CN106326440B - A kind of man-machine interaction method and device towards intelligent robot - Google Patents
A kind of man-machine interaction method and device towards intelligent robot Download PDFInfo
- Publication number
- CN106326440B CN106326440B CN201610730823.9A CN201610730823A CN106326440B CN 106326440 B CN106326440 B CN 106326440B CN 201610730823 A CN201610730823 A CN 201610730823A CN 106326440 B CN106326440 B CN 106326440B
- Authority
- CN
- China
- Prior art keywords
- active user
- interest
- information
- user
- interaction data
- 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
- G06F16/30—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
- G06F16/35—Clustering; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A kind of man-machine interaction method and device towards intelligent robot, wherein this method comprises: user's identification step, obtains the multi-modal interaction data of active user's input, parse to multi-modal interaction data, determine the identity information of active user；Interest, which is classified, determines step, and the historical interaction data of active user is obtained according to the identity information of active user, the interest classification information of active user is determined using knowledge mapping combination historical interaction data；Feedback information generation step generates feedback information and exports according to the interest classification information of active user.The method increase the accuracys for the user interest point determined to improve the Humanization Level of Municipal of intelligent robot so that intelligent robot feedback information generated is more in line with the behavioural habits of user, improves the user experience of robot.
Description
Technical field
The present invention relates to robotic technology fields, specifically, being related to a kind of human-computer interaction side towards intelligent robot
Method and device.
Background technique
With the continuous development of science and technology, the introducing of information technology, computer technology and artificial intelligence technology, machine
Industrial circle is gradually walked out in the research of people, gradually extends to the neck such as medical treatment, health care, family, amusement and service industry
Domain.And requirement of the people for robot also conform to the principle of simplicity single duplicate mechanical action be promoted to have anthropomorphic question and answer, independence and with
The intelligent robot that other robot interacts, human-computer interaction also just become an important factor for determining intelligent robot development.
User often exposes many hobbies or point of interest of user during interacting with robot.And
If can effectively extract and using if these user interest point information, undoubtedly will enable intelligent robot effectively guides
And the interested topic of user is talked about, to improve user's viscosity of product.
The extracting method of existing user interest point generally requires a large amount of corpus of text to carry out correlation analysis, and most
The interest point information obtained eventually is difficult effectively to be handed over according to obtained interest point information with user often than broad
Mutually.
Summary of the invention
To solve the above problems, the present invention provides a kind of man-machine interaction methods towards intelligent robot comprising:
User's identification step, obtain active user input multi-modal interaction data, to the multi-modal interaction data into
Row parsing, determines the identity information of the active user；
Interest, which is classified, determines step, and the history interaction of the active user is obtained according to the identity information of the active user
Data determine the interest classification information of the active user using knowledge mapping in conjunction with the historical interaction data；
Feedback information generation step generates feedback information and exports according to the interest classification information of the active user.
According to one embodiment of present invention, classify in the interest and determine in step, by the history interaction of active user
Point of interest vocabulary in data projects in the knowledge mapping, and the interest point of the active user is determined according to knowledge mapping
Category information.
According to one embodiment of present invention, classify in the interest and determine in step,
Point of interest vocabulary in the historical interaction data is counted, and is projected in knowledge mapping；
Clustering is carried out to each point of interest in the knowledge mapping, determines the interest classification of the active user
Information.
According to one embodiment of present invention, in the feedback information generation step, according to the interest of active user point
Category information determines classification corresponding with the interest classification information in knowledge mapping, extracts the up-to-date information in the classification, root
According to the up-to-date information, generates feedback information and export.
The present invention also provides a kind of human-computer interaction devices towards intelligent robot comprising:
Subscriber identification module is used to obtain the multi-modal interaction data of active user's input, to the multi-modal interaction
Data are parsed, and determine the identity information of the active user；
Interest classification determining module, is used to obtain going through for the active user according to the identity information of the active user
History interaction data determines the interest classification information of the active user using knowledge mapping in conjunction with the historical interaction data；
Feedback information generation module is used for the interest classification information according to the active user, generates feedback information simultaneously
Output.
