CN106503123A - A kind of deep learning intelligent response system based on computer cloud data - Google Patents
A kind of deep learning intelligent response system based on computer cloud data Download PDFInfo
- Publication number
- CN106503123A CN106503123A CN201610910975.7A CN201610910975A CN106503123A CN 106503123 A CN106503123 A CN 106503123A CN 201610910975 A CN201610910975 A CN 201610910975A CN 106503123 A CN106503123 A CN 106503123A
- Authority
- CN
- China
- Prior art keywords
- user
- answer
- unit
- information
- word
- 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
- 230000004044 response Effects 0.000 title claims abstract description 28
- 238000013135 deep learning Methods 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 42
- 230000008569 process Effects 0.000 claims abstract description 41
- 230000000694 effects Effects 0.000 claims abstract description 10
- 238000000605 extraction Methods 0.000 claims abstract description 4
- 239000000463 material Substances 0.000 claims abstract description 4
- 238000013507 mapping Methods 0.000 claims description 33
- 238000004458 analytical method Methods 0.000 claims description 18
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000005457 optimization Methods 0.000 claims description 12
- 238000007619 statistical method Methods 0.000 claims description 12
- 230000009471 action Effects 0.000 claims description 11
- 230000011218 segmentation Effects 0.000 claims description 11
- 238000005065 mining Methods 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 3
- 230000008878 coupling Effects 0.000 claims description 3
- 238000010168 coupling process Methods 0.000 claims description 3
- 238000005859 coupling reaction Methods 0.000 claims description 3
- 238000000151 deposition Methods 0.000 claims description 3
- 238000012854 evaluation process Methods 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 3
- 230000008451 emotion Effects 0.000 description 7
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000002996 emotional effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000036651 mood Effects 0.000 description 2
- 239000003973 paint Substances 0.000 description 2
- 230000000052 comparative effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000012360 testing 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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/338—Presentation of query results
-
- 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
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/54—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for retrieval
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/253—Grammatical analysis; Style critique
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
- G10L15/26—Speech to text systems
-
- 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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Library & Information Science (AREA)
- Signal Processing (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Remote Sensing (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A kind of deep learning intelligent response system based on computer cloud data, including：Real-time position information, for positioning to user's real time position, is sent to cartographic information delineation unit by positioning unit；Cartographic information delineation unit, delimit User Activity region for the description information based on the trajectory segment of user in Preset Time；It is additionally operable to the complete map for depicting specific region in advance, and detailed each point of interest marked in the specific region on map；Information receiving unit, for process after information be sent to Database Unit；Database Unit, sets up knowledge base for collecting and arranging the answer knowledge material of each user's proposition problem and answer, and to story extraction candidate keywords, and the content to key word carries out handmarking, to carry out follow-up keyword index；Social networkies describe unit, for obtain interrelated between the user in specific region and influence each other and user between the different social role of performer.
Description
Technical field
The present invention relates to intelligent answer robotics, more particularly to a kind of depth based on computer cloud data
Practise intelligent response system.
Background technology
Based on the mobile Internet platform of current popular, the research for carrying out intelligent answer robot system be one emerging
Research field.The research field being related to includes based on mobile Internet platform, user in campus real time position dynamic
The Changing Pattern of state variation monitoring, User Activity position and scope, the regular course of User Activity are defined and are pushed away with personalized task
Recommend, the fusion of the artificial intelligence's knowledge base combined with user context key element and question and answer specialist system etc. all with mobile Internet
On the related technical field of campus intelligent answer robot.
Not yet having in prior art, the campus intelligent answer machine for combining is excavated for mobile Internet and big data
The correlation technique of device people's system.
Content of the invention
In view of this, the present invention proposes a kind of deep learning intelligent response system based on computer cloud data.
