CN106649524B - A kind of deep learning intelligent response system of the modified based on computer cloud data - Google Patents
A kind of deep learning intelligent response system of the modified based on computer cloud data Download PDFInfo
- Publication number
- CN106649524B CN106649524B CN201610910988.4A CN201610910988A CN106649524B CN 106649524 B CN106649524 B CN 106649524B CN 201610910988 A CN201610910988 A CN 201610910988A CN 106649524 B CN106649524 B CN 106649524B
- Authority
- CN
- China
- Prior art keywords
- user
- information
- answer
- unit
- sent
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90332—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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A kind of deep learning intelligent response system of the modified based on computer cloud data, comprising: real-time position information is sent to cartographic information delineation unit for positioning to user's real time position 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 also used to depict the complete map of specific region in advance, and the detailed each point of interest marked in the specific region on map；Information receiving unit, for treated, information is sent to Database Unit；Database Unit proposes that the answer knowledge material of problem and answer establishes knowledge base for collecting and arranging each user, handmarking is carried out to story extraction candidate keywords, and to the content of keyword, to carry out subsequent keyword index；Social networks describes unit, for obtain it is 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 robotic technology field, in particular to a kind of modified is based on computer cloud data
Deep learning intelligent response system.
Background technique
Based on mobile Internet platform currently popular, the research for carrying out intelligent answer robot system is one emerging
Research field.The research field being related to include based on mobile Internet platform, user in campus real time position it is dynamic
State variation monitoring, the changing rule of User Activity position and range, the regular course of User Activity is defined to be pushed away with personalized task
Recommend, the fusion of the artificial intelligence knowledge base combined with user context element and question and answer expert system etc. all with mobile Internet
On the relevant technical field of campus intelligent answer robot.
There has been no excavate the campus intelligent answer machine combined with big data for mobile Internet in the prior art
The relevant technologies of device people's system.
Summary of the invention
In view of this, the present invention proposes a kind of deep learning intelligent response system of the modified based on computer cloud data.
A kind of deep learning intelligent response system of the modified based on computer cloud data comprising such as lower unit:
Real-time position information is sent to cartographic information and described by positioning unit for positioning to user's real time position
Unit；
Cartographic information delineation unit, for receiving the real-time position information of positioning unit transmission, and real-time position information shape
At the action trail of user, the action trail of user is segmented, and trajectory segment is described；Based in preset time
The description information of the trajectory segment of user delimit User Activity region；It is also used to depict the complete map of specific region in advance,
And the detailed each point of interest marked in the specific region on map, it is a certain specific in the real-time position information of user
When point of interest, the relevant information of the particular point of interest is pushed；
Information receiving unit is believed for receiving the text query or speech query information of user's input for text query
When breath, by Chinese word segmentation, semantic analysis and the text mining of syntactic analysis and processing, and by treated, information is sent to number
According to library unit；When for speech query information, speech query information is first identified as text query information, and by Chinese point
Word, semantic analysis and the text mining of syntactic analysis and processing, and information is sent to Database Unit by treated；It is being literary
When this query information, by treated, information is sent to Emotion identification unit, when for speech query information, while will be after processing
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；When to be low or sad, the relevant information of particular point of interest is pushed strong
It spends the instruction turned down and is sent to cartographic information delineation unit；
The Emotion identification unit includes following text Emotion identification subelement and voice mood identification subelement:
Text Emotion identification subelement includes that classification storage represents general, low, sad, glad standard vocabulary；
It is trained and is categorized into each classification by vocabulary of the classifier functions to test input, and according to classification
As a result judgment models are established；
Received information is matched with each single context of target word in standard vocabulary, captures semantic comparison
Information, and the mood of text information is judged acquired semantic comparative information；
Voice mood identifies that subelement identification subelement is used to identify the emotional information of voice by speech recognition technology；
Database Unit proposes that the answer knowledge material of problem and answer establishes knowledge for collecting and arranging each user
Library carries out handmarking to story extraction candidate keywords, and to the content of keyword, to carry out subsequent keyword rope
Draw；It is problem knowledge library and answer knowledge base by Knowledge base partition, wherein for storing each of user's proposition in problem knowledge library
Kind of demand and problem there are problems that in answer knowledge base and the demand in problem knowledge library and the answer content to match, answer
Thinking and answer detailed process；And the association of question and answer matching degree assessment is established between problem knowledge library and answer knowledge base, it closes
The matching degree being combined between metric question and answer, and this process is combined with subsequent user satisfaction feedback,
It is provided commonly for the optimization to knowledge base, and update and optimization to related content in problem knowledge library and answer knowledge base；
Social networks describes 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 respectively has different user property and user task,
And the interaction between user constitutes respective customer relationship and social circle.