According to one embodiment of present invention, the interest classification determining module is configured to the history interaction of active user
Point of interest vocabulary in data projects in the knowledge mapping, and the interest point of the active user is determined according to knowledge mapping
Category information.
According to one embodiment of present invention, the interest classification determining module is configured to first to history interaction number
Point of interest vocabulary in is counted, and is projected in knowledge mapping, then to each point of interest in the knowledge mapping
Clustering is carried out, determines the interest classification information of the active user.
According to one embodiment of present invention, the feedback information generation module is configured to according to the interest of active user point
Category information determines classification corresponding with the interest classification information in knowledge mapping, extracts the up-to-date information in the classification, root
According to the up-to-date information, generates feedback information and export.
Man-machine interaction method provided by the present invention towards intelligent robot is no longer needed as the prior art to big
The corpus of text of amount is analyzed the point of interest to determine user, but using knowledge mapping come according to user and intelligent robot
Direct a small amount of chat content obtains the point of interest of user, so that it is interested anti-to generate user according to the point of interest of user
Feedforward information, and then user and intelligent robot is attracted to carry out continuing interaction.The method increase the user interest points determined
Accuracy improves intelligent machine so that intelligent robot feedback information generated is more in line with the behavioural habits of user
The Humanization Level of Municipal of device people improves the user experience of robot.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention can be by specification, right
Specifically noted structure is achieved and obtained in claim and attached drawing.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is required attached drawing in technical description to do simple introduction:
Fig. 1 is the implementation flow chart of the man-machine interaction method according to an embodiment of the invention towards intelligent robot；
Fig. 2 is the implementation process of the man-machine interaction method in accordance with another embodiment of the present invention towards intelligent robot
Figure；
Fig. 3 is the structural schematic diagram of the human-computer interaction device according to an embodiment of the invention towards intelligent robot.
Specific embodiment
Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings and examples, how to apply to the present invention whereby
Technological means solves technical problem, and the realization process for reaching technical effect can fully understand and implement.It needs to illustrate
As long as not constituting conflict, each feature in each embodiment and each embodiment in the present invention can be combined with each other,
It is within the scope of the present invention to be formed by technical solution.
Meanwhile in the following description, for illustrative purposes and numerous specific details are set forth, to provide to of the invention real
Apply the thorough understanding of example.It will be apparent, however, to one skilled in the art, that the present invention can not have to tool here
Body details or described ad hoc fashion are implemented.
In addition, step shown in the flowchart of the accompanying drawings can be in the department of computer science of such as a group of computer-executable instructions
It is executed in system, although also, logical order is shown in flow charts, and it in some cases, can be to be different from herein
Sequence execute shown or described step.
Existing man-machine interaction method is mostly determined using LDA (Latent Dirichlet Allocation) model
Center topic in user interaction process.LDA is a kind of document body generation model, also referred to as three layers of Bayesian probability mould
Type includes word, main body and document three-decker.Generally it can be thought that each word of an article is by " with certain probability
Some theme being selected, and from this theme with some word of certain probability selection " such a process obtains, and this is namely
So-called generation model.Wherein, document obeys multinomial distribution to theme, and theme equally obeys multinomial distribution to word.
Although it is a large amount of that it realizes that process needs to rely on however, traditional LDA model can extract center topic
Text analyzing, and finally obtained is also a series of isolated words, is unable to get accurate center topic.
For the above problem in the presence of the prior art, the present invention provides a kind of new people towards intelligent robot
Machine exchange method.This method carries out the extraction of user interest point using knowledge mapping, and according to the point of interest extracted come
Corresponding feedback information is generated to export to user.
In order to clearly illustrate realization principle, the reality of the man-machine interaction method provided by the present invention towards intelligent robot
Existing process and advantage to make man-machine interaction method provided by the present invention further below in conjunction with different embodiments
Ground explanation.
Embodiment one:
Fig. 1 shows the implementation flow chart of the man-machine interaction method towards intelligent robot provided by the present embodiment.