A kind of deep learning intelligent response system based on computer cloud data, which is included such as lower unit：
Real-time position information, for positioning to user's real time position, is sent to cartographic information description by positioning unit
Unit；
Cartographic information delineation unit, for receiving the real-time position information of positioning unit transmission, and real-time position information shape
Into the action trail of user, the action trail of user is carried out segmentation, and trajectory segment is described；Based in Preset Time
The description information of the trajectory segment of user delimit User Activity region；The complete map for depicting specific region in advance is additionally operable to,
And on map detailed each point of interest marked in the specific region, be a certain specific in the real-time position information of user
During point of interest, the relevant information of the particular point of interest is pushed；
Information receiving unit, the text query or speech query information for receiving user's input are being believed for text query
During breath, through the text mining and process of Chinese word segmentation, semantic analysis and syntactic analysiss, and by process after information be sent to number
According to library unit；For speech query information when, speech query information is identified as text query information first, and through Chinese point
The text mining and process of word, semantic analysis and syntactic analysiss, and by process after information be sent to Database Unit；
Database Unit, sets up knowledge for collecting and arranging the answer knowledge material of each user's proposition problem and answer
Storehouse, to story extraction candidate keywords, and the content to key word carries out handmarking, to carry out follow-up key word rope
Draw；It is problem knowledge storehouse and answer knowledge base by Knowledge base partition, is used for depositing each of user's proposition wherein in problem knowledge storehouse
The demand of kind and problem, be present in answer knowledge base and the demand and the answer content for matching, answer in problem knowledge storehouse
Thinking and answer detailed process；And the association that question and answer matching degree is assessed is set up between problem knowledge storehouse and answer knowledge base, close
The matching degree being combined between metric question and answer, and this process is combined with follow-up user satisfaction feedback,
It is provided commonly for the optimization to knowledge base, and the renewal and optimization to related content in problem knowledge storehouse and answer knowledge base；
Social networkies describe unit, for obtaining interrelated between the user in specific region and influencing each other and use
The different social role of performer between family, so that it is determined that each user each has different user properties and user task,
And the interaction between user constitutes respective customer relationship and social circle.
In the deep learning intelligent response system based on computer cloud data of the present invention, which is included as placed an order
Unit：
Statistical analysis unit, for according to the description information of the trajectory segment of user, each user in Preset Time each
There is the interaction between different user properties and user task, and user to constitute respective customer relationship and social circle's life
Into and preserve the stroke rule information table of user；Include user within each time period in the stroke rule information table of user
The interest of zone of action, activity item and user.
In the deep learning intelligent response system based on computer cloud data of the present invention, the cartographic information is retouched
Paint unit to be additionally operable to, when the real-time position information of positioning unit transmission meets the point of interest in specific region, the point of interest be sent out
Deliver to statistical analysis unit；
Statistical analysis unit is judged in the time point in point of interest item whether to be handled；There is backlog
When, sent to information receiving unit with the interest point name and backlog；
Text mining and process of the information receiving unit through Chinese word segmentation, semantic analysis and syntactic analysiss, and will process
Information afterwards is sent to Database Unit；
The answer content matched with problem, answer thinking and answer detailed process are pushed and are shown by Database Unit.
In the deep learning intelligent response system based on computer cloud data of the present invention,
In the processing authority that social networkies describe the backlog for prestoring user in unit, processing authority is divided into certainly
Oneself processes and allows specific user's alternate process in social circle.
In the deep learning intelligent response system based on computer cloud data of the present invention,
Statistical analysis unit there is backlog in certain time period for user and user is in backlog
Zone of action outside when, judge that whether the backlog is the pending thing for allowing specific user's alternate process in social circle
, the backlog is sent to user social contact circle corresponding other users if it is.
In the deep learning intelligent response system based on computer cloud data of the present invention,
Matching degree between Database Unit vacuum metrics question and answer, and this process is satisfied with follow-up user
Degree feedback combines, and is provided commonly for the optimization to knowledge base, and to related content in problem knowledge storehouse and answer knowledge base more
Newly include with optimization：
Coupling mapping relations will be set up between question and answer after question and answer matching degree evaluation process, and to candidate answers
Ranking is carried out with the matching degree of problem, several candidate answers in the top is supplied to user and is selected, while allowing
User is evaluated to the answer of problem, and the result of evaluation is fed back to question answering system in time carries out the correction of question and answer matching degree
Replacement and renewal with knowledge in knowledge base.
