CN106156365A - A kind of generation method and device of knowledge mapping - Google Patents
A kind of generation method and device of knowledge mapping Download PDFInfo
- Publication number
- CN106156365A CN106156365A CN201610628591.6A CN201610628591A CN106156365A CN 106156365 A CN106156365 A CN 106156365A CN 201610628591 A CN201610628591 A CN 201610628591A CN 106156365 A CN106156365 A CN 106156365A
- Authority
- CN
- China
- Prior art keywords
- data
- text data
- knowledge
- knowledge mapping
- urtext
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/253—Grammatical analysis; Style critique
-
- 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
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Machine Translation (AREA)
Abstract
The invention provides the generation method and device of a kind of knowledge mapping, the method includes: the urtext data of designated field are carried out morphology, grammer and/or semantic analysis, obtains standardized text data；Extracting factural information from described standardized text data, described factural information includes following element: the relation between relation and entity and attribute between entity, attribute, entity；Use the default form of expression that described factural information is carried out structured representation, obtain the structural data pair of described factural information；Utilize described structural data to as knowledge entry, build knowledge mapping.The generation method of knowledge mapping that the present invention proposes, it is possible to construct and there is knowledge mapping targetedly, meet designated field, such as child field, intelligent interaction demand, promote the interactive experience of different demand user.
Description
Technical field
The present invention relates to field of computer technology, particularly relate to a kind of knowledge mapping for child field intelligent interaction
Generate method and device.
Background technology
Child is the crowd being easiest to Intelligent hardware in the market accept, and it is intelligent is mainly reflected in interactive intelligence
On, but little with research for childrenese and knowledge processing.The mode of common interactive dialogue majority retrieval, structure one is asked
One corpus answered, calculates customer problem and the similarity of language material problem, and then provides corresponding reply, and this shallow-layer that belongs to is handed over
Mutually.
The degree of depth needs to build knowledge mapping to carry out knowledge excavation and reasoning alternately.Knowledge mapping, refers to entity, concept
As node, using semantic relation as the semantic network on limit.Knowledge mapping makes knowledge acquisition more direct, therefore, it is possible to for reading
The knowledge of semantic association is provided, thus realizes facilitation, intellectuality and the hommization read.
In realizing process of the present invention, inventor finds at least to there is problems in that in prior art existing knowledge graph
Spectrum majority is all pervasive purpose, and lacking of property is insufficient for the intelligent interaction demand in child field.
Summary of the invention
In view of the above problems, the embodiment of the present invention proposes the generation method and device of a kind of knowledge mapping, in order to solve
Existing lacking of property of knowledge mapping, is insufficient for designated field, such as child field, the problem of intelligent interaction demand.
According to an aspect of the invention, it is provided a kind of generation method of knowledge mapping, the method includes:
The urtext data of designated field are carried out morphology, grammer and/or semantic analysis, obtains standardized text number
According to；
Extracting factural information from described standardized text data, described factural information includes following element: entity, genus
The relation between relation and entity and attribute between property, entity；
Use the default form of expression that described factural information is carried out structured representation, obtain the structuring of described factural information
Data pair；
Utilize described structural data to as knowledge entry, build knowledge mapping.
Alternatively, described method also includes:
The urtext of designated field is obtained from resource website, audio resource, video resource and/or third-party server
Data.
Alternatively, described urtext data are carried out morphology, grammer and/or semantic analysis, obtain standardized text number
According to, including:
File structure according to described urtext data carries out paragraph structure division；
The each paragraph structure marked off is carried out morphology, grammer and/or semantic analysis, obtains standardized text data.
Alternatively, the described file structure according to described urtext data carries out paragraph structure division, including:
The file structure of described urtext data is determined, according to described file structure pair according to file structure distribution characteristics
Described urtext data carry out paragraph structure division, or
The paragraph sorter model using training in advance carries out file structure classification to the paragraph of described urtext data,
According to classification results, described urtext data are carried out paragraph structure division.
Alternatively, described each paragraph structure to marking off carries out morphology, grammer and/or semantic analysis, including:
If described urtext data are Chinese resource, each paragraph structure marked off is carried out participle, part-of-speech tagging
And phrase chunking, and remove the punctuation mark in paragraph structure；
If described urtext data are foreign language resource, each paragraph structure marked off is carried out stem process, morphology
Reduction and phrase chunking, and remove the punctuation mark in paragraph structure.
Alternatively, described extraction factural information from described standardized text data, including:
Described standardized text data are carried out Knowledge Extraction, obtain noun present in described standardized text data,
And the relation between each noun；
The result obtaining Knowledge Extraction carries out the identification of factural information, obtains described factural information.
Alternatively, described described standardized text data are carried out Knowledge Extraction, including:
Architectural feature according to noun of all categories extract from described standardized text data the noun of respective classes with
And the relation between each noun, or
Word in described standardized text data is classified by the noun classification device model using training in advance, according to
Classification results identification also extracts the relation between noun of all categories and each noun.
Alternatively, described method also includes:
Use relational database mode that the knowledge mapping built is stored, or
Use Hash table mode that the knowledge mapping built is stored, or
Use indexed mode that the knowledge mapping built is stored.
Alternatively, described method also includes:
Knowledge mapping according to building carries out man-machine interaction.
According to another aspect of the present invention, it is provided that the generating means of a kind of knowledge mapping, this system includes:
Pretreatment unit, for the urtext data of designated field are carried out morphology, grammer and/or semantic analysis,
To standardized text data；
Information extracting unit, for extracting factural information from described standardized text data, described factural information includes
Following element: the relation between relation and entity and attribute between entity, attribute, entity；
Information presentation unit, is used for using the default form of expression that described factural information is carried out structured representation, obtains institute
State the structural data pair of factural information；
Construction unit, is used for utilizing described structural data to as knowledge entry, builds knowledge mapping.
Alternatively, described device also includes:
Acquiring unit, specifies for obtaining from resource website, audio resource, video resource and/or third-party server
The urtext data in field.
Alternatively, described pretreatment unit, including:
First processing module, for carrying out paragraph structure division according to the file structure of described urtext data；
Second processing module, for each paragraph structure marked off is carried out morphology, grammer and/or semantic analysis, obtains
Standardized text data.
Alternatively, described information extracting unit, including:
Abstraction module, for described standardized text data are carried out Knowledge Extraction, obtains described standardized text data
Present in relation between noun, and each noun；
Identification module, the result for obtaining Knowledge Extraction carries out the identification of factural information, obtains described factural information.
Alternatively, described device also includes:
Memory element, for using relational database mode that the knowledge mapping built is stored, or, use Hash table
The knowledge mapping built is stored by mode, or, use indexed mode that the knowledge mapping built is stored.
Alternatively, described device also includes:
Interactive unit, for carrying out man-machine interaction according to the knowledge mapping built.
The generation method and device of the knowledge mapping that the present invention provides, by extracting thing from the text data of designated field
Real information, is indicated factural information with the default form of expression, and uses the structuring being indicated with the default form of expression
Data to as knowledge entry, build knowledge mapping, and then can construct and have knowledge mapping targetedly, meet and specify neck
Territory, such as child field, intelligent interaction demand, promote the interactive experience of different demand user.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of description, and in order to allow above and other objects of the present invention, the feature and advantage can
Become apparent, below especially exemplified by the detailed description of the invention of the present invention.
Accompanying drawing explanation
By reading the detailed description of hereafter preferred implementation, various other advantage and benefit common for this area
Technical staff will be clear from understanding.Accompanying drawing is only used for illustrating the purpose of preferred implementation, and is not considered as the present invention
Restriction.And in whole accompanying drawing, it is denoted by the same reference numerals identical parts.In the accompanying drawings:
Fig. 1 is the flow chart of the generation method of a kind of knowledge mapping that the embodiment of the present invention proposes；
Fig. 2 is the flow chart of the generation method of a kind of knowledge mapping that another embodiment of the present invention proposes；
Fig. 3 be a kind of knowledge mapping that the embodiment of the present invention proposes generation method in the segmentation flow chart of step S11；
Fig. 4 be a kind of knowledge mapping that the embodiment of the present invention proposes generation method in the segmentation flow chart of step S12；
Fig. 5 is the structured flowchart of the generating means of a kind of knowledge mapping that the embodiment of the present invention proposes；
Fig. 6 is the structured flowchart of the generating means of a kind of knowledge mapping that another embodiment of the present invention proposes.