In deep learning intelligent response system of the modified of the present invention based on computer cloud data comprising such as
Lower unit:
Statistical analysis unit, for according to the description information of the trajectory segment of user, each user in preset time respectively
Respective customer relationship is constituted with the interaction between different user properties and user task and user and social circle is raw
At and save the stroke rule information table of user；It include user in the stroke rule information table of user within each period
The interest of zone of action, activity item and user.
In deep learning intelligent response system of the modified of the present invention based on computer cloud data, the map
Information portrayal unit is also used to when the real-time position information that positioning unit is sent meets the point of interest in specific region, this is emerging
Interest point is sent to statistical analysis unit；
Statistical analysis unit judges at the time point in point of interest item whether to be handled；There are backlogs
When, information receiving unit is sent to the interest point name and backlog；
Information receiving unit passes through Chinese word segmentation, semantic analysis and the text mining of syntactic analysis and processing, and will processing
Information afterwards is sent to Database Unit；
The answer content to match with problem, answer thinking and answer detailed process are pushed and are shown by Database Unit.
In deep learning intelligent response system of the modified of the present invention based on computer cloud data,
The processing authority that the backlog of user is stored in advance in unit is described in social networks, processing authority is divided into certainly
Oneself handles and allows specific user's alternate process in social circle.
In deep learning intelligent response system of the modified of the present invention based on computer cloud data,
Statistical analysis unit there is backlog in a certain period of time for user and user is in backlog
Zone of action except when, judge the backlog whether be allow social circle in specific user's alternate process thing to be processed
, the backlog is if it is sent to corresponding other users in user social contact circle.
In deep learning intelligent response system of the modified of the present invention based on computer cloud data,
The matching degree between question and answer is measured in Database Unit, and this process and subsequent user is satisfied
Degree feedback combines, and is provided commonly for the optimization to knowledge base, and more to related content in problem knowledge library and answer knowledge base
Newly include: with optimization
By the way that after question and answer matching degree evaluation process matching mapping relations will be established between question and answer, and to candidate answers
Ranking is carried out with the matching degree of problem, several candidate answers in the top are supplied to user and are selected, are allowed simultaneously
User evaluates the answer of problem, and the result of evaluation is timely feedbacked to the amendment that question and answer matching degree is carried out to question answering system
With the replacement and update of knowledge in knowledge base.
