CN109471954A - Content recommendation method, device, equipment and storage medium based on mobile unit - Google Patents
Content recommendation method, device, equipment and storage medium based on mobile unit Download PDFInfo
- Publication number
- CN109471954A CN109471954A CN201811149285.XA CN201811149285A CN109471954A CN 109471954 A CN109471954 A CN 109471954A CN 201811149285 A CN201811149285 A CN 201811149285A CN 109471954 A CN109471954 A CN 109471954A
- Authority
- CN
- China
- Prior art keywords
- target user
- media content
- mood
- user
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of content recommendation method based on mobile unit, device, equipment and storage medium.This method comprises: determining the mood of the target user according to the facial image of target user；According to the mood of the target user, the first media content corresponding with the mood is obtained；It controls the mobile unit and recommends first media content to the target user.The embodiment of the present invention is based on facial image and identifies face mood, does real-time recommendation in conjunction with face mood, so that the content recommended more meets the demand of user, improves the accuracy rate of recommendation, user experience is higher.
Description
Technical field
The present invention relates to field of artificial intelligence more particularly to a kind of content recommendation methods based on mobile unit, dress
It sets, equipment and storage medium.
Background technique
With the development of artificial intelligence technology, the intelligence of automobile is increasingly taken seriously, and user is not only to the peace of driving
Full performance has higher requirement, also values very much the experience of intelligence in driving procedure, hommization.
Currently, be typically provided with mobile unit on automobile, watch or listen to media content for user, media content for example including
Video or audio file, in the related technology, user can indicate that mobile unit plays media content by voice operating, vehicle-mounted to set
It is standby that media content is recommended to user based on user's history played data, and play out, above-mentioned way of recommendation accuracy rate is lower.
Summary of the invention
The present invention provides a kind of content recommendation method based on mobile unit, device, equipment and storage medium, is pushed away with improving
Recommend mode accuracy rate.
In a first aspect, the present invention provides a kind of content recommendation method based on mobile unit, comprising:
According to the facial image of target user, the mood of the target user is determined；
According to the mood of the target user, the first media content corresponding with the mood is obtained；
It controls the mobile unit and recommends first media content to the target user.
Second aspect, the present invention provide a kind of content recommendation device based on mobile unit, comprising:
Determining module determines the mood of the target user for the facial image according to target user；
Processing module obtains the first media content corresponding with the mood for the mood according to the target user；
Control module recommends first media content to the target user for controlling the mobile unit.
The third aspect, the embodiment of the present invention provide a kind of computer readable storage medium, are stored thereon with computer program,
Method described in any one of first aspect is realized when the computer program is executed by processor.
Fourth aspect, the embodiment of the present invention provide a kind of electronic equipment, comprising:
Processor；And
Memory, for storing the executable instruction of the processor；
Wherein, the processor is configured to execute described in any one of first aspect via the executable instruction is executed
Method.
Content recommendation method based on mobile unit, device, equipment and storage medium provided in an embodiment of the present invention, according to
The facial image of target user determines the mood of the target user；According to the mood of the target user, obtain and the feelings
Corresponding first media content of thread；It controls the mobile unit and recommends first media content to the target user, it is above-mentioned
Face mood is identified based on facial image in scheme, does real-time recommendation in conjunction with face mood, so that the content recommended more meets
The demand of user, improves the accuracy rate of recommendation, and user experience is higher.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.
Figure 1A is the application scenarios schematic diagram of the embodiment of the present invention；
Figure 1B is the flow diagram of content recommendation method one embodiment provided by the invention based on mobile unit；
Fig. 2 is the structural schematic diagram of content recommendation device one embodiment provided by the invention based on mobile unit；
Fig. 3 is the structural schematic diagram of one embodiment of electronic equipment provided by the invention；
Fig. 4 is the structural schematic diagram of another embodiment of electronic equipment provided by the invention.
Through the above attached drawings, it has been shown that the specific embodiment of the disclosure will be hereinafter described in more detail.These attached drawings
It is not intended to limit the scope of this disclosure concept by any means with verbal description, but is by referring to specific embodiments
Those skilled in the art illustrate the concept of the disclosure.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all implementations consistent with this disclosure.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the disclosure.
