CN109739964A - Knowledge data providing method, device, electronic equipment and storage medium - Google Patents
Knowledge data providing method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN109739964A CN109739964A CN201811613073.2A CN201811613073A CN109739964A CN 109739964 A CN109739964 A CN 109739964A CN 201811613073 A CN201811613073 A CN 201811613073A CN 109739964 A CN109739964 A CN 109739964A
- Authority
- CN
- China
- Prior art keywords
- word
- knowledge
- query
- knowledge data
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The embodiment of the present disclosure provides a kind of knowledge data providing method, device, electronic equipment and storage medium.Knowledge data providing method includes: to obtain inquiry request sentence；Word segmentation processing is carried out to inquiry request sentence, obtains at least one query word；Obtain expanded keyword corresponding with each query word respectively from extension dictionary；The combination of each query word that will acquire or its corresponding expanded keyword is matched with multiple semantic matches expression formulas respectively, obtains the information of query intention；Knowledge data corresponding with the query intention is obtained from knowledge base；The knowledge data is provided.The inquiry request proposed in a manner of natural language can be understood, be analyzed, demand matching is carried out to the key message extracted from inquiry request by the semantic understanding frame of building, and the query intention obtained according to matching, the corresponding knowledge data in knowledge base is provided, so as to provide the knowledge data for being accurately matched to its query intention for inquiry user.
Description
Technical field
The embodiment of the present disclosure is related to technical field of information processing more particularly to a kind of knowledge data providing method, device, electricity
Sub- equipment and storage medium.
Background technique
The information retrieval carried out on Web at present mainly utilizes search engine, carries out the keyword match based on character
Retrieval.Although search engine avoids the blindness of user's browsing network information to a certain extent, convenience is brought to user,
But the main problem of this retrieval mode is while returning to a large amount of incoherent results but misses out some related pages
Face is largely unable to satisfy the demand of user.It is traditional based on Information locating in face of the surge of network information
Web information representation method, so that existing information retrieval faces difficulty and awkward situation described above.
Summary of the invention
The embodiment of the present disclosure provides a kind of information processing technology scheme, and the technology for being analyzed based on intelligent semantic is provided
Knowledge data, with intelligent in information search, accurately offer user's actual queries knowledge informations.
According to the first aspect of the embodiments of the present disclosure, a kind of knowledge data providing method is provided, comprising: obtain inquiry request
Sentence；Word segmentation processing is carried out to the inquiry request sentence, obtains at least one query word；It is obtained respectively from extension dictionary and each
The corresponding expanded keyword of a query word, the extension dictionary include the expanded keyword of multiple queries word and as reality
The classification information of the query word of pronouns, general term for nouns, numerals and measure words；The combination of each query word that will acquire or its corresponding expanded keyword is distinguished
It is matched with multiple semantic matches expression formulas, obtains the information of query intention；It is obtained and the query intention pair from knowledge base
The knowledge data answered；The knowledge data is provided.
Optionally, the query intention includes the information of knowledget opic and knowledge attribute.
Optionally, each knowledge data in the knowledge base is stored as comprising knowledget opic, knowledge attribute and corresponding
The triple of knowledge answer.
Optionally, the expanded keyword includes the following word of at least one of query word: synonym, substitution word, mark
Mutatis mutandis word and hypernym.
Optionally, the semantic matches expression formula includes single the first matching keywords or single entity as entity word
The information of object type, and the information of query intention corresponding with the semantic matches expression formula includes matching key with described
The information of the preset attribute of word or the corresponding knowledget opic of entity object classification and the knowledget opic.
Optionally, the semantic matches expression formula further includes at least one second matching keywords, and with the semanteme
The information of the corresponding query intention of matching expression includes knowledge master corresponding with the matching keywords or entity object classification
The information of topic and knowledge attribute corresponding at least one described second matching keywords.
According to the second aspect of an embodiment of the present disclosure, a kind of knowledge data offer device is provided, comprising: request mould
Block, for obtaining inquiry request sentence；Word segmentation module is requested, for obtaining the inquiry request that module obtains to the request sentence
Sentence carries out word segmentation processing, obtains at least one query word；Request expansion module, for obtained respectively from extension dictionary with it is described
The corresponding expanded keyword of each query word that request module is got, the extension dictionary includes multiple queries word
Expanded keyword and the query word as entity word classification information；Matching module is requested, for extending the request
The combination of each query word or its corresponding expanded keyword that module is got respectively with multiple semantic matches expression formulas
It is matched, obtains the information of query intention；Knowledge data obtains module, matches mould with the request for obtaining from knowledge base
The corresponding knowledge data of the query intention that Block- matching obtains；Knowledge data provides module, is used to provide the described knowledge data acquisition
The knowledge data that module obtains.
Optionally, the query intention includes the information of knowledget opic and knowledge attribute, and each item in the knowledge base is known
Know data and is stored as the triple comprising knowledget opic, knowledge attribute and corresponding knowledge answer.
Optionally, the expanded keyword includes the following word of at least one of query word: synonym, substitution word, mark
Mutatis mutandis word and hypernym.
According to the third aspect of an embodiment of the present disclosure, a kind of electronic equipment is provided, comprising: processor and memory；It is described
Memory makes the processor execute any aforementioned knowledge number for storing at least one executable instruction, the executable instruction
The step of according to providing method.
According to a fourth aspect of embodiments of the present disclosure, a kind of computer readable storage medium is provided, it is described computer-readable
Storage medium is stored with executable instruction, and the executable instruction makes the processor execute any aforementioned knowledge data provider
The step of method.
Scheme is provided by the knowledge data that the disclosure provides, it can be to the inquiry request proposed in a manner of natural language
Understood, analyzed, demand matching is carried out to the key message extracted from inquiry request by the semantic understanding frame of building, and
And the query intention obtained according to matching, the corresponding knowledge data in knowledge base is provided, so as to provide standard for inquiry user
Really it is matched to the knowledge data of its query intention.
Detailed description of the invention
Fig. 1 is the schematic diagram for showing the exemplary process of building semantic understanding frame；
Fig. 2 shows the exemplary knowledge mappings using disease category as knowledget opic；
Fig. 3 is the flow chart for showing the processing of knowledge data providing method according to the exemplary embodiment of the disclosure；
Fig. 4 is the schematic diagram for showing the accessed path of the exemplary knowledge mapping in Fig. 3 and knowledge data；
Fig. 5~Fig. 7 is shown respectively knowledget opic, knowledge attribute and knowledge according to the exemplary embodiment of the disclosure and answers
The schematic diagram of case；
Fig. 8 is to show to provide the logic diagram of device according to the knowledge data of the disclosure；
Fig. 9 is the structural schematic diagram for showing the electronic equipment according to some embodiments of the disclosure.