In the deep learning intelligent response system based on computer cloud data of the present invention,
Mapping relations matrix M in Database Unit between problem knowledge storehouse and key to the issue wordq,kIt is expressed as follows：
Wherein Rq→kRepresent mapping relations therebetween, Qi(i=1...n) problem of representation and its number, Kj(j=
1...m) problem of representation key word and its number；One problem can be disassembled and be been described by for multiple key words, while one
Key word can also apply in multiple problems；Tij(i=1 ... n, j=1...m) problem of representation i is made up of key to the issue word j
Content of text；
Mapping relations matrix M in Database Unit between key to the issue word and answer key wordk,k’It is expressed as follows：
Wherein Rk→k'Represent mapping relations therebetween, Ki(i=1 ... n) problem of representation key word and its number, K'j(j
=1 ... m) represents answer key word and its number；One key to the issue word can correspond to multiple problem answers key words, while
One answer key word can also apply in multiple key to the issue words；Tij(i=1 ... n, j=1 ... m) problem of representation key word i
The content of text that is answered by answer key word j；
Mapping relations matrix M in Database Unit between answer key word and answerk’,aIt is expressed as follows：
Wherein Rk'→aRepresent mapping relations therebetween, K'i(i=1 ... n) represents answer key word and its number, Aj(j
=1 ... m) represents answer and its number；One answer key word can be in order to describe multiple answers, while an answer can also
It is described with multiple answer key words；Tij(i=1 ... n, j=1 ... m) represent that answer key word i is described to answer j
Content of text；
Mapping relations matrix M in Database Unit between answer and answer rankinga,rankIt is expressed as follows：
Wherein Ra→rankRepresent mapping relations therebetween, Ai(i=1 ... n) represents answer and its number,Represent the ranking of answer i；
Mapping relations matrix M in Database Unit between answer and user satisfactiona,usIt is expressed as follows：
WhereinRepresent mapping relations therebetween, Ai(i=1...n) answer and its number, U are representeds,j(j=
1 ... m) represents user satisfaction and its number；One answer can be evaluated by multiple users, can have multiple users full
Meaning degree, while a user can also be evaluated to multiple answers, provides the customer satisfaction evaluation of multiple answers respectively；Pij
(i=1 ... n, j=1 ... m) represent the user satisfaction evaluated by answer i by user j.
Implement the deep learning intelligent response system based on computer cloud data of present invention offer compared with prior art
Have the advantages that：For aiding in user (the such as teacher and that (such as in campus) newly adds in specific region
Raw etc.) faster it is familiar with and adapts to environment (the such as University Environment of user place universities and colleges and cultural atmosphere), preferably use with other
Friend relation is set up between family, and the artificial intelligence's knowledge base that sets up by situation key element is the daily of movable crowd in specific region
Life is preferably serviced.So that user faster, is more preferably familiar with specific region internal and external environment, hardware/software infrastructure, regional culture
Deng, and systematicness is carried out with question and answer mode represent with a series of.
Description of the drawings
Fig. 1 is the deep learning intelligent response system architecture diagram based on computer cloud data of the embodiment of the present invention.
Specific embodiment
As shown in figure 1, for the defect of prior art, the present invention proposes a kind of depth based on computer cloud data
Intelligent response system is practised, which is included such as lower unit：
Real-time position information, for positioning to user's real time position, is sent to cartographic information description by positioning unit
Unit.Alternatively, positioning unit can pass through the function that the app such as mobile phone realize positioning.
Cartographic information delineation unit, for receiving the real-time position information of positioning unit transmission, and real-time position information shape
Into the action trail of user, the action trail of user is carried out segmentation, and trajectory segment is described；Based in Preset Time
The description information of the trajectory segment of user delimit User Activity region；The complete map for depicting specific region in advance is additionally operable to,
And on map detailed each point of interest marked in the specific region, be a certain specific in the real-time position information of user
During point of interest, the relevant information of the particular point of interest is pushed.It is alternatively possible to the algorithm filtered based on user collaborative pushes the spy
Determine the relevant information of point of interest.Such as through some point of interest, when being coffee, then push coffee phase in adnexa preset range
The information of pass is to user.
The action trail of user is carried out segmentation, and trajectory segment is described, for example, user is if a university
Raw, the trajectory segment from dormitory to teaching building is described as " turning out for work ".These are only schematically.
Information receiving unit, the text query or speech query information for receiving user's input are being believed for text query
During breath, through the text mining and process of Chinese word segmentation, semantic analysis and syntactic analysiss, and by process after information be sent to number
According to library unit；For speech query information when, speech query information is identified as text query information first, and through Chinese point
The text mining and process of word, semantic analysis and syntactic analysiss, and by process after information be sent to Database Unit；For text
During this Query Information, by process after information be sent to Emotion identification unit, for speech query information when, while will process after
Information and speech query information be sent to Emotion identification unit；
Emotion identification unit, the information for being sent according to information receiving unit judge the emotional state of user, user's
Emotional state is divided into general, low, sad, glad；For low or sad when, will particular point of interest relevant information push strong
The instruction that degree is turned down is sent to cartographic information delineation unit；
The Emotion identification unit includes following word Emotion identification subelement and voice mood identification subelement：
Word Emotion identification subelement includes that classification storage represents general, low, sad, glad standard vocabulary；
The vocabulary of test input is trained by classifier functions and is categorized in each classification, and according to classification
As a result judgment models are set up；
The information of reception is mated with each single linguistic context of target word in standard vocabulary, is caught semantic contrast
Information, and the emotion of Word message is judged to acquired semantic comparative information；
Voice mood identification subelement identification subelement is used for the emotional information for recognizing voice by speech recognition technology.
