segment and institute State the incidence relation structure knowledge mapping between knowledge meta-instance.
Further, described to match the keyword with domain body according to default rule, know described in acquisition Knowledge meta-instance in knowledge content of text segment, the association between the attribute and the knowledge meta-instance of the knowledge meta-instance Relationship, including:
By the field theme at least one of knowledge content of text segment keyword and the domain body into Row matching, determines the field theme of the knowledge content of text segment;
By at least one of knowledge content of text segment keyword according to default rule and corresponding field master The included model of topic is matched, in determining and the knowledge content of text fragment match model and the knowledge text Hold the knowledge meta-instance of segment;
By at least one of knowledge content of text segment keyword according to default rule and corresponding model Attribute is matched, and determines the attribute of knowledge meta-instance in the knowledge content of text segment;
The attribute of knowledge meta-instance in incidence relation and the knowledge content of text segment between binding model determines Incidence relation between knowledge meta-instance.
Further, it is described by least one of knowledge content of text segment keyword according to default rule with Model included by corresponding field theme is matched, and is determined and the model of the knowledge content of text fragment match and institute The knowledge meta-instance of knowledge content of text segment is stated, including:
By at least one of knowledge content of text segment keyword and the model included by corresponding field theme It is matched successively, determines the confidence level of each model;
The model with the knowledge content of text fragment match is determined according to the confidence level of each model;
At least one of knowledge content of text segment keyword is matched with the content of corresponding model, really The knowledge meta-instance of the fixed knowledge content of text segment.
Further, described by least one of knowledge content of text segment keyword and corresponding field theme Included model is matched successively, determines the confidence level of each model, including:
Multiple models included by the theme of field for the knowledge content of text segment, by the knowledge content of text At least one of segment keyword is matched successively with multiple contents of the model, determines the weight of the model;
According to the weight of the multiple model, the confidence level of the multiple model is determined.
Further, the attribute of the knowledge meta-instance includes:Common property and relating attribute;
The common property includes:Primary attribute;
The knowledge meta-instance according in the multiple knowledge content of text segment, the knowledge meta-instance attribute with And after the incidence relation structure knowledge mapping between the knowledge meta-instance, further include:
Obtain the relevant information of the corresponding knowledge content of text segment of knowledge meta-instance;The relevant information includes:Knowledge The content and source-information of content of text segment;
The relevant information of the knowledge content of text segment is determined as to the primary attribute value of knowledge meta-instance.
Further, knowledge meta-instance, the Knowledge Element reality according in the multiple knowledge content of text segment After incidence relation structure knowledge mapping between the attribute and the knowledge meta-instance of example, further include:
Multiple association knowledges member that there is the first incidence relation with the knowledge meta-instance is obtained from the knowledge mapping Example;
The related letter of the corresponding knowledge content of text segment of the association knowledge meta-instance is obtained from the knowledge mapping Breath;
The relevant information of the corresponding knowledge content of text segment of the association knowledge meta-instance is determined as knowledge meta-instance The first relating attribute value.
Further, knowledge meta-instance, the Knowledge Element reality according in the multiple knowledge content of text segment After incidence relation structure knowledge mapping between the attribute and the knowledge meta-instance of example, further include:
The knowledge mapping is shown.
Further, knowledge meta-instance, the Knowledge Element reality according in the multiple knowledge content of text segment After incidence relation structure knowledge mapping between the attribute and the knowledge meta-instance of example, further include:
The inquiry instruction of user is received, knowledge meta-instance is carried in the inquiry instruction;
According to the Knowledge Element Query By Example knowledge mapping, attribute, the Knowledge Element for obtaining the knowledge meta-instance are real Example incidence relation, the corresponding knowledge content of text segment of the knowledge meta-instance and with the knowledge meta-instance have be associated with The corresponding knowledge content of text segment of association knowledge meta-instance of relationship;
The attribute of the knowledge meta-instance, the incidence relation of the knowledge meta-instance, the knowledge meta-instance is corresponding Knowledge content of text segment and there is the association knowledge meta-instance of incidence relation corresponding knowledge text with the knowledge meta-instance This contents fragment is shown.
In the present invention, the corpus information at least one field by obtaining knowledge mapping to be built, the corpus information Including:Multiple knowledge content of text segments;Participle and part-of-speech tagging are carried out to the knowledge content of text segment, described in acquisition Keyword in knowledge content of text segment;The keyword is matched according to default rule with domain body, is obtained Between the attribute and the knowledge meta-instance of knowledge meta-instance, the knowledge meta-instance in the knowledge content of text segment Incidence relation;The domain body includes:Field theme, at least one model that field theme includes, the attribute of model with And the incidence relation between model;The model includes at least one knowledge meta-instance;According to the multiple knowledge content of text Incidence relation structure between the attribute and the knowledge meta-instance of knowledge meta-instance, the knowledge meta-instance in segment is known Know collection of illustrative plates.The present invention realizes automation structure knowledge mapping, reduces the construction cost of knowledge mapping, improves knowledge mapping Structure efficiency and accuracy rate.
The second aspect of the invention is to provide a kind of knowledge mapping structure system, including:
Acquisition module, the corpus information at least one field for obtaining knowledge mapping to be built, the corpus information Including:Multiple knowledge content of text segments;
Participle and part-of-speech tagging module, for carrying out participle and part-of-speech tagging to the knowledge content of text segment, Obtain the keyword in the knowledge content of text segment;
Matching module is known for matching the keyword with domain body according to default rule described in acquisition Knowledge meta-instance in knowledge content of text segment, the association between the attribute and the knowledge meta-instance of the knowledge meta-instance Relationship;The domain body includes:Field theme, at least one model that field theme includes, the attribute and model of model Between incidence relation;The model includes at least one knowledge meta-instance;
Module is built, for real according to the knowledge meta-instance in the multiple knowledge content of text segment, the Knowledge Element Incidence relation between the attribute and the knowledge meta-instance of example builds knowledge mapping.
