CN106057200A - Semantic-based interaction system and interaction method - Google Patents
Semantic-based interaction system and interaction method Download PDFInfo
- Publication number
- CN106057200A CN106057200A CN201610461831.8A CN201610461831A CN106057200A CN 106057200 A CN106057200 A CN 106057200A CN 201610461831 A CN201610461831 A CN 201610461831A CN 106057200 A CN106057200 A CN 106057200A
- Authority
- CN
- China
- Prior art keywords
- rule
- semantic
- module
- user
- natural language
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000003993 interaction Effects 0.000 title abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 12
- 230000008569 process Effects 0.000 claims description 27
- 230000002452 interceptive effect Effects 0.000 claims description 19
- 238000004458 analytical method Methods 0.000 claims description 18
- 238000013507 mapping Methods 0.000 claims description 10
- 230000002567 autonomic effect Effects 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000007906 compression Methods 0.000 claims description 5
- 230000008878 coupling Effects 0.000 claims description 5
- 238000010168 coupling process Methods 0.000 claims description 5
- 238000005859 coupling reaction Methods 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 claims description 5
- 238000013499 data model Methods 0.000 claims description 4
- 230000008909 emotion recognition Effects 0.000 claims description 4
- 238000004064 recycling Methods 0.000 claims description 3
- 238000011069 regeneration method Methods 0.000 claims description 2
- 230000001149 cognitive effect Effects 0.000 claims 1
- 230000006854 communication Effects 0.000 abstract description 5
- 238000004891 communication Methods 0.000 abstract description 4
- 241000282414 Homo sapiens Species 0.000 abstract 3
- 238000010586 diagram Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 241000208340 Araliaceae Species 0.000 description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 description 3
- 230000006835 compression Effects 0.000 description 3
- 235000008434 ginseng Nutrition 0.000 description 3
- 235000013305 food Nutrition 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 235000012054 meals Nutrition 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 1
- 241001347978 Major minor Species 0.000 description 1
- 230000004308 accommodation Effects 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/226—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics
- G10L2015/227—Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics of the speaker; Human-factor methodology
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a semantic-based interaction system and interaction method. By defining a regular semantic parameter model, a machine furthest reads human language expression; and by applying a regular engine, index definition and fuzzy associated operation, the dimensions of data are reduced, the processing efficiency of the machine is improved, a computer understands user's language while positively responding to a user and reaches the level of real human beings, and the communication of the computer is just as same as that of human beings in real life.
Description
Technical field
The present invention relates to human-computer interaction technique field, particularly relate to a kind of based on semantic interactive system and exchange method.
Background technology
Human-computer interaction technology (Human-Computer Interaction Techniques) refers to by computer defeated
Enter, outut device, realize the technology of people and computer dialog in an efficient way.It includes that machine passes through output or display device
Thering is provided the most for information about to people and prompting is asked for instructions, people by input equipment, to machine input, for information about and ask for instructions by prompting,
Answer a question.Speech recognition technology is the one in man-machine interaction., often there is following asking in existing speech recognition technology
Topic: 1. owing to being provided without structurized rule objects, therefore precision of identifying speech is low, poor reliability；2. natural language is without fall
Dimension process, in vector space model, a word is exactly a dimension, text classification, cluster excavation calculate in, high-dimensional to
Between amount, Similarity Measure can consume a large amount of computer resource and cause dimension disaster；3. cannot realize the natural language to user to carry out
Localized, dialect and the matching analysis of custom of speaking；The most in use, it is impossible to enriched by autonomic learning and improve word
Storehouse.
Summary of the invention
An object of the present invention is to provide a kind of based on semantic interactive system, with improve system voice accuracy of identification and
Reliability, realizes reparation and the more New function of system dictionary simultaneously.
Interactive system based on semanteme in this programme, including rule engine module, for by the semantic rule of natural language
Then it is defined as the discernible rule objects of computer, and described rule objects is stored in rule mapping library.
Intelligent analysis module, for profound language understanding and reasoning, based on big data analysis and process user language
Custom and incidence relation thereof, mate with rule objects after analysis, and realizes self-regeneration and self renewal process.
Intelligent chip module, for message groups bag, encode, decode, distribute, receive, linear prediction processing procedure, it is achieved
Speech compression processes, and provides a user with personalisation interface and call；
Rule mapping library, is used for storing the discernible rule objects of computer.
