CN107704559A - A kind of semantic understanding method and device - Google Patents
A kind of semantic understanding method and device Download PDFInfo
- Publication number
- CN107704559A CN107704559A CN201710905504.1A CN201710905504A CN107704559A CN 107704559 A CN107704559 A CN 107704559A CN 201710905504 A CN201710905504 A CN 201710905504A CN 107704559 A CN107704559 A CN 107704559A
- Authority
- CN
- China
- Prior art keywords
- semantic
- text
- net
- range difference
- received
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 241000270322 Lepidosauria Species 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 239000000463 material Substances 0.000 description 6
- 235000012054 meals Nutrition 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 239000008267 milk Substances 0.000 description 3
- 210000004080 milk Anatomy 0.000 description 3
- 235000013336 milk Nutrition 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000001149 cognitive effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241001365789 Oenanthe crocata Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Abstract
The invention discloses a kind of semantic understanding method and device, methods described includes：Semantic text to be analyzed is obtained, based on the semantic net of image schema structure semantic text, obtains the range difference of the vector space of each received text in the vector space and ontology database of semantic net, and received text corresponding with semantic text is determined according to range difference.Scheme provided in an embodiment of the present invention, without prestoring a variety of expression-forms for same semanteme, and also without being the different template of different scene configurations in advance, semantic understanding efficiency high.
Description
Technical field
The present invention relates to smart city technical field, more particularly to a kind of semantic understanding method and device.
Background technology
The construction of smart city be unable to do without man-machine deep interaction, the support of more too busy to get away semantic understanding system.Wisdom city
The wisdom of city's application proposes higher requirement to semantic understanding.
Semantic understanding method common at present mainly has two kinds, and a kind of is the statistical method understood based on people, specifically, in advance
First count and store same semantic a variety of sayings, when with semantic text to be analyzed, by semantic text with depositing in advance
A variety of sayings of storage are compared, to determine the true semanteme expressed by semantic text to be analyzed；Another method is based on mould
Plate gauge then configures realization, specifically,, will when with semantic text to be analyzed for the different template of different scene settings
Semantic text and each template matches, until be determined for compliance with the template of the semantic text, and determined according to the template of determination to be analyzed
Semantic text expressed by true semanteme.For example, semantic text to be analyzed is " I will buy the train ticket in Changsha ", configuration
Scene template can be that first word is subject, interval " buying " is action, and the 5th word start generally " destination " place name
Deng, when semantic text to be analyzed and after each template matches, it is determined that with above-mentioned scene template matches, so can determine that to be analyzed
Semantic text expressed true semanteme be train ticket that purchase destination is Changsha.
To the discovery of the research process of prior art, the first semantic understanding method needs to prestore a variety of inventor
Saying, yet with region and the difference of habits and customs, it is impossible to accomplish all sayings of an exhaustive meaning, so, the language
The degree of accuracy of adopted understanding method is relatively low；And second of semantic understanding method, it is necessary to be in advance the different mould of different scene configurations
Plate, semantic understanding are less efficient.
The content of the invention
In order to solve the above technical problems, the embodiments of the invention provide a kind of method and device, to solve in the prior art
The problem of online programming time is long, technical scheme is as follows：
A kind of semantic understanding method, including：
Obtain semantic text to be analyzed；
The semantic net of the semantic text is built based on purpose schema；
Obtain the range difference of the vector space of each received text in the vector space and ontology database of the semantic net；
Received text corresponding with the semantic text is determined according to the range difference.
It is preferably based on before the semantic net that purpose figure builds the semantic text, in addition to：
According to the definition rule in the ontology database to single body, the semantic text is segmented, to obtain
Obtain multiple semantic Ziwen sheets；
The part of speech of the multiple semantic Ziwen sheet is marked respectively；
Correspondingly, the semantic net of the semantic text is built based on purpose figure, including：
According to the multiple semantic Ziwen sheet and the part of speech, the semantic net based on the purpose figure structure semantic text.