Alternatively, the formula of judgment models is as follows：
Wherein, w is target classification word in context window, and c is the input vocabulary in situational meaning；K is existing for negative word remittance abroad
Probability；Sim represents similarity cosine value, and σ is Dynamic gene.
Database Unit, sets up knowledge for collecting and arranging the answer knowledge material of each user's proposition problem and answer
Storehouse, to story extraction candidate keywords, and the content to key word carries out handmarking, to carry out follow-up key word rope
Draw；It is problem knowledge storehouse and answer knowledge base by Knowledge base partition, is used for depositing each of user's proposition wherein in problem knowledge storehouse
The demand of kind and problem, be present in answer knowledge base and the demand and the answer content for matching, answer in problem knowledge storehouse
Thinking and answer detailed process；And the association that question and answer matching degree is assessed is set up between problem knowledge storehouse and answer knowledge base, close
The matching degree being combined between metric question and answer, and this process is combined with follow-up user satisfaction feedback,
It is provided commonly for the optimization to knowledge base, and the renewal and optimization to related content in problem knowledge storehouse and answer knowledge base.
Social networkies describe unit, for obtaining interrelated between the user in specific region and influencing each other and use
The different social role of performer between family, so that it is determined that each user each has different user properties and user task,
And the interaction between user constitutes respective customer relationship and social circle.Alternatively, customer relationship and social circle can draw
Graduation, the user in different grades of social circle have different information browse authorities.
In the deep learning intelligent response system based on computer cloud data of the present invention, which is included as placed an order
Unit：
Statistical analysis unit, for according to the description information of the trajectory segment of user, each user in Preset Time each
There is the interaction between different user properties and user task, and user to constitute respective customer relationship and social circle's life
Into and preserve the stroke rule information table of user；Include user within each time period in the stroke rule information table of user
The interest of zone of action, activity item and user.
In the deep learning intelligent response system based on computer cloud data of the present invention, the cartographic information is retouched
Paint unit to be additionally operable to, when the real-time position information of positioning unit transmission meets the point of interest in specific region, the point of interest be sent out
Deliver to statistical analysis unit.
Statistical analysis unit is judged in the time point in point of interest item whether to be handled；There is backlog
When, sent to information receiving unit with the interest point name and backlog.
Text mining and process of the information receiving unit through Chinese word segmentation, semantic analysis and syntactic analysiss, and will process
Information afterwards is sent to Database Unit.
The answer content matched with problem, answer thinking and answer detailed process are pushed and are shown by Database Unit.
In the deep learning intelligent response system based on computer cloud data of the present invention,
In the processing authority that social networkies describe the backlog for prestoring user in unit, processing authority is divided into certainly
Oneself processes and allows specific user's alternate process in social circle.Implement the present embodiment, the use of user can be greatly improved just
Profit.
In the deep learning intelligent response system based on computer cloud data of the present invention,
Statistical analysis unit there is backlog in certain time period for user and user is in backlog
Zone of action outside when, judge that whether the backlog is the pending thing for allowing specific user's alternate process in social circle
, the backlog is sent to user social contact circle corresponding other users if it is.Embodiment the present embodiment, is carrying
While high convenience for users, safety is also improved.
In the deep learning intelligent response system based on computer cloud data of the present invention,
Matching degree between Database Unit vacuum metrics question and answer, and this process is satisfied with follow-up user
Degree feedback combines, and is provided commonly for the optimization to knowledge base, and to related content in problem knowledge storehouse and answer knowledge base more
Newly include with optimization：
Coupling mapping relations will be set up between question and answer after question and answer matching degree evaluation process, and to candidate answers
Ranking is carried out with the matching degree of problem, several candidate answers in the top is supplied to user and is selected, while allowing
User is evaluated to the answer of problem, and the result of evaluation is fed back to question answering system in time carries out the correction of question and answer matching degree
Replacement and renewal with knowledge in knowledge base.