Detailed description of the invention
Embodiments of the invention are described below in detail, and the example of described embodiment is shown in the drawings, the most from start to finish
Same or similar label represents same or similar element or has the element of same or like function.Below with reference to attached
The embodiment that figure describes is exemplary, is only used for explaining the present invention, and is not construed as limiting the claims.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singulative used herein " ", "
Individual ", " described " and " being somebody's turn to do " may also comprise plural form.It is to be further understood that use in the description of the present invention arranges
Diction " including " refers to there is described feature, integer, step, operation, element and/or assembly, but it is not excluded that existence or adds
Other features one or more, integer, step, operation, element, assembly and/or their group.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, and all terms used herein (include technology art
Language and scientific terminology), have with the those of ordinary skill in art of the present invention be commonly understood by identical meaning.Also should
Be understood by, those terms defined in such as general dictionary, it should be understood that have with in the context of prior art
The meaning that meaning is consistent, and unless by specific definitions, otherwise will not explain by idealization or the most formal implication.
Fig. 1 shows the flow chart of the generation method of a kind of knowledge mapping of the embodiment of the present invention.With reference to Fig. 1, the present invention
The generation method of knowledge mapping that embodiment proposes specifically includes following steps:
S11, urtext data to designated field carry out morphology, grammer and/or semantic analysis, obtain standardized text
Data.
Wherein, it is intended that field refers to the field of currently practical application scenarios, such as the child field mutual for child intelligence,
Specifically can be determined according to reality application.Morphology, grammer and/or semantic analysis refer to the urtext data to designated field
The operations such as structuring process and word segmentation processing are carried out based on morphology, grammer and/or semantic analysis.
S12, extracting factural information from described standardized text data, described factural information includes following element: entity,
The relation between relation and entity and attribute between attribute, entity.
In the present embodiment, entity refers to name entity word and event name etc.；Attribute refers to the noun naming entity to modify, as
Age, sex, character relation etc..Wherein, the relation of entity attribute, mainly by the probability of calculating co-occurrence, extracts what entity had,
The attribute word of maximum probability.Relation between entity, on the one hand according to the co-occurrence probabilities in sentence, on the other hand according to identification
The entity attribute relation gone out extracts entity relationship.
S13, employing are preset the form of expression and described factural information are carried out structured representation, obtain the knot of described factural information
Structure data pair.
In the present embodiment, the manifestation mode of N tuple can be used to realize described factural information is carried out structured representation, obtain
The structural data pair of described factural information.
In a concrete example, illustrate as a example by tlv triple.Concrete, according to the result of knowledge excavation, identify
Output entity and attribute, and the relation of entity attribute, construct tlv triple.Each factural information can be expressed as (entity,
Attribute, relation).
S14, utilize described structural data to as knowledge entry, build knowledge mapping.
The generation method of the knowledge mapping that the embodiment of the present invention provides, by extracting thing from the text data of designated field
Real information, is indicated factural information with the default form of expression, and uses the structuring being indicated with the default form of expression
Data to as knowledge entry, build knowledge mapping, and then can construct and have knowledge mapping targetedly, meet and specify neck
Territory, such as child field, intelligent interaction demand, promote the interactive experience of different demand user.
In an alternate embodiment of the present invention where, as in figure 2 it is shown, before step S11, described method also includes following
Step:
S10, from resource website, audio resource, video resource and/or third-party server, obtain the original of designated field
Text data.
In the embodiment of the present invention, also included before step S11 from resource website, audio resource, video resource and/or
Tripartite's server obtains the step of the urtext data of designated field, the one or many in the concrete in the following manner of this step
Kind:
(1) from resource website, the urtext data of designated field, are obtained by webpage capture method.Apply in reality
In, can use web crawlers technology that webpage is captured, to obtain the urtext data of designated field from resource website；
And/or, use network packet capturing technology webpage to be captured, to obtain the urtext number of designated field from resource website
According to.
Wherein, packet capturing refer to send network transmission carry out intercepting and capturing with the packet received, retransmit, edit, unloading etc.
Operation, network packet capturing technology can be by intercepting and capturing network data.
Web crawlers is a program automatically extracting webpage, is the important component part of search engine.Exemplary, with
As a example by using web crawlers technology to carry out webpage capture, network captures process and includes: first selected seed URL
URL, puts into URL queue to be captured by these seeds URL；From URL array to be captured, take out URL to be captured, resolve and wait to grab
Take the domain name system DNS of URL, check the webpage corresponding with URL to be captured, and the URL that these corresponding webpages have been checked is put into
Capture URL queue；Analyze and captured the URL in URL queue, analyze other URL wherein comprised, and other URL are put into
URL queue to be captured, circulates hence into the next one.During it should be noted that webpage is captured by the embodiment of the present invention
Above-mentioned any one or more crawl strategy can be used to capture, the invention is not limited in this regard.
(2) from voice resource, the urtext data of designated field, are obtained by contents extraction audio recognition method.Tool
Body, voice resource can be changed into text by speech recognition technology, obtains urtext data.
(3) from video resource, the urtext data of designated field, are obtained by image-recognizing method.Concrete, depending on
Frequently the caption information in video resource can be extracted and converted to text by image recognition technology by resource, obtains urtext
Data.
(4) the urtext data of designated field, are obtained by third-party server.Concrete, can by with third party
Mechanism carries out cooperative resource, obtains the new content resources such as writer child from the server of the third-party institution.
It should be noted that the mode of the urtext data obtaining designated field provided in the embodiment of the present invention, only
For illustrating, those skilled in the art can select above-mentioned any one or more mode to carry out according to practical application request
The acquisition of urtext data, the invention is not limited in this regard.
In an alternate embodiment of the present invention where, as it is shown on figure 3, step S11 in above-described embodiment farther includes
Following steps:
S111, file structure according to described urtext data carry out paragraph structure division.
Wherein, the file structure according to described urtext data in described step S111 carries out paragraph structure division,
Specifically include: determine the file structure of described urtext data according to file structure distribution characteristics, according to described file structure
Described urtext data are carried out paragraph structure division, or uses the paragraph sorter model of training in advance to described original literary composition
The paragraph of notebook data carries out file structure classification, according to classification results, described urtext data is carried out paragraph structure division.
Divide, in the embodiment of the present invention, by by former to realize the paragraph structure of urtext data quickly and accurately
Beginning text data carries out structuring, distinguishes the paragraphs such as title, text, author, time, classification, it is achieved urtext data
Paragraph structure divides.Concrete.Concrete, can be according to file structure distribution characteristics, such as: in the position of text, length, word
The aspect features such as appearance, determine the file structure of described urtext data.Or a little corpus of artificial mark, according to above-mentioned spy
Levy structure paragraph sorter model paragraph is classified, predict the outcome as paragraph properties using classification.
S112, each paragraph structure marked off is carried out morphology, grammer and/or semantic analysis, obtain standardized text number
According to.
Wherein, described step S112 carries out morphology, grammer and/or semantic analysis to each paragraph structure marked off,
Specifically include: if described urtext data are for Chinese resource, each paragraph structure marked off is carried out participle, part-of-speech tagging
And phrase chunking, and remove the punctuation mark in paragraph structure；If described urtext data are foreign language resource, to division
The each paragraph structure gone out carries out stem process, lemmatization and phrase chunking, and removes the punctuation mark in paragraph structure.
Divide to realize the paragraph structure of urtext data quickly and accurately, the embodiment of the present invention, former by judging
The language of beginning text data, if urtext data are Chinese resource, then carries out Chinese word segmentation, part of speech mark to Chinese resource
Note, phrase chunking etc..Concrete available Open-Source Tools carries out morphology, grammer and/or semantic analysis to Chinese.If described textual data
According to during for foreign language resource, according to corresponding language tool, Chinese resource is carried out morphology, grammer and/or semantic analysis, such as, to English
Language resource carries out stem process, lemmatization, phrase chunking etc., refers to remove tense, word suffix and be reduced into former word.The most also
With Open-Source Tools, English resources can be carried out morphology, grammer and/or semantic analysis.