Term " includes " in description and claims of this specification and the attached drawing and " having " and they appoint
What is deformed, it is intended that is covered and non-exclusive is included.Such as contain the process, method, system, production of a series of steps or units
Product or equipment are not limited to listed step or unit, but optionally further comprising the step of not listing or unit, or
Optionally further comprising the other step or units intrinsic for these process, methods, product or equipment.
Application scenarios according to the present invention are introduced first:
Content recommendation method provided in an embodiment of the present invention based on mobile unit is applied in vehicle-mounted scene, to user
Recommend media content.
The executing subject of content recommendation method is electronic equipment in the embodiment of the present invention, which is specifically as follows vehicle
Carry equipment itself, or the external equipment communicated with electronic equipment, such as server, the embodiment of the present invention to this and it is unlimited
It is fixed.
As shown in Figure 1A, mobile unit can be interacted with server, if executing subject is server, server be can control
Mobile unit acquires the facial image of target user, and the facial image of the target user based on acquisition obtains the feelings of target user
Thread, and according to the mood of target user, the first media content corresponding with the mood is obtained, control mobile unit is used to target
Recommend first media content in family.
If executing subject is mobile unit itself, mobile unit acquires the facial image of target user, the mesh based on acquisition
The facial image for marking user obtains the mood of target user, and according to the mood of target user, obtains corresponding with the mood
First media content recommends first media content to target user, wherein obtains the mood and acquisition first of target user
Media content can be by interacting realization with server.
The method of the embodiment of the present invention obtains the first matchmaker corresponding with the mood according to the mood of the target user
Hold in vivo, and recommend first media content, due to considering the current mood of user, more meets the demand of user, give user
Bring more intelligent experience.
Technical solution of the present invention is described in detail with specific embodiment below.These specific implementations below
Example can be combined with each other, and the same or similar concept or process may be repeated no more in some embodiments.
Figure 1B is the flow diagram of content recommendation method one embodiment provided by the invention based on mobile unit.Such as figure
Shown in 1B, method provided in this embodiment, comprising:
Step 101, the facial image according to target user, determine the mood of the target user.
Specifically, when needing to recommend media content to user, the current facial image of acquisition target user first can be with
Acquire the facial image of target user in real time by the image acquisition component of mobile unit, and according to the face figure of the target user
Picture can use deep learning algorithm and determine the current mood of the target user.Mood may include at least one of following: anger
It is anger, contempt, detest, fear, happy, amimia, sad or surprised.
Optionally, before step 101, following operation can also be performed:
Control the phonetic order that the mobile unit receives the user；The phonetic order is used to indicate described vehicle-mounted set
It is standby to play media content；
According to the phonetic order of the user, triggering executes the facial image according to target user, determines that the target is used
The operation of the mood at family.
Specifically, the phonetic order of user can be received by the voice collecting component of mobile unit, such as microphone,
After receiving user and indicating to play the phonetic order of media content, triggering executes the recommended method of the embodiment of the present invention, that is, holds
The operation of row step 101.
For example, target user exports phonetic order " playing music ", then the scheme for executing the embodiment of the present invention is triggered.
Step 102, according to the mood of the target user, obtain the first media content corresponding with the mood.
Specifically, can be obtained corresponding with the mood based on target recommended models are based on according to the mood of target user
Multiple media contents therefrom select a media content, as the first media content；Or the total medium content that will acquire is made
For the first media content, user is allowed to select, or plays total medium content in order.
It for example, the mood of target user is sadness, then can choose some cheerful and light-hearted song recommendations to target user, allow mesh
The mood sad mood of mark user is alleviated.
Further, the target recommended models, can be based on what is be trained based on convolutional neural networks, specifically may be used
To be trained in the following way:
Multiple groups mood and media content corresponding with the mood are obtained as training sample；
According to the training sample, the initial training model based on convolutional neural networks is trained, the mesh is obtained
Mark recommended models.
Specifically, obtaining training sample first, training sample can be the multi-group data by label, and every group of data include
A kind of mood and at least one corresponding media content of the mood.
Initial training model is trained according to training sample, obtains final target recommended models.
It in practical applications, can also be according to the actual feedback more fresh target recommended models of user.