Beneficial effects of the present invention is as follows:
1. being provided with rule engine module, by rule engine module, the semantic rule of natural language being defined as computer can know
Other rule objects, owing to have employed the discernible structurized rule objects of computer, therefore can improve the essence of speech recognition
Degree and reliability.
2. described rule objects is stored in rule mapping library, effective information can be extracted also during user uses
Add dictionary, so abundant by autonomic learning for system and improve that dictionary provides may.
The language understanding of profound level the most of the present invention and reasoning, refer to sound Emotion identification, such as, same one
Words, the no tone, the result that may mate has difference；Sound characteristic identification, such as sound are sharper, then system can push away
This user disconnected is probably women.
User language of the present invention custom and incidence relation thereof, i.e. analyze the habit of speaking of localized, dialect and user
Used.Different regions has different dialects to be accustomed to, and different car owners also has different customs of speaking, and such as, party A-subscriber says " I
It is hungry ", possible system does not identifies the when of the most mutual, and what system interrogation party A-subscriber said is " cuisines " etc,
Now party A-subscriber rewords " cuisines ", and system identification goes out, and just can directly say " cuisines " when that party A-subscriber representing " being hungry " next time, that
System is it is known that party A-subscriber's expression is " being hungry ".
By intelligent analysis module, localized, dialect, user habit can be analyzed, it is achieved rule objects and the big data of system
The coupling of (including localized, dialect and user habit term), expands the analyst coverage of natural language, and the suitability is more
Extensively, and reparation and the renewal of system dictionary can be realized simultaneously.
The reparation of the system dictionary described in the present invention and renewal, refer to judge the standard of vocabulary by continually entering of user
Really and effectiveness.Such as, user uses keyword A not find relevant content for the first time, then system can be automatically by this pass
Key word A adds to dictionary；If user has changed keyword B removal search, then can be determined that this keyword A and keyword B can
Incidence relation can be there is, then this relation temporarily can be updated in dictionary, after treating, also have same user to say this
During keyword, it may be determined that this keyword is effective.
4. by intelligent chip module, for message groups bag, encode, decode, distribute, receive, linear prediction processed
Journey, it is achieved speech compression function, it is while ensuring communication safety, shorten man-machine interaction response speed, and to
Family provides personalisation interface to call the calling function realizing user to required information.
Linear prediction processing procedure described in the present invention is prior art, it was predicted that be according to existed between discrete signal
Determine the feature of relatedness, utilize the most one or more signal estimation next signal, then must be poor to actual value and predictive value
(forecast error) encodes.If prediction is relatively accurate, then error is the least.Under conditions of equal accuracy requires, so that it may with relatively
Few bit encodes, and reaches to compress the purpose of data.
Further, also include data model definitions module, the form that described data model definitions module definition N kind is different,
For the natural language data of input are converted into the perceptible form of system.The meaning of the form that definition N kind is different is base
Originally the exchange of all of data is met.
Further, described rule engine module includes word-dividing mode, de-redundant module, scaling module, determines generic module and determine ginseng
Module.By above-mentioned module, can respectively natural language be carried out word segmentation processing, de-redundant process, calibration process, determine class process and
Surely considering and handling reason, so after participle and de-redundant, higher-dimension represents in the latent semantic space being projected in low-dimensional, reduces problem
Scale, while reducing feature space dimension, it is possible to excavates the semantic information between word, the matter of characteristic set after raising dimensionality reduction
Amount, promotes text representation quality.
Further, described intelligent analysis module includes recycling module, unique match module and priority match module.Described
Recycling module be used for reclaiming insignificant voice, described unique match module is for carrying out unique with rule objects
Join；Described priority match module is for preferentially mating information similar with rule objects in system with rule objects.
It is a further object of the present invention to provide a kind of based on semantic exchange method, comprise the following steps:
1) semantic rule of natural language is defined as the discernible rule objects of computer, and described rule objects is stored in
In rule mapping library；
2) to profound language understanding and reasoning, based on big data analysis and process user language custom and incidence relation thereof,
Mate with rule objects after analysis, and carry out emotion recognition simultaneously；
3) for message groups bag, encode, decode, distribute, receive, linear prediction processing procedure, and realize speech compression merit
Can, it is while ensuring communication safety, and shortens the response speed of man-machine interaction, and provides a user with personalisation interface and call.