In an alternate embodiment of the present invention where, as shown in Figure 4, in above-described embodiment step S12 from described standard
Change and text data extracts factural information, further include steps of
S121, described standardized text data are carried out Knowledge Extraction, obtain present in described standardized text data
Relation between noun, and each noun.
Wherein, described step S121 carries out Knowledge Extraction to described standardized text data, specifically include: according to respectively
The architectural feature of the noun of classification extracts between noun and each noun of respective classes from described standardized text data
Relation, or use the noun classification device model of training in advance that the word in described standardized text data is classified, according to
Classification results identification also extracts the relation between noun of all categories and each noun.Concrete, the relation between noun can root
Determine according to the co-occurrence probabilities in sentence.
S122, the result obtaining Knowledge Extraction carry out the identification of factural information, obtain described factural information.
In order to realize the Knowledge Extraction of standardized text data quickly and accurately, the embodiment of the present invention, by having counted
According to observation, noun is started word, the feature such as word, word length that terminates determines the architectural feature of noun of all categories, and according to
The architectural feature of noun of all categories extracts the pass between noun and each noun of respective classes from standardized text data
System, and then obtain factural information.
Illustrated in greater detail is carried out below as a example by name:
First, extract surname word, can extract according to One Hundred Family Names or from existing name.
Add up the word probability often occurred in name again, as word n times occurs altogether at text, occur M time in name, then word is permissible
Probability as name is M/N；
Finally judge ending, be typically based on length and word probability, probability is similar with second step, calculating word in the middle of name,
The probability that ending occurs, adds that the restriction (general 2-4 the word of Chinese personal name) of length i.e. may recognize that name.
Additionally, in another embodiment of the invention, it is also possible to method based on statistical model realizes, specific as follows:
First, structure mark language material.To pretreated text data, the name in mark sentence；
Secondly, the architectural feature of noun of all categories is extracted.Available feature include part of speech, word length, lexeme put, previous
Individual word, front word part of speech, later word, rear word part of speech etc..
Finally, model and predict.Such as, based on the language material marked and the tag file extracted, statistical model is trained.
The model that trained is loaded, to standardized text data prediction the noun that identifies respective classes during prediction.
In an alternate embodiment of the present invention where, described method is further comprising the steps of: use relational database mode
The knowledge mapping built is stored, or uses Hash table mode that the knowledge mapping built is stored, or use index
The knowledge mapping built is stored by mode.
Knowledge store is for follow-up knowledge application, needs the aspects such as consideration inquiry property, search efficiency, space hold
Factor.The storage of knowledge mapping in the present invention, as a example by three kinds of storage methods, is explained by the embodiment of the present invention, tool
Body is as follows:
Use relational database mode that the knowledge mapping built is stored.This storage mode is to structural data pair
(entity, attribute, relation) design database table, completes knowledge store and inquiry according to table key assignments.
Use Hash table mode that the knowledge mapping built is stored.This storage mode is by knowledge agent (structuring number
Entity according to centering) as key, remaining is as value, structure hash table storage.
Use indexed mode that the knowledge mapping built is stored, knowledge (structural data to) done full-text index,
Structure forward index and inverted index complete storage and inquiry.
Implementing of the present invention is optional, described method is further comprising the steps of: according to the knowledge mapping built
Carry out man-machine interaction.
The application process of knowledge mapping is varied, is usually according to the knowledge excavated, and storage format and issuer
Method, completes the process of knowledge reasoning, man-machine interaction.During application, need the information such as the entity in identification problem sentence, attribute, and
It is converted into the grammer of knowledge query, finally provides the reasoning results according to the relation in collection of illustrative plates.
It should be noted that above-mentioned any one can be used when knowledge mapping is stored by the embodiment of the present invention to deposit
Storage mode realizes, the invention is not limited in this regard.
Below with the Snow White's children's story in child field as specific embodiment, technical solution of the present invention is carried out in detail
Thin explanation.
One, first the children's story text got is done pretreatment, obtain standardized text data.
Two, according to the result of pretreatment, the Knowledge Extraction i.e. extraction of factural information is carried out to doing standardized text data.
Extraction content includes the personage in story, such as Snow White, Seven Dwarfs, queen, prince etc.；Event, such as emperor
After ask witch mirror, Snow White eat poison Fructus Mali pumilae, Snow White is rescued.
Three, knowledge mapping builds
The fact that Knowledge Extraction information is preserved with the form of structural data pair, utilizes described structural data pair
As knowledge entry, build knowledge mapping, and the knowledge mapping obtained is stored.
Factural information includes personage, place, time etc..The tlv triple of representation, such as event represents:
(Snow White is rescued, and sues and labours, Seven Dwarfs)；
(Snow White is rescued, and is rescued, Snow White)；
(Snow White is rescued, place, forest log cabin)；
Four, knowledge mapping application
Child asks: who has rescued Snow White？
First, carry out proper name identification, identify name: Snow White, event: rescued.Target is to ask the people that sues and labours.
Further according to recognition result, inquiry knowledge store finds (Snow White is rescued, and sues and labours, Seven Dwarfs).
Provide the artificial Seven Dwarfs that sue and labour.
Ultimately producing reply, Seven Dwarfs have rescued Snow White, finishing man-machine interaction.
For embodiment of the method, in order to be briefly described, therefore it is all expressed as a series of combination of actions, but this area
Technical staff should know, the embodiment of the present invention is not limited by described sequence of movement, because implementing according to the present invention
Example, some step can use other orders or carry out simultaneously.Secondly, those skilled in the art also should know, description
Described in embodiment belong to preferred embodiment, necessary to the involved action not necessarily embodiment of the present invention.
Fig. 5 diagrammatically illustrates the structured flowchart of the generating means of the knowledge mapping of one embodiment of the invention.With reference to figure
5, the generating means of the knowledge mapping of the embodiment of the present invention specifically includes pretreatment unit 501, information extracting unit 502, information
Represent unit 503 and construction unit 504, wherein: pretreatment unit 501, for the urtext data of designated field are entered
Row morphology, grammer and/or semantic analysis, obtain standardized text data；Information extracting unit 502, for from described standardization
Extracting factural information in text data, described factural information includes following element: relation between entity, attribute, entity and
Relation between entity and attribute；Information presentation unit 503, is used for using the default form of expression to tie described factural information
Structure represents, obtains the structural data pair of described factural information；Construction unit 504, is used for utilizing described structural data pair
As knowledge entry, build knowledge mapping.
The generating means of the knowledge mapping that the embodiment of the present invention provides, information extracting unit 502 is by from through pretreatment
Extracting factural information in the text data of the designated field after unit 501 process, information presentation unit 503 is with the default form of expression
Factural information is indicated, uses the structural data being indicated with the default form of expression to work for construction unit 504
For knowledge entry, build knowledge mapping, and then can construct there is knowledge mapping targetedly, meet designated field, such as youngster
Virgin field, intelligent interaction demand, promote the interactive experience of different demand user.
In an alternate embodiment of the present invention where, as shown in Figure 6, described device also includes acquiring unit 500, described in obtain
Take unit 500, for obtaining the former of designated field from resource website, audio resource, video resource and/or third-party server
Beginning text data.
Concrete, described acquiring unit 500 can obtain the urtext number of designated field by least one mode following
According to:
From resource website, the urtext data of designated field are obtained by webpage capture method；
From voice resource, the urtext data of designated field are obtained by contents extraction audio recognition method；
From video resource, the urtext data of designated field are obtained by image-recognizing method；
The urtext data of designated field are obtained by third-party server.
In an alternate embodiment of the present invention where, described pretreatment unit 501, at the first processing module and second
Reason module, wherein: the first processing module, for carrying out paragraph structure division according to the file structure of described urtext data；
Second processing module, for each paragraph structure marked off is carried out morphology, grammer and/or semantic analysis, obtains standardization literary composition
Notebook data.
Wherein, the first processing module, specifically for determining described urtext data according to file structure distribution characteristics
Described urtext data are carried out paragraph structure division according to described file structure, or use training in advance by file structure
Paragraph sorter model carries out file structure classification to the paragraph of described urtext data, according to classification results to described original
Text data carries out paragraph structure division.