During training objective recommended models, it is also contemplated that the representation data of target user, it can in representation data
To include the data such as multiple user properties, such as gender, hobby, age, educational background.
Specifically increase the dimension of user property in above-mentioned training sample, i.e. every group of data include a kind of mood, the mood
At least one corresponding media content and user property.
Further, it when obtaining the first media content corresponding with mood based on target recommended models, is also based on
Preset Generalization bounds, for example, by using new hot Generalization bounds, program of the content source for example including broadcasting time topN, for example (,) it is former
Name or tens programs, N are the integer greater than 1.
Step 103, the control mobile unit recommend first media content to the target user.
Specifically, can control mobile unit after the first media content to be recommended has been determined and recommend to target user,
Such as first media content include multiple media files, user can select one of them to play out according to actual needs, or
Person, mobile unit play in order those media files according to preset order.
After recommending the first media content to target user, the instruction that mobile unit receives user can control, such as
Phonetic order then needs again alternatively, touch operation instruction etc., such as target user issue phonetic order " changing a song "
The first media content is obtained to be recommended, alternatively, click recommendation list in some media file, thus select the media file into
Row plays.
Optionally, it after step 103, can also proceed as follows:
The target user is received to the feedback information of first media content；
According to the target user to the feedback information of first media content, and/or, after the target user updates
Representation data, the target recommended models are updated.
Specifically, target user feeds back the first media content of recommendation, the feedback information of target user is obtained, it can
It, further can also be simultaneously according to the updated picture of target user to be updated based on the feedback information to target recommended models
As data, target recommended models are updated.
Target user feeds back the first media content of recommendation, such as likes first media content, or collection
First media content, does not like first media content etc..
In some embodiments, it is also based on the representation data of user, target recommended models are updated, the present invention
Embodiment does not limit this.
The method of the present embodiment determines the mood of the target user according to the facial image of target user；According to described
The mood of target user obtains the first media content corresponding with the mood；The mobile unit is controlled to use to the target
First media content is recommended at family, is based on facial image in above scheme and identifies face mood, does reality in conjunction with face mood
When recommend so that the content recommended more meets the demand of user, improve the accuracy rate of recommendation, user experience is higher.
On the basis of the above embodiments, optionally, in order to enable media content recommended to the user more meets user's
Demand, step 102 can be realized in the following way:
According to the mood of the target user, based on target recommended models obtain it is corresponding with the mood at least one the
Two media contents；
Determine each second media content, respectively with the target user hobby record in include media content
Between correlation；The hobby record includes the identification information of the media content of target user hobby；
According between the media content for including in each second media content and the hobby record of the target user
Correlation, first media content is selected from second media content.
Wherein, target user hobby media content identification information for example including title, affiliated classification, author's title,
The information such as style of song.
Specifically, firstly, obtaining corresponding with mood at least one based on target recommended models according to the mood of target user
A second media content.
Then correlation of each second media content respectively between the media content of target user's hobby is determined, it can be with
It is ranked up according to correlation, using biggish preceding several second media contents of correlation as the first media content recommendations to use
Family, alternatively, using the second media content of correlation maximum as the first media content recommendations to user.
For example, the mood of target user be sadness, the second media content of acquisition include song " small dimple ", " love multiplied by
Infinity ", " sweet tea sweet tea ", " leaving earth surface " etc., the media that those second media contents are liked with target user respectively
Compare between content, determine the correlation between the media content liked with target user, it is assumed that the media of target user's hobby
Content is love song, songster etc..Correlation is greater than the media content of preset value as the first media content, such as by " small wine
Nest " recommends the target user.
In the present embodiment, based on the correlation between media content, the first media content to be recommended is selected, due to considering
The hobby of user, the accuracy rate of recommendation are higher.
On the basis of the above embodiments, in order to enable media content recommended to the user more meets the demand of user, and
And the media content recommended is richer, optionally, step 102 can also be realized using following another way:
According to the mood of the target user, based on target recommended models obtain it is corresponding with the mood at least one the
Three media contents；
According to the hobby of the target user and at least one other user record, determine respectively the target user with
Correlation between the other users；
According to the correlation between the target user and the other users, institute is selected from the third media content
State the first media content.
Specifically, firstly, obtaining corresponding with mood at least one based on target recommended models according to the mood of target user
A third media content.Wherein, third media content can be identical or different with the second media content.