Specific embodiment
(identical label indicates identical element in several attached drawings) and embodiment with reference to the accompanying drawing, implement the disclosure
The specific embodiment of example is described in further detail.Following embodiment is not limited to the disclosure for illustrating the disclosure
Range.
It will be understood by those skilled in the art that the terms such as " first ", " second " in the embodiment of the present disclosure are only used for distinguishing
Different step, equipment or module etc., neither represent any particular technology meaning, also do not indicate that the inevitable logic between them is suitable
Sequence.
The disclosure is intended to non-structured natural language carrying out structural description, to construct knowledge base, and is based on language
Reason and good sense solution rule provides the knowledge data in knowledge base.For this reason, it may be necessary to divide the various corpus for constructing knowledge base
Analysis and tissue, and establish including a whole set of of knowledge base and semantic understanding rule for providing the semantic understanding of knowledge data
Frame.
In order to construct the semantic understanding frame, the knowledge corpus of magnanimity is needed to construct the knowledge for actually having knowledge data
Library, the semantic matches rule base for carrying out accurate semantic matches to query demand and for the word in query demand
It is extended and extension dictionary needed for semantic matches.
A kind of exemplary place for being constructed semantic understanding frame based on mass knowledge corpus is described hereinafter with reference to Fig. 1
Reason.
Text participle
The chinese character sequence of corpus, is cut into significant word by the rule-based participle technique combined with statistics, is used
Positive maximum participle technique and rescan technology, while guaranteeing to segment efficiency, it can be found that most of overlap type
Segmentation ambiguity.The cutting ambiguity processing technique of Case-based Reasoning, accurately handles ambiguity, and system is made to have good expand
Filling property.
Entity recognition
On the basis of text participle, the automatic various entities extracted in corpus.Using hidden Markov (HMM) model into
Row name identification and part-of-speech tagging: on the basis of Dictionary based segment, the reality of common non-nesting is identified using the hidden horse model of bottom
Body, and high-rise hidden horse model is successively taken to identify complicated nested entity；Then the unregistered word that will identify that is with scientific algorithm
Probability out is added in the hidden horse model of class-based cutting, and unregistered word and ambiguity are not as special case, with generic word one
Act the competition for participating in various candidate results.
Dictionary excavates
In conjunction with the terminological dictionary accumulated, some new terms are dug out by automatic mining technology, form final major term
Allusion quotation, automatic mining mainly include domain term discovery and new word discovery both direction.
Domain term finds the automatic abstracting method of Field Words based on un-annotated data.This method is mainly carried out in three steps:
Firstly, " tightness degree " combined between word in corpus is calculated, according to threshold filtering on the basis of participle；Then right
Corpus is counted, and the feature of word is obtained；Finally, we utilize SVM machine learning method, according to the feature of word to word
Classified to obtain Field Words.
New word discovery includes that entity word obtains and the acquisition of non-physical word.
Entity word obtain: there is employed herein stacking hidden Markov model (Cascaded Hidden Markov
Model, abbreviation Cascaded HMM) in unified hidden Markov model identify all kinds of name entities, and it is hidden at these
Certain connection is set up in Markov model, forms an integrated name entity recognition system.
In addition, also marking the classification information of each entity word for the entity word of acquisition.For example, to entity word " mid-autumn
Section ", marking its classification is red-letter day；To entity word " Beijing ", marking its classification is place name.
Non-physical word obtains: carrying out word string frequency statistics using Nagao algorithm, the statistics frequency of occurrences is greater than the N of certain value
To the word string of M member；Then Substring reduction is carried out with certain strategy, short string is fallen in long string merger, and primary filtration falls the rubbish in candidate string
Rubbish；Three kinds of strategies are finally integrated, last filtering is carried out to candidate string, obtains high frequency word string, using general geological coodinate system filtering, IWP mistake
The means such as filter, the filter of mutual reliability and the filtering of head and the tail word carry out the filtration of rubbish string, finally obtain candidate non-physical substring
(non-physical word).
Entity word (and its classification information) and non-physical word the deposit extension dictionary that will acquire.
Synonymy obtains
Research for synonym automatic identification is divided by the technology path of use, can be divided mainly into based on literal phase
Like degree, the vocabulary cooccurrence relation based on semantic dictionary, based on Large Scale Corpus, based on retrieval log etc..
If in two lexemes, as soon as lexeme is the secondary class of another lexeme, then saying that there are upper bottoms between them
Relationship (hyponymy) or hierarchical relationship.Relationship between car (car) and vehicle (vehicles) is exactly a kind of upper bottom
Relationship.Hyponymy be it is asymmetric, we call specificity stronger lexeme the hyponym of the stronger lexeme of generality
(hyponym), the stronger lexeme of generality is called the hypernym (hypernym) of the stronger lexeme of specificity.Therefore, we
It can be said that car is the hyponym of vehicle, and vehicle is the hypernym of car.Classification of the hypernym but also as car.
The target of level semantic relation building is to excavate the relationship of hypernym-hyponym (is-a) between word.Level
The method of relation recognition includes: method based on pattern extraction, based on term vector (Distributed Representation)
Method, based on statistical method etc..
In addition, being also some non-standards, the word of standard is arranged standard word, and adapts to the natural expression side of language
Formula, for the corresponding one or more substitution words of word setting.
The synonym obtained, substitution word, standard words and hypernym will be excavated and be also stored in extension dictionary.
For example, it is directed to the sufferer of AIDS, settable following three groups of expanded keywords:
Patient AIDS；HIV patient；Suffer from the people of AIDS；Patient；There is the people of AIDS；AIDS patient；AIDS VICTIMS；
AIDS patient；Patient；Patient；Ai Si patient；AIDS patient；Aids patient；AIDS sufferer；AIDS patient；AIDS
Patient；AIDS patient；The patient of AIDS；AIDS patient, this group of word indicate aids patient, this group of expanded keyword it is every
A word is all synonym relationship.
HIV infection person；Inhibition of HIV the infected；AIDS virus person is infected；The infected；AIDS the infected；HIV infection
Person；HIV patient；Patients infected hiv, this group of expanded keyword indicate People living with HIV.
HIV carriers；Carrier；AIDS virus carrier；HIV carrier；AIDS carrier；AIDS
Malicious carrier；AIDS virus carrier；The carrier of AIDS, this group of crucial carrier for indicating AIDS virus of word extension.
There are certain complementarity between these methods, therefore, in order to promote the accuracy of level semantic relation identification, this
System uses the method identification hierarchical semantic relations that a variety of methods be combined with each other.