In deep learning intelligent response system of the modified of the present invention based on computer cloud data,
Mapping relations matrix M in Database Unit between problem knowledge library and key to the issue wordq,kIt is expressed as follows:
Wherein Rq→kIndicate mapping relations between the two, Qi(i=1...n) problem and its number, K are indicatedj(j=
1...m key to the issue word and its number) are indicated；One problem can be disassembled to be described for multiple keywords, while one
Keyword can also apply in multiple problems；Tij(i=1...n, j=1...m) indicates problem i by key to the issue word j institute group
At content of text；
Mapping relations matrix M in Database Unit between key to the issue word and answer keywordk,k’It is expressed as follows:
Wherein Rk→k'Indicate mapping relations between the two, Ki(i=1...n) key to the issue word and its number, K' are indicatedj
(j=1...m) answer keyword and its number are indicated；One key to the issue word can correspond to multiple problem answers keywords,
An answer keyword can also apply in multiple key to the issue words simultaneously；Tij(i=1...n, j=1...m) indicates problem
The content of text that keyword i is answered by answer keyword j；
Mapping relations matrix M in Database Unit between answer keyword and answerk’,aIt is expressed as follows:
Wherein Rk'→aIndicate mapping relations between the two, K'i(i=1...n) answer keyword and its number, A are indicatedj
(j=1...m) answer and its number are indicated；One answer keyword can be to describe multiple answers, while an answer
It can be described with multiple answer keywords；Tij(i=1...n, j=1...m) indicate answer keyword i to answer j into
The content of text of row description；
Mapping relations matrix M in Database Unit between answer and answer rankinga,rankIt is expressed as follows:
Wherein Ra→rankIndicate mapping relations between the two, Ai(i=1...n) answer and its number are indicated,Indicate the ranking of answer i；
Mapping relations matrix M in Database Unit between answer and user satisfactiona,usIt is expressed as follows:
WhereinIndicate mapping relations between the two, Ai(i=1...n) answer and its number, U are indicateds,j(j=
1...m user satisfaction and its number) are indicated；One answer can be evaluated by multiple users, can possess multiple users
Satisfaction, while a user can also evaluate multiple answers, provide the customer satisfaction evaluation of multiple answers respectively；
Pij(i=1...n, j=1...m) indicates the user satisfaction that answer i is evaluated by user j.
Implement deep learning intelligent response system of the modified provided by the invention based on computer cloud data and existing skill
Art, which is compared, has the advantages that the user for assisting in specific region (such as in campus) to be newly added (for example teaches
Teacher and student etc.) faster be familiar with and adapt to environment (such as user where universities and colleges University Environment and cultural atmosphere), preferably with
Friend relation is established between other users, and is movable crowd in specific region by the artificial intelligence knowledge base that situation element is established
Daily life preferably service.So that user faster, is more preferably familiar with specific region internal and external environment, hardware/software infrastructure, area
Domain culture etc., and showed with a series of with question and answer mode progress systematicness.The strong of push can also be adjusted according to the mood of user
Degree, humanization level are higher.
Detailed description of the invention
Fig. 1 is deep learning intelligent response system structure frame of the modified based on computer cloud data of the embodiment of the present invention
Figure.
Specific embodiment
As shown in Figure 1, in view of the drawbacks of the prior art, the invention proposes a kind of modifieds based on computer cloud data
Deep learning intelligent response system comprising such as lower unit:
Real-time position information is sent to cartographic information and described by positioning unit for positioning to user's real time position
Unit.Optionally, positioning unit can realize the function of positioning by app such as mobile phones.
Cartographic information delineation unit, for receiving the real-time position information of positioning unit transmission, and real-time position information shape
At the action trail of user, the action trail of user is segmented, and trajectory segment is described；Based in preset time
The description information of the trajectory segment of user delimit User Activity region；It is also used to depict the complete map of specific region in advance,
And the detailed each point of interest marked in the specific region on map, it is a certain specific in the real-time position information of user
When point of interest, the relevant information of the particular point of interest is pushed.It is alternatively possible to which the algorithm based on user collaborative filtering pushes the spy
Determine the relevant information of point of interest.For example have passed through some point of interest, when being coffee, then push coffee phase in attachment preset range
The information of pass is to user.
The action trail of user is segmented, and trajectory segment is described, for example, user is if it is a university
It is raw, the trajectory segment from dormitory to teaching building is described as " turning out for work ".The above is only schematical.
