CN108098767A - A kind of robot awakening method and device - Google Patents
A kind of robot awakening method and device Download PDFInfo
- Publication number
- CN108098767A CN108098767A CN201611067947.XA CN201611067947A CN108098767A CN 108098767 A CN108098767 A CN 108098767A CN 201611067947 A CN201611067947 A CN 201611067947A CN 108098767 A CN108098767 A CN 108098767A
- Authority
- CN
- China
- Prior art keywords
- face
- robot
- wake
- target face
- target
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
- B25J9/161—Hardware, e.g. neural networks, fuzzy logic, interfaces, processor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
Landscapes
- Engineering & Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Robotics (AREA)
- General Health & Medical Sciences (AREA)
- Mechanical Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Geometry (AREA)
- Manipulator (AREA)
Abstract
The embodiment of the invention discloses a kind of robot awakening methods and device, method to include:It is detected according to the face that face judgment rule obtains camera;If detecting target face, the effective information of the target face is obtained;According to the effective information, speech recognition application service is triggered;The wake-up that the speech recognition application service is generated according to the voice data and dictionary of acquisition is received to instruct, and according to the wake-up wake instruction robot.The embodiment of the present invention triggers speech recognition application service by obtaining the effective information of target face, and robot is further waken up according to the phonetic order of acquisition and dictionary, pass through conditioning each other for recognition of face and speech recognition, substantially reduce false wake-up probability, and altogether dispense with the learning cost of first user, the default acoustic model of voice service business offer is provided, allows the entire flow that wakes up more naturally, effectively increasing wake-up success rate.
Description
Technical field
The present embodiments relate to robotic technology fields, and in particular to a kind of robot awakening method and device.
Background technology
With the development of robot market, the intelligence degree of robot is higher and higher, therefore more and more intelligent machines
Device people initially enters average family and business place, for example, sweeping robot, special robot, show the way robot etc., significantly
Facilitate people’s lives.But due to machine without 24 it is small when run without interruption, in most cases, can keep standby
State to save electricity consumption, while extends the service life of robot.Therefore, it is necessary to a kind of efficient robotic awakening methods.
Wake-up is to open people and the first step of robot interactive flow, and the wake-up mode of existing robot, which generally uses, to be based on
The voice of acoustic model wakes up, and voice wake-up refers to through the phonetic entry for containing specific wake-up word come " triggering " speech recognition system
It unites to realize subsequent interactive voice.This wake-up mode need default fixed 2~3 wake up word meet at voice service business into
The Algorithm for Training of row a period of time can just be delivered for use, and pronounce there are certain requirements in itself to waking up word, not possess flexible modification
Property;And user must accurately say to wake up word and could open with the matching of default acoustic model and interact, and have certain
Learning cost so that the interaction flow of people and robot is excessively stiff passive.
The content of the invention
Since existing wake-up mode in itself pronounces there are certain requirements to waking up word, do not possess flexibly modification property;And user
It must accurately say and wake up the problem of word and match with default acoustic model could wake up, proposition of the embodiment of the present invention
A kind of robot awakening method and device.
In a first aspect, the embodiment of the present invention proposes a kind of robot awakening method, including:
It is detected according to the face that face judgment rule obtains camera;
If detecting target face, the effective information of the target face is obtained;
According to the effective information, speech recognition application service is triggered;
The wake-up that the speech recognition application service is generated according to the voice data and dictionary of acquisition is received to instruct, and according to
The wake-up wake instruction robot.
Optionally, the method further includes:
The dictionary is updated according to the phonetic order.
Optionally, if described detect target face, before the effective information for obtaining the target face, further include:
Camera is kept to open in the dormant state, image is obtained according to predeterminated frequency and is sent to server;
Correspondingly, if described detect target face, the effective information of the target face is obtained, is specifically included:
If server is detected in described image comprising target face, the target face in described image is obtained
Effective information, and parameter A is sent to the robot;
If server is detected in described image not comprising target face, parameter B is sent to the robot.
Optionally, whether the face judgment rule is more than threshold value, and the mesh for the face size of the target face
Mark whether face includes complete face information;
Wherein, when being judged according to sliding window strategy face, according to determining the probability score of each window
Whether the face size of target face is more than threshold value, whether judges the target face according to decision tree and cascade classifier strategy
Include complete face information.