Preferably, received text corresponding with the semantic text is determined according to the range difference, including：
Determine that minimum range is poor from the range difference；
Will received text corresponding with the minimum range difference as received text corresponding with the semantic text.
Preferably, in addition to：
Export answer corresponding with the received text determined.
Preferably, in addition to：
Beforehand through the automatic reptile on network node text message is captured from each website；
The text message is converted to the body for meeting the definition rule；
The body is stored into the ontology database.
A kind of semantic understanding device, including：
Obtain semantic text to be analyzed；
The semantic net of the semantic text is built based on purpose schema；
Obtain the range difference of the vector space of each received text in the vector space and ontology database of the semantic net；
Received text corresponding with the semantic text is determined according to the range difference.
It is preferably based on before the semantic net that purpose figure builds the semantic text, in addition to：
According to the definition rule in the ontology database to single body, the semantic text is segmented, to obtain
Obtain multiple semantic Ziwen sheets；
The part of speech of the multiple semantic Ziwen sheet is marked respectively；
Correspondingly, the semantic net of the semantic text is built based on purpose figure, including：
According to the multiple semantic Ziwen sheet and the part of speech, the semantic net based on the purpose figure structure semantic text.
Preferably, received text corresponding with the semantic text is determined according to the range difference, including：
Determine that minimum range is poor from the range difference；
Will received text corresponding with the minimum range difference as received text corresponding with the semantic text.
Preferably, in addition to：
Export answer corresponding with the received text determined.
Preferably, in addition to：
Beforehand through the automatic reptile on network node text message is captured from each website；
The text message is converted to the body for meeting the definition rule；
The body is stored into the ontology database.
Technical scheme provided in an embodiment of the present invention, semantic text to be analyzed is obtained, built based on image schema semantic
The semantic net of text, obtain the distance of the vector space of each received text in the vector space and ontology database of semantic net
Difference, and received text corresponding with semantic text is determined according to range difference.Scheme provided in an embodiment of the present invention, without for same
One semanteme prestores a variety of expression-forms, and also without being the different template of different scene configurations in advance, semantic understanding
Efficiency high.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, without having to pay creative labor, may be used also
To obtain other accompanying drawings according to these accompanying drawings.
A kind of a kind of schematic flow sheet for semantic understanding method that Fig. 1 is provided by the embodiment of the present invention；
A kind of another schematic flow sheet for semantic understanding method that Fig. 2 is provided by the embodiment of the present invention；
A kind of a kind of structural representation for semantic understanding device that Fig. 3 is provided by the embodiment of the present invention；
A kind of another structural representation for semantic understanding device that Fig. 4 is provided by the embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.Based on this
Embodiment in invention, the every other reality that those of ordinary skill in the art are obtained under the premise of creative work is not made
Example is applied, belongs to the scope of protection of the invention.
Referring to Fig. 1, Fig. 1 is a kind of a kind of implementation process figure of semantic understanding method provided in an embodiment of the present invention, institute
The method of stating includes：
Step S101, semantic text to be analyzed is obtained；
The form of the semantic text to be analyzed can be speech text, or writing text, can also be voice
The combination of text and writing text, in addition, according to the needs of practical application, the form of semantic text is not limited in above-mentioned three kinds
Form.
Step S102, the semantic net of the semantic text is built based on image schema；
Image schema is in order to which space structure is mapped to concept structure retouching again in face of the compressibility of perceptual experience progress
Write.
Image schema illustrated below：
1) we come university from family.
2) the long train of row length is seen, from first segment compartment to last one section.
3) a drop water is rolled on ground from desktop.
4) exquisiteness is flown to from Hong Kong.
5) highway connects Beijing and Shanghai.
Although the activity that model sentence represents has dynamic having static state, seeming actual between unrelated activity has
Something in common, specifically, there are a stock, or starting point, along a path incoming terminal, i.e., all follow " stock-road
Pattern as footpath-terminal ", therefore, model sentence constitute an image schema, referred to as path schema.
And for example：
A I one bottle of milk is taken out in refrigerator.
B I milk is exported in feeding bottle.
C I milk poured into teacup.
Money is put into pocket to d by I, walks out bank, creeps into car.