Dividing to realize the paragraph structure of urtext data quickly and accurately, in the embodiment of the present invention, first processes
Module, by urtext data are carried out structuring, distinguishes the paragraphs such as title, text, author, time, classification, it is achieved former
The paragraph structure of beginning text data divides.Concrete.Concrete, can be according to file structure distribution characteristics, such as: the position of text
Put, the aspect feature such as length, word content, determine the file structure of described urtext data.Or the manually a little training of mark
Language material, builds paragraph sorter model according to features described above and classifies paragraph, predict the outcome as paragraph properties using classification.
Wherein, the second processing module, if be Chinese resource specifically for described urtext data, each to mark off
Paragraph structure carries out participle, part-of-speech tagging and phrase chunking, and removes the punctuation mark in paragraph structure；If described original literary composition
When notebook data is foreign language resource, each paragraph structure marked off is carried out stem process, lemmatization and phrase chunking, and goes
Except the punctuation mark in paragraph structure.
Dividing to realize the paragraph structure of urtext data quickly and accurately, the embodiment of the present invention, second processes mould
Block is by judging the language of urtext data, if urtext data are Chinese resource, then Chinese resource is carried out Chinese
Participle, part-of-speech tagging, phrase chunking etc..Concrete available Open-Source Tools carries out morphology, grammer and/or semantic analysis to Chinese.
If described text data is foreign language resource, according to corresponding language tool, Chinese resource is carried out morphology, grammer and/or semanteme point
Analysis, such as, carries out stem process, lemmatization, phrase chunking etc. to English resources, refers to remove tense, word suffix and be reduced into
Former word.Concrete can also carry out morphology, grammer and/or semantic analysis with Open-Source Tools to English resources.
In an alternate embodiment of the present invention where, described information extracting unit 502, including abstraction module and identification mould
Block, wherein: abstraction module, for described standardized text data are carried out Knowledge Extraction, obtains described standardized text data
Present in relation between noun, and each noun；Identification module, the result for obtaining Knowledge Extraction carries out true letter
The identification of breath, obtains described factural information.
Wherein, abstraction module, specifically for the architectural feature according to noun of all categories from described standardized text data
Relation between noun and each noun of middle extraction respective classes, or use the noun classification device model of training in advance to described
Word in standardized text data is classified, according to classification results identification and extract noun of all categories and each noun it
Between relation.Concrete, the relation between noun can determine according to the co-occurrence probabilities in sentence.
In order to realize the Knowledge Extraction of standardized text data, the embodiment of the present invention, information extracting unit quickly and accurately
502 by the observation to data with existing, noun is started word, terminate the feature such as word, word length determine noun of all categories
Architectural feature, and according to the architectural feature of noun of all categories extract from standardized text data respective classes noun and
Relation between each noun, and then obtain factural information.
In an alternate embodiment of the present invention where, described device also includes the memory element not shown in accompanying drawing, and this is deposited
Storage unit, for using relational database mode that the knowledge mapping built is stored, or, use Hash table mode to structure
Knowledge mapping store, or, use indexed mode to build knowledge mapping store.
In an alternate embodiment of the present invention where, described device also includes the interactive unit not shown in accompanying drawing, this friendship
Unit mutually, for carrying out man-machine interaction according to the knowledge mapping built.
For device embodiment, due to itself and embodiment of the method basic simlarity, so describe is fairly simple, relevant
Part sees the part of embodiment of the method and illustrates.
In sum, the generation method and device of the knowledge mapping that the embodiment of the present invention provides, by from designated field
Text data extracts factural information, with the default form of expression, factural information is indicated, and uses with the default form of expression
The structural data being indicated to as knowledge entry, builds knowledge mapping, and then can construct to have and know targetedly
Know collection of illustrative plates, meet designated field, such as child field, intelligent interaction demand, promote the interactive experience of different demand user.
Through the above description of the embodiments, those skilled in the art is it can be understood that can lead to the present invention
Cross hardware to realize, it is also possible to the mode adding necessary general hardware platform by software realizes.Based on such understanding, this
Bright technical scheme can embody with the form of software product, and this software product can be stored in a non-volatile memories
Medium (can be CD-ROM, USB flash disk, portable hard drive etc.) in, including some instructions with so that a computer equipment (can be
Personal computer, server, or the network equipment etc.) perform the method described in each embodiment of the present invention.
It will be appreciated by those skilled in the art that accompanying drawing is the schematic diagram of a preferred embodiment, the module in accompanying drawing or stream
Journey is not necessarily implemented necessary to the present invention.
It will be appreciated by those skilled in the art that the module in the system in embodiment can describe according to embodiment to carry out point
It is distributed in the system of embodiment, it is also possible to carry out respective change and be disposed other than in one or more systems of the present embodiment.On
The module stating embodiment can merge into a module, it is also possible to is further split into multiple submodule.
The above is only the some embodiments of the present invention, it is noted that for the ordinary skill people of the art
For Yuan, under the premise without departing from the principles of the invention, it is also possible to make some improvements and modifications, these improvements and modifications also should
It is considered as protection scope of the present invention.
Claims (13)
1. the generation method of a knowledge mapping, it is characterised in that including:
The urtext data of designated field are carried out morphology, grammer and/or semantic analysis, obtains standardized text data；
Extracting factural information from described standardized text data, described factural information includes following element: entity, attribute, reality
The relation between relation and entity and attribute between body；
Use the default form of expression that described factural information is carried out structured representation, obtain the structural data of described factural information
Right；
Utilize described structural data to as knowledge entry, build knowledge mapping.
Method the most according to claim 1, it is characterised in that described method also includes:
The urtext number of designated field is obtained from resource website, audio resource, video resource and/or third-party server
According to.
Method the most according to claim 1 and 2, it is characterised in that described urtext data are carried out morphology, grammer
And/or semantic analysis, obtain standardized text data, including:
File structure according to described urtext data carries out paragraph structure division；
The each paragraph structure marked off is carried out morphology, grammer and/or semantic analysis, obtains standardized text data.
Method the most according to claim 3, it is characterised in that the described file structure according to described urtext data enters
Row paragraph structure divides, including:
The file structure of described urtext data is determined, according to described file structure to described according to file structure distribution characteristics
Urtext data carry out paragraph structure division, or
The paragraph sorter model using training in advance carries out file structure classification to the paragraph of described urtext data, according to
Classification results carries out paragraph structure division to described urtext data.
Method the most according to claim 3, it is characterised in that described each paragraph structure to marking off carries out morphology, language
Method and/or semantic analysis, including:
If described urtext data be Chinese resource, each paragraph structure marked off is carried out participle, part-of-speech tagging and
Phrase chunking, and remove the punctuation mark in paragraph structure；
If described urtext data are foreign language resource, each paragraph structure marked off is carried out stem process, lemmatization
And phrase chunking, and remove the punctuation mark in paragraph structure.
Method the most according to claim 1 and 2, it is characterised in that described extraction thing from described standardized text data
Real information, including:
Described standardized text data are carried out Knowledge Extraction, obtains noun present in described standardized text data, and
Relation between each noun；
The result obtaining Knowledge Extraction carries out the identification of factural information, obtains described factural information.
Method the most according to claim 6, it is characterised in that described described standardized text data are carried out knowledge take out
Take, including:
Architectural feature according to noun of all categories extracts the noun of respective classes and each from described standardized text data
Relation between noun, or
Word in described standardized text data is classified, according to classification by the noun classification device model using training in advance
Result identification also extracts the relation between noun of all categories and each noun.
Method the most according to claim 1, it is characterised in that described method also includes:
Use relational database mode that the knowledge mapping built is stored, or
Use Hash table mode that the knowledge mapping built is stored, or
Use indexed mode that the knowledge mapping built is stored.
9. the generating means of a knowledge mapping, it is characterised in that including:
Pretreatment unit, for the urtext data of designated field are carried out morphology, grammer and/or semantic analysis, is marked
Standardization text data；
Information extracting unit, for extracting factural information from described standardized text data, described factural information includes following
Element: the relation between relation and entity and attribute between entity, attribute, entity；
Information presentation unit, is used for using the default form of expression that described factural information is carried out structured representation, obtains described thing
The structural data pair of real information；
Construction unit, is used for utilizing described structural data to as knowledge entry, builds knowledge mapping.