Optionally, the wake-up for receiving the speech recognition application service and being generated according to the voice data and dictionary of acquisition
Instruction, and according to the wake-up wake instruction robot after, further include:
Export the feedback information after robot wakes up.
Second aspect, the embodiment of the present invention also propose a kind of robot Rouser, including:
Face detection module, the face for being obtained according to face judgment rule to camera are detected;
If effective information acquisition module for detecting target face, obtains the effective information of the target face;
Voice activated module, for according to the effective information, triggering speech recognition application service;
Robot wake-up module is given birth to for receiving the speech recognition application service according to the voice data and dictionary of acquisition
Into wake-up instruction, and according to the wake-up wake instruction robot.
Optionally, described device further includes:
Word library updating module, for being updated according to the phonetic order to the dictionary.
Optionally, described device further includes:
For camera to be kept to open in the dormant state, it is concurrent to obtain image according to predeterminated frequency for image collection module
It send to server;
Correspondingly, if the effective information acquisition module is specifically used for detecting in described image comprising target face,
The effective information of the target face in described image is obtained, and parameter A is sent to the robot;If it detects described
Parameter B the robot is not sent to then comprising target face in image.
Optionally, face judgment rule described in the effective information acquisition module is the face size of the target face
Whether threshold value is more than, and whether the target face includes complete face information;
Wherein, when being judged according to sliding window strategy face, according to determining the probability score of each window
Whether the face size of target face is more than threshold value, whether judges the target face according to decision tree and cascade classifier strategy
Include complete face information.
Optionally, described device further includes:
Feedback information output module, for exporting the feedback information after robot wakes up.
As shown from the above technical solution, the embodiment of the present invention is known by obtaining the effective information of target face to trigger voice
Other application service, and robot is further waken up according to the phonetic order of acquisition and dictionary, pass through recognition of face and speech recognition
Condition each other, substantially reduce false wake-up probability, and altogether dispense with the learning cost of first user, be not limited to voice service
The default acoustic model that business provides allows the entire flow that wakes up more naturally, effectively increasing wake-up success rate.
Description of the drawings
It in order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention, for those of ordinary skill in the art, without creative efforts, can be with
Other attached drawings are obtained according to these figures.
Fig. 1 is a kind of flow diagram for robot awakening method that one embodiment of the invention provides;
Fig. 2 is the flow diagram for another robot awakening method that one embodiment of the invention provides;
Fig. 3 is a kind of structure diagram for robot Rouser that one embodiment of the invention provides.
Specific embodiment
Below in conjunction with the accompanying drawings, the specific embodiment of the present invention is further described.Following embodiment is only used for more
Technical scheme is clearly demonstrated, and is not intended to limit the protection scope of the present invention and limits the scope of the invention.
Fig. 1 shows a kind of flow diagram of robot awakening method provided in this embodiment, including:
S101, the face obtained according to face judgment rule to camera are detected;
Wherein, the face judgment rule is the rule that face is determined according to face size and face characteristic.
The face judgment rule determines under what conditions, robot assert user be in can interactive region, only
When user be in can interactive region when, wake up the machine talent it is significant.
Specifically, the face judgment rule include two big elements, first, whether facial size reaches standard, the element
For carrying out Distance Judgment reference, for apart from robot user farther out, without waking up robot;Second, face characteristic, i.e.,
Whether face information is complete, and whether front is in face of robot for judging user for the element, to determine whether user intends to wake up
Robot.
If S102, detecting target face, the effective information of the target face is obtained.
Wherein, the target face is the face for meeting face judgment rule.
The effective information is the information that can be used in triggering speech recognition application service, special including face size and face
Sign.
Specifically, camera is called persistently to detect face, the target of interactive condition is determined for compliance with according to face judgment rule
Face, and obtain the facial size and face characteristic of the target face.
Whether face information is effective, decides whether to open speech recognition engine, Face datection is placed on the first step, Ke Yiyou
Effect reduces the power consumption of computer.
Component that Face datection is waken up as robot and the action for triggering speech recognition engine, it is final into
Work(wake-up needs Face datection and speech recognition to meet condition simultaneously.
S103, according to the effective information, trigger speech recognition application service;
Wherein, the speech recognition application service is the application service that the voice messaging of user is identified.
The corresponding instruction of voice data that the phonetic order sends for the user that robot receives.
