CN110377761A - A kind of method and device enhancing video tastes - Google Patents
A kind of method and device enhancing video tastes Download PDFInfo
- Publication number
- CN110377761A CN110377761A CN201910630024.8A CN201910630024A CN110377761A CN 110377761 A CN110377761 A CN 110377761A CN 201910630024 A CN201910630024 A CN 201910630024A CN 110377761 A CN110377761 A CN 110377761A
- Authority
- CN
- China
- Prior art keywords
- mood
- information
- multimedia messages
- decibel
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 235000019640 taste Nutrition 0.000 title claims abstract description 45
- 230000002708 enhancing effect Effects 0.000 title claims abstract description 44
- 230000036651 mood Effects 0.000 claims description 160
- 230000033764 rhythmic process Effects 0.000 claims description 63
- 230000008451 emotion Effects 0.000 claims description 35
- 238000004891 communication Methods 0.000 claims description 26
- 230000002159 abnormal effect Effects 0.000 claims description 16
- 230000001815 facial effect Effects 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 11
- 230000001360 synchronised effect Effects 0.000 claims description 10
- 230000000747 cardiac effect Effects 0.000 claims description 8
- 230000000694 effects Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 3
- 230000000452 restraining effect Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 5
- 230000002452 interceptive effect Effects 0.000 description 5
- 235000015170 shellfish Nutrition 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 230000005236 sound signal Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000003796 beauty Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011982 device technology Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 208000001491 myopia Diseases 0.000 description 1
- 230000007958 sleep Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/43—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/43—Querying
- G06F16/435—Filtering based on additional data, e.g. user or group profiles
- G06F16/436—Filtering based on additional data, e.g. user or group profiles using biological or physiological data of a human being, e.g. blood pressure, facial expression, gestures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/48—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/483—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- 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
-
- 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
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/24—Speech recognition using non-acoustical features
- G10L15/25—Speech recognition using non-acoustical features using position of the lips, movement of the lips or face analysis
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/63—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for estimating an emotional state
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Acoustics & Sound (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Library & Information Science (AREA)
- Physiology (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Child & Adolescent Psychology (AREA)
- Hospice & Palliative Care (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Processing Or Creating Images (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention discloses a kind of method and apparatus for enhancing video tastes, which comprises obtains the first multimedia messages, identifies key message, handled according to key message the first multimedia messages, to obtain the second multimedia messages.Invention increases user experience and interests.
Description
Technical field
The present invention relates to technical field of image processing, in particular to a kind of method and device for enhancing video tastes.
Background technique
With the development of camera technique and electronic device technology, camera function has become electronic equipment equipment, and (such as mobile phone is put down
Plate computer etc.) standard configuration.Consequent is the generation of more next more application of taking pictures, for example, people can use various take pictures
The processing such as U.S. face, textures, filter are carried out using to photo or video.
When video communication/recorded video, the image quality processing mode of video is: when without portrait, restoring the effect of original scene;
When having portrait, by Identification of Images, portrait area is highlighted, then colour of skin colors countenance restores the effect of original scene
Fruit;When having portrait, by Identification of Images, increase portrait beauty Yan Xiaoguo;When having portrait, user is manually selected by paster software
Paster is applied to record short-sighted frequency.Also, in more people's video communications, without above-mentioned, the image quality processing mode of video.
However, reducing processing or the increase portrait beauty Yan Xiaoguo of either image quality color, video communication or recording
Relatively single in experience, interest is not strong.
Summary of the invention
The object of the present invention is to provide a kind of method and devices for enhancing video tastes, are recording to solve the prior art
The image quality processing of video or during video communication, video is upper or video communication experience on it is more single, cause to reduce use
Family experience, the not strong problem of interest.
To solve the above-mentioned problems, the invention is realized by the following technical scheme:
A method of enhancing video tastes, include following procedure: the first multimedia messages obtained, identify key message,
First multimedia messages are handled according to the key message, to obtain the second multimedia messages.
Further, also include: showing and/or store second multimedia messages.
Further, first multimedia messages include image information and voice messaging.
Further, the identification key message includes: to the figure in the first multimedia messages acquired in current time
As information progress recognition of face, gender information and portrait expression information are obtained;
Voice messaging in first multimedia messages acquired in current time is analyzed, the fluctuation of voice decibel is obtained
Status information and crucial type of emotion information.