Knowledge mapping building
Knowledge mapping be by by the subjects such as applied mathematics, graphics, Information Visualization Technology, information science theory with
Method and the methods of meterological citation analysis, Co-occurrence Analysis combine, and the core of subject is visually shown using visual map
Core structure, developing history, Disciplinary Frontiers and whole Knowledge framework reach the modern theory of Multidisciplinary Integration purpose.It is complicated
Ken shown by data mining, information processing, knowledge measure and graphic plotting, disclose the dynamic of ken
The state rule of development.
Fig. 2 shows the exemplary knowledge mappings using disease category as knowledget opic.Knowledge mapping as shown in Figure 2
In, first nodes are diseases, it includes 4 index paths, can find 4 two-level nodes according to this 4 paths, be respectively
Detection, prevention, drug, treatment.Each two-level node has several path indexings to 3 grades of nodes again.For most preferably controlling for AIDS
Treatment method this problem, word segmentation result are [AIDS] [best] [treatment] [methods], pass through the word segmentation result after lexicon extension
It is [$ disease] [best] [treatment] [method], this word segmentation result is sent in the space structure of semantic base, the road retrieved
Diameter is [$ disease] [treatment] [method].
Knowledge mapping is the semantic knowledge-base of a structuring, and composition unit is " entity-relationship-entity " ternary
Group, for describing concept and its correlation in physical world with sign format.For from the angle of knowledge query and offer,
Each knowledge data in the knowledge base is the triple form comprising knowledge agent, knowledge attribute and knowledge answer.
Language Ambiguity brings difficulty to search.Such as user input query word " Taj Mahal ", conventional search draws
Holding up can not understand that user wants inquiry is to commemorate mausoleum or position musician.Knowledge mapping intelligent search is by all these possibility
Property conclude grouping, user only need click wherein one group i.e. it can be seen that be directed to specific meanings all search results.
The knowledge base including knowledge data and the expansion word including multiple words can be constructed as a result, and as entity word
Word classification information extension dictionary.Wherein, the expansion word may include, but be not limited to, query word it is at least one with
Lower word: synonym, standard words and hypernym.
In addition it is also necessary to construct the semantic matches rule base of the semantic matches for demand.Specifically, it is advised in semantic matches
Then inventory has multiple semantic matches expression formulas.
The building of semantic matches expression formula
Semantic understanding is that the query demand of user is matched by Key Term based on semantic matches expression formula.Due to language
Each semantic feature has relevance in the front-back direction in adopted matching rule (such as semantic matches expression formula), therefore compared to nothing
The keyword in direction, it is more accurate to be described to be intended to semantic matching rule.
For example, three problems that the Mid-autumn Festival has a holiday or vacation, " how the Mid-autumn Festival has a holiday or vacation? ", " Mid-autumn Festival, which was had a holiday or vacation? ", " the Mid-autumn Festival
Have a holiday or vacation how many days? ", it can be defined as follows 3 semantic matches expression formulas:
[Mid-autumn Festival] [how] [having a holiday or vacation]
[Mid-autumn Festival] [which] [has a holiday or vacation]
[Mid-autumn Festival] [having a holiday or vacation] [several days]
The purpose for defining semantic matches expression formula is in order to be abstracted the different ways to put questions of same problem, by question sentence
Key Term summarize question sentence and be intended to, therefore expression formula preferably as far as possible simple, can covering problem it is as more as possible.So by upper example
In expression formula be further simplified are as follows:
[Mid-autumn Festival] [has a holiday or vacation]
Aforementioned expression can be used as a simple semantic matches expression formula, the letter having a holiday or vacation for the matching inquiry Mid-autumn Festival
Breath.Wherein, [Mid-autumn Festival] including entity word is used to match knowledget opic, and [having a holiday or vacation] including matching keywords is for matching
The information of attribute corresponding with knowledget opic out, the i.e. information of having a holiday or vacation in the Mid-autumn Festival.But the Dragon Boat Festival, National Day, these sections of the Spring Festival
There is general attribute in day, in order to continue to expand the coverage area of expression formula, can be abstracted as to an entity pair these red-letter days
It is as follows as classification:
[$ red-letter day] [having a holiday or vacation]
Wherein, [$ red-letter day] indicates an entity class, and it is any can be matched to the Mid-autumn Festival, the Dragon Boat Festival, National Day, Spring Festival etc.
Red-letter day.When input " how the Mid-autumn Festival has a holiday or vacation? ", matching result is as follows:
Semantic matches expression formula: [$ red-letter day] [having a holiday or vacation]
Matching entities: { $ red-letter day: the Mid-autumn Festival }
Matching is intended to: [Mid-autumn Festival, arrangement of having a holiday or vacation]
In aforementioned matching expression, [$ red-letter day] including entity object classification for matching knowledget opic, including
[having a holiday or vacation] with keyword is used to match the information of attribute corresponding with knowledget opic, the i.e. arrangement of having a holiday or vacation of the Dragon Boat Festival.
When input " how the Mid-autumn Festival has a holiday? ".
[$ red-letter day] [having a holiday or vacation] ≠ [$ red-letter day] [having a holiday]
At this moment it needs " to have a holiday or vacation " and is defined as synonymous phrase with " having a holiday " and [has a holiday or vacation；Have a holiday], it is extended and is expressed by synonym
The coverage area of formula.
[$ red-letter day] [having a holiday or vacation]=[$ red-letter day] [having a holiday]
Several exemplary representation forms of semantic matches expression formula are described below.
1) comprising single the first matching keywords or single entity object type as entity word
Example:
Semantic matches expression formula: [Education on AIDS day]
The query intention matched: [aids prevention, AIDS day]
Wherein, knowledget opic is " aids prevention ", and knowledge attribute is " AIDS day ".
Here, semantic matches expression formula only includes single matching keywords, hereon referred to as " the first matching keywords ", with
" the second matching keywords " hereinafter are mutually distinguished.
Example:
Semantic matches expression formula: [$ synthetic drug]
The query intention matched: [aids prevention, novel drug type]
Wherein, knowledget opic is " aids prevention ", and knowledge attribute is " novel drug type ".
Here, semantic matches expression formula only includes the information of single entity object type, i.e. " synthetic drug ".
2) comprising it is single as the first matching keywords or single entity object type of entity word and at least one the
Two matching keywords
Example:
Semantic matches expression formula: [$ credit card] [discounting]
The query intention matched: [$ credit card, preference item]
Example:
Semantic matches expression formula: [Education on AIDS day] [which]
Semantic matches expression formula: [Education on AIDS day] [anti-]
Semantic matches expression formula: [Education on AIDS day] [teenager]
It is used equally for matching query intention: [aids prevention, AIDS day]
Example:
Semantic matches expression formula: [old age] [$ patient] [immune]
Semantic matches expression formula: [old age] [$ patient] [feature]
Semantic matches expression formula: [old age] [$ patient] [symptom]
It is used equally for matching query intention: [AIDS disease symptoms, old the infected's symptom feature]
The processing of the knowledge data providing method based on aforementioned semantic understanding frame is specifically described hereinafter with reference to Fig. 3.It can
The processing of this method is executed in the client server of network.