In the deep learning intelligent response system based on computer cloud data of the present invention,
Mapping relations matrix M in Database Unit between problem knowledge storehouse and key to the issue wordq,kIt is expressed as follows：
Wherein Rq→kRepresent mapping relations therebetween, Qi(i=1 ... n) problem of representation and its number, Kj(j=
1...m) problem of representation key word and its number；One problem can be disassembled and be been described by for multiple key words, while one
Key word can also apply in multiple problems；Tij(m) problem of representation i is made up of key to the issue word j for i=1...n, j=1 ...
Content of text；
Mapping relations matrix M in Database Unit between key to the issue word and answer key wordk,k’It is expressed as follows：
Wherein Rk→k'Represent mapping relations therebetween, Ki(i=1...n) problem of representation key word and its number, K'j
(j=1...m) answer key word and its number are represented；One key to the issue word can correspond to multiple problem answers key words,
An answer key word can also apply in multiple key to the issue words simultaneously；Tij(i=1...n, j=1...m) problem of representation
The content of text answered by answer key word j by key word i；
Mapping relations matrix M in Database Unit between answer key word and answerk’,aIt is expressed as follows：
Wherein Rk'→aRepresent mapping relations therebetween, K'i(i=1...n) answer key word and its number, A are representedj
(j=1...m) answer and its number are represented；One answer key word can be in order to describe multiple answers, while an answer
Can be described with multiple answer key words；Tij(i=1 ... n, j=1 ... m) represent that answer key word i is carried out to answer j
The content of text of description；
Mapping relations matrix M in Database Unit between answer and answer rankinga,rankIt is expressed as follows：
Wherein Ra→rankRepresent mapping relations therebetween, Ai(i=1 ... n) represents answer and its number,Represent the ranking of answer i；
Mapping relations matrix M in Database Unit between answer and user satisfactiona,usIt is expressed as follows：
WhereinRepresent mapping relations therebetween, Ai(i=1 ... n) represents answer and its number, Us,j(j=
1...m) user satisfaction and its number are represented；One answer can be evaluated by multiple users, can have multiple users
Satisfaction, while a user can also be evaluated to multiple answers, provides the customer satisfaction evaluation of multiple answers respectively；
Pij(i=1...n, j=1...m) represents the user satisfaction evaluated by answer i by user j.
Implement the deep learning intelligent response system based on computer cloud data of present invention offer compared with prior art
Have the advantages that：For aiding in user (the such as teacher and that (such as in campus) newly adds in specific region
Raw etc.) faster it is familiar with and adapts to environment (the such as University Environment of user place universities and colleges and cultural atmosphere), preferably use with other
Friend relation is set up between family, and the artificial intelligence's knowledge base that sets up by situation key element is the daily of movable crowd in specific region
Life is preferably serviced.So that user faster, is more preferably familiar with specific region internal and external environment, hardware/software infrastructure, regional culture
Deng, and systematicness is carried out with question and answer mode represent with a series of.
It is understood that for the person of ordinary skill of the art, can be done with technology according to the present invention design
Go out other various corresponding changes and deformation, and all these changes and deformation should all belong to the protection model of the claims in the present invention
Enclose.
