CN106991123A - 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 PDF

Info

Publication number
CN106991123A
CN106991123A CN201710107291.8A CN201710107291A CN106991123A CN 106991123 A CN106991123 A CN 106991123A CN 201710107291 A CN201710107291 A CN 201710107291A CN 106991123 A CN106991123 A CN 106991123A
Authority
CN
China
Prior art keywords
topic
user
information
children
interactive
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
Application number
CN201710107291.8A
Other languages
Chinese (zh)
Inventor
邱模武
徐振敬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Guangnian Wuxian Technology Co Ltd
Original Assignee
Beijing Guangnian Wuxian Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Guangnian Wuxian Technology Co Ltd filed Critical Beijing Guangnian Wuxian Technology Co Ltd
Priority to CN201710107291.8A priority Critical patent/CN106991123A/en
Publication of CN106991123A publication Critical patent/CN106991123A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24Querying
    • G06F16/242Query formulation
    • G06F16/2423Interactive query statement specification based on a database schema
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/36Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/374Thesaurus
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/951Indexing; Web crawling techniques

Abstract

A kind of man-machine interaction method and device towards intelligent robot, wherein, this method includes:Interactive information obtaining step, obtains the multi-modal interactive information on user, wherein, interactive voice information is included in multi-modal interactive information;Interaction topic determines step, determines whether user is child user according to multi-modal interactive information, wherein, if user is child user, interactive voice information is parsed, and determined from default children's topic storehouse according to analysis result currently to interact topic;Feedback information exports step, generates conversational feedback information based on current interaction topic and exports.This method with child user during interacting; the vocabulary and topic of adult can be effectively filtered out; so as to improve the degree of purity of data; so also avoid intelligent robot and unsuitable content is pushed to child user; the physical and mental health of child user is protected, the Consumer's Experience of intelligent robot is improved.