Inquiry request sentence is obtained in step S310 referring to Fig. 3.
Specifically, the inquiry request sentence of user's input can be for example received by client application or browser interface.Such as
Fruit executes this method in server end, then server can receive the inquiry request sentence from client application or browser application.
The inquiry request sentence can be the user query demand of natural language expressing, such as " how is Beijing weather? ", " the battalion of chicken in large dish
Form point how? " Deng.
In step S320, word segmentation processing is carried out to the inquiry request sentence, obtains at least one query word.
Any applicable text analysis technique can be used, or use the aforementioned rule-based participle skill combined with statistics
Art, by inquiry request sentence segmentation at significant query word, such as " Beijing ", " weather ", " how ", " chicken in large dish ".
In step S330, expanded keyword corresponding with each query word, the expansion are obtained respectively from extension dictionary
Opening up dictionary includes the expanded keyword of multiple queries word and the classification information of the query word as entity word.
As previously mentioned, expanded keyword includes the following word of at least one of query word: synonym, substitution word, standard
Word and hypernym etc..Therefore, in the step, each query word that word segmentation processing can be obtained and the expansion word in extension dictionary
It is matched respectively, obtains expanded keyword corresponding with each query word.Wherein, crucial for the extension of entity word for property
Word also can get its classification information.
For example, for query word " Rong Cheng ", it is possible to provide its synonym " Foochow "；For query word " car ", it is possible to provide
Its hypernym " motor vehicle ", and its classification information " vehicle " is provided；For query word " nice ", it is possible to provide standard words
" taste " etc..
In step S340, the combination of each query word that will acquire or its corresponding expanded keyword respectively with it is more
A semantic matches expression formula is matched, and the information of query intention is obtained.
For example, it is assumed that for " Dragon Boat Festival " and its classification " red-letter day " and " being put in the expanded keyword that step S330 is got
Vacation ", " having a holiday " can then match to obtain query entity with one of [$ red-letter day] [having a holiday or vacation], [$ red-letter day] [having a holiday] by it to be conduct
The Dragon Boat Festival in red-letter day, it is intended that have a holiday or vacation (time, regulation) etc..
It will be described below the example of several step S310~S340 processing.
Example:
The inquiry request sentence of input: " Mountain Everest "
The query word that word segmentation processing obtains: " Mountain Everest "
Semantic matches expression formula: [mountain peak $]
Match obtained query intention: [Mountain Everest, brief introduction]
Example:
The inquiry request sentence of input: " Mountain Everest is how high? "
The query word that word segmentation processing obtains: " Mountain Everest ", "high"
Expanded keyword: " Mountain Everest ", " height "
Semantic matches expression formula: [mountain peak $] [height]
Match obtained query intention: [Mountain Everest, height]
Example:
The inquiry request sentence of input: " information of discount of wide hair ONE card "
The query word that word segmentation processing obtains: " wide hair ONE card ", " discounting ", " information "
Expanded keyword: " $ credit card "
Semantic matches expression formula: [$ credit card] [discounting]
Match obtained query intention: [wide hair ONE card, preference item]
After such as preceding processing obtains the information of query intention, step S350 is executed.
As it can be seen that the query intention that matching obtains includes the information of knowledget opic and knowledge attribute.
In step S350, knowledge data corresponding with the query intention is obtained from knowledge base.
Specifically, it is being stored with knowing for multiple triples comprising knowledget opic, knowledge attribute and corresponding knowledge answer
Know in library, searches knowledge data corresponding with the query intention.
Fig. 4 is the schematic diagram for showing the accessed path of the exemplary knowledge mapping in Fig. 3 and knowledge data.It below will ginseng
The processing of step S350 is described according to the example shown in Fig. 4.
Assuming that the query intention obtained from step S340 is [AIDS, treatment], then " $ disease " node is first found.By
In the child node of " $ disease " include [detection, prevention, drug, treatment], then by " treatment " attribute in query intention respectively with four
A child node is matched, until being matched to child node " treatment ".Hereafter, knowledge in knowledge base theme AIDS is transferred
Treat the attribute value of attribute, such as the content of the treatment method in relation to AIDS.
In addition, the schematic diagram of knowledget opic, knowledge attribute and knowledge answer is shown respectively in Fig. 5~Fig. 7.In step
S360 provides the knowledge data.
It can be shown by text, voice plays, video playing or network are sent etc., and the offer of any or various ways is got
Knowledge data.
Device is provided according to the knowledge data of the embodiment of the present disclosure referring to Fig. 8 description.
Referring to Fig. 8, providing device 800 according to a kind of knowledge data of some embodiments of the disclosure includes:
Request module 810, for obtaining inquiry request sentence；
Word segmentation module 820 is requested, is carried out at participle for obtaining the inquiry request sentence that module 810 obtains to request sentence
Reason, obtains at least one query word；
Expansion module 830 is requested, for obtaining each institute got with request module 820 respectively from extension dictionary
State the corresponding expanded keyword of query word, the extension dictionary includes the expanded keyword of multiple queries word and as entity word
Query word classification information；
Request matching module 840, each query word for expansion module 830 will to be requested to get or its is corresponding
The combination of expanded keyword is matched with multiple semantic matches expression formulas respectively, obtains the information of query intention；
Knowledge data obtains module 850, anticipates for obtaining the inquiry matched with request matching module 840 from knowledge base
Scheme corresponding knowledge data；
Knowledge data provides module 860, obtains the knowledge data that module 850 obtains for providing knowledge data.
Wherein, the query intention includes the information of knowledget opic and knowledge attribute, each knowledge in the knowledge base
Data are stored as the triple comprising knowledget opic, knowledge attribute and corresponding knowledge answer.
Optionally, the expanded keyword includes the following word of at least one of query word: synonym, substitution word, mark
Mutatis mutandis word and hypernym.
Knowledge data, which provides device 800, has the beneficial effect realized with any aforementioned knowledge data providing method, herein
It will not go into details.
The embodiment of the present disclosure additionally provides a kind of electronic equipment.Fig. 9 is to show to be set according to the electronics with regard to the embodiment of the present disclosure
Standby 900 structural schematic diagram.The electronic equipment 900 can be such as mobile terminal, personal computer (PC), tablet computer, clothes
Business device etc..
