CN107294837A - Engaged in the dialogue interactive method and system using virtual robot - Google Patents
Engaged in the dialogue interactive method and system using virtual robot Download PDFInfo
- Publication number
- CN107294837A CN107294837A CN201710362605.9A CN201710362605A CN107294837A CN 107294837 A CN107294837 A CN 107294837A CN 201710362605 A CN201710362605 A CN 201710362605A CN 107294837 A CN107294837 A CN 107294837A
- Authority
- CN
- China
- Prior art keywords
- virtual robot
- interactive
- robot
- modal
- dialogue
- 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
- 230000002452 interceptive effect Effects 0.000 title claims abstract description 78
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000003993 interaction Effects 0.000 claims abstract description 53
- 230000004044 response Effects 0.000 claims description 22
- 230000009471 action Effects 0.000 claims description 15
- 230000008859 change Effects 0.000 claims description 8
- 230000036651 mood Effects 0.000 claims description 7
- 230000002996 emotional effect Effects 0.000 claims description 6
- 230000008921 facial expression Effects 0.000 claims description 4
- 235000005336 Allium ursinum Nutrition 0.000 claims description 3
- 244000003363 Allium ursinum Species 0.000 claims description 3
- 238000004891 communication Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000012545 processing Methods 0.000 description 9
- 230000005540 biological transmission Effects 0.000 description 5
- 210000004556 brain Anatomy 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 2
- 230000008451 emotion Effects 0.000 description 2
- 239000011800 void material Substances 0.000 description 2
- 241000238558 Eucarida Species 0.000 description 1
- 101000746134 Homo sapiens DNA endonuclease RBBP8 Proteins 0.000 description 1
- 101000969031 Homo sapiens Nuclear protein 1 Proteins 0.000 description 1
- 206010062717 Increased upper airway secretion Diseases 0.000 description 1
- 206010028916 Neologism Diseases 0.000 description 1
- 102100021133 Nuclear protein 1 Human genes 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 208000026435 phlegm Diseases 0.000 description 1
- 235000011888 snacks Nutrition 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/02—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/225—Feedback of the input speech
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The present invention provides a kind of use virtual robot and engaged in the dialogue interactive method, wherein, the image of virtual robot is fabricated when application brings into operation and shown in default viewing area, and this method comprises the following steps:Obtain single mode and/or multi-modal interactive demand signal;Call the multi-modal robot capability interface of currently interaction;Utilize the multi-modal robot capability, reply data of the generation for the interactive demand signal;The reply data is exported in multi-modal form by the image of constructed virtual robot.The present invention is engaged in the dialogue interaction using virtual robot, on the one hand can enrich the individual of dialogue, and a certain vivid individual is shown by 3-D view or two dimensional image in the user graphical interface of chat system, the imagination space of user is enhanced.On the other hand, dialog information content intact to be expressed can also be showed by the animated show of virtual image.
Description
Technical field
The present invention relates to artificial intelligence field, specifically, being related to a kind of is used to engage in the dialogue friendship using virtual robot
Mutual method and system.
Background technology
The exploitation of robot chat interactive system is directed to imitating human conversation.The chat robots that early stage is widely known by the people should
Include the received inputs of processing such as small i chat robots, siri chat robots on iPhone (including text with program
Sheet or voice) and responded, to attempt to imitate mankind's response between context.
However, wanting to imitate human conversation completely, the interactive experience of user, these existing robot chat systems are enriched
Far it is not by far up to the mark.
The content of the invention
To solve the above problems, engaged in the dialogue interactive method the invention provides a kind of use virtual robot, it is described
The image of virtual robot is fabricated when application brings into operation and shown in default viewing area, and methods described includes following
Step:
Obtain single mode and/or multi-modal interactive demand signal;
Call the multi-modal robot capability interface of currently interaction;
Utilize the multi-modal robot capability, reply data of the generation for the interactive demand signal;
The reply data is exported in multi-modal form by the image of constructed virtual robot.
According to one embodiment of present invention, it is described virtual in the interactive method that engaged in the dialogue using virtual robot
The image of robot may be based on the two dimension or three-dimensional animation image of cartoon figure, real person or buckram man.
According to one embodiment of present invention, in the interactive method that engaged in the dialogue using virtual robot, the response
Data include the emotional parameters associated with the interactive demand signal.
According to one embodiment of present invention, in the interactive method that engaged in the dialogue using virtual robot, with multi-modal
Form, which exports the reply data, to be included:The virtual robot selects the following multi-modal way of output according to the emotional parameters
In one or more exported:
The change of the facial expression of virtual robot;
Represent the specific limb action of mood;
The voice of the specific tone, intonation.
According to one embodiment of present invention, engaged in the dialogue using virtual robot in interactive method, it is described other
Individual includes single people, single virtual robot or single tangible machine people.
According to one embodiment of present invention, it is waiting waiting in the interactive method that engaged in the dialogue using virtual robot
Receive from the application make for the conversation content reply data when, the virtual robot according to waited when
Between the length multi-modal conventional response output that independently selection is pre-set to be interacted temporarily.
According to one embodiment of present invention, the text envelope in the reply data is exported on the interactive interface of application
Breath, and/or, the interactive voice information obtained by voice acquisition device.
According to another aspect of the present invention, a kind of storage medium is additionally provided, is stored thereon with executable any of the above-described
The program code of method and step described in.
According to another aspect of the present invention, a kind of dialogue interactive system of use virtual robot is additionally provided.This is
System includes:
Mobile device, is provided with application thereon;
Multi-modal robot program's bag, it is activated when the application is run, to cause the application to perform such as preceding institute
The method and step stated;
Virtual robot interface, to the action that the image of the virtual robot is exported to user and is made;
Multi-modal robot capability interface, it is called with the correspondence ability processing interactive demand signal, and will obtain
Reply data be back to the mobile device.
The present invention is engaged in the dialogue interaction using virtual robot, the individual of dialogue on the one hand can be enriched, by a certain image
Individual shown by 3-D view or two dimensional image in the user graphical interface of chat system so that user seems
It is to talk with people, rather than machine, enhance the imagination space of user.On the other hand, using with the virtual of image output
The robot interaction that engages in the dialogue can also carry out complete emotion expression service, in addition to phonetically increasing mood, can also lead to
The animated show for crossing virtual image shows dialog information content intact to be expressed.Therefore, can using the present invention
To cause chat interactive system to obtain bigger progress on human conversation is imitated.
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
Accompanying drawing is used for providing a further understanding of the present invention, and constitutes a part for specification, the reality with the present invention
Apply example to be provided commonly for explaining the present invention, be not construed as limiting the invention.In the accompanying drawings:
Fig. 1-3 shows and engaged in the dialogue interactive schematic diagram according to the use virtual robot of the present invention;
Fig. 4 further show in more detail the internal structure block diagram of mobile device according to an embodiment of the invention;
Fig. 5 shows the internal structure block diagram of cloud server according to an embodiment of the invention;
Fig. 6 shows the structured flowchart of cloud server according to another embodiment of the invention;
Fig. 7 shows the schematic diagram for the database for constituting cloud server;
Fig. 8 is shown and engaged in the dialogue interactive overall procedure using virtual robot according to one embodiment of present invention
Figure;
Fig. 9 is shown and engaged in the dialogue interactive detailed process using virtual robot according to one embodiment of present invention
Figure;
Figure 10 is shown according to one embodiment of present invention in interaction individual, mobile device and cloud server tripartite
Between the flow chart that is communicated, and
The use virtual robot that Figure 11 shows according to another embodiment of the invention engages in the dialogue interactive text
The schematic diagram of input mode.
Embodiment
To make the object, technical solutions and advantages of the present invention clearer, the embodiment of the present invention is made below in conjunction with accompanying drawing
Further describe in detail.
Fig. 1-3 respectively illustrates the field for interacting dialogue with virtual robot 601 according to the interaction individual 202 of the present invention
Jing Tu.Wherein, interaction individual is respectively single people 202A, another virtual robot 202B or tangible machine people 202C.
As shown in figure 1, interaction individual 202 is people, mobile device 201 can be the smart mobile phone of the user, tablet personal computer,
Wearable device etc..Various applications are installed, these applications include but is not limited to, and social activity should on mobile device 201
With, educational applications, news application, audiovisual applications etc..One kind that chat application belongs in social class application, such as it is most common
QQ chat applications, wechat etc..In this kind of conversational applications of wechat, user is typically all that another user for having friends with it enters
Row interaction.Another user is typically also the people of entity.
As shown in figure 1, in one embodiment of the invention, mobile device 201 provides the client of application, and provide with
The hardware supported of the man-machine interaction of user, for example, obtain phonetic entry by voice array, and the dynamic of user is obtained by camera
Make, text input is obtained by touch-screen or keyboard;And, voice, the animation by virtual image are played by loudspeaker
Display comes output action and expression and exports content of text by display screen.
The application accesses multi-modal interactive robot so that multi-modal interactive robot turns into one in dialog procedure
Member, user can select to carry out question and answer, chat with the multi-modal robot that interacts.
The cloud server is to carry out semantic understanding to the interaction demand of user there is provided the multi-modal interactive robot
The terminal of the disposal ability of (language semantic understands, Action Semantic understands), realization is interacted with user's.
The virtual image is the carrier of the multi-modal interactive robot, to the multimode of the multi-modal interactive robot
State output is showed.
Virtual robot (using virtual image as carrier) is:The multi-modal interactive robot is carrier with virtual image
Community, i.e.,:UI image designs using determination is carriers;, based on multi-modal man-machine interaction, with AI such as semanteme, emotion, cognitions
Ability;User is set to enjoy the personalized and intelligentized service robot of Flow Experience.
It is not the mankind that Fig. 2 and Fig. 3, which respectively illustrate user, but virtual robot 202B or tangible machine people 202C
Situation.Virtual robot 202B can be another front end applications chatted using robot in identical application, two void
Intend robot to engage in the dialogue interaction.Also either, virtual robot 202B is the interaction agent in another application.Such as the institutes of Fig. 2 and 3
Show that the multi-modal interactive robot is parsed by cloud server, so as to obtain response multi-modal data.
In the present invention, virtual robot (using virtual image as carrier) is:The multi-modal interactive robot with it is virtual
Image is the community of carrier, can be opened a dialogue, be chatted with voice, text or multi-modal mode with people 202A.Below
Give one example and illustrate the interactive dialogue process of virtual robot 601 and people 202A.Travel what commercial undertaking provided at one
In public number, user can chat with its so expansion.
Virtual robot 601 is said:(smile), has anything to want to me merely (greeting)
People 202A is said:Have, I, which finds out, travels, where good you feel
Virtual robot 601 is said:Many places all very beautiful (smile).You are intended to the slight heat place of any still
Pleasantly cool local (query) of a bit
People 202A is said:I does not decide also for this, but I tends to the place of any of reducing phlegm and internal heat, scenic place.
Virtual robot 601 is said:It is such (smile), you, which are intended to travel at home, is also intended to travel abroad
(query)
People 202A is said:At home, going abroad will also get the visa, trouble.
Virtual robot 601 is said:Good (interested), I See, the good heat place of any of landscape have it is following these,
Such as Chengdu, Chongqing, Xiamen, Hainan, Shenzhen etc..Which (query) you think
People 202A is said:I is not familiar with to these cities, and you can introduce respectively
Virtual robot 601 is said:Alright, first, Chengdu and Chongqing border on geographical position, and you can be together
Go, the landscape in Chengdu and Chongqing is also very beautiful, is had mountain and water, and above all Chengdu and Chongqing are the paradise of cuisines,
There are most hot chafing dish, the snack that also pot chief etc. is much fond of eating.
People 202A is said:Alright, you are good intimate.Thank you.
In talking with more than, virtual robot 601 can select mood when responding and waiting other side to respond
Output.The response in expression that content in above question and answer in bracket is made for virtual robot 601.Except answering in expression
Answer, virtual robot 601 can also express the feelings of virtual robot at that time by way of lowering one's voice and raising intonation
Thread.Except the response in expression and intonation, virtual robot 601 can also express the feelings of oneself by the action on limbs
Thread, such as a series of actions such as nod, wave, sitting down, standing.
Virtual robot 601 can by judging the emotional change of interactive object, according to the emotional change of interactive object come
Make the change on corresponding expression, intonation and limbs.Virtual robot 601 can also occur in program interim card or network
To dance or other performance forms make up the interaction that program interim card and network problem brought and do not flowed when problem
Smooth defect.In addition, the user for slightly lacking some recognition capabilities, this interaction output can also improve their dialogue
Interaction capabilities.
Fig. 4 shows that use virtual robot according to an embodiment of the invention engages in the dialogue interactive system architecture
Block diagram.(identified not in figure as shown in figure 4, the system includes mobile device 201, other individuals 202 and cloud server 203
Entirely).Wherein, mobile device 201 includes kernel 2011, communication module 2012, user interface UI 2013, types of applications APP
2014 and input/output module 2015.Other individuals include people 202A, virtual robot 202B and physical machine as described above
Device people 202C.Cloud server 203 includes reply data storehouse, multi-modal robot interface 2032 and processing system etc., relevant
It will be introduced behind details.
The calculating and the processing of information for the data that kernel 2011 is used in mobile device 201.For example when conversational applications add
After carrying row, the transmission of data and information that communication module 2012 is used between mobile device 201 and cloud server 203.
In one example, mobile device 201 has wireless communication ability, and its data and information between high in the clouds 203 is exchanged
Transmitted by mobile Internet.
In mobile device 201, user interface UI 2013 some viewing area to show virtual robot image,
The interactive data produced between interactive object are shown in other viewing areas.The virtual robot image shown in viewing area
The two dimension or three-dimensional animation image of cartoon figure, real person or buckram man are may be based on, virtual robot is joined according to mood
One or more in the following multi-modal way of output of number selection are exported:The change of the facial expression of virtual robot, generation
The specific limb action and the specific tone, the voice of intonation for thread of expressing one's feelings.Interaction between the interactive object shown in viewing area
The data of generation can be speech form and textual form or other display formats that can be interacted.
Download and the specific location that successfully certain applies APP 2014 to be stored in storage medium is installed.For the present invention's
Chat feature block 2014B is specifically included in embodiment, social networking application APP 2014.Applying for the present invention is not having base locally
In natural language interaction capabilities, it is necessary to ask cloud server 203 to return to multi-modal reply data.The present invention is used for showing void
The virtual robot plug-in card program bag 2014A for intending the front end of image can mount in chat feature block 2014.Certainly, with plug-in unit shape
It is only a kind of implementation of the invention that formula, which is installed in application, to realize that the virtual image display function of conversational applications is not limited
In this.
For the purpose of illustration, the present invention enriches the feature of existing application using card format.Enable plug-in unit using offer
The respective services enough applied, including load mode is provided, are loaded into program bag plug-in unit and are assisted using with network transmission
In view, so as to carry out data exchange with program bag plug-in unit.Program bag plug-in unit, which is necessarily dependent upon, applies competence exertion itself function, only
Can not normally it be run by program bag plug-in unit.On the contrary, using and need not rely on program bag plug-in unit and can just run.
Need to conclude plug-in protocol between application program and plug-in unit.That is, provided in plug-in protocol, in application program
Which function can be used in plug-in unit.Specific in the present invention, in plug-in protocol, it can be stated that in it is multi-modal should
Answer is utilized according to needs by plug-in card program.In plug-in card program 2014A, multi-modal reply data can be analyzed, and find and response
The mood of Data Matching, action carry out animation output.In addition, when application is enabled, specifically when user chooses multi-modal machine
When people is chatted, plug-in card program will be received using the order that animating image is shown the need for sending, so that predetermined
Animation is carried out in viewing area to show.
In one embodiment, with it is described above slightly different, mobile device 201 can have general local
Parse the ability of interaction data.For example, mobile device 201 is also possible that local echoing database.Kernel 2011 can be to obtaining
The interaction data taken in local echoing database based on searching for matching answer.In view of the processing energy of mobile device 201
Power and storage capacity, these interacting operations are all fairly simple.Can be at this such as simple greeting, conventional question and answer language
Ground is obtained.And be related to and complicated algorithm parsing is carried out to the interaction content that user inputs, and learn the feelings in expanding data storehouse
Scape, then still can be obtained by allowing mobile device 201 to access cloud server 203.In the present embodiment, mobile device 201
Possess and determine whether to be communicated to obtain the ability of multi-modal reply data from high in the clouds.In addition, being set beyond the clouds with movement
Standby communication it is not smooth or, it is local in mobile device 201 in the case that high in the clouds calculates the overlong time that multi-modal reply data is spent
It is also than advantageous to provide multi-modal reply data.
Interactive voice and text message of the input/output module 2015 for receiving other individual inputs, or front end are more
The mode robot response voice and text message to be exported.Input/output module 2015 is by the above information transmission to UI
Viewing area 2013, UI viewing areas 2013 show information above, so that interactive object is checked.
The example of input equipment includes keyboard, cursor control device (mouse), the microphone for voice operating, scanning
Instrument, touch function (such as the capacitance type transducers to detect physical touch), camera (are examined using visible or nonvisible wavelength
Survey the action for not being related to touch) etc..Output equipment is for example including display screen, loudspeaker, haptic response apparatus etc..Movement is set
Standby communication capacity includes wired and radio communication.For example including:One or more Wi-Fi antennas, gps antenna, cellular antenna,
NFC antenna, Bluetooth antenna.
Other individuals 202 are the interactive object interacted with virtual robot, and the object interacted with virtual robot can be
One side, or multi-party.
Fig. 5 shows the system medium cloud that use virtual robot according to an embodiment of the invention engages in the dialogue interactive
End structure block diagram.Reply data storehouse 2031 comprising general population's reply data storehouse 2031B, personalization reply data storehouse 2031C with
And interaction particular responses database 2031D.
Wherein, adaptive voice model 2031A is adapted to the different problems of distinct interaction object, according to each interaction pair
As the characteristics of and speciality, train the certain database for adapting to specific interactive object, adaptive voice model 2031A can match somebody with somebody
Close personalization reply data storehouse 2031C and use.
General population's reply data storehouse 2031B is the reply data storehouse of the population stored in cloud server 203, number
According to stored in storehouse be multiple interactive objects reply data, do not possess personalization.
Personalized reply data storehouse 2031C is the exclusive reply data storehouse of specific interactive object in other individuals, this
Database can enrich with increasing for interactive dialogue so that interaction afterwards is more personalized and more suitable
Profit.
Interaction particular responses database 2031D is the particular responses data in an interaction, often produces and once hands over
Mutually, an interaction particular responses database 2031D for storing this interaction data will be generated.Interaction particular responses database
2031D coordinates general population's reply data storehouse 2031B and personalization reply data storehouse 2031C to use.
Fig. 6 shows the structured flowchart of cloud server according to another embodiment of the present invention.As illustrated, cloud service
Device 203 is made up of high in the clouds brain 600 and database resource 660, and database resource 660 is respectively at two differences with high in the clouds brain
Entity in.High in the clouds brain 600 has powerful calculation processing power, and it includes:Application service end 610, other application resource
620th, search engine 630, processing system 640, communication interface 650.Application service end 610 is used for realizing that multi-modal robot is directed to
The parsing operation of multi-modal data.Semantic analysis is carried out using natural language model by processing system 640, the meaning of user is obtained
Figure, then accesses database resource 660 by search engine 640 again and finds reply data in corresponding database.
Communication interface 650 provides the ability for being used to that server 203 is directly communicated with mobile device 201 beyond the clouds.
The dialog text that prevailing transmission applications client is sent in communication interface 650 and the response that parsing computing is obtained beyond the clouds
Text data.
In addition, also having other application resource 620 on cloud server (high in the clouds brain) 203, to be carried to mobile device 203
For other feature-rich applications.
Fig. 7 shows the relation schematic diagram for the database for constituting cloud server.As shown in fig. 7, general population's response
Database 2031B is more than personalized reply data storehouse 2031C and is more than interaction particular responses database 2031D.Wherein, general population
Reply data storehouse 2031B reflects that the probability used for word or interaction are asked based on collective's interacting activity of many users
Inscribe classification.In reality, general population's reply data storehouse 2031B uses a large amount of history interacted on interactive object by developer
Training data is built.General population's reply data storehouse 2031B can be directed to as the user crowd of entirety or being total to for colony
It is not customized with use and for particular individual.General population's reply data storehouse 2031B can represent to be directed to interaction problems
Known response whole set.
Personalized reply data storehouse 2031C is obtained based on the actual use of individual.Personalized reply data storehouse 2031C is anti-
User is reflected by the typed word of interaction or the voice of output, and adaptive voice model 2031A learns and followed the trail of above word
Language and voice, the existing words of general population's reply data storehouse 2031B and voice can distribute to personalized reply data
The word and voice that storehouse 2031C is not yet included in general population's reply data storehouse 2031B can be as neologism and languages
Sound is added in personalized reply data storehouse 2031C.Therefore personalized reply data storehouse 2031C can be covered as depicted general
Logical crowd's reply data storehouse 2031B subset.
Interaction particular responses database 2031D represents the word and voice for correspondence interaction scenarios.For example, in interaction
Hold the work for being only limited to interactive object and do not include the other guide beyond work.Adaptive voice model 2031A can match somebody with somebody
Being set to maintenance and management is used for the corresponding special sound model database of multiple interaction scenarios.Interaction particular responses database
2031D can represent the subset of personalized reply data storehouse 2031C as represented in the figure.
Fig. 8 shows that use virtual robot according to an embodiment of the invention engages in the dialogue interactive group method
Flow chart.
According to the present invention, the image of virtual robot can be just fabricated and in default viewing area when application brings into operation
Shown in domain, i.e., user is before only implementing and opening and apply after this operation but do not have started and interact, the present invention
In virtual robot image have been shown in the specific region of mobile device, this process be in order to ensure interaction it is smooth
Carry out.Interactive object in the present invention includes but is not limited to two, interactive object should comprising virtual robot and with it is virtual
Other individuals that robot is interacted.Certainly, virtual robot of the invention image correspondence plug-in unit can also be that user sends
Request requires to show when with it dialogue.This is in social chat application as very universal in QQ, WeChat application.And it is right
In mobile device for built-in chat robots client application, may just it be built when clicking on the client application
Image can be more particularly suitable.
As illustrated, in step S801, being mounted with that the application of virtual robot plug-in unit passes through the input mould of mobile device
Block obtains single mode and/or multi-modal interactive demand signal.That is, when other interaction individuals such as people opens the application on mobile device
When, when sending dialogue interaction request and inputting the content for needing to interact with virtual robot, the multi-modal robot installed will
Dialogue interactive demand signal can be obtained.Other individual input interaction contents modes include phonetic entry, text input and its
The input form that he can interact.
Next, in step S802, the multi-modal interactive robot in mobile device 201 leads to cloud server 203
News, call multi-modal interaction data Processing Interface, complete semantic processes process so that the multi-modal robot completes language
Adopted understandability.
In step S803, interactive demand signal is handled using the multi-modal robot capability of cloud server, is generated
For the multi-modal reply data of interactive demand signal.Reply data can return to the application of mobile device by COM1
Client.
Finally, in step S804, answer number is exported in multi-modal form by the image of constructed virtual robot
According to.Constructed virtual robot can coordinate the change of facial expression, the specific limb action and the specific tone that represent mood,
The voice output reply data of intonation.
Fig. 9 is shown according to the interactive another flow chart of the invention that engages in the dialogue.As illustrated, in step S901, moving
Dynamic equipment sends conversation content to cloud server.Afterwards, mobile device, which is constantly in, waits multi-modal on cloud server
The reply of robot.During wait, the time that mobile device can be spent to returned data carries out Clocked operation.If
The reply data not returned for a long time, such as, exceeded predetermined time span 5S, then mobile device can select to carry out this
Ground is replied, and reply data is locally commonly used in generation.Then the plug-in unit output from virtual robot image is with locally commonly using with response
Animation, and call voice playing equipment carry out speech play.
Figure 10 is shown according to one embodiment of present invention in interaction individual, mobile device and cloud in further detail
The flow chart that end server is communicated between the parties.
As illustrated, before dialogue interaction is proceeded by, the instruction for starting application is sent by interaction individual.Such as pass through
Specific sentence opens certain application installed on mobile device, or opens the application by touch, specific action.This needs
Mobile device has the visual identity ability or tactilely-perceptible ability of hardware, such as is provided with camera and with touch-screen.
When mobile device is by these hardware acceptances to virtual robot plug-in unit after enabled instruction, installed before operation, build empty
Intend the robot animation image.The structure of virtual robot animating image is needed to use graphical modeling algorithm, and the present invention can be used
Any modeling method disclosed in the prior art carries out two dimension or 3-D view modeling.Enter to be about in specified viewing area
Virtual image is shown.The operation of this step is completed in the number designation 1 in figure.
After interaction individual sees virtual animating image, talked with to mobile device by voice, action or text input
Where data, such as the problem of asking " travel”
Mobile device is locally being changed to the dialogue data including voice, action or text, and formation can be for transmission to
The data mode in high in the clouds, is then transmitted.As shown in the number designation 2 in figure.
The dialogue data that high in the clouds brain is just received carries out semantic parsing, and scans for obtaining corresponding reply data, such as
Shown in number designation 3 in figure.Then mobile device is returned to by communication interface.
Mobile device is handled the reply data of return.Relate generally to carry out these data point in different paths
Hair.The reply data part such as returned is sent to voice playing equipment and played out, and another part is shown to by text
On display screen.In addition, these data should be also sent in card module, with the virtual robot image built simultaneously
The output that the broadcasting of voice is acted and expressed one's feelings, as shown in the number designation 4 in figure.Because the operation of output needs several portions
It is point common to complete, therefore coordinate to control the output of these modules to be particularly important, virtual robot image otherwise occurs
Animation is exported to be occurred with the nonsynchronous phenomenon of speech play.
Therefore, in the present invention, a set of targetedly synchronization system is designed, the operation of speech play and animation are shown
Operation is synchronized.When mobile device exports reply data, synchronic command is firstly generated.Plug-in unit and application under synchronic command
Other hardware modules called such as display device, voice playing equipment carry out corresponding operating.
Figure 11 is to be engaged in the dialogue interactive text input side according to the use virtual robot of one embodiment of the present of invention
The schematic diagram of formula.As shown in figure 9, including mobile device 201, virtual robot 601, text input medium 901 and cloud in figure
Hold server 203.Fig. 9 shows, according to one embodiment of present invention, in the method interacted using virtual robot,
Interaction between interactive object can not only carry out carrying out in the way of text in the way of voice.Input medium 901 1
As for be interactive object hand, interactive object inputs interactive content by way of key entry, expansion interaction.Input medium
901 can input text message by soft keyboard.Soft keyboard be not on keyboard, but on viewing area 2011,
Soft keyboard is to click on to input character by input medium 901 by software simulating keyboard.
It should be understood that disclosed embodiment of this invention is not limited to specific structure disclosed herein, process step
Or material, and the equivalent substitute for these features that those of ordinary skill in the related art are understood should be extended to.It should also manage
Solution, 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.
While it is disclosed that embodiment as above, but described content is only to facilitate understanding the present invention and adopting
Embodiment, is not limited to the present invention.Any those skilled in the art to which this invention pertains, are not departing from this
On the premise of the disclosed spirit and scope of invention, any modification and change can be made in the implementing form and in details,
But the scope of patent protection of the present invention, still should be subject to the scope of the claims as defined in the appended claims.
Claims (9)
- A kind of interactive method 1. use virtual robot engages in the dialogue, it is characterised in that the image of the virtual robot exists Using being fabricated and being shown in default viewing area when bringing into operation, it the described method comprises the following steps:Obtain single mode and/or multi-modal interactive demand signal;Call the multi-modal robot capability interface of currently interactionUtilize the multi-modal robot capability, reply data of the generation for the interactive demand signal;The reply data is exported in multi-modal form by the image of constructed virtual robot.
- The interactive method 2. use virtual robot as claimed in claim 1 engages in the dialogue, it is characterised in that the virtual machine The image of device people may be based on the two dimension or three-dimensional animation image of cartoon figure, real person or buckram man.
- The interactive method 3. use virtual robot as claimed in claim 1 engages in the dialogue, it is characterised in that the answer number According to the emotional parameters for including associating with the interactive demand signal.
- The interactive method 4. use virtual robot as claimed in claim 3 engages in the dialogue, it is characterised in that with multi-modal shape Formula, which exports the reply data, to be included:The virtual robot is selected in the following multi-modal way of output according to the emotional parameters One or more exported:The change of the facial expression of virtual robot;Represent the specific limb action of mood;The voice of the specific tone, intonation.
- 5. engaged in the dialogue interactive method using virtual robot as claimed in claim 1, it is characterised in that it is described other Body includes single people, single virtual robot or single tangible machine people.
- The interactive method 6. use virtual robot as claimed in claim 1 engages in the dialogue, it is characterised in that to be received waiting From the application make for the conversation content reply data when, the virtual robot is according to the time waited The length multi-modal conventional response that independently selection is pre-set exports to be interacted temporarily.
- The interactive method 7. use virtual robot as claimed in claim 1 engages in the dialogue, it is characterised in that methods described is also Including, the text message in the reply data is exported on the interactive interface of application, and/or, obtained by voice acquisition device The interactive voice information taken.
- 8. a kind of storage medium, is stored thereon with the program of the executable method and step as any one of claim 1-7 Code.
- 9. a kind of dialogue interactive system of use virtual robot, it is characterised in that the system includes:Mobile device, is provided with application thereon;Multi-modal robot program's bag, it is activated when the application is run, to cause the application to perform such as claim Method and step any one of 1-7;Virtual robot interface, to the action that the image of the virtual robot is exported to user and is made;Multi-modal robot capability interface, it is back to handle the interactive demand signal, and by obtained reply data The mobile device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710362605.9A CN107294837A (en) | 2017-05-22 | 2017-05-22 | Engaged in the dialogue interactive method and system using virtual robot |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710362605.9A CN107294837A (en) | 2017-05-22 | 2017-05-22 | Engaged in the dialogue interactive method and system using virtual robot |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107294837A true CN107294837A (en) | 2017-10-24 |
Family
ID=60095188
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710362605.9A Pending CN107294837A (en) | 2017-05-22 | 2017-05-22 | Engaged in the dialogue interactive method and system using virtual robot |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107294837A (en) |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107784355A (en) * | 2017-10-26 | 2018-03-09 | 北京光年无限科技有限公司 | The multi-modal interaction data processing method of visual human and system |
CN108388399A (en) * | 2018-01-12 | 2018-08-10 | 北京光年无限科技有限公司 | The method of state management and system of virtual idol |
CN108415995A (en) * | 2018-02-13 | 2018-08-17 | 北京百度网讯科技有限公司 | searching method and device |
CN108804698A (en) * | 2018-03-30 | 2018-11-13 | 深圳狗尾草智能科技有限公司 | Man-machine interaction method, system, medium based on personage IP and equipment |
CN109448737A (en) * | 2018-08-30 | 2019-03-08 | 百度在线网络技术(北京)有限公司 | Creation method, device, electronic equipment and the storage medium of virtual image |
CN109692392A (en) * | 2019-01-30 | 2019-04-30 | 华东交通大学 | A kind of musical therapy method and system based on cloud platform |
CN109739605A (en) * | 2018-12-29 | 2019-05-10 | 北京百度网讯科技有限公司 | The method and apparatus for generating information |
CN110152314A (en) * | 2018-02-13 | 2019-08-23 | 卡西欧计算机株式会社 | Session output system, session export server, session output method and storage medium |
CN110223683A (en) * | 2019-05-05 | 2019-09-10 | 安徽省科普产品工程研究中心有限责任公司 | Voice interactive method and system |
CN110286756A (en) * | 2019-06-13 | 2019-09-27 | 深圳追一科技有限公司 | Method for processing video frequency, device, system, terminal device and storage medium |
CN110413841A (en) * | 2019-06-13 | 2019-11-05 | 深圳追一科技有限公司 | Polymorphic exchange method, device, system, electronic equipment and storage medium |
CN110428824A (en) * | 2018-04-28 | 2019-11-08 | 深圳市冠旭电子股份有限公司 | A kind of exchange method of intelligent sound box, device and intelligent sound box |
CN110688911A (en) * | 2019-09-05 | 2020-01-14 | 深圳追一科技有限公司 | Video processing method, device, system, terminal equipment and storage medium |
CN110808038A (en) * | 2019-11-11 | 2020-02-18 | 腾讯科技(深圳)有限公司 | Mandarin assessment method, device, equipment and storage medium |
CN111290682A (en) * | 2018-12-06 | 2020-06-16 | 阿里巴巴集团控股有限公司 | Interaction method and device and computer equipment |
CN112182173A (en) * | 2020-09-23 | 2021-01-05 | 支付宝(杭州)信息技术有限公司 | Human-computer interaction method and device based on virtual life and electronic equipment |
CN112529992A (en) * | 2019-08-30 | 2021-03-19 | 阿里巴巴集团控股有限公司 | Dialogue processing method, device, equipment and storage medium of virtual image |
CN113691686A (en) * | 2021-09-17 | 2021-11-23 | 杭州一知智能科技有限公司 | Intelligent voice outbound system and method based on WeChat |
CN113783771A (en) * | 2021-09-17 | 2021-12-10 | 杭州一知智能科技有限公司 | AI virtual human interaction method and system based on WeChat |
CN113886551A (en) * | 2021-10-18 | 2022-01-04 | 深圳追一科技有限公司 | Digital human rendering method and device, storage medium and electronic equipment |
Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101127737A (en) * | 2007-09-25 | 2008-02-20 | 腾讯科技(深圳)有限公司 | Implementation method of UI, user terminal and instant communication system |
CN101187990A (en) * | 2007-12-14 | 2008-05-28 | 华南理工大学 | A session robotic system |
CN101242373A (en) * | 2007-11-14 | 2008-08-13 | 李强 | 3-dimensin dynamic network chat |
CN101243437A (en) * | 2005-08-18 | 2008-08-13 | 微软公司 | Virtual robot communication format customized by endpoint |
CN103489210A (en) * | 2013-09-06 | 2014-01-01 | 雷路德 | Virtual character proactive contacting system and method thereof |
CN103702100A (en) * | 2013-12-17 | 2014-04-02 | Tcl商用信息科技(惠州)股份有限公司 | 3D (three-dimensional) display method and 3D display system for scenario |
US20140337439A1 (en) * | 2013-05-09 | 2014-11-13 | International Business Machines Corporation | Electronic mail delivery negotiation and rejection |
WO2016042039A1 (en) * | 2014-09-16 | 2016-03-24 | Foundation For Research And Technology - Hellas (Forth) | Gesture recognition apparatuses, methods and systems for human-machine interaction |
CN105511608A (en) * | 2015-11-30 | 2016-04-20 | 北京光年无限科技有限公司 | Intelligent robot based interaction method and device, and intelligent robot |
CN105700481A (en) * | 2016-03-23 | 2016-06-22 | 北京光年无限科技有限公司 | Intelligent robot motion generation method and system |
CN105975622A (en) * | 2016-05-28 | 2016-09-28 | 蔡宏铭 | Multi-role intelligent chatting method and system |
CN106297789A (en) * | 2016-08-19 | 2017-01-04 | 北京光年无限科技有限公司 | The personalized interaction method of intelligent robot and interactive system |
CN106295792A (en) * | 2016-08-05 | 2017-01-04 | 北京光年无限科技有限公司 | Dialogue data interaction processing method based on multi-model output and device |
CN106294726A (en) * | 2016-08-09 | 2017-01-04 | 北京光年无限科技有限公司 | Based on the processing method and processing device that robot role is mutual |
CN106326981A (en) * | 2016-08-31 | 2017-01-11 | 北京光年无限科技有限公司 | Method and device of robot for automatically creating personalized virtual robot |
CN106326980A (en) * | 2016-08-31 | 2017-01-11 | 北京光年无限科技有限公司 | Robot and method for simulating human facial movements by robot |
CN106335058A (en) * | 2016-10-12 | 2017-01-18 | 北京光年无限科技有限公司 | Multi-mode interacting method applied to intelligent robot system and intelligent robots |
CN106580347A (en) * | 2016-11-29 | 2017-04-26 | 武汉智普天创科技有限公司 | Determination method for emotional state |
-
2017
- 2017-05-22 CN CN201710362605.9A patent/CN107294837A/en active Pending
Patent Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101243437A (en) * | 2005-08-18 | 2008-08-13 | 微软公司 | Virtual robot communication format customized by endpoint |
CN101127737A (en) * | 2007-09-25 | 2008-02-20 | 腾讯科技(深圳)有限公司 | Implementation method of UI, user terminal and instant communication system |
CN101242373A (en) * | 2007-11-14 | 2008-08-13 | 李强 | 3-dimensin dynamic network chat |
CN101187990A (en) * | 2007-12-14 | 2008-05-28 | 华南理工大学 | A session robotic system |
US20140337439A1 (en) * | 2013-05-09 | 2014-11-13 | International Business Machines Corporation | Electronic mail delivery negotiation and rejection |
CN103489210A (en) * | 2013-09-06 | 2014-01-01 | 雷路德 | Virtual character proactive contacting system and method thereof |
CN103702100A (en) * | 2013-12-17 | 2014-04-02 | Tcl商用信息科技(惠州)股份有限公司 | 3D (three-dimensional) display method and 3D display system for scenario |
WO2016042039A1 (en) * | 2014-09-16 | 2016-03-24 | Foundation For Research And Technology - Hellas (Forth) | Gesture recognition apparatuses, methods and systems for human-machine interaction |
CN105511608A (en) * | 2015-11-30 | 2016-04-20 | 北京光年无限科技有限公司 | Intelligent robot based interaction method and device, and intelligent robot |
CN105700481A (en) * | 2016-03-23 | 2016-06-22 | 北京光年无限科技有限公司 | Intelligent robot motion generation method and system |
CN105975622A (en) * | 2016-05-28 | 2016-09-28 | 蔡宏铭 | Multi-role intelligent chatting method and system |
CN106295792A (en) * | 2016-08-05 | 2017-01-04 | 北京光年无限科技有限公司 | Dialogue data interaction processing method based on multi-model output and device |
CN106294726A (en) * | 2016-08-09 | 2017-01-04 | 北京光年无限科技有限公司 | Based on the processing method and processing device that robot role is mutual |
CN106297789A (en) * | 2016-08-19 | 2017-01-04 | 北京光年无限科技有限公司 | The personalized interaction method of intelligent robot and interactive system |
CN106326981A (en) * | 2016-08-31 | 2017-01-11 | 北京光年无限科技有限公司 | Method and device of robot for automatically creating personalized virtual robot |
CN106326980A (en) * | 2016-08-31 | 2017-01-11 | 北京光年无限科技有限公司 | Robot and method for simulating human facial movements by robot |
CN106335058A (en) * | 2016-10-12 | 2017-01-18 | 北京光年无限科技有限公司 | Multi-mode interacting method applied to intelligent robot system and intelligent robots |
CN106580347A (en) * | 2016-11-29 | 2017-04-26 | 武汉智普天创科技有限公司 | Determination method for emotional state |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107784355A (en) * | 2017-10-26 | 2018-03-09 | 北京光年无限科技有限公司 | The multi-modal interaction data processing method of visual human and system |
CN108388399A (en) * | 2018-01-12 | 2018-08-10 | 北京光年无限科技有限公司 | The method of state management and system of virtual idol |
CN108388399B (en) * | 2018-01-12 | 2021-04-06 | 北京光年无限科技有限公司 | Virtual idol state management method and system |
CN110152314A (en) * | 2018-02-13 | 2019-08-23 | 卡西欧计算机株式会社 | Session output system, session export server, session output method and storage medium |
CN108415995A (en) * | 2018-02-13 | 2018-08-17 | 北京百度网讯科技有限公司 | searching method and device |
CN108804698A (en) * | 2018-03-30 | 2018-11-13 | 深圳狗尾草智能科技有限公司 | Man-machine interaction method, system, medium based on personage IP and equipment |
CN110428824A (en) * | 2018-04-28 | 2019-11-08 | 深圳市冠旭电子股份有限公司 | A kind of exchange method of intelligent sound box, device and intelligent sound box |
CN109448737A (en) * | 2018-08-30 | 2019-03-08 | 百度在线网络技术(北京)有限公司 | Creation method, device, electronic equipment and the storage medium of virtual image |
CN109448737B (en) * | 2018-08-30 | 2020-09-01 | 百度在线网络技术(北京)有限公司 | Method and device for creating virtual image, electronic equipment and storage medium |
CN111290682A (en) * | 2018-12-06 | 2020-06-16 | 阿里巴巴集团控股有限公司 | Interaction method and device and computer equipment |
CN109739605A (en) * | 2018-12-29 | 2019-05-10 | 北京百度网讯科技有限公司 | The method and apparatus for generating information |
CN109692392A (en) * | 2019-01-30 | 2019-04-30 | 华东交通大学 | A kind of musical therapy method and system based on cloud platform |
CN110223683A (en) * | 2019-05-05 | 2019-09-10 | 安徽省科普产品工程研究中心有限责任公司 | Voice interactive method and system |
CN110286756A (en) * | 2019-06-13 | 2019-09-27 | 深圳追一科技有限公司 | Method for processing video frequency, device, system, terminal device and storage medium |
CN110413841A (en) * | 2019-06-13 | 2019-11-05 | 深圳追一科技有限公司 | Polymorphic exchange method, device, system, electronic equipment and storage medium |
CN112529992B (en) * | 2019-08-30 | 2022-08-19 | 阿里巴巴集团控股有限公司 | Dialogue processing method, device, equipment and storage medium of virtual image |
CN112529992A (en) * | 2019-08-30 | 2021-03-19 | 阿里巴巴集团控股有限公司 | Dialogue processing method, device, equipment and storage medium of virtual image |
CN110688911A (en) * | 2019-09-05 | 2020-01-14 | 深圳追一科技有限公司 | Video processing method, device, system, terminal equipment and storage medium |
CN110688911B (en) * | 2019-09-05 | 2021-04-02 | 深圳追一科技有限公司 | Video processing method, device, system, terminal equipment and storage medium |
CN110808038A (en) * | 2019-11-11 | 2020-02-18 | 腾讯科技(深圳)有限公司 | Mandarin assessment method, device, equipment and storage medium |
CN110808038B (en) * | 2019-11-11 | 2024-05-31 | 腾讯科技(深圳)有限公司 | Mandarin evaluating method, device, equipment and storage medium |
CN112182173A (en) * | 2020-09-23 | 2021-01-05 | 支付宝(杭州)信息技术有限公司 | Human-computer interaction method and device based on virtual life and electronic equipment |
CN113691686A (en) * | 2021-09-17 | 2021-11-23 | 杭州一知智能科技有限公司 | Intelligent voice outbound system and method based on WeChat |
CN113783771A (en) * | 2021-09-17 | 2021-12-10 | 杭州一知智能科技有限公司 | AI virtual human interaction method and system based on WeChat |
CN113886551A (en) * | 2021-10-18 | 2022-01-04 | 深圳追一科技有限公司 | Digital human rendering method and device, storage medium and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107294837A (en) | Engaged in the dialogue interactive method and system using virtual robot | |
US20220284896A1 (en) | Electronic personal interactive device | |
JP7408048B2 (en) | Anime character driving method and related device based on artificial intelligence | |
CN107340859B (en) | Multi-modal interaction method and system of multi-modal virtual robot | |
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 | |
CN110286756A (en) | Method for processing video frequency, device, system, terminal device and storage medium | |
US10096316B2 (en) | Sharing intents to provide virtual assistance in a multi-person dialog | |
CN110288077A (en) | A kind of synthesis based on artificial intelligence is spoken the method and relevant apparatus of expression | |
US10079013B2 (en) | Sharing intents to provide virtual assistance in a multi-person dialog | |
JP6889281B2 (en) | Analyzing electronic conversations for presentations in alternative interfaces | |
CN107632706B (en) | Application data processing method and system of multi-modal virtual human | |
CN110413841A (en) | Polymorphic exchange method, device, system, electronic equipment and storage medium | |
CN107870977A (en) | Chat robots output is formed based on User Status | |
CN107704169B (en) | Virtual human state management method and system | |
WO2019165877A1 (en) | Message pushing method, apparatus and device and storage medium | |
CN110249325A (en) | Input system with traffic model | |
CN109324688A (en) | Exchange method and system based on visual human's behavioral standard | |
CN107784355A (en) | The multi-modal interaction data processing method of visual human and system | |
CN110209778A (en) | A kind of method and relevant apparatus of dialogue generation | |
KR20200115660A (en) | How to apply intelligent | |
CN109343695A (en) | Exchange method and system based on visual human's behavioral standard | |
CN114064943A (en) | Conference management method, conference management device, storage medium and electronic equipment | |
CN113850898A (en) | Scene rendering method and device, storage medium and electronic equipment | |
CN117632109A (en) | Virtual digital assistant construction method, device, electronic equipment and storage medium |
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: 20171024 |