Description

A kind of man-machine interaction method and device towards intelligent robot
Technical field
The present invention relates to robotic technology field, specifically, it is related to a kind of man-machine interaction side towards intelligent robot Method and device.
Background technology
With the continuous development of scientific technology, the introducing of information technology, computer technology and artificial intelligence technology, machine Industrial circle is progressively walked out in the research of people, gradually extend to the neck such as medical treatment, health care, family, amusement and service industry Domain.And people for the requirement of robot also conform to the principle of simplicity the multiple mechanical action of substance be promoted to anthropomorphic question and answer, independence and with The intelligent robot that other robot is interacted, man-machine interaction also just turns into the key factor for determining intelligent robot development.
For intelligent robot, its interactive object had both been probably adult, it is also possible to children, existing intelligence machine Man-machine interaction method used in people can push away some topics that interact for being not suitable for children during being interacted with children Give child user.
The content of the invention
To solve the above problems, the invention provides a kind of man-machine interaction method towards intelligent robot, it includes:
Interactive information obtaining step, obtains the multi-modal interactive information on user, wherein, the multi-modal interactive information In include interactive voice information;
Interaction topic determines step, determines whether the user is child user according to the multi-modal interactive information, its In, if the user is child user, the interactive voice information is parsed, and according to analysis result from default youngster Current interaction topic is determined in children's stories exam pool;
Feedback information exports step, generates conversational feedback information based on the current interactive topic and exports.
According to one embodiment of present invention, methods described also includes:
Children's topic storehouse construction step, data are crawled based on network, are that the network is climbed using default topic classification model Each topic addition adult's topic label or children's topic label for evidence of fetching, are built described using the topic of children's topic label Default children's topic storehouse.
According to one embodiment of present invention, in children's topic storehouse construction step, default topic classification mould is utilized Type crawls the news label of data according to the network and adds label to crawl each topic of data for the network.
According to one embodiment of present invention, methods described also includes:
Topic tag modification step, modifies according to the feedback information of the user got to the label of correspondence topic.
According to one embodiment of present invention, in the interactive topic determines step, always according to the multi-modal interaction Information determines the ID of child user, and the corresponding exportable topic of the child user is determined according to the ID, and according to The analysis result determines currently to interact topic from the corresponding exportable topic of the user.
Present invention also offers a kind of human-computer interaction device towards intelligent robot, it includes:
Interactive information acquisition module, it is used to obtain the multi-modal interactive information on user, wherein, the multi-modal friendship Interactive voice information is included in mutual information;
Interaction topic determining module, it is used to determine whether the user is that children use according to the multi-modal interactive information Family, wherein, if the user be child user, the interactive voice information is parsed, and according to analysis result from Current interaction topic is determined in default children's topic storehouse;
Feedback information output module, it is used for based on the current interactive topic generation conversational feedback information and exported.
According to one embodiment of present invention, described device also includes:
Children's topic storehouse builds module, and it is used to crawl data based on network, is described using default topic classification model Network crawls each topic addition adult's topic label or children's topic label of data, utilizes the topic structure of children's topic label Build default children's topic storehouse.
According to one embodiment of present invention, children's topic storehouse builds module and is configured to utilize default topic classification mould Type crawls the news label of data according to the network and adds label to crawl each topic of data for the network.
According to one embodiment of present invention, described device also includes:
Topic tag modification module, it is used to carry out the label of correspondence topic according to the feedback information of the user got Modification.
According to one embodiment of present invention, the interactive topic determining module is configured to always according to the multi-modal interaction Information determines the ID of child user, and the corresponding exportable topic of the child user is determined according to the ID, and according to The analysis result determines currently to interact topic from the corresponding exportable topic of the user.
Man-machine interaction method provided by the present invention for intelligent robot is in the process interacted with child user In, the vocabulary and topic of adult can be effectively filtered out, so as to improve the degree of purity of data, intelligence machine is so also avoided People pushes unsuitable content to child user, protects the physical and mental health of child user, improves the user's body of intelligent robot Test.
Other features and advantages of the present invention will be illustrated in the following description, also, partly becomes from specification Obtain it is clear that or being understood by implementing the present invention.The purpose of the present invention and other advantages can be by specification, rights Specifically noted structure is realized and obtained in claim and accompanying drawing.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing There is the accompanying drawing required in technology description to do simple introduction:
Fig. 1 is the implementation process signal of the man-machine interaction method according to an embodiment of the invention towards intelligent robot Figure;
Fig. 2 is that the implementation process of the man-machine interaction method in accordance with another embodiment of the present invention towards intelligent robot is shown It is intended to;
Fig. 3 is shown according to the implementation process of the man-machine interaction method towards intelligent robot of further embodiment of the present invention It is intended to;
Fig. 4 is the structural representation of the human-computer interaction device according to an embodiment of the invention towards intelligent robot.
Embodiment