Further, the matching module includes:
First matching unit is used at least one of knowledge content of text segment keyword and the field sheet Field theme in body is matched, and determines the field theme of the knowledge content of text segment;
Second matching unit is used at least one of knowledge content of text segment keyword according to preset rule Then matched with the model included by corresponding field theme, determine with the model of the knowledge content of text fragment match with And the knowledge meta-instance of the knowledge content of text segment;
Third matching unit is used at least one of knowledge content of text segment keyword according to preset rule It is then matched with the attribute of corresponding model, determines the attribute of knowledge meta-instance in the knowledge content of text segment;
It is real to be used for Knowledge Element in the incidence relation between binding model and the knowledge content of text segment for determination unit The attribute of example, determines the incidence relation between knowledge meta-instance.
In the present invention, the corpus information at least one field by obtaining knowledge mapping to be built, the corpus information Including:Multiple knowledge content of text segments;Participle and part-of-speech tagging are carried out to the knowledge content of text segment, described in acquisition Keyword in knowledge content of text segment;The keyword is matched according to default rule with domain body, is obtained Between the attribute and the knowledge meta-instance of knowledge meta-instance, the knowledge meta-instance in the knowledge content of text segment Incidence relation;The domain body includes:Field theme, at least one model that field theme includes, the attribute of model with And the incidence relation between model;The model includes at least one knowledge meta-instance;According to the multiple knowledge content of text Incidence relation structure between the attribute and the knowledge meta-instance of knowledge meta-instance, the knowledge meta-instance in segment is known Know collection of illustrative plates.The present invention realizes automation structure knowledge mapping, reduces the construction cost of knowledge mapping, improves knowledge mapping Structure efficiency and accuracy rate.
Description of the drawings
Fig. 1 is the flow chart of knowledge mapping construction method one embodiment provided by the invention;
Fig. 2 is the flow chart of another embodiment of knowledge mapping construction method provided by the invention;
Fig. 3 is the flow chart of another embodiment of knowledge mapping construction method provided by the invention;
Fig. 4 is the structural schematic diagram that knowledge mapping provided by the invention builds system one embodiment;
Fig. 5 is the structural schematic diagram that knowledge mapping provided by the invention builds another embodiment of system.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art The every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Fig. 1 is the flow chart of knowledge mapping construction method one embodiment provided by the invention, as shown in Figure 1, including:
101, the corpus information at least one field of knowledge mapping to be built is obtained, corpus information includes:Multiple knowledge Content of text segment.
The executive agent of knowledge mapping construction method provided by the invention is that knowledge mapping builds system, knowledge mapping structure System can be hardware devices or the softwares on hardware device such as computer, server.
Wherein, field can refer to professional domain, such as " metallurgy " field, " economy " field, " medicine " field etc., and field can There is " pediatric medicine " field below multiple subdomains, such as " medicine " field to have.Corpus information refers to knowledge content of text piece Section, the Description of Knowledge content by way of natural language can be divided into raw language material and idiom material.The language of original not processed index Expect that language material of making a living, the language material after Machining Analysis are known as idiom material.Idiom material includes raw text content, natural language point Knowledge meta-instance and its attribute etc. described in word result and part of speech analysis result, text.Involved in the present embodiment to wait for structure The corpus information for building knowledge mapping is made a living language material.For example " meningitis can be confirmed knowledge content of text segment by medical practitioner Rear antibiotic medicine is treated ".
102, participle and part-of-speech tagging are carried out to knowledge content of text segment, obtains the pass in knowledge content of text segment Keyword.
103, keyword is matched according to default rule with domain body, is obtained in knowledge content of text segment Incidence relation between knowledge meta-instance, the attribute of knowledge meta-instance and knowledge meta-instance;Domain body includes:Field master Topic, at least one model that field theme includes, the incidence relation between the attribute and model of model;Model includes at least one A knowledge meta-instance.
Wherein, field theme can refer to professional domain or subdomains.Professional domain, such as " metallurgy " field, " economy " Field, " medicine " field etc., field can have and have " pediatric medicine " field below multiple subdomains, such as " medicine " field.Often Being had in a field has the models such as " hospital ", " expert ", " disease ", " drug " in multiple models, such as " medicine " field.Each Model has oneself distinctive attribute, such as " disease " model has " symptom ", " diagnosis ", " pathological change ", " therapeutic scheme " Equal attributes.Had between model and have " treatment " relationship between various incidence relations, such as " drug " and " disease ", " expert " and Also the relationship of " being good at treatment " is had between " disease "." meningitis " is a knowledge meta-instance of " disease " model." antibiotic Drug " is a knowledge meta-instance of " drug " model.There is " treatment " relationship between " antibiotic medicine " and " meningitis ".
104, according to the attribute and Knowledge Element of knowledge meta-instance, knowledge meta-instance in multiple knowledge content of text segments Incidence relation between example builds knowledge mapping.
Further, after step 104, can also include:Knowledge mapping is shown.
Specifically, knowledge mapping structure system can provide the displaying interface that can be interacted, and be shown in a manner of visual Knowledge mapping stores collection of illustrative plates node and relationship for example, by using chart database Neo4j, is shown on a web browser using D3 plug-in units whole A knowledge mapping.In addition, knowledge mapping structure system can also according to the demand of user be shown knowledge mapping.For example, The knowledge mapping for receiving user checks instruction, and the field theme in some field is carried in instruction;Knowledge mapping build system according to The knowledge mapping for checking the corresponding field of instruction displaying of user.
Further, after step 104, can also include:The inquiry instruction of user is received, carries and knows in inquiry instruction Know meta-instance;It is closed according to the association of Knowledge Element Query By Example knowledge mapping, the attribute, knowledge meta-instance that obtain knowledge meta-instance System, the corresponding knowledge content of text segment of knowledge meta-instance and the association knowledge member reality with knowledge meta-instance with incidence relation The corresponding knowledge content of text segment of example;By the attribute of knowledge meta-instance, the incidence relation of knowledge meta-instance, knowledge meta-instance pair The knowledge content of text segment answered and there is the corresponding knowledge text of the association knowledge meta-instance of incidence relation with knowledge meta-instance This contents fragment is shown.