Above example sentence is all and " container " is relevant, and money has been put into pocket this " container " by I, and having walked out bank, this " holds
Device ", once again into another " container " car, by the experience of " container " many times, the purpose schema of formation one " container ".
It is the register expression-form of image schema used by the embodiment of the present invention, register is a kind of cognitive context, uses it
To show semantic unit feature or describe concept characteristic.For example, when defining " finger ", it is necessary to refer to " hand ", define
When " hand ", it is necessary to refer to " arm ", therefore, " hand " is the register of " finger "；" arm " is the register of " hand ", finally,
" space ", " time " and " motion " is the register of " body ", because " body " existed and moved in time and space.Therefore,
The semantic net of semantic text can be built according to the register expression-form of image schema.
Wherein, semantic net is a kind of preferable network structure, to words of description and the correlation of concept, in semantic net
With multiple network nodes, the semanteme represented by the network path that different network nodes is formed is different.
Step S103, the vector space of each received text in the vector space and ontology database of the semantic net is obtained
Range difference；
There is various semantic standard expression-forms in ontology database, such as " you have had a meal " this standard text
This, the semantic text to be analyzed corresponding to it can have a variety of, " you eaten " such as " eaten ", according to dialect and life
The expression-form of the difference of custom living, semantic text to be analyzed and received text varies.
It should be noted that even if the text to be analyzed of expression " you have had a meal " semanteme differs a lot of with received text,
The range difference of the space vector of text and received text so to be analyzed is still less than the text to be analyzed and other standards text
Space vector range difference, the other standards text expressed from received text it is semantic different, for example, other standards text can
Think " I goes to Beijing by train ".
After the semantic net of semantic text to be analyzed has been built, the space vector and ontology data of the semantic net are obtained
The space vector of semantic net in storehouse corresponding to each received text, and obtain the range difference of two spaces vector.
Step S104, received text corresponding with the semantic text is determined according to the range difference.
Technical scheme provided in an embodiment of the present invention, semantic text to be analyzed is obtained, built based on image schema semantic
The semantic net of text, obtain the distance of the vector space of each received text in the vector space and ontology database of semantic net
Difference, and received text corresponding with semantic text is determined according to range difference.Scheme provided in an embodiment of the present invention, without for same
One semanteme prestores a variety of expression-forms, and also without being the different template of different scene configurations in advance, semantic understanding
Efficiency high.
Referring to Fig. 2, Fig. 2 is a kind of another implementation process figure of semantic understanding method provided in an embodiment of the present invention,
Methods described includes：
Step S201, semantic text to be analyzed is obtained；
The form of the semantic text to be analyzed can be speech text, or writing text, can also be voice
The combination of text and writing text, in addition, according to the needs of practical application, the form of semantic text is not limited in above-mentioned three kinds
Form.
Step S202, according to the definition rule in the ontology database to single body, the semantic text is carried out
Participle, to obtain multiple semantic Ziwen sheets；
Ziwen sheet obtained by after generally being segmented to semantic text is nature word, wherein, the knot after time sentence segments naturally
Fruit, such as " I will buy the train ticket in Changsha ", the natural word after participle is, I, to buy, go, Changsha, train, ticket totally eight
Individual natural word.
But in ontology database, train ticket belongs to single body, be integral into word, rather than take apart it is fixed respectively
Justice, so, when being segmented to semantic text to be analyzed, it is impossible to which the regular partition according to division nature word is to be analyzed
Semantic text, and should be drawn according to the definition rule in ontology database to single body and semantic text to be analyzed is divided
Word operates, and e.g., the train ticket in Changsha is bought for me ", multiple semantic Ziwens after participle are originally, I, to buy, go, be long
It is husky, train ticket.
Step S203, the part of speech of the multiple semantic Ziwen sheet is marked respectively；
Part of speech in the present embodiment refers to the attributes such as verb, noun or the adjective of semantic Ziwen sheet, such as language
Foster son's text " I, to buy, go, Changsha, train ticket ", " I " is pronoun, " will " be adverbial word, " buy, go " is verb, " long
Husky, train ticket " is noun, " " it is adjective.