Device the most according to claim 9, it is characterised in that described device also includes:
Acquiring unit, for obtaining designated field from resource website, audio resource, video resource and/or third-party server
Urtext data.
11. according to the device described in claim 9 or 10, it is characterised in that described pretreatment unit, including:
First processing module, for carrying out paragraph structure division according to the file structure of described urtext data；
Second processing module, for each paragraph structure marked off is carried out morphology, grammer and/or semantic analysis, obtains standard
Change text data.
12. according to the device described in claim 9 or 10, it is characterised in that described information extracting unit, including:
Abstraction module, for described standardized text data are carried out Knowledge Extraction, obtains depositing in described standardized text data
Noun, and the relation between each noun；
Identification module, the result for obtaining Knowledge Extraction carries out the identification of factural information, obtains described factural information.
13. devices according to claim 9, it is characterised in that described device also includes:
Memory element, for using relational database mode that the knowledge mapping built is stored, or, use Hash table mode
The knowledge mapping built is stored, or, use indexed mode that the knowledge mapping built is stored.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610628591.6A CN106156365B (en) | 2016-08-03 | 2016-08-03 | A kind of generation method and device of knowledge mapping |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610628591.6A CN106156365B (en) | 2016-08-03 | 2016-08-03 | A kind of generation method and device of knowledge mapping |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106156365A true CN106156365A (en) | 2016-11-23 |
| CN106156365B CN106156365B (en) | 2019-06-18 |
Family
ID=57328826
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610628591.6A Active CN106156365B (en) | 2016-08-03 | 2016-08-03 | A kind of generation method and device of knowledge mapping |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106156365B (en) |
Cited By (63)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106294321A (en) * | 2016-08-04 | 2017-01-04 | 北京智能管家科技有限公司 | The dialogue method for digging of a kind of specific area and device |
| CN106599091A (en) * | 2016-11-24 | 2017-04-26 | 上海交通大学 | Storage and indexing method of RDF graph structures stored based on key values |
| CN106777331A (en) * | 2017-01-11 | 2017-05-31 | 北京航空航天大学 | Knowledge mapping generation method and device |
| CN106776564A (en) * | 2016-12-21 | 2017-05-31 | 张永成 | The method for recognizing semantics and system of a kind of knowledge based collection of illustrative plates |
| CN106933804A (en) * | 2017-03-10 | 2017-07-07 | 上海数眼科技发展有限公司 | A kind of structured message abstracting method based on deep learning |
| CN106934042A (en) * | 2017-03-16 | 2017-07-07 | 中国人民解放军国防科学技术大学 | A kind of knowledge mapping represents model and its method |
| CN107016072A (en) * | 2017-03-23 | 2017-08-04 | 成都市公安科学技术研究所 | Knowledge-based inference system and method based on social networks knowledge mapping |
| CN107066621A (en) * | 2017-05-11 | 2017-08-18 | 腾讯科技（深圳）有限公司 | A kind of search method of similar video, device and storage medium |
| CN107122444A (en) * | 2017-04-24 | 2017-09-01 | 北京科技大学 | A kind of legal knowledge collection of illustrative plates method for auto constructing |
| CN107169078A (en) * | 2017-05-10 | 2017-09-15 | 京东方科技集团股份有限公司 | Knowledge of TCM collection of illustrative plates and its method for building up and computer system |
| CN107301235A (en) * | 2017-06-27 | 2017-10-27 | 山东浪潮商用***有限公司 | A kind of communicating knowledge collection of illustrative plates display systems |
| CN107341215A (en) * | 2017-06-07 | 2017-11-10 | 北京航空航天大学 | A kind of vertical knowledge mapping classification ensemble querying method of multi-source based on Distributed Computing Platform |
| CN107526795A (en) * | 2017-08-17 | 2017-12-29 | 晶赞广告（上海）有限公司 | Construction method and device, storage medium, the computing device of knowledge base |
| CN107633075A (en) * | 2017-09-22 | 2018-01-26 | 吉林大学 | A kind of multi-source heterogeneous data fusion platform and fusion method |
| CN107832407A (en) * | 2017-11-03 | 2018-03-23 | 上海点融信息科技有限责任公司 | For generating the information processing method, device and readable storage medium storing program for executing of knowledge mapping |
| CN107908671A (en) * | 2017-10-25 | 2018-04-13 | 南京擎盾信息科技有限公司 | Knowledge mapping construction method and system based on law data |
| CN108133030A (en) * | 2017-12-29 | 2018-06-08 | 北京物灵智能科技有限公司 | A kind of realization method and system for painting this question and answer |
| CN108170813A (en) * | 2017-12-29 | 2018-06-15 | 智搜天机（北京）信息技术有限公司 | A kind of method and its system of full media content intelligent checks |
| CN108182245A (en) * | 2017-12-28 | 2018-06-19 | 北京锐安科技有限公司 | The construction method and device of people's object properties classificating knowledge collection of illustrative plates |
| CN108197119A (en) * | 2018-02-05 | 2018-06-22 | 成都卓观信息技术有限公司 | The archives of paper quality digitizing solution of knowledge based collection of illustrative plates |
| CN108304493A (en) * | 2018-01-10 | 2018-07-20 | 深圳市腾讯计算机***有限公司 | A kind of the hypernym method for digging and device of knowledge based collection of illustrative plates |
| CN108536724A (en) * | 2018-02-13 | 2018-09-14 | 西安理工大学 | Main body recognition methods in a kind of metro design code based on the double-deck hash index |
| CN108665141A (en) * | 2018-04-03 | 2018-10-16 | 山东科技大学 | A method of extracting emergency response procedural model automatically from accident prediction scheme |
| CN108874915A (en) * | 2018-05-30 | 2018-11-23 | 苏州思必驰信息科技有限公司 | Method of Knowledge Organization, system, electronic equipment and storage medium |
| CN109002435A (en) * | 2018-06-06 | 2018-12-14 | 达而观信息科技（上海）有限公司 | A kind of data processing method and device |
| CN109189947A (en) * | 2018-11-07 | 2019-01-11 | 曲阜师范大学 | A kind of mobile data knowledge mapping method for auto constructing based on relational database |
| CN109299290A (en) * | 2018-12-07 | 2019-02-01 | 广东小天才科技有限公司 | A kind of dub in background music recommended method and the electronic equipment of knowledge based map |
| CN109347798A (en) * | 2018-09-12 | 2019-02-15 | 东软集团股份有限公司 | Generation method, device, equipment and the storage medium of network security knowledge map |
| CN109523988A (en) * | 2018-11-26 | 2019-03-26 | 安徽淘云科技有限公司 | A kind of text deductive method and device |
| CN109582799A (en) * | 2018-06-29 | 2019-04-05 | 北京百度网讯科技有限公司 | The determination method, apparatus and electronic equipment of knowledge sample data set |
| CN109582958A (en) * | 2018-11-20 | 2019-04-05 | 厦门大学深圳研究院 | A kind of disaster story line construction method and device |
| CN109657065A (en) * | 2018-10-31 | 2019-04-19 | 百度在线网络技术（北京）有限公司 | Knowledge mapping processing method, device and electronic equipment |
| CN110134842A (en) * | 2019-04-03 | 2019-08-16 | 深圳价值在线信息科技股份有限公司 | Information matching method, device, storage medium and server based on Information Atlas |
| CN110209827A (en) * | 2018-02-07 | 2019-09-06 | 腾讯科技（深圳）有限公司 | Searching method, device, computer readable storage medium and computer equipment |
| CN110222198A (en) * | 2019-06-18 | 2019-09-10 | 卓尔智联(武汉)研究院有限公司 | Non-ferrous metal industry knowledge mapping construction method, electronic device and storage medium |
