CN109358751A - A kind of wake-up control method of robot, device and equipment - Google Patents
A kind of wake-up control method of robot, device and equipment Download PDFInfo
- Publication number
- CN109358751A CN109358751A CN201811238629.4A CN201811238629A CN109358751A CN 109358751 A CN109358751 A CN 109358751A CN 201811238629 A CN201811238629 A CN 201811238629A CN 109358751 A CN109358751 A CN 109358751A
- Authority
- CN
- China
- Prior art keywords
- word
- wake
- robot
- response policy
- preconfigured
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 230000004044 response Effects 0.000 claims abstract description 189
- 230000000007 visual effect Effects 0.000 claims description 44
- 230000033001 locomotion Effects 0.000 claims description 29
- 230000002618 waking effect Effects 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 15
- 230000003068 static effect Effects 0.000 claims description 12
- 238000010586 diagram Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 241000209140 Triticum Species 0.000 description 1
- 235000021307 Triticum Nutrition 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000009429 distress Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
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
- 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
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Manipulator (AREA)
- Toys (AREA)
Abstract
The embodiment of the invention discloses a kind of wake-up control method of robot, device and equipment to execute different response policies, the response policy of robot be enriched, to meet the needs of more application scenarios to the state difference current according to wake-up word and robot.The wake-up control method of the robot, comprising: obtain the voice data of user;When including preset wake-up word in determining the voice data, based on preconfigured wake-up word response policy, according to the wake-up word for including in the voice data, determine corresponding target response strategy, preconfigured wake up includes the corresponding relationship waken up between word and response policy in word response policy;It controls the robot and executes the target response strategy.
Description
Technical field
The present invention relates to artificial intelligence fields, more particularly, to the wake-up control method, device and equipment of a kind of robot.
Background technique
With the continuous development of artificial intelligence, the robot industry for relying on artificial intelligence has also obtained biggish development,
Consequent, service robot are also formally landed and are come into operation in different field.
Service robot is configured with voice interactive function mostly, can be used by a user specific wake-up word and wake up, and with
User interacts.When using robot for the first time in view of many users, in this case it is not apparent that the wake-up word of robot gets used to " you
Well ", " " etc. exchanges with robot, and the phrases such as " hello ", " " can generally be added in the wake-up word of robot as wake-up word.
When using more wake-up words, the response policies executed after being waken up by different wake-up words are being identical for existing robot
's.For example, robot, for the wake-up word of " the small small X of X " and the wake-up word of " hello ", response policy is to reply " to ask pheno
It tells ".Inventor has found in the implementation of the present invention, existing using the robots for waking up word more, by different wake-up words
Identical response policy is executed after wake-up, the response policy of robot is more single under such mode, is unable to satisfy more applied fields
The demand of scape.
Summary of the invention
The embodiment of the present invention provides the wake-up control method, device and equipment of a kind of robot, to according to wake up word and
The current state of robot is different, executes different response policies, the response policy of robot is enriched, to meet more application scenarios
Demand.
In a first aspect, the embodiment of the present invention provides a kind of wake-up control method of robot, comprising:
Obtain the voice data of user;
When including preset wake-up word in determining voice data, it is based on preconfigured wake-up word response policy, according to
The wake-up word for including in voice data determines corresponding target response strategy, includes in preconfigured wake-up word response policy
Wake up the corresponding relationship between word and response policy;
Control robot performance objective response policy.
In a kind of possible embodiment, in the above method provided in an embodiment of the present invention, corresponding target is being determined
Before response policy, further includes:
Obtain the current state of robot;
Corresponding mesh is determined according to the wake-up word for including in voice data based on preconfigured wake-up word response policy
Response policy is marked, preconfigured wake up includes the corresponding relationship waken up between word and response policy in word response policy, comprising:
It is current according to the wake-up word and robot that include in voice data based on preconfigured wake-up word response policy
State, determine corresponding target response strategy, preconfigured wake up includes the shape for waking up word, robot in word response policy
Corresponding relationship between state and response policy.
In a kind of possible embodiment, in the above method provided in an embodiment of the present invention, corresponding target is being determined
Before response policy, further includes:
Obtain the current visual identity result of robot;
Corresponding mesh is determined according to the wake-up word for including in voice data based on preconfigured wake-up word response policy
Response policy is marked, preconfigured wake up includes the corresponding relationship waken up between word and response policy in word response policy, comprising:
It is current according to the wake-up word and robot that include in voice data based on preconfigured wake-up word response policy
Visual identity as a result, determine corresponding target response strategy, include wake-up word, machine in preconfigured wake-ups word response policy
Corresponding relationship between the visual identity result and response policy of device people.
In a kind of possible embodiment, in the above method provided in an embodiment of the present invention, visual identity result includes
Visual identity result to user and at least one of the visual identity result to environment.
In a kind of possible embodiment, in the above method provided in an embodiment of the present invention, preconfigured wake-up word
Response policy, comprising:
Wake up word be the first kind to wake up the state of word and robot be movement when, response policy is stop motion, is played
First speech message, and rotate so that robot screen user oriented;
Wake up word be the second class to wake up the state of word and robot be movement when, response policy is stop motion, is played
Second speech message, and when determining the voice data for not getting user in preset duration again, restore movement.