By above-mentioned exchange method, right owing to the semantic rule of natural language to be defined as the discernible rule of computer
As, therefore can improve precision and the reliability of speech recognition.
Described rule objects is stored in rule mapping library, effective information can be extracted during user uses and add
Dictionary, so abundant by autonomic learning for system and improve that dictionary provides may.
By step 2), feasible system information data is precisely mated with rule objects, and can realize being used for simultaneously
The emotion recognition of voice, is that statement, rhetorical question, query be contrary with the fact or the certainly tone as identified, thus realization is different
Occasion from export different information datas under linguistic context.
Further, before step 1), also include defining the form that N kind is different, by the natural language data conversion of input
The perceptible form of one-tenth system, to substantially meet the exchange of all of data.
Further, in step 1), the semantic rule of natural language is defined as the side of the discernible rule objects of computer
Formula is: natural language carries out word segmentation processing, de-redundant process, calibration process respectively, determines class process and surely consider and handle reason.Through participle
After de-redundant, higher-dimension represents in the latent semantic space being projected in low-dimensional, reduces the scale of problem, is reducing feature space dimension
While degree, it is possible to excavating the semantic information between word, after raising dimensionality reduction, the quality of characteristic set, promotes text representation quality.
Further, described coupling includes: if it is insignificant for identifying the natural language that user says, then to this nature language
Speech data reclaim, if identifying the natural language that user says have unique match information, then provide this unique match letter
Breath；If identifying the natural language that user says have Similarity matching information, the most preferentially provide this Similarity matching information.Above-mentioned
Joining process, if identifying the natural language that user says have Similarity matching information, the most preferentially providing this Similarity matching information, this
Plant the mode of fuzzy matching, be favorably improved the matching efficiency of speech recognition.
Further, in step 2) in, also include by rule objects newly-increased in autonomic learning extracting rule storehouse, with perfect
The step of dictionary.The autonomous renewal of feasible system dictionary.
Further, described rule objects uses structured parameter model, described structured parameter model includes being intended to,
Region, information point, classification and planning mode, parameter can combination in any.Use structured parameter model, parameter can combination in any,
I.e. can arbitrarily overturn order of speaking, lengthen, shorten argument structure, a large amount of empty cluster can be avoided and increase stability, even if
User is reverse to speak, and system still can be understood, so a lot of empty cluster will not be returned, user will not be allowed to think that system is bad
With, say that what does not all identify.
Accompanying drawing explanation
Fig. 1 is embodiment of the present invention basic module block diagram based on semantic interactive system.
In Fig. 2 rule engine module based on semantic interactive system that is the embodiment of the present invention and intelligent analysis module
Join schematic diagram.
Fig. 3 is that the embodiment of the present invention is based on rule engine module participle schematic diagram in semantic interactive system.Erecting in figure
Each vocabulary is split by line statement.
Fig. 4 is that the embodiment of the present invention is based on rule engine module de-redundant flow chart in semantic interactive system.
Fig. 5 is that the embodiment of the present invention is based on rule engine module de-redundant schematic diagram in semantic interactive system.Square frame in figure
The vocabulary retained after statement de-redundant.
Fig. 6 is that the embodiment of the present invention is based on rule engine module calibration schematic diagram in semantic interactive system.
Fig. 7 is that the embodiment of the present invention determines class schematic diagram based on rule engine module in semantic interactive system.
Fig. 8 is that the embodiment of the present invention joins schematic diagram surely based on rule engine module in semantic interactive system.
Fig. 9 is that the embodiment of the present invention maps schematic diagram based on rule engine module classification another name in semantic interactive system.
Detailed description of the invention
Below by detailed description of the invention, the present invention is further detailed explanation:
One, basic module, as shown in Figure 1.
Natural language described in user inputs via input equipment, by rule engine module, by the semanteme of natural language
Rule is defined as the discernible rule objects of computer, and is stored in by described rule objects in rule mapping library.Lead to the most again
Crossing intelligent analysis module to mate, the intelligent analysis module of the present embodiment includes dialect storehouse, feature database, structured parameter storehouse,
The result of coupling has three kinds: if it is insignificant for identifying the natural language that user says, then carry out back these natural language data
Receiving, if identifying the natural language that user says have unique match information, then providing this unique match information；If the use of identifying
The natural language that family is said has Similarity matching information, the most preferentially provides this Similarity matching information.By intelligent chip module,
The intelligent chip module of the present embodiment can be DSP, after providing unique match information or Similarity matching information, transmits control and refers to
Order, system pushes relevant information data to user.If when intelligent analysis module does not analyzes concrete meaning, it is possible to inquiry is used
Family.
