CN106663131A - Personalized response generating method and personalized response generating system based on user portrait - Google Patents
Personalized response generating method and personalized response generating system based on user portrait Download PDFInfo
- Publication number
- CN106663131A CN106663131A CN201680001748.0A CN201680001748A CN106663131A CN 106663131 A CN106663131 A CN 106663131A CN 201680001748 A CN201680001748 A CN 201680001748A CN 106663131 A CN106663131 A CN 106663131A
- Authority
- CN
- China
- Prior art keywords
- user
- answer
- portrait
- module
- candidate
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
-
- 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
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Electrically Operated Instructional Devices (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a personalized response generating method and a personalized response generating system based on user portrait. The personalized response generating method comprises steps that S1: user input adopts multi-mode input, and the multi-mode input conversion of the multi-mode input is carried out, and a text question is generated after the conversion; S2: candidate answers are generated generated according to the converted text question, and every candidate answer is scored; S3: the similarity calculation between the vector generated by the user portrait and the vector of every candidate answer is carried out; S4: the weighting summation and the rearrangement of the similarity calculated by the S3 and the score generated by the S2 are carried out, and the candidate answer having the highest score is used as the final output answer. By adopting the user portrait way, the answer of the question is provided, and the function of personalized response is satisfied.
Description
Technical field
The present invention relates to technical field of data processing, and more particularly to a kind of personalized answer life drawn a portrait based on user
Into method and system.
Background technology
User draws a portrait, and is also called user role (Persona), is that one kind is delineated targeted customer, contact user's demand and set
The effective tool in meter direction.For example in product development, can be used to position product and planned;When implementing, can
Gathered so that user is drawn a portrait as the label (tag) for portraying user characteristics, for example:The primary attributes such as age, sex, educational background, or
Interest characteristics of person user etc.;In product promotion, potential customers colony can be excavated according to user's portrait, be carried out targetedly
Products Show.With the continuous development of information technology, user's portrait is also gradually applied in more areas.
As people are continuously increased to the demand for quickly and accurately obtaining information, at artificial intelligence and natural language
The question answering system in reason field is gradually risen, and it can allow user to put question to (complete and colloquial question sentence) with natural language, and be use
Family returns a succinct, accurate answer.But existing question and answer are all that the judgement answered by question sentence is generated, for
Family is with no personalization, and Consumer's Experience not enough enriches.
The content of the invention
For the deficiencies in the prior art, the present invention is provided a kind of personalized answer generation method drawn a portrait based on user and is
System, by the way of by user's portrait vector in combination with tradition answers vector, obtains that there is personalized answer to generate, and realizes
The individualized experience of question and answer.
To solve above-mentioned technical problem, the present invention is provided a kind of personalization drawn a portrait based on user and answers generation method, bag
Include:Step 1:The multi-modal input of user input, and multi-modal input conversion is carried out to the multi-modal input, it is translated into text
This problem;Step 2:Carry out answering according to the text question of the conversion and generate candidate answers, and each candidate to generating
Answer is given a mark;Step 3:The draw a portrait vector of vector sum each candidate answers for generating of user is carried out into Similarity Measure;
Step 4:The fraction that the similarity that the step 3 is calculated draws with the step 2 is weighted and is added, resets, and by score
Highest candidate answers the answer as final output.
Preferably, step 2-4 is to perform on the server.
The present invention also provides a kind of personalized answer generation method drawn a portrait based on user, it is characterised in that include:Step
1:User input text question;Step 2:Carry out answering according to the text question and generate candidate answers, and it is each to what is generated
Individual candidate answers are given a mark;Step 3:The draw a portrait vector of vector sum each candidate answers for generating of user is carried out into similarity
Calculate;Step 4:The fraction that the similarity that the step 3 is calculated draws with the step 2 is weighted and is added, resets, and will
The candidate of highest scoring answers the answer as final output.
Preferably, step 2-4 is to perform on the server.