In a kind of possible embodiment, in the above method provided in an embodiment of the present invention, preconfigured wake-up word
Response policy, comprising:
Wake up word be the first kind to wake up the state of word and robot be static when, response policy is to play third voice
Message, and rotate so that robot screen user oriented;
Wake up word be the second class to wake up the state of word and robot be static when, response policy is rotation so that machine
People's screen user oriented.
In a kind of possible embodiment, in the above method provided in an embodiment of the present invention, preconfigured wake-up word
Response policy, comprising:
It is first kind wake-up word and preconfigured people is determined according to the current visual identity result of robot wakes up word
In face database when the human face data of not stored user, response policy is to play the 4th speech message, and mark the user as first
Class user;
It is the second class wake-up word and preconfigured people is determined according to the current visual identity result of robot wakes up word
In face database when the human face data of not stored user, response policy is to play the 5th preset speech message, and mark user
For the second class user.
In a kind of possible embodiment, in the above method provided in an embodiment of the present invention, preconfigured wake-up word
Response policy, comprising:
When waking up word is that third class wakes up word, response policy is triggering warning message, and/or the urgent electricity that calling is reserved
Words.
Second aspect, the embodiment of the present invention provide a kind of wake-up control device of robot, comprising:
Acquiring unit, for obtaining the voice data of user;
Processing unit is based on preconfigured wake-up word when for including preset wake-up word in determining voice data
Response policy determines that corresponding target response strategy, preconfigured wake-up word are rung according to the wake-up word for including in voice data
Answering includes the corresponding relationship waken up between word and response policy in strategy;
Control unit, for controlling robot performance objective response policy.
In a kind of possible embodiment, in above-mentioned apparatus provided in an embodiment of the present invention, acquiring unit is also used to: being obtained
Take the state that robot is current;
Processing unit is specifically used for: being based on preconfigured wake-up word response policy, is called out according to include in voice data
It wakes up the current state of word and robot, determines corresponding target response strategy, wrapped in preconfigured wake-up word response policy
Include the corresponding relationship between the state and response policy that wake up word, robot.
In a kind of possible embodiment, in above-mentioned apparatus provided in an embodiment of the present invention, acquiring unit is also used to: being obtained
Take the visual identity result that robot is current;
Processing unit is specifically used for: being based on preconfigured wake-up word response policy, is called out according to include in voice data
The current visual identity of word and robot wake up as a result, determining corresponding target response strategy, preconfigured wake-ups word responds
It include the corresponding relationship waken up between word, robotic vision recognition result and response policy in strategy.
In a kind of possible embodiment, in above-mentioned apparatus provided in an embodiment of the present invention, visual identity result includes
Visual identity result to user and at least one of the visual identity result to environment.
In a kind of possible embodiment, in above-mentioned apparatus provided in an embodiment of the present invention, preconfigured wake-up word
Response policy, comprising:
Wake up word be the first kind to wake up the state of word and robot be movement when, response policy is stop motion, is played
First speech message, and rotate so that robot screen user oriented;
Wake up word be the second class to wake up the state of word and robot be movement when, response policy is stop motion, is played
Second speech message, and when determining the voice data for not getting user in preset duration again, restore movement.
In a kind of possible embodiment, in above-mentioned apparatus provided in an embodiment of the present invention, preconfigured wake-up word
Response policy, comprising:
Wake up word be the first kind to wake up the state of word and robot be static when, response policy is to play third voice
Message, and rotate so that robot screen user oriented;
Wake up word be the second class to wake up the state of word and robot be static when, response policy is rotation so that machine
People's screen user oriented.
In a kind of possible embodiment, in above-mentioned apparatus provided in an embodiment of the present invention, preconfigured wake-up word
Response policy, comprising:
It is first kind wake-up word and preconfigured people is determined according to the current visual identity result of robot wakes up word
In face database when the human face data of not stored user, response policy is to play the 4th speech message, and mark the user as first
Class user;
It is the second class wake-up word and preconfigured people is determined according to the current visual identity result of robot wakes up word
In face database when the human face data of not stored user, response policy is to play the 5th preset speech message, and mark user
For the second class user.
In a kind of possible embodiment, in above-mentioned apparatus provided in an embodiment of the present invention, preconfigured wake-up word
Response policy, comprising:
When waking up word is that third class wakes up word, response policy is triggering warning message, and/or the urgent electricity that calling is reserved
Words.
The third aspect, the embodiment of the present invention provide a kind of wake-up control equipment of robot, comprising: at least one processing
Device, at least one processor and computer program instructions stored in memory, when computer program instructions are by processor
The method as provided by first aspect of the embodiment of the present invention is realized when execution.
Fourth aspect, the embodiment of the present invention provide a kind of computer readable storage medium, are stored thereon with computer program
The method as provided by first aspect of the embodiment of the present invention is realized in instruction when computer program instructions are executed by processor.
Wake-up control method, device, equipment and the medium of robot provided in an embodiment of the present invention, obtain the voice of user
Data when in determining voice data comprising preset wake-up word, are based on preconfigured wake-up word response policy, according to voice
The wake-up word for including in data determines corresponding target response strategy, and controls robot performance objective response policy.