| CN110275965A (en) * | 2019-06-27 | 2019-09-24 | 卓尔智联(武汉)研究院有限公司 | Pseudo event detection method, electronic device and computer readable storage medium |
| CN110347845A (en) * | 2019-07-15 | 2019-10-18 | 北京明略软件***有限公司 | The method for drafting and device of knowledge mapping |
| CN110399605A (en) * | 2018-04-17 | 2019-11-01 | 富士施乐株式会社 | Information processing unit and the computer-readable medium for storing program |
| TWI682287B (en) * | 2018-10-25 | 2020-01-11 | 財團法人資訊工業策進會 | Knowledge graph generating apparatus, method, and computer program product thereof |
| CN110738982A (en) * | 2019-10-22 | 2020-01-31 | 珠海格力电器股份有限公司 | request processing method and device and electronic equipment |
| CN110750651A (en) * | 2019-10-16 | 2020-02-04 | 同方知网(北京)技术有限公司 | Knowledge graph construction method and generation device based on scientific and technological achievements |
| CN110851610A (en) * | 2018-07-25 | 2020-02-28 | 百度在线网络技术（北京）有限公司 | Knowledge graph generation method and device, computer equipment and storage medium |
| CN111160841A (en) * | 2019-11-29 | 2020-05-15 | 广东轩辕网络科技股份有限公司 | Organization architecture construction method and device based on knowledge graph |
| CN111259163A (en) * | 2020-01-14 | 2020-06-09 | 北京明略软件***有限公司 | Knowledge graph generation method and device and computer readable storage medium |
| CN111259160A (en) * | 2018-11-30 | 2020-06-09 | 百度在线网络技术（北京）有限公司 | Knowledge graph construction method, device, equipment and storage medium |
| CN111339311A (en) * | 2019-12-30 | 2020-06-26 | 智慧神州(北京)科技有限公司 | Method, device and processor for extracting structured events based on generative network |
| CN111368145A (en) * | 2018-12-26 | 2020-07-03 | 沈阳新松机器人自动化股份有限公司 | Knowledge graph creating method and system and terminal equipment |
| CN111460080A (en) * | 2020-03-25 | 2020-07-28 | 中国人民解放军国防科技大学 | Event map construction and query method and system for open source data heat analysis |
| WO2020155749A1 (en) * | 2019-01-31 | 2020-08-06 | 平安科技（深圳）有限公司 | Method and apparatus for constructing personal knowledge graph, computer device, and storage medium |
| CN112001825A (en) * | 2020-08-18 | 2020-11-27 | 上海松鼠课堂人工智能科技有限公司 | Learning cognitive path planning system based on cognitive map |
| CN112148893A (en) * | 2020-09-25 | 2020-12-29 | 南方电网数字电网研究院有限公司 | Energy analysis knowledge graph construction method and energy analysis visualization method |
| CN112487213A (en) * | 2020-12-18 | 2021-03-12 | 清华大学 | Cross-language-domain knowledge graph construction method and device |
| CN112613315A (en) * | 2020-12-29 | 2021-04-06 | 重庆农村商业银行股份有限公司 | Text knowledge automatic extraction method, device, equipment and storage medium |
| CN112632214A (en) * | 2020-12-24 | 2021-04-09 | 中国建设银行股份有限公司 | Method and device for creating list data index |
| CN112733515A (en) * | 2020-12-31 | 2021-04-30 | 贝壳技术有限公司 | Text generation method and device, electronic equipment and readable storage medium |
| CN112765363A (en) * | 2021-01-19 | 2021-05-07 | 昆明理工大学 | Demand map construction method for scientific and technological service demand |
| CN112951446A (en) * | 2021-04-16 | 2021-06-11 | 平安科技（深圳）有限公司 | Medicine query method, device, equipment and storage medium based on medicine atlas |
| CN113220835A (en) * | 2021-05-08 | 2021-08-06 | 北京百度网讯科技有限公司 | Text information processing method and device, electronic equipment and storage medium |
| CN113609309A (en) * | 2021-08-16 | 2021-11-05 | 脸萌有限公司 | Knowledge graph construction method and device, storage medium and electronic equipment |
| US11379733B2 (en) | 2019-07-10 | 2022-07-05 | International Business Machines Corporation | Detecting and predicting object events from images |
| US11403328B2 (en) | 2019-03-08 | 2022-08-02 | International Business Machines Corporation | Linking and processing different knowledge graphs |
| CN116401375A (en) * | 2023-03-23 | 2023-07-07 | 深圳宏鹏数字供应链管理有限公司 | Knowledge graph construction method and system |
| CN116955639A (en) * | 2023-04-24 | 2023-10-27 | 浙商期货有限公司 | Method and device for constructing future industry chain knowledge graph and computer equipment |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11829726B2 (en) | 2021-01-25 | 2023-11-28 | International Business Machines Corporation | Dual learning bridge between text and knowledge graph |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003196296A (en) * | 2001-12-25 | 2003-07-11 | Celestar Lexico-Sciences Inc | Document knowledge managing device, document knowledge managing method, its program, and recording medium |
| US6598043B1 (en) * | 1999-10-04 | 2003-07-22 | Jarg Corporation | Classification of information sources using graph structures |
| 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 |
| CN105550190A (en) * | 2015-06-26 | 2016-05-04 | 许昌学院 | Knowledge graph-oriented cross-media retrieval system |
| CN105574098A (en) * | 2015-12-11 | 2016-05-11 | 百度在线网络技术（北京）有限公司 | Knowledge graph generation method and device and entity comparing method and device |
-
2016
- 2016-08-03 CN CN201610628591.6A patent/CN106156365B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6598043B1 (en) * | 1999-10-04 | 2003-07-22 | Jarg Corporation | Classification of information sources using graph structures |
| JP2003196296A (en) * | 2001-12-25 | 2003-07-11 | Celestar Lexico-Sciences Inc | Document knowledge managing device, document knowledge managing method, its program, and recording medium |
| 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 |
| CN105550190A (en) * | 2015-06-26 | 2016-05-04 | 许昌学院 | Knowledge graph-oriented cross-media retrieval system |
| CN105574098A (en) * | 2015-12-11 | 2016-05-11 | 百度在线网络技术（北京）有限公司 | Knowledge graph generation method and device and entity comparing method and device |
Non-Patent Citations (2)
| Title |
|---|
| 刘峤 等: ""知识图谱构建技术综述"", 《计算机研究与发展》 * |
| 周安林: ""基于Web的实体信息提取和搜索研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (91)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106294321A (en) * | 2016-08-04 | 2017-01-04 | 北京智能管家科技有限公司 | The dialogue method for digging of a kind of specific area and device |
| CN106294321B (en) * | 2016-08-04 | 2019-05-31 | 北京儒博科技有限公司 | A kind of the dialogue method for digging and device of specific area |
| CN106599091A (en) * | 2016-11-24 | 2017-04-26 | 上海交通大学 | Storage and indexing method of RDF graph structures stored based on key values |
| CN106599091B (en) * | 2016-11-24 | 2020-07-14 | 上海交通大学 | RDF graph structure storage and index method based on key value storage |
| CN106776564A (en) * | 2016-12-21 | 2017-05-31 | 张永成 | The method for recognizing semantics and system of a kind of knowledge based collection of illustrative plates |
| CN106777331A (en) * | 2017-01-11 | 2017-05-31 | 北京航空航天大学 | Knowledge mapping generation method and device |
| CN106933804B (en) * | 2017-03-10 | 2020-03-31 | 上海数眼科技发展有限公司 | Structured information extraction method based on deep learning |
| CN106933804A (en) * | 2017-03-10 | 2017-07-07 | 上海数眼科技发展有限公司 | A kind of structured message abstracting method based on deep learning |
| CN106934042A (en) * | 2017-03-16 | 2017-07-07 | 中国人民解放军国防科学技术大学 | A kind of knowledge mapping represents model and its method |
| CN106934042B (en) * | 2017-03-16 | 2020-05-29 | 中国人民解放军国防科学技术大学 | Knowledge graph representation system and implementation method thereof |
| CN107016072A (en) * | 2017-03-23 | 2017-08-04 | 成都市公安科学技术研究所 | Knowledge-based inference system and method based on social networks knowledge mapping |
| CN107016072B (en) * | 2017-03-23 | 2020-05-15 | 成都市公安科学技术研究所 | Knowledge inference system and method based on social network knowledge graph |
| CN107122444A (en) * | 2017-04-24 | 2017-09-01 | 北京科技大学 | A kind of legal knowledge collection of illustrative plates method for auto constructing |
