CN107783650A - A kind of man-machine interaction method and device based on virtual robot - Google Patents
A kind of man-machine interaction method and device based on virtual robot Download PDFInfo
- Publication number
- CN107783650A CN107783650A CN201710840497.1A CN201710840497A CN107783650A CN 107783650 A CN107783650 A CN 107783650A CN 201710840497 A CN201710840497 A CN 201710840497A CN 107783650 A CN107783650 A CN 107783650A
- Authority
- CN
- China
- Prior art keywords
- information
- user
- modal
- virtual robot
- feedback information
- 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
- 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
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2203/00—Indexing scheme relating to G06F3/00 - G06F3/048
- G06F2203/01—Indexing scheme relating to G06F3/01
- G06F2203/011—Emotion or mood input determined on the basis of sensed human body parameters such as pulse, heart rate or beat, temperature of skin, facial expressions, iris, voice pitch, brain activity patterns
Abstract
A kind of man-machine interaction method based on virtual robot, including:Step 1: obtain multi-modal input information;Step 2: parsing multi-modal input information, judge to whether there is user in designated area, wherein, if user in designated area be present, perform step 3;Step 3: the analysis result based on multi-modal input information carries out intention assessment, determine user view, according to user view, call the multi-modal interaction data related with current interaction scenarios to generate and export corresponding multi-modal feedback information, wherein, the virtual robot copyright in multi-modal feedback information is vivid related to current interaction scenarios information.This method can be exported the form that the related content of enterprise and enterprise product is interacted by virtual robot, make reception of the client to enterprises propagandist content more complete, so that user can quickly and easily get the related content about enterprise and enterprise product by virtual robot, so as to contribute to the popularization of business event.
Description
Technical field
The present invention relates to robotic technology field, specifically, is related to a kind of man-machine interaction side based on virtual 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 requirement of the people for robot is also conformed 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 interacts, man-machine interaction also just turn into an important factor for determining intelligent robot development.
At present, virtual robot is increasingly welcome by user as a kind of intelligent robot with virtual image,
But the interaction scenarios of virtual robot relatively limit to, using the teaching of the invention it is possible to provide service it is limited, how to widen virtual robot service neck
Domain turns into the problem of current urgent need to resolve
The content of the invention
To solve the above problems, the invention provides a kind of man-machine interaction method based on virtual robot, methods described
Enable virtual robot and include the image of the virtual robot in default viewing area, it includes:
Step 1: obtain multi-modal input information;
Step 2: parsing the multi-modal input information, judge to whether there is user in designated area, wherein,
If user be present in the designated area, step 3 is performed;
Step 3: the analysis result based on the multi-modal input information carries out intention assessment, user view is determined, according to
The user view, call the multi-modal interaction data related with current interaction scenarios to generate and export corresponding multi-modal feedback
Information, wherein, the virtual robot copyright in the multi-modal feedback information is vivid related to the current interaction scenarios information.
According to one embodiment of present invention, in the step 2, if user is not present in the designated area,
Step 4 is performed, in the step 4, generates and exports default enterprise's promotion message.
According to one embodiment of present invention, in the step 3, also by being carried out to the multi-modal input information
Parsing, obtains the user feeling information of the user, and generates and export corresponding multi-modal with reference to the user feeling information
Feedback information.
According to one embodiment of present invention, the multi-modal feedback information also includes and the virtual robot copyright shape
As corresponding voice feedback information.
According to one embodiment of present invention, in the step 3, actively generate and export reception function prompt information,
And the input information fed back according to the user with regard to the reception function prompt information judges whether to need to start reception function,
Wherein, if necessary to start reception function, then generated according to current interaction scenarios information and export corresponding multi-modal feedback letter
Breath, wherein, the multi-modal feedback information includes Quick Response Code corresponding with the reception function phase.