As shown in Figure 1, acquisition active user is defeated in step s101 first for man-machine interaction method provided by the present embodiment
The multi-modal interaction data entered.It should be pointed out that in different embodiments of the invention, this method is obtained in step s101
The multi-modal interaction data got can also be voice data and text either voice data, is also possible to text data
The combination of data, or it is the reasonable combination of other reasonable interaction data (such as images) and voice data and text data, this
It invents without being limited thereto.
After the multi-modal interaction data for obtaining active user's input, this method is in step s 102 to the multi-modal data
It is parsed, to obtain the identity information of active user.For example, if including language in the multi-modal interactive information of user's input
Message breath, then party's rule can extract corresponding voiceprint according to the voice messaging in step s 102, and should
What voiceprint and intelligent robot itself or cloud server stored is that voice print database is matched, due to voice print database
In each voiceprint be identity information corresponding with specific user, therefore being also assured that out active user.
It should be pointed out that in other embodiments of the invention, according to data included in multi-modal interaction data
The difference of type can also be determined currently to use using other reasonable manners according to accessed multi-modal interaction data
The identity information at family, the invention is not limited thereto.
As shown in Figure 1, after obtaining the identity information of active user, this method can be in step s 103 in the present embodiment
The historical interaction data of active user is obtained according to the identity information of active user.Specifically, in the present embodiment, intelligent robot
The interaction data (i.e. historical interaction data) of multiple users in certain period of time is stored in itself and/or cloud server, it should
Method in step s 103 can be according to the identity information of active user come in intelligent robot itself and/or cloud server
The interaction data stored is retrieved, to obtain the historical interaction data of active user.
It should be pointed out that in different embodiments of the invention, the history of active user accessed by this method is handed over
The data volume (i.e. the length of period) of mutual data can be configured to different reasonable values according to actual needs, therefore herein not
The contents of the section is defined.
After obtaining the historical interaction data of active user, this method utilizes knowledge mapping combination history in step S104
Interaction data determines the interest classification information of active user.Due to had existed inside knowledge mapping established entity with
Relationship between entity, it includes there is an a large amount of Predefined information, therefore can be more accurately from user using knowledge mapping
The focus that user is extracted with a small amount of chat content (such as historical interaction data) of robot, that is, determine the interest of user
Classification information, to preferably carry out the recommendation of relevant information.
After obtaining the classification information of active user, this method also can in step s105 according to the classification information come
It generates corresponding feedback information and exports.Since the interest classification information of the obtained active user of knowledge mapping can be more quasi-
Really reflect the point of interest of active user, therefore obviously can be more in line with and be worked as according to point of interest feedback information generated
The interaction of preceding user is expected, and carries out lasting interaction so as to cause user and intelligent robot.
It should be pointed out that in different embodiments of the invention, this method generates feedback simultaneously in step s105
Information can be various forms of multi-modal interactive information, and the invention is not limited thereto.For example, in one embodiment of the present of invention
In, feedback information that this method is generated and exported in step s105 either voice messaging, is also possible to character information,
It can also be other appropriate messages such as image information, or be the reasonable combination of the above various information.
It can be seen that the man-machine interaction method towards intelligent robot provided by the present embodiment no longer from foregoing description
It needs to analyze a large amount of corpus of text as the prior art point of interest to determine user, but utilizes knowledge mapping
Come according to user and intelligent robot, directly a small amount of chat content obtains the point of interest of user, thus according to the interest of user
It puts to generate the interested feedback information of user, and then user and intelligent robot is attracted to carry out continuing interaction.This method improves
The accuracy for the user interest point determined, so that intelligent robot feedback information generated is more in line with user's
Behavioural habits improve the Humanization Level of Municipal of intelligent robot, improve the user experience of robot.
Embodiment two:
Fig. 2 shows the implementation flow charts of the man-machine interaction method provided by the present embodiment towards intelligent robot.
As shown in Fig. 2, the man-machine interaction method obtains active user's input in step s 201 first in the present embodiment
Multi-modal interaction data, and the multi-modal interaction data being parsed in step S202, so that it is determined that active user out
Identity information.After determining the identity information of active user, this method is believed in step S203 according to the identity of active user
It ceases to obtain the historical interaction data of active user.