The knowledge system construction that every field can be inquired by above-mentioned knowledge mapping user, can also inquire and certain A relevant all documents of knowledge meta-instance, to use.
In the present embodiment, the corpus information at least one field by obtaining knowledge mapping to be built, the language material letter Breath includes:Multiple knowledge content of text segments;Participle and part-of-speech tagging are carried out to the knowledge content of text segment, obtain institute State the keyword in knowledge content of text segment;The keyword is matched according to default rule with domain body, is obtained Take knowledge meta-instance in the knowledge content of text segment, the attribute of the knowledge meta-instance and the knowledge meta-instance it Between incidence relation;The domain body includes:Field theme, at least one model that field theme includes, the attribute of model And the incidence relation between model;The model includes at least one knowledge meta-instance;According in the multiple knowledge text The incidence relation held between the attribute and the knowledge meta-instance of the knowledge meta-instance in segment, the knowledge meta-instance is built Knowledge mapping.The present invention realizes automation structure knowledge mapping, reduces the construction cost of knowledge mapping, improves knowledge graph The structure efficiency and accuracy rate of spectrum.
Fig. 2 is the flow chart of another embodiment of knowledge mapping construction method provided by the invention, as shown in Fig. 2, in Fig. 1 On the basis of illustrated embodiment, step 103 can specifically include:
1031, by the field theme progress at least one of knowledge content of text segment keyword and domain body Match, determines the field theme of knowledge content of text segment.
1032, by least one of knowledge content of text segment keyword according to default rule and corresponding field master The included model of topic is matched, the model and knowledge content of text segment of determination and knowledge content of text fragment match Knowledge meta-instance.
Wherein, knowledge mapping structure system can by least one of knowledge content of text segment keyword with it is corresponding Model included by the theme of field is matched successively, determines the confidence level of each model;Confidence level according to each model is true Fixed and knowledge content of text fragment match model;By at least one of knowledge content of text segment keyword and corresponding mould The content of type is matched, and determines the knowledge meta-instance of knowledge content of text segment.
Specifically, multiple models included by the field theme for knowledge content of text segment, knowledge mapping structure system System can match at least one of knowledge content of text segment keyword successively with multiple contents of the model, really The weight of cover half type;According to the weight of the multiple model, the confidence level of the multiple model is determined.Wherein, knowledge mapping structure The system of building can carry out multiple contents of at least one of knowledge content of text segment keyword and the model successively Match, the quantity of content similar at least one of knowledge content of text segment keyword is determined, so that it is determined that the power of model Weight.
Wherein, the content of model is the knowledge meta-instance that model includes.
It needs to illustrate, matching rule includes mainly rule name and Rule content two parts, Rule content are Knowledge mapping builds the object of network analysis application, is to be extended by regular expression, such as " creating the time " is one Rule, its content are that " ^.* is created in (.*) year .* $ ", which is mainly used to identify the creation time of some object.
This system increases customized identifier on the basis of regular expression.
Proper name word indicator:[[{str}]], wherein str is enumerated value, indicates proper name word class, classification can be in proper name Defined in vocabulary.Acquiescence includes following several:A:Personage;B:Place;C:Event;D:Mechanism;E:Time.
In addition to acquiescence, can in proper name vocabulary customization type, common sense class word built in the data system of proper name vocabulary It converges, the proper name word of professional domain can import the dictionary of professional domain.Proper name vocabulary creates for auxiliary regular, extends canonical table Up to the matching scope of formula, domain knowledge is added.
1033, by least one of knowledge content of text segment keyword according to default rule and corresponding model Attribute is matched, and determines the attribute of knowledge meta-instance in knowledge content of text segment.
Specifically, the attribute of model includes:Common property and relating attribute.For common property, pass through rule If with it is rear obtain it is multiple as a result, can in conjunction with weight and number of repetition it is high select one, other attributes are deposited as supplement Storage is got up, and manual confirmation is waited for.Such as identify " Peking University " creation time have it is multiple as a result, wherein only have one be 1900 Year, others are all 1898, then result can adopt 1898.
For relating attribute, by after rule match if obtained multiple as a result, can be by resulting text content all It stores.Then system does content of text following analysis.If the relationship between relating attribute and model is reflected Penetrate, then illustrate that keyword must be Knowledge Element, such as " meningitis can be confirmed by medical practitioner after antibiotic medicine come Treatment " this section words, the value that the treatment attribute of disease knowledge meta-instance " meningitis " has been gone out by Rule Extraction are that " medical practitioner is true Antibiotic medicine after recognizing " is obtained " antibiotic medicine " by keyword extraction, and in domain body management, it is provided with There is treatment relationship between " disease " model and " drug " model, and is mapped with " treatment " attribute of " disease ".So It is hereby achieved that " antibiotic medicine " is exactly the knowledge meta-instance of " drug " model.At this point, if our knowledge mapping is deposited At " antibiotic medicine ", it is associated with then can be established with " meningitis ", it can be certainly if there are no " antibiotic ", system in collection of illustrative plates The dynamic new knowledge meta-instance for generating " drug " model.It is thus achieved that the automation extension of knowledge meta-instance.
1034, in the incidence relation between binding model and knowledge content of text segment knowledge meta-instance attribute, really Determine the incidence relation between knowledge meta-instance.
In the present embodiment, the corpus information at least one field by obtaining knowledge mapping to be built, the language material letter Breath includes:Multiple knowledge content of text segments;Participle and part-of-speech tagging are carried out to the knowledge content of text segment, obtain institute State the keyword in knowledge content of text segment;It will be at least one of knowledge content of text segment keyword and domain body Field theme matched, determine the field theme of knowledge content of text segment;By in knowledge content of text segment at least One keyword is matched according to default rule with the model included by corresponding field theme, in determining and knowledge text Hold the model of fragment match and the knowledge meta-instance of knowledge content of text segment;By at least one in knowledge content of text segment A keyword is matched according to default rule with the attribute of corresponding model, determines Knowledge Element in knowledge content of text segment The attribute of example;The attribute of knowledge meta-instance in incidence relation and knowledge content of text segment between binding model determines Incidence relation between knowledge meta-instance;According to knowledge meta-instance, the knowledge in the multiple knowledge content of text segment Incidence relation between the attribute of meta-instance and the knowledge meta-instance builds knowledge mapping.The present invention realizes automation structure Knowledge mapping is built, the construction cost of knowledge mapping is reduced, improves the structure efficiency and accuracy rate of knowledge mapping.