Two, the coupling in rule engine module and intelligent analysis module is as shown in Figure 2.
Word segmentation processing, de-redundant that the rule engine module of the present embodiment includes carrying out natural language process, calibration processes,
Determine class process and surely consider and handle reason.
Three, the participle in rule engine module is as shown in Figure 3.The so-called participle of the present embodiment refers to language user inputted
The vocabulary of sentence carries out piecemeal segmentation.
Four, the de-redundant flow process in rule engine module is as shown in Figure 4.It is defeated that de-redundant described in the present embodiment refers to remove user
Vocabulary nonessential in the statement entered.
Five, the de-redundant in rule engine module is illustrated as shown in Figure 5.
Six, the calibration in rule engine module is as shown in Figure 6.Calibration described in the present embodiment refers to determine described in user
Object.
Six, rule engine module determines class as shown in Figure 7.Class of determining described in the present embodiment refers to determine described in user
The classification of object.
Seven, rule engine module determines ginseng as shown in Figure 8.Determine ginseng refers to determine to be described in user described in the present embodiment
Which parameter of object.
In some embodiments of the invention, described rule objects uses structured parameter model.Further below
Detailed description:
Structured parameter model
The structured parameter of user speech input:
<intention>+<region>+<information point>+<classification>+<planning mode>
Input parameter can be in any combination.
Interaction process:
Initiative information source, iterative process, share interactive interface.
<intention>
I to go to (acquiescence)+search/arrange navigation purpose ground
As a example by searching or arranging navigation purpose ground, for voice messaging analysis the structural data response user of user's input
Request, comprises but is not limited only to herein below:
Road location is major-minor, just
Planning mode closely, soon, at a high speed, charge
Search/arrange navigation INTRM intermediate point by the way
Route management route is checked, simulates, is deleted
Share found the team with fleet, add, exit, remove team, kicking a player, head car, with car, destination's setting/acquirement, good friend, point
Enjoy
Communication process phone, note, wechat
History navigation history track
Vehicle condition and Sensing Satellite location and OBD
Information inquiry weather, road conditions
Arrange and management parameters and user data
<region>
Save administrative division title
Borough draws title, area code coding
District's administrative division title, region postcode
Street administrative division title, region postcode
Support another name
As: the Inner Mongol-> Inner Mongol, Tianhe District-> Milky Way
The appellation of language convention, such as: city originally becomes district, district originally becomes city
Support combination, such as: Chao-Shan Area
List imports
<information point>
Doorplate
Clear and definite road doorplate numbering
Fuzzy doorplate location algorithm: doorplate sequence of parity, the most close, algorithm location
Title
Information point name keys, road name keyword, another name keyword
Phone
Fixed telephone number, special service number (such as: closest 120/110/119)
Crossing
Two road name keys
Road+direction
Concrete road name+directional information (such as: three rings are outer)
Traffic website
Concrete public traffic station title (such as: princess graveyard ferrum, subway Stone steles bridge)
Traffic website+mark
Concrete public traffic station title+website attribute-bit (such as: princess's grave station C exports)
Information point+direction
The main location supporting fuzzy class, concrete information point title+directional information (such as: Milky Way north of the city, Milky Way north of the city door)
Self-defined
Obtain user and define the place (such as: family, company, haircut, the name of friend) of preservation
<classification>
Use big class and group two-stage classification structure
Big class, flexibly.
Big class kind can carry out mining analysis according to engine Unidentified user phrase data, therefrom takes out and separates out new class
Another name claims, and the ownership that carried out by the statement that originally cannot resolve of intelligence is classified.
Engine can be analyzed excavating according to the temperature of group that user uses, frequency, is divided into big from newly by group
Class, and take out the group separating out more standby user use habit simultaneously.
Group, expansible.
The phrase data that big class is directly retrieved can be analyzed excavating by engine by user, takes out and separates out new group
Classification, reduces user's interaction times, improves the engine map accuracy to information retrieval.
The delimiter of item name share family language convention onboard.
Item name can map in classification existing with map/navigation engine.
Item name support combination and combined crosswise.
Item name support is called.
Item name support imports.