It should be pointed out that the present embodiment in step S201 to step S203 specific implementation principle and realize process with
Content involved in step S101 to step S103 is similar in above-described embodiment one, therefore herein no longer to step S201 to step
The content of S203 is repeated.
After obtaining the historical interaction data of active user, this method can will be emerging in the historical interaction data of active user
Interest point vocabulary projects in knowledge mapping, and the interest classification information of active user is determined according to the knowledge spectrogram.
Specifically, as shown in Fig. 2, this method can in step S204 to the point of interest vocabulary in the historical interaction data into
Row statistics, and statistical result is projected in knowledge mapping.For example, " basketball " occurs in the historical interaction data of active user
Twice, then " basketball " this node can be obtained by two points in knowledge mapping；Five times in the historical interaction data of active user
Content relevant to eating merely is arrived, then " cuisines " this node can be obtained by five points in knowledge mapping.Due to knowledge mapping
In content corresponding to each node be that therefore these nodes necessarily include the emerging of active user mentioned in historical interaction data
Interesting information, and the score of each node also just characterizes the significance level of the node in knowledge mapping.In this way, also just will
The statistical result of point of interest vocabulary in the historical interaction data of active user has projected in knowledge mapping.
This method then carries out clustering to point of interest each in knowledge mapping in step S205, so that it is determined that going out to work as
The interest classification information of preceding user.For knowledge spectrogram, between each node be no longer it is isolated, according to each node it
Between distance carry out cluster operation, so as to obtain the topic that user is most interested in, also just obtained active user in this way
Interest classification information.
After obtaining the interest classification information of active user, this method is believed in step S206 according to the classification of active user
Breath, determines classification corresponding with the interest classification information in knowledge mapping.After obtaining the category, this method can be in step
The relevant information (such as up-to-date information) of the category is extracted in S207, and generates according to the relevant information feedback information and defeated
Out to active user.
For example, if be repeatedly mentioned in the historical interaction data of active user " Yao Ming ", and Yao Ming is a basketball fortune
It mobilizes, therefore this method can determine that classification corresponding with active user's classification information can in knowledge mapping in step S206
To be " basketball ", therefore this method can also generate corresponding feedback information in step S207 according to the news information
It (such as basketball team, the U.S. wins Olympic champion again) and exports to active user, and this will obviously attract active user and intelligence
Robot carries out chat interaction.
The present invention also provides a kind of human-computer interaction device towards intelligent robot, Fig. 3 is shown should in the present embodiment
The structural schematic diagram of device.
As shown in figure 3, the human-computer interaction device that the present embodiment is supplied to preferably includes: subscriber identification module 301, emerging
Interest classification determining module 302 and feedback information generation module 303.Wherein, subscriber identification module 301 is for obtaining active user
The multi-modal interaction data of input.It should be pointed out that in different embodiments of the invention, subscriber identification module 301 is obtained
The multi-modal interaction data got can also be voice data and text either voice data, is also possible to text data
The combination of data, or it is the reasonable combination of other reasonable interaction data (such as images) and voice data and text data, this
It invents without being limited thereto.
After the multi-modal interaction data for obtaining active user's input, subscriber identification module 301 can be to the multi-modal interaction
Data are parsed to obtain the identity information of active user.Specifically, in the present embodiment, it is preferable if accessed
It include voice messaging in multi-modal interactive information, subscriber identification module 301 can then be believed by the vocal print extracted in voice messaging
Cease and determine according to the voiceprint identity information of active user；If including in accessed multi-modal interactive information
Image information, subscriber identification module 301 then can determine active user's by way of recognition of face and/or gesture identification
Identity information.
It should be pointed out that in other embodiments of the invention, according to data included in multi-modal interaction data
The difference of type, subscriber identification module 301 can also be using other reasonable manners come according to accessed multi-modal interaction
Data determine the identity information of active user, and the invention is not limited thereto.
After obtaining the identity information of active user, subscriber identification module 301 can transmit the identity information of active user
Give interest classification determining module 302.Interest classifies determining module 302 after receiving the identity information, can be according to active user
Identity information obtain active user historical interaction data.