After treating analysis semantic text and carrying out participle operation, the sub- text marking word of multiple semantemes is obtained to participle operation
Property.
Step S204, according to the multiple semantic Ziwen sheet and the part of speech, the semantic text is built based on purpose figure
Semantic net；
It is the register expression-form of image schema used by the embodiment of the present invention, register is a kind of cognitive context, uses it
To show semantic unit feature or describe concept characteristic.For example, when defining " finger ", it is necessary to refer to " hand ", define
When " hand ", it is necessary to refer to " arm ", therefore, " hand " is the register of " finger "；" arm " is the register of " hand ", finally,
" space ", " time " and " motion " is the register of " body ", because " body " existed and moved in time and space.Therefore,
The semantic net of semantic text can be built according to the register expression-form of image schema.
Wherein, semantic net is a kind of preferable network structure, to words of description and the correlation of concept, in semantic net
With multiple network nodes, the semanteme represented by the network path that different network nodes is formed is different.
There are multiple nodes, the embodiment of the present invention is determined by the part of speech of multiple semantic Ziwen sheets and Ziwen sheet in semantic net
Multiple nodes in semantic net, and further build semantic net.
Step S205, the vector space of each received text in the vector space and ontology database of the semantic net is obtained
Range difference；
Body in ontology database is properly termed as idiom material again, and the idiom material is by raw language material, according to ontology database
In definition rule conversion get
Wherein, body includes single body and received text, and single body refers to may be constructed the single body of sentence,
And received text then refers to the sentence being made up of single body.
Wherein, raw language material refers to the text message captured beforehand through the automatic reptile on network node from each website,
After the text message of crawl to be converted to the text for meeting the definition rule, you can idiom material corresponding to acquisition, afterwards will be ripe
Language material is stored into ontology database, you can obtains the body in ontology database.
Step S206, determine that minimum range is poor from the range difference；
Step S207, will received text corresponding with the minimum range difference as standard corresponding with the semantic text
Text；
There is various semantic standard expression-forms in ontology database, such as " you have had a meal " this standard text
This, the semantic text to be analyzed corresponding to it can have a variety of, " you eaten " such as " eaten ", according to dialect and life
The expression-form of the difference of custom living, semantic text to be analyzed and received text varies.
It should be noted that even if the text to be analyzed of expression " you have had a meal " semanteme differs a lot of with received text,
The range difference of the space vector of text and received text so to be analyzed is still less than the text to be analyzed and other standards text
Space vector range difference, the other standards text expressed from received text it is semantic different, for example, other standards text can
Think " I goes to Beijing by train ".
After the semantic net of semantic text to be analyzed has been built, the space vector and ontology data of the semantic net are obtained
The space vector of semantic net in storehouse corresponding to each received text, and obtain the range difference of two spaces vector.
It can be determined and the immediate received text of semantic text to be analyzed according to the minimum range difference of space vector.
Step S208, output answer corresponding with the received text determined.
When it is determined that after received text immediate with text to be analyzed, being exported according to the received text of determination to user
Answer.
Technical scheme provided in an embodiment of the present invention, semantic text to be analyzed is obtained, built based on image schema semantic
The semantic net of text, obtain the distance of the vector space of each received text in the vector space and ontology database of semantic net
Difference, and received text corresponding with semantic text is determined according to range difference.Scheme provided in an embodiment of the present invention, without for same
One semanteme prestores a variety of expression-forms, and also without being the different template of different scene configurations in advance, semantic understanding
Efficiency high.
Referring to Fig. 3, Fig. 3 is a kind of structural representation of semantic understanding device provided in an embodiment of the present invention, the device
The implementation procedure of method, the device include in embodiment corresponding to the course of work reference picture 1 of each unit in structural representation：
First acquisition unit 310, for obtaining semantic text to be analyzed；
Construction unit 320, for building the semantic net of the semantic text based on purpose schema；
Second acquisition unit 330, each standard text in the vector space and ontology database for obtaining the semantic net
The range difference of this vector space；
Determining unit 340, received text corresponding with the semantic text is determined according to the range difference with language.