As shown in figure 9, electronic equipment 900 may include memory and processor.Specifically, electronic equipment 900 includes one
A or multiple processors, communication device etc., one or more of processors for example: one or more central processing unit
(CPU) 901, and/or one or more image processor (GPU) 913 etc., processor can be according to being stored in read-only memory
(ROM) it the executable instruction in 902 or is loaded into from storage section 908 executable in random access storage device (RAM) 903
It instructs and executes various movements appropriate and processing.Communication device includes communication component 912 and/or communication interface 909.Wherein,
Communication component 912 may include but be not limited to network interface card, and the network interface card may include but be not limited to IB (Infiniband) network interface card, and communication connects
Mouth 909 includes the communication interface of the network interface cards of LAN card, modem etc., and communication interface 909 is via such as because of spy
The network of net executes communication process.
Processor can with communicate in read-only memory 902 and/or random access storage device 903 to execute executable instruction,
It is connected by communication bus 904 with communication component 912 and is communicated through communication component 912 with other target devices, to completes this
The corresponding operation of any one image processing method that open embodiment provides, for example, obtaining inquiry request sentence；To the inquiry
It requests sentence to carry out word segmentation processing, obtains at least one query word；It is obtained respectively from extension dictionary and each query word pair
The expanded keyword answered, the extension dictionary include the expanded keyword of multiple queries word and the query word as entity word
Classification information；The combination of each query word that will acquire or its corresponding expanded keyword respectively with multiple semantic matches
Expression formula is matched, and the information of query intention is obtained；Knowledge data corresponding with the query intention is obtained from knowledge base；It mentions
For the knowledge data.
In addition, in RAM 903, various programs and data needed for being also stored with device operation.CPU 901 or GPU
913, ROM 902 and RAM 903 is connected with each other by communication bus 904.In the case where there is 903 RAM, ROM 902 is can
Modeling block.RAM 903 stores executable instruction, or executable instruction is written into ROM 902 at runtime, and executable instruction makes
Processor executes the corresponding operation of above-mentioned communication means.Input/output (I/O) interface 905 is also connected to communication bus 904.It is logical
Letter component 912 can integrate setting, may be set to be with multiple submodule (such as multiple IB network interface cards), and in communication bus
It chains.
I/O interface 905 is connected to lower component: the importation 906 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 907 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 908 including hard disk etc.；
And the communication interface 909 of the network interface card including LAN card, modem etc..Driver 910 also connects as needed
It is connected to I/O interface 905.Detachable media 911, such as disk, CD, magneto-optic disk, semiconductor memory etc. are pacified as needed
On driver 910, in order to be mounted into storage section 908 as needed from the computer program read thereon.
It should be noted that framework as shown in Figure 9 is only a kind of optional implementation, it, can root during concrete practice
The component count amount and type of above-mentioned Fig. 9 are selected, are deleted, increased or replaced according to actual needs；It is set in different function component
It sets, separately positioned or integrally disposed and other implementations, such as the separable setting of GPU and CPU or can be by GPU collection can also be used
At on CPU, the separable setting of communication device, can also be integrally disposed on CPU or GPU, etc..These interchangeable embodiment party
Formula each falls within the protection scope of the disclosure.
The electronic equipment of the embodiment of the present disclosure can be used to implement corresponding image processing method in above-described embodiment, the electricity
Each device in sub- equipment can be used for executing each step in above method embodiment, for example, the figure being outlined above
As processing method can be realized by the dependent instruction that the processor of electronic equipment calls memory to store, for sake of simplicity,
This is repeated no more.
According to the embodiment of the present disclosure, a kind of computer program production may be implemented as above with reference to the process of flow chart description
Product.For example, the embodiment of the present disclosure includes a kind of computer program product comprising be tangibly embodied on machine readable media
Computer program, computer program include the program code for method shown in execution flow chart, and program code may include pair
The corresponding instruction of method and step of embodiment of the present disclosure offer should be executed, for example, the instruction for obtaining inquiry request sentence；With
In carrying out word segmentation processing to the inquiry request sentence, the instruction of at least one query word is obtained；For distinguishing from extension dictionary
The instruction of expanded keyword corresponding with each query word is obtained, the extension dictionary includes the extension pass of multiple queries word
The classification information of keyword and the query word as entity word；Each query word or its corresponding expansion for will acquire
It opens up crucial contamination to be matched with multiple semantic matches expression formulas respectively, obtains the instruction of the information of query intention；For
The instruction of knowledge data corresponding with the query intention is obtained from knowledge base；It is used to provide the described the instruction of knowledge data.?
In such embodiment, which can be downloaded and installed from network by communication device, and/or from detachable
Medium 911 is mounted.When the computer program is executed by processor, function disclosed in the method for the embodiment of the present disclosure is executed
Energy.
Disclosed method and device, electronic equipment and storage medium may be achieved in many ways.For example, can pass through
Software, hardware, firmware or software, hardware, firmware any combination realize method and apparatus, the electronics of the embodiment of the present disclosure
Equipment and storage medium.The said sequence of the step of for method merely to be illustrated, the method for the embodiment of the present disclosure
Step is not limited to sequence described in detail above, unless specifically stated otherwise.In addition, in some embodiments, may be used also
The disclosure is embodied as to record program in the recording medium, these programs include for realizing according to the side of the embodiment of the present disclosure
The machine readable instructions of method.Thus, the disclosure also covers program of the storage for executing the method according to the embodiment of the present disclosure
Recording medium.
The description of the embodiment of the present disclosure is given for the purpose of illustration and description, and is not exhaustively or to incite somebody to action
The disclosure is limited to disclosed form, and many modifications and variations are obvious for the ordinary skill in the art.Choosing
Selecting and describe embodiment is the principle and practical application in order to more preferably illustrate the disclosure, and makes those skilled in the art
It will be appreciated that the disclosure is to design various embodiments suitable for specific applications with various modifications.
Claims (11)
1. a kind of knowledge data providing method, comprising:
Obtain inquiry request sentence；
Word segmentation processing is carried out to the inquiry request sentence, obtains at least one query word；
Obtain expanded keyword corresponding with each query word respectively from extension dictionary, the extension dictionary includes multiple looks into
Ask the expanded keyword of word and the classification information of the query word as entity word；
The combination of each query word that will acquire or its corresponding expanded keyword is expressed with multiple semantic matches respectively
Formula is matched, and the information of query intention is obtained；
Knowledge data corresponding with the query intention is obtained from knowledge base；
The knowledge data is provided.
2. the method according to claim 1, wherein the query intention includes knowledget opic and knowledge attribute
Information.
3. according to the method described in claim 2, it is characterized in that, each knowledge data in the knowledge base be stored as include
The triple of knowledget opic, knowledge attribute and corresponding knowledge answer.
4. the method according to claim 1, wherein the expanded keyword include query word it is at least one with
Lower word: synonym, substitution word, standard words and hypernym.