In the wake-up control program of robot provided in an embodiment of the present invention, by responding plan in preconfigured wake-up word
Slightly middle configuration of robotic corresponding response policy under different wake-up words, allows the robot to recognizing user speech number
When the wake-up word for including in, according to the difference for waking up word, different response policies is taken, is waken up with using in the prior art more
The robot of word executes identical response policy after being waken up by different wake-up words and compares, for different wake-up words, takes
Different response policies can enrich the response policy of robot, to meet the needs of more application scenarios.
Detailed description of the invention
Fig. 1 is the schematic flow diagram of the wake-up control method of robot provided in an embodiment of the present invention;
Fig. 2 is the structural schematic diagram of the wake-up control device of robot provided in an embodiment of the present invention;
Fig. 3 is the structural schematic diagram of the wake-up control equipment of robot provided in an embodiment of the present invention.
Specific embodiment
With reference to the accompanying drawing, to a kind of wake-up control method of robot provided in an embodiment of the present invention, appliance arrangement and
The specific embodiment of medium is described in detail.
It should be noted that the wake-up control program of robot provided in an embodiment of the present invention, it can be by robot
The controller in portion or control centre's control execute, can also be by the external equipment with robot communication (for example, server, shifting
Dynamic terminal etc.) control execution, it is not limited in the embodiment of the present invention.
As shown in Figure 1, the wake-up control method of robot provided in an embodiment of the present invention, may include steps of:
Step 101, the voice data of user is obtained.
When it is implemented, when obtaining the voice data of user, if the wake-up of robot provided in an embodiment of the present invention controls
Scheme is executed by the controller of robot or control centre's control, then can directly pass through microphone or Mike in robot
Wind array acquisition voice data;If the wake-up control program of robot provided in an embodiment of the present invention is by outer with robot communication
Equipment control in portion's executes, then the microphone in the available robot of external equipment or the collected voice number of microphone array
According to.
In one example, when the microphone in robot or microphone array acquire voice data, wheat can be passed through
A certain range of voice data around gram elegance collection robot can also be acquired a certain around robot by microphone array
The a certain range of voice data in direction.
Step 102, when in determining voice data comprising preset wake-up word, plan is responded based on preconfigured wake-up word
Slightly, according to the wake-up word for including in voice data, corresponding target response strategy, preconfigured wake-up word response policy are determined
In include the corresponding relationship waken up between word and response policy.
When it is implemented, comprising that can be wrapped according in voice data after preset wake-up word in determining voice data
It is corresponding to search the wake-up word for determining and including in voice data from preconfigured wake-up word response policy for the wake-up word included
Target response strategy.Wherein, preconfigured wake up includes the corresponding pass waken up between word and response policy in word response policy
System.
Waking up the corresponding relationship between word and response policy can predefine according to the demand of practical application scene.
Step 103, robot performance objective response policy is controlled.
In a kind of possible embodiment, it is based on preconfigured wake-up word response policy, is wrapped according in voice data
The wake-up word included determines corresponding target response strategy, can be combined with the current state of robot, specifically, in determination
Before corresponding target response strategy, the current state of robot can also be obtained, then is responded based on preconfigured wake-up word
Strategy determines that corresponding target response strategy, preconfigured wake-up word respond plan according to the wake-up word for including in voice data
It include the corresponding relationship waken up between word and response policy in slightly, comprising: it is based on preconfigured wake-up word response policy, according to
The current state of the wake-up word and robot for including in voice data, determines corresponding target response strategy, preconfigured
Waking up includes the corresponding relationship waken up between the state and response policy of word, robot in word response policy.
Wherein, the current state of robot can include but is not limited to: the motion state of robot and/or appointing for robot
Business state.The current state of robot can be obtained from the controller of robot or control centre, naturally it is also possible to using other
Mode obtains.When it is implemented, by taking motion state as an example, the current motion state of robot is used in available robot
The measurement result of property measuring unit (Inertial Measurement Unit, IMU), and then based on the measurement result got
It determines, the current motion state of the determining robot of IMU can also be directly acquired, it is not limited in the embodiment of the present invention.
In the present embodiment, preconfigured wake up includes waking up word, the state of robot and response plan in word response policy
Corresponding relationship between slightly, is illustrated preconfigured wake-up word response policy below with reference to specific embodiment.
In a possible embodiment, preconfigured wake-up word response policy, comprising: waking up word as the first kind
When the state for waking up word and robot is movement, response policy is stop motion, plays the first speech message, and rotate so that
Robot screen faces user;Wake up word be the second class to wake up the state of word and robot be movement when, response policy is to stop
It only moves, plays the second speech message, and when determining the voice data for not getting user in preset duration again, restore fortune
It is dynamic.
It should be noted that wake up word be the second class to wake up the state of word and robot be movement when, response policy is
Stop motion plays the second speech message, after playing the second speech message, however, it is determined that get user in preset duration again
Voice data when, the first speech message can be played, and rotate so that robot screen user oriented.