Present invention also offers a kind of human-computer interaction device based on virtual robot, described device is configured to virtual machine
The image of device people is shown in default viewing area, and described device includes:
Data obtaining module is inputted, it is used to obtain multi-modal input information;
Data processing module, it is connected with the input data obtaining module, for entering to the multi-modal input information
Row parsing, judge to whether there is user in designated area, wherein, if user be present in the designated area, based on described
The analysis result of multi-modal input information carries out intention assessment, determines user view, according to the user view, calls and current
The related multi-modal interaction data of interaction scenarios generates and exports corresponding multi-modal feedback information, wherein, it is described multi-modal anti-
Virtual robot copyright in feedforward information is vivid related to the current interaction scenarios information.
According to one embodiment of present invention, if user, the data processing module are not present in the designated area
Then it is configured to generate and export default enterprise's promotion message.
According to one embodiment of present invention, the data processing module is configured to also by believing the multi-modal input
Breath is parsed, and obtains the user feeling information of the user, and is generated and exported corresponding with reference to the user feeling information
Multi-modal feedback information.
According to one embodiment of present invention, the multi-modal feedback information also includes and the virtual robot copyright shape
As corresponding voice feedback information.
According to one embodiment of present invention, the data processing module is configured to actively generate and exports reception function and carries
Show information, and the input information fed back according to the user with regard to the reception function prompt information judges whether to need startup to connect
Standby function, wherein, if necessary to start reception function, then generated and exported corresponding multi-modal according to current interaction scenarios information
Feedback information, wherein, the multi-modal feedback information includes Quick Response Code corresponding with the reception function phase.
Present invention also offers a kind of storage medium, it is stored with the storage medium described in executable as above any one
The program code of man-machine interaction method step based on virtual robot.
Man-machine interaction method provided by the present invention based on virtual robot causes the version of shown virtual robot
Power image or action match with current interaction scenarios, by the related content of enterprise and enterprise product (such as Introduction of enterprises, look forward to
Industry product introduction etc.) exported by the form of virtual robot interaction, so that reception of the client to enterprises propagandist content
More completely, relevant enterprise and enterprise can quickly and easily be got by virtual robot by so also allowing for user
The related content of product, so as to contribute to the popularization of business event.
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 be the man-machine interaction method according to an embodiment of the invention based on virtual robot realize scene illustrate
Figure;
Fig. 2 is the implementation process signal of the man-machine interaction method according to an embodiment of the invention based on virtual robot
Figure;
Fig. 3 is that the implementation process of the man-machine interaction method in accordance with another embodiment of the present invention based on virtual robot is shown
It is intended to;
Fig. 4 is shown according to the implementation process of the man-machine interaction method based on virtual robot of another embodiment of the invention
It is intended to;
Fig. 5 is the structural representation of the human-computer interaction device according to an embodiment of the invention based on virtual robot.
Embodiment
Embodiments of the present invention are described in detail below with reference to drawings and Examples, and how the present invention is applied whereby
Technological means solves technical problem, and the implementation process for reaching technique effect can fully understand and implement according to this.Need to illustrate
As long as not forming conflict, each embodiment in 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 not have to tool here
Body details or described ad hoc fashion are implemented.
In addition, can be in the department of computer science of such as one group computer executable instructions the flow of accompanying drawing illustrates the step of
Performed in system, although also, show logical order in flow charts, in some cases, can be with different from herein
Order perform shown or described step.
The invention provides a kind of new man-machine interaction method based on virtual robot, the man-machine interaction method can lead to
Cross and show that virtual robot copyright image accordingly related to enterprise and enterprise product is come and user carries out man-machine interaction.Fig. 1
Show this method in the present embodiment realizes schematic diagram of a scenario.
As shown in figure 1, in the present embodiment, being somebody's turn to do the man-machine interaction method based on virtual robot can use in implementation process
To the image display 101 for showing virtual robot image 103.It is pointed out that implement in the different of the present invention
In example, above-mentioned image display 101 can realize that the invention is not restricted to this according to being actually needed using different equipment.
For example, in one embodiment of the invention, above-mentioned image display 101 can show virtual machine using liquid crystal display
Device it is humanoid as;And in another embodiment of the present invention, above-mentioned image display 101 can also using holographic projector come
Show virtual robot image 103.
