CN109376633A - A kind of children pacify method and device - Google Patents
A kind of children pacify method and device Download PDFInfo
- Publication number
- CN109376633A CN109376633A CN201811195504.8A CN201811195504A CN109376633A CN 109376633 A CN109376633 A CN 109376633A CN 201811195504 A CN201811195504 A CN 201811195504A CN 109376633 A CN109376633 A CN 109376633A
- Authority
- CN
- China
- Prior art keywords
- children
- pacified
- strategy
- emotional information
- pacify
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06V40/174—Facial expression recognition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
-
- 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
-
- 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
- G06V40/172—Classification, e.g. identification
Abstract
This application provides a kind of children to pacify method and device, when progress children pacify, passes through the first facial image for obtaining children；First facial image is input to preparatory trained face Emotion identification model, the first emotional information of the children is obtained using the face Emotion identification model；According to first emotional information, is pacified in policy library from the mood pre-established and determine and corresponding with the emotional information pacify strategy；Strategy is pacified according to determining to pacify the children.The application can determine the current emotional of children by the first facial image of children, and be pacified automatically based on the current emotional of children children, enable to driver in driving vehicle processes, do not divert one's attention, and reduce the probability that traffic accident occurs.In addition, the embodiment of the present application can also pacify strategy in currently determining replacing when pacifying strategy and can not prove effective, the probability that children are pacified is improved.
Description
Technical field
This application involves technical field of vehicle, pacify method and device in particular to a kind of children.
Background technique
Driver is in driving vehicle processes, if children in vehicles cries and screams, driver later pacifies children, it is easy to cause
System for distraction of driver causes traffic accident.Therefore, in order to allow driver to feel at ease to drive, it is necessary to a kind of to have automatically in the car
Imitate the method for pacifying the children that cry and scream.Currently, the prior art is all to play the modes such as music by manually opening video and pacified
It comforts, it is still to be improved in terms of intelligent, hommization.
Summary of the invention
In view of this, a kind of children of being designed to provide of the embodiment of the present application pacify method and device, can pass through
The first facial image of children determines the current emotional of children, and the current emotional based on children pacifies children automatically,
It enables to driver in driving vehicle processes, is not divert one's attention, reduce the probability that traffic accident occurs.In addition, the application is real
Applying example also replacement can pacify strategy when what is currently determined pacifies strategy and can not prove effective, improve children pacified it is general
Rate.
In a first aspect, the embodiment of the present application, which provides a kind of children, pacifies method, comprising:
Obtain the first facial image of children；
First facial image is input to preparatory trained face Emotion identification model, uses the face mood
Identification model obtains the first emotional information of the children；
According to first emotional information, the determining and emotional information pair in policy library is pacified from the mood pre-established
That answers pacifies strategy；
Strategy is pacified according to determining to pacify the children.
With reference to first aspect, the embodiment of the present application provides the first possible embodiment of first aspect, wherein base
The face Emotion identification model is obtained in following methods:
Multiple bands are obtained to be in a bad mood the face sample image of label；
For face sample image described in every, the subgraph of the target site in the face sample image is extracted；
The subgraph of multiple target sites is input in first nerves network corresponding with each target site respectively, is obtained
Take the feature vector of each subgraph；
After the feature vector of each subgraph is spliced, it is input to the nervus opticus network constructed in advance and carries out feature
Study, and obtain the Emotion identification result of the face sample image；
According to the Emotion identification of the mood label of all face sample images and every face sample image as a result, to institute
It states first nerves network and the nervus opticus network is trained, obtain the face Emotion identification model.
With reference to first aspect, the embodiment of the present application provides second of possible embodiment of first aspect, wherein institute
Stating mood and pacifying policy library includes: a variety of emotional informations, corresponding with emotional information described in every kind a variety of to pacify strategy；
According to first emotional information, determining and first mood in policy library is pacified from the mood pre-established and is believed
Cease it is corresponding pacify strategy, specifically include:
According to first emotional information, determining and first feelings in policy library are pacified from the mood pre-established
The consistent emotional information of thread information, and select one kind to pacify plan from determining corresponding a variety of pacify in strategy of the emotional information
Slightly, strategy is pacified as corresponding with first emotional information.
The possible embodiment of second with reference to first aspect, the embodiment of the present application provide the third of first aspect
Possible embodiment, wherein the mood is pacified in policy library further include: target peace corresponding with emotional information described in every kind
Comfort effect；
It is described pacified according to strategy the children are pacified after, further includes:
Acquisition pacifies result to what the children were pacified；
Pacify whether result reaches the target soothing effect described in determination；
It is again corresponding from the determining emotional information if the result of pacifying is not up to the target soothing effect
A variety of pacify in strategy reselect one kind and pacify strategy, described pacify plan as corresponding with first emotional information
Slightly, and the step of strategy pacifies the children is pacified in return according to determining, until the result of pacifying reaches
The target soothing effect.
The third possible embodiment with reference to first aspect, the embodiment of the present application provide the 4th kind of first aspect
Possible embodiment, wherein the acquisition pacifies result to what the children were pacified, comprising:
In the preset time after pacifying strategy according to determining and pacifying the children, periodically acquire
The second facial image of the children；
Second facial image that each period is obtained is input to preparatory trained face Emotion identification model, makes
The children are obtained in second emotional information in the period with the face Emotion identification model；
Second emotional information that each period is obtained, is pacified as this what the children were pacified
As a result.
The third possible embodiment with reference to first aspect, the embodiment of the present application provide the 5th kind of first aspect
Possible embodiment, wherein the acquisition is pacified after result what the children were pacified, further includes:
Result and the preset target soothing effect are pacified according to described, policy library is pacified to the mood and is carried out more
Newly.