S104, the wake-up instruction that the speech recognition application service is generated according to the voice data and dictionary of acquisition is received,
And according to the wake-up wake instruction robot.
Wherein, the dictionary wakes up dictionary, this day common face repertorie for daily " greeting ".Data in dictionary must be
Meet the words and phrases of natural language specification, such as " hello ", " Hi ", " good morning " words and phrases.
Daily meeting language is most natural interactive mode in person to person's contacts, therefore, is talked about daily meeting language as wake-up
Art fits well on user's custom, also possesses the advantage of zero cost education user.User only needs to appear in before camera and uses nature
Language and robot interactive, you can wake up successfully, fixed without learning and memory and wake up word.
Specifically, when capturing the effective information of target face, using effective information as triggering speech recognition application clothes
The condition of business lights the UI interfaces of robot and triggers speech recognition engine.
Light the concrete operations at UI interfaces of robot such as:It opens eyes etc. and to show the UI of robot wake-up states, it can
The feedback in user interface is given, corresponding UI interfaces are closed when face is lost, and are restored to original state.
When grabbing the target face for meeting face judgment rule, obtain the effective information of target face and open immediately
Speech recognition application service, while Face datection is kept to continue to capture face information;When target face is lost, close voice and know
Other application service.
The face judgment rule and the dictionary determine that robot wakes up the height of probability, sentence by adjusting face
It the parameter for rule of breaking and improves dictionary information and can flexibly and effectively control the wake-up probability of robot.
Specifically, the present embodiment is divided into two parts, is respectively recognition of face and speech recognition.On the basis of recognition of face
On, wake operation is completed by everyday words (speech recognition), single use is extended and fixes the pattern that word wakes up that wakes up, make wake-up
More easily naturally, reduced or remitted new user use threshold, need not illustrate guidance under conditions of successfully complete wake-up.
The present embodiment triggers speech recognition application service, and further basis by obtaining the effective information of target face
The phonetic order and dictionary of acquisition wake up robot, by conditioning each other for recognition of face and speech recognition, substantially reduce and call out by mistake
Awake probability, and the learning cost of first user is altogether dispensed with, the default acoustic model of voice service business offer is provided,
The entire flow that wakes up is allowed more naturally, effectively increasing wake-up success rate.
Further, on the basis of above method embodiment, the method further includes:
S105, the dictionary is updated according to the phonetic order.
Since the degree of perfection of dictionary information determines the wake-up probability of robot, it is therefore desirable to keep the upgrading of dictionary more
Newly, so that newest language material is updated to dictionary in real time.
Further, on the basis of above method embodiment, before S101, further include:
S100, camera is kept to open in the dormant state, image is obtained according to predeterminated frequency and is sent to server.
In order to save the power consumption of robot, extend the service life of robot, therefore in the case where no user instructs, make machine
People enters dormant state;But in order to the timely and effective wake-up for triggering robot, it is necessary to keep the opening of camera, with
The image of face information is persistently captured, when acquirement meets the effective information of target face of face judgment rule, is triggered immediately
Speech recognition application service.
Speech recognition application service is triggered by camera under robot dormant state, camera is reduced and voice is known
The power consumption that other application service is persistently opened simultaneously,
For example, once robot enters dormant state, then the frequency for being kept for 3s/ times by camera captures a figure
Piece upload server.Correspondingly, when the picture of server-side detection crawl is if there is face information then return parameters A to robot,
Then speech recognition engine is opened immediately by robot;If crawl picture effective face information is not detected when if return parameters B to
Robot, then robot continue capturing pictures and be not turned on speech recognition engine.Wherein, parameter A references have face information, parameter
B is referred to without face information;
Further, on the basis of above method embodiment, the face judgment rule is the face of the target face
Whether portion's size is more than threshold value, and whether the target face includes complete face information;
Wherein, when being judged according to sliding window strategy face, according to determining the probability score of each window
Whether the face size of target face is more than threshold value, whether judges the target face according to decision tree and cascade classifier strategy
Include complete face information.
The threshold value is to be preset according to the specific requirement of user.
The face judgment rule determines under what conditions, robot assert user be in can interactive region, only
When user be in can interactive region when, wake up the machine talent it is significant.
Specifically, Face datection algorithm uses sliding window strategy, all areas on image is detected, for each
Image is filtered from region (being known as image window) using decision tree and cascade classifier strategy.Filtering process can calculate each
The probability score of window simultaneously compares the threshold value of setting and completes to filter the operation of invalid window, is finally obtained after multiple filtration
Qualified image window is to get to Face datection result.
The face judgment rule include two big elements, first, whether facial size reaches standard, the element for do away from
From judging to refer to, for apart from robot user farther out, without waking up robot;Second, face characteristic, i.e. face information is
No complete, whether front is in face of robot for judging user for the element, to determine whether user intends to wake up robot.
For example, face size is represented with face's pixel number, the threshold value is set as 200.When the figure that camera obtains
The face size of face is 300 as in, and recognizes complete face information, then can determine the face is target face;When taking the photograph
The face size of face is 300 in the image obtained as head, and unidentified to complete face information, then illustrates that user facing away from
Robot, the face are not target faces;When the face size of face in the image that camera obtains is 180, regardless of whether knowing
Complete face information is clipped to, which is not target face.
By according to threshold value and whether comprising complete face information being used as face judgment rule, target can be quickly determined
Face.
Further, on the basis of above method embodiment, after S104, further include:
Feedback information after S106, the wake-up of output robot.
Wherein, the feedback information can be text information for user can be made to know the information that robot has waken up, can
Think image information, or voice messaging.
Specifically, after the speech recognition application service wakes up robot according to the phonetic order and dictionary of acquisition, machine
Device people exports the feedback information after waking up.
By giving field feedback, user can be made to know the state of robot in time, preferably to be interacted.
Fig. 2 shows the flow diagram of robot awakening method provided in this embodiment, judges presetting face
On the premise of rule and dictionary, mainly including following three steps:
A1, in the dormant state, camera is kept it turned on, and persistently detects face, and people is obtained after face is detected
The effective information of face simultaneously performs A2;
A2, using the effective face information obtained in A1 as trigger condition, light UI interfaces and trigger speech recognition application
Service;
A3, when speech recognition application service acquisition to effective information (speech trigger instruction), by being matched with dictionary,
Successful match then completes robot wake operation and exports response results.
The present embodiment employs the integrated collaborative scheme of recognition of face and speech recognition, is detected effectively by recognition of face
Information wakes up robot screen and activates speech recognition, is obtained eventually by voice recognition result and face recognition result
Dual effective information is automatically waken up robot.A kind of more flexible controllable robot wake-up mode is provided, is improved man-machine
Interactive fluency makes wake-up mode more rich more easy to use.
Fig. 3 shows a kind of structure diagram of robot Rouser provided in this embodiment, and described device includes:People
Face detection module 301, effective information acquisition module 302, voice activated module 303 and robot wake-up module 304, wherein:
The face that the face detection module 301 is used to obtain camera according to face judgment rule is detected;
If the effective information acquisition module 302 obtains the effective of the target face for detecting target face
Information;
The voice activated module 303 is used to, according to the effective information, trigger speech recognition application service;
The robot wake-up module 304 be used to receiving the speech recognition application service according to the voice data of acquisition and
The wake-up instruction of dictionary generation, and according to the wake-up wake instruction robot.
Specifically, the face detection module 301 is detected according to the face that face judgment rule obtains camera;
If the effective information acquisition module 302 detects target face, the effective information of the target face is obtained;The voice
Trigger module 303 triggers speech recognition application service according to the effective information;The robot wake-up module 304 receives institute
It states the wake-up that speech recognition application service is generated according to the voice data and dictionary of acquisition to instruct, and is called out according to the wake-up instruction
Wake up robot.
The present embodiment triggers speech recognition application service, and further basis by obtaining the effective information of target face
The phonetic order and dictionary of acquisition wake up robot, by conditioning each other for recognition of face and speech recognition, substantially reduce and call out by mistake
Awake probability, and the learning cost of first user is altogether dispensed with, the default acoustic model of voice service business offer is provided,
The entire flow that wakes up is allowed more naturally, effectively increasing wake-up success rate.
Further, on the basis of above device embodiment, described device further includes:
Word library updating module, for being updated according to the phonetic order to the dictionary.
Further, on the basis of above device embodiment, described device further includes:
For camera to be kept to open in the dormant state, it is concurrent to obtain image according to predeterminated frequency for image collection module
It send to server;
Correspondingly, if the effective information acquisition module 302 is specifically used for detecting in described image comprising target face,
The effective information of the target face in described image is then obtained, and parameter A is sent to the robot;If detect institute
It states in image not comprising target face, then parameter B is sent to the robot.
Further, on the basis of above device embodiment, face is sentenced described in the effective information acquisition module 301
Whether disconnected rule is more than threshold value for the face size of the target face, and whether the target face is believed comprising complete face
Breath;
Wherein, when being judged according to sliding window strategy face, according to determining the probability score of each window
Whether the face size of target face is more than threshold value, whether judges the target face according to decision tree and cascade classifier strategy
Include complete face information.
Further, on the basis of above device embodiment, described device further includes:
Feedback information output module, for exporting the feedback information after robot wakes up.
Robot Rouser described in the present embodiment can be used for performing above method embodiment, principle and technology effect
Seemingly, details are not described herein again for fruit.
The apparatus embodiments described above are merely exemplary, wherein the unit illustrated as separating component can
To be or may not be physically separate, the component shown as unit may or may not be physics list
Member, you can be located at a place or can also be distributed in multiple network element.It can be selected according to the actual needs
In some or all of module realize the purpose of this embodiment scheme.Those of ordinary skill in the art are not paying creativeness
Work in the case of, you can to understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It is realized by the mode of software plus required general hardware platform, naturally it is also possible to pass through hardware.Based on such understanding, on
Technical solution is stated substantially in other words to embody the part that the prior art contributes in the form of software product, it should
Computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD, including several fingers
Order, which is used, so that computer equipment (can be personal computer, server or the network equipment etc.) performs each implementation
Method described in some parts of example or embodiment.
It should be noted that:The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although reference
The present invention is described in detail in previous embodiment, it will be understood by those of ordinary skill in the art that:It still can be right
Technical solution recorded in foregoing embodiments modifies or carries out equivalent substitution to which part technical characteristic;And this
A little modifications are replaced, and the essence of appropriate technical solution is not made to depart from the spirit and model of various embodiments of the present invention technical solution
It encloses.
Claims (10)
1. a kind of robot awakening method, which is characterized in that including:
It is detected according to the face that face judgment rule obtains camera;
If detecting target face, the effective information of the target face is obtained;
According to the effective information, speech recognition application service is triggered;
The wake-up that the speech recognition application service is generated according to the voice data and dictionary of acquisition is received to instruct, and according to described
Wake up wake instruction robot.
2. according to the method described in claim 1, it is characterized in that, the method further includes:
The dictionary is updated according to the phonetic order.
3. according to the method described in claim 1, it is characterized in that, if described detect target face, obtain the target
Before the effective information of face, further include:
Camera is kept to open in the dormant state, image is obtained according to predeterminated frequency and is sent to server;
Correspondingly, if described detect target face, the effective information of the target face is obtained, is specifically included:
If server is detected in described image comprising target face, the effective of the target face in described image is obtained
Information, and parameter A is sent to the robot;
If server is detected in described image not comprising target face, parameter B is sent to the robot.
4. according to the method described in claim 1, it is characterized in that, the face judgment rule is the face of the target face
Whether size is more than threshold value, and whether the target face includes complete face information;
Wherein, when judging according to sliding window strategy face, the target is determined according to the probability score of each window
Whether the face size of face is more than threshold value, judges whether the target face includes according to decision tree and cascade classifier strategy
Complete face information.
5. according to claim 1-4 any one of them methods, which is characterized in that described to receive the speech recognition application service
The wake-up generated according to the voice data of acquisition and dictionary instructs, and according to the wake-up wake instruction robot after, also wrap
It includes:
Export the feedback information after robot wakes up.
6. a kind of robot Rouser, which is characterized in that including:
Face detection module, the face for being obtained according to face judgment rule to camera are detected;
If effective information acquisition module for detecting target face, obtains the effective information of the target face;
Voice activated module, for according to the effective information, triggering speech recognition application service;
Robot wake-up module is generated according to the voice data and dictionary of acquisition for receiving the speech recognition application service
Instruction is waken up, and according to the wake-up wake instruction robot.
7. device according to claim 6, which is characterized in that described device further includes:
Word library updating module, for being updated according to the phonetic order to the dictionary.
8. device according to claim 6, which is characterized in that described device further includes:
Image collection module for camera to be kept to open in the dormant state, obtains image according to predeterminated frequency and is sent to
Server;
Correspondingly, if the effective information acquisition module is specifically used for detecting in described image comprising target face, obtain
The effective information of the target face in described image, and parameter A is sent to the robot;If detect described image
In not comprising target face, then parameter B is sent to the robot.
9. device according to claim 6, which is characterized in that face described in the effective information acquisition module judges rule
Then whether the face size for the target face is more than threshold value, and whether the target face includes complete face information;
Wherein, when judging according to sliding window strategy face, the target is determined according to the probability score of each window
Whether the face size of face is more than threshold value, judges whether the target face includes according to decision tree and cascade classifier strategy
Complete face information.
10. according to claim 6-9 any one of them devices, which is characterized in that described device further includes:
Feedback information output module, for exporting the feedback information after robot wakes up.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611067947.XA CN108098767A (en) | 2016-11-25 | 2016-11-25 | A kind of robot awakening method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611067947.XA CN108098767A (en) | 2016-11-25 | 2016-11-25 | A kind of robot awakening method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108098767A true CN108098767A (en) | 2018-06-01 |
Family
ID=62204664
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611067947.XA Pending CN108098767A (en) | 2016-11-25 | 2016-11-25 | A kind of robot awakening method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108098767A (en) |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109119078A (en) * | 2018-10-26 | 2019-01-01 | 北京石头世纪科技有限公司 | Automatic robot's control method, device, automatic robot and medium |
CN109343897A (en) * | 2018-08-09 | 2019-02-15 | 北京云迹科技有限公司 | Awakening method and device for robot |
CN109358751A (en) * | 2018-10-23 | 2019-02-19 | 北京猎户星空科技有限公司 | A kind of wake-up control method of robot, device and equipment |
CN109683708A (en) * | 2018-12-14 | 2019-04-26 | 北京猎户星空科技有限公司 | Smart machine control method, device, electronic equipment and storage medium |
CN109822581A (en) * | 2018-12-08 | 2019-05-31 | 浙江国自机器人技术有限公司 | Guide method for computer room robot |
CN109934205A (en) * | 2019-03-26 | 2019-06-25 | 北京儒博科技有限公司 | A kind of learning object recalls method, apparatus, robot and storage medium |
CN110032982A (en) * | 2019-04-22 | 2019-07-19 | 广东博智林机器人有限公司 | Robot leads the way method, apparatus, robot and storage medium |
CN110253595A (en) * | 2019-06-21 | 2019-09-20 | 北京猎户星空科技有限公司 | A kind of smart machine control method and device |
CN110647732A (en) * | 2019-09-16 | 2020-01-03 | 广州云从信息科技有限公司 | Voice interaction method, system, medium and device based on biological recognition characteristics |
CN110908718A (en) * | 2018-09-14 | 2020-03-24 | 上海擎感智能科技有限公司 | Face recognition activated voice navigation method, system, storage medium and equipment |
CN111063354A (en) * | 2019-10-30 | 2020-04-24 | 云知声智能科技股份有限公司 | Man-machine interaction method and device |
CN111078297A (en) * | 2018-10-18 | 2020-04-28 | 奇酷互联网络科技(深圳)有限公司 | Method for waking up voice assistant, mobile terminal and computer readable storage medium |
CN111230891A (en) * | 2018-11-29 | 2020-06-05 | 深圳市优必选科技有限公司 | Robot and voice interaction system thereof |
CN111312241A (en) * | 2020-02-10 | 2020-06-19 | 深圳创维-Rgb电子有限公司 | Unmanned shopping guide method, terminal and storage medium |
WO2020135067A1 (en) * | 2018-12-24 | 2020-07-02 | 同方威视技术股份有限公司 | Voice interaction method and device, robot, and computer readable storage medium |