In the present embodiment, the virtual robot image shown by image display 101 is and enterprise and enterprise product
Corresponding.In order to clearly illustrate the realization of the man-machine interaction method provided by the present invention based on virtual robot original
Reason, implementation process and advantage, come to the man-machine interaction side based on virtual robot below in conjunction with different embodiments
Method is further described.
Embodiment one:
Fig. 2 shows the implementation process signal for the man-machine interaction method based on virtual robot that the present embodiment is provided
Figure.
As shown in Fig. 2 the man-machine interaction method based on virtual robot that the present embodiment is provided is first in step S201
It is middle to obtain multi-modal input information.In the present embodiment, accessed multi-modal input information had been both in step s 201 for this method
The video information (i.e. user images information) on user can be included, can also be comprising the audio-frequency information that user is inputted (i.e.
User speech information).Certainly, in other embodiments of the invention, obtained in step s 201 according to actual conditions, this method
Other appropriate messages can also be included in the multi-modal interactive information got, the invention is not restricted to this.
After multi-modal input information is got, this method can be carried out in step S202 to above-mentioned multi-modal input information
Parsing, and judge to whether there is user in designated area according to the analysis result obtained by step S202 in step S203.
In the present embodiment, above-mentioned designated area can be for show virtual robot copyright image image display before it is certain
Regional extent, the present invention are not defined to the particular location and size of above-mentioned designated area.In other realities of the present invention
Apply in example, this method can also determine to whether there is user in designated area by other means, for example, passing through microphone array
Row, in the range of receiving of the microphone array, it is determined that when receiving user speech, you can it is determined that user be present.
Specifically, in the present embodiment, this method is in step S202 preferably to the figure in above-mentioned multi-modal input information
As information progress image procossing, to determine specific region (the i.e. area corresponding with above-mentioned designated area of accessed image
Domain) in whether there is humanoid figure's picture.Wherein, if humanoid figure's picture is not present in the specific region of accessed image, then
Also can judges user is not present in designated area this method in step S203;And if the specified area of acquired image
Humanoid figure's picture in domain be present, then also can judges user be present in designated area to this method in step S203.
If user is not present in designated area, then there is not pedestrian or client before then representing image display,
So now this method can preferably generate and export default enterprise's promotion message.In the present embodiment, above-mentioned default enterprise promotes
Information can be that the Introduction of enterprises video of relevant enterprise in current interaction scenarios or enterprise product introduce video etc..Certainly, exist
In other embodiments of the invention, if user is not present in designated area, this method can not also export related feedback information,
So that image display is in a dormant state, so contribute to reduce energy consumption.
If user in designated area be present, then pedestrian or client occur before then representing image display, now
This method can carry out intention assessment in step S204 based on the analysis result of multi-modal input information, so that it is determined that going out user
It is intended to.
Specifically, in the present embodiment, this method can be believed the audio in above-mentioned multi-modal input information in step S204
Breath is parsed, so as to obtain out interactive topic.Interaction topic can characterize user and interact or take turns more in single-wheel with robot
The interactive subject surrounded in interaction, this method utilize determined interaction topic to primarily determine that out final needs
The context being related to required for the feedback information of generation.
Certainly, in other embodiments of the invention, when including text message in above-mentioned multi-modal input information, the party
Method can also determine to interact topic in step S204 by way of extracting the keyword in text message.And work as user institute
When to interactively enter information be voice dialog information of input, voice dialog information can be converted to corresponding text by this method first
This information, then determine to interact topic by parsing text message.
After determining to interact topic, this method can utilize it is default be intended to collection of illustrative plates, according to the interaction topic determined come
Determine user view.Intention can be considered as robot and attempt to understand in interactive process with itself visual angle, and user is at certain
The plan for reaching certain purpose it is expected under kind theme or topic.Because the content involved by interaction topic is relatively broad, therefore
This method also just needs to excavate and determine that user needs to obtain from robot in follow-up interactive process to be intended to collection of illustrative plates
Information (i.e. robot needs the information to user feedback).