Information receiving unit is believed for receiving the text query or speech query information of user's input for text query
When breath, by Chinese word segmentation, semantic analysis and the text mining of syntactic analysis and processing, and by treated, information is sent to number
According to library unit；When for speech query information, speech query information is first identified as text query information, and by Chinese point
Word, semantic analysis and the text mining of syntactic analysis and processing, and information is sent to Database Unit by treated；It is being literary
When this query information, by treated, information is sent to Emotion identification unit, when for speech query information, while will be after processing
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；When to be low or sad, the relevant information of particular point of interest is pushed strong
It spends the instruction turned down and is sent to cartographic information delineation unit；
The Emotion identification unit includes following text Emotion identification subelement and voice mood identification subelement:
Text Emotion identification subelement includes that classification storage represents general, low, sad, glad standard vocabulary；
It is trained and is categorized into each classification by vocabulary of the classifier functions to test input, and according to classification
As a result judgment models are established；
Received information is matched with each single context of target word in standard vocabulary, captures semantic comparison
Information, and the mood of text information is judged acquired semantic comparative information；
Voice mood identifies that subelement identification subelement is used to identify the emotional information of voice by speech recognition technology.
Optionally, 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 indicates similarity cosine value, and σ is Dynamic gene.
Database Unit proposes that the answer knowledge material of problem and answer establishes knowledge for collecting and arranging each user
Library carries out handmarking to story extraction candidate keywords, and to the content of keyword, to carry out subsequent keyword rope
Draw；It is problem knowledge library and answer knowledge base by Knowledge base partition, wherein for storing each of user's proposition in problem knowledge library
Kind of demand and problem there are problems that in answer knowledge base and the demand in problem knowledge library and the answer content to match, answer
Thinking and answer detailed process；And the association of question and answer matching degree assessment is established between problem knowledge library and answer knowledge base, it closes
The matching degree being combined between metric question and answer, and this process is combined with subsequent user satisfaction feedback,
It is provided commonly for the optimization to knowledge base, and update and optimization to related content in problem knowledge library and answer knowledge base.
Social networks describes 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 respectively has different user property and user task,
And the interaction between user constitutes respective customer relationship and social circle.Optionally, customer relationship and social circle can draw
It classifies, the user in different grades of social circle has different information browse permissions.
In deep learning intelligent response system of the modified of the present invention based on computer cloud data comprising such as
Lower unit:
Statistical analysis unit, for according to the description information of the trajectory segment of user, each user in preset time respectively
Respective customer relationship is constituted with the interaction between different user properties and user task and user and social circle is raw
At and save the stroke rule information table of user；It include user in the stroke rule information table of user within each period
The interest of zone of action, activity item and user.
In deep learning intelligent response system of the modified of the present invention based on computer cloud data, the map
Information portrayal unit is also used to when the real-time position information that positioning unit is sent meets the point of interest in specific region, this is emerging
Interest point is sent to statistical analysis unit.
Statistical analysis unit judges at the time point in point of interest item whether to be handled；There are backlogs
When, information receiving unit is sent to the interest point name and backlog.
Information receiving unit passes through Chinese word segmentation, semantic analysis and the text mining of syntactic analysis and processing, and will processing
Information afterwards is sent to Database Unit.
The answer content to match with problem, answer thinking and answer detailed process are pushed and are shown by Database Unit.
In deep learning intelligent response system of the modified of the present invention based on computer cloud data,
The processing authority that the backlog of user is stored in advance in unit is described in social networks, processing authority is divided into certainly
Oneself handles and allows specific user's alternate process in social circle.Implement the present embodiment, the use of user can be greatly improved just
Benefit.
In deep learning intelligent response system of the modified of the present invention based on computer cloud data,
Statistical analysis unit there is backlog in a certain period of time for user and user is in backlog
Zone of action except when, judge the backlog whether be allow social circle in specific user's alternate process thing to be processed
, the backlog is if it is sent to corresponding other users in user social contact circle.Embodiment the present embodiment is mentioning
While high convenience for users, safety is also improved.