Describe embodiments of the present invention in detail below with reference to drawings and Examples, how the present invention is applied whereby Technological means solves technical problem, and reaches the implementation process of technique effect and can fully understand and implement according to this.Need explanation As long as not constituting each embodiment in conflict, the present invention and each feature in each embodiment can be combined with each other, The technical scheme formed is within protection scope of the present invention.
Meanwhile, in the following description, many details are elaborated for illustrative purposes, 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 be without tool here Body details or described ad hoc fashion are implemented.
In addition, the step of the flow of accompanying drawing is illustrated can such as one group computer executable instructions department of computer science Performed in system, and, although logical order is shown in flow charts, but in some cases, can be with different from herein Order perform shown or described step.
For existing intelligent robot, it can be based on specifically interacting words during interacting with user Inscribe to generate corresponding conversation sentence.However, when user is children, existing intelligent robot was interacted with user Occur in journey to content of the child user push on adult's topic (topic such as on love, military or violence), This is obviously unfavorable for the physical and mental development of child user.
For the drawbacks described above present in existing man-machine interaction method, the invention provides a kind of new towards intelligence machine The man-machine interaction method and device of people.The man-machine interaction method can only be suitable for children's when active user is child user Interact topic to interact with child user, so as to ensure the physical and mental health of child user.
In order to clearly illustrate that the realization of the man-machine interaction method provided by the present invention towards intelligent robot is former Reason, implementation process and advantage, are further described below in conjunction with different embodiments to the man-machine interaction method.
Embodiment one:
Fig. 1 shows the implementation process signal for the man-machine interaction method towards intelligent robot that the present embodiment is provided Figure.
As shown in figure 1, the man-machine interaction method that the present embodiment is provided is obtained on user's in step S101 first Multi-modal interactive information.Wherein, this method multi-modal interactive information on user accessed in step S101 includes Interactive voice information.
After the multi-modal interactive information on user is got, this method can be in step s 102 according to above-mentioned multi-modal Interactive information determines whether the active user of intelligent robot is child user.In the present embodiment, this method is based preferably on The acoustic feature of virgin voice to judge according to interactive voice information accessed in step S101 the current use of intelligent robot Whether family is child user.
Specifically, in the present embodiment, this method extracts the formant in interactive voice information first in step s 102, with Whether the active user for judging intelligent robot further according to above-mentioned formant afterwards is child user.The voice that children are sent Formant is greater than the formant for sent voice of being grown up, therefore this method also just can be according to children speech and adult's voice Above-mentioned difference come carry out user whether be child user judgement.
It is pointed out that in other embodiments of the invention, this method can also using other reasonable manners come Whether the active user for judging intelligent robot is child user, and the invention is not restricted to this.
Relative to adult's voice, children speech has longer vowel duration, higher fundamental frequency, and these parameters Dynamic range it is larger.Simultaneously for repeating twice for same vowel, the spectral change of children speech is than adult's voice Greatly, the characteristics of variability of formant also has identical.Further, since the pronunciation of vowel is influenceed larger by consonant articulation thereafter, And the coordination articulation ability of children is poor, therefore the front half section for same vowel and second half section, the spectral change of children speech Property than adult voice it is big.Features described above based on children speech, in one embodiment of the invention, this method also can Judged with features such as voice-based duration, fundamental frequency and/or envelope spectrums intelligent robot active user whether be Virgin user.
In addition it is also necessary to, it is noted that according in this method multi-modal interactive information accessed in step S101 The difference of included information, method provided by the present invention can also judge working as intelligent robot using other rational methods Whether preceding user is child user, and the present invention is similarly not so limited to.For example, in one embodiment of the invention, if the party The image information on user is included in method multi-modal interactive information accessed in step S101, then this method is also The mode of image recognition can be used in step s 102 to judge the active user of intelligent robot whether for child user.
If as shown in figure 1, active user is child user, then party's rule can be in step s 103 to step S101 In accessed interactive voice information parsed, and is determined from default children's topic storehouse according to analysis result currently to interact Topic.
In the present embodiment, this method can be entered to interactive voice information accessed in step S101 in step s 103 Row keyword extraction, and currently interaction topic is determined from default children's topic storehouse according to the keyword extracted.
Above-mentioned default children's topic storehouse is built in advance, and specifically, in the present embodiment, this method is based preferably on net Network crawls data to utilize default topic classification model to be each topic addition adult's topic label that above-mentioned network crawls data Or children's topic label.After the label for each topic that network crawls data is obtained, this method also can just extract children The topic of topic label, and construct according to these topics children's topic storehouse.
In the present embodiment, this method adds adult's topic label in each topic that data are crawled for network or and children talk about When inscribing label, to crawl the news label of data according to network topic label can also be carried out using default topic classification model Addition.
For example, if the data that this method is crawled are " gratitude first love is once paid me ", this method is according to above-mentioned News label in love corresponding to data, it is possible to use default topic classification model sets the above-mentioned topic label for crawling data For adult's topic label.
If for another example the data that crawl of this method for " what nonsense said, being exactly just should not be terrified, more than other side it is ruthless I Just double ruthless, kill them ", violence news label of this method according to corresponding to above-mentioned data, it is possible to use default topic The above-mentioned topic label for crawling data is set to topic label of being grown up by disaggregated model.