Specifically, in the present embodiment, when according to interaction topic to determine the intention of user, this method first can be default
It is intended to determine the node corresponding to above-mentioned interactive topic in collection of illustrative plates, then is intended to determine with above-mentioned interaction in collection of illustrative plates default
Node corresponding to topic is the node (i.e. terminal node) corresponding to the line of start node, so that according to terminal node come really
Make user view.
By the node being connected with start node there may be multiple, therefore the terminal node that this method is determined
May be multiple.For such case, in the present embodiment, this method first can be according to the multiple sections being connected with start node
Point determines that multiple candidate users are intended to, and then these candidate users are intended to carry out confidence level sequence, and according to ranking results
To determine required user view.
Specifically, in the present embodiment, this method is according to the default weight for being intended to each node line in picture come to these
Candidate user is intended to be ranked up, and the candidate user of weight selection maximum is intended to be used as final required user view.
Certainly, in other embodiments of the invention, this method can also be using other rational methods come according to multi-modal
Input information determines user view, and the invention is not restricted to this.
As shown in Fig. 2 in the present embodiment, after user view is determined, this method can be in step S205 according to user
It is intended to, calls the multi-modal input information related with current interaction scenarios to generate corresponding multi-modal feedback information.
In the present embodiment, virtual robot copyright image is included in the multi-modal feedback information that this method is generated, should
The vivid enterprise or enterprise product to corresponding to current interaction scenarios of virtual robot copyright is related.For example, this method is in step
Generated in S205 and show virtual robot copyright image can be enterprise lucky figure image or the enterprise
Cartoon character of a certain product etc..
It is pointed out that in the present embodiment, according to being actually needed, above-mentioned steps S201 to step S205 both can be complete
Realizing for the relevant hardware devices directly interacted with user in current interaction scenarios are arranged at, can also be by upper
State and ordinatedly realized with cloud server for the relevant hardware devices directly interacted with user, the invention is not restricted to this.
For example, when above-mentioned steps are needed by the relevant hardware devices and cloud server for directly being interacted with user
When ordinatedly realizing, this method can be by the multi-modal input information transfer got to cloud server, with by cloud service
Device generates multi-modal feedback information by performing above-mentioned steps S202 to step S205, then multi-modal anti-by what is generated again
Feedforward information is transmitted to being exported for the relevant hardware devices directly interacted with user.
It is also desirable to, it is noted that in different embodiments of the invention, this method generated in step S205 simultaneously
The multi-modal feedback information of output both can be comprising the vivid animation of virtual robot copyright or comprising virtual machine
The knot of animation and the corresponding voice messaging (such as with the vivid related story voice of the virtual robot copyright) of people's copyright image
Close, or be the combination of the information of the animation comprising virtual robot copyright image and other proper forms, the invention is not restricted to
This.
As can be seen that the man-machine interaction method based on virtual robot that the present embodiment is provided causes from foregoing description
It is shown go out virtual robot copyright image or action match with current interaction scenarios, by enterprise and enterprise product
Related content (such as Introduction of enterprises, enterprise product introduction etc.), the form interacted by virtual robot are exported, so that
Reception of the client to enterprises propagandist content is more complete, and so also allowing for user can be by virtual robot come convenient, fast
Ground gets the related content about enterprise and enterprise product, so as to contribute to the popularization of business event.
Embodiment two:
Fig. 3 shows the implementation process signal for the man-machine interaction method based on virtual robot that the present embodiment is provided
Figure.
As shown in figure 3, the man-machine interaction method based on virtual robot that the present embodiment is provided is first in step S301
It is middle to obtain multi-modal input information, then in step s 302 to above-mentioned multi-modal input information parsing, and in step S303
Judged to whether there is user in designated area according to the analysis result obtained by step S302.Used if existed in designated area
Family, then party's rule can be in step s 304 by carrying out intention knowledge to accessed multi-modal input information in step S301
Not, so that it is determined that going out user view.