Then it is recorded according to the hobby of target user and at least one other user, determines target user and other respectively
Correlation between user；Hobby record includes the identification information of the media content of user preferences；Wherein, identification information can be found in
The explanation of previous embodiment.
According to the correlation between the target user and the other users, institute is selected from the third media content
State the first media content.
For example, the hobby record display of target user is liked listening Zhou Jielun, selection likes listening the other users of Zhou Jielun to make
For the associated user of the user, the song that the corresponding other users of the mood for selecting the target user current are liked, and recommend
The target user.
Further, the correlation according between the target user and the other users, from the third media
First media content is selected in content, can specifically include following operation:
According to the correlation between the target user and the other users, use relevant to the target user is determined
Family；
It is recorded according to the hobby of the user relevant to the target user, selects institute from the third media content
State the first media content.
It selects from third media content specifically, can be, remembers in the hobby record of user relevant to target user
The media content of record, the biggish media content of correlation.
For example, the hobby record display of target user is liked listening Zhou Jielun, selection likes listening the other users of Zhou Jielun to make
For the associated user of the user, the current mood of target user is sadness, and the song that associated user likes has " simple Love ", then selects
The song recommendations are selected to the target user.
In the present embodiment, the hobby record based on the relevant user of target user selects the first media content to be recommended,
Due to considering the hobby of target user and associated user, the accuracy rate of recommendation is higher.
On the basis of the above embodiments, optionally, the mood that target user is determined in step 101, can specifically pass through
As under type is realized:
Control the facial image that the mobile unit obtains the target user；
According to the facial image of the target user, the corresponding emotion of the facial image is determined using deep learning algorithm
Confidence scoring；
Determine mood corresponding with the emotion confidence scoring.
Specifically, the facial image of target user is obtained first in the corresponding mood of the facial image that determines user, it can
To be obtained by the image acquisition component of mobile unit, such as camera.
Then determine that the corresponding emotion confidence of facial image got scores using deep learning algorithm, it finally can root
According to the corresponding relationship of emotion confidence scoring and mood, mood corresponding with the scoring of emotion confidence is determined.The feelings that can be identified
Thread such as indignation, is detested, is frightened, happy, amimia, sad and surprised contempt.The scoring of emotion confidence is for example including for every
A kind of confidence level of mood.
It can be trained to obtain training pattern based on the training sample obtained in advance.Training sample can be a large amount of labels
The facial image of mood.
Wherein, it determines that the corresponding emotion confidence of the facial image scores using deep learning algorithm, can specifically pass through
As under type is realized:
According to the facial image of the target user, feature vector is obtained；Described eigenvector includes described for characterizing
The characteristic information of the mood of target user；
Described eigenvector is input in the training pattern based on the deep learning algorithm, determines the facial image
Corresponding emotion confidence scoring.
Specifically, analyzing the facial image got, feature vector is obtained, this feature vector includes feature letter
Breath, characteristic information is, for example, the human face expression in facial image.
According to feature vector, based on the training pattern of deep learning algorithm, determine that the corresponding emotion confidence of facial image is commented
Point.
In the present embodiment, the mood of user is determined by deep learning algorithm, efficiency is higher, and accuracy rate is higher.
Fig. 2 is the structure chart of content recommendation device one embodiment provided by the invention based on mobile unit, such as Fig. 2 institute
Show, the content recommendation device based on mobile unit of the present embodiment, comprising:
Determining module 201 determines the mood of the target user for the facial image according to target user；
Processing module 202 obtains in the first media corresponding with the mood for the mood according to the target user
Hold；
Control module 203 recommends first media content to the target user for controlling the mobile unit
Optionally, the processing module 202, is specifically used for:
According to the mood of the target user, based on target recommended models obtain it is corresponding with the mood at least one the
Two media contents；
Determine each second media content, respectively with the target user hobby record in include media content
Between correlation；The hobby record includes the identification information of the media content of target user hobby；
According between the media content for including in each second media content and the hobby record of the target user
Correlation, first media content is selected from second media content.