Specifically, it in the present embodiment, is stored in intelligent robot itself and/or cloud server more in certain period of time
The interaction data (i.e. historical interaction data) of a user, interest classification determining module 302 can be believed according to the identity of active user
Breath is to retrieve the interaction data stored in intelligent robot itself and/or cloud server, to currently be used
The historical interaction data at family.
After obtaining the historical interaction data of active user, interest classifies determining module 302 can be using knowledge mapping combination
Historical interaction data determines the interest classification information of active user.Due to having existed established reality inside knowledge mapping
Relationship between body and entity, it includes there is an a large amount of Predefined information, therefore using knowledge mapping can more accurately from
A small amount of chat content (such as historical interaction data) of user and robot extracts the focus of user, that is, determines user's
Interest classification information, to preferably carry out the recommendation of relevant information.
It should be pointed out that interest classifies determining module 302 according to the historical interaction data of active user in the present embodiment
Determine the interest classification information of active user concrete principle and process can also using such as step S204 in embodiment two and
Mode shown in step S205, the invention is not limited thereto.
After obtaining the classification information of active user, which can be transferred to instead by interest classification determining module 302
Feedforward information generation module 303, to generate corresponding feedback information according to the classification information simultaneously by feedback information generation module 303
Output.Since the interest classification information of the obtained active user of knowledge mapping can more accurately reflect active user's
Point of interest, therefore be expected according to the interaction that point of interest feedback information generated obviously can be more in line with active user, from
And user and intelligent robot is caused to carry out lasting interaction.
It should be pointed out that feedback information generation module 303 is according to the interest classification information of active user in the present embodiment
Generate feedback information principle and process preferably with content class involved in step S206 in embodiment two and step S207
Seemingly, no longer feedback information generation module 303 is not repeated herein.
It should be understood that disclosed embodiment of this invention is not limited to specific structure disclosed herein or processing step
Suddenly, the equivalent substitute for these features that those of ordinary skill in the related art are understood should be extended to.It should also be understood that
It is that term as used herein is used only for the purpose of describing specific embodiments, and is not intended to limit.
" one embodiment " or " embodiment " mentioned in specification means the special characteristic described in conjunction with the embodiments, structure
Or characteristic is included at least one embodiment of the present invention.Therefore, the phrase " reality that specification various places throughout occurs
Apply example " or " embodiment " the same embodiment might not be referred both to.
Although above-mentioned example is used to illustrate principle of the present invention in one or more application, for the technology of this field
For personnel, without departing from the principles and ideas of the present invention, hence it is evident that can in form, the details of usage and implementation
It is upper that various modifications may be made and does not have to make the creative labor.Therefore, the present invention is defined by the appended claims.
Claims (4)
1. a kind of man-machine interaction method towards intelligent robot characterized by comprising
User's identification step obtains the multi-modal interaction data of active user's input, solves to the multi-modal interaction data
Analysis, determines the identity information of the active user；
Interest, which is classified, determines step, and the history interaction number of the active user is obtained according to the identity information of the active user
According to the interest classification information of the active user is determined in conjunction with the historical interaction data using knowledge mapping；
Feedback information generation step generates feedback information and exports according to the interest classification information of the active user；
Wherein, classify in the interest and determine in step:
Point of interest vocabulary in the historical interaction data is counted, and is projected in knowledge mapping；
Clustering is carried out to each point of interest in the knowledge mapping, determines the interest classification letter of the active user
Breath.
2. the method as described in claim 1, which is characterized in that in the feedback information generation step, according to active user
Interest classification information, determine classification corresponding with the interest classification information in knowledge mapping, extract in the classification most
New information generates feedback information and exports according to the up-to-date information.
3. a kind of human-computer interaction device towards intelligent robot characterized by comprising
Subscriber identification module is used to obtain the multi-modal interaction data of active user's input, to the multi-modal interaction data
It is parsed, determines the identity information of the active user；
Interest classification determining module, the history for being used to obtain the active user according to the identity information of the active user are handed over
Mutual data determine the interest classification information of the active user using knowledge mapping in conjunction with the historical interaction data；
Feedback information generation module is used for the interest classification information according to the active user, generates feedback information and exports；
Wherein, the interest classification determining module is configured to first unite to the point of interest vocabulary in the historical interaction data
Meter, and project in knowledge mapping, clustering then is carried out to each point of interest in the knowledge mapping, is determined described
The interest classification information of active user.