It is pointed out that in the present embodiment, above-mentioned steps S301 to step S304 specific implementation principle and realization
Process is identical with step S201 in above-described embodiment one to step S204 realization principle and implementation process, therefore no longer right herein
Above-mentioned steps S301 to step S304 related content are repeated.
In the present embodiment, this method, can also be in step S305 in above-mentioned steps S301 in addition to determining user view
Accessed multi-modal input information is parsed to determine user feeling information.Specifically, in the present embodiment, this method
In step S305 recognition of face can be carried out to the image information in multi-modal input information accessed in step S301
To obtain the facial image in image, Expression Recognition then is carried out to obtained facial image again, so also can according to table
Feelings recognition result determines user feeling information.
Certainly, in other embodiments of the invention, this method can also use other rational methods in step S305
To determine user feeling information according to multi-modal input information, the invention is not restricted to this.For example, in one embodiment of invention
In, this method can also be by carrying out Application on Voiceprint Recognition, according to vocal print to the voice messaging of accessed multi-modal input information
Recognition result determines user feeling information.
After user view and user feeling information is obtained, in the present embodiment, this method can in step S306 basis
Above-mentioned user view and user feeling information, to call the multi-modal interaction data related to current interaction scenarios, with generation
Corresponding multi-modal feedback information.
Embodiment three:
Fig. 4 shows the implementation process signal for the man-machine interaction method based on virtual robot that the present embodiment is provided
Figure.
As shown in figure 4, the man-machine interaction method based on virtual robot that the present embodiment is provided is first in step S401
It is middle to obtain multi-modal input information, then to above-mentioned multi-modal input information parsing in step S402, and in step S403
Judged to whether there is user in designated area according to the analysis result obtained by step S402.
It is pointed out that in the present embodiment, above-mentioned steps S401 to step S403 specific implementation principle and realization
Process is identical with step S201 in above-described embodiment one to step S203 realization principle and implementation process, therefore no longer right herein
Above-mentioned steps S401 to step S403 related content are repeated.
In the present embodiment, if user in designated area be present, then party's rule can actively generate in step s 404
And export reception function prompt information.For example, this method detects in designated area that user be present (has detected user's entrance
To specified services scope) when, the virtual image of the mascot of enterprise can be shown and export such as that " you are good, it is necessary to which I is you services
" voice messaging.
This method can obtain user in step S405 and be directed to above-mentioned reception function after function prompt information is received in output
The input information that prompt message is fed back, and judge now whether to need to start reception function according to the input information.
For example, if the input information that user is fed back for reception function prompt information is that such as " I wants to learn about
The voice messaging of the product of your enterprises ", then this method will also judge now to need to start reception function;And if user
The input information fed back for reception function prompt information is the voice messaging such as " being out of use, thanks ", then this method
Also will judge now start reception function, at this moment party's rule can perform step S407 to generate and export default enterprise
Industry promotion message.
In the present embodiment, if this method now needs to start reception function in step S405, then party's rule meeting
Corresponding multi-modal feedback information is generated and exported according to current interaction scenarios information in step S406.In the present embodiment,
This method generated in step S406 and export multi-modal feedback information preferably include it is corresponding with the reception function phase
Quick Response Code.User can receive APP by scanning the Quick Response Code to obtain the enterprise of the public number of current enterprise or the enterprise, this
Sample user can receive the guiding of virtual robot in real time on the intelligent terminal of oneself.
For example, if the application scenarios of this method are hotel, then this method is exported multi-modal in step S406
Feedback information can then include the reception APP in the hotel, and user can install reception APP on the intelligent terminal of oneself.With
Family can know the house type guidance information and hotel's overall structure in the hotel during using the reception APP in the hotel
Information etc..
For another example if the application scenarios of this method are amusement park, then this method is exported more in step S406
Mode feedback information can then include the public number of the amusement park, and user can know the field of the amusement park by the public number
The information such as institute's general layout, points for attention introduction and the queuing situation in each place.
Present invention also offers a kind of storage medium, it is stored with the storage medium executable as described above based on virtual
The program code of the man-machine interaction method step of robot.In addition, present invention also offers a kind of people based on virtual robot
Machine interactive device, Fig. 5 show the structural representation of the human-computer interaction device in the present embodiment.