Optionally, the processing module 202, is specifically used for:
According to the mood of the target user, based on target recommended models obtain it is corresponding with the mood at least one the
Three media contents；
According to the hobby of the target user and at least one other user record, determine respectively the target user with
Correlation between the other users；
According to the correlation between the target user and the other users, institute is selected from the third media content
State the first media content.
Optionally, the processing module 202, is specifically used for:
According to the correlation between the target user and the other users, use relevant to the target user is determined
Family；
It is recorded according to the hobby of the user relevant to the target user, selects institute from the third media content
State the first media content.
Optionally, the processing module 202, is also used to:
Multiple groups mood and media content corresponding with the mood are obtained as training sample；
According to the training sample, the initial training model based on convolutional neural networks is trained, the mesh is obtained
Mark recommended models.
Optionally, further includes:
Receiving module, for receiving the target user to the feedback information of first media content；
The processing module 202 is also used to the feedback information according to the target user to first media content,
And/or the updated representation data of target user, the target recommended models are updated.
Optionally, the determining module 201, is specifically used for:
Control the facial image that the mobile unit obtains the target user；
According to the facial image of the target user, the corresponding emotion of the facial image is determined using deep learning algorithm
Confidence scoring；
Determine mood corresponding with the emotion confidence scoring.
Optionally, the determining module 201, is specifically used for:
According to the facial image of the target user, feature vector is obtained；Described eigenvector includes described for characterizing
The characteristic information of the mood of target user；
Described eigenvector is input in the training pattern based on the deep learning algorithm, determines the facial image
Corresponding emotion confidence scoring.
Optionally, the determining module 201, is specifically used for:
According to the corresponding relationship of emotion confidence scoring and mood, feelings corresponding with the emotion confidence scoring are determined
Thread.
Optionally, the control module, is also used to:
Before the facial image according to target user, the mood for determining the target user,
Control the phonetic order that the mobile unit receives the user；The phonetic order is used to indicate described vehicle-mounted set
It is standby to play media content；
According to the phonetic order of the user, triggering executes the facial image according to target user, determines the mesh
Mark the operation of the mood of user.
Optionally, the mood includes at least one of the following: indignation, contempt, detests, is frightened, happy, amimia, sad
Or it is surprised.
The device of the present embodiment can be used for executing the technical solution of above method embodiment, realization principle and technology
Effect is similar, and details are not described herein again.
Fig. 3 is the structure chart of one embodiment of electronic equipment provided by the invention, as shown in figure 3, the electronic equipment includes:
Processor 301, and, the memory 302 of the executable instruction for storage processor 301.
It optionally, can also include: communication interface 303, for being communicated with other equipment.
Above-mentioned component can be communicated by one or more bus.
Wherein, processor 301 is configured to execute via the executable instruction is executed corresponding in preceding method embodiment
Method, specific implementation process may refer to preceding method embodiment, and details are not described herein again.
Further, if the electronic equipment is mobile unit, as shown in figure 4, optionally, which can also include
Image acquisition component, such as camera.
A kind of computer readable storage medium is also provided in the embodiment of the present invention, is stored thereon with computer program, it is described
Realize that corresponding method in preceding method embodiment, specific implementation process may refer to when computer program is executed by processor
Preceding method embodiment, it is similar that the realization principle and technical effect are similar, and details are not described herein again.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
Its embodiment.The present invention is directed to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Person's adaptive change follows the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by following
Claims are pointed out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by appended claims
System.
Claims (22)
1. a kind of content recommendation method based on mobile unit characterized by comprising
According to the facial image of target user, the mood of the target user is determined；
According to the mood of the target user, the first media content corresponding with the mood is obtained；
It controls the mobile unit and recommends first media content to the target user.
2. the method according to claim 1, wherein the mood according to the target user, acquisition and institute
State corresponding first media content of mood, comprising:
According to the mood of the target user, at least one second matchmaker corresponding with the mood is obtained based on target recommended models
Hold in vivo；
Determine each second media content, respectively with the target user hobby record in include media content between
Correlation；The hobby record includes the identification information of the media content of target user hobby；
According to the phase between the media content for including in each second media content and the hobby record of the target user
Guan Xing selects first media content from second media content.