4. device as claimed in claim 3, which is characterized in that the feedback information generation module is configured to according to active user
Interest classification information, determine classification corresponding with the interest classification information in knowledge mapping, extract in the classification most
New information generates feedback information and exports according to the up-to-date information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610730823.9A CN106326440B (en) | 2016-08-26 | 2016-08-26 | A kind of man-machine interaction method and device towards intelligent robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610730823.9A CN106326440B (en) | 2016-08-26 | 2016-08-26 | A kind of man-machine interaction method and device towards intelligent robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106326440A CN106326440A (en) | 2017-01-11 |
| CN106326440B true CN106326440B (en) | 2019-11-29 |
Family
ID=57791060
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610730823.9A Active CN106326440B (en) | 2016-08-26 | 2016-08-26 | A kind of man-machine interaction method and device towards intelligent robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106326440B (en) |
Families Citing this family (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106991123A (en) * | 2017-02-27 | 2017-07-28 | 北京光年无限科技有限公司 | A kind of man-machine interaction method and device towards intelligent robot |
| WO2018157349A1 (en) * | 2017-03-02 | 2018-09-07 | 深圳前海达闼云端智能科技有限公司 | Method for interacting with robot, and interactive robot |
| CN108573390A (en) * | 2017-03-08 | 2018-09-25 | 北京跃盟科技有限公司 | Content method for dynamically processing and system |
| EP3566399A4 (en) | 2017-03-31 | 2020-08-19 | Microsoft Technology Licensing, LLC | Providing news recommendation in automated chatting |
| CN110019824A (en) * | 2017-07-20 | 2019-07-16 | 苏州狗尾草智能科技有限公司 | Man-machine interaction method, the apparatus and system of knowledge based map |
| CN110019848A (en) * | 2017-12-22 | 2019-07-16 | 深圳市优必选科技有限公司 | Talk with exchange method, device and robot |
| CN110309316B (en) * | 2018-06-08 | 2022-10-25 | 腾讯科技（深圳）有限公司 | Method and device for determining knowledge graph vector, terminal equipment and medium |
| CN108900612A (en) * | 2018-06-29 | 2018-11-27 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN109918409A (en) * | 2019-03-04 | 2019-06-21 | 珠海格力电器股份有限公司 | A kind of equipment portrait construction method, device, storage medium and equipment |
| CN110175227B (en) * | 2019-05-10 | 2021-03-02 | 神思电子技术股份有限公司 | Dialogue auxiliary system based on team learning and hierarchical reasoning |
| CN110489513A (en) * | 2019-06-24 | 2019-11-22 | 覃立万 | A kind of intelligent robot social information processing method and the social intercourse system with people |
| CN112463102B (en) * | 2019-09-06 | 2024-03-22 | 佛山市顺德区美的电热电器制造有限公司 | Household appliance, interaction method and interaction device thereof, and electronic equipment |
| CN112732376A (en) * | 2019-10-28 | 2021-04-30 | 阿里巴巴集团控股有限公司 | Information interaction method and device based on page |
| CN111209403B (en) * | 2019-11-22 | 2024-02-13 | 泰康保险集团股份有限公司 | Data processing method, device, medium and electronic equipment |
| CN111221984B (en) * | 2020-01-15 | 2024-03-01 | 北京百度网讯科技有限公司 | Multi-mode content processing method, device, equipment and storage medium |
| CN112559834A (en) * | 2020-12-21 | 2021-03-26 | 浙江合张量科技有限公司 | Multi-mode output method for intelligent robot system |
| CN114880422B (en) * | 2022-07-08 | 2022-09-13 | 北京百度网讯科技有限公司 | Interest point information processing method based on robot process automation and related device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914536A (en) * | 2014-03-31 | 2014-07-09 | 北京百度网讯科技有限公司 | Interest point recommending method and system for electronic maps |
| CN104281622A (en) * | 2013-07-11 | 2015-01-14 | 华为技术有限公司 | Information recommending method and information recommending device in social media |
| CN104537065A (en) * | 2014-12-29 | 2015-04-22 | 北京奇虎科技有限公司 | Search result pushing method and system |