5. the method according to claim 1, wherein the semantic matches expression formula includes individually being used as entity word
The first matching keywords or single entity object type information, and inquiry corresponding with the semantic matches expression formula anticipate
The information of figure includes the default of knowledget opic corresponding with the matching keywords or entity object classification and the knowledget opic
The information of attribute.
6. according to the method described in claim 5, it is characterized in that, the semantic matches expression formula further include at least one second
Matching keywords, and the information of query intention corresponding with the semantic matches expression formula include with the matching keywords or
The letter of the corresponding knowledget opic of entity object classification and knowledge attribute corresponding at least one described second matching keywords
Breath.
7. a kind of knowledge data provides device, comprising:
Request module, for obtaining inquiry request sentence；
Word segmentation module is requested, word segmentation processing is carried out for obtaining the inquiry request sentence that module obtains to the request sentence, obtains
Take at least one query word；
Expansion module is requested, for obtaining each inquiry got with the request module respectively from extension dictionary
The corresponding expanded keyword of word, the extension dictionary include the expanded keyword of multiple queries word and the inquiry as entity word
The classification information of word；
Matching module is requested, each query word or its corresponding extension for getting the request expansion module close
Key contamination is matched with multiple semantic matches expression formulas respectively, obtains the information of query intention；
Knowledge data obtains module, for corresponding from the query intention that knowledge base is obtained with the request matching module matches
Knowledge data；
Knowledge data provides module, is used to provide the described knowledge data and obtains the knowledge data that module obtains.
8. device according to claim 7, which is characterized in that the query intention includes knowledget opic and knowledge attribute
Information, each knowledge data in the knowledge base are stored as comprising knowledget opic, knowledge attribute and corresponding knowledge answer
Triple.
9. method according to claim 7 or 8, which is characterized in that the expanded keyword includes at least the one of query word
Kind or less word: synonym, substitution word, standard words and hypernym.
10. a kind of electronic equipment characterized by comprising processor and memory；
The memory makes the processor execute such as right for storing at least one executable instruction, the executable instruction
It is required that described in any one of 1~6 the step of knowledge data providing method.
11. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has executable finger
It enables, the executable instruction makes the processor execute such as knowledge data providing method according to any one of claims 1 to 6
The step of.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811613073.2A CN109739964A (en) | 2018-12-27 | 2018-12-27 | Knowledge data providing method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811613073.2A CN109739964A (en) | 2018-12-27 | 2018-12-27 | Knowledge data providing method, device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109739964A true CN109739964A (en) | 2019-05-10 |
Family
ID=66360203
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811613073.2A Pending CN109739964A (en) | 2018-12-27 | 2018-12-27 | Knowledge data providing method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109739964A (en) |
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110263180A (en) * | 2019-06-13 | 2019-09-20 | 北京百度网讯科技有限公司 | It is intended to knowledge mapping generation method, intension recognizing method and device |
| CN110347816A (en) * | 2019-07-15 | 2019-10-18 | 腾讯科技（上海）有限公司 | A kind of information recommendation method and device |
| CN110502616A (en) * | 2019-08-29 | 2019-11-26 | 上海墨百意信息科技有限公司 | A kind of method, equipment and the computer storage medium of determining garbage classification |
| CN110543546A (en) * | 2019-07-18 | 2019-12-06 | 华瑞新智科技（北京）有限公司 | Method and device for inquiring hidden danger problems in industrial equipment |
| CN110784768A (en) * | 2019-10-17 | 2020-02-11 | 珠海格力电器股份有限公司 | Multimedia resource playing method, storage medium and electronic equipment |
| CN110795528A (en) * | 2019-09-05 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Data query method and device, electronic equipment and storage medium |
| CN111090739A (en) * | 2019-10-30 | 2020-05-01 | 贝壳技术有限公司 | Information processing method, information processing device, electronic device, and storage medium |
| CN111104803A (en) * | 2019-12-31 | 2020-05-05 | 科大讯飞股份有限公司 | Semantic understanding processing method, device and equipment and readable storage medium |
| CN111160041A (en) * | 2019-12-30 | 2020-05-15 | 科大讯飞股份有限公司 | Semantic understanding method and device, electronic equipment and storage medium |
| CN111159546A (en) * | 2019-12-24 | 2020-05-15 | 腾讯科技（深圳）有限公司 | Event pushing method and device, computer readable storage medium and computer equipment |
| CN111221943A (en) * | 2020-01-13 | 2020-06-02 | 口口相传(北京)网络技术有限公司 | Query result matching degree calculation method and device |
| CN111309827A (en) * | 2020-03-23 | 2020-06-19 | 平安医疗健康管理股份有限公司 | Knowledge graph construction method and device, computer system and readable storage medium |
| CN111324720A (en) * | 2020-03-04 | 2020-06-23 | 万贝科技集团有限公司 | Natural language processing method based on annular matching |
| CN111339239A (en) * | 2019-06-13 | 2020-06-26 | 海通证券股份有限公司 | Knowledge retrieval method and device, storage medium and server |
| CN111552792A (en) * | 2020-04-30 | 2020-08-18 | 中国建设银行股份有限公司 | Information query method and device, electronic equipment and storage medium |
| CN111752922A (en) * | 2020-06-28 | 2020-10-09 | 中国银行股份有限公司 | Method and device for establishing knowledge database and realizing knowledge query |
| CN111897947A (en) * | 2020-07-30 | 2020-11-06 | 杭州橙鹰数据技术有限公司 | Data analysis processing method and device based on open source information |
| CN112015919A (en) * | 2020-09-15 | 2020-12-01 | 重庆广播电视大学重庆工商职业学院 | Dialogue management method based on learning auxiliary knowledge graph |