3. the method according to claim 1, wherein the mood according to the target user, acquisition and institute
State corresponding first media content of mood, comprising:
According to the mood of the target user, at least one third matchmaker corresponding with the mood is obtained based on target recommended models
Hold in vivo；
According to the hobby of the target user and at least one other user record, determine respectively the target user with it is described
Correlation between other users；
According to the correlation between the target user and the other users, described is selected from the third media content
One media content.
4. according to the method described in claim 3, it is characterized in that, it is described according to the target user and the other users it
Between correlation, first media content is selected from the third media content, comprising:
According to the correlation between the target user and the other users, user relevant to the target user is determined；
It is recorded according to the hobby of the user relevant to the target user, described the is selected from the third media content
One media content.
5. according to the described in any item methods of claim 2-4, which is characterized in that the mood according to the target user,
Before acquisition the first media content corresponding with the mood, further includes:
Multiple groups mood and media content corresponding with the mood are obtained as training sample；
According to the training sample, the initial training model based on convolutional neural networks is trained, the target is obtained and pushes away
Recommend model.
6. according to the described in any item methods of claim 2-4, which is characterized in that described to control the mobile unit to the mesh
Mark user recommends after first media content, further includes:
The target user is received to the feedback information of first media content；
According to the target user to the feedback information of first media content, and/or, the updated picture of target user
As data, the target recommended models are updated.
7. method according to claim 1-4, which is characterized in that the facial image according to target user,
Determine the mood of the target user, comprising:
Control the facial image that the mobile unit obtains the target user；
According to the facial image of the target user, the corresponding emotion confidence of the facial image is determined using deep learning algorithm
Scoring；
Determine mood corresponding with the emotion confidence scoring.
8. the method according to the description of claim 7 is characterized in that the facial image according to the target user, utilizes
Deep learning algorithm determines the corresponding emotion confidence scoring of the facial image, comprising:
According to the facial image of the target user, feature vector is obtained；Described eigenvector includes for characterizing the target
The characteristic information of the mood of user；
Described eigenvector is input in the training pattern based on the deep learning algorithm, determines that the facial image is corresponding
Emotion confidence scoring.
9. the method according to the description of claim 7 is characterized in that determination feelings corresponding with the emotion confidence scoring
Thread, comprising:
According to the corresponding relationship of emotion confidence scoring and mood, mood corresponding with the emotion confidence scoring is determined.
10. method according to claim 1-4, which is characterized in that the facial image according to target user,
Before the mood for determining the target user, further includes:
Control the phonetic order that the mobile unit receives the user；The phonetic order is used to indicate the mobile unit and broadcasts
Put media content；
According to the phonetic order of the user, triggering executes the facial image according to target user, determines that the target is used
The operation of the mood at family.
11. method according to claim 1-4, which is characterized in that
The mood includes at least one of the following: indignation, contempt, detests, is frightened, happy, amimia, sad or surprised.
12. a kind of content recommendation device based on mobile unit characterized by comprising
Determining module determines the mood of the target user for the facial image according to target user；
Processing module obtains the first media content corresponding with the mood for the mood according to the target user；
Control module recommends first media content to the target user for controlling mobile unit.
13. a kind of electronic equipment characterized by comprising
Processor；And
Memory, for storing the executable instruction of the processor；
Wherein, the processor is configured to perform the following operations via the executable instruction is executed:
According to the facial image of target user, the mood of the target user is determined；
According to the mood of the target user, the first media content corresponding with the mood is obtained；
It controls mobile unit and recommends first media content to the target user.
14. electronic equipment according to claim 13, which is characterized in that the processor is specifically used for:
According to the mood of the target user, at least one second matchmaker corresponding with the mood is obtained based on target recommended models
Hold in vivo；
Determine each second media content, respectively with the target user hobby record in include media content between
Correlation；The hobby record includes the identification information of the media content of target user hobby；
According to the phase between the media content for including in each second media content and the hobby record of the target user
Guan Xing selects first media content from second media content.
15. electronic equipment according to claim 13, which is characterized in that the processor is specifically used for:
According to the mood of the target user, at least one third matchmaker corresponding with the mood is obtained based on target recommended models
Hold in vivo；
According to the hobby of the target user and at least one other user record, determine respectively the target user with it is described
Correlation between other users；
According to the correlation between the target user and the other users, described is selected from the third media content
One media content.