Second aspect, the embodiment of the present application provide a kind of children's pacifying device, comprising:
First facial image obtains module, for obtaining the first facial image of children；
First emotional information obtains module, for first facial image to be input to preparatory trained face mood
Identification model obtains the first emotional information of the children using the face Emotion identification model；
Tactful determining module is pacified, for pacifying policy library from the mood pre-established according to first emotional information
Middle determination is corresponding with the emotional information to pacify strategy；
Module is pacified, the children are pacified for pacifying strategy according to determining.
In conjunction with second aspect, the embodiment of the present application provides the first possible embodiment of second aspect, wherein also
It include: that face Emotion identification model obtains module；
The face Emotion identification model obtains module, for obtaining the face Emotion identification mould based on following methods
Type:
Multiple bands are obtained to be in a bad mood the face sample image of label；
For face sample image described in every, the subgraph of the target site in the face sample image is extracted；
The subgraph of multiple target sites is input in first nerves network corresponding with each target site respectively, is obtained
Take the feature vector of each subgraph；
After the feature vector of each subgraph is spliced, it is input to the nervus opticus network constructed in advance and carries out feature
Study, and obtain the Emotion identification result of the face sample image；
According to the Emotion identification of the mood label of all face sample images and every face sample image as a result, to institute
It states first nerves network and the nervus opticus network is trained, obtain the face Emotion identification model.
In conjunction with second aspect, the embodiment of the present application provides second of possible embodiment of second aspect, wherein institute
Stating mood and pacifying policy library includes: a variety of emotional informations, corresponding with emotional information described in every kind a variety of to pacify strategy；
It is described to pacify tactful determining module, it is specifically used for according to first emotional information, from the feelings pre-established
Thread pacifies the determining and consistent emotional information of the first emotional information in policy library, and corresponding from the determining emotional information
A variety of pacify in strategy select one kind to pacify strategy, pacify strategy as corresponding with first emotional information.
In conjunction with second of possible embodiment of second aspect, the embodiment of the present application provides the third of second aspect
Possible embodiment, wherein the mood is pacified in policy library further include: target peace corresponding with emotional information described in every kind
Comfort effect；
Further include: it pacifies strategy and redefines module；
The strategy of pacifying redefines module, after pacifying module, obtains the peace pacified the children
Comfort result；
Pacify whether result reaches the target soothing effect described in determination；
It is again corresponding from the determining emotional information if the result of pacifying is not up to the target soothing effect
A variety of pacify in strategy reselect one kind and pacify strategy, described pacify plan as corresponding with first emotional information
Slightly, and the step of strategy pacifies the children is pacified in return according to determining, until the result of pacifying reaches
The target soothing effect.
In conjunction with the third possible embodiment of second aspect, the embodiment of the present application provides the 4th kind of second aspect
Possible embodiment, wherein the strategy of pacifying redefines module, specifically using following step obtain to the children into
What row was pacified pacifies result:
In the preset time after pacifying strategy according to determining and pacifying the children, periodically acquire
The second facial image of the children；
Second facial image that each period is obtained is input to preparatory trained face Emotion identification model, makes
The children are obtained in second emotional information in the period with the face Emotion identification model；
Second emotional information that each period is obtained, is pacified as this what the children were pacified
As a result.
In conjunction with the third possible embodiment of second aspect, the embodiment of the present application provides the 5th kind of second aspect
Possible embodiment, wherein further include: mood pacifies policy library update module；
The mood pacifies policy library update module, for obtain to the children pacified pacify result it
Afterwards,
Result and the preset target soothing effect are pacified according to described, policy library is pacified to the mood and is carried out more
Newly.
Children provided by the embodiments of the present application pacify method and device, when progress children pacify, pass through acquisition
The first facial image of children；First facial image is input to preparatory trained face Emotion identification model, is used
The face Emotion identification model obtains the first emotional information of the children；According to first emotional information, built from advance
Vertical mood, which is pacified, to be determined in policy library and corresponding with the emotional information pacifies strategy；It is right that strategy is pacified according to determining
The children pacify.The application can determine the current emotional of children by the first facial image of children, and be based on youngster
Virgin current emotional pacifies children automatically, enables to driver in driving vehicle processes, is not divert one's attention, and reduces and hands over
Interpreter thus occur probability.
In addition, the embodiment of the present application can also pacify strategy in currently determining replacing when pacifying strategy and can not prove effective,
Improve the probability that children are pacified.
To enable the above objects, features, and advantages of the application to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only some embodiments of the application, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 shows the flow chart that a kind of children provided by the embodiment of the present application pacify method；
Fig. 2 shows children provided by the embodiment of the present application to pacify in method, obtains the stream of face Emotion identification model
Cheng Tu；
Fig. 3 shows children provided by the embodiment of the present application and pacifies in method, to first nerves network and nervus opticus
The flow chart that network is trained；
Fig. 4 shows children provided by the embodiment of the present application and pacifies in method, to first nerves network and nervus opticus
The flow chart of operation is compared when network is trained；
Fig. 5 shows children provided by the embodiment of the present application and pacifies in method, the process pacified again children
Figure；
Fig. 6 shows children provided by the embodiment of the present application and pacifies in method, and acquisition is pacified what children were pacified
As a result flow chart；
Fig. 7 shows a kind of structural schematic diagram of children's pacifying device provided by the embodiment of the present application；
Fig. 8 shows a kind of structural schematic diagram of computer equipment provided by the embodiment of the present application.
Specific embodiment
To keep the purposes, technical schemes and advantages of the embodiment of the present application clearer, below in conjunction with the embodiment of the present application
Middle attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only
It is some embodiments of the present application, instead of all the embodiments.The application being usually described and illustrated herein in the accompanying drawings is real
The component for applying example can be arranged and be designed with a variety of different configurations.Therefore, below to the application's provided in the accompanying drawings
The detailed description of embodiment is not intended to limit claimed scope of the present application, but is merely representative of the selected reality of the application
Apply example.Based on embodiments herein, those skilled in the art institute obtained without making creative work
There are other embodiments, shall fall in the protection scope of this application.