| CN112035680A (en) * | 2020-09-15 | 2020-12-04 | 重庆广播电视大学重庆工商职业学院 | Knowledge graph construction method of intelligent auxiliary learning machine |
| CN112102840A (en) * | 2020-09-09 | 2020-12-18 | 中移（杭州）信息技术有限公司 | Semantic recognition method, device, terminal and storage medium |
| CN112100343A (en) * | 2020-08-17 | 2020-12-18 | 深圳数联天下智能科技有限公司 | Method for expanding knowledge graph, electronic equipment and storage medium |
| CN112133145A (en) * | 2020-04-20 | 2020-12-25 | 陈彦艳 | Receptive type combined discovery type multidisciplinary applied thinking cognition teaching system |
| CN112307171A (en) * | 2020-10-30 | 2021-02-02 | 中国电力科学研究院有限公司 | Institutional standard retrieval method and system based on power knowledge base and readable storage medium |
| CN112463932A (en) * | 2020-12-14 | 2021-03-09 | 北京明略软件系统有限公司 | Method, device and equipment for information query |
| WO2021047169A1 (en) * | 2019-09-12 | 2021-03-18 | 竹间智能科技（上海）有限公司 | Information query method and apparatus, storage medium, and smart terminal |
| CN112667781A (en) * | 2020-12-31 | 2021-04-16 | 北京万方数据股份有限公司 | Malignant tumor document acquisition method and device |
| CN113032677A (en) * | 2021-04-01 | 2021-06-25 | 李旻达 | Query information processing method and device based on artificial intelligence |
| CN113111155A (en) * | 2020-01-10 | 2021-07-13 | 阿里巴巴集团控股有限公司 | Information display method, device, equipment and storage medium |
| CN113672699A (en) * | 2021-08-12 | 2021-11-19 | 国家电网有限公司大数据中心 | Knowledge graph-based NL2SQL generation method |
| CN114548100A (en) * | 2022-03-01 | 2022-05-27 | 深圳市医未医疗科技有限公司 | Clinical scientific research auxiliary method and system based on big data technology |
| CN114610860A (en) * | 2022-05-07 | 2022-06-10 | 荣耀终端有限公司 | Question answering method and system |
| CN114860872A (en) * | 2022-04-13 | 2022-08-05 | 北京百度网讯科技有限公司 | Data processing method, device, equipment and storage medium |
| CN116501841A (en) * | 2023-06-26 | 2023-07-28 | 深圳市唯特视科技有限公司 | Fuzzy query method, system and storage medium for data model |
| CN112102840B (en) * | 2020-09-09 | 2024-05-03 | 中移（杭州）信息技术有限公司 | Semantic recognition method, semantic recognition device, terminal and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8190595B2 (en) * | 2009-03-28 | 2012-05-29 | Microsoft Corporation | Flexible query hints in a relational database |
| CN103838833A (en) * | 2014-02-24 | 2014-06-04 | 华中师范大学 | Full-text retrieval system based on semantic analysis of relevant words |
| CN105653576A (en) * | 2015-12-16 | 2016-06-08 | 上海智臻智能网络科技股份有限公司 | Information searching method and apparatus, manual position service method and system |
| CN107741976A (en) * | 2017-10-16 | 2018-02-27 | 泰康保险集团股份有限公司 | Intelligent response method, apparatus, medium and electronic equipment |
| CN107885874A (en) * | 2017-11-28 | 2018-04-06 | 上海智臻智能网络科技股份有限公司 | Data query method and apparatus, computer equipment and computer-readable recording medium |
-
2018
- 2018-12-27 CN CN201811613073.2A patent/CN109739964A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8190595B2 (en) * | 2009-03-28 | 2012-05-29 | Microsoft Corporation | Flexible query hints in a relational database |
| CN103838833A (en) * | 2014-02-24 | 2014-06-04 | 华中师范大学 | Full-text retrieval system based on semantic analysis of relevant words |
| CN105653576A (en) * | 2015-12-16 | 2016-06-08 | 上海智臻智能网络科技股份有限公司 | Information searching method and apparatus, manual position service method and system |
| CN107741976A (en) * | 2017-10-16 | 2018-02-27 | 泰康保险集团股份有限公司 | Intelligent response method, apparatus, medium and electronic equipment |
| CN107885874A (en) * | 2017-11-28 | 2018-04-06 | 上海智臻智能网络科技股份有限公司 | Data query method and apparatus, computer equipment and computer-readable recording medium |
Cited By (47)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110263180B (en) * | 2019-06-13 | 2021-06-04 | 北京百度网讯科技有限公司 | Intention knowledge graph generation method, intention identification method and device |
| CN110263180A (en) * | 2019-06-13 | 2019-09-20 | 北京百度网讯科技有限公司 | It is intended to knowledge mapping generation method, intension recognizing method and device |
| CN111339239A (en) * | 2019-06-13 | 2020-06-26 | 海通证券股份有限公司 | Knowledge retrieval method and device, storage medium and server |
| CN110347816A (en) * | 2019-07-15 | 2019-10-18 | 腾讯科技（上海）有限公司 | A kind of information recommendation method and device |
| CN110347816B (en) * | 2019-07-15 | 2023-08-04 | 腾讯科技（上海）有限公司 | Information recommendation method and device |
| CN110543546A (en) * | 2019-07-18 | 2019-12-06 | 华瑞新智科技（北京）有限公司 | Method and device for inquiring hidden danger problems in industrial equipment |
| CN110543546B (en) * | 2019-07-18 | 2022-03-22 | 华瑞新智科技（北京）有限公司 | Method and device for inquiring hidden danger problems in industrial equipment |
| CN110502616A (en) * | 2019-08-29 | 2019-11-26 | 上海墨百意信息科技有限公司 | A kind of method, equipment and the computer storage medium of determining garbage classification |
| CN110795528A (en) * | 2019-09-05 | 2020-02-14 | 腾讯科技（深圳）有限公司 | Data query method and device, electronic equipment and storage medium |
| CN110795528B (en) * | 2019-09-05 | 2023-10-13 | 腾讯科技（深圳）有限公司 | Data query method and device, electronic equipment and storage medium |
| WO2021047169A1 (en) * | 2019-09-12 | 2021-03-18 | 竹间智能科技（上海）有限公司 | Information query method and apparatus, storage medium, and smart terminal |
| CN110784768A (en) * | 2019-10-17 | 2020-02-11 | 珠海格力电器股份有限公司 | Multimedia resource playing method, storage medium and electronic equipment |
| CN111090739A (en) * | 2019-10-30 | 2020-05-01 | 贝壳技术有限公司 | Information processing method, information processing device, electronic device, and storage medium |
| CN111159546B (en) * | 2019-12-24 | 2023-10-24 | 深圳市雅阅科技有限公司 | Event pushing method, event pushing device, computer readable storage medium and computer equipment |
| CN111159546A (en) * | 2019-12-24 | 2020-05-15 | 腾讯科技（深圳）有限公司 | Event pushing method and device, computer readable storage medium and computer equipment |
| CN111160041A (en) * | 2019-12-30 | 2020-05-15 | 科大讯飞股份有限公司 | Semantic understanding method and device, electronic equipment and storage medium |
| CN111160041B (en) * | 2019-12-30 | 2024-02-13 | 科大讯飞股份有限公司 | Semantic understanding method and device, electronic equipment and storage medium |
| CN111104803A (en) * | 2019-12-31 | 2020-05-05 | 科大讯飞股份有限公司 | Semantic understanding processing method, device and equipment and readable storage medium |