Fig. 3 is the structural schematic diagram of another embodiment of knowledge mapping construction method provided by the invention, as shown in figure 3, On the basis of embodiment shown in Fig. 1, further include:
105, the relevant information of the corresponding knowledge content of text segment of knowledge meta-instance is obtained;Relevant information includes:Knowledge The content and source-information of content of text segment.
106, the relevant information of knowledge content of text segment is determined as to the primary attribute value of knowledge meta-instance.
107, multiple association knowledge meta-instances that there is the first incidence relation with knowledge meta-instance are obtained from knowledge mapping.
108, the relevant information of the corresponding knowledge content of text segment of association knowledge meta-instance is obtained from knowledge mapping.
109, the relevant information of the corresponding knowledge content of text segment of association knowledge meta-instance is determined as knowledge meta-instance The first relating attribute value.
In the present embodiment, by the base that the relevant information of knowledge content of text segment is determined as to corresponding knowledge meta-instance Plinth attribute value will have the corresponding knowledge content of text of multiple association knowledge meta-instances of the first incidence relation with knowledge meta-instance Relevant information be determined as knowledge meta-instance the first relating attribute value so that knowledge mapping structure system receiving It, can be by the attribute of knowledge meta-instance, the association of the knowledge meta-instance when inquiry request of the carrying knowledge meta-instance of user Relationship, the corresponding knowledge content of text segment of the knowledge meta-instance and the pass with the knowledge meta-instance with incidence relation The corresponding knowledge content of text segment of connection knowledge meta-instance is shown to user.
One of ordinary skill in the art will appreciate that:Realize that all or part of step of above-mentioned each method embodiment can lead to The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer read/write memory medium.The journey When being executed, execution includes the steps that above-mentioned each method embodiment to sequence;And storage medium above-mentioned includes:ROM, RAM, magnetic disc or The various media that can store program code such as person's CD.
Fig. 4 is the structural schematic diagram that knowledge mapping provided by the invention builds system one embodiment, as shown in figure 4, packet It includes:
Acquisition module 41, the corpus information at least one field for obtaining knowledge mapping to be built, corpus information packet It includes:Multiple knowledge content of text segments;
Participle and part-of-speech tagging module 42 are obtained for carrying out participle and part-of-speech tagging to knowledge content of text segment Take the keyword in knowledge content of text segment;
Matching module 43 obtains knowledge text for matching keyword with domain body according to default rule Incidence relation between the attribute and knowledge meta-instance of knowledge meta-instance, knowledge meta-instance in contents fragment;Domain body Including:Field theme, at least one model that field theme includes, the incidence relation between the attribute and model of model;Mould Type includes at least one knowledge meta-instance;
Module 44 is built, for the category according to knowledge meta-instance, knowledge meta-instance in multiple knowledge content of text segments Property and knowledge meta-instance between incidence relation build knowledge mapping.
Knowledge mapping structure system provided by the invention can be the hardware devices such as computer, server or be mounted on hard Software in part equipment.
Further, knowledge mapping structure system can also include:Display module, for being shown to knowledge mapping.
Specifically, knowledge mapping structure system can provide the displaying interface that can be interacted, and be shown in a manner of visual Knowledge mapping stores collection of illustrative plates node and relationship for example, by using chart database Neo4j, is shown on a web browser using D3 plug-in units whole A knowledge mapping.In addition, knowledge mapping structure system can also according to the demand of user be shown knowledge mapping.For example, The knowledge mapping for receiving user checks instruction, and the field theme in some field is carried in instruction;Knowledge mapping build system according to The knowledge mapping for checking the corresponding field of instruction displaying of user.
Further, knowledge mapping structure system can also receive the inquiry instruction of user, carry and know in inquiry instruction Know meta-instance;It is closed according to the association of Knowledge Element Query By Example knowledge mapping, the attribute, knowledge meta-instance that obtain knowledge meta-instance System, the corresponding knowledge content of text segment of knowledge meta-instance and the association knowledge member reality with knowledge meta-instance with incidence relation The corresponding knowledge content of text segment of example;By the attribute of knowledge meta-instance, the incidence relation of knowledge meta-instance, knowledge meta-instance pair The knowledge content of text segment answered and there is the corresponding knowledge text of the association knowledge meta-instance of incidence relation with knowledge meta-instance This contents fragment is shown.
The knowledge system construction that every field can be inquired by above-mentioned knowledge mapping user, can also inquire and certain A relevant all documents of knowledge meta-instance, to use.
Further, after knowledge mapping structure system structure knowledge mapping, it is corresponding that knowledge meta-instance can also be obtained The relevant information of knowledge content of text segment;Relevant information includes:The content and source-information of knowledge content of text segment;It will The relevant information of knowledge content of text segment is determined as the primary attribute value of knowledge meta-instance;From knowledge mapping obtain with it is described Knowledge meta-instance has multiple association knowledge meta-instances of the first incidence relation;Association knowledge meta-instance is obtained from knowledge mapping The relevant information of corresponding knowledge content of text segment;By the corresponding knowledge content of text segment of the association knowledge meta-instance Relevant information is determined as the value of the first relating attribute of knowledge meta-instance.
It is real by the way that the relevant information of knowledge content of text segment is determined as corresponding Knowledge Element that knowledge mapping builds system The primary attribute value of example will have multiple association knowledge meta-instances of the first incidence relation corresponding knowledge text with knowledge meta-instance The relevant information of this content is determined as the value of the first relating attribute of knowledge meta-instance, so that knowledge mapping structure system exists It, can be by the attribute of knowledge meta-instance, the knowledge meta-instance when receiving the inquiry request of carrying knowledge meta-instance of user Incidence relation, the corresponding knowledge content of text segment of the knowledge meta-instance and with the knowledge meta-instance have be associated with The corresponding knowledge content of text segment of association knowledge meta-instance of system is shown to user.