Driver is in driving vehicle processes, if children in vehicles cries and screams, driver later pacifies children, it is easy to cause
System for distraction of driver causes traffic accident.Therefore, in order to allow driver to feel at ease to drive, it is necessary to a kind of to have automatically in the car
Imitate the method for pacifying the children that cry and scream.Currently, in the prior art, needing, which just can know that by the manual feedback of interior parent, pacifies
Whether the mode of children is effective, therefore scheme in the related technology is still incomplete, still needs in terms of intelligent, hommization
It improves.Based on this, a kind of children provided by the embodiments of the present application pacify method and device, can pass through artificial intelligence technology pair
Children are pacified automatically, and are constantly automatically updated and pacified strategy, and more intelligentized level is reached, so that driver is driving
In vehicle processes, do not divert one's attention, reduces the probability that traffic accident occurs.
For convenient for understanding the present embodiment, first to a kind of children disclosed in the embodiment of the present application pacify method into
Row is discussed in detail.
Shown in Figure 1, children's method of pacifying includes S101~S104 provided by the embodiment of the present application:
S101: the first facial image of children is obtained.
Herein, the first facial image is the facial image before pacifying children.
When specific implementation, the first facial image of children is periodically obtained in real time by camera.It is every to obtain one
The first facial image is opened it is necessary to detect the emotional information of a current child.
S102: the first facial image is input to preparatory trained face Emotion identification model, is known using face mood
Other model obtains the first emotional information of children.
Herein, shown in Figure 2, the embodiment of the present application is based on following methods and obtains face Emotion identification model:
S201: multiple bands are obtained and are in a bad mood the face sample image of label.
S202: it is directed to every face sample image, extracts the subgraph of the target site in the face sample image.
Herein, target site includes: at least one of eyes, mouth, forehead, cheek；
For example, extracting the subgraph of the target site in face sample image using image Segmentation Technology.
S203: first nerves network corresponding with each target site is input to the subgraph of multiple target sites respectively
In, obtain the feature vector of each subgraph.
Herein, the corresponding first nerves network of each target site, each first nerves network is for extracting each mesh
Mark the feature vector of the subgraph at position.
For example, first nerves network can for convolutional neural networks (Convolutional Neural Network,
CNN), Scale invariant features transform (Scale-invariant feature transform, SIFT) algorithm etc..
S204: after the feature vector of each subgraph is spliced, be input to the nervus opticus network that constructs in advance into
Row feature learning, and obtain the Emotion identification result of the face sample image.
Optionally, connecting method can be successively connecting method.The successively connecting method refers to all subgraphs
Feature vector is successively stitched together, and forms a feature vector.
Such as the feature vector of each subgraph be respectively (0.1,0.2,0.3), (0.4,0.5,0.6), (0.7,0.8,
0.9) feature vector, then obtained by successively connecting method is (0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9).
Herein, nervus opticus network is used to carry out feature learning to spliced feature vector, obtains the face sample graph
The Emotion identification result of picture.
For example, nervus opticus network can be convolutional neural networks, reverse transmittance nerve network (Back Propagation
Neural Network, BP neural network), support vector machines (Support Vector Machine, SVM) etc..
S205: according to the mood label of all face sample images and the Emotion identification knot of every face sample image
Fruit is trained first nerves network and nervus opticus network, obtains face Emotion identification model.
For example, mood label may include: sobbing, agitation, gloomy, glad, tranquil etc..
Shown in Figure 3 when specific implementation, the embodiment of the present application is by following step to first nerves network and the
Two neural networks are trained:
S301: according to the mood label of all face sample images and the Emotion identification knot of every face sample image
Fruit carries out epicycle training to first nerves network and nervus opticus network.
Specifically, shown in Figure 4, it can be by executing following comparison operating procedure, until every face sample image
Emotion identification result it is consistent with the mood label of every face sample image, terminate to first nerves network and nervus opticus net
The epicycle training of network:
S401: the Emotion identification result of every face sample image and the mood label of every face sample image are carried out
It compares.
S402: the mood label of Emotion identification result and every face sample image for every face sample image is not
Unanimous circumstances adjust the parameter of first nerves network and nervus opticus network.
S403: the new spy of the subgraph of each target site is extracted again using the first nerves network after adjusting parameter
Vector is levied, after again being spliced the new feature vector of each subgraph, is input to the nervus opticus network constructed in advance
Feature learning is carried out, and obtains the new Emotion identification result of the face sample image；And it executes compare operation again.
Finish to after the training of the epicycle of first nerves network and nervus opticus network, needing to first nerves network and the
Two neural networks carry out more wheel training, until training result meets preset training error standard.
S302: according to the mood label of all face sample images and the Emotion identification knot of every face sample image
Fruit carries out more wheel training to first nerves network and nervus opticus network, obtains face Emotion identification model.
After the first emotional information for obtaining children through the above steps, children provided by the embodiment of the present application pacify method
Further include S103~S104:
S103: it according to the first emotional information, pacifies in policy library and determines and institute's the first mood letter from the mood pre-established
It ceases and corresponding pacifies strategy.
Herein, it includes: a variety of emotional informations that mood, which pacifies policy library, corresponding with every kind of emotional information a variety of to pacify plan
Slightly；
Such as: a variety of emotional informations include: sobbing, agitation, gloomy, glad, tranquil etc.；
Such as the mood bad for sobbing, agitation, gloomy etc., mood, which is pacified, corresponding in policy library a variety of pacifies strategy
Include: the nursery rhymes for playing children and liking, play the cartoon that children like, play the music that children like, plays children and like
Story, control interior certain controlled toys and act, such as controlled down toy or drum-shaped rattle etc.；Herein, by
In nursery rhymes, cartoon, music, story all there are many kinds of, each can pacify strategy as one kind.Or
Each nursery rhymes, each cartoon, each music, each story etc. that respectively children like add at least one mark
Label pacify strategy using these labels composition, then determine the corresponding nursery rhymes of the label, cartoon, sound according to determining label
Pleasure, story etc..