CN111767793A (en) * | 2020-05-25 | 2020-10-13 | 联想(北京)有限公司 | Data processing method and device |
CN112784634A (en) * | 2019-11-07 | 2021-05-11 | 北京沃东天骏信息技术有限公司 | Video information processing method, device and system |
CN113221630A (en) * | 2021-03-22 | 2021-08-06 | 刘鸿 | Estimation method of human eye watching lens and application of estimation method in intelligent awakening |
CN113319852A (en) * | 2021-06-08 | 2021-08-31 | 北京京东乾石科技有限公司 | Device and method for managing authority of inspection robot |
CN114310909A (en) * | 2022-01-26 | 2022-04-12 | 美的集团(上海)有限公司 | Robot and control method thereof |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012100185A (en) * | 2010-11-05 | 2012-05-24 | Panasonic Corp | Video conference system, video conference method, program and recording medium |
CN104376627A (en) * | 2014-12-01 | 2015-02-25 | 江西洪都航空工业集团有限责任公司 | Intelligent ushering system |
CN104820556A (en) * | 2015-05-06 | 2015-08-05 | 广州视源电子科技股份有限公司 | Method and device for waking up voice assistant |
CN105700363A (en) * | 2016-01-19 | 2016-06-22 | 深圳创维-Rgb电子有限公司 | Method and system for waking up smart home equipment voice control device |
CN105912092A (en) * | 2016-04-06 | 2016-08-31 | 北京地平线机器人技术研发有限公司 | Voice waking up method and voice recognition device in man-machine interaction |
CN106069050A (en) * | 2016-06-22 | 2016-11-09 | 广西横县莉妃花圃农业科技有限公司 | The breeding method that a kind of Flos Gardeniae is potted plant |
CN106156762A (en) * | 2016-08-12 | 2016-11-23 | 乐视控股(北京)有限公司 | Take pictures processing method and processing device |
-
2016
- 2016-11-25 CN CN201611067947.XA patent/CN108098767A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012100185A (en) * | 2010-11-05 | 2012-05-24 | Panasonic Corp | Video conference system, video conference method, program and recording medium |
CN104376627A (en) * | 2014-12-01 | 2015-02-25 | 江西洪都航空工业集团有限责任公司 | Intelligent ushering system |
CN104820556A (en) * | 2015-05-06 | 2015-08-05 | 广州视源电子科技股份有限公司 | Method and device for waking up voice assistant |
CN105700363A (en) * | 2016-01-19 | 2016-06-22 | 深圳创维-Rgb电子有限公司 | Method and system for waking up smart home equipment voice control device |
CN105912092A (en) * | 2016-04-06 | 2016-08-31 | 北京地平线机器人技术研发有限公司 | Voice waking up method and voice recognition device in man-machine interaction |
CN106069050A (en) * | 2016-06-22 | 2016-11-09 | 广西横县莉妃花圃农业科技有限公司 | The breeding method that a kind of Flos Gardeniae is potted plant |
CN106156762A (en) * | 2016-08-12 | 2016-11-23 | 乐视控股(北京)有限公司 | Take pictures processing method and processing device |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109343897A (en) * | 2018-08-09 | 2019-02-15 | 北京云迹科技有限公司 | Awakening method and device for robot |
CN110908718A (en) * | 2018-09-14 | 2020-03-24 | 上海擎感智能科技有限公司 | Face recognition activated voice navigation method, system, storage medium and equipment |
CN111078297A (en) * | 2018-10-18 | 2020-04-28 | 奇酷互联网络科技(深圳)有限公司 | Method for waking up voice assistant, mobile terminal and computer readable storage medium |
CN109358751A (en) * | 2018-10-23 | 2019-02-19 | 北京猎户星空科技有限公司 | A kind of wake-up control method of robot, device and equipment |
CN109119078A (en) * | 2018-10-26 | 2019-01-01 | 北京石头世纪科技有限公司 | Automatic robot's control method, device, automatic robot and medium |
CN111230891B (en) * | 2018-11-29 | 2021-07-27 | 深圳市优必选科技有限公司 | Robot and voice interaction system thereof |
CN111230891A (en) * | 2018-11-29 | 2020-06-05 | 深圳市优必选科技有限公司 | Robot and voice interaction system thereof |
CN109822581A (en) * | 2018-12-08 | 2019-05-31 | 浙江国自机器人技术有限公司 | Guide method for computer room robot |
CN109683708A (en) * | 2018-12-14 | 2019-04-26 | 北京猎户星空科技有限公司 | Smart machine control method, device, electronic equipment and storage medium |
WO2020135067A1 (en) * | 2018-12-24 | 2020-07-02 | 同方威视技术股份有限公司 | Voice interaction method and device, robot, and computer readable storage medium |