Technical scheme provided in an embodiment of the present invention, semantic text to be analyzed is obtained, built based on image schema semantic
The semantic net of text, obtain the distance of the vector space of each received text in the vector space and ontology database of semantic net
Difference, and received text corresponding with semantic text is determined according to range difference.Scheme provided in an embodiment of the present invention, without for same
One semanteme prestores a variety of expression-forms, and also without being the different template of different scene configurations in advance, semantic understanding
Efficiency high.
Referring to Fig. 4, Fig. 4 is a kind of structural representation of semantic understanding device provided in an embodiment of the present invention, the device
The implementation procedure of method, the device include in embodiment corresponding to the course of work reference picture 3 of each unit in structural representation：
First acquisition unit 410, for obtaining semantic text to be analyzed；
Participle unit 420, before the semantic net based on the purpose figure structure semantic text, according to the body number
According to the definition rule in storehouse to single body, the semantic text is segmented, to obtain multiple semantic Ziwen sheets；
Unit 430 is marked, for marking the part of speech of the multiple semantic Ziwen sheet respectively；
Subelement 440 is built, for according to the multiple semantic Ziwen sheet and the part of speech, based on described in purpose figure structure
The semantic net of semantic text
Second acquisition unit 450, each standard text in the vector space and ontology database for obtaining the semantic net
The range difference of this vector space；
First determination subelement 460, for determining that minimum range is poor from the range difference；
Second determination subelement 470, for will received text corresponding with the minimum range difference as with the semanteme
Received text corresponding to text.
Output unit 480, the corresponding answer of received text for exporting with determining.
Technical scheme provided in an embodiment of the present invention, semantic text to be analyzed is obtained, built based on image schema semantic
The semantic net of text, obtain the distance of the vector space of each received text in the vector space and ontology database of semantic net
Difference, and received text corresponding with semantic text is determined according to range difference.Scheme provided in an embodiment of the present invention, without for same
One semanteme prestores a variety of expression-forms, and also without being the different template of different scene configurations in advance, semantic understanding
Efficiency high.
For device or system embodiment, because it essentially corresponds to embodiment of the method, so related part referring to
The part explanation of embodiment of the method.Device or system embodiment described above is only schematical, wherein described
The unit illustrated as separating component can be or may not be physically separate, and the part shown as unit can be with
It is or may not be physical location, you can with positioned at a place, or can also be distributed on multiple NEs.Can
To select some or all of module therein to realize the purpose of this embodiment scheme according to the actual needs.This area is common
Technical staff is without creative efforts, you can to understand and implement.
In several embodiments provided by the present invention, it should be understood that disclosed system, apparatus and method, do not having
Have more than in the spirit and scope of the present invention, can realize in other way.Current embodiment is a kind of exemplary
Example, should not be taken as limiting, given particular content should in no way limit the purpose of the present invention.For example, the unit or
The division of subelement, only a kind of division of logic function, can there are other dividing mode, such as multiple lists when actually realizing
First or multiple subelements combine.In addition, multiple units can with or component can combine or be desirably integrated into another and be
System, or some features can be ignored, or not perform.
In addition, the schematic diagram of described system, apparatus and method and different embodiments, without departing from the scope of the present invention
It is interior, it can combine or integrate with other systems, module, techniques or methods.Another, shown or discussed mutual coupling
Close or direct-coupling or communication connection can be by some interfaces, the INDIRECT COUPLING or communication connection of device or unit, can be with
It is electrical, mechanical or other forms.
Described above is only the embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications also should
It is considered as protection scope of the present invention.
Claims (10)
- A kind of 1. semantic understanding method, it is characterised in that including：Obtain semantic text to be analyzed；The semantic net of the semantic text is built based on purpose schema；Obtain the range difference of the vector space of each received text in the vector space and ontology database of the semantic net；Received text corresponding with the semantic text is determined according to the range difference.