To solve above-mentioned technical problem, the present invention also provides a kind of personalized answer generation system drawn a portrait based on user,
Including:Multi-modal input conversion module, is converted into text and asks for the multi-modal input of user input to be carried out into multi-modal input
Topic;Generation module is answered, for carrying out answer generation according to the text question of the conversion, and each candidate to generating answers
Case is given a mark;User draws a portrait similarity calculation module, vector sum each candidate answers generated for user to be drawn a portrait
Vector carries out Similarity Measure;And answer output module, for by the similarity of the calculating and the answer generation module
The fraction for drawing is weighted addition, resets, and the candidate of highest scoring is answered as final result output.
Preferably, the answer generation module, user's portrait similarity calculation module and answer output module are in service
On device.
To solve above-mentioned technical problem, the present invention also provides a kind of personalized answer generation system drawn a portrait based on user,
Including:Problem input module, answer generation module, user's portrait similarity calculation module and answer output module.Wherein, ask
Topic input module, the problem for receiving user's input is simultaneously sent to question and answer generation module;Generation module is answered, for according to defeated
The text question for entering carries out answer generation, and each candidate answers to generating are given a mark;User's portrait Similarity Measure
Module, for the draw a portrait vector of vector sum each candidate answers for generating of user to be carried out into Similarity Measure;And answer is defeated
Go out module, for will calculate similarity as another fraction, be weighted with the fraction that traditional approach draws and be added, weigh
Row, and the candidate of highest scoring is answered as final result output.
Preferably, the answer generation module, user's portrait similarity calculation module and answer output module are in service
On device.
In general, compared to prior art, technical scheme has the advantages that:
1st, carry out answering by user's portrait and generate the characteristics of meeting personalization;
2nd, user's portrait vector is carried out into Similarity Measure with candidate answers vector, and by the similarity for calculating and tradition side
The answer fraction that formula is obtained is weighted, and the answer for obtaining is more accurate.
Description of the drawings
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
The accompanying drawing to be used needed for having technology description is briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is the personalized flow chart for answering generation method drawn a portrait based on user that one embodiment of the invention is provided;
Fig. 2 is the personalized structural representation for answering generation system drawn a portrait based on user that one embodiment of the invention is provided
Figure;
Fig. 3 is the personalized structural representation for answering generation system drawn a portrait based on user that another embodiment of the present invention is provided
Figure.
Specific embodiment
In order that the objects, technical solutions and advantages of the present invention become more apparent, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only to explain the present invention, and
It is not used in the restriction present invention.
Fig. 1 show the personalized flow process for answering generation method drawn a portrait based on user of one embodiment of the invention offer
Figure, comprises the following steps:
Step 1:The multi-modal input of user input, and the multi-modal input to being input into carries out multi-modal input conversion, by it
It is converted into text question.For example, user input voice, and the voice to being input into carries out voice conversion, is translated into text and asks
Topic.Note that " multi-modal input " as referred to herein including but not limited to, video, face, expression, scene, vocal print, fingerprint, rainbow
Film pupil, light sensation, etc. information.
Step 2:Carry out answering according to the text question of conversion and generate candidate answers, and each candidate answers to generating
Given a mark.In embodiments of the present invention, answer generation can be carried out using traditional answer generating mode;
Step 3:The draw a portrait vector of vector sum each candidate answers for generating of user is carried out into Similarity Measure;
Step 4:The similarity that above-mentioned steps 3 are calculated is carried out as another fraction with the fraction that traditional approach draws
Weighting summation, rearrangement, and answer the answer as final output using the candidate of highest scoring.
Wherein, in the step 1, user can also directly input text question, and step 1-4 can be held in server
OK.That is, input voice and voice are not necessary the step of conversion.
Fig. 2 is shown the personalized structure for answering generation system drawn a portrait based on user of one embodiment of the invention offer and is shown
Be intended to, including it is multi-modal input conversion module (for example, phonetic entry conversion module), answer generation module, user portrait it is similar
Degree computing module and answer output module.Wherein, phonetic entry conversion module, for the voice of user input to be carried out into voice
Conversion, is translated into text question;Generation module is answered, it is for carrying out answer generation according to the text question of conversion and right
Each candidate answers for generating are given a mark;User's portrait similarity calculation module, the vector generated for user to be drawn a portrait
Similarity Measure is carried out with the vector of each candidate answers;And answer output module, for will calculate similarity as
Another fraction, is weighted with the fraction that traditional approach draws and is added, resets, and the candidate of highest scoring is answered as most
Whole answer output.