And if the data that this method is crawled are " thanking household to work laboriously me to bring up ", this method can be utilized The above-mentioned topic for crawling data is categorized as family's topic by default topic classification model, and the label of family's topic is set to Children's topic label.
It is pointed out that in other embodiments of the invention, this method can also be using other rational methods come complete Into the structure in children's topic storehouse, the invention is not restricted to this.
In step s 103, this method can be crucial by being carried out to interactive voice information accessed in step S101 Word is extracted, so as to determine current interaction topic from default children's topic storehouse according to the keyword extracted.
After current interaction topic is determined, this method also can just be determined according in step S103 in step S104 What is gone out currently interacts topic to generate corresponding conversational feedback information and exported.
Existing man-machine interaction method is during control intelligent robot carries out man-machine interaction with child user, it is likely that The information comprising adult's vocabulary or topic can be fed back to child user, and the method that the present embodiment is provided based on children by being talked about Exam pool feeds back to the information of child user to generate, and effectively can filter out adult's vocabulary or topic, so as to improve data Degree of purity so that intelligent robot feed back to child user vocabulary and topic be more suitable for child user body and mind hair Exhibition.
Embodiment two:
Fig. 2 shows the implementation process signal for the man-machine interaction method towards intelligent robot that the present embodiment is provided Figure.
As shown in Fig. 2 the man-machine interaction method that the present embodiment is provided is obtained on user's in step s 201 first Multi-modal interactive information.Wherein, the accessed multi-modal interactive information on user includes this method in step s 201 Interactive voice information.
After the multi-modal interactive information on user is got, this method can be in step S202 according to above-mentioned multi-modal Interactive information determines whether the active user of intelligent robot is child user.Wherein, if the active user of intelligent robot For child user, then party's rule can be entered in step S203 to interactive voice information accessed in above-mentioned steps S201 Row parsing, and current interaction topic is determined according to analysis result from default children's topic storehouse.
After current interaction topic is determined, this method can be in step S204 based on working as being determined in step S203 Preceding interactive topic gives the child user to generate corresponding conversational feedback information and export.
It is pointed out that in the present embodiment, above-mentioned steps S201 to step S204 realization principle and implementation process It is similar with the content that step S101 in above-described embodiment one is illustrated to step S104, therefore herein no longer to step S201 to step S204 related content is repeated.
By the conversational feedback information that this method is exported in step S204 still suffer from the unsuitable child user can Can, therefore as shown in Fig. 2 the method that is provided of the present embodiment is after output conversational feedback information, can also obtain child user or It is that other associated users (guardian of such as child user) are directed to the corresponding feedback letter that above-mentioned conversational feedback information is inputted Breath.In step S205, the feedback that this method can be inputted according to accessed above-mentioned child user or other associated users Information is modified to the label of current session topic.
For example, child user because see external snow in room and to intelligent robot have input such as ", it is big under outside The voice messaging of snow ", this method by then control machine people be based on weather topic output such as " yes, but hear interior The feedback voice of Mongolian there a lot of sheep because heavy snow has been freezed to death ".And these feedback voices are not appropriate for pair of child user Words, therefore parent is after above-mentioned feedback voice is heard, can be inputted to intelligent robot " not saying these with him ".And the present embodiment The above-mentioned feedback voice that the man-machine interaction method provided can then be inputted according to parent is come by the label of " heavy snow freeze to death sheep " By children's topic be changed to for adult topic, so as to avoid occurring the feedback content again in follow-up interaction.
Embodiment three:
Fig. 3 shows the implementation process signal for the man-machine interaction method towards intelligent robot that the present embodiment is provided Figure.
As shown in figure 3, the man-machine interaction method that the present embodiment is provided is obtained on user's in step S301 first Multi-modal interactive information.Wherein, this method multi-modal interactive information on user accessed in step S301 includes Interactive voice information.
After the multi-modal interactive information on user is got, this method can be in step s 302 according to above-mentioned multi-modal Interactive information determines whether the active user of intelligent robot is child user.Wherein, if the active user of intelligent robot For child user, then party's rule can be in step S303 according to multi-modal interaction letter accessed in above-mentioned steps S301 Breath determines the ID of the child user.
In the present embodiment, information of this method according to included in multi-modal interactive information accessed in step S301 Difference, the ID of child user can be determined in different ways.If for example, in above-mentioned multi-modal interactive information Include voice messaging, then party's rule can determine the child user by carrying out Application on Voiceprint Recognition to above-mentioned voice messaging ID;And if including image information in above-mentioned multi-modal interactive information, then party's rule can be by above-mentioned image Information carries out recognition of face to determine the ID of the child user.
It is pointed out that in other embodiments of the invention, this method can also be using other rational methods come root On the multi-modal interactive information of user the ID of user is determined according to accessed, and the invention is not restricted to this.
After the ID of child user is determined, this method can be in step s 304 according to obtained by step S303 ID determines the exportable topic corresponding to the child user.In the present embodiment, defeated different to that should have of different IDs Go out topic, the corresponding exportable topic of each ID can be determined in advance.
After the exportable topic corresponding to the child user is obtained, this method can be handed over above-mentioned voice in step S305 Mutual information is parsed, and current interaction words are determined in the exportable topic according to corresponding to analysis result from the child user Topic.Finally, this method also can just be generated based on the current interaction topic determined in step S305 in step S306 Corresponding conversational feedback information is simultaneously exported.