Wherein, the first kind wakes up word and the second class wakes up word and can be preset according to practical application scene, for example, first
Class, which wakes up word, to be the higher wake-up word of identification, and such as the proprietary address " the small small X of X " of robot, the second class wakes up word can be with
For the lower wake-up word of identification, such as some common phrases " hello ", " ".
First speech message and the second speech message can equally be preset according to practical application scene, for example, first
Speech message can be specific response message, such as " please tell ", " next ", and the second speech message can be request confirmation
Message, such as " you cry out me? ".
It certainly, when it is implemented, can also be with the format of preset first speech message and the second speech message, then by machine
People replys according to the actual situation.For example, the first preset spoken message format is " XX please be told ", the second preset language
Sound message format is " XX, you cry out me? ", then robot is by visual identity, when determining that active user is small A, if playing
First speech message can play " small A please be told ", if playing the second speech message, can play that " small A, you cry out me
? ".
Preset duration can flexibly be set according to actual needs, and it is not limited in the embodiment of the present invention, for example, when default
A length of 5 seconds.
In an example it is assumed that it is " the small small X of X " that the first kind, which wakes up word, it is " hello ", the first voice that the second class, which wakes up word,
Message is " please tell ", and the second speech message is " you cry out me ".Determining that wake-up word is " the small small X of X " and robot is current
State be movement when, stop motion, play " please tell " speech message, while rotate so that robot screen in face of use
Family.
When determining that waking up the state that word is " hello " and robot is current is to move, stop motion, " you cry out me for broadcasting
? " speech message, while acquiring the voice data of user, however, it is determined that do not collect the voice number of user in preset duration
According to then restoring to move, certainly, however, it is determined that collect the voice data of user in preset duration, then can play " please tell "
Speech message, while rotating so that robot screen faces user.
In a kind of possible embodiment, preconfigured wake-up word response policy, further includes: wake up word be first
When the state of class wake-up word and robot is static, response policy is to play third speech message, and rotate so that robot screen
Curtain faces user;Wake up word be the second class to wake up the state of word and robot be static when, response policy is rotation so that machine
Device people's screen user oriented.
Wherein, third speech message can be preset according to practical application scene, can also by robot according to
Preset format is determined, and it is not limited in the embodiment of the present invention.
In one example, it will again be assumed that it is " the small small X of X " that the first kind, which wakes up word, and it is " hello ", third language that the second class, which wakes up word,
Sound message is " please tell ".When the state for determining that wake-up word is " the small small X of X " and robot is current is static, broadcasting " asks pheno
Tell " speech message, while rotate so that robot screen face user.
When the state for determining that wake-up word is " hello " and robot is current is static, voice messaging is not played, control turns
It is dynamic so that robot screen faces user, while can also in screen playing animation.
In a kind of possible embodiment, it is based on preconfigured wake-up word response policy, is wrapped according in voice data
The wake-up word included determines corresponding target response strategy, can be combined with the current visual identity of robot as a result, specific next
It says, before determining corresponding target response strategy, the current visual identity of robot can also be obtained as a result, based on matching in advance
The wake-up word response policy set determines corresponding target response strategy, is pre-configured with according to the wake-up word for including in voice data
To wake up include the corresponding relationship waken up between word and response policy in word response policy, comprising: be based on preconfigured wake-up
Word response policy, according to the current visual identity of the wake-up word and robot that include in voice data as a result, determination is corresponding
Target response strategy includes waking up word, robotic vision recognition result and response in preconfigured wake-up word response policy
Corresponding relationship between strategy.
In a kind of possible embodiment, visual identity result includes visual identity result to user and to environment
At least one of visual identity result.
When visual identity result includes the visual identity result to user, robotic vision recognition result specifically can be with
It is the judgement for the human face data that user whether is stored in preconfigured face database as a result, robotic vision recognition result
It is also possible to the matching result of human face data in the human face data and preconfigured face database of user, the embodiment of the present invention
It does not limit this.
It is the human face data that user whether is stored in preconfigured face database with robotic vision recognition result
Judgement result for, in such cases, preconfigured wake-up word response policy, comprising: wake up word be the first kind wake up
Word and the face number that not stored user in preconfigured face database is determined according to the current visual identity result of robot
According to when, response policy is to play the 4th speech message, and marks the user as first kind user;Word is being waken up as the wake-up of the second class
Word and the face number that not stored user in preconfigured face database is determined according to the current visual identity result of robot
According to when, response policy is to play preset the 5th speech message, and mark the user as the second class user.
Wherein, the 4th speech message and the 5th speech message can be preset according to practical application scene, can also be by
Robot is determined according to preset format, and it is not limited in the embodiment of the present invention.For example, the 4th speech message can be
For the speech message of old user, such as " hello, and where I was as meeting you " etc., the 5th speech message can be for for new user
Speech message, such as " hello, I wants to make a friend with you ".