| CN107169078A (en) * | 2017-05-10 | 2017-09-15 | 京东方科技集团股份有限公司 | Knowledge of TCM collection of illustrative plates and its method for building up and computer system |
| US10929440B2 (en) | 2017-05-10 | 2021-02-23 | Boe Technology Group Co., Ltd. | Traditional Chinese medicine knowledge graph and establishment method therefor, and computer system |
| CN107066621A (en) * | 2017-05-11 | 2017-08-18 | 腾讯科技（深圳）有限公司 | A kind of search method of similar video, device and storage medium |
| CN107341215B (en) * | 2017-06-07 | 2020-05-12 | 北京航空航天大学 | Multi-source vertical knowledge graph classification integration query system based on distributed computing platform |
| CN107341215A (en) * | 2017-06-07 | 2017-11-10 | 北京航空航天大学 | A kind of vertical knowledge mapping classification ensemble querying method of multi-source based on Distributed Computing Platform |
| CN107301235A (en) * | 2017-06-27 | 2017-10-27 | 山东浪潮商用***有限公司 | A kind of communicating knowledge collection of illustrative plates display systems |
| CN107526795A (en) * | 2017-08-17 | 2017-12-29 | 晶赞广告（上海）有限公司 | Construction method and device, storage medium, the computing device of knowledge base |
| CN107526795B (en) * | 2017-08-17 | 2020-05-29 | 晶赞广告（上海）有限公司 | Knowledge base construction method and device, storage medium and computing equipment |
| CN107633075A (en) * | 2017-09-22 | 2018-01-26 | 吉林大学 | A kind of multi-source heterogeneous data fusion platform and fusion method |
| CN107908671B (en) * | 2017-10-25 | 2022-02-01 | 南京擎盾信息科技有限公司 | Knowledge graph construction method and system based on legal data |
| CN107908671A (en) * | 2017-10-25 | 2018-04-13 | 南京擎盾信息科技有限公司 | Knowledge mapping construction method and system based on law data |
| CN107832407A (en) * | 2017-11-03 | 2018-03-23 | 上海点融信息科技有限责任公司 | For generating the information processing method, device and readable storage medium storing program for executing of knowledge mapping |
| CN108182245A (en) * | 2017-12-28 | 2018-06-19 | 北京锐安科技有限公司 | The construction method and device of people's object properties classificating knowledge collection of illustrative plates |
| CN108170813A (en) * | 2017-12-29 | 2018-06-15 | 智搜天机（北京）信息技术有限公司 | A kind of method and its system of full media content intelligent checks |
| CN108133030A (en) * | 2017-12-29 | 2018-06-08 | 北京物灵智能科技有限公司 | A kind of realization method and system for painting this question and answer |
| CN108304493A (en) * | 2018-01-10 | 2018-07-20 | 深圳市腾讯计算机***有限公司 | A kind of the hypernym method for digging and device of knowledge based collection of illustrative plates |
| CN108304493B (en) * | 2018-01-10 | 2020-06-12 | 深圳市腾讯计算机***有限公司 | Hypernym mining method and device based on knowledge graph |
| CN108197119A (en) * | 2018-02-05 | 2018-06-22 | 成都卓观信息技术有限公司 | The archives of paper quality digitizing solution of knowledge based collection of illustrative plates |
| CN110209827B (en) * | 2018-02-07 | 2023-09-19 | 腾讯科技（深圳）有限公司 | Search method, search device, computer-readable storage medium, and computer device |
| CN110209827A (en) * | 2018-02-07 | 2019-09-06 | 腾讯科技（深圳）有限公司 | Searching method, device, computer readable storage medium and computer equipment |
| CN108536724A (en) * | 2018-02-13 | 2018-09-14 | 西安理工大学 | Main body recognition methods in a kind of metro design code based on the double-deck hash index |
| CN108665141A (en) * | 2018-04-03 | 2018-10-16 | 山东科技大学 | A method of extracting emergency response procedural model automatically from accident prediction scheme |
| CN110399605A (en) * | 2018-04-17 | 2019-11-01 | 富士施乐株式会社 | Information processing unit and the computer-readable medium for storing program |
| CN108874915A (en) * | 2018-05-30 | 2018-11-23 | 苏州思必驰信息科技有限公司 | Method of Knowledge Organization, system, electronic equipment and storage medium |
| CN109002435A (en) * | 2018-06-06 | 2018-12-14 | 达而观信息科技（上海）有限公司 | A kind of data processing method and device |
| US11151179B2 (en) | 2018-06-29 | 2021-10-19 | Beijing Baidu Netcom Science Technology Co., Ltd. | Method, apparatus and electronic device for determining knowledge sample data set |
| CN109582799B (en) * | 2018-06-29 | 2020-09-22 | 北京百度网讯科技有限公司 | Method and device for determining knowledge sample data set and electronic equipment |
| CN109582799A (en) * | 2018-06-29 | 2019-04-05 | 北京百度网讯科技有限公司 | The determination method, apparatus and electronic equipment of knowledge sample data set |
| CN110851610B (en) * | 2018-07-25 | 2022-09-27 | 百度在线网络技术（北京）有限公司 | Knowledge graph generation method and device, computer equipment and storage medium |
| CN110851610A (en) * | 2018-07-25 | 2020-02-28 | 百度在线网络技术（北京）有限公司 | Knowledge graph generation method and device, computer equipment and storage medium |
| CN109347798A (en) * | 2018-09-12 | 2019-02-15 | 东软集团股份有限公司 | Generation method, device, equipment and the storage medium of network security knowledge map |
| TWI682287B (en) * | 2018-10-25 | 2020-01-11 | 財團法人資訊工業策進會 | Knowledge graph generating apparatus, method, and computer program product thereof |
| US11250035B2 (en) | 2018-10-25 | 2022-02-15 | Institute For Information Industry | Knowledge graph generating apparatus, method, and non-transitory computer readable storage medium thereof |
| CN109657065A (en) * | 2018-10-31 | 2019-04-19 | 百度在线网络技术（北京）有限公司 | Knowledge mapping processing method, device and electronic equipment |
| CN109189947A (en) * | 2018-11-07 | 2019-01-11 | 曲阜师范大学 | A kind of mobile data knowledge mapping method for auto constructing based on relational database |
| CN109582958A (en) * | 2018-11-20 | 2019-04-05 | 厦门大学深圳研究院 | A kind of disaster story line construction method and device |
| CN109523988B (en) * | 2018-11-26 | 2021-11-05 | 安徽淘云科技股份有限公司 | Text deduction method and device |
| CN109523988A (en) * | 2018-11-26 | 2019-03-26 | 安徽淘云科技有限公司 | A kind of text deductive method and device |
| CN111259160B (en) * | 2018-11-30 | 2023-08-29 | 百度在线网络技术（北京）有限公司 | Knowledge graph construction method, device, equipment and storage medium |
| CN111259160A (en) * | 2018-11-30 | 2020-06-09 | 百度在线网络技术（北京）有限公司 | Knowledge graph construction method, device, equipment and storage medium |
| CN109299290A (en) * | 2018-12-07 | 2019-02-01 | 广东小天才科技有限公司 | A kind of dub in background music recommended method and the electronic equipment of knowledge based map |
| CN111368145A (en) * | 2018-12-26 | 2020-07-03 | 沈阳新松机器人自动化股份有限公司 | Knowledge graph creating method and system and terminal equipment |
| WO2020155749A1 (en) * | 2019-01-31 | 2020-08-06 | 平安科技（深圳）有限公司 | Method and apparatus for constructing personal knowledge graph, computer device, and storage medium |
| US11403328B2 (en) | 2019-03-08 | 2022-08-02 | International Business Machines Corporation | Linking and processing different knowledge graphs |
| CN110134842A (en) * | 2019-04-03 | 2019-08-16 | 深圳价值在线信息科技股份有限公司 | Information matching method, device, storage medium and server based on Information Atlas |
| CN110222198A (en) * | 2019-06-18 | 2019-09-10 | 卓尔智联(武汉)研究院有限公司 | Non-ferrous metal industry knowledge mapping construction method, electronic device and storage medium |
| CN110275965A (en) * | 2019-06-27 | 2019-09-24 | 卓尔智联(武汉)研究院有限公司 | Pseudo event detection method, electronic device and computer readable storage medium |
| CN110275965B (en) * | 2019-06-27 | 2021-12-21 | 卓尔智联(武汉)研究院有限公司 | False news detection method, electronic device and computer readable storage medium |
| US11379733B2 (en) | 2019-07-10 | 2022-07-05 | International Business Machines Corporation | Detecting and predicting object events from images |
| CN110347845A (en) * | 2019-07-15 | 2019-10-18 | 北京明略软件***有限公司 | The method for drafting and device of knowledge mapping |