The alias definition of classification
User speech input is colloquial, it would be desirable to colloquial vocabulary is mapped to concrete one-level classification or two grades of classifications
In.As shown in Figure 9.Such as:
Example one: phonetic entry " converges to romote antiquity and has a meal ", and key word " is had a meal " and is mapped to food and drink, and engine should be able to be enumerated and converge adnexa romote antiquity
Food and drink StoreFront list.
Example two: phonetic entry " is sung to Tianhe District K ", and key word " K song " is mapped to KTV, and engine should be able to be set out Tianhe District
KTV.
Example three: phonetic entry " firmly hotel ", because not having area information, is then set out neighbouring hotel accommodations list.
The exchange method based on semanteme of the present embodiment, comprises the steps:
The natural language data of input are converted into the perceptible form of system by the form that definition N kind is different.
Natural language carries out word segmentation processing respectively, de-redundant processes, calibration processes, determine class process and surely consider and handle reason, will be from
So the semantic rule of language is defined as the discernible rule objects of computer, and described rule objects is stored in rule mapping library
In；
To profound language understanding and reasoning, based on big data analysis and process user language custom and incidence relation thereof, point
Mate with rule objects after analysis, and carry out emotion recognition simultaneously, by rule newly-increased in autonomic learning extracting rule storehouse
Object, to improve the step of dictionary；
For message groups bag, encode, decode, distribute, receive, linear prediction processing procedure, and realize speech compression function,
It is while ensuring communication safety, and shortens the response speed of man-machine interaction, and provides a user with personalisation interface and call.
Above-described is only embodiments of the invention, and in scheme, the known general knowledge such as concrete structure and characteristic is not made at this
Too much describing, before one skilled in the art know the applying date or priority date, technical field that the present invention belongs to is all of
Ordinary technical knowledge, it is possible to know all of prior art in this field, and there is normal experiment hands before this date of application
The ability of section, one skilled in the art can improve in conjunction with self-ability and implement under the enlightenment that the application is given
This programme, some typical known features or known method should not become one skilled in the art and implement the application
Obstacle.It should be pointed out that, for a person skilled in the art, on the premise of without departing from present configuration, it is also possible to make
Going out some deformation and improvement, these also should be considered as protection scope of the present invention, and these are all without affecting the effect that the present invention implements
Fruit and practical applicability.The protection domain that this application claims should be as the criterion with the content of its claim, the tool in description
Body embodiments etc. record the content that may be used for explaining claim.
Claims (10)
1. based on semantic interactive system, it is characterised in that including:
Rule engine module, for being defined as the discernible rule objects of computer, and by institute by the semantic rule of natural language
State rule objects to be stored in rule mapping library；
Intelligent analysis module, for profound language understanding and reasoning, is accustomed to based on big data analysis and process user language
And incidence relation, mate with rule objects after analysis, and realize self-regeneration and self renewal process；
Intelligent chip module, for message groups bag, encode, decode, distribute, receive, linear prediction processing procedure, it is achieved voice
Compress softwares processes, and provides a user with personalisation interface and call；
Rule mapping library, is used for storing the discernible rule objects of computer.
It is the most according to claim 1 based on semantic interactive system, it is characterised in that: also include data model definitions mould
Block, the form that described data model definitions module definition N kind is different, can for the natural language data of input are converted into system
Cognitive form.
It is the most according to claim 1 based on semantic interactive system, it is characterised in that: described rule engine module includes point
Word module, de-redundant module, scaling module, determine generic module and determine moduli block.
It is the most according to claim 1 based on semantic interactive system, it is characterised in that: described intelligent analysis module includes
Recycling module, unique match module and priority match module.
5. based on semantic exchange method, it is characterised in that: comprise the following steps:
1) semantic rule of natural language is defined as the discernible rule objects of computer, and described rule objects is stored in
In rule mapping library；
2) to profound language understanding and reasoning, based on big data analysis and process user language custom and incidence relation thereof,
Mate with rule objects after analysis, and carry out emotion recognition simultaneously；
3) for message groups bag, encode, decode, distribute, receive, linear prediction processing procedure, it is achieved speech compression process,
And provide a user with personalisation interface and call.
It is the most according to claim 5 based on semantic exchange method, it is characterised in that: before step 1), it is fixed also to include
The natural language data of input are converted into the perceptible form of system by the form that justice N kind is different.