In an example it is assumed that it is " the small small X of X " that the first kind, which wakes up word, it is " hello ", the 4th voice that the second class, which wakes up word,
Message is " hello, and where I was as meeting you ", and the 5th speech message is " hello, I wants to make a friend with you ".It is called out in determination
Word of waking up is " the small small X of X " and is determined according to the current visual identity result of robot not stored in preconfigured face database
The speech message of " hello, and where I was as meeting you " when the human face data of user, is played, while being the first kind by user's mark
User (for example, old user).Determining that waking up word is " hello " and determines according to the current visual identity result of robot preparatory
The voice in the face database of configuration when the human face data of not stored user, playing " hello, I wants to make a friend with you " disappears
Breath, while being the second class user (for example, new user) by user's mark.
It should be noted that when it is implemented, when determining target response strategy, in conjunction with the current state of robot or
It can be with flexible choice, for example, being determined according to the current visual identity result of robot in conjunction with the visual identity result of robot
It, then can be according to waking up the current shape of word and robot when being stored with the human face data of user in preconfigured face database
State determines target response strategy, or determines target response strategy according only to word is waken up.
In a kind of possible embodiment, in preconfigured wake-up word response policy can with custom strategies, such as:
When waking up word is that third class wakes up word, response policy is triggering warning message, and/or the emergency call that calling is reserved.
Wherein, third class wakes up word and can preset according to actual needs, for example, in the scenes such as hospital, third class
Word, such as " help help ", " distress call ", " SOS " can be waken up for flash appeal class by waking up word.
In an example it is assumed that it is " help help " that third class, which wakes up word,.When determining that waking up word is " help help ",
Trigger warning message, and call reserved emergency call (such as: 120).
In a kind of possible embodiment, the wake-up control program of robot provided in an embodiment of the present invention is in robot
Controller when perhaps executing in control centre controller or control centre can also utilize the wake-up got from server
Word response policy updates currently stored wake-up word response policy.
Based on identical inventive concept, the embodiment of the present invention also provides a kind of wake-up control device of robot.
As shown in Fig. 2, the embodiment of the present invention provides a kind of wake-up control device of robot, comprising:
Acquiring unit 201, for obtaining the voice data of user.
Processing unit 202 is based on preconfigured wake-up when for including preset wake-up word in determining voice data
Word response policy determines corresponding target response strategy, preconfigured wake-up word according to the wake-up word for including in voice data
It include the corresponding relationship waken up between word and response policy in response policy.
Control unit 203, for controlling robot performance objective response policy.
In a kind of possible embodiment, acquiring unit 201 is also used to: obtaining the current state of robot;Processing is single
Member 202 is specifically used for: based on preconfigured wake-up word response policy, according to the wake-up word and machine for including in voice data
The current state of people determines corresponding target response strategy, includes waking up word, machine in preconfigured wake-up word response policy
Corresponding relationship between the state and response policy of people.
In a kind of possible embodiment, acquiring unit 201 is also used to: obtaining the current visual identity knot of robot
Fruit;Processing unit 202 is specifically used for: preconfigured wake-up word response policy is based on, according to the wake-up for including in voice data
The current visual identity of word and robot is as a result, determine corresponding target response strategy, preconfigured wake-ups word response plan
It include the corresponding relationship waken up between word, robotic vision recognition result and response policy in slightly.
In a kind of possible embodiment, visual identity result includes visual identity result to user and to environment
At least one of visual identity result.
In a kind of possible embodiment, preconfigured wake-up word response policy, comprising: waking up word as the first kind
When the state for waking up word and robot is movement, response policy is stop motion, plays the first speech message, and rotate so that
Robot screen user oriented;Wake up word be the second class to wake up the state of word and robot be movement when, response policy is to stop
It only moves, plays the second speech message, and when determining the voice data for not getting user in preset duration again, restore fortune
It is dynamic.
In a kind of possible embodiment, preconfigured wake-up word response policy, comprising: waking up word as the first kind
When the state of wake-up word and robot is static, response policy is to play third speech message, and rotate so that robot screen
User oriented;Wake up word be the second class to wake up the state of word and robot be static when, response policy is rotation so that machine
People's screen user oriented.
In a kind of possible embodiment, preconfigured wake-up word response policy, comprising: waking up word as the first kind
It wakes up word and determines the people of not stored user in preconfigured face database according to the current visual identity result of robot
When face data, response policy is to play the 4th speech message, and mark the user as first kind user;It is that the second class is called out waking up word
Awake word and the face that not stored user in preconfigured face database is determined according to the current visual identity result of robot
When data, response policy is to play the 5th preset speech message, and mark the user as the second class user.
In a kind of possible embodiment, preconfigured wake-up word response policy, comprising: waking up word as third class
When waking up word, response policy is triggering warning message, and/or the emergency call that calling is reserved.
In addition, the wake-up control method and device in conjunction with the robot of Fig. 1-Fig. 2 embodiment of the present invention described can be by
The wake-up of robot controls equipment to realize.Fig. 3 shows the wake-up control equipment of robot provided in an embodiment of the present invention
Hardware structural diagram.
Wake-up control equipment is specifically as follows the control equipment of robot interior, or outer with robot communication
Portion's equipment, such as server, mobile terminal, it is not limited in the embodiment of the present invention.
The wake-up control equipment of robot may include processor 301 and the memory for being stored with computer program instructions
302。
Specifically, above-mentioned processor 301 may include central processing unit (CPU) or specific integrated circuit
(Application Specific Integrated Circuit, ASIC), or may be configured to implement implementation of the present invention
One or more integrated circuits of example.