Optionally, different strategies of pacifying has different weights, and weight is preferentially executed when pacifying children
It is worth and higher pacifies strategy.
When specific implementation, according to the first emotional information, pacifies in policy library and determine and the from the mood pre-established
The consistent emotional information of one emotional information, and select one kind to pacify plan from determining corresponding a variety of pacify in strategy of emotional information
Slightly, strategy is pacified as corresponding with the first emotional information.
S104: children are pacified according to determining strategy of pacifying.
Herein, mood is pacified in policy library further include: target soothing effect corresponding with every kind of emotional information.
Such as the mood bad for sobbing, agitation, gloomy etc., corresponding target soothing effect can be to pacify children
To calmness or glad mood etc..
It is shown in Figure 5, according to pacify strategy children are pacified after, by following step to children carry out again
It pacifies:
S501: acquisition pacifies result to what children were pacified.
It is shown in Figure 6 when specific implementation, result is pacified to what children were pacified by following step acquisition:
S601: it pacifies in the preset time after strategy pacifies children, periodically acquires according to determining
The second virgin facial image.
It should be noted that when, it is pacified after strategy pacifies children according to determining, it may be in a period of time
Just play the effect pacified later, therefore, it is necessary to according to it is determining pacify default after strategy pacifies children when
In, periodically acquire the second facial image of children.For example, can be 2 minutes, 5 minutes etc. in preset time.
S602: the second facial image that each period is obtained is input to preparatory trained face Emotion identification model,
Children are obtained in second emotional information in the period using face Emotion identification model.
S603: the second emotional information that each period is obtained pacifies result to what children were pacified as this.
By step S501 obtain to children pacified pacify result after, execute following step:
S502: determination pacifies whether result reaches target soothing effect.
When specific implementation, judgement pacify result whether reach mood pacify it is consistent with the first emotional information in policy library
The corresponding target soothing effect of emotional information.Such as when target soothing effect is tranquil or glad, judgement pacifies result (i.e.
Second emotional information) whether be tranquil or glad, if it is judged that be it is yes, then pacify result and reached target soothing effect,
If it is judged that be it is no, then pacify result and do not reach target soothing effect.
S503: again corresponding a variety of from determining emotional information if pacifying result miss the mark soothing effect
It pacifies in strategy and reselects one kind and pacify strategy, pacify strategy as corresponding with the first emotional information, and return according to really
Fixed pacifies the step of strategy pacifies children, reaches target soothing effect until pacifying result.
Target soothing effect can be reached due to cannot be guaranteed once pacify, it is therefore desirable to pacify strategy by changing
Children are repeatedly pacified, until children are pacified success, that is, result is pacified and reaches target soothing effect.
Optionally, it is pacified after result by step S501 acquisition what children were pacified, further includes: tied according to pacifying
Fruit and preset target soothing effect, pacify policy library to mood and are updated.
For example, if by one kind pacify strategy children are pacified after, corresponding result of pacifying does not reach mesh
Soothing effect is marked, illustrates that this is pacified strategy and pacifies no effect to the first emotional information of children, then reduces this and pacify strategy
Weight；If pacified after strategy pacifies children by one kind, it is corresponding pacify result and reached target pacify effect
Fruit illustrates that this is pacified strategy and effectively then increases the weight for pacifying strategy to the pacifying for the first emotional information of children.
Change every kind of weight for pacifying strategy in this way, when pacifying again children afterwards, according to the of children
One emotional information, so that it may be pacified from mood and preferentially choose the biggish peace of weight corresponding with first emotional information in policy library
Strategy is comforted to pacify children.
It should be noted that it is ongoing for pacifying the process that policy library is updated to mood, because children are not
Music that same time may like or cartoon etc. are changing, and cause to pacify children and effectively pacify strategy also continuous
Variation.
Children provided by the embodiments of the present application pacify method, when carrying out children and pacifying, by obtain children the
One facial image；First facial image is input to preparatory trained face Emotion identification model, uses face Emotion identification
The first emotional information of model acquisition children；According to the first emotional information, pacifies in policy library and determine from the mood pre-established
It is corresponding with emotional information to pacify strategy；Children are pacified according to determining strategy of pacifying.The application can pass through children
The first facial image determine the current emotional of children, and children are pacified automatically based on the current emotional of children, can
So that driver is not divert one's attention in driving vehicle processes, the probability that traffic accident occurs is reduced.
In addition, the embodiment of the present application can also pacify strategy in currently determining replacing when pacifying strategy and can not prove effective,
Improve the probability that children are pacified.
Another embodiment of the application additionally provides the specific embodiment that a kind of children pacify method:
Camera is installed on chairs in rear rows of vehicles, camera is for obtaining the first of the children to sit in the back row on seat
Face image.This camera band wireless transport module (WIFI) or wire transmission module, can be by collected first facial image
It is transferred to vehicle centre console multimedia vehicle system；Multimedia vehicle system Built-in Image processing function, by training in advance
Face Emotion identification model, obtain the first emotional information of children；If the first emotional information is to cry, is irritated, gloomy etc.
Bad mood then pacifies mode into the children of vehicle system.Interior artificial intelligence machine learns engine from pre-establishing
Mood, which is pacified, to be determined in policy library and corresponding with emotional information pacifies strategy；Children are pacified according to determining strategy of pacifying
It comforts.When pacifying, children music, the story etc. that like can be played by the multimedia play equipment of vehicle self-carrying, it can also be with
The cartoon etc. that children like, or control are played by the video playback apparatus (such as tablet computer etc.) being mounted on back seat
The interior certain controlled toys of system act, such as controlled down toy or drum-shaped rattle etc..Herein, if being mounted with to put down
When plate computer, tablet computer can also act as camera.