Fig. 3 show the personalized structure for answering generation system drawn a portrait based on user of another embodiment of the present invention offer
Schematic diagram, including problem input module, answer generation module, user's portrait similarity calculation module and answer output module.
Wherein, problem input module, the problem for receiving user's input is simultaneously sent to question and answer generation module;Generation module is answered, is used
In carrying out answer generation according to the text question of input, and each candidate answers to generating are given a mark;User's portrait phase
Like degree computing module, for the draw a portrait vector of vector sum each candidate answers for generating of user to be carried out into Similarity Measure;With
And answer output module, for will calculate similarity as another fraction, be weighted with the fraction that traditional approach draws
It is added, resets, and the candidate of highest scoring is answered as final result output.
In one embodiment, the answer generation module, user's portrait similarity calculation module and answer output module
It is on the server.
The personalized answer generation method drawn a portrait based on user and system that the present invention is provided, by way of user draws a portrait
Answer in realize question and answer is generated, and can meet the function of personalized answer.
Presently preferred embodiments of the present invention is the foregoing is only, not to limit the present invention, all essences in the present invention
Any modification, equivalent and improvement made within god and principle etc., should be included within the scope of the present invention.
Claims (8)
1. generation method is answered in a kind of personalization drawn a portrait based on user, it is characterised in that included:
Step 1:The multi-modal input of user input, and multi-modal input conversion is carried out to the multi-modal input, it is translated into
Text question;
Step 2:Carry out answering according to the text question of the conversion and generate candidate answers, and each candidate answers to generating
Given a mark;
Step 3:The draw a portrait vector of vector sum each candidate answers for generating of user is carried out into Similarity Measure;
Step 4:The fraction that the similarity that the step 3 is calculated draws with the step 2 is weighted and is added, resets, and will
The candidate of highest scoring answers the answer as final output.
2. it is as claimed in claim 1 to answer generation method based on the personalized of user's portrait, it is characterised in that step 2-
4 is to perform on the server.
3. generation method is answered in a kind of personalization drawn a portrait based on user, it is characterised in that included:
Step 1:User input text question;
Step 2:Carry out answering according to the text question and generate candidate answers, and each candidate answers to generating carry out beating
Point;
Step 3:The draw a portrait vector of vector sum each candidate answers for generating of user is carried out into Similarity Measure;
Step 4:The fraction that the similarity that the step 3 is calculated draws with the step 2 is weighted and is added, resets, and will
The candidate of highest scoring answers the answer as final output.
4. it is as claimed in claim 3 to answer generation method based on the personalized of user's portrait, it is characterised in that step 2-
4 is to perform on the server.
5. generation system is answered in a kind of personalization drawn a portrait based on user, it is characterised in that included:
Multi-modal input conversion module, is converted into text and asks for the multi-modal input of user input to be carried out into multi-modal input
Topic;
Generation module is answered, for carrying out answer generation, and each candidate to generating according to the text question of the conversion
Answer is given a mark;
User draws a portrait similarity calculation module, for the draw a portrait vector of vector sum each candidate answers for generating of user to be carried out
Similarity Measure;And
Answer output module, for the fraction that the similarity of the calculating draws with the answer generation module to be weighted into phase
Plus, reset, and the candidate of highest scoring is answered as final result output.
6. it is as claimed in claim 5 to answer generation system based on the personalized of user's portrait, it is characterised in that the answer life
It is on the server into module, user's portrait similarity calculation module and answer output module.
7. generation system is answered in a kind of personalization drawn a portrait based on user, it is characterised in that included:
Problem input module, for the text question of receiving user's input;
Generation module is answered, for carrying out answer generation according to the text question, and each candidate answers to generating are entered
Row marking;
User draws a portrait similarity calculation module, for the draw a portrait vector of vector sum each candidate answers for generating of user to be carried out
Similarity Measure;And
Answer output module, for the fraction that the similarity of the calculating draws with the answer generation module to be weighted into phase
Plus, reset, and the candidate of highest scoring is answered as final result output.
8. it is as claimed in claim 7 to answer generation system based on the personalized of user's portrait, it is characterised in that the answer life
It is on the server into module, user's portrait similarity calculation module and answer output module.