In the present embodiment, the corpus information at least one field by obtaining knowledge mapping to be built, the language material letter Breath includes:Multiple knowledge content of text segments;Participle and part-of-speech tagging are carried out to the knowledge content of text segment, obtain institute State the keyword in knowledge content of text segment;The keyword is matched according to default rule with domain body, is obtained Take knowledge meta-instance in the knowledge content of text segment, the attribute of the knowledge meta-instance and the knowledge meta-instance it Between incidence relation;The domain body includes:Field theme, at least one model that field theme includes, the attribute of model And the incidence relation between model;The model includes at least one knowledge meta-instance;According in the multiple knowledge text The incidence relation held between the attribute and the knowledge meta-instance of the knowledge meta-instance in segment, the knowledge meta-instance is built Knowledge mapping.The present invention realizes automation structure knowledge mapping, reduces the construction cost of knowledge mapping, improves knowledge graph The structure efficiency and accuracy rate of spectrum.
Further, in conjunction with reference to figure 5, on the basis of embodiment shown in Fig. 4, the matching module 43 includes:
First matching unit 431, for will be at least one of knowledge content of text segment keyword and domain body Field theme matched, determine the field theme of knowledge content of text segment;
Second matching unit 432 is used at least one of knowledge content of text segment keyword according to preset rule It is then matched, determine the model with knowledge content of text fragment match and is known with the model included by corresponding field theme Know the knowledge meta-instance of content of text segment;
Third matching unit 433 is used at least one of knowledge content of text segment keyword according to preset rule It is then matched with the attribute of corresponding model, determines the attribute of knowledge meta-instance in knowledge content of text segment;
It is real to be used for Knowledge Element in the incidence relation between binding model and knowledge content of text segment for determination unit 434 The attribute of example, determines the incidence relation between knowledge meta-instance.
Wherein, knowledge mapping structure system can by least one of knowledge content of text segment keyword with it is corresponding Model included by the theme of field is matched successively, determines the confidence level of each model;Confidence level according to each model is true Fixed and knowledge content of text fragment match model;By at least one of knowledge content of text segment keyword and corresponding mould The content of type is matched, and determines the knowledge meta-instance of knowledge content of text segment.
Specifically, multiple models included by the field theme for knowledge content of text segment, knowledge mapping structure system System can match at least one of knowledge content of text segment keyword successively with multiple contents of the model, really The weight of cover half type;According to the weight of the multiple model, the confidence level of the multiple model is determined.Wherein, knowledge mapping structure The system of building can carry out multiple contents of at least one of knowledge content of text segment keyword and the model successively Match, the quantity of content similar at least one of knowledge content of text segment keyword is determined, so that it is determined that the power of model Weight.
Wherein, the content of model is the knowledge meta-instance that model includes.
It also needs to illustrate, the attribute of model may include:Common property and relating attribute.For common property For, by after rule match if obtain it is multiple as a result, can in conjunction with weight and number of repetition it is high select one, other Attribute is stored as supplement, waits for manual confirmation.Such as identify " Peking University " creation time have it is multiple as a result, wherein Only one is 1900, and others are all 1898, then result can adopt 1898.
For relating attribute, by after rule match if obtained multiple as a result, can be by resulting text content all It stores.Then system does content of text following analysis.If the relationship between relating attribute and model is reflected Penetrate, then illustrate that keyword must be Knowledge Element, such as " meningitis can be confirmed by medical practitioner after antibiotic medicine come Treatment " this section words, the value that the treatment attribute of disease knowledge meta-instance " meningitis " has been gone out by Rule Extraction are that " medical practitioner is true Antibiotic medicine after recognizing " is obtained " antibiotic medicine " by keyword extraction, and in domain body management, it is provided with There is treatment relationship between " disease " model and " drug " model, and is mapped with " treatment " attribute of " disease ".So It is hereby achieved that " antibiotic medicine " is exactly the knowledge meta-instance of " drug " model.At this point, if our knowledge mapping is deposited At " antibiotic medicine ", it is associated with then can be established with " meningitis ", it can be certainly if there are no " antibiotic ", system in collection of illustrative plates The dynamic new knowledge meta-instance for generating " drug " model.It is thus achieved that the automation extension of knowledge meta-instance.
In the present embodiment, the corpus information at least one field by obtaining knowledge mapping to be built, the language material letter Breath includes:Multiple knowledge content of text segments;Participle and part-of-speech tagging are carried out to the knowledge content of text segment, obtain institute State the keyword in knowledge content of text segment;It will be at least one of knowledge content of text segment keyword and domain body Field theme matched, determine the field theme of knowledge content of text segment;By in knowledge content of text segment at least One keyword is matched according to default rule with the model included by corresponding field theme, in determining and knowledge text Hold the model of fragment match and the knowledge meta-instance of knowledge content of text segment;By at least one in knowledge content of text segment A keyword is matched according to default rule with the attribute of corresponding model, determines Knowledge Element in knowledge content of text segment The attribute of example;The attribute of knowledge meta-instance in incidence relation and knowledge content of text segment between binding model determines Incidence relation between knowledge meta-instance;According to knowledge meta-instance, the knowledge in the multiple knowledge content of text segment Incidence relation between the attribute of meta-instance and the knowledge meta-instance builds knowledge mapping.The present invention realizes automation structure Knowledge mapping is built, the construction cost of knowledge mapping is reduced, improves the structure efficiency and accuracy rate of knowledge mapping.
Finally it should be noted that:The above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations;To the greatest extent Present invention has been described in detail with reference to the aforementioned embodiments for pipe, it will be understood by those of ordinary skill in the art that:Its according to So can with technical scheme described in the above embodiments is modified, either to which part or all technical features into Row equivalent replacement;And these modifications or replacements, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution The range of scheme.