It is pointed out that in the present embodiment, above-mentioned steps S305 and step S306's implements principle and realization Process is similar with the content that step S103 in above-described embodiment one and step S104 are illustrated, thus herein no longer to step S305 and Step S306 related content is repeated.
From foregoing description as can be seen that the man-machine interaction method provided by the present invention for intelligent robot with youngster During virgin user interacts, the vocabulary and topic of adult can be effectively filtered out, so that the degree of purity of data is improved, this Sample also avoids intelligent robot and unsuitable content is pushed to child user, protects the physical and mental health of child user, improves The Consumer's Experience of intelligent robot.
Present invention also offers a kind of human-computer interaction device towards intelligent robot, wherein, Fig. 4 shows the present embodiment In the human-computer interaction device structural representation.
As shown in figure 4, the human-computer interaction device that the present embodiment is provided is preferably included:Interactive information acquisition module 401, Interaction topic determining module 402, feedback information output module 403, children's topic storehouse build module 404 and topic tag modification Module 405.
The user of interactive information acquisition module 401 obtains the multi-modal interactive information on user, wherein, in the present embodiment, Interactive voice information is preferably included in multi-modal interactive information accessed by interactive information acquisition module 401.Certainly, at this In the other embodiment of invention, according to actual interaction scenarios, the multi-modal interaction letter accessed by interactive information acquisition module 401 Also include the information (such as image information) comprising other proper forms in breath, the invention is not restricted to this.
After the multi-modal interactive information on user is got, interactive information acquisition module 401 can will be above-mentioned multi-modal Interactive information is transmitted to the interaction topic determining module 402 being attached thereto.In the present embodiment, the meeting of interaction topic determining module 402 Whether the active user that intelligent robot is judged according to above-mentioned multi-modal interactive information is child user.
Wherein, if active user is child user, then interaction topic determining module 402 then can be further to above-mentioned more Interactive voice information in mode interactive information is parsed, and is determined currently from default children's topic storehouse according to analysis result Interaction topic.
In the present embodiment, the current interaction topic that interaction topic determining module 402 can determine itself is transmitted to feedback Message output module 403, to generate corresponding dialogue according to above-mentioned current interactive topic instead by feedback information output module 403 Feedforward information simultaneously exports and gives the child user, so as to realize the man-machine interaction between intelligent robot and child user.
It is pointed out that in different embodiments of the invention, interactive information acquisition module 401, interaction topic are determined Module 402 and feedback information output module 403 realize the concrete principle and process of respective function both can with embodiment one The content that step S101 is illustrated to step S104 is similar, can also be illustrated with step S201 in embodiment two to step S204 Content it is similar, can also be similar with the content that step S301 in embodiment three is illustrated to step S306, therefore no longer right herein The related content of interactive information acquisition module 401, interaction topic determining module 402 and feedback information output module 403 is gone to live in the household of one's in-laws on getting married State.
It is also desirable to which, it is noted that in the present embodiment, interaction topic determining module 402 is it is determined that currently interact topic When used default children's topic storehouse by children's topic storehouse build module 404 build obtain.In the present embodiment, children's words Exam pool structure module 404 is based preferably on network and crawls data to utilize default topic classification model to be that above-mentioned network crawls data Each topic addition adult's topic label or children's topic label.Obtaining the label that network crawls each topic of data Afterwards, children's topic storehouse builds module 404 and also just extracts the topic of children's topic label, and is constructed according to these topics Children's stories exam pool.
In the present embodiment, children's topic storehouse builds module 404 and adds adult's words in each topic that data are crawled for network Inscribe label or and during children's topic label, the news mark of data can also be crawled according to network using default topic classification model Sign to carry out the addition of topic label.
In the present embodiment, feedback information output module 403 is after output conversational feedback information, interactive information acquisition module 401 can also obtain child user or other associated users (guardian of such as child user) for above-mentioned conversational feedback information The corresponding feedback information inputted.If the feedback information that above-mentioned child user or other associated users are inputted characterizes anti- If conversational feedback information that feedforward information output module 403 is exported is unreasonable, interactive information acquisition module 401 can be by above-mentioned youngster The transmission of feedback information that virgin user or other associated users are inputted to the topic tag modification module 405 being attached thereto, with The feedback information inputted by topic tag modification module 405 according to accessed above-mentioned child user or other associated users The label of current session topic is modified.
It is pointed out that in the present embodiment, topic tag modification module 405 realize itself function concrete principle and Process is similar with the content that step S205 is illustrated in above-described embodiment two, therefore herein no longer to topic tag modification module 405 Related content repeated.
Certainly, in other embodiments of the invention, according to actual needs, above-mentioned human-computer interaction device can also not include Children's topic storehouse builds module 404 and topic tag modification module 405, and the invention is not restricted to this.
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 only used for describing the purpose of specific embodiment, and is not intended to limit.
" one embodiment " or " embodiment " mentioned in specification means special characteristic, the structure described in conjunction with the embodiments Or during 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 " 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 applications, for the technology of this area For personnel, in the case of the principle and thought without departing substantially from the present invention, hence it is evident that can in form, the details of usage and implementation It is upper various modifications may be made and without paying creative work.Therefore, the present invention is defined by the appended claims.