In deep learning intelligent response system of the modified of the present invention based on computer cloud data,
The matching degree between question and answer is measured in Database Unit, and this process and subsequent user is satisfied
Degree feedback combines, and is provided commonly for the optimization to knowledge base, and more to related content in problem knowledge library and answer knowledge base
Newly include: with optimization
By the way that after question and answer matching degree evaluation process matching mapping relations will be established between question and answer, and to candidate answers
Ranking is carried out with the matching degree of problem, several candidate answers in the top are supplied to user and are selected, are allowed simultaneously
User evaluates the answer of problem, and the result of evaluation is timely feedbacked to the amendment that question and answer matching degree is carried out to question answering system
With the replacement and update of knowledge in knowledge base.
In deep learning intelligent response system of the modified of the present invention based on computer cloud data,
Mapping relations matrix M in Database Unit between problem knowledge library and key to the issue wordq,kIt is expressed as follows:
Wherein Rq→kIndicate mapping relations between the two, Qi(i=1...n) problem and its number, K are indicatedj(j=
1...m key to the issue word and its number) are indicated；One problem can be disassembled to be described for multiple keywords, while one
Keyword can also apply in multiple problems；Tij(i=1...n, j=1...m) indicates problem i by key to the issue word j institute group
At content of text；
Mapping relations matrix M in Database Unit between key to the issue word and answer keywordk,k’It is expressed as follows:
Wherein Rk→k'Indicate mapping relations between the two, Ki(i=1...n) key to the issue word and its number, K' are indicatedj
(j=1...m) answer keyword and its number are indicated；One key to the issue word can correspond to multiple problem answers keywords,
An answer keyword can also apply in multiple key to the issue words simultaneously；Tij(i=1...n, j=1...m) indicates problem
The content of text that keyword i is answered by answer keyword j；
Mapping relations matrix M in Database Unit between answer keyword and answerk’,aIt is expressed as follows:
Wherein Rk'→aIndicate mapping relations between the two, K'i(i=1...n) answer keyword and its number, A are indicatedj
(j=1...m) answer and its number are indicated；One answer keyword can be to describe multiple answers, while an answer
It can be described with multiple answer keywords；Tij(i=1...n, j=1...m) indicate answer keyword i to answer j into
The content of text of row description；
Mapping relations matrix M in Database Unit between answer and answer rankinga,rankIt is expressed as follows:
Wherein Ra→rankIndicate mapping relations between the two, Ai(i=1...n) answer and its number are indicated,Indicate the ranking of answer i；
Mapping relations matrix M in Database Unit between answer and user satisfactiona,usIt is expressed as follows:
WhereinIndicate mapping relations between the two, Ai(i=1...n) answer and its number, U are indicateds,j(j=
1...m user satisfaction and its number) are indicated；One answer can be evaluated by multiple users, can possess multiple users
Satisfaction, while a user can also evaluate multiple answers, provide the customer satisfaction evaluation of multiple answers respectively；
Pij(i=1...n, j=1...m) indicates the user satisfaction that answer i is evaluated by user j.
Implement deep learning intelligent response system of the modified provided by the invention based on computer cloud data and existing skill
Art, which is compared, has the advantages that the user for assisting in specific region (such as in campus) to be newly added (for example teaches
Teacher and student etc.) faster be familiar with and adapt to environment (such as user where universities and colleges University Environment and cultural atmosphere), preferably with
Friend relation is established between other users, and is movable crowd in specific region by the artificial intelligence knowledge base that situation element is established
Daily life preferably service.So that user faster, is more preferably familiar with specific region internal and external environment, hardware/software infrastructure, area
Domain culture etc., and showed with a series of with question and answer mode progress systematicness.
It is understood that for those of ordinary skill in the art, can do in accordance with the technical idea of the present invention
Various other changes and modifications out, and all these changes and deformation all should belong to the protection model of the claims in the present invention
It encloses.