Claims (10)

1. a kind of knowledge mapping construction method, which is characterized in that including:
The corpus information at least one field of knowledge mapping to be built is obtained, the corpus information includes:Multiple knowledge texts Contents fragment;
Participle and part-of-speech tagging are carried out to the knowledge content of text segment, obtain the pass in the knowledge content of text segment Keyword;
The keyword is matched according to default rule with domain body, is obtained in the knowledge content of text segment Knowledge meta-instance, the knowledge meta-instance attribute and the knowledge meta-instance between incidence relation;The domain body Including:Field theme, at least one model that field theme includes, the incidence relation between the attribute and model of model;Institute It includes at least one knowledge meta-instance to state model;
According to the attribute of knowledge meta-instance, the knowledge meta-instance in the multiple knowledge content of text segment and described know The incidence relation known between meta-instance builds knowledge mapping.
2. according to the method described in claim 1, it is characterized in that, it is described by the keyword according to default rule and field Ontology is matched, obtain knowledge meta-instance in the knowledge content of text segment, the knowledge meta-instance attribute and Incidence relation between the knowledge meta-instance, including:
By the field theme progress at least one of knowledge content of text segment keyword and the domain body Match, determines the field theme of the knowledge content of text segment;
By at least one of knowledge content of text segment keyword according to default rule and corresponding field theme institute Including model matched, determine and the model of the knowledge content of text fragment match and the knowledge content of text piece The knowledge meta-instance of section;
By at least one of knowledge content of text segment keyword according to the attribute of default rule and corresponding model It is matched, determines the attribute of knowledge meta-instance in the knowledge content of text segment;
The attribute of knowledge meta-instance, determines knowledge in incidence relation and the knowledge content of text segment between binding model Incidence relation between meta-instance.
3. according to the method described in claim 2, it is characterized in that, it is described by the knowledge content of text segment at least one A keyword is matched according to default rule with the model included by corresponding field theme, is determined and the knowledge text The knowledge meta-instance of the matched model of contents fragment and the knowledge content of text segment, including:
Successively by least one of knowledge content of text segment keyword and the model included by corresponding field theme It is matched, determines the confidence level of each model;
The model with the knowledge content of text fragment match is determined according to the confidence level of each model;
At least one of knowledge content of text segment keyword is matched with the content of corresponding model, determines institute State the knowledge meta-instance of knowledge content of text segment.
4. according to the method described in claim 3, it is characterized in that, it is described by the knowledge content of text segment at least one A keyword is matched successively with the model included by corresponding field theme, determines the confidence level of each model, including:
Multiple models included by the theme of field for the knowledge content of text segment, by the knowledge content of text segment At least one of keyword matched successively with multiple contents of the model, determine the weight of the model;
According to the weight of the multiple model, the confidence level of the multiple model is determined.
5. according to the method described in claim 1, it is characterized in that, the attribute of the knowledge meta-instance includes:Common property and Relating attribute;
The common property includes:Primary attribute;
The knowledge meta-instance according in the multiple knowledge content of text segment, the attribute of the knowledge meta-instance and institute After stating the incidence relation structure knowledge mapping between knowledge meta-instance, further include:
Obtain the relevant information of the corresponding knowledge content of text segment of knowledge meta-instance;The relevant information includes:Knowledge text The content and source-information of contents fragment;
The relevant information of the knowledge content of text segment is determined as to the primary attribute value of knowledge meta-instance.
6. according to the method described in claim 5, it is characterized in that, described according in the multiple knowledge content of text segment Knowledge meta-instance, the knowledge meta-instance attribute and the knowledge meta-instance between incidence relation structure knowledge mapping it Afterwards, further include:
Multiple association knowledge meta-instances that there is the first incidence relation with the knowledge meta-instance are obtained from the knowledge mapping;
The relevant information of the corresponding knowledge content of text segment of the association knowledge meta-instance is obtained from the knowledge mapping;
The relevant information of the corresponding knowledge content of text segment of the association knowledge meta-instance is determined as the of knowledge meta-instance The value of one relating attribute.
7. according to the method described in claim 1, it is characterized in that, described according in the multiple knowledge content of text segment Knowledge meta-instance, the knowledge meta-instance attribute and the knowledge meta-instance between incidence relation structure knowledge mapping it Afterwards, further include:
The knowledge mapping is shown.
8. according to the method described in claim 1, it is characterized in that, described according in the multiple knowledge content of text segment Knowledge meta-instance, the knowledge meta-instance attribute and the knowledge meta-instance between incidence relation structure knowledge mapping it Afterwards, further include:
The inquiry instruction of user is received, knowledge meta-instance is carried in the inquiry instruction;
According to the Knowledge Element Query By Example knowledge mapping, the attribute of the knowledge meta-instance, the knowledge meta-instance are obtained Incidence relation, the corresponding knowledge content of text segment of the knowledge meta-instance and with the knowledge meta-instance have incidence relation The corresponding knowledge content of text segment of association knowledge meta-instance;
By the attribute of the knowledge meta-instance, the incidence relation of the knowledge meta-instance, the corresponding knowledge of the knowledge meta-instance Content of text segment and have in the corresponding knowledge text of the association knowledge meta-instance of incidence relation with the knowledge meta-instance Hold segment to be shown.
9. a kind of knowledge mapping builds system, which is characterized in that including:
Acquisition module, the corpus information at least one field for obtaining knowledge mapping to be built, the corpus information include: Multiple knowledge content of text segments;
Participle and part-of-speech tagging module are obtained for carrying out participle and part-of-speech tagging to the knowledge content of text segment Keyword in the knowledge content of text segment;
Matching module obtains the knowledge text for matching the keyword with domain body according to default rule Association between the attribute and the knowledge meta-instance of knowledge meta-instance, the knowledge meta-instance in this contents fragment is closed System;The domain body includes:Field theme, at least one model that field theme includes, the attribute and model of model it Between incidence relation;The model includes at least one knowledge meta-instance;
Module is built, for according to knowledge meta-instance, the knowledge meta-instance in the multiple knowledge content of text segment Incidence relation between attribute and the knowledge meta-instance builds knowledge mapping.
10. system according to claim 9, which is characterized in that the matching module includes:
First matching unit, for will be at least one of knowledge content of text segment keyword and the domain body Field theme matched, determine the field theme of the knowledge content of text segment;
Second matching unit, for by least one of knowledge content of text segment keyword according to default rule with Model included by corresponding field theme is matched, and is determined and the model of the knowledge content of text fragment match and institute State the knowledge meta-instance of knowledge content of text segment;
Third matching unit, for by least one of knowledge content of text segment keyword according to default rule with The attribute of corresponding model is matched, and determines the attribute of knowledge meta-instance in the knowledge content of text segment;
Determination unit is used for knowledge meta-instance in the incidence relation between binding model and the knowledge content of text segment Attribute determines the incidence relation between knowledge meta-instance.
CN201710220269.4A 2017-04-06 2017-04-06 Knowledge graph construction method and system Active CN108694177B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710220269.4A CN108694177B (en) 2017-04-06 2017-04-06 Knowledge graph construction method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710220269.4A CN108694177B (en) 2017-04-06 2017-04-06 Knowledge graph construction method and system