As shown in figure 5, in the present embodiment, it is somebody's turn to do the human-computer interaction device based on virtual robot and preferably includes:Input letter
Cease acquisition module 501 and data processing module 502.Wherein, according to being actually needed, input data obtaining module 501 can be adopted
Realized with different device or equipment, so as to obtain different types of input information.
For example, if necessary to obtain image information, then input data obtaining module 501 then needs to include corresponding image
Collecting device (such as imaging first-class);And voice messaging is obtained if desired, then input data obtaining module 501 then needs to wrap
Include corresponding voice capture device (such as microphone etc.);And text message is obtained if desired, then input acquisition of information mould
Block 501 then needs to include corresponding text collection equipment (such as physical keyboard or dummy keyboard etc.).
Data processing module 502 is connected with input acquisition of information mould 501, and it can be passed to input data obtaining module 501
Defeated next multi-modal input information is parsed, and carries out intention assessment according to analysis result, so that it is determined that going out user view.
Specifically, in the present embodiment, data processing module 502 preferably includes cloud server.Input acquisition of information mould
Block 501 get it is multi-modal input information after, can will it is above-mentioned it is multi-modal input information by related data transmission network (such as
Ethernet etc.) transmit to cloud server, to be parsed by cloud server to above-mentioned multi-modal input information.
In the present embodiment, cloud server, which is preferably by the default collection of illustrative plates that is intended to, to be come to the multi-modal parsing knot for inputting information
Fruit carries out intention assessment, so as to obtain user view.Certainly, in other embodiments of the invention, cloud server can be with
User view is determined using other rational methods, the invention is not restricted to this.
After user view is obtained, cloud server is called with currently interacting field always according to the user view determined
The related multi-modal interaction data of scape, to generate and export corresponding multi-modal feedback information.Wherein, above-mentioned multi-modal feedback letter
Vivid (the enterprise for example, corresponding to current interaction scenarios related to current interaction scenarios information of virtual robot copyright in breath
Lucky figure image or related cartoon character etc.).
After above-mentioned multi-modal feedback information is generated, cloud server can be by above-mentioned multi-modal transmission of feedback information to setting
Output equipment in current interaction scenarios, with above-mentioned multi-modal feedback information is exported by the output equipment (such as
Show virtual robot copyright image or output voice corresponding with virtual robot copyright image etc.).
It is pointed out that in different embodiments of the invention, above-mentioned cloud server realizes the specific original of its function
Reason and process both can be identical to step S205 disclosure of that with step S202 in above-described embodiment one, can also with it is upper
It is identical to step S306 disclosure of that to state step S302 in embodiment two, can also be with step S402 in above-described embodiment three
It is identical to step S407 disclosure of that, therefore no longer the related content of cloud server is repeated herein.
Certainly, in other embodiments of the invention, the function of cloud server and the function of output equipment can be with
It is integrated in a certain equipment being arranged in current interaction scenarios to realize, so inputs data obtaining module 501 also with regard to nothing
The multi-modal input information got need to be uploaded to cloud server, and can changed by locally carrying out data processing.
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 apply, for the technology of this area
For personnel, in the case of without departing substantially from the principle and thought 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 pay creative work.Therefore, the present invention is defined by the appended claims.
Claims (11)
1. a kind of man-machine interaction method based on virtual robot, it is characterised in that virtual robot is enabled, by the virtual machine
The image of device people is shown in default viewing area, including:
Step 1: obtain multi-modal input information;
Step 2: parsing the multi-modal input information, judge to whether there is user in designated area, wherein, if
User in the designated area be present, then perform step 3;
Step 3: the analysis result based on the multi-modal input information carries out intention assessment, user view is determined, according to described
User view, call the multi-modal interaction data related with current interaction scenarios to generate and export corresponding multi-modal feedback letter
Breath, wherein, the virtual robot copyright in the multi-modal feedback information is vivid related to the current interaction scenarios information.