Claims (6)
1. a kind of deep learning intelligent response system based on computer cloud data, it is characterised in which is included such as lower unit：
Real-time position information, for positioning to user's real time position, is sent to cartographic information delineation unit by positioning unit；
Cartographic information delineation unit, for receiving the real-time position information of positioning unit transmission, and real-time position information is formed and is used
The action trail of user is carried out segmentation, and trajectory segment is described by the action trail at family；Based on user in Preset Time
The description information of trajectory segment delimit User Activity region；It is additionally operable to the complete map for depicting specific region in advance, and
Detailed each point of interest marked in the specific region on map, is a certain special interests in the real-time position information of user
During point, the relevant information of the particular point of interest is pushed；
Information receiving unit, the text query or speech query information for receiving user's input, for text query information when,
Through the text mining and process of Chinese word segmentation, semantic analysis and syntactic analysiss, and by process after information be sent to data base
Unit；For speech query information when, speech query information is identified as text query information first, and through Chinese word segmentation, language
Justice analysis and syntactic analysiss text mining and process, and by process after information be sent to Database Unit；
Database Unit, sets up knowledge base for collecting and arranging the answer knowledge material of each user's proposition problem and answer,
To story extraction candidate keywords, and the content to key word carries out handmarking, to carry out follow-up keyword index；Will
Knowledge base partition is problem knowledge storehouse and answer knowledge base, is used for the various demands for depositing user's proposition wherein in problem knowledge storehouse
And problem, there are problems that in answer knowledge base with problem knowledge storehouse in demand and the answer content for matching, answer thinking and
Answer detailed process；And the association that question and answer matching degree is assessed is set up between problem knowledge storehouse and answer knowledge base, associating is used for
Matching degree between metric question and answer, and this process is combined with follow-up user satisfaction feedback, common use
In the optimization to knowledge base, and the renewal and optimization to related content in problem knowledge storehouse and answer knowledge base；
Social networkies describe unit, for obtain between the user in specific region interrelated and influence each other and user it
Between the different social role of performer, so that it is determined that each user each has different user properties and user task, and
Interaction between user constitutes respective customer relationship and social circle；
Statistical analysis unit, for each having according to the description information of the trajectory segment of user, each user in Preset Time
Interaction between different user properties and user task, and user constitutes respective customer relationship and social circle generates simultaneously
Preserve the stroke rule information table of user；Include activity of the user within each time period in the stroke rule information table of user
The interest in region, activity item and user.
2. the deep learning intelligent response system based on computer cloud data as claimed in claim 1, it is characterised in that described
Cartographic information delineation unit is additionally operable to when the real-time position information of positioning unit transmission meets the point of interest in specific region, will
The point of interest is sent to statistical analysis unit；
Statistical analysis unit is judged in the time point in point of interest item whether to be handled；When there is backlog,
Sent to information receiving unit with the interest point name and backlog；
Text mining and process of the information receiving unit through Chinese word segmentation, semantic analysis and syntactic analysiss, and by process after
Information is sent to Database Unit；
The answer content matched with problem, answer thinking and answer detailed process are pushed and are shown by Database Unit.
3. the deep learning intelligent response system based on computer cloud data as claimed in claim 2, it is characterised in that
In the processing authority that social networkies describe the backlog for prestoring user in unit, processing authority is divided at oneself
Specific user's alternate process in reason and permission social circle.
4. the deep learning intelligent response system based on computer cloud data as claimed in claim 3, it is characterised in that
Statistical analysis unit is used for user and there is backlog in certain time period and work of the user in backlog
When outside dynamic region, judge whether the backlog is the backlog for allowing specific user's alternate process in social circle,
If it is the backlog is sent to user social contact circle corresponding other users.
5. the deep learning intelligent response system based on computer cloud data as claimed in claim 1, it is characterised in that
Matching degree between Database Unit vacuum metrics question and answer, and will be anti-with follow-up user satisfaction for this process
Feedback combines, and is provided commonly for the optimization to knowledge base, and the renewal to related content in problem knowledge storehouse and answer knowledge base with
Optimization includes：
After question and answer matching degree evaluation process will between question and answer set up coupling mapping relations, and to candidate answers with ask
The matching degree of topic carries out ranking, several candidate answers in the top is supplied to user and is selected, while allowing user
The answer of problem is evaluated, and the result of evaluation is fed back to question answering system in time carries out the correction of question and answer matching degree and knows
Know the replacement and renewal of knowledge in storehouse.