Claims (10)

1. a kind of man-machine interaction method towards intelligent robot, it is characterised in that including:
Interactive information obtaining step, obtains the multi-modal interactive information on user, wherein, wrapped in the multi-modal interactive information Information containing interactive voice;
Interaction topic determines step, determines whether the user is child user according to the multi-modal interactive information, wherein, such as Really described user is child user, then the interactive voice information is parsed, and talked about according to analysis result from default children Current interaction topic is determined in exam pool;
Feedback information exports step, generates conversational feedback information based on the current interactive topic and exports.
2. the method as described in claim 1, it is characterised in that also include:
Children's topic storehouse construction step, data are crawled based on network, are that the network crawls number using default topic classification model According to each topic addition adult's topic label or children's topic label, built using the topic of children's topic label described default Children's topic storehouse.
3. method as claimed in claim 2, it is characterised in that in children's topic storehouse construction step, utilize default words Topic disaggregated model crawls the news label of data according to the network and adds mark to crawl each topic of data for the network Label.
4. such as method according to any one of claims 1 to 3, it is characterised in that also include:
Topic tag modification step, modifies according to the feedback information of the user got to the label of correspondence topic.
5. such as method according to any one of claims 1 to 4, it is characterised in that in the interactive topic determines step, also The ID of child user is determined according to the multi-modal interactive information, determines that the child user is corresponding according to the ID Exportable topic, and determined from the corresponding exportable topic of the user according to the analysis result currently to interact topic.
6. a kind of human-computer interaction device towards intelligent robot, it is characterised in that including:
Interactive information acquisition module, it is used to obtain the multi-modal interactive information on user, wherein, the multi-modal interaction letter Interactive voice information is included in breath;
Interaction topic determining module, it is used to determine whether the user is child user according to the multi-modal interactive information, Wherein, if the user be child user, the interactive voice information is parsed, and according to analysis result from preset Current interaction topic is determined in children's topic storehouse;
Feedback information output module, it is used for based on the current interactive topic generation conversational feedback information and exported.
7. device as claimed in claim 6, it is characterised in that also include:
Children's topic storehouse builds module, and it is used to crawl data based on network, is the network using default topic classification model Each topic addition adult's topic label or children's topic label of data are crawled, institute is built using the topic of children's topic label State default children's topic storehouse.
8. device as claimed in claim 7, it is characterised in that children's topic storehouse builds module and is configured to utilize default words Topic disaggregated model crawls the news label of data according to the network and adds mark to crawl each topic of data for the network Label.
9. the device as any one of claim 6~8, it is characterised in that also include:
Topic tag modification module, it is used to repair the label of correspondence topic according to the feedback information of the user got Change.
10. the device as any one of claim 6~9, it is characterised in that the interactive topic determining module is configured to The ID of child user is determined always according to the multi-modal interactive information, child user correspondence is determined according to the ID Exportable topic, and determined from the corresponding exportable topic of the user according to the analysis result currently to interact topic.
CN201710107291.8A 2017-02-27 2017-02-27 A kind of man-machine interaction method and device towards intelligent robot Pending CN106991123A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710107291.8A CN106991123A (en) 2017-02-27 2017-02-27 A kind of man-machine interaction method and device towards intelligent robot