It is the most according to claim 5 based on semantic exchange method, it is characterised in that: in step 1), by natural language
Semantic rule is defined as the mode of the discernible rule objects of computer: respectively natural language is carried out word segmentation processing, de-redundant
Process, calibration process, determine class process and surely consider and handle reason.
It is the most according to claim 5 based on semantic exchange method, it is characterised in that: described coupling includes: if identifying
It is insignificant for going out the natural language that user says, then reclaim these natural language data, if identifying the nature that user says
Language has unique match information, then provide this unique match information；If identify the natural language that user says be have similar
Match information, the most preferentially provide this Similarity matching information.
It is the most according to claim 5 based on semantic exchange method, it is characterised in that: in step 2) in, also include passing through
Rule objects newly-increased in autonomic learning extracting rule storehouse, to improve the step of dictionary.
The most according to claim 1 or 5 based on semantic interactive system, it is characterised in that: described rule objects uses
Structured parameter model, described structured parameter model includes intention, region, information point, classification and planning mode, and parameter can
Combination in any.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610461831.8A CN106057200A (en) | 2016-06-23 | 2016-06-23 | Semantic-based interaction system and interaction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610461831.8A CN106057200A (en) | 2016-06-23 | 2016-06-23 | Semantic-based interaction system and interaction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106057200A true CN106057200A (en) | 2016-10-26 |
Family
ID=57168123
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610461831.8A Pending CN106057200A (en) | 2016-06-23 | 2016-06-23 | Semantic-based interaction system and interaction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106057200A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107452373A (en) * | 2017-07-26 | 2017-12-08 | 上海与德通讯技术有限公司 | Robot interactive method and system |
| CN108172223A (en) * | 2017-12-14 | 2018-06-15 | 深圳市欧瑞博科技有限公司 | Voice instruction recognition method, device and server and computer readable storage medium |
| CN108563633A (en) * | 2018-03-29 | 2018-09-21 | 腾讯科技（深圳）有限公司 | A kind of method of speech processing and server |
| CN108871370A (en) * | 2018-07-03 | 2018-11-23 | 北京百度网讯科技有限公司 | Air navigation aid, device, equipment and medium |
| CN109063090A (en) * | 2018-07-26 | 2018-12-21 | 挖财网络技术有限公司 | Automate operation management system |
| CN109147784A (en) * | 2018-09-10 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | Voice interactive method, equipment and storage medium |
| CN109190008A (en) * | 2018-07-26 | 2019-01-11 | 挖财网络技术有限公司 | Automate operation management method |
| CN110111788A (en) * | 2019-05-06 | 2019-08-09 | 百度在线网络技术（北京）有限公司 | The method and apparatus of interactive voice, terminal, computer-readable medium |
| CN110428807A (en) * | 2019-08-15 | 2019-11-08 | 三星电子（中国）研发中心 | A kind of audio recognition method based on deep learning, system and device |
| CN110489517A (en) * | 2018-05-09 | 2019-11-22 | 鼎捷软件股份有限公司 | The Auto-learning Method and system of virtual assistant |
| CN110555204A (en) * | 2018-05-31 | 2019-12-10 | 北京京东尚科信息技术有限公司 | emotion judgment method and device |
| CN111179935A (en) * | 2018-11-12 | 2020-05-19 | 中移（杭州）信息技术有限公司 | Voice quality inspection method and device |
| CN112256737A (en) * | 2020-10-30 | 2021-01-22 | 深圳前海微众银行股份有限公司 | HIVE rule matching data method, device and storage medium |
| CN112347279A (en) * | 2020-05-20 | 2021-02-09 | 杭州贤芯科技有限公司 | Method for searching mobile phone photos |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5748973A (en) * | 1994-07-15 | 1998-05-05 | George Mason University | Advanced integrated requirements engineering system for CE-based requirements assessment |
| JPH11237894A (en) * | 1998-02-19 | 1999-08-31 | Nippon Telegr & Teleph Corp <Ntt> | Method and device for comprehending language |