16. electronic equipment according to claim 15, which is characterized in that the processor is specifically used for:
According to the correlation between the target user and the other users, user relevant to the target user is determined；
It is recorded according to the hobby of the user relevant to the target user, described the is selected from the third media content
One media content.
17. the described in any item electronic equipments of 4-16 according to claim 1, which is characterized in that the processor is also used to:
Multiple groups mood and media content corresponding with the mood are obtained as training sample；
According to the training sample, the initial training model based on convolutional neural networks is trained, the target is obtained and pushes away
Recommend model.
18. the described in any item electronic equipments of 4-16 according to claim 1, which is characterized in that the processor is also used to:
The target user is received to the feedback information of first media content；
According to the target user to the feedback information of first media content, and/or, the updated picture of target user
As data, the target recommended models are updated.
19. the described in any item electronic equipments of 3-16 according to claim 1, which is characterized in that the processor is specifically used for:
Control the facial image that the mobile unit obtains the target user；
According to the facial image of the target user, the corresponding emotion confidence of the facial image is determined using deep learning algorithm
Scoring；
Determine mood corresponding with the emotion confidence scoring.
20. electronic equipment according to claim 19, which is characterized in that the processor is specifically used for:
According to the facial image of the target user, feature vector is obtained；Described eigenvector includes for characterizing the target
The characteristic information of the mood of user；
Described eigenvector is input in the training pattern based on the deep learning algorithm, determines that the facial image is corresponding
Emotion confidence scoring.
21. the described in any item electronic equipments of 3-16 according to claim 1, which is characterized in that the processor is also used to:
Control the phonetic order that the mobile unit receives the user；The phonetic order is used to indicate the mobile unit and broadcasts
Put media content；
According to the phonetic order of the user, triggering executes the facial image according to target user, determines that the target is used
The operation of the mood at family.
22. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
Claim 1-11 described in any item methods are realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811149285.XA CN109471954A (en) | 2018-09-29 | 2018-09-29 | Content recommendation method, device, equipment and storage medium based on mobile unit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811149285.XA CN109471954A (en) | 2018-09-29 | 2018-09-29 | Content recommendation method, device, equipment and storage medium based on mobile unit |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109471954A true CN109471954A (en) | 2019-03-15 |
Family
ID=65664730
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811149285.XA Pending CN109471954A (en) | 2018-09-29 | 2018-09-29 | Content recommendation method, device, equipment and storage medium based on mobile unit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109471954A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110008879A (en) * | 2019-03-27 | 2019-07-12 | 深圳市尼欧科技有限公司 | Vehicle-mounted personalization audio-video frequency content method for pushing and device |
| CN110955798A (en) * | 2019-11-27 | 2020-04-03 | 中国第一汽车股份有限公司 | Control method, device and equipment based on vehicle-mounted multimedia system and vehicle |
| CN111400610A (en) * | 2020-02-11 | 2020-07-10 | 北京梧桐车联科技有限责任公司 | Vehicle-mounted social contact method and device and computer storage medium |
| US11544314B2 (en) | 2019-06-27 | 2023-01-03 | Spotify Ab | Providing media based on image analysis |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105700682A (en) * | 2016-01-08 | 2016-06-22 | 北京乐驾科技有限公司 | Intelligent gender and emotion recognition detection system and method based on vision and voice |
| CN105976843A (en) * | 2016-05-18 | 2016-09-28 | 乐视控股（北京）有限公司 | In-vehicle music control method, device, and automobile |
| CN106562793A (en) * | 2015-10-08 | 2017-04-19 | 松下电器（美国）知识产权公司 | Method for controlling information display apparatus, and information display apparatus |