2. the method as described in claim 1, it is characterised in that in the step 2, if do not deposited in the designated area
In user, then step 4 is performed, in the step 4, generate and export default enterprise's promotion message.
3. method as claimed in claim 1 or 2, it is characterised in that in the step 3, also by described multi-modal defeated
Enter information to be parsed, obtain the user feeling information of the user, and generated with reference to the user feeling information and export phase
The multi-modal feedback information answered.
4. such as method according to any one of claims 1 to 3, it is characterised in that the multi-modal feedback information also include with
The corresponding voice feedback information of the virtual robot copyright image.
5. such as method according to any one of claims 1 to 4, it is characterised in that in the step 3, actively generate and defeated
Go out to receive function prompt information, and the input information judgement fed back according to the user with regard to the reception function prompt information is
It is no to need to start reception function, wherein, if necessary to start reception function, then generate and export according to current interaction scenarios information
Corresponding multi-modal feedback information, wherein, the multi-modal feedback information includes Quick Response Code corresponding with the reception function phase.
6. a kind of human-computer interaction device based on virtual robot, it is characterised in that described device is configured to virtual robot
Image be shown in default viewing area, described device includes:
Data obtaining module is inputted, it is used to obtain multi-modal input information;
Data processing module, it is connected with the input data obtaining module, for being solved to the multi-modal input information
Analysis, judge to whether there is user in designated area, wherein, if user be present in the designated area, based on the multimode
The analysis result of state input information carries out intention assessment, determines user view, according to the user view, calls with currently interacting
The related multi-modal interaction data of scene generates and exports corresponding multi-modal feedback information, wherein, the multi-modal feedback letter
Virtual robot copyright in breath is vivid related to the current interaction scenarios information.
7. device as claimed in claim 6, it is characterised in that if user, the data are not present in the designated area
Processing module is then configured to generate and export default enterprise's promotion message.
8. device as claimed in claims 6 or 7, it is characterised in that the data processing module is configured to also by described
Multi-modal input information is parsed, and obtains the user feeling information of the user, and generate with reference to the user feeling information
And export corresponding multi-modal feedback information.
9. the device as any one of claim 6~8, it is characterised in that the multi-modal feedback information also include with
The corresponding voice feedback information of the virtual robot copyright image.
10. the device as any one of claim 6~9, it is characterised in that the data processing module is configured to actively
Generate and export reception function prompt information, and the input fed back according to the user with regard to the reception function prompt information is believed
Breath judges whether to need to start reception function, wherein, if necessary to start reception function, then given birth to according to current interaction scenarios information
Into and export corresponding multi-modal feedback information, wherein, the multi-modal feedback information includes corresponding with the reception function
Quick Response Code.
11. a kind of storage medium, it is characterised in that be stored with the storage medium executable as any in claim 1-5
The program code of method and step described in.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710840497.1A CN107783650A (en) | 2017-09-18 | 2017-09-18 | A kind of man-machine interaction method and device based on virtual robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710840497.1A CN107783650A (en) | 2017-09-18 | 2017-09-18 | A kind of man-machine interaction method and device based on virtual robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107783650A true CN107783650A (en) | 2018-03-09 |
Family
ID=61437876
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710840497.1A Pending CN107783650A (en) | 2017-09-18 | 2017-09-18 | A kind of man-machine interaction method and device based on virtual robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107783650A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109857929A (en) * | 2018-12-29 | 2019-06-07 | 北京光年无限科技有限公司 | A kind of man-machine interaction method and device for intelligent robot |