- 2. according to the method for claim 1, it is characterised in that based on purpose figure build the semantic text semantic net it Before, in addition to：According to the definition rule in the ontology database to single body, the semantic text is segmented, it is more to obtain Individual semantic Ziwen sheet；The part of speech of the multiple semantic Ziwen sheet is marked respectively；Correspondingly, the semantic net of the semantic text is built based on purpose figure, including：According to the multiple semantic Ziwen sheet and the part of speech, the semantic net based on the purpose figure structure semantic text.
- 3. according to the method for claim 1, it is characterised in that determined according to the range difference corresponding with the semantic text Received text, including：Determine that minimum range is poor from the range difference；Will received text corresponding with the minimum range difference as received text corresponding with the semantic text.
- 4. according to the method for claim 3, it is characterised in that also include：Export answer corresponding with the received text determined.
- 5. according to the method for claim 2, it is characterised in that also include：Beforehand through the automatic reptile on network node text message is captured from each website；The text message is converted to the body for meeting the definition rule；The body is stored into the ontology database.
- A kind of 6. semantic understanding device, it is characterised in that including：First acquisition unit, for obtaining semantic text to be analyzed；Construction unit, for building the semantic net of the semantic text based on purpose schema；Second acquisition unit, the vector of each received text in vector space and ontology database for obtaining the semantic net The range difference in space；Determining unit, received text corresponding with the semantic text is determined according to the range difference with language.
- 7. device according to claim 6, it is characterised in that also include：Participle unit, before the semantic net based on the purpose figure structure semantic text, according in the ontology database Definition rule to single body, is segmented to the semantic text, to obtain multiple semantic Ziwen sheets；Unit is marked, for marking the part of speech of the multiple semantic Ziwen sheet respectively；Correspondingly, the construction unit, including：Subelement is built, for according to the multiple semantic Ziwen sheet and the part of speech, the semantic text to be built based on purpose figure This semantic net.
- 8. device according to claim 6, it is characterised in that the determining unit, including：First determination subelement, for determining that minimum range is poor from the range difference；Second determination subelement, for will be with received text corresponding to the minimum range difference as corresponding with the semantic text Received text.
- 9. device according to claim 8, it is characterised in that also include：Output unit, the corresponding answer of received text for exporting with determining.
- 10. device according to claim 7, it is characterised in that also include：Placement unit, for capturing text message from each website beforehand through the automatic reptile on network node；Converting unit, the body of the definition rule is met for the text message to be converted to；Memory cell, for the body to be stored into the ontology database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710905504.1A CN107704559B (en) | 2017-09-29 | 2017-09-29 | Semantic understanding method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710905504.1A CN107704559B (en) | 2017-09-29 | 2017-09-29 | Semantic understanding method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107704559A true CN107704559A (en) | 2018-02-16 |
| CN107704559B CN107704559B (en) | 2020-06-05 |
Family
ID=61175508
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710905504.1A Active CN107704559B (en) | 2017-09-29 | 2017-09-29 | Semantic understanding method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107704559B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111654581A (en) * | 2020-04-30 | 2020-09-11 | 南京智音云数字科技有限公司 | Intelligent dialogue robot control method and system |
| CN112236766A (en) * | 2018-04-20 | 2021-01-15 | 脸谱公司 | Assisting users with personalized and contextual communication content |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218444A (en) * | 2013-04-22 | 2013-07-24 | 中央民族大学 | Method of Tibetan language webpage text classification based on semanteme |
| CN105843897A (en) * | 2016-03-23 | 2016-08-10 | 青岛海尔软件有限公司 | Vertical domain-oriented intelligent question and answer system |
-
2017