Publications (2)

Publication Number Publication Date
CN108694177A true CN108694177A (en) 2018-10-23
CN108694177B CN108694177B (en) 2022-02-18

Family

ID=63842733

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710220269.4A Active CN108694177B (en) 2017-04-06 2017-04-06 Knowledge graph construction method and system

Country Status (1)

Country Link
CN (1) CN108694177B (en)

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN109947952A (en) * 2019-03-20 2019-06-28 武汉市软迅科技有限公司 Search method, device, equipment and storage medium based on english knowledge map
CN109977419A (en) * 2019-04-09 2019-07-05 福建奇点时空数字科技有限公司 A kind of knowledge mapping building system
CN109977291A (en) * 2019-03-20 2019-07-05 武汉市软迅科技有限公司 Search method, device, equipment and storage medium based on physical knowledge map
CN110119814A (en) * 2019-04-29 2019-08-13 武汉开目信息技术股份有限公司 Knowledge rule modeling and inference method based on object relationship chain
CN110489561A (en) * 2019-07-12 2019-11-22 平安科技(深圳)有限公司 Knowledge mapping construction method, device, computer equipment and storage medium
CN110543574A (en) * 2019-08-30 2019-12-06 北京百度网讯科技有限公司 knowledge graph construction method, device, equipment and medium
CN110674360A (en) * 2019-09-27 2020-01-10 厦门美亚亿安信息科技有限公司 Method and system for constructing data association graph and tracing data
CN110929037A (en) * 2019-09-29 2020-03-27 珠海格力电器股份有限公司 Knowledge graph construction method and device, terminal and storage medium
CN110955764A (en) * 2019-11-19 2020-04-03 百度在线网络技术(北京)有限公司 Scene knowledge graph generation method, man-machine conversation method and related equipment
CN111104505A (en) * 2019-12-30 2020-05-05 浙江阿尔法人力资源有限公司 Information prompting method, device, equipment and storage medium
CN111159431A (en) * 2019-12-30 2020-05-15 深圳Tcl新技术有限公司 Knowledge graph-based information visualization method, device, equipment and storage medium
CN113051374A (en) * 2021-06-02 2021-06-29 北京沃丰时代数据科技有限公司 Text matching optimization method and device
CN113569051A (en) * 2020-04-29 2021-10-29 北京金山数字娱乐科技有限公司 Knowledge graph construction method and device
CN114579765A (en) * 2022-03-07 2022-06-03 四川大学 Network shooting range weapon base construction method based on open source information analysis
CN117408338A (en) * 2023-12-14 2024-01-16 神州医疗科技股份有限公司 Method and system for constructing knowledge graph of traditional Chinese medicine decoction pieces based on Chinese pharmacopoeia

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070208693A1 (en) * 2006-03-03 2007-09-06 Walter Chang System and method of efficiently representing and searching directed acyclic graph structures in databases
US20130096944A1 (en) * 2011-10-13 2013-04-18 The Board of Trustees of the Leland Stanford, Junior, University Method and System for Ontology Based Analytics
CN103488724A (en) * 2013-09-16 2014-01-01 复旦大学 Book-oriented reading field knowledge map construction method
CN103699663A (en) * 2013-12-27 2014-04-02 中国科学院自动化研究所 Hot event mining method based on large-scale knowledge base
CN103886046A (en) * 2014-03-11 2014-06-25 中国信息安全测评中心 Automatic semanteme extraction method for Web data exchange
CN105893551A (en) * 2016-03-31 2016-08-24 上海智臻智能网络科技股份有限公司 Method and device for processing data and knowledge graph
CN106095858A (en) * 2016-06-02 2016-11-09 海信集团有限公司 A kind of audio video searching method, device and terminal
CN106250412A (en) * 2016-07-22 2016-12-21 浙江大学 The knowledge mapping construction method merged based on many source entities

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070208693A1 (en) * 2006-03-03 2007-09-06 Walter Chang System and method of efficiently representing and searching directed acyclic graph structures in databases
US20130096944A1 (en) * 2011-10-13 2013-04-18 The Board of Trustees of the Leland Stanford, Junior, University Method and System for Ontology Based Analytics
CN103488724A (en) * 2013-09-16 2014-01-01 复旦大学 Book-oriented reading field knowledge map construction method
CN103699663A (en) * 2013-12-27 2014-04-02 中国科学院自动化研究所 Hot event mining method based on large-scale knowledge base
CN103886046A (en) * 2014-03-11 2014-06-25 中国信息安全测评中心 Automatic semanteme extraction method for Web data exchange
CN105893551A (en) * 2016-03-31 2016-08-24 上海智臻智能网络科技股份有限公司 Method and device for processing data and knowledge graph
CN106095858A (en) * 2016-06-02 2016-11-09 海信集团有限公司 A kind of audio video searching method, device and terminal
CN106250412A (en) * 2016-07-22 2016-12-21 浙江大学 The knowledge mapping construction method merged based on many source entities

Non-Patent Citations (9)

* Cited by examiner, † Cited by third party
Title
JIANDONG LI 等: "A Rule-Based Knowledge Discovery Engine Embedded Semantic Graph Knowledge Repository for Retail Business", 《ADVANCED CLOUD AND BIG DATA》 *
吴运兵 等: "知识图谱学习和推理研究进展", 《小型微型计算机系统》 *
周宇 等: "面向关联数据的高校机构知识库构建方法研究", 《图书情报工作》 *
张德政 等: "基于本体的中医知识图谱构建", 《情报工程》 *
朱游娟: "初中数学问题的全知识图谱设计与实现", 《中国优秀硕士学位论文全文数据库 社会科学Ⅱ辑》 *
熊晶 等: "甲骨文知识图谱构建中的实体关系发现研究", 《计算机工程与科学》 *
王巍巍 等: "双语影视知识图谱的构建研究", 《北京大学学报(自然科学版》 *
胡芳槐: "基于多种数据源的中文知识图谱构建方法研究", 《中国博士学位论文全文数据库 信息科技辑》 *
黄小燕: "基于潜在语义关系的更年期综合症知识图库的构建及其应用研究", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》 *