| CN1898665A (en) * | 2003-10-23 | 2007-01-17 | 霍尼韦尔国际公司 | Method and apparatus for a hierarchical object model-based constrained language interpreter-parser |
| US20070239430A1 (en) * | 2006-03-28 | 2007-10-11 | Microsoft Corporation | Correcting semantic classification of log data |
| CN101604204A (en) * | 2009-07-09 | 2009-12-16 | 北京科技大学 | Distributed cognitive technology for intelligent emotional robot |
| US8346563B1 (en) * | 2012-04-10 | 2013-01-01 | Artificial Solutions Ltd. | System and methods for delivering advanced natural language interaction applications |
| CN103136360A (en) * | 2013-03-07 | 2013-06-05 | 北京宽连十方数字技术有限公司 | Internet behavior markup engine and behavior markup method corresponding to same |
| CN103488752A (en) * | 2013-09-24 | 2014-01-01 | 沈阳美行科技有限公司 | POI (point of interest) searching method |
| CN104462064A (en) * | 2014-12-15 | 2015-03-25 | 陈包容 | Method and system for prompting content input in information communication of mobile terminals |
| CN105183834A (en) * | 2015-08-31 | 2015-12-23 | 上海电科智能系统股份有限公司 | Ontology library based transportation big data semantic application service method |
| CN106796787A (en) * | 2014-05-20 | 2017-05-31 | 亚马逊技术有限公司 | The linguistic context carried out using preceding dialog behavior in natural language processing is explained |
-
2016
- 2016-06-23 CN CN201610461831.8A patent/CN106057200A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5748973A (en) * | 1994-07-15 | 1998-05-05 | George Mason University | Advanced integrated requirements engineering system for CE-based requirements assessment |
| JPH11237894A (en) * | 1998-02-19 | 1999-08-31 | Nippon Telegr & Teleph Corp <Ntt> | Method and device for comprehending language |
| CN1898665A (en) * | 2003-10-23 | 2007-01-17 | 霍尼韦尔国际公司 | Method and apparatus for a hierarchical object model-based constrained language interpreter-parser |
| US20070239430A1 (en) * | 2006-03-28 | 2007-10-11 | Microsoft Corporation | Correcting semantic classification of log data |
| CN101604204A (en) * | 2009-07-09 | 2009-12-16 | 北京科技大学 | Distributed cognitive technology for intelligent emotional robot |
| US8346563B1 (en) * | 2012-04-10 | 2013-01-01 | Artificial Solutions Ltd. | System and methods for delivering advanced natural language interaction applications |
| CN103136360A (en) * | 2013-03-07 | 2013-06-05 | 北京宽连十方数字技术有限公司 | Internet behavior markup engine and behavior markup method corresponding to same |
| CN103488752A (en) * | 2013-09-24 | 2014-01-01 | 沈阳美行科技有限公司 | POI (point of interest) searching method |
| CN106796787A (en) * | 2014-05-20 | 2017-05-31 | 亚马逊技术有限公司 | The linguistic context carried out using preceding dialog behavior in natural language processing is explained |
| CN104462064A (en) * | 2014-12-15 | 2015-03-25 | 陈包容 | Method and system for prompting content input in information communication of mobile terminals |
| CN105183834A (en) * | 2015-08-31 | 2015-12-23 | 上海电科智能系统股份有限公司 | Ontology library based transportation big data semantic application service method |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107452373A (en) * | 2017-07-26 | 2017-12-08 | 上海与德通讯技术有限公司 | Robot interactive method and system |
| CN108172223A (en) * | 2017-12-14 | 2018-06-15 | 深圳市欧瑞博科技有限公司 | Voice instruction recognition method, device and server and computer readable storage medium |
| CN108563633A (en) * | 2018-03-29 | 2018-09-21 | 腾讯科技（深圳）有限公司 | A kind of method of speech processing and server |
| CN110489517B (en) * | 2018-05-09 | 2023-10-31 | 鼎捷软件股份有限公司 | Automatic learning method and system of virtual assistant |
| CN110489517A (en) * | 2018-05-09 | 2019-11-22 | 鼎捷软件股份有限公司 | The Auto-learning Method and system of virtual assistant |
| CN110555204A (en) * | 2018-05-31 | 2019-12-10 | 北京京东尚科信息技术有限公司 | emotion judgment method and device |
| JP2020008579A (en) * | 2018-07-03 | 2020-01-16 | ベイジン バイドゥ ネットコム サイエンス アンド テクノロジー カンパニー リミテッド | Navigation method, navigation device, equipment and medium |
| CN108871370A (en) * | 2018-07-03 | 2018-11-23 | 北京百度网讯科技有限公司 | Air navigation aid, device, equipment and medium |
| JP7042240B2 (en) | 2018-07-03 | 2022-03-25 | ベイジン バイドゥ ネットコム サイエンス テクノロジー カンパニー リミテッド | Navigation methods, navigation devices, equipment and media |