| CN106649843A (en) * | 2016-12-30 | 2017-05-10 | 上海博泰悦臻电子设备制造有限公司 | Media file recommending method and system based on vehicle-mounted terminal and vehicle-mounted terminal |
| CN106878364A (en) * | 2015-12-11 | 2017-06-20 | 比亚迪股份有限公司 | Information-pushing method, system, Cloud Server and vehicle for vehicle |
| CN108549720A (en) * | 2018-04-24 | 2018-09-18 | 京东方科技集团股份有限公司 | It is a kind of that method, apparatus and equipment, storage medium are pacified based on Emotion identification |
-
2018
- 2018-09-29 CN CN201811149285.XA patent/CN109471954A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106562793A (en) * | 2015-10-08 | 2017-04-19 | 松下电器（美国）知识产权公司 | Method for controlling information display apparatus, and information display apparatus |
| CN106878364A (en) * | 2015-12-11 | 2017-06-20 | 比亚迪股份有限公司 | Information-pushing method, system, Cloud Server and vehicle for vehicle |
| CN105700682A (en) * | 2016-01-08 | 2016-06-22 | 北京乐驾科技有限公司 | Intelligent gender and emotion recognition detection system and method based on vision and voice |
| CN105976843A (en) * | 2016-05-18 | 2016-09-28 | 乐视控股（北京）有限公司 | In-vehicle music control method, device, and automobile |
| CN106649843A (en) * | 2016-12-30 | 2017-05-10 | 上海博泰悦臻电子设备制造有限公司 | Media file recommending method and system based on vehicle-mounted terminal and vehicle-mounted terminal |
| CN108549720A (en) * | 2018-04-24 | 2018-09-18 | 京东方科技集团股份有限公司 | It is a kind of that method, apparatus and equipment, storage medium are pacified based on Emotion identification |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110008879A (en) * | 2019-03-27 | 2019-07-12 | 深圳市尼欧科技有限公司 | Vehicle-mounted personalization audio-video frequency content method for pushing and device |
| US11544314B2 (en) | 2019-06-27 | 2023-01-03 | Spotify Ab | Providing media based on image analysis |
| CN110955798A (en) * | 2019-11-27 | 2020-04-03 | 中国第一汽车股份有限公司 | Control method, device and equipment based on vehicle-mounted multimedia system and vehicle |
| CN111400610A (en) * | 2020-02-11 | 2020-07-10 | 北京梧桐车联科技有限责任公司 | Vehicle-mounted social contact method and device and computer storage medium |
| CN111400610B (en) * | 2020-02-11 | 2023-08-01 | 北京梧桐车联科技有限责任公司 | Vehicle-mounted social method and device and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106548773B (en) | Child user searching method and device based on artificial intelligence | |
| US10987596B2 (en) | Spectator audio analysis in online gaming environments | |
| US11334804B2 (en) | Cognitive music selection system and method | |
| CN109471954A (en) | Content recommendation method, device, equipment and storage medium based on mobile unit | |
| US9396758B2 (en) | Semi-automatic generation of multimedia content | |
| KR20210110620A (en) | Interaction methods, devices, electronic devices and storage media | |
| US11176484B1 (en) | Artificial intelligence system for modeling emotions elicited by videos | |
| US11375256B1 (en) | Artificial intelligence system for modeling emotions elicited by videos | |
| US10284537B2 (en) | Methods, systems, and media for presenting information related to an event based on metadata | |
| CN110209843A (en) | Multimedia resource playback method, device, equipment and storage medium | |
| CN112328849B (en) | User portrait construction method, user portrait-based dialogue method and device | |
| US10293260B1 (en) | Player audio analysis in online gaming environments | |
| US9524751B2 (en) | Semi-automatic generation of multimedia content | |
| CN104460981A (en) | Presenting audio based on biometrics parameters | |
| US20080096174A1 (en) | Tutorial generation unit, multimedia management system, portable apparatus, method of explanation of multimedia management behavior, computer program product | |
| JP2011528879A (en) | Apparatus and method for providing a television sequence | |
| US8874444B2 (en) | Simulated conversation by pre-recorded audio navigator | |
| US11849160B2 (en) | Image analysis system | |
| CN109545185A (en) | Interactive system evaluation method, evaluation system, server and computer-readable medium | |
| EP2720155A1 (en) | Information processing device, information processing method and program | |
| US20220406280A1 (en) | Information processing apparatus, information processing method, and information processing program | |
| US20160357498A1 (en) | Gamified Adaptive Digital Disc Jockey | |
| CN115212543A (en) | Interface switchable fitness system | |
| CN111522914B (en) | Labeling data acquisition method and device, electronic equipment and storage medium | |
| CN113240004A (en) | Video information determination method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190315 |
|
| RJ01 | Rejection of invention patent application after publication |