6. the deep learning intelligent response system based on computer cloud data as claimed in claim 1, it is characterised in that
Mapping relations matrix M in Database Unit between problem knowledge storehouse and key to the issue wordq,kIt is expressed as follows：
Wherein Rq→kRepresent mapping relations therebetween, Qi(i=1...n) problem of representation and its number, Kj(j=1...m) table
Show key to the issue word and its number；One problem can be disassembled and be been described by for multiple key words, while a key word
Can apply in multiple problems；TijThe text is made up of key to the issue word j by (i=1...n, j=1...m) problem of representation i
Content；
Mapping relations matrix M in Database Unit between key to the issue word and answer key wordk,k’It is expressed as follows：
Wherein Rk→k'Represent mapping relations therebetween, Ki(i=1...n) problem of representation key word and its number, K'j(j=
1...m) answer key word and its number are represented；One key to the issue word can correspond to multiple problem answers key words, while
One answer key word can also apply in multiple key to the issue words；Tij(i=1...n, j=1...m) problem of representation is crucial
The content of text answered by answer key word j by word i；
Mapping relations matrix M in Database Unit between answer key word and answerk’,aIt is expressed as follows：
Wherein Rk'→aRepresent mapping relations therebetween, K'i(i=1...n) answer key word and its number, A are representedj(j=
1...m) answer and its number are represented；One answer key word can be in order to describe multiple answers, while an answer can also
It is described with multiple answer key words；Tij(i=1 ... n, j=1...m) represents that answer key word i is described to answer j
Content of text；
Mapping relations matrix M in Database Unit between answer and answer rankinga,rankIt is expressed as follows：
Wherein Ra→rankRepresent mapping relations therebetween, Ai(i=1...n) answer and its number are represented,
Represent the ranking of answer i；
Mapping relations matrix M in Database Unit between answer and user satisfactiona,usIt is expressed as follows：
WhereinRepresent mapping relations therebetween, Ai(i=1...n) answer and its number, U are representeds,j(j=1...m)
Represent user satisfaction and its number；One answer can be evaluated by multiple users, can have multiple user satisfaction,
A user can also be evaluated to multiple answers simultaneously, provide the customer satisfaction evaluation of multiple answers respectively；Pij(i=
1...n, j=1...m) user satisfaction evaluated by answer i is represented by user j.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610910975.7A CN106503123A (en) | 2016-10-20 | 2016-10-20 | A kind of deep learning intelligent response system based on computer cloud data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610910975.7A CN106503123A (en) | 2016-10-20 | 2016-10-20 | A kind of deep learning intelligent response system based on computer cloud data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106503123A true CN106503123A (en) | 2017-03-15 |
Family
ID=58294460
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610910975.7A Pending CN106503123A (en) | 2016-10-20 | 2016-10-20 | A kind of deep learning intelligent response system based on computer cloud data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106503123A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107133303A (en) * | 2017-04-28 | 2017-09-05 | 百度在线网络技术（北京）有限公司 | Method and apparatus for output information |
| CN107368547A (en) * | 2017-06-28 | 2017-11-21 | 西安交通大学 | A kind of intelligent medical automatic question-answering method based on deep learning |
| CN107729468A (en) * | 2017-10-12 | 2018-02-23 | 华中科技大学 | Answer extracting method and system based on deep learning |
| CN108399216A (en) * | 2018-02-07 | 2018-08-14 | 山东浪潮通软信息科技有限公司 | A kind of intelligent assistant's realization method and system based on software function |
| CN108549628A (en) * | 2018-03-16 | 2018-09-18 | 北京云知声信息技术有限公司 | The punctuate device and method of streaming natural language information |
| CN108681560A (en) * | 2018-04-17 | 2018-10-19 | 西安交通大学 | A kind of university student's mobile location information analysis method towards Intelligent campus |
| CN108958247A (en) * | 2018-07-02 | 2018-12-07 | 深圳市益鑫智能科技有限公司 | A kind of guided robot |
| CN109427334A (en) * | 2017-09-01 | 2019-03-05 | 王阅 | A kind of man-machine interaction method and system based on artificial intelligence |
| CN109598658A (en) * | 2018-11-30 | 2019-04-09 | 暨南大学 | A kind of newborn service system and method for entering a school |
| CN113704565A (en) * | 2021-10-28 | 2021-11-26 | 浙江大学 | Learning type space-time index method, device and medium based on global interval error |
| CN116304981A (en) * | 2023-03-09 | 2023-06-23 | 苏州大学 | User data association fusion method and system for multi-source heterogeneous online service platform |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101118554A (en) * | 2007-09-14 | 2008-02-06 | 中兴通讯股份有限公司 | Intelligent interactive request-answering system and processing method thereof |
| CN104699708A (en) * | 2013-12-09 | 2015-06-10 | 中国移动通信集团北京有限公司 | Self-learning method and device for customer service robot |