Claims (5)
1. a kind of deep learning intelligent response system of modified based on computer cloud data, which is characterized in that it includes as follows
Unit:
Real-time position information is sent to cartographic information delineation unit for positioning to user's real time position 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 segmented, and trajectory segment is described by the action trail at family；Based on user in preset time
Trajectory segment description information delimit User Activity region；It is also used to depict the complete map of specific region in advance, and
The 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
When point, the relevant information of the particular point of interest is pushed；
Information receiving unit, for receiving the text query or speech query information of user's input, when for text query information,
By Chinese word segmentation, semantic analysis and the text mining of syntactic analysis and processing, and by treated, information is sent to database
Unit；When for speech query information, speech query information is first identified as text query information, and pass through Chinese word segmentation, language
The text mining and processing of justice analysis and syntactic analysis, and information is sent to Database Unit by treated；It is looked into for text
When asking information, will treated that information is sent to Emotion identification unit, when for speech query information, while will treated believes
Breath and speech query information are sent to Emotion identification unit；
Emotion identification unit, the information for being sent according to information receiving unit judge the emotional state of user, the mood of user
State is divided into general, low, sad, glad；When to be low or sad, the relevant information of particular point of interest is pushed into intensity tune
Low instruction is sent to cartographic information delineation unit；
The Emotion identification unit includes following text Emotion identification subelement and voice mood identification subelement:
Text Emotion identification subelement includes that classification storage represents general, low, sad, glad standard vocabulary；
It is trained and is categorized into each classification by vocabulary of the classifier functions to test input, and according to the result of classification
Establish judgment models；
Received information is matched with each single context of target word in standard vocabulary, captures semantic comparison letter
Breath, and the mood of text information is judged acquired semantic comparative information；
Voice mood identifies that subelement identification subelement is used to identify the emotional information of voice by speech recognition technology；
Database Unit proposes that the answer knowledge material of problem and answer establishes knowledge base for collecting and arranging each user,
Handmarking is carried out to story extraction candidate keywords, and to the content of keyword, to carry out subsequent keyword index；It will
Knowledge base partition is problem knowledge library and answer knowledge base, wherein for storing the various demands of user's proposition in problem knowledge library
And problem, there are problems that in answer knowledge base with the demand in problem knowledge library and the answer content to match, answer thinking and
Answer detailed process；And the association of question and answer matching degree assessment is established between problem knowledge library and answer knowledge base, association is used for
Matching degree between metric question and answer, and this process is combined with subsequent user satisfaction feedback, it is common to use
In the optimization to knowledge base, and update and optimization to related content in problem knowledge library and answer knowledge base；
Social networks describes unit, for obtain between the user in specific region it is interrelated and influence each other and user it
Between the different social role of performer, so that it is determined that each user respectively has different user property and user task, and
Interaction between user constitutes respective customer relationship and social circle；
Statistical analysis unit, for respectively being had 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
Save the stroke rule information table of user；It include activity of the user within each period in the stroke rule information table of user
The interest in region, activity item and user.
2. deep learning intelligent response system of the modified as described in claim 1 based on computer cloud data, feature exist
In the cartographic information delineation unit is also used to meet the interest in specific region in the real-time position information that positioning unit is sent
When point, which is sent to statistical analysis unit；
Statistical analysis unit judges at the time point in point of interest item whether to be handled；When there are backlog,
Information receiving unit is sent to the interest point name and backlog；
Information receiving unit passes through Chinese word segmentation, semantic analysis and the text mining of syntactic analysis and processing, and by treated
Information is sent to Database Unit；
The answer content to match with problem, answer thinking and answer detailed process are pushed and are shown by Database Unit.
3. deep learning intelligent response system of the modified as claimed in claim 2 based on computer cloud data, feature exist
In,
The processing authority that the backlog of user is stored in advance in unit is described in social networks, processing authority is divided at oneself
Specific user's alternate process in reason and permission social circle.
4. deep learning intelligent response system of the modified as claimed in claim 3 based on computer cloud data, feature exist
In,
Statistical analysis unit there is backlog in a certain period of time for user and user is in the work of backlog
When except 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 corresponding other users in user social contact circle.