CN111383346A (en) * | 2020-03-03 | 2020-07-07 | 深圳创维-Rgb电子有限公司 | Interaction method and system based on intelligent voice, intelligent terminal and storage medium |
CN111966212A (en) * | 2020-06-29 | 2020-11-20 | 百度在线网络技术(北京)有限公司 | Multi-mode-based interaction method and device, storage medium and smart screen device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103440677A (en) * | 2013-07-30 | 2013-12-11 | 四川大学 | Multi-view free stereoscopic interactive system based on Kinect somatosensory device |
US20150089445A1 (en) * | 2006-01-30 | 2015-03-26 | Microsoft Corporation | Controlling Application Windows In An Operating System |
CN105868827A (en) * | 2016-03-25 | 2016-08-17 | 北京光年无限科技有限公司 | Multi-mode interaction method for intelligent robot, and intelligent robot |
-
2017
- 2017-09-18 CN CN201710840497.1A patent/CN107783650A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150089445A1 (en) * | 2006-01-30 | 2015-03-26 | Microsoft Corporation | Controlling Application Windows In An Operating System |
CN103440677A (en) * | 2013-07-30 | 2013-12-11 | 四川大学 | Multi-view free stereoscopic interactive system based on Kinect somatosensory device |
CN105868827A (en) * | 2016-03-25 | 2016-08-17 | 北京光年无限科技有限公司 | Multi-mode interaction method for intelligent robot, and intelligent robot |
Non-Patent Citations (1)
Title |
---|
张红琼: "《替代人类互作的机器人》", 30 April 2012, 安徽美术出版社 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109857929A (en) * | 2018-12-29 | 2019-06-07 | 北京光年无限科技有限公司 | A kind of man-machine interaction method and device for intelligent robot |
CN109857929B (en) * | 2018-12-29 | 2021-06-15 | 北京光年无限科技有限公司 | Intelligent robot-oriented man-machine interaction method and device |
CN111383346A (en) * | 2020-03-03 | 2020-07-07 | 深圳创维-Rgb电子有限公司 | Interaction method and system based on intelligent voice, intelligent terminal and storage medium |
CN111383346B (en) * | 2020-03-03 | 2024-03-12 | 深圳创维-Rgb电子有限公司 | Interactive method and system based on intelligent voice, intelligent terminal and storage medium |
CN111966212A (en) * | 2020-06-29 | 2020-11-20 | 百度在线网络技术(北京)有限公司 | Multi-mode-based interaction method and device, storage medium and smart screen device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107728780A (en) | A kind of man-machine interaction method and device based on virtual robot | |
US11036469B2 (en) | Parsing electronic conversations for presentation in an alternative interface | |
CN107294837A (en) | Engaged in the dialogue interactive method and system using virtual robot | |
US11151765B2 (en) | Method and apparatus for generating information | |
CN107704169B (en) | Virtual human state management method and system | |
US11024286B2 (en) | Spoken dialog system, spoken dialog device, user terminal, and spoken dialog method, retrieving past dialog for new participant | |
CN107632706B (en) | Application data processing method and system of multi-modal virtual human | |
CN110400251A (en) | Method for processing video frequency, device, terminal device and storage medium | |
CN107329990A (en) | A kind of mood output intent and dialogue interactive system for virtual robot | |
CN106464768A (en) | In-call translation | |
CN104735480B (en) | Method for sending information and system between mobile terminal and TV | |
CN107808191A (en) | The output intent and system of the multi-modal interaction of visual human | |
CN106471444A (en) | A kind of exchange method of virtual 3D robot, system and robot | |
CN113793398A (en) | Drawing method and device based on voice interaction, storage medium and electronic equipment | |
CN107783650A (en) | A kind of man-machine interaction method and device based on virtual robot | |
CN109005190A (en) | A method of full-duplex voice dialogue and page control are realized based on webpage | |
CN113850898A (en) | Scene rendering method and device, storage medium and electronic equipment | |
CN111063346A (en) | Cross-media star emotion accompany interaction system based on machine learning | |
CN113703585A (en) | Interaction method, interaction device, electronic equipment and storage medium | |
CN113792196A (en) | Method and device for man-machine interaction based on multi-modal dialog state representation | |
CN113742473A (en) | Digital virtual human interaction system and calculation transmission optimization method thereof | |
CN107705166A (en) | Information processing method and device | |
CN113157241A (en) | Interaction equipment, interaction device and interaction system | |
KR20210025943A (en) | Messenger based advertising method and apparatus | |
CN116628153B (en) | Method, device, equipment and medium for controlling dialogue of artificial intelligent 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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180309 |