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710107291.8A CN106991123A (en) 2017-02-27 2017-02-27 A kind of man-machine interaction method and device towards intelligent robot

Publications (1)

Publication Number Publication Date
CN106991123A true CN106991123A (en) 2017-07-28

Family

ID=59412491

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710107291.8A Pending CN106991123A (en) 2017-02-27 2017-02-27 A kind of man-machine interaction method and device towards intelligent robot

Country Status (1)

Country Link
CN (1) CN106991123A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107728780A (en) * 2017-09-18 2018-02-23 北京光年无限科技有限公司 A kind of man-machine interaction method and device based on virtual robot
CN108000526A (en) * 2017-11-21 2018-05-08 北京光年无限科技有限公司 Dialogue exchange method and system for intelligent robot
CN108037905A (en) * 2017-11-21 2018-05-15 北京光年无限科技有限公司 A kind of interaction output method and intelligent robot for intelligent robot
CN108108340A (en) * 2017-11-28 2018-06-01 北京光年无限科技有限公司 For the dialogue exchange method and system of intelligent robot
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
CN108933730A (en) * 2018-06-29 2018-12-04 百度在线网络技术(北京)有限公司 Information-pushing method and device

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105843382A (en) * 2016-03-18 2016-08-10 北京光年无限科技有限公司 Man-machine interaction method and device
CN105956179A (en) * 2016-05-30 2016-09-21 上海智臻智能网络科技股份有限公司 Data filtering method and apparatus
CN106021273A (en) * 2016-04-25 2016-10-12 北京光年无限科技有限公司 Method and system for processing information facing question answering robot
CN106205612A (en) * 2016-07-08 2016-12-07 北京光年无限科技有限公司 Information processing method and system towards intelligent robot
CN106294774A (en) * 2016-08-11 2017-01-04 北京光年无限科技有限公司 User individual data processing method based on dialogue service and device
CN106326440A (en) * 2016-08-26 2017-01-11 北京光年无限科技有限公司 Human-computer interaction method and device facing intelligent robot