- 2017-09-29 CN CN201710905504.1A patent/CN107704559B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103218444A (en) * | 2013-04-22 | 2013-07-24 | 中央民族大学 | Method of Tibetan language webpage text classification based on semanteme |
| CN105843897A (en) * | 2016-03-23 | 2016-08-10 | 青岛海尔软件有限公司 | Vertical domain-oriented intelligent question and answer system |
Non-Patent Citations (1)
| Title |
|---|
| 贾思宇等: "基于语义网分析的在线学习智能答疑方法研究", 《情报杂志》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112236766A (en) * | 2018-04-20 | 2021-01-15 | 脸谱公司 | Assisting users with personalized and contextual communication content |
| CN111654581A (en) * | 2020-04-30 | 2020-09-11 | 南京智音云数字科技有限公司 | Intelligent dialogue robot control method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107704559B (en) | 2020-06-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106611597B (en) | Voice awakening method and device based on artificial intelligence | |
| CN106294854A (en) | A kind of man-machine interaction method for intelligent robot and device | |
| CN109616108A (en) | More wheel dialogue interaction processing methods, device, electronic equipment and storage medium | |
| CN108920622A (en) | A kind of training method of intention assessment, training device and identification device | |
| CN106326440B (en) | A kind of man-machine interaction method and device towards intelligent robot | |
| WO2019174428A1 (en) | Method and device for obtaining reply information | |
| CN103970417B (en) | A kind of information processing method and electronic equipment | |
| WO2018036555A1 (en) | Session processing method and apparatus | |
| CN110377716A (en) | Exchange method, device and the computer readable storage medium of dialogue | |
| US9047868B1 (en) | Language model data collection | |
| CN106933807A (en) | Memorandum event-prompting method and system | |
| CN107992299B (en) | Neural network hyper-parameter extraction and conversion method, system, device and storage medium | |
| CN111090728A (en) | Conversation state tracking method and device and computing equipment | |
| CN107480122A (en) | A kind of artificial intelligence exchange method and artificial intelligence interactive device | |
| CN105704013A (en) | Context-based topic updating data processing method and apparatus | |
| CN105989067B (en) | Method, user equipment and the training server of text snippet are generated from picture | |
| CN107015962A (en) | Towards the implementation method and device of the self-defined intention assessment of intelligent robot | |
| CN109243468A (en) | Audio recognition method, device, electronic equipment and storage medium | |
| CN107704559A (en) | A kind of semantic understanding method and device | |
| CN109741735A (en) | The acquisition methods and device of a kind of modeling method, acoustic model | |
| CN111523324A (en) | Training method and device for named entity recognition model | |
| CN106503008A (en) | File memory method and device and file polling method and apparatus | |
| JP2019133127A (en) | Voice recognition method, apparatus and server | |
| CN106681981B (en) | The mask method and device of Chinese part of speech | |
| CN101561725A (en) | Method and system of fast handwriting input |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Ye Yuping Inventor after: Zeng Qiwen Inventor after: Wang Hongchao Inventor before: Wang Hongchao |
|
| CB03 | Change of inventor or designer information | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180319 Address after: 100094, No. 16, No. 16, No. 10, hospital No. 10, Wandong Road, northwest of Haidian District, Beijing City, 506 Applicant after: Beijing ruantong Zhicheng Technology Co. Ltd. Address before: 100193, No. 16, No. 16, No. 10, hospital No. 10, Wandong Road, northwest of Haidian District, Beijing City, 502 Applicant before: Isoftstone Power Information Technology (Group) Co., Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210127 Address after: 100094 room 106, 1st floor, building 16, east yard, No.10, xibeiwangdong Road, Haidian District, Beijing Patentee after: Beijing Softcom Smart City Technology Co.,Ltd. Address before: 506, 5 / F, building 16, east yard, No. 10, xibeiwangdong Road, Haidian District, Beijing 100094 Patentee before: BEIJING ISOFTSTONE ZHICHENG TECHNOLOGY Co.,Ltd. |
|
| CP03 | Change of name, title or address |
Address after: Room 301-1, floor 3, building 10, Zhongguancun Software Park, No. 8, Dongbeiwang West Road, Haidian District, Beijing 100193 Patentee after: Beijing softong Intelligent Technology Co.,Ltd. Address before: 100094 room 106, 1st floor, building 16, east yard, No.10, xibeiwangdong Road, Haidian District, Beijing Patentee before: Beijing Softcom Smart City Technology Co.,Ltd. |
|
| CP03 | Change of name, title or address |