| CN110750651B (en) * | 2019-10-16 | 2023-05-26 | 同方知网数字出版技术股份有限公司 | Knowledge graph construction method based on scientific and technological achievements |
| CN110750651A (en) * | 2019-10-16 | 2020-02-04 | 同方知网(北京)技术有限公司 | Knowledge graph construction method and generation device based on scientific and technological achievements |
| CN110738982B (en) * | 2019-10-22 | 2022-01-28 | 珠海格力电器股份有限公司 | Request processing method and device and electronic equipment |
| CN110738982A (en) * | 2019-10-22 | 2020-01-31 | 珠海格力电器股份有限公司 | request processing method and device and electronic equipment |
| CN111160841A (en) * | 2019-11-29 | 2020-05-15 | 广东轩辕网络科技股份有限公司 | Organization architecture construction method and device based on knowledge graph |
| CN111339311A (en) * | 2019-12-30 | 2020-06-26 | 智慧神州(北京)科技有限公司 | Method, device and processor for extracting structured events based on generative network |
| CN111259163A (en) * | 2020-01-14 | 2020-06-09 | 北京明略软件***有限公司 | Knowledge graph generation method and device and computer readable storage medium |
| WO2021143014A1 (en) * | 2020-01-14 | 2021-07-22 | 北京明略软件***有限公司 | Method and device for generating knowledge graph, and computer readable storage medium |
| CN111460080B (en) * | 2020-03-25 | 2022-04-22 | 中国人民解放军国防科技大学 | Event map construction and query method and system for open source data heat analysis |
| CN111460080A (en) * | 2020-03-25 | 2020-07-28 | 中国人民解放军国防科技大学 | Event map construction and query method and system for open source data heat analysis |
| CN112001825A (en) * | 2020-08-18 | 2020-11-27 | 上海松鼠课堂人工智能科技有限公司 | Learning cognitive path planning system based on cognitive map |
| CN112148893A (en) * | 2020-09-25 | 2020-12-29 | 南方电网数字电网研究院有限公司 | Energy analysis knowledge graph construction method and energy analysis visualization method |
| CN112487213A (en) * | 2020-12-18 | 2021-03-12 | 清华大学 | Cross-language-domain knowledge graph construction method and device |
| CN112632214A (en) * | 2020-12-24 | 2021-04-09 | 中国建设银行股份有限公司 | Method and device for creating list data index |
| CN112613315A (en) * | 2020-12-29 | 2021-04-06 | 重庆农村商业银行股份有限公司 | Text knowledge automatic extraction method, device, equipment and storage medium |
| CN112613315B (en) * | 2020-12-29 | 2024-06-07 | 重庆农村商业银行股份有限公司 | Text knowledge automatic extraction method, device, equipment and storage medium |
| CN112733515A (en) * | 2020-12-31 | 2021-04-30 | 贝壳技术有限公司 | Text generation method and device, electronic equipment and readable storage medium |
| CN112765363A (en) * | 2021-01-19 | 2021-05-07 | 昆明理工大学 | Demand map construction method for scientific and technological service demand |
| CN112765363B (en) * | 2021-01-19 | 2022-11-22 | 昆明理工大学 | Demand map construction method for scientific and technological service demand |
| CN112951446A (en) * | 2021-04-16 | 2021-06-11 | 平安科技（深圳）有限公司 | Medicine query method, device, equipment and storage medium based on medicine atlas |
| CN113220835B (en) * | 2021-05-08 | 2023-09-29 | 北京百度网讯科技有限公司 | Text information processing method, device, electronic equipment and storage medium |
| CN113220835A (en) * | 2021-05-08 | 2021-08-06 | 北京百度网讯科技有限公司 | Text information processing method and device, electronic equipment and storage medium |
| WO2023022655A3 (en) * | 2021-08-16 | 2023-04-13 | 脸萌有限公司 | Knowledge map construction method and apparatus, storage medium, and electronic device |
| CN113609309A (en) * | 2021-08-16 | 2021-11-05 | 脸萌有限公司 | Knowledge graph construction method and device, storage medium and electronic equipment |
| CN113609309B (en) * | 2021-08-16 | 2024-02-06 | 脸萌有限公司 | Knowledge graph construction method and device, storage medium and electronic equipment |
| CN116401375A (en) * | 2023-03-23 | 2023-07-07 | 深圳宏鹏数字供应链管理有限公司 | Knowledge graph construction method and system |
| CN116401375B (en) * | 2023-03-23 | 2024-02-20 | 深圳宏鹏数字供应链管理有限公司 | Knowledge graph construction method and system |
| CN116955639A (en) * | 2023-04-24 | 2023-10-27 | 浙商期货有限公司 | Method and device for constructing future industry chain knowledge graph and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106156365B (en) | 2019-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106156365B (en) | A kind of generation method and device of knowledge mapping | |
| CN109657054B (en) | Abstract generation method, device, server and storage medium | |
| CN109189942B (en) | Construction method and device of patent data knowledge graph | |
| CN109284357B (en) | Man-machine conversation method, device, electronic equipment and computer readable medium | |
| CN110196901A (en) | Construction method, device, computer equipment and the storage medium of conversational system | |
| CN104503998B (en) | For the kind identification method and device of user query sentence | |
| CN111026842A (en) | Natural language processing method, natural language processing device and intelligent question-answering system | |
| CN108829682B (en) | Computer readable storage medium, intelligent question answering method and intelligent question answering device | |
| CN106570180A (en) | Artificial intelligence based voice searching method and device | |
| CN103886034A (en) | Method and equipment for building indexes and matching inquiry input information of user | |
| CN110910283A (en) | Method, device, equipment and storage medium for generating legal document | |
| JP2014502754A (en) | Method and apparatus for blocking harmful information on the Internet | |
| CN110287314B (en) | Long text reliability assessment method and system based on unsupervised clustering | |
| CN108121697A (en) | Method, apparatus, equipment and the computer storage media that a kind of text is rewritten | |
| CN111259160A (en) | Knowledge graph construction method, device, equipment and storage medium | |
| CN114238573A (en) | Information pushing method and device based on text countermeasure sample | |
| CN112149386A (en) | Event extraction method, storage medium and server | |
| CN110209721A (en) | Judgement document transfers method, apparatus, server and storage medium | |
| CN108363700A (en) | The method for evaluating quality and device of headline | |
| CN112069312A (en) | Text classification method based on entity recognition and electronic device | |
| CN110377745B (en) | Information processing method, information retrieval device and server | |
| CN112613321A (en) | Method and system for extracting entity attribute information in text | |
| CN116150651A (en) | AI-based depth synthesis detection method and system | |
| CN108268443B (en) | Method and device for determining topic point transfer and acquiring reply text | |
| CN110610003A (en) | Method and system for assisting text annotation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: Room 508-598, Xitian Gezhuang Town Government Office Building, No. 8 Xitong Road, Miyun County Economic Development Zone, Beijing 101500 Applicant after: Beijing Rubo Technology Co., Ltd. Address before: Room 508-598, Xitian Gezhuang Town Government Office Building, No. 8 Xitong Road, Miyun County Economic Development Zone, Beijing 101500 Applicant before: BEIJING INTELLIGENT HOUSEKEEPER TECHNOLOGY CO., LTD. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210819 Address after: 301-112, floor 3, building 2, No. 18, YANGFANGDIAN Road, Haidian District, Beijing 100038 Patentee after: Beijing Rubu Technology Co.,Ltd. Address before: Room 508-598, Xitian Gezhuang Town Government Office Building, No. 8 Xitong Road, Miyun County Economic Development Zone, Beijing 101500 Patentee before: BEIJING ROOBO TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right |