| CN109063090A (en) * | 2018-07-26 | 2018-12-21 | 挖财网络技术有限公司 | Automate operation management system |
| CN109190008A (en) * | 2018-07-26 | 2019-01-11 | 挖财网络技术有限公司 | Automate operation management method |
| CN109147784A (en) * | 2018-09-10 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | Voice interactive method, equipment and storage medium |
| CN109147784B (en) * | 2018-09-10 | 2021-06-08 | 百度在线网络技术（北京）有限公司 | Voice interaction method, device and storage medium |
| US11176938B2 (en) | 2018-09-10 | 2021-11-16 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method, device and storage medium for controlling game execution using voice intelligent interactive system |
| CN111179935A (en) * | 2018-11-12 | 2020-05-19 | 中移（杭州）信息技术有限公司 | Voice quality inspection method and device |
| CN111179935B (en) * | 2018-11-12 | 2022-06-28 | 中移（杭州）信息技术有限公司 | Voice quality inspection method and device |
| CN110111788B (en) * | 2019-05-06 | 2022-02-08 | 阿波罗智联(北京)科技有限公司 | Voice interaction method and device, terminal and computer readable medium |
| CN110111788A (en) * | 2019-05-06 | 2019-08-09 | 百度在线网络技术（北京）有限公司 | The method and apparatus of interactive voice, terminal, computer-readable medium |
| CN110428807A (en) * | 2019-08-15 | 2019-11-08 | 三星电子（中国）研发中心 | A kind of audio recognition method based on deep learning, system and device |
| CN112347279A (en) * | 2020-05-20 | 2021-02-09 | 杭州贤芯科技有限公司 | Method for searching mobile phone photos |
| CN112256737A (en) * | 2020-10-30 | 2021-01-22 | 深圳前海微众银行股份有限公司 | HIVE rule matching data method, device and storage medium |
| CN112256737B (en) * | 2020-10-30 | 2024-05-28 | 深圳前海微众银行股份有限公司 | Method, equipment and storage medium for matching HIVE rule with data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106057200A (en) | Semantic-based interaction system and interaction method | |
| CN109801491B (en) | Intelligent navigation method, device and equipment based on risk assessment and storage medium | |
| CN106297785B (en) | Intelligent service system based on Internet of vehicles | |
| KR100792208B1 (en) | Method and Apparatus for generating a response sentence in dialogue system | |
| US11017770B2 (en) | Vehicle having dialogue system and control method thereof | |
| CN113392986B (en) | Highway bridge information extraction method based on big data and management maintenance system | |
| KR20190109614A (en) | Method and apprartus for chatbots in customer service analyzing hierarchical user expression and generating responses | |
| CN111651609A (en) | Multi-turn dialogue method and system integrating knowledge graph and emotion supervision | |
| CN111597350B (en) | Rail transit event knowledge graph construction method based on deep learning | |
| CN103488752B (en) | A kind of search method of POI intelligent retrievals | |
| CN112735383A (en) | Voice signal processing method, device, equipment and storage medium | |
| CN107562828B (en) | Multi-source maritime information searching and conflict processing system and method | |
| CN115292461B (en) | Man-machine interaction learning method and system based on voice recognition | |
| CN110309277A (en) | Human-computer dialogue semanteme parsing method and system | |
| CN116450799B (en) | Intelligent dialogue method and equipment applied to traffic management service | |
| CN115022471B (en) | Intelligent robot voice interaction system and method | |
| JP4244423B2 (en) | Proper word string estimation device | |
| CN110110048B (en) | Query guiding method and device | |
| CN114090732A (en) | Automatic generation method and system for rail transit fault processing scheme | |
| CN114818740B (en) | Man-machine cooperation method and system based on domain knowledge graph | |
| CN108932351B (en) | Method and system for generating route map of carbon capture and sequestration technology | |
| CN112836517A (en) | Method for processing mining risk signal based on natural language | |
| CN113053416A (en) | Speech emotion recognition system based on knowledge graph | |
| CN117172643B (en) | Efficient logistics operation method and system based on big data | |
| CN113409776B (en) | Voice recognition method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161026 |
|
| RJ01 | Rejection of invention patent application after publication |