| CN111104803B (en) * | 2019-12-31 | 2024-02-13 | 科大讯飞股份有限公司 | Semantic understanding processing method, device, equipment and readable storage medium |
| CN113111155A (en) * | 2020-01-10 | 2021-07-13 | 阿里巴巴集团控股有限公司 | Information display method, device, equipment and storage medium |
| CN113111155B (en) * | 2020-01-10 | 2024-04-19 | 阿里巴巴集团控股有限公司 | Information display method, device, equipment and storage medium |
| CN111221943B (en) * | 2020-01-13 | 2023-08-08 | 口口相传(北京)网络技术有限公司 | Query result matching degree calculation method and device |
| CN111221943A (en) * | 2020-01-13 | 2020-06-02 | 口口相传(北京)网络技术有限公司 | Query result matching degree calculation method and device |
| CN111324720A (en) * | 2020-03-04 | 2020-06-23 | 万贝科技集团有限公司 | Natural language processing method based on annular matching |
| CN111309827A (en) * | 2020-03-23 | 2020-06-19 | 平安医疗健康管理股份有限公司 | Knowledge graph construction method and device, computer system and readable storage medium |
| CN112133145A (en) * | 2020-04-20 | 2020-12-25 | 陈彦艳 | Receptive type combined discovery type multidisciplinary applied thinking cognition teaching system |
| CN111552792A (en) * | 2020-04-30 | 2020-08-18 | 中国建设银行股份有限公司 | Information query method and device, electronic equipment and storage medium |
| CN111552792B (en) * | 2020-04-30 | 2023-11-21 | 中国建设银行股份有限公司 | Information query method and device, electronic equipment and storage medium |
| CN111752922A (en) * | 2020-06-28 | 2020-10-09 | 中国银行股份有限公司 | Method and device for establishing knowledge database and realizing knowledge query |
| CN111897947A (en) * | 2020-07-30 | 2020-11-06 | 杭州橙鹰数据技术有限公司 | Data analysis processing method and device based on open source information |
| CN112100343A (en) * | 2020-08-17 | 2020-12-18 | 深圳数联天下智能科技有限公司 | Method for expanding knowledge graph, electronic equipment and storage medium |
| CN112102840B (en) * | 2020-09-09 | 2024-05-03 | 中移（杭州）信息技术有限公司 | Semantic recognition method, semantic recognition device, terminal and storage medium |
| CN112102840A (en) * | 2020-09-09 | 2020-12-18 | 中移（杭州）信息技术有限公司 | Semantic recognition method, device, terminal and storage medium |
| CN112035680A (en) * | 2020-09-15 | 2020-12-04 | 重庆广播电视大学重庆工商职业学院 | Knowledge graph construction method of intelligent auxiliary learning machine |
| CN112015919A (en) * | 2020-09-15 | 2020-12-01 | 重庆广播电视大学重庆工商职业学院 | Dialogue management method based on learning auxiliary knowledge graph |
| CN112307171A (en) * | 2020-10-30 | 2021-02-02 | 中国电力科学研究院有限公司 | Institutional standard retrieval method and system based on power knowledge base and readable storage medium |
| CN112307171B (en) * | 2020-10-30 | 2022-02-11 | 中国电力科学研究院有限公司 | Institutional standard retrieval method and system based on power knowledge base and readable storage medium |
| CN112463932A (en) * | 2020-12-14 | 2021-03-09 | 北京明略软件系统有限公司 | Method, device and equipment for information query |
| CN112667781A (en) * | 2020-12-31 | 2021-04-16 | 北京万方数据股份有限公司 | Malignant tumor document acquisition method and device |
| CN113032677A (en) * | 2021-04-01 | 2021-06-25 | 李旻达 | Query information processing method and device based on artificial intelligence |
| CN113672699A (en) * | 2021-08-12 | 2021-11-19 | 国家电网有限公司大数据中心 | Knowledge graph-based NL2SQL generation method |
| CN114548100A (en) * | 2022-03-01 | 2022-05-27 | 深圳市医未医疗科技有限公司 | Clinical scientific research auxiliary method and system based on big data technology |
| CN114860872A (en) * | 2022-04-13 | 2022-08-05 | 北京百度网讯科技有限公司 | Data processing method, device, equipment and storage medium |
| CN114610860B (en) * | 2022-05-07 | 2022-09-27 | 荣耀终端有限公司 | Question answering method and system |
| CN114610860A (en) * | 2022-05-07 | 2022-06-10 | 荣耀终端有限公司 | Question answering method and system |
| CN116501841A (en) * | 2023-06-26 | 2023-07-28 | 深圳市唯特视科技有限公司 | Fuzzy query method, system and storage medium for data model |
| CN116501841B (en) * | 2023-06-26 | 2023-09-08 | 深圳市唯特视科技有限公司 | Fuzzy query method, system and storage medium for data model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109739964A (en) | Knowledge data providing method, device, electronic equipment and storage medium | |
| US10169454B2 (en) | Unsupervised ontology-based graph extraction from texts | |
| El-Kishky et al. | Scalable topical phrase mining from text corpora | |
| Shutova et al. | Statistical metaphor processing | |
| Chan et al. | A text-based decision support system for financial sequence prediction | |
| WO2021139229A1 (en) | Text rhetorical sentence generation method, apparatus and device, and readable storage medium | |
| CN110222045A (en) | A kind of data sheet acquisition methods, device and computer equipment, storage medium | |
| CN112559684A (en) | Keyword extraction and information retrieval method | |
| US11886815B2 (en) | Self-supervised document representation learning | |
| Rodrigues et al. | Advanced applications of natural language processing for performing information extraction | |
| CN111046272A (en) | Intelligent question-answering system based on medical knowledge map | |
| CN112989208A (en) | Information recommendation method and device, electronic equipment and storage medium | |
| Bella et al. | Domain-based sense disambiguation in multilingual structured data | |
| CN116383430A (en) | Knowledge graph construction method, device, equipment and storage medium | |
| Liebeskind et al. | Semiautomatic construction of cross-period thesaurus | |
| CN112800244B (en) | Method for constructing knowledge graph of traditional Chinese medicine and national medicine | |
| Kokane et al. | Supervised word sense disambiguation with recurrent neural network model | |
| Rao et al. | Enhancing multi-document summarization using concepts | |
| Varma et al. | IIIT Hyderabad in Guided Summarization and Knowledge Base Population. | |
| RK Rao et al. | Patent document summarization using conceptual graphs | |
| Dung et al. | Ontology-based information extraction and information retrieval in health care domain | |
| CN117435714B (en) | Knowledge graph-based database and middleware problem intelligent diagnosis system | |
| Batyrshin et al. | Advances in Computational Intelligence | |
| Srikumar | The semantics of role labeling | |
| Ning | Research on the extraction of accounting multi-relationship information based on cloud computing and multimedia |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190510 |
|
| RJ01 | Rejection of invention patent application after publication |