| CN105205180A (en) * | 2015-10-27 | 2015-12-30 | 无锡天脉聚源传媒科技有限公司 | Knowledge map evaluation method and device |
| CN105681830A (en) * | 2016-02-06 | 2016-06-15 | 优住（北京）科技股份公司 | Advertisement playing system and playing platform based on interest points of user |
| CN105824935A (en) * | 2016-03-18 | 2016-08-03 | 北京光年无限科技有限公司 | Method and system for information processing for question and answer robot |
-
2016
- 2016-08-26 CN CN201610730823.9A patent/CN106326440B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104281622A (en) * | 2013-07-11 | 2015-01-14 | 华为技术有限公司 | Information recommending method and information recommending device in social media |
| CN103914536A (en) * | 2014-03-31 | 2014-07-09 | 北京百度网讯科技有限公司 | Interest point recommending method and system for electronic maps |
| CN104537065A (en) * | 2014-12-29 | 2015-04-22 | 北京奇虎科技有限公司 | Search result pushing method and system |
| CN105205180A (en) * | 2015-10-27 | 2015-12-30 | 无锡天脉聚源传媒科技有限公司 | Knowledge map evaluation method and device |
| CN105681830A (en) * | 2016-02-06 | 2016-06-15 | 优住（北京）科技股份公司 | Advertisement playing system and playing platform based on interest points of user |
| CN105824935A (en) * | 2016-03-18 | 2016-08-03 | 北京光年无限科技有限公司 | Method and system for information processing for question and answer robot |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106326440A (en) | 2017-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106326440B (en) | A kind of man-machine interaction method and device towards intelligent robot | |
| WO2018036555A1 (en) | Session processing method and apparatus | |
| CN106407178B (en) | A kind of session abstraction generating method, device, server apparatus and terminal device | |
| CN107480122B (en) | Artificial intelligence interaction method and artificial intelligence interaction device | |
| WO2019174428A1 (en) | Method and device for obtaining reply information | |
| CN112818107B (en) | Conversation robot for daily life and chat method thereof | |
| CN109690526A (en) | Method and apparatus for intelligent automatic chatting | |
| CN105022733B (en) | DINFO OEC text analyzings method for digging and equipment | |
| CN106294854A (en) | A kind of man-machine interaction method for intelligent robot and device | |
| CN110489513A (en) | A kind of intelligent robot social information processing method and the social intercourse system with people | |
| CN103593412B (en) | A kind of answer method and system based on tree structure problem | |
| CN109271634A (en) | A kind of microblog text affective polarity check method based on user feeling tendency perception | |
| CN105631749A (en) | User portrait calculation method based on statistical data | |
| Prata et al. | Social data analysis of Brazilian's mood from Twitter | |
| CN104008182A (en) | Measuring method of social network communication influence and measure system thereof | |
| CN114387061A (en) | Product pushing method and device, electronic equipment and readable storage medium | |
| CN111026866B (en) | Domain-oriented text information extraction clustering method, device and storage medium | |
| Wu et al. | Automatic chatbot knowledge acquisition from online forum via rough set and ensemble learning | |
| CN112287082A (en) | Data processing method, device, equipment and storage medium combining RPA and AI | |
| CN115186080A (en) | Intelligent question-answering data processing method, system, computer equipment and medium | |
| KR20180116103A (en) | Continuous conversation method and system by using automating conversation scenario network | |
| Fariha et al. | A new framework for mining frequent interaction patterns from meeting databases | |
| CN108306813A (en) | Processing method, server and the client of conversation message | |
| CN106462579B (en) | Dictionary is constructed for selected context | |
| CN106708950A (en) | Data processing method and device used for intelligent robot self-learning system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |