CN106200962A - Exchange method and system towards intelligent robot - Google Patents
Exchange method and system towards intelligent robot Download PDFInfo
- Publication number
- CN106200962A CN106200962A CN201610538777.2A CN201610538777A CN106200962A CN 106200962 A CN106200962 A CN 106200962A CN 201610538777 A CN201610538777 A CN 201610538777A CN 106200962 A CN106200962 A CN 106200962A
- Authority
- CN
- China
- Prior art keywords
- topic
- data
- current
- intelligent robot
- module
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90332—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/015—Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Neurosurgery (AREA)
- Neurology (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Dermatology (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Manipulator (AREA)
Abstract
The invention discloses a kind of exchange method towards intelligent robot and system, method includes: receive multi-modal interaction data；According to multi-modal interaction data, determine the first topic；Obtain context data；Based on context data, determine current second topic in multiple second topics from the first topic；Interact with user based on current second topic.The present invention topic is accurately positioned can help improve dialogue experience, promote multi-modal topic mutual time continuity.Therefore, topic can accurately be navigated to compare current second topic of refinement by the present invention, the interactive information that intelligent robot exports according to this topic is high with the current demand laminating degree of user, while adding intelligent robot interaction capabilities, hence it is evident that improve user's use viscosity to intelligent robot.
Description
Technical field
The present invention relates to intelligent robot technology field, particularly relate to a kind of exchange method towards intelligent robot, also
Relate to a kind of interactive system towards intelligent robot.
Background technology
Along with the development of science and technology, the introducing of information technology, computer technology and artificial intelligence technology, machine
Industrial circle is the most progressively walked out in the research of people, gradually extend to the necks such as medical treatment, health care, family, amusement and service occupation
Territory.People for the requirement of robot also conform to the principle of simplicity the multiple mechanical action of substance be promoted to have the most intelligent, autonomy and with
The intelligent robot that other intelligent bodies are mutual.
During existing human computer conversation, intelligent robot generally carries out base only in accordance with current multi-modal interactive information
The location of this topic, is then based on this basic topic and interacts with user.
But, it is many that above-mentioned intelligent robot and the interactive mode of user can not meet dialogue topic in actual interaction
The demand of sample, thus it is easily caused the inaccuracy of location topic, and then cause the interactive information and use exported according to this topic
Family current demand laminating degree is the highest.Visible, in prior art, intelligent robot can seriously reduce user with the interactive mode of user
Experience, thus affect user's use viscosity to intelligent robot product.
Summary of the invention
The technical problem to be solved is: intelligent robot and the interactive mode of user in prior art, it is impossible to
Meet and actual interaction is talked with the multifarious demand of topic, thus be easily caused the inaccuracy of location topic, and then cause
The interactive information exported according to this topic is the highest with user's current demand laminating degree.In prior art, intelligent robot is with user's
Interactive mode can have a strong impact on user's use viscosity to intelligent robot product.
In order to solve above-mentioned technical problem, the invention provides a kind of exchange method towards intelligent robot and system.
According to an aspect of the invention, it is provided a kind of exchange method towards intelligent robot, comprising:
Receive multi-modal interaction data；
According to described multi-modal interaction data, determine the first topic；
Obtain context data；
According to described context data, multiple second topics from described first topic determine current second topic,
Described second topic is the sub-topic under described first topic；
Interact with user based on described current second topic.
Preferably, the above-mentioned exchange method towards intelligent robot also includes:
Obtain the data memory in memory system；
Based on described context data and described data memory, multiple second topics from described first topic determine
Described current second topic.
Preferably, described data memory includes housebroken topic data.
Preferably, based on described context data and described data memory, multiple second from described first topic
Topic determines current second topic, including:
Based on described context data, multiple second topics from described first topic pick out multiple to be selected second
Topic；
Each second topic to be selected is made to mate with described housebroken topic data respectively successively；
Using the second topic to be selected of mating most with described housebroken topic data as described current second topic.
Preferably, the above-mentioned exchange method towards intelligent robot also includes:
According to described multi-modal interaction data, obtain current emotional value；
Judge that whether described current emotional value is less than the emotion threshold value preset；
Judge described current emotional value less than described emotion threshold value time, stop and user between mutual.
According to another aspect of the present invention, it is provided that a kind of interactive system towards intelligent robot, comprising:
Multi-modal interaction data receiver module, is set to receive multi-modal interaction data；
First topic determines module, is set to, according to described multi-modal interaction data, determine the first topic；
Context data acquisition module, is set to obtain context data；
Current second topic determines module, is set to according to described context data, multiple from described first topic
Second topic determining, current second topic, described second topic are the sub-topic under described first topic；
Interactive module, is set to interact with user based on described current second topic.
Preferably, the above-mentioned interactive system towards intelligent robot also includes data memory acquisition module, and it is set to
Obtain the data memory in memory system；
Described current second topic determines that module is specifically configured to: based on described context data and described data memory,
Multiple second topics from described first topic determine described current second topic.
Preferably, described data memory includes housebroken topic data.
Preferably, described current second topic determines that module includes:
Module of selection, is set to, based on described context data, choose in multiple second topics from described first topic
Select multiple second topic to be selected；
Matching unit, is set to make successively each second topic to be selected to carry out with described housebroken topic data respectively
Join；
Current second topic determines unit, is set to the second words to be selected will mated most with described housebroken topic data
Topic is as described current second topic.
Preferably, the above-mentioned interactive system towards intelligent robot also includes:
Current emotional value determines module, is set to, according to described multi-modal interaction data, obtain current emotional value；
Judge module, is set to judge that whether described current emotional value is less than the emotion threshold value preset；
Stopping modular, is set to when described judge module judges described current emotional value less than described emotion threshold value,
Stop and user between mutual.
Compared with prior art, the one or more embodiments in such scheme can have the advantage that or useful effect
Really:
The application present invention, first determines the first topic according to multi-modal interaction data, and the most based on context data are from the
Multiple second topics of refinement determine under one topic current second topic, and carries out actively handing over user based on the second topic
Mutually.It can be seen that the present invention topic is accurately positioned can help improve dialogue experience, promote multi-modal topic mutual time
Continuity.Therefore, topic can accurately be navigated to compare current second topic of refinement by the present invention, intelligent robot according to
The interactive information of this topic output is high with the current demand laminating degree of user, is adding the same of intelligent robot interaction capabilities
Time, hence it is evident that improve user's use viscosity to intelligent robot.
Other features and advantages of the present invention will illustrate in the following description, and partly become from description
It is clear that or understand by implementing the present invention.The purpose of the present invention and other advantages can be by wanting in description, right
The structure asking specifically noted in book and accompanying drawing realizes and obtains.
Accompanying drawing explanation
Accompanying drawing is for providing a further understanding of the present invention, and constitutes a part for description, with the reality of the present invention
Execute example to be provided commonly for explaining the present invention, be not intended that limitation of the present invention.In the accompanying drawings:
Fig. 1 shows the embodiment of the present invention the first schematic flow sheet towards the exchange method of intelligent robot；
Fig. 2 shows embodiment of the present invention the second schematic flow sheet towards the exchange method of intelligent robot；
Fig. 3 shows in the embodiment of the present invention and determines from multiple second topics based on context data and data memory
The schematic flow sheet of the method for current second topic；
Fig. 4 shows the embodiment of the present invention the third schematic flow sheet towards the exchange method of intelligent robot；
Fig. 5 shows the embodiment of the present invention the first structural representation towards the interactive system of intelligent robot；
Fig. 6 shows embodiment of the present invention the second structural representation towards the interactive system of intelligent robot；
Fig. 7 shows that in the embodiment of the present invention, current second topic determines the structural representation of module；And
Fig. 8 shows the embodiment of the present invention the third structural representation towards the interactive system of intelligent robot.
Detailed description of the invention
Describe embodiments of the present invention in detail below with reference to drawings and Examples, whereby how the present invention is applied
Technological means solves technical problem, and the process that realizes reaching technique effect can fully understand and implement according to this.Need explanation
As long as not constituting conflict, each embodiment in the present invention and each feature in each embodiment can be combined with each other,
The technical scheme formed is all within protection scope of the present invention.
During existing human computer conversation, current way retrains conversation content typically by contextual information,
Or carrying out feedback result according to the stimulation of single mode, there is not topic in conversation content, and structure more dissipates rather than restrains.
It can be seen that the interactive mode of intelligent robot and user in prior art, it is impossible to meet in actual interaction
The dialogue multifarious demand of topic, thus it is easily caused the inaccuracy of location topic, and then cause the friendship exported according to this topic
Mutual information is the highest with user's current demand laminating degree.In prior art, intelligent robot can have a strong impact on the interactive mode of user
User's use viscosity to intelligent robot product.
In order to solve above-mentioned technical problem, embodiments provide a kind of information processing system towards intelligent robot
System.
Embodiment one
Fig. 1 shows the embodiment of the present invention the first schematic flow sheet towards the exchange method of intelligent robot.Such as Fig. 1
Shown in, the present embodiment, towards the exchange method of intelligent robot, mainly includes that step 101 is to step 105.
In a step 101, multi-modal interaction data is received.
Specifically, the multi-modal interaction data that system first receiving front-end module transmits.In the present embodiment, multi-modal number
According to mainly including voice messaging, visual information and tactile data etc., do not limit to, may also include environmental information etc..
Such as, for visual information, first system can detect image or video information, then to the image detected,
Video information carries out image recognition processing, obtains the meaning of image expression and the event of triggering.
For voice messaging, first system can obtain the voice of user's input, then the voice got is carried out language
Sound identification, obtains the text corresponding with this voice.
For tactile data, first system can detect user and act on the touching intensity information of intelligent robot, then
Dynamics size and stress point is extracted from touching intensity information.
It should be noted that the technological means that those skilled in the art can be used usually to use realizes for above-mentioned vision
The detection of information, voice messaging and touch information and process, therefore the most do not carry out these technological means launching explanation.
In a step 102, according to multi-modal interaction data, determine the first topic.
In step 103, context data is obtained.Before and after context (context) data are primarily referred to as language environment
State.
At step 104, based on context data, multiple second topics from the first topic determine current second words
Topic.
In step 105, interact with user based on current second topic.
Specifically, intelligent robot first according to acquired multi-modal interaction data carry out relative broad range, wide in range
One topic (the biggest topic) positions, and includes the second topic (the least words of multiple narrower range, refinement under the first topic
Topic), the second topic is the sub-topic under the first topic.Then, intelligent robot (is typically deposited further according to the context data obtained
Storage is inside intelligent robot) from multiple second topics, determine second topic mated most with current session process,
The most current second topic.Finally, after determining current second topic, intelligent robot carry out in thinking mutual or actively
Alternately.I.e. intelligent robot based on determined by current second topic multi-modal output data are exported, to enter with user
Row is mutual or the most mutual.
For example, intelligent robot is said " I am very glad " by user with dancing for joy, and intelligent robot is according to acquisition
Multi-modal interaction data (visual information " is danced for joy ", voice messaging " today ... very glad ") determines that the first topic is " glad
Thing ".Here, the first topic " happy event " can include National Day, birthday, good result, love etc..Then, intelligence
Robot can obtain context data, the second topic under based on context data determine the first topic, such as, and robot
In the context data obtained, storing one section of dialogue is that robot is asked " today, what you felt like doing ", and user says that " today is
October 1, is my birthday！I prepares to participate in the birthday party that kith and kin prepare meticulously！”.Intelligent robot is according to above-mentioned
Context data (herein referring to interactive voice data) understands, and user is because having celebrated a birthday and glad, i.e. intelligent robot from
Selecting " birthday " in numerous second topics is current second topic.Then, intelligent robot is based on current second topic " birthday "
That carries out between user is mutual.Such as, intelligent robot can go forward to embrace user, say " dear, wish that you are raw. simultaneously
Day is happy, has today every year, has today all the time！", it is also possible to continuing inquiry, such as " you guess and whom have today to participate in your life
Day party ", " your father and mother can or can not come back from the U.S. ", " your new boyfriend can or can not participate in ", " you prepare to send in the birthday
What permitted be willing to upper " etc. around the problem of this topic.
The application embodiment of the present invention is towards the information processing method of intelligent robot, first true according to multi-modal interaction data
Fixed first topic, determines current second words in multiple second topics that the most based on context data refine from the first topic
Topic, and carry out the most mutual based on the second topic with user.Dialogue can be helped improve it can be seen that topic is accurately positioned
Experience, promote multi-modal topic mutual time continuity.Therefore, topic can accurately be navigated to compare refinement by the present embodiment
Current second topic, the current demand laminating degree height of the interactive information that intelligent robot exports according to this topic and user,
While adding intelligent robot interaction capabilities, hence it is evident that improve user's use viscosity to intelligent robot.
Embodiment two
Present embodiments provide the another kind of information processing method towards intelligent robot.
Fig. 2 shows embodiment of the present invention the second schematic flow sheet towards the exchange method of intelligent robot.Such as Fig. 2
Shown in, the present embodiment towards the exchange method of intelligent robot, mainly include above-mentioned steps 101,102,103 and 105 and under
State step 201 and the step 202 of specific descriptions.
In step 201, the data memory in memory system is obtained.Data memory is such as to time, space, event, feelings
The record of thread etc..
In step 202., based on context data and data memory, multiple second topics from the first topic determine
Current second topic.
The present embodiment, on the basis of embodiment one, has obtained the data support of memory system.Here, memory system is main
For assisting the location of topic, navigate to remember in topic by topic by extraction time, space, event information etc..This enforcement
Example mainly utilizes the data memory obtained from memory system, in conjunction with context data, determines current second topic.
The present embodiment utilizes context data and combines data memory to determine current second topic, improves selected working as
The accuracy of front second topic, makes man-machine interaction more class peopleization, is conducive to improving further the interaction capabilities of intelligent robot
And increase the use viscosity of user.
Embodiment three
The present embodiment is on the basis of embodiment two and embodiment three, to data memory and based on data memory and up and down
Literary composition data determine that the method for current second topic is optimized.
In the present embodiment, data memory includes housebroken topic data.Housebroken topic data such as includes state
Celebrating topic, birthday topic, good result topic, love topic, raw baby's topic, bonus topic, spring outing topic etc..Housebroken
Topic data refers to for a certain topic, trains data closely-related with this topic.Utilize housebroken topic number
According to, in interactive process, intelligent robot can judge which topic is current session content belong to rapidly.
Fig. 3 shows in the embodiment of the present invention and determines from multiple second topics based on context data and data memory
The schematic flow sheet of the method for current second topic.As it is shown on figure 3, the embodiment of the present invention is based on context data and memory number
According to, the method determining current second topic in multiple second topics from the first topic, mainly include that step 301 is to step
303。
In step 301, based on context data, multiple second topics from the first topic are picked out multiple to be selected
Second topic.
In step 302, each second topic to be selected is made to mate with housebroken topic data respectively successively.
In step 303, using the second topic to be selected of mating most with housebroken topic data as current second topic.
Specifically, it is primarily based on context data, multiple second topics from the first topic is picked out multiple to be selected
Second topic.The most successively for each second topic to be selected, this second topic to be selected is made to carry out with housebroken topic data
Coupling.Comform select during the second topic to be selected selects the topic that mates most with housebroken topic data as this current the
Two topics.
During specific embodiment, can mark for the matching result of each second topic to be selected, then root
Current second topic is determined according to score.In general, the score of the second topic to be selected mated most with housebroken topic data
The highest, this second topic to be selected is chosen as current second topic.
Continuing the above-mentioned example celebrated a birthday, memory system record has a following housebroken topic data: National Day topic, the birthday
Topic, good result topic, love topic, raw baby's topic, bonus topic, spring outing topic etc..Based on above-mentioned data memory and upper
Context data, intelligent robot determines that current second topic is " birthday topic ", and launches with user based on this " birthday topic "
Dialogue is mutual.
In the present embodiment, intelligent robot utilizes context data and housebroken topic data to determine current second words
Topic, improves the accuracy of selected current second topic, improves the class human nature of intelligent robot, is conducive to improving intelligence further
The interaction capabilities of energy robot and the use viscosity of increase user.
Embodiment four
Present embodiments provide another information processing method towards intelligent robot.
Fig. 4 shows the embodiment of the present invention the third schematic flow sheet towards the exchange method of intelligent robot.Such as Fig. 4
Shown in, the present embodiment towards the exchange method of intelligent robot on the basis of above-mentioned any embodiment, add step 401 to
Step 403.
In step 401, according to multi-modal interaction data, obtain current emotional value.
In step 402, it is judged that whether current emotional value is less than the emotion threshold value preset.
In step 403, judge current emotional value less than emotion threshold value time, stop and user between mutual.
Specifically, after step 105, i.e. start to interact with user based on current second topic at intelligent robot
Afterwards, monitor the emotion value of user at any time, when the emotion value of the emotion of user is less than the emotion threshold value preset, stop and user
Interact.
It is to say, during man-machine interaction, in addition it is also necessary to combine after emotion result of calculation determines whether to trigger
Continuous interbehavior.If the emotion of user is in abnormality, then be deemed unsuitable for initiating topic and guide, skip at this time
Reason result.Then, wait that pretreatment stage looks for chance to trigger actively interbehavior after eligible again.
The present embodiment utilizes the current emotional result of calculation for user to carry out auxiliary judgment if appropriate for carrying out currently
Topic guides, and stops current topic in time when user emotion exception mutual, to avoid causing the dislike of user.Visible, this reality
Execute example and be conducive to improving interaction capabilities and the experience of user of intelligent robot.
Embodiment five
Corresponding to above-described embodiment one to embodiment four, embodiments provide a kind of letter towards intelligent robot
Breath processing system.
Fig. 5 shows the embodiment of the present invention the first structural representation towards the interactive system of intelligent robot.Such as Fig. 5
Shown in, the present embodiment mainly includes the multi-modal interaction data receiver module being sequentially connected with towards the interactive system of intelligent robot
501, the first topic determines that module 502, current second topic determine module 503 and interactive module 504, and talks about with current second
Topic determines the context data acquisition module 505 that module 503 connects.
Specifically, multi-modal interaction data receiver module 501, it is set to receive multi-modal interaction data.
First topic determines module 502, is set to, according to multi-modal interaction data, determine the first topic.
Context data acquisition module 505, is set to obtain context data.
Current second topic determines module 503, is set to based on context data, multiple second words from the first topic
Determining current second topic in topic, the second topic is the sub-topic under the first topic.
Interactive module 504, is set to interact with user based on current second topic.
The application embodiment of the present invention is towards the information processing system of intelligent robot, first true according to multi-modal interaction data
Fixed first topic, determines current second words in multiple second topics that the most based on context data refine from the first topic
Topic, and carry out the most mutual based on the second topic with user.Dialogue can be helped improve it can be seen that topic is accurately positioned
Experience, promote multi-modal topic mutual time continuity.Therefore, topic can accurately be navigated to compare refinement by the present embodiment
Current second topic, the current demand laminating degree height of the interactive information that intelligent robot exports according to this topic and user,
While adding intelligent robot interaction capabilities, hence it is evident that improve user's use viscosity to intelligent robot.
Embodiment six
Embodiments provide the another kind of information processing system towards intelligent robot.
With reference to Fig. 6, the present embodiment connects towards the information processing system of intelligent robot except above-mentioned multi-modal interaction data
Receive module the 501, first topic and determine that module 502, current second topic determine module 503, interactive module 504 and context data
Outside acquisition module 505, also include determining, with current second topic, the data memory acquisition module 601 that module 503 is connected.Should
Data memory acquisition module 601 is set to obtain the data memory in memory system.
It addition, in the present embodiment, current second topic determines that module 503 is specifically configured to: obtain based on context data
The data memory that the context data of delivery block 505 acquisition and data memory acquisition module 601 obtain is many from the first topic
Individual second topic determines current second topic.
The present embodiment utilizes context data and combines data memory to determine current second topic, improves selected working as
The accuracy of front second topic, improves the class human nature of intelligent robot, is conducive to improving further the mutual energy of intelligent robot
Power and the use viscosity of increase user.
Embodiment seven
The present embodiment is on the basis of embodiment five and embodiment six, and content and current second topic to data memory are true
The structure of cover half block 503 is further optimized.
In the present embodiment, data memory includes housebroken topic data.
Fig. 7 shows that in the embodiment of the present invention, current second topic determines the structural representation of module 503.As it is shown in fig. 7,
Current second topic of the present embodiment determines module of selection 701, matching unit 702 that module 503 mainly includes being sequentially connected with and works as
Front second topic determines unit 703.
Specifically, module of selection 701, it is set to based on context data, in multiple second topics from the first topic
Pick out multiple second topic to be selected.
Matching unit 702, is set to make successively each second topic to be selected to carry out with housebroken topic data respectively
Join.
Current second topic determines unit 703, is set to the second words to be selected will mated most with housebroken topic data
Topic is as current second topic.
In the present embodiment, intelligent robot utilizes context data and housebroken topic data to determine current second words
Topic, improves the accuracy of selected current second topic, makes man-machine interaction more class people, is conducive to improving intelligent machine further
The interaction capabilities of device people and the use viscosity of increase user.
Embodiment eight
Present embodiments provide another information processing method towards intelligent robot.
Fig. 8 shows the embodiment of the present invention the third structural representation towards the interactive system of intelligent robot.Such as Fig. 8
Shown in, the present embodiment is towards interactive system base of any embodiment in above-described embodiment five to embodiment seven of intelligent robot
On plinth, also include that the current emotional value being sequentially connected with determines module 801, judge module 802 and stopping modular 803.
Specifically, current emotional value determines module 801, is set to, according to multi-modal interaction data, obtain current emotional value.
Judge module 802, is set to judge that whether current emotional value is less than the emotion threshold value preset.
Stopping modular 803, be set to judge module 802 judge current emotional value less than emotion threshold value time, stop with
Mutual between user.
The present embodiment utilizes the current emotional result of calculation for user to carry out auxiliary judgment if appropriate for carrying out currently
Topic guides, and stops current topic in time when user emotion exception mutual, to avoid causing the dislike of user.Visible, this reality
Execute example and be conducive to improving interaction capabilities and the experience of user of intelligent robot.
The concrete refinement of the operation it should be noted that in embodiment five to embodiment eight in modules and unit, can
See above in conjunction with the Fig. 1 to Fig. 4 explanation to the inventive method (referring specifically to embodiment one to embodiment four), the most detailed at this
Carefully repeat.
Those skilled in the art should be understood that each module of the above-mentioned present invention or each step can be with general calculating
Device realizes, and they can concentrate on single calculating device, or is distributed in the network that multiple calculating device is formed
On, alternatively, they can realize with calculating the executable program code of device, it is thus possible to be stored in storage
Device is performed by calculating device, or they are fabricated to respectively each integrated circuit modules, or by many in them
Individual module or step are fabricated to single integrated circuit module and realize.So, the present invention be not restricted to any specific hardware and
Software combines.
While it is disclosed that embodiment as above, but described content is only to facilitate understand the present invention and adopt
Embodiment, be not limited to the present invention.Technical staff in any the technical field of the invention, without departing from this
On the premise of spirit and scope disclosed in invention, in form and any amendment and change can be made in details implement,
But protection scope of the present invention, still must be defined in the range of standard with appending claims.
Claims (10)
1. the exchange method towards intelligent robot, it is characterised in that including:
Receive multi-modal interaction data；
According to described multi-modal interaction data, determine the first topic；
Obtain context data；
According to described context data, multiple second topics from described first topic determine current second topic, described
Second topic is the sub-topic under described first topic；
Interact with user based on described current second topic.
Method the most according to claim 1, it is characterised in that also include:
Obtain the data memory in memory system；
Based on described context data and described data memory, multiple second topics from described first topic determine described
Current second topic.
Method the most according to claim 2, it is characterised in that described data memory includes housebroken topic data.
Method the most according to claim 3, it is characterised in that based on described context data and described data memory, from
Multiple second topics under described first topic determine current second topic, including:
Based on described context data, multiple second topics from described first topic are picked out multiple second words to be selected
Topic；
Each second topic to be selected is made to mate with described housebroken topic data respectively successively；
Using the second topic to be selected of mating most with described housebroken topic data as described current second topic.
Method the most according to any one of claim 1 to 4, it is characterised in that also include:
According to described multi-modal interaction data, obtain current emotional value；
Judge that whether described current emotional value is less than the emotion threshold value preset；
Judge described current emotional value less than described emotion threshold value time, stop and user between mutual.
6. the interactive system towards intelligent robot, it is characterised in that including:
Multi-modal interaction data receiver module, is set to receive multi-modal interaction data；
First topic determines module, is set to, according to described multi-modal interaction data, determine the first topic；
Context data acquisition module, is set to obtain context data；
Current second topic determines module, is set to according to described context data, multiple second from described first topic
Topic determining, current second topic, described second topic are the sub-topic under described first topic；
Interactive module, is set to interact with user based on described current second topic.
System the most according to claim 6, it is characterised in that also include data memory acquisition module, it is set to obtain
Data memory in memory system；
Described current second topic determines that module is specifically configured to: based on described context data and described data memory, from institute
State and multiple second topics under the first topic determine described current second topic.
System the most according to claim 7, it is characterised in that described data memory includes housebroken topic data.
System the most according to claim 8, it is characterised in that described current second topic determines that module includes:
Module of selection, is set to, based on described context data, pick out in multiple second topics from described first topic
Multiple second topics to be selected；
Matching unit, is set to make each second topic to be selected mate with described housebroken topic data respectively successively；
Current second topic determines unit, is set to make the second topic to be selected mated most with described housebroken topic data
For described current second topic.
10. according to the system according to any one of claim 6 to 9, it is characterised in that also include:
Current emotional value determines module, is set to, according to described multi-modal interaction data, obtain current emotional value；
Judge module, is set to judge that whether described current emotional value is less than the emotion threshold value preset；
Stopping modular, is set to, when described judge module judges described current emotional value less than described emotion threshold value, stop
And mutual between user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610538777.2A CN106200962A (en) | 2016-07-08 | 2016-07-08 | Exchange method and system towards intelligent robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610538777.2A CN106200962A (en) | 2016-07-08 | 2016-07-08 | Exchange method and system towards intelligent robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106200962A true CN106200962A (en) | 2016-12-07 |
Family
ID=57472934
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610538777.2A Pending CN106200962A (en) | 2016-07-08 | 2016-07-08 | Exchange method and system towards intelligent robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106200962A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106843461A (en) * | 2016-12-13 | 2017-06-13 | 北京光年无限科技有限公司 | A kind of interactive output intent and robot for robot |
| CN106873773A (en) * | 2017-01-09 | 2017-06-20 | 北京奇虎科技有限公司 | Robot interactive control method, server and robot |
| CN107704612A (en) * | 2017-10-23 | 2018-02-16 | 北京光年无限科技有限公司 | Dialogue exchange method and system for intelligent robot |
| CN107870994A (en) * | 2017-10-31 | 2018-04-03 | 北京光年无限科技有限公司 | Man-machine interaction method and system for intelligent robot |
| CN109726277A (en) * | 2018-12-30 | 2019-05-07 | 联想(北京)有限公司 | A kind of data processing method and device |
| CN112015881A (en) * | 2020-10-23 | 2020-12-01 | 和美（深圳）信息技术股份有限公司 | Automatic switching method and system for man-machine conversation process of intelligent robot |
| CN113656562A (en) * | 2020-11-27 | 2021-11-16 | 话媒(广州)科技有限公司 | Multi-round man-machine psychological interaction method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140372931A1 (en) * | 2013-04-16 | 2014-12-18 | Google Inc. | Text suggestion output using past interaction data |
| CN104836720A (en) * | 2014-02-12 | 2015-08-12 | 北京三星通信技术研究有限公司 | Method for performing information recommendation in interactive communication, and device |
| CN105094315A (en) * | 2015-06-25 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Method and apparatus for smart man-machine chat based on artificial intelligence |
| CN105701211A (en) * | 2016-01-13 | 2016-06-22 | 北京光年无限科技有限公司 | Question-answering system-oriented active interaction data processing method and system |
| CN105740948A (en) * | 2016-02-04 | 2016-07-06 | 北京光年无限科技有限公司 | Intelligent robot-oriented interaction method and device |
-
2016
- 2016-07-08 CN CN201610538777.2A patent/CN106200962A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140372931A1 (en) * | 2013-04-16 | 2014-12-18 | Google Inc. | Text suggestion output using past interaction data |
| CN104836720A (en) * | 2014-02-12 | 2015-08-12 | 北京三星通信技术研究有限公司 | Method for performing information recommendation in interactive communication, and device |
| CN105094315A (en) * | 2015-06-25 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Method and apparatus for smart man-machine chat based on artificial intelligence |
| CN105701211A (en) * | 2016-01-13 | 2016-06-22 | 北京光年无限科技有限公司 | Question-answering system-oriented active interaction data processing method and system |
| CN105740948A (en) * | 2016-02-04 | 2016-07-06 | 北京光年无限科技有限公司 | Intelligent robot-oriented interaction method and device |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106843461A (en) * | 2016-12-13 | 2017-06-13 | 北京光年无限科技有限公司 | A kind of interactive output intent and robot for robot |
| CN106873773A (en) * | 2017-01-09 | 2017-06-20 | 北京奇虎科技有限公司 | Robot interactive control method, server and robot |
| CN107704612A (en) * | 2017-10-23 | 2018-02-16 | 北京光年无限科技有限公司 | Dialogue exchange method and system for intelligent robot |
| CN107870994A (en) * | 2017-10-31 | 2018-04-03 | 北京光年无限科技有限公司 | Man-machine interaction method and system for intelligent robot |
| CN109726277A (en) * | 2018-12-30 | 2019-05-07 | 联想(北京)有限公司 | A kind of data processing method and device |
| CN112015881A (en) * | 2020-10-23 | 2020-12-01 | 和美（深圳）信息技术股份有限公司 | Automatic switching method and system for man-machine conversation process of intelligent robot |
| CN113656562A (en) * | 2020-11-27 | 2021-11-16 | 话媒(广州)科技有限公司 | Multi-round man-machine psychological interaction method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106200962A (en) | Exchange method and system towards intelligent robot | |
| US8954431B2 (en) | Smart collaborative brainstorming tool | |
| CN110364148A (en) | Natural assistant's interaction | |
| CN106096717A (en) | Information processing method and system towards intelligent robot | |
| CN107491284A (en) | The digital assistants of automation state report are provided | |
| CN106020488A (en) | Man-machine interaction method and device for conversation system | |
| CN107665708A (en) | Intelligent sound exchange method and system | |
| CN102428440A (en) | System and method for synchronization and disambiguation of multimodal inputs | |
| CN106205612A (en) | Information processing method and system towards intelligent robot | |
| CN110598576A (en) | Sign language interaction method and device and computer medium | |
| CN105867633A (en) | Intelligent robot oriented information processing method and system | |
| CN105912530A (en) | Intelligent robot-oriented information processing method and system | |
| CN105945949A (en) | Information processing method and system for intelligent robot | |
| CN106502382A (en) | Active exchange method and system for intelligent robot | |
| CN103591947B (en) | The voice background navigation method of mobile terminal and mobile terminal | |
| CN106730234A (en) | A kind of intelligent mood persuasion system | |
| CN102945120A (en) | Children application based man-machine interaction auxiliary system and interaction method | |
| Vu et al. | Emotion recognition based on human gesture and speech information using RT middleware | |
| CN110310657A (en) | A kind of audio data processing method and device | |
| CN107786430A (en) | Robot chat method and system | |
| JP2010009512A (en) | Conversation display method and server device | |
| Chernova et al. | Crowdsourcing hri through online multiplayer games. | |
| Narayana et al. | Cooperating with avatars through gesture, language and action | |
| Rothwell et al. | Comparison of common ground models for human--computer dialogue: Evidence for audience design | |
| CN106202417A (en) | A kind of man-machine interaction method for intelligent robot and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into 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: 20161207 |