Cited By (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN109947952A (en) * 2019-03-20 2019-06-28 武汉市软迅科技有限公司 Search method, device, equipment and storage medium based on english knowledge map
CN109977291A (en) * 2019-03-20 2019-07-05 武汉市软迅科技有限公司 Search method, device, equipment and storage medium based on physical knowledge map
CN109977419A (en) * 2019-04-09 2019-07-05 福建奇点时空数字科技有限公司 A kind of knowledge mapping building system
CN109977419B (en) * 2019-04-09 2023-04-07 厦门美域中央信息科技有限公司 Knowledge graph construction system
CN110119814B (en) * 2019-04-29 2022-04-29 武汉开目信息技术股份有限公司 Knowledge rule modeling and reasoning method based on object relation chain
CN110119814A (en) * 2019-04-29 2019-08-13 武汉开目信息技术股份有限公司 Knowledge rule modeling and inference method based on object relationship chain
CN110489561A (en) * 2019-07-12 2019-11-22 平安科技(深圳)有限公司 Knowledge mapping construction method, device, computer equipment and storage medium
CN110543574B (en) * 2019-08-30 2022-05-17 北京百度网讯科技有限公司 Knowledge graph construction method, device, equipment and medium
CN110543574A (en) * 2019-08-30 2019-12-06 北京百度网讯科技有限公司 knowledge graph construction method, device, equipment and medium
CN110674360A (en) * 2019-09-27 2020-01-10 厦门美亚亿安信息科技有限公司 Method and system for constructing data association graph and tracing data
CN110929037A (en) * 2019-09-29 2020-03-27 珠海格力电器股份有限公司 Knowledge graph construction method and device, terminal and storage medium
CN110955764A (en) * 2019-11-19 2020-04-03 百度在线网络技术(北京)有限公司 Scene knowledge graph generation method, man-machine conversation method and related equipment
CN111104505A (en) * 2019-12-30 2020-05-05 浙江阿尔法人力资源有限公司 Information prompting method, device, equipment and storage medium
CN111159431A (en) * 2019-12-30 2020-05-15 深圳Tcl新技术有限公司 Knowledge graph-based information visualization method, device, equipment and storage medium
CN111104505B (en) * 2019-12-30 2023-08-25 浙江阿尔法人力资源有限公司 Information prompting method, device, equipment and storage medium
CN113569051A (en) * 2020-04-29 2021-10-29 北京金山数字娱乐科技有限公司 Knowledge graph construction method and device
CN113051374A (en) * 2021-06-02 2021-06-29 北京沃丰时代数据科技有限公司 Text matching optimization method and device
CN114579765B (en) * 2022-03-07 2023-08-15 四川大学 Network shooting range weapon library construction method based on open source information analysis
CN114579765A (en) * 2022-03-07 2022-06-03 四川大学 Network shooting range weapon base construction method based on open source information analysis
CN117408338A (en) * 2023-12-14 2024-01-16 神州医疗科技股份有限公司 Method and system for constructing knowledge graph of traditional Chinese medicine decoction pieces based on Chinese pharmacopoeia
CN117408338B (en) * 2023-12-14 2024-03-12 神州医疗科技股份有限公司 Method and system for constructing knowledge graph of traditional Chinese medicine decoction pieces based on Chinese pharmacopoeia

Also Published As

Publication number Publication date
CN108694177B (en) 2022-02-18

Similar Documents

Publication Publication Date Title
CN108694177A (en) Knowledge mapping construction method and system
Berman Principles of big data: preparing, sharing, and analyzing complex information
Pedersen et al. DanNet: the challenge of compiling a wordnet for Danish by reusing a monolingual dictionary
CA2747669C (en) Method and system for validation of claims against policy with contextualized semantic interoperability
JP6413256B2 (en) CONFERENCE SUPPORT DEVICE, CONFERENCE SUPPORT DEVICE CONTROL METHOD, AND PROGRAM
US20140280314A1 (en) Dimensional Articulation and Cognium Organization for Information Retrieval Systems
Ulrich et al. Metadata repository for improved data sharing and reuse based on HL7 FHIR.
EP2191399A1 (en) System and method for analyzing electronic data records
JP2008276550A (en) Document retrieval system and document retrieval method
CN103544321A (en) Data processing method and device for micro-blog emotion information
CN110189802A (en) Biaxial stress structure cohort study information system based on index storage model
Kim et al. Toward harmonising WHO International Classifications: a nursing perspective
KR20170052020A (en) Providing system for classification of diseases using questions and answer
Abdollahpour et al. Embodiment of rhetorical moves in lexical bundles in abstracts of the medical sciences
CN109299238B (en) Data query method and device
Gašpar et al. Measuring Terminology Consistency in Translated Corpora: Implementation of the Herfindahl-Hirshman Index
Burrows The History and Provenance of Manuscripts in the Collection of Sir Thomas Phillipps: New Approaches to Digital Representation
Richesson et al. Heterogeneous but “standard” coding systems for adverse events: Issues in achieving interoperability between apples and oranges
CN112349367A (en) Method and device for generating simulation medical record, electronic equipment and storage medium
Hakim et al. Corpus development for indonesian consumer-health question answering system
Afzaal et al. Syntactic complexity in translated eHealth discourse of COVID-19: A comparable parallel corpus approach
Darmody et al. An introduction to computerised analysis of qualitative data
Houssein et al. Semantic protocol and resource description framework query language: a comprehensive review
TWI281111B (en) System and method for identifying corresponding translation
WO2022079593A1 (en) A system and a way to automatically monitor clinical trials - virtual monitor (vm) and a way to record medical history

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
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20230609

Address after: 3007, Hengqin international financial center building, No. 58, Huajin street, Hengqin new area, Zhuhai, Guangdong 519031

Patentee after: New founder holdings development Co.,Ltd.

Patentee after: BEIJING FOUNDER ELECTRONICS Co.,Ltd.

Address before: 100871, Beijing, Haidian District, Cheng Fu Road, No. 298, Zhongguancun Fangzheng building, 9 floor

Patentee before: PEKING UNIVERSITY FOUNDER GROUP Co.,Ltd.

Patentee before: BEIJING FOUNDER ELECTRONICS Co.,Ltd.