| CN104933157A (en) * | 2015-06-26 | 2015-09-23 | 百度在线网络技术（北京）有限公司 | Method and device used for obtaining user attribute information, and server |
| CN105488164A (en) * | 2015-11-30 | 2016-04-13 | 北京光年无限科技有限公司 | Question and answer (QA) data processing method and device, intelligent robot |
-
2016
- 2016-10-20 CN CN201610910975.7A patent/CN106503123A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101118554A (en) * | 2007-09-14 | 2008-02-06 | 中兴通讯股份有限公司 | Intelligent interactive request-answering system and processing method thereof |
| CN104699708A (en) * | 2013-12-09 | 2015-06-10 | 中国移动通信集团北京有限公司 | Self-learning method and device for customer service robot |
| CN104933157A (en) * | 2015-06-26 | 2015-09-23 | 百度在线网络技术（北京）有限公司 | Method and device used for obtaining user attribute information, and server |
| CN105488164A (en) * | 2015-11-30 | 2016-04-13 | 北京光年无限科技有限公司 | Question and answer (QA) data processing method and device, intelligent robot |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107133303A (en) * | 2017-04-28 | 2017-09-05 | 百度在线网络技术（北京）有限公司 | Method and apparatus for output information |
| CN107368547A (en) * | 2017-06-28 | 2017-11-21 | 西安交通大学 | A kind of intelligent medical automatic question-answering method based on deep learning |
| CN109427334A (en) * | 2017-09-01 | 2019-03-05 | 王阅 | A kind of man-machine interaction method and system based on artificial intelligence |
| CN107729468A (en) * | 2017-10-12 | 2018-02-23 | 华中科技大学 | Answer extracting method and system based on deep learning |
| CN107729468B (en) * | 2017-10-12 | 2019-12-17 | 华中科技大学 | answer extraction method and system based on deep learning |
| CN108399216A (en) * | 2018-02-07 | 2018-08-14 | 山东浪潮通软信息科技有限公司 | A kind of intelligent assistant's realization method and system based on software function |
| CN108549628A (en) * | 2018-03-16 | 2018-09-18 | 北京云知声信息技术有限公司 | The punctuate device and method of streaming natural language information |
| CN108681560A (en) * | 2018-04-17 | 2018-10-19 | 西安交通大学 | A kind of university student's mobile location information analysis method towards Intelligent campus |
| CN108958247A (en) * | 2018-07-02 | 2018-12-07 | 深圳市益鑫智能科技有限公司 | A kind of guided robot |
| CN109598658A (en) * | 2018-11-30 | 2019-04-09 | 暨南大学 | A kind of newborn service system and method for entering a school |
| CN113704565A (en) * | 2021-10-28 | 2021-11-26 | 浙江大学 | Learning type space-time index method, device and medium based on global interval error |
| CN116304981A (en) * | 2023-03-09 | 2023-06-23 | 苏州大学 | User data association fusion method and system for multi-source heterogeneous online service platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106649524B (en) | A kind of deep learning intelligent response system of the modified based on computer cloud data | |
| CN106503123A (en) | A kind of deep learning intelligent response system based on computer cloud data | |
| CN109241258B (en) | Deep learning intelligent question-answering system applied to tax field | |
| US11710070B2 (en) | Machine learned model framework for screening question generation | |
| WO2021159632A1 (en) | Intelligent questioning and answering method and apparatus, computer device, and computer storage medium | |
| CN110209897B (en) | Intelligent dialogue method, device, storage medium and equipment | |
| CN107291783B (en) | Semantic matching method and intelligent equipment | |
| KR102011870B1 (en) | Server and method for matching employee with employer based on video information | |
| US20190220824A1 (en) | Machine learning systems for matching job candidate resumes with job requirements | |
| CN105824959B (en) | Public opinion monitoring method and system | |
| CN110413783B (en) | Attention mechanism-based judicial text classification method and system | |
| US11372940B2 (en) | Embedding user categories using graphs for enhancing searches based on similarities | |
| CN106991161A (en) | A kind of method for automatically generating open-ended question answer | |
| CN110992988B (en) | Speech emotion recognition method and device based on domain confrontation | |
| KR102117287B1 (en) | Method and apparatus of dialog scenario database constructing for dialog system | |
| CN109635080A (en) | Acknowledgment strategy generation method and device | |
| CN109933650B (en) | Method and system for understanding picture title in operation | |
| CN113886531B (en) | Intelligent question-answer operation determining method, device, computer equipment and storage medium | |
| CN108345612A (en) | A kind of question processing method and device, a kind of device for issue handling | |
| CN108803890A (en) | A kind of input method, input unit and the device for input | |
| CN104778283A (en) | User occupation classification method and system based on microblog | |
| CN107967302A (en) | Game customer service conversational system based on deep neural network | |
| Zheng et al. | A deep learning approach for expert identification in question answering communities | |
| CN109543176A (en) | A kind of abundant short text semantic method and device based on figure vector characterization | |
| CN112132536A (en) | Post recommendation method, system, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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: 20170315 |
|
| RJ01 | Rejection of invention patent application after publication |