After pacifying children, the second facial image of children is obtained by camera；By collected second
Facial image is transferred to vehicle centre console multimedia vehicle system, and multimedia vehicle system passes through preparatory trained face mood
Identification model obtains the second emotional information of children, and obtains and pacify result to what children were pacified；Pass through interior artificial intelligence
Energy machine learning engine, determination pacify whether result reaches target soothing effect；If pacifying result miss the mark pacifies effect
Fruit then reselects one kind and pacifies strategy from corresponding a variety of pacify in strategy of determining emotional information again, as with first
Emotional information is corresponding to pacify strategy, and returns and pacify the step of strategy pacifies children according to determining, until pacifying
As a result reach target soothing effect.Each acquisition children are pacified pacify result after, interior artificial intelligence machine
Learn engine according to result and preset target soothing effect is pacified, policy library is pacified to mood and is updated.
Specific embodiment provided by the present application can by artificial intelligence technology according to the emotional information of children by vehicle from
It is dynamic to pacify mode into children, children are pacified, and constantly automatically update and pacify strategy automatically, reaches more intelligentized
Level reduces the probability that traffic accident occurs so that driver is not divert one's attention in driving vehicle processes.
Based on the same inventive concept, it is additionally provided in the embodiment of the present application and pacifies the corresponding children side of pacifying of method with children
Subtraction unit, since the principle that the device in the embodiment of the present application solves the problems, such as pacifies method phase with the above-mentioned children of the embodiment of the present application
Seemingly, therefore the implementation of device may refer to the implementation of method, and overlaps will not be repeated.
It is shown in Figure 7, children's pacifying device provided by the embodiment of the present application, comprising:
First facial image obtains module 71, for obtaining the first facial image of children；
First emotional information obtains module 72, knows for the first facial image to be input to trained face mood in advance
Other model obtains the first emotional information of children using face Emotion identification model；
Tactful determining module 73 is pacified, for being pacified in policy library from the mood pre-established according to the first emotional information
Determination is corresponding with emotional information to pacify strategy；
Module 74 is pacified, for pacifying according to determining strategy of pacifying children.
Optionally, children's pacifying device provided by the embodiment of the present application, further includes: face Emotion identification model obtains mould
Block 75；
Face Emotion identification model obtains module 75, for obtaining face Emotion identification model based on following methods:
Multiple bands are obtained to be in a bad mood the face sample image of label；
For every face sample image, the subgraph of the target site in the face sample image is extracted；
The subgraph of multiple target sites is input in first nerves network corresponding with each target site respectively, is obtained
Take the feature vector of each subgraph；
After the feature vector of each subgraph is spliced, it is input to the nervus opticus network constructed in advance and carries out feature
Study, and obtain the Emotion identification result of the face sample image；
According to the Emotion identification of the mood label of all face sample images and every face sample image as a result, to
One neural network and nervus opticus network are trained, and obtain face Emotion identification model.
Optionally, it includes: a variety of feelings that the mood in children's pacifying device provided by the embodiment of the present application, which pacifies policy library,
Thread information, it is corresponding with every kind of emotional information a variety of to pacify strategy；
Optionally, tactful determining module 73 is pacified, is specifically used for according to the first emotional information, from the mood peace pre-established
It comforts in policy library determining with the consistent emotional information of the first emotional information, and a variety of pacifies plan from determining emotional information is corresponding
It selects one kind to pacify strategy in slightly, pacifies strategy as corresponding with the first emotional information.
Optionally, the mood in children's pacifying device provided by the embodiment of the present application is pacified in policy library further include: with
The corresponding target soothing effect of every kind of emotional information；
Optionally, children's pacifying device provided by the embodiment of the present application further include: pacify strategy and redefine module 76；
It pacifies strategy and redefines module 76, after pacifying module 74, acquisition pacifies knot to what children were pacified
Fruit；
Determination pacifies whether result reaches target soothing effect；
If pacifying result miss the mark soothing effect, a variety of plan is pacified from determining emotional information is corresponding again
One kind is reselected in slightly and pacifies strategy, pacifies strategy as corresponding with the first emotional information, and return according to determining peace
The step of strategy pacifies children is comforted, reaches target soothing effect until pacifying result.
Optionally, it pacifies strategy and redefines module 76, it is specific that the peace pacified children is obtained using following step
Comfort result:
It is pacified in the preset time after strategy pacifies children according to determining, periodically acquires the of children
Two facial images；
The second facial image that each period is obtained is input to preparatory trained face Emotion identification model, user
Face Emotion identification model obtains children in second emotional information in the period；
The second emotional information that each period is obtained pacifies result to what children were pacified as this.
Optionally, children's pacifying device provided by the embodiment of the present application further include: mood pacifies policy library update module
77；
Mood pacifies policy library update module 77, after pacifying result for what is pacified in acquisition children,
According to result and preset target soothing effect is pacified, policy library is pacified to mood and is updated.
Children's pacifying device provided by the embodiments of the present application, when carrying out children and pacifying, by obtain children the
One facial image；First facial image is input to preparatory trained face Emotion identification model, uses face Emotion identification
The first emotional information of model acquisition children；According to the first emotional information, pacifies in policy library and determine from the mood pre-established
It is corresponding with emotional information to pacify strategy；Children are pacified according to determining strategy of pacifying.The application can pass through children
The first facial image determine the current emotional of children, and children are pacified automatically based on the current emotional of children, can
So that driver is not divert one's attention in driving vehicle processes, the probability that traffic accident occurs is reduced.
In addition, the embodiment of the present application can also pacify strategy in currently determining replacing when pacifying strategy and can not prove effective,
Improve the probability that children are pacified.
The embodiment of the present application also provides a kind of computer readable storage medium, stored on the computer readable storage medium
There is computer program, which executes the step of above-mentioned children pacify method when being run by processor.
Specifically, which can be general storage medium, such as mobile disk, hard disk, on the storage medium
Computer program when being run, be able to carry out above-mentioned children and pacify method, so as to pass through the first facial image of children
It determines the current emotional of children, and children is pacified automatically based on the current emotional of children, driver is enabled to drive
It sails in vehicle processes, is not divert one's attention, reduce the probability that traffic accident occurs.