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/CN2016/087755 WO2018000270A1 (en) | 2016-06-29 | 2016-06-29 | Personalized response generating method and system based on profile |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106663131A true CN106663131A (en) | 2017-05-10 |
Family
ID=58838407
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201680001748.0A Pending CN106663131A (en) | 2016-06-29 | 2016-06-29 | Personalized response generating method and personalized response generating system based on user portrait |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN106663131A (en) |
WO (1) | WO2018000270A1 (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108875055A (en) * | 2018-06-28 | 2018-11-23 | 联想(北京)有限公司 | A kind of answer providing method and equipment |
CN109376361A (en) * | 2018-11-16 | 2019-02-22 | 北京九狐时代智能科技有限公司 | A kind of intension recognizing method and device |
CN110457440A (en) * | 2019-08-09 | 2019-11-15 | 宝宝树(北京)信息技术有限公司 | A kind of method, apparatus, equipment and medium feeding back answer |
CN110674276A (en) * | 2019-09-23 | 2020-01-10 | 深圳前海微众银行股份有限公司 | Robot self-learning method, robot terminal, device and readable storage medium |
CN111741104A (en) * | 2020-06-18 | 2020-10-02 | 腾讯科技(深圳)有限公司 | Method for determining response message, method for configuring response message, device, equipment and storage medium |
CN111858716A (en) * | 2020-07-24 | 2020-10-30 | 厦门至恒融兴信息技术有限公司 | Automatic flow processing technology for mass financial payment data |
CN115190336A (en) * | 2022-06-27 | 2022-10-14 | 青软创新科技集团股份有限公司 | Crowdsourcing type network teaching oriented live broadcast connection method and system |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110109961A (en) * | 2019-05-10 | 2019-08-09 | 宜信博诚保险销售服务(北京)股份有限公司 | User's portrait acquisition methods and device, customer requirement retrieval method and device |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103761286A (en) * | 2014-01-14 | 2014-04-30 | 河南科技大学 | Method for retrieving service resources on basis of user interest |
CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术(北京)有限公司 | Man-machine interaction method and system based on artificial intelligence |
CN105183803A (en) * | 2015-08-25 | 2015-12-23 | 天津大学 | Personalized search method and search apparatus thereof in social network platform |
CN105487663A (en) * | 2015-11-30 | 2016-04-13 | 北京光年无限科技有限公司 | Intelligent robot oriented intention identification method and system |
CN105574133A (en) * | 2015-12-15 | 2016-05-11 | 苏州贝多环保技术有限公司 | Multi-mode intelligent question answering system and method |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103729424B (en) * | 2013-12-20 | 2017-03-15 | 百度在线网络技术(北京)有限公司 | Evaluation method and system is answered in Ask-Answer Community |
CN105095357A (en) * | 2015-06-24 | 2015-11-25 | 百度在线网络技术(北京)有限公司 | Method and device for processing consultation data |
CN105243143B (en) * | 2015-10-14 | 2018-07-24 | 湖南大学 | Recommendation method and system based on real-time phonetic content detection |
-
2016
- 2016-06-29 WO PCT/CN2016/087755 patent/WO2018000270A1/en active Application Filing
- 2016-06-29 CN CN201680001748.0A patent/CN106663131A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103761286A (en) * | 2014-01-14 | 2014-04-30 | 河南科技大学 | Method for retrieving service resources on basis of user interest |
CN105183803A (en) * | 2015-08-25 | 2015-12-23 | 天津大学 | Personalized search method and search apparatus thereof in social network platform |
CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术(北京)有限公司 | Man-machine interaction method and system based on artificial intelligence |
CN105487663A (en) * | 2015-11-30 | 2016-04-13 | 北京光年无限科技有限公司 | Intelligent robot oriented intention identification method and system |
CN105574133A (en) * | 2015-12-15 | 2016-05-11 | 苏州贝多环保技术有限公司 | Multi-mode intelligent question answering system and method |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108875055A (en) * | 2018-06-28 | 2018-11-23 | 联想(北京)有限公司 | A kind of answer providing method and equipment |
CN108875055B (en) * | 2018-06-28 | 2021-12-24 | 联想(北京)有限公司 | Answer providing method and equipment |
CN109376361A (en) * | 2018-11-16 | 2019-02-22 | 北京九狐时代智能科技有限公司 | A kind of intension recognizing method and device |