5. deep learning intelligent response system of the modified as described in claim 1 based on computer cloud data, feature exist
In,
The matching degree between question and answer is measured in Database Unit, and this process and subsequent user satisfaction is anti-
Feedback combines, and is provided commonly for the optimization to knowledge base, and to the update of related content in problem knowledge library and answer knowledge base with
Optimization includes:
By after question and answer matching degree evaluation process will between question and answer establish matching mapping relations, and to candidate answers with ask
The matching degree of topic carries out ranking, several candidate answers in the top are supplied to user and are selected, while allowing user
The answer of problem is evaluated, and the result of evaluation is timely feedbacked and carries out the amendment of question and answer matching degree to question answering system and knows
Know the replacement and update of knowledge in library.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610910988.4A CN106649524B (en) | 2016-10-20 | 2016-10-20 | A kind of deep learning intelligent response system of the modified based on computer cloud data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610910988.4A CN106649524B (en) | 2016-10-20 | 2016-10-20 | A kind of deep learning intelligent response system of the modified based on computer cloud data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106649524A CN106649524A (en) | 2017-05-10 |
| CN106649524B true CN106649524B (en) | 2019-11-22 |
Family
ID=58856032
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610910988.4A Active CN106649524B (en) | 2016-10-20 | 2016-10-20 | A kind of deep learning intelligent response system of the modified based on computer cloud data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106649524B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107301168A (en) * | 2017-06-01 | 2017-10-27 | 深圳市朗空亿科科技有限公司 | Intelligent robot and its mood exchange method, system |
| CN109997127B (en) * | 2017-06-05 | 2023-07-18 | 谷歌有限责任公司 | Logical segment data processing system |
| CN109145092B (en) * | 2017-06-15 | 2022-05-17 | 阿里巴巴集团控股有限公司 | Database updating and intelligent question and answer management method, device and equipment |
| CN107590274A (en) * | 2017-09-27 | 2018-01-16 | 合肥博力生产力促进中心有限公司 | A kind of intelligent Answer System for patent service |
| CN108038230B (en) * | 2017-12-26 | 2022-05-20 | 北京百度网讯科技有限公司 | Information generation method and device based on artificial intelligence |
| CN108717413B (en) * | 2018-03-26 | 2021-10-08 | 浙江大学 | Open field question-answering method based on hypothetical semi-supervised learning |
| CN110727793B (en) * | 2018-06-28 | 2023-03-24 | 百度在线网络技术（北京）有限公司 | Method, device, terminal and computer readable storage medium for area identification |
| 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 |
| CN109145084B (en) * | 2018-07-10 | 2022-07-01 | 创新先进技术有限公司 | Data processing method, data processing device and server |
| CN109299240B (en) * | 2018-09-30 | 2022-02-25 | 北京小谛机器人科技有限公司 | Chat robot knowledge display method and device |
| CN109598658B (en) * | 2018-11-30 | 2023-05-02 | 暨南大学 | New-use entrance service system and method |
| CN109815322B (en) * | 2018-12-27 | 2021-03-12 | 东软集团股份有限公司 | Response method and device, storage medium and electronic equipment |
| CN110046903A (en) * | 2019-01-15 | 2019-07-23 | 阿里巴巴集团控股有限公司 | Data processing method, system, server and readable storage medium storing program for executing |
| WO2021056127A1 (en) * | 2019-09-23 | 2021-04-01 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for analyzing sentiment |
| CN114706795A (en) * | 2022-06-07 | 2022-07-05 | 湖南智擎科技有限公司 | Turing test method, device and system for SaaS artificial intelligence application |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103823844A (en) * | 2014-01-26 | 2014-05-28 | 北京邮电大学 | Question forwarding system and question forwarding method on the basis of subjective and objective context and in community question-and-answer service |
| 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 |
| CN104836720A (en) * | 2014-02-12 | 2015-08-12 | 北京三星通信技术研究有限公司 | Method for performing information recommendation in interactive communication, and device |
| CN104834679A (en) * | 2015-04-14 | 2015-08-12 | 苏州大学 | Representation and inquiry method of behavior track and device therefor |
| 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 |
| CN105023047A (en) * | 2014-04-15 | 2015-11-04 | 上海莫言信息科技有限公司 | Tourism service individuation online ordering realization method based on travel itinerary |
-
2016
- 2016-10-20 CN CN201610910988.4A patent/CN106649524B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN103823844A (en) * | 2014-01-26 | 2014-05-28 | 北京邮电大学 | Question forwarding system and question forwarding method on the basis of subjective and objective context and in community question-and-answer service |
| CN104836720A (en) * | 2014-02-12 | 2015-08-12 | 北京三星通信技术研究有限公司 | Method for performing information recommendation in interactive communication, and device |
| CN105023047A (en) * | 2014-04-15 | 2015-11-04 | 上海莫言信息科技有限公司 | Tourism service individuation online ordering realization method based on travel itinerary |
| CN104834679A (en) * | 2015-04-14 | 2015-08-12 | 苏州大学 | Representation and inquiry method of behavior track and device therefor |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106649524A (en) | 2017-05-10 |
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 | |
| CN110148318B (en) | Digital teaching assistant system, information interaction method and information processing method | |
| CN105843875B (en) | A kind of question and answer data processing method and device towards intelligent robot | |
| CN106570708B (en) | Management method and system of intelligent customer service knowledge base | |
| WO2021159632A1 (en) | Intelligent questioning and answering method and apparatus, computer device, and computer storage medium | |
| CN104850539B (en) | A kind of natural language understanding method and the tourism question answering system based on this method | |
| CN106095833B (en) | Human-computer dialogue content processing method | |
| CN110209897B (en) | Intelligent dialogue method, device, storage medium and equipment | |
| KR102011870B1 (en) | Server and method for matching employee with employer based on video information | |
| CN105808590B (en) | Search engine implementation method, searching method and device | |
| CN107818164A (en) | A kind of intelligent answer method and its system | |
| CN106777257B (en) | Intelligent dialogue model construction system and method based on dialect | |
| CN109308319B (en) | Text classification method, text classification device and computer readable storage medium | |
| CN110175227A (en) | A kind of dialogue auxiliary system based on form a team study and level reasoning | |
| CN105068661A (en) | Man-machine interaction method and system based on artificial intelligence | |
| US11216725B2 (en) | Data searching system and method | |
| CN110321564B (en) | Multi-round dialogue intention recognition method | |
| JP2014522540A (en) | Microblog sequencing, search, display method and system | |
| CN106649404B (en) | Method and device for creating session scene database | |
| CN112364234B (en) | Automatic grouping system for online discussion | |
| CN109635080A (en) | Acknowledgment strategy generation method and device | |
| CN109271523A (en) | A kind of government document subject classification method based on information retrieval | |
| CN109325780A (en) | A kind of exchange method of the intelligent customer service system in E-Governance Oriented field | |
| CN109559576A (en) | A kind of children companion robot and its early teaching system self-learning method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20191029 Address after: Room 307, Zijin Oriental Building, 288 Qiyue Street, Suzhou Industrial Park, Jiangsu Province Applicant after: TIANJU DIHE (SUZHOU) DATA CO.,LTD. Address before: Room 6, building 999, No. 315000, South Ring Road, Jiangdong District, Ningbo, Zhejiang, China Applicant before: NINGBO JIANGDONG DAJIN BAIHUI INFORMATION TECHNOLOGY CO.,LTD. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Room 307, Zijin Oriental building, No. 288, Qiyue street, Suzhou Industrial Park, Suzhou, Jiangsu 215000 Patentee after: Tianju DIHE (Suzhou) Technology Co.,Ltd. Address before: Room 307, Zijin Oriental building, No. 288, Qiyue street, Suzhou Industrial Park, Suzhou, Jiangsu 215000 Patentee before: TIANJU DIHE (SUZHOU) DATA CO.,LTD. |