In addition, the embodiment of the present application can also pacify strategy in currently determining replacing when pacifying strategy and can not prove effective,
Improve the probability that children are pacified.
Method is pacified corresponding to the children in Fig. 1, the embodiment of the present application also provides a kind of computer equipments, such as Fig. 8 institute
Show, which includes memory 1000, processor 2000 and be stored on the memory 1000 and can be on the processor 2000
The computer program of operation, wherein above-mentioned processor 2000 realizes that above-mentioned children pacify method when executing above-mentioned computer program
The step of.
Specifically, above-mentioned memory 1000 and processor 2000 can be general memory and processor, not do here
It is specific to limit, when the computer program of 2000 run memory 1000 of processor storage, it is able to carry out the above-mentioned children side of pacifying
Method determines the current emotional of children so as to the first facial image by children, and based on the current emotional of children to youngster
Child is pacified automatically, is enabled to driver in driving vehicle processes, is not divert one's attention, and the general of traffic accident generation is reduced
Rate.
In addition, the embodiment of the present application can also pacify strategy in currently determining replacing when pacifying strategy and can not prove effective,
Improve the probability that children are pacified.
Children provided by the embodiment of the present application pacify the computer program product of method and device, including store journey
The computer readable storage medium of sequence code, the instruction that said program code includes can be used for executing institute in previous methods embodiment
The method stated, specific implementation can be found in embodiment of the method, and details are not described herein.
In all examples being illustrated and described herein, any occurrence should be construed as merely illustratively, without
It is as limitation, therefore, other examples of exemplary embodiment can have different values.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description
It with the specific work process of device, can refer to corresponding processes in the foregoing method embodiment, details are not described herein.In the application
In provided several embodiments, it should be understood that disclosed systems, devices and methods, it can be real by another way
It is existing.The apparatus embodiments described above are merely exemplary.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in the executable non-volatile computer-readable storage medium of a processor.Based on this understanding, the application
Technical solution substantially the part of the part that contributes to existing technology or the technical solution can be with software in other words
The form of product embodies, which is stored in a storage medium, including some instructions use so that
One computer equipment (can be personal computer, server or the network equipment etc.) executes each embodiment institute of the application
State all or part of the steps of method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (Read-Only
Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. is various to deposit
Store up the medium of program code.
Finally, it should be noted that embodiment described above, the only specific embodiment of the application, to illustrate the application
Technical solution, rather than its limitations, the protection scope of the application is not limited thereto, although with reference to the foregoing embodiments to this Shen
It please be described in detail, those skilled in the art should understand that: anyone skilled in the art
Within the technical scope of the present application, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of the embodiment of the present application technical solution, should all cover the protection in the application
Within the scope of.Therefore, the protection scope of the application shall be subject to the protection scope of the claim.
Claims (12)
1. a kind of children pacify method characterized by comprising
Obtain the first facial image of children；
First facial image is input to preparatory trained face Emotion identification model, uses the face Emotion identification
Model obtains the first emotional information of the children；
According to first emotional information, it is corresponding with the emotional information that determination in policy library is pacified from the mood pre-established
Pacify strategy；
Strategy is pacified according to determining to pacify the children.
2. the method according to claim 1, wherein obtaining the face Emotion identification mould based on following methods
Type:
Multiple bands are obtained to be in a bad mood the face sample image of label；
For face sample image described in every, the subgraph of the target site in the face sample image is extracted；
The subgraph of multiple target sites is input in first nerves network corresponding with each target site respectively, is obtained each
The feature vector of a subgraph；
After the feature vector of each subgraph is spliced, it is input to the nervus opticus network constructed in advance and carries out characterology
It practises, and obtains the Emotion identification result of the face sample image；
According to the Emotion identification of the mood label of all face sample images and every face sample image as a result, to described
One neural network and the nervus opticus network are trained, and obtain the face Emotion identification model.
3. the method according to claim 1, wherein it includes: a variety of emotional informations that the mood, which pacifies policy library,
It is corresponding with emotional information described in every kind a variety of to pacify strategy；
According to first emotional information, determining and first emotional information pair in policy library is pacified from the mood pre-established
That answers pacifies strategy, specifically includes:
According to first emotional information, determining and first mood in policy library is pacified from the mood pre-established and is believed
Consistent emotional information is ceased, and selects one kind to pacify strategy from determining corresponding a variety of pacify in strategy of the emotional information,
Strategy is pacified as corresponding with first emotional information.
4. according to the method described in claim 3, it is characterized in that, the mood is pacified in policy library further include: with every kind of institute
State the corresponding target soothing effect of emotional information；
It is described pacified according to strategy the children are pacified after, further includes:
Acquisition pacifies result to what the children were pacified；
Pacify whether result reaches the target soothing effect described in determination；
If the result of pacifying is not up to the target soothing effect, again corresponding more from the determining emotional information
Kind pacify in strategy and to reselect one kind and pacify strategy, as it is corresponding with first emotional information it is described pacify strategy, and
The step of strategy pacifies the children, is pacified in return according to determining, until the result of pacifying reaches the mesh
Mark soothing effect.
5. according to the method described in claim 4, it is characterized in that, the acquisition pacifies knot to what the children were pacified
Fruit, comprising:
In the preset time after pacifying strategy according to determining and pacifying the children, periodically acquire described
The second facial image of children；
Second facial image that each period is obtained is input to preparatory trained face Emotion identification model, uses institute
It states face Emotion identification model and obtains the children in second emotional information in the period；
Second emotional information that each period is obtained, pacifies knot to what the children were pacified as this
Fruit.
6. according to the method described in claim 4, it is characterized in that, the acquisition pacifies result to what the children were pacified
Later, further includes:
Result and the preset target soothing effect are pacified according to described, policy library is pacified to the mood and is updated.