Memory 302 may include the mass storage for data or instruction.For example it rather than limits, memory
302 may include hard disk drive (Hard Disk Drive, HDD), floppy disk drive, flash memory, CD, magneto-optic disk, tape or logical
With the combination of universal serial bus (Universal Serial Bus, USB) driver or two or more the above.It is closing
In the case where suitable, memory 302 may include the medium of removable or non-removable (or fixed).In a suitable case, it stores
Device 302 can be inside or outside data processing equipment.In a particular embodiment, memory 302 is nonvolatile solid state storage
Device.In a particular embodiment, memory 302 includes read-only memory (ROM).In a suitable case, which can be mask
ROM, programming ROM (PROM), erasable PROM (EPROM), the electric erasable PROM (EEPROM), electrically-alterable ROM of programming
(EAROM) or the combination of flash memory or two or more the above.
Processor 301 is by reading and executing the computer program instructions stored in memory 302, to realize above-mentioned implementation
The wake-up control method of any one robot in example.
In one example, the wake-up control equipment of robot may also include communication interface 303 and bus 310.Wherein, such as
Shown in Fig. 3, processor 301, memory 302, communication interface 303 connect by bus 310 and complete mutual communication.
Communication interface 303 is mainly used for realizing in the embodiment of the present invention between each module, device, unit and/or equipment
Communication.
Bus 310 includes hardware, software or both, and the component of the wake-up control equipment of robot is coupled to each other one
It rises.For example it rather than limits, bus may include accelerated graphics port (AGP) or other graphics bus, enhancing industrial standard frame
Structure (EISA) bus, front side bus (FSB), super transmission (HT) interconnection, Industry Standard Architecture (ISA) bus, infinite bandwidth interconnection,
Low pin count (LPC) bus, memory bus, micro- channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-
Express (PCI-X) bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association part (VLB) bus or
The combination of other suitable buses or two or more the above.In a suitable case, bus 310 may include one
Or multiple buses.Although specific bus has been described and illustrated in the embodiment of the present invention, the present invention considers any suitable bus
Or interconnection.
The wake-up control equipment of the robot can be executed in the embodiment of the present invention based on the voice data for getting user
Robot wake-up control method, thus realize in conjunction with Fig. 1-Fig. 2 describe robot wake-up control method and device.
In addition, the embodiment of the present invention can provide a kind of meter in conjunction with the wake-up control method of the robot in above-described embodiment
Calculation machine readable storage medium storing program for executing is realized.Computer program instructions are stored on the computer readable storage medium;The computer journey
The wake-up control method of any one robot in above-described embodiment is realized in sequence instruction when being executed by processor.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The shape for the computer program product implemented in usable storage medium (including but not limited to magnetic disk storage and optical memory etc.)
Formula.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (10)
1. a kind of wake-up control method of robot characterized by comprising
Obtain the voice data of user;
When including preset wake-up word in determining the voice data, it is based on preconfigured wake-up word response policy, according to
The wake-up word for including in the voice data determines that corresponding target response strategy, the preconfigured wake-up word respond plan
It include the corresponding relationship waken up between word and response policy in slightly;
It controls the robot and executes the target response strategy.
2. the method according to claim 1, wherein before determining corresponding target response strategy, further includes:
Obtain the current state of the robot;
Corresponding mesh is determined according to the wake-up word for including in the voice data based on preconfigured wake-up word response policy
Response policy is marked, preconfigured wake up includes the corresponding relationship waken up between word and response policy in word response policy,
Include:
Based on preconfigured wake-up word response policy, according to the wake-up word and the robot for including in the voice data
Current state determines corresponding target response strategy, includes waking up word, machine in the preconfigured wake-up word response policy
Corresponding relationship between the state and response policy of device people.
3. the method according to claim 1, wherein before determining corresponding target response strategy, further includes:
Obtain the current visual identity result of the robot;
Corresponding mesh is determined according to the wake-up word for including in the voice data based on preconfigured wake-up word response policy
Response policy is marked, preconfigured wake up includes the corresponding relationship waken up between word and response policy in word response policy,
Include:
Based on preconfigured wake-up word response policy, according to the wake-up word and the robot for including in the voice data
Current visual identity includes in the preconfigured wake-up word response policy as a result, determine corresponding target response strategy
Wake up the corresponding relationship between word, robotic vision recognition result and response policy.
4. according to the method described in claim 3, it is characterized in that, the visual identity result includes the visual identity to user
As a result and at least one of the visual identity result of environment.
5. according to the method described in claim 2, it is characterized in that, the preconfigured wake-up word response policy, comprising:
The wake-up word be the first kind to wake up the state of word and the robot be movement when, the response policy is to stop
Movement plays the first speech message, and rotates so that robot screen is towards the user;
The wake-up word be the second class to wake up the state of word and the robot be movement when, the response policy is to stop
Movement plays the second speech message, and when determining the voice data for not getting the user in preset duration again, restores fortune
It is dynamic.
6. according to the method described in claim 2, it is characterized in that, the preconfigured wake-up word response policy, comprising:
The wake-up word be the first kind to wake up the state of word and the robot be static when, the response policy is to play
Third speech message, and rotate so that robot screen is towards the user;
The wake-up word be the second class to wake up the state of word and the robot be static when, the response policy is rotation
So that robot screen is towards the user.
7. according to the method described in claim 3, it is characterized in that, the preconfigured wake-up word response policy, comprising:
It is first kind wake-up word in the wake-up word and is pre-configured with according to the current visual identity result determination of the robot
Face database in the not stored user human face data when, the response policy is to play the 4th speech message, and is marked
Remember that the user is first kind user;
It is the second class wake-up word in the wake-up word and is pre-configured with according to the current visual identity result determination of the robot
Face database in the not stored user human face data when, the response policy is to play preset the 5th voice to disappear
Breath, and marking the user is the second class user.
8. the method according to claim 1, wherein the preconfigured wake-up word response policy, comprising:
When the wake-up word is that third class wakes up word, the response policy is triggering warning message, and/or reserved tight of calling
Urgent telegram words.
9. a kind of wake-up control device of robot characterized by comprising
Acquiring unit, for obtaining the voice data of user;
Processing unit is based on preconfigured wake-up word when for including preset wake-up word in determining the voice data
Response policy determines corresponding target response strategy according to the wake-up word for including in the voice data, described preconfigured
Waking up includes the corresponding relationship waken up between word and response policy in word response policy;
Control unit executes the target response strategy for controlling the robot.
10. a kind of wake-up of robot controls equipment characterized by comprising at least one processor, at least one processor
And the computer program instructions of storage in the memory, when the computer program instructions are executed by the processor
Realize such as method of any of claims 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811238629.4A CN109358751A (en) | 2018-10-23 | 2018-10-23 | A kind of wake-up control method of robot, device and equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811238629.4A CN109358751A (en) | 2018-10-23 | 2018-10-23 | A kind of wake-up control method of robot, device and equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109358751A true CN109358751A (en) | 2019-02-19 |
Family
ID=65346354
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811238629.4A Pending CN109358751A (en) | 2018-10-23 | 2018-10-23 | A kind of wake-up control method of robot, device and equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109358751A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109920425A (en) * | 2019-04-03 | 2019-06-21 | 北京石头世纪科技股份有限公司 | Robot voice control method and device, robot and medium |
CN110051289A (en) * | 2019-04-03 | 2019-07-26 | 北京石头世纪科技股份有限公司 | Robot voice control method and device, robot and medium |
CN110136704A (en) * | 2019-04-03 | 2019-08-16 | 北京石头世纪科技股份有限公司 | Robot voice control method and device, robot and medium |
CN110534102A (en) * | 2019-09-19 | 2019-12-03 | 北京声智科技有限公司 | A kind of voice awakening method, device, equipment and medium |
CN110727821A (en) * | 2019-10-12 | 2020-01-24 | 深圳海翼智新科技有限公司 | Method, apparatus, system and computer storage medium for preventing device from being awoken by mistake |
JP2020149038A (en) * | 2019-03-11 | 2020-09-17 | バイドゥ オンライン ネットワーク テクノロジー (ベイジン) カンパニー リミテッド | Method and apparatus for waking up device |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104881108A (en) * | 2014-02-27 | 2015-09-02 | 青岛海尔机器人有限公司 | Intelligent man-machine interaction method and device |
CN106847285A (en) * | 2017-03-31 | 2017-06-13 | 上海思依暄机器人科技股份有限公司 | A kind of robot and its audio recognition method |
CN106863319A (en) * | 2017-01-17 | 2017-06-20 | 北京光年无限科技有限公司 | A kind of robot awakening method and device |
CN107223280A (en) * | 2017-03-03 | 2017-09-29 | 深圳前海达闼云端智能科技有限公司 | robot awakening method, device and robot |
CN108068121A (en) * | 2017-12-22 | 2018-05-25 | 达闼科技(北京)有限公司 | A kind of man-machine interaction control method, device and robot |
CN108098767A (en) * | 2016-11-25 | 2018-06-01 | 北京智能管家科技有限公司 | A kind of robot awakening method and device |
CN108235745A (en) * | 2017-05-08 | 2018-06-29 | 深圳前海达闼云端智能科技有限公司 | robot awakening method, device and robot |
CN108231079A (en) * | 2018-02-01 | 2018-06-29 | 北京百度网讯科技有限公司 | For the method, apparatus, equipment and computer readable storage medium of control electronics |
CN108297098A (en) * | 2018-01-23 | 2018-07-20 | 上海大学 | The robot control system and method for artificial intelligence driving |
CN108510992A (en) * | 2018-03-22 | 2018-09-07 | 北京云知声信息技术有限公司 | The method of voice wake-up device |
-
2018
- 2018-10-23 CN CN201811238629.4A patent/CN109358751A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104881108A (en) * | 2014-02-27 | 2015-09-02 | 青岛海尔机器人有限公司 | Intelligent man-machine interaction method and device |
CN108098767A (en) * | 2016-11-25 | 2018-06-01 | 北京智能管家科技有限公司 | A kind of robot awakening method and device |
CN106863319A (en) * | 2017-01-17 | 2017-06-20 | 北京光年无限科技有限公司 | A kind of robot awakening method and device |
CN107223280A (en) * | 2017-03-03 | 2017-09-29 | 深圳前海达闼云端智能科技有限公司 | robot awakening method, device and robot |
CN106847285A (en) * | 2017-03-31 | 2017-06-13 | 上海思依暄机器人科技股份有限公司 | A kind of robot and its audio recognition method |
CN108235745A (en) * | 2017-05-08 | 2018-06-29 | 深圳前海达闼云端智能科技有限公司 | robot awakening method, device and robot |
CN108068121A (en) * | 2017-12-22 | 2018-05-25 | 达闼科技(北京)有限公司 | A kind of man-machine interaction control method, device and robot |
CN108297098A (en) * | 2018-01-23 | 2018-07-20 | 上海大学 | The robot control system and method for artificial intelligence driving |
CN108231079A (en) * | 2018-02-01 | 2018-06-29 | 北京百度网讯科技有限公司 | For the method, apparatus, equipment and computer readable storage medium of control electronics |
CN108510992A (en) * | 2018-03-22 | 2018-09-07 | 北京云知声信息技术有限公司 | The method of voice wake-up device |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2020149038A (en) * | 2019-03-11 | 2020-09-17 | バイドゥ オンライン ネットワーク テクノロジー (ベイジン) カンパニー リミテッド | Method and apparatus for waking up device |
US11270690B2 (en) | 2019-03-11 | 2022-03-08 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for waking up device |
CN109920425A (en) * | 2019-04-03 | 2019-06-21 | 北京石头世纪科技股份有限公司 | Robot voice control method and device, robot and medium |
CN110051289A (en) * | 2019-04-03 | 2019-07-26 | 北京石头世纪科技股份有限公司 | Robot voice control method and device, robot and medium |
CN110136704A (en) * | 2019-04-03 | 2019-08-16 | 北京石头世纪科技股份有限公司 | Robot voice control method and device, robot and medium |
CN109920425B (en) * | 2019-04-03 | 2021-11-12 | 北京石头世纪科技股份有限公司 | Robot voice control method and device, robot and medium |
CN110136704B (en) * | 2019-04-03 | 2021-12-28 | 北京石头世纪科技股份有限公司 | Robot voice control method and device, robot and medium |
CN114010102A (en) * | 2019-04-03 | 2022-02-08 | 北京石头世纪科技股份有限公司 | Cleaning robot |
CN110051289B (en) * | 2019-04-03 | 2022-03-29 | 北京石头世纪科技股份有限公司 | Voice control method and device for sweeping robot, robot and medium |
CN114010102B (en) * | 2019-04-03 | 2023-01-03 | 北京石头创新科技有限公司 | Cleaning robot |
CN110534102A (en) * | 2019-09-19 | 2019-12-03 | 北京声智科技有限公司 | A kind of voice awakening method, device, equipment and medium |
CN110727821A (en) * | 2019-10-12 | 2020-01-24 | 深圳海翼智新科技有限公司 | Method, apparatus, system and computer storage medium for preventing device from being awoken by mistake |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109358751A (en) | A kind of wake-up control method of robot, device and equipment | |
CN110060685B (en) | Voice wake-up method and device | |
KR101753509B1 (en) | Identifying people that are proximate to a mobile device user via social graphs, speech models, and user context | |
US11948241B2 (en) | Robot and method for operating same | |
WO2017215297A1 (en) | Cloud interactive system, multicognitive intelligent robot of same, and cognitive interaction method therefor | |
CN107871506A (en) | The awakening method and device of speech identifying function | |
CN108075892A (en) | The method, apparatus and equipment of a kind of speech processes | |
CN106663219A (en) | Methods and systems of handling a dialog with a robot | |
CN109166575A (en) | Exchange method, device, smart machine and the storage medium of smart machine | |
CN112231021B (en) | Method and device for guiding new functions of software | |
CN113168227A (en) | Method of performing function of electronic device and electronic device using the same | |
CN104503834B (en) | A kind of information processing method and the first electronic equipment | |
CN110187766A (en) | A kind of control method of smart machine, device, equipment and medium | |
CN108536418A (en) | A kind of method, apparatus and wireless sound box of the switching of wireless sound box play mode | |
US20180054688A1 (en) | Personal Audio Lifestyle Analytics and Behavior Modification Feedback | |
JP2009166184A (en) | Guide robot | |
CN110871813A (en) | Control method and device of virtual robot, vehicle, equipment and storage medium | |
CN109671430A (en) | A kind of method of speech processing and device | |
CN114299933A (en) | Speech recognition model training method, device, equipment, storage medium and product | |
CN104793747A (en) | Method, device and system for inputting through wearable device | |
CN111339881A (en) | Baby growth monitoring method and system based on emotion recognition | |
CN113658586B (en) | Training method of voice recognition model, voice interaction method and device | |
CN111176435A (en) | User behavior-based man-machine interaction method and sound box | |
CN110515449B (en) | Method and device for awakening intelligent equipment | |
CN112634911A (en) | Man-machine conversation method, electronic device and computer readable 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: 20190219 |