CN110457440A (en) * | 2019-08-09 | 2019-11-15 | 宝宝树(北京)信息技术有限公司 | A kind of method, apparatus, equipment and medium feeding back answer |
CN110674276A (en) * | 2019-09-23 | 2020-01-10 | 深圳前海微众银行股份有限公司 | Robot self-learning method, robot terminal, device and readable storage medium |
CN111741104A (en) * | 2020-06-18 | 2020-10-02 | 腾讯科技(深圳)有限公司 | Method for determining response message, method for configuring response message, device, equipment and storage medium |
CN111858716A (en) * | 2020-07-24 | 2020-10-30 | 厦门至恒融兴信息技术有限公司 | Automatic flow processing technology for mass financial payment data |
CN111858716B (en) * | 2020-07-24 | 2023-10-13 | 厦门至恒融兴信息技术有限公司 | Automatic flow processing technology for massive financial payment data |
CN115190336A (en) * | 2022-06-27 | 2022-10-14 | 青软创新科技集团股份有限公司 | Crowdsourcing type network teaching oriented live broadcast connection method and system |
CN115190336B (en) * | 2022-06-27 | 2023-02-28 | 青软创新科技集团股份有限公司 | Crowdsourcing type network teaching oriented live broadcast connection method and system |
Also Published As
Publication number | Publication date |
---|---|
WO2018000270A1 (en) | 2018-01-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106663131A (en) | Personalized response generating method and personalized response generating system based on user portrait | |
CN109065055B (en) | Method, storage medium, and apparatus for generating AR content based on sound | |
Rincon et al. | A new emotional robot assistant that facilitates human interaction and persuasion | |
CN106489148A (en) | A kind of intention scene recognition method that is drawn a portrait based on user and system | |
CN114818691A (en) | Article content evaluation method, device, equipment and medium | |
Kryvonos et al. | Methods to create systems for the analysis and synthesis of communicative information | |
Jia et al. | A multimodal human-computer interaction system and its application in smart learning environments | |
CN114969282B (en) | Intelligent interaction method based on rich media knowledge graph multi-modal emotion analysis model | |
Irfan et al. | Dynamic emotional language adaptation in multiparty interactions with agents | |
Rozaliev et al. | Methods and Models for Identifying Human Emotions by Recognition Gestures and Motion | |
Stocky et al. | Shared reality: Spatial intelligence in intuitive user interfaces | |
CN116883608B (en) | Multi-mode digital person social attribute control method and related device | |
Kesarwani et al. | Student Chatbot System: A Review on Educational Chatbot | |
Le-Tien et al. | Developing a Chatbot system using Deep Learning based for Universities consultancy | |
Qi-rong | Research on intelligent tutoring system based on affective model | |
Wanner et al. | Towards a multimedia knowledge-based agent with social competence and human interaction capabilities | |
Lokeshwar et al. | An App to Assist Differently Abled People | |
Amini et al. | Modeling Rapport for Conversations About Health with Autonomous Avatars from Video Corpus of Clinician-Client Therapy Sessions | |
Bogdan et al. | Intelligent assistant for people with low vision abilities | |
Sumi | Affective Human Computer Interaction. | |
Binder | Episodic and semantic memory for interactions with voice-based conversational agents: developing an integrative model of technology engagement and cognitive elaboration | |
Rekha et al. | Mobile translation system from speech language to hand motion language | |
Tarawneh et al. | An Infrastructure for Studying the Role of Sentiment in Human-Robot Interaction | |
Ichimura et al. | Emotion orientated recommendation system for Hiroshima tourist by fuzzy Petri Net | |
CN116959448A (en) | Speech recognition method, device, storage medium and electronic equipment |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: Room 301, Building 39, 239 Renmin Road, Gusu District, Suzhou City, Jiangsu Province, 215000 Applicant after: Suzhou Dogweed Intelligent Technology Co., Ltd. Address before: 518000 Dongfang Science and Technology Building 1307-09, 16 Keyuan Road, Yuehai Street, Nanshan District, Shenzhen City, Guangdong Province Applicant before: Shenzhen green bristlegrass intelligence Science and Technology Ltd. |
|
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170510 |