7. a kind of children's pacifying device characterized by comprising
First facial image obtains module, for obtaining the first facial image of children；
First emotional information obtains module, for first facial image to be input to preparatory trained face Emotion identification
Model obtains the first emotional information of the children using the face Emotion identification model；
Tactful determining module is pacified, for being pacified in policy library really from the mood pre-established according to first emotional information
It is calmly corresponding with the emotional information to pacify strategy；
Module is pacified, the children are pacified for pacifying strategy according to determining.
8. device according to claim 7, which is characterized in that further include: face Emotion identification model obtains module；
The face Emotion identification model obtains module, for obtaining the face Emotion identification model based on following methods:
Multiple bands are obtained to be in a bad mood the face sample image of label；
For face sample image described in every, the subgraph of the target site in the face sample image is extracted；
The subgraph of multiple target sites is input in first nerves network corresponding with each target site respectively, is obtained each
The feature vector of a subgraph；
After the feature vector of each subgraph is spliced, it is input to the nervus opticus network constructed in advance and carries out characterology
It practises, and obtains the Emotion identification result of the face sample image；
According to the Emotion identification of the mood label of all face sample images and every face sample image as a result, to described
One neural network and the nervus opticus network are trained, and obtain the face Emotion identification model.
9. device according to claim 7, which is characterized in that it includes: a variety of emotional informations that the mood, which pacifies policy library,
It is corresponding with emotional information described in every kind a variety of to pacify strategy；
It is described to pacify tactful determining module, it is specifically used for according to first emotional information, from the mood peace pre-established
The determining and consistent emotional information of the first emotional information in policy library is comforted, and corresponding more from the determining emotional information
Kind, which is pacified in strategy, selects one kind to pacify strategy, pacifies strategy as corresponding with first emotional information.
10. device according to claim 9, which is characterized in that the mood is pacified in policy library further include: with every kind of institute
State the corresponding target soothing effect of emotional information；
Further include: it pacifies strategy and redefines module；
The strategy of pacifying redefines module, and after pacifying module, acquisition pacifies knot to what the children were pacified
Fruit；
Pacify whether result reaches the target soothing effect described in determination；
If the result of pacifying is not up to the target soothing effect, again corresponding more from the determining emotional information
Kind pacify in strategy and to reselect one kind and pacify strategy, as it is corresponding with first emotional information it is described pacify strategy, and
The step of strategy pacifies the children, is pacified in return according to determining, until the result of pacifying reaches the mesh
Mark soothing effect.
11. device according to claim 10, which is characterized in that the strategy of pacifying redefines module, specific to use
Following step acquisition pacifies result to what the children were pacified:
In the preset time after pacifying strategy according to determining and pacifying the children, periodically acquire described
The second facial image of children；
Second facial image that each period is obtained is input to preparatory trained face Emotion identification model, uses institute
It states face Emotion identification model and obtains the children in second emotional information in the period；
Second emotional information that each period is obtained, pacifies knot to what the children were pacified as this
Fruit.
12. device according to claim 10, which is characterized in that further include: mood pacifies policy library update module；
The mood pacifies policy library update module, after pacifying result for what is pacified in acquisition the children,
Result and the preset target soothing effect are pacified according to described, policy library is pacified to the mood and is updated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811195504.8A CN109376633A (en) | 2018-10-15 | 2018-10-15 | A kind of children pacify method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811195504.8A CN109376633A (en) | 2018-10-15 | 2018-10-15 | A kind of children pacify method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109376633A true CN109376633A (en) | 2019-02-22 |
Family
ID=65397802
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811195504.8A Pending CN109376633A (en) | 2018-10-15 | 2018-10-15 | A kind of children pacify method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109376633A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110237372A (en) * | 2019-07-24 | 2019-09-17 | 南阳医学高等专科学校第一附属医院 | Children's Intelligent Atomizer |
| CN110837813A (en) * | 2019-11-14 | 2020-02-25 | 爱驰汽车有限公司 | Environment equipment control method and device, electronic equipment and storage medium |
| CN110944149A (en) * | 2019-11-12 | 2020-03-31 | 上海博泰悦臻电子设备制造有限公司 | Child care system and method for vehicle |
| CN111203888A (en) * | 2020-02-24 | 2020-05-29 | 湘潭大学 | Baby service robot control system and operation method |
| CN111353401A (en) * | 2020-02-24 | 2020-06-30 | 湘潭大学 | Visual sense and emotion module of baby service robot |
| CN111741116A (en) * | 2020-06-28 | 2020-10-02 | 海尔优家智能科技（北京）有限公司 | Emotion interaction method and device, storage medium and electronic device |
| CN112382311A (en) * | 2020-11-16 | 2021-02-19 | 谭昊玥 | Infant crying intention identification method and device based on hybrid neural network |
| CN113657134A (en) * | 2020-05-12 | 2021-11-16 | 北京地平线机器人技术研发有限公司 | Voice playing method and device, storage medium and electronic equipment |