CN109934205A (en) * | 2019-03-26 | 2019-06-25 | 北京儒博科技有限公司 | A kind of learning object recalls method, apparatus, robot and storage medium |
CN110032982A (en) * | 2019-04-22 | 2019-07-19 | 广东博智林机器人有限公司 | Robot leads the way method, apparatus, robot and storage medium |
CN110032982B (en) * | 2019-04-22 | 2021-05-25 | 广东博智林机器人有限公司 | Robot guiding method, device, robot and storage medium |
CN110253595B (en) * | 2019-06-21 | 2022-01-21 | 北京猎户星空科技有限公司 | Intelligent equipment control method and device |
CN110253595A (en) * | 2019-06-21 | 2019-09-20 | 北京猎户星空科技有限公司 | A kind of smart machine control method and device |
CN110647732A (en) * | 2019-09-16 | 2020-01-03 | 广州云从信息科技有限公司 | Voice interaction method, system, medium and device based on biological recognition characteristics |
CN111063354A (en) * | 2019-10-30 | 2020-04-24 | 云知声智能科技股份有限公司 | Man-machine interaction method and device |
CN111063354B (en) * | 2019-10-30 | 2022-03-25 | 云知声智能科技股份有限公司 | Man-machine interaction method and device |
CN112784634A (en) * | 2019-11-07 | 2021-05-11 | 北京沃东天骏信息技术有限公司 | Video information processing method, device and system |
CN111312241A (en) * | 2020-02-10 | 2020-06-19 | 深圳创维-Rgb电子有限公司 | Unmanned shopping guide method, terminal and storage medium |
CN111767793A (en) * | 2020-05-25 | 2020-10-13 | 联想(北京)有限公司 | Data processing method and device |
CN113221630A (en) * | 2021-03-22 | 2021-08-06 | 刘鸿 | Estimation method of human eye watching lens and application of estimation method in intelligent awakening |
CN113319852A (en) * | 2021-06-08 | 2021-08-31 | 北京京东乾石科技有限公司 | Device and method for managing authority of inspection robot |
CN113319852B (en) * | 2021-06-08 | 2023-09-26 | 北京京东乾石科技有限公司 | Inspection robot right management device and method |
CN114310909A (en) * | 2022-01-26 | 2022-04-12 | 美的集团(上海)有限公司 | Robot and control method thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108098767A (en) | A kind of robot awakening method and device | |
CN105700363B (en) | A kind of awakening method and system of smart home device phonetic controller | |
TWI646444B (en) | Method for waking up intelligent robot and intelligent robot | |
US20200228648A1 (en) | Method and apparatus for detecting abnormality of caller | |
US10482886B2 (en) | Interactive robot and human-robot interaction method | |
EP3617946B1 (en) | Context acquisition method and device based on voice interaction | |
CN106934471A (en) | It is applied to the meeting room management method and system of intelligent robot | |
CN105469065A (en) | Recurrent neural network-based discrete emotion recognition method | |
US20070156625A1 (en) | Method for movie animation | |
US20190272846A1 (en) | Smart robot and method for man-machine interaction | |
EP1416427A3 (en) | Person recognising apparatus, person recognising method & passage controller | |
US11341825B1 (en) | Implementing deterrent protocols in response to detected security events | |
CN111128157B (en) | Wake-up-free voice recognition control method for intelligent household appliance, computer readable storage medium and air conditioner | |
CN105528228A (en) | Apparatus and method for automatically closing applications | |
CN107766785A (en) | A kind of face recognition method | |
CN108198265A (en) | Attendance checking system based on voice and face composite identification | |
CN106503786B (en) | Multi-modal interaction method and device for intelligent robot | |
CN103268686A (en) | Anti-theft system based on face recognition | |
US20220084529A1 (en) | Method and apparatus for awakening wearable device | |
CN107808085A (en) | the fingerprint control method and system of intelligent terminal | |
CN111508493B (en) | Voice wake-up method and device, electronic equipment and storage medium | |
CN109377995A (en) | Method and device for controlling equipment | |
CN109286706A (en) | display device | |
CN108766431A (en) | Automatic awakening method based on voice recognition and electronic equipment | |
KR20190001067A (en) | Method and apparatus for speech recognition |
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: 20180601 |