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105843382A (en) * 2016-03-18 2016-08-10 北京光年无限科技有限公司 Man-machine interaction method and device
CN106021273A (en) * 2016-04-25 2016-10-12 北京光年无限科技有限公司 Method and system for processing information facing question answering robot
CN105956179A (en) * 2016-05-30 2016-09-21 上海智臻智能网络科技股份有限公司 Data filtering method and apparatus
CN106205612A (en) * 2016-07-08 2016-12-07 北京光年无限科技有限公司 Information processing method and system towards intelligent robot
CN106294774A (en) * 2016-08-11 2017-01-04 北京光年无限科技有限公司 User individual data processing method based on dialogue service and device
CN106326440A (en) * 2016-08-26 2017-01-11 北京光年无限科技有限公司 Human-computer interaction method and device facing intelligent robot

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107728780A (en) * 2017-09-18 2018-02-23 北京光年无限科技有限公司 A kind of man-machine interaction method and device based on virtual robot
CN107728780B (en) * 2017-09-18 2021-04-27 北京光年无限科技有限公司 Human-computer interaction method and device based on virtual robot
CN108000526A (en) * 2017-11-21 2018-05-08 北京光年无限科技有限公司 Dialogue exchange method and system for intelligent robot
CN108037905A (en) * 2017-11-21 2018-05-15 北京光年无限科技有限公司 A kind of interaction output method and intelligent robot for intelligent robot
CN108108340A (en) * 2017-11-28 2018-06-01 北京光年无限科技有限公司 For the dialogue exchange method and system of intelligent robot
CN108108340B (en) * 2017-11-28 2021-07-23 北京光年无限科技有限公司 Dialogue interaction method and system for intelligent robot
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
CN108933730A (en) * 2018-06-29 2018-12-04 百度在线网络技术(北京)有限公司 Information-pushing method and device

Similar Documents

Publication Publication Date Title
CN106991123A (en) A kind of man-machine interaction method and device towards intelligent robot
CN105807933B (en) A kind of man-machine interaction method and device for intelligent robot
Paleček et al. Relativism and the ontological turn within anthropology
CN105798918A (en) Interactive method and device for intelligent robot
CN107728780A (en) A kind of man-machine interaction method and device based on virtual robot
CN105760362B (en) A kind of question and answer evaluation method and device towards intelligent robot
CN107273477A (en) A kind of man-machine interaction method and device for robot
CN106294726A (en) Based on the processing method and processing device that robot role is mutual
CN106531162A (en) Man-machine interaction method and device used for intelligent robot
CN106294854A (en) A kind of man-machine interaction method for intelligent robot and device
CN106528530A (en) Method and device for determining sentence type
CN106598241A (en) Interactive data processing method and device for intelligent robot
CN106503786A (en) Multi-modal exchange method and device for intelligent robot
KR101649911B1 (en) dialog system using extended domain and natural language recognition method thereof
WO2017200078A1 (en) Dialog method, dialog system, dialog device, and program
KR101937778B1 (en) System, method and recording medium for machine-learning based korean language conversation using artificial intelligence
CN109461435A (en) A kind of phoneme synthesizing method and device towards intelligent robot
JP6864326B2 (en) Dialogue methods, dialogue systems, dialogue devices, and programs
Inahara The rejected voice: towards intersubjectivity in speech language pathology
Probst et al. Polyphonic coding in qualitative analysis: conversation as musical motet
CN108177151A (en) A kind of robot and its ontology voice interactive system
CN107066288A (en) A kind of multi-modal exchange method and device for intelligent robot
Haugh et al. Transformative continuations,(dis) affiliation, and accountability in Japanese interaction
CN106548777A (en) A kind of data processing method and device for intelligent robot
Förster Enactivism and Robotic Language Acquisition: A Report from the Frontier

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20170728