| CN113657134B (en) * | 2020-05-12 | 2024-04-23 | 北京地平线机器人技术研发有限公司 | Voice playing method and device, storage medium and electronic equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140341422A1 (en) * | 2013-05-10 | 2014-11-20 | Tencent Technology (Shenzhen) Company Limited | Systems and Methods for Facial Property Identification |
| CN106372622A (en) * | 2016-09-30 | 2017-02-01 | 北京奇虎科技有限公司 | Facial expression classification method and device |
| CN107243905A (en) * | 2017-06-28 | 2017-10-13 | 重庆柚瓣科技有限公司 | Mood Adaptable System based on endowment robot |
| CN206579503U (en) * | 2017-03-14 | 2017-10-24 | 何瑶嘉 | A kind of child safety seat with playing function |
| CN107633203A (en) * | 2017-08-17 | 2018-01-26 | 平安科技（深圳）有限公司 | Facial emotions recognition methods, device and storage medium |
| CN107678291A (en) * | 2017-10-31 | 2018-02-09 | 珠海格力电器股份有限公司 | The control method and device of indoor environment |
| CN108001451A (en) * | 2016-10-27 | 2018-05-08 | 福特全球技术公司 | Adaptive apparatus and method are carried out to driver status for vehicle |
| CN108564673A (en) * | 2018-04-13 | 2018-09-21 | 北京师范大学 | A kind of check class attendance method and system based on Global Face identification |
-
2018
- 2018-10-15 CN CN201811195504.8A patent/CN109376633A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140341422A1 (en) * | 2013-05-10 | 2014-11-20 | Tencent Technology (Shenzhen) Company Limited | Systems and Methods for Facial Property Identification |
| CN106372622A (en) * | 2016-09-30 | 2017-02-01 | 北京奇虎科技有限公司 | Facial expression classification method and device |
| CN108001451A (en) * | 2016-10-27 | 2018-05-08 | 福特全球技术公司 | Adaptive apparatus and method are carried out to driver status for vehicle |
| CN206579503U (en) * | 2017-03-14 | 2017-10-24 | 何瑶嘉 | A kind of child safety seat with playing function |
| CN107243905A (en) * | 2017-06-28 | 2017-10-13 | 重庆柚瓣科技有限公司 | Mood Adaptable System based on endowment robot |
| CN107633203A (en) * | 2017-08-17 | 2018-01-26 | 平安科技（深圳）有限公司 | Facial emotions recognition methods, device and storage medium |
| CN107678291A (en) * | 2017-10-31 | 2018-02-09 | 珠海格力电器股份有限公司 | The control method and device of indoor environment |
| CN108564673A (en) * | 2018-04-13 | 2018-09-21 | 北京师范大学 | A kind of check class attendance method and system based on Global Face identification |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110237372A (en) * | 2019-07-24 | 2019-09-17 | 南阳医学高等专科学校第一附属医院 | Children's Intelligent Atomizer |
| CN110237372B (en) * | 2019-07-24 | 2021-11-09 | 南阳医学高等专科学校第一附属医院 | Intelligent atomizer for children |
| CN110944149A (en) * | 2019-11-12 | 2020-03-31 | 上海博泰悦臻电子设备制造有限公司 | Child care system and method for vehicle |
| CN110837813A (en) * | 2019-11-14 | 2020-02-25 | 爱驰汽车有限公司 | Environment equipment control method and device, electronic equipment and storage medium |
| CN111353401B (en) * | 2020-02-24 | 2021-07-02 | 湘潭大学 | Visual and emotional system of baby service robot |
| CN111203888A (en) * | 2020-02-24 | 2020-05-29 | 湘潭大学 | Baby service robot control system and operation method |
| CN111353401A (en) * | 2020-02-24 | 2020-06-30 | 湘潭大学 | Visual sense and emotion module of baby service robot |
| CN113657134A (en) * | 2020-05-12 | 2021-11-16 | 北京地平线机器人技术研发有限公司 | Voice playing method and device, storage medium and electronic equipment |
| CN113657134B (en) * | 2020-05-12 | 2024-04-23 | 北京地平线机器人技术研发有限公司 | Voice playing method and device, storage medium and electronic equipment |
| CN111741116A (en) * | 2020-06-28 | 2020-10-02 | 海尔优家智能科技（北京）有限公司 | Emotion interaction method and device, storage medium and electronic device |
| CN111741116B (en) * | 2020-06-28 | 2023-08-22 | 海尔优家智能科技（北京）有限公司 | Emotion interaction method and device, storage medium and electronic device |
| CN112382311A (en) * | 2020-11-16 | 2021-02-19 | 谭昊玥 | Infant crying intention identification method and device based on hybrid neural network |
| CN112382311B (en) * | 2020-11-16 | 2022-08-19 | 谭昊玥 | Infant crying intention identification method and device based on hybrid neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109376633A (en) | A kind of children pacify method and device | |
| US11908060B2 (en) | System for neurobehaviorual animation | |
| Ye et al. | Automated vehicle’s behavior decision making using deep reinforcement learning and high-fidelity simulation environment | |
| Yannakakis | Game AI revisited | |
| US20220189093A1 (en) | Interaction based on in-vehicle digital persons | |
| US11869237B2 (en) | Modular hierarchical vision system of an autonomous personal companion | |
| US20220224963A1 (en) | Trip-configurable content | |
| JP2022524944A (en) | Interaction methods, devices, electronic devices and storage media | |
| Saldien et al. | A motion system for social and animated robots | |
| US11402975B2 (en) | Apparatus and method for providing interactive content | |
| US10108855B2 (en) | Fitness device-based simulator and simulation method using the same | |
| US20230009454A1 (en) | Digital character with dynamic interactive behavior | |
| Brock et al. | Developing a lightweight rock-paper-scissors framework for human-robot collaborative gaming | |
| Maroto-Gómez et al. | Active learning based on computer vision and human–robot interaction for the user profiling and behavior personalization of an autonomous social robot | |
| DeLanda | Materialist phenomenology: A philosophy of perception | |
| Stevens | Memory and dance:‘Bodies of Knowledge’in contemporary dance | |
| Maroto-Gómez et al. | A preference learning system for the autonomous selection and personalization of entertainment activities during human-robot interaction | |
| KR102222714B1 (en) | System for automatically matching educational content based on user information | |
| KR102162356B1 (en) | Method for controlling of image based on biometric information | |
| CN111656361B (en) | Target realizing device in synthetic reality scene | |
| KR102596322B1 (en) | Method, system, and non-transitory computer-readable recording medium for authoring contents based on in-vehicle video | |
| Chaudhary et al. | Deep Learning in Gaming and Animations: Principles and Applications | |
| Torelli | HoloLearn: mixed reality experiences for persons with neurodevelopmental disorders | |
| CN117899328A (en) | Sleep assisting method, apparatus, device and readable storage medium | |
| Rosenkind | Creating Believable, Emergent Behaviour in Virtual Agents, Using a Synthetic Psychology Approach |
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 |
Application publication date: 20190222 |
|
| RJ01 | Rejection of invention patent application after publication |