Further, described that first multimedia messages are handled according to the key message further include: to call
Mood model library, according to the gender information, portrait expression information, voice decibel fluctuation status and crucial type of emotion information with
Mood model in the mood model library is matched, and personage's feelings in the first multimedia messages described in current time are obtained
Thread, and default mood animation associated with personage's mood and virtual special efficacy;
It will be with more than described the first of the default mood animation of personage's mood associated and virtual special efficacy and current time
Media information is integrated, and the second multimedia messages are obtained.
Further, the identification key message further also includes: pre-establishing face template feature database;
The facial image in described image information is extracted,
Face template feature database is called, by the facial image and the face figure being stored in the face template feature database
Decent is matched, and obtains matched facial image sample, and gender associated with the matched facial image sample
Information and portrait expression information.
Further, the decibel fluctuation status information includes normal decibel fluctuation status and abnormal decibel fluctuation status;
The voice decibel s per second in the voice messaging is recorded, first in first time interval t1 seconds interval is calculated
Average decibel value S1;The second average decibel value in the second time interval value t2 seconds intervals before calculating first time interval t1
S2;It calculates the described first average decibel value S1 and second be averaged the percentage of decibel value S2, obtains the decibel percent value X that is averaged,
Judgement, when the average decibel percent value X is more than or equal to 0.8x, the obtained decibel fluctuation status information is normal point
Shellfish fluctuation status;
When the equal decibel percent value X is less than 0.8x, the obtained decibel fluctuation status information is abnormal decibel
Fluctuation status;Wherein, x is default decibel threshold.
Further, obtaining the crucial type of emotion information includes following procedure: pre-establishing crucial mood literal pool;
Speech recognition is carried out to the voice messaging and obtains text information,
Crucial mood literal pool is called, by the text information and the text sample being stored in the crucial mood literal pool
This is matched, and matched text sample, and crucial type of emotion associated with the matched text sample are obtained.
Further, which is characterized in that also include: synchronous to obtain the user when obtaining first multimedia messages
Rhythm of the heart fluctuation status information;Later, mood model library is called, according to the gender information, portrait expression information, voice decibel
Fluctuation status, crucial type of emotion information and the rhythm of the heart fluctuation status information of the user and the mood in the mood model library
Model is matched, and obtains personage's mood in the first multimedia messages described in current time, and with personage's mood phase
Associated default mood animation and virtual special efficacy;It then, will be with the default mood animation of personage's mood associated and virtually
First multimedia messages at special efficacy and current time are integrated, and the second multimedia messages are obtained.
Further, the rhythm of the heart fluctuation status information includes: normal cardiac rhythm fluctuation status and abnormal heart rhythm fluctuation status;
The rhythm of the heart h of the user is persistently recorded, the first mean heart rate value H1 in third time interval t3 seconds intervals is calculated;
The second mean heart rate value H2 in being spaced for the 4th time interval value t4 seconds before calculating third time interval t3;Calculate described
The percentage of one mean heart rate value H1 and the second mean heart rate value H2 obtain mean heart rate percent value H, judgement, when described flat
When equal rhythm of the heart percent value H is more than or equal to 0.8y, the obtained rhythm of the heart fluctuation status information is normal cardiac rhythm fluctuation status;
When the mean heart rate percent value H is less than 0.8y, the obtained rhythm of the heart fluctuation status information is the abnormal heart
Restrain fluctuation status;Wherein, y is default rhythm of the heart threshold value.
On the other hand, a method of enhancing video tastes, include following procedure: when multiple users carry out video communication
When, synchronous the first multimedia messages for obtaining each user, first multimedia messages include image information and voice messaging;
The key message for identifying first multimedia messages of each user respectively, according to the key message to currently speaking
First multimedia messages of user handle, to obtain the second multimedia messages corresponding to the user, and at this
It is shown at the position of user window.
Further, first multimedia messages include image information and voice messaging.
Further, the key message of first multimedia messages for identifying each user respectively specifically:
Lip reading identification and speech recognition are carried out to first multimedia messages of each user, for positioning current time
The user to speak determines the first multimedia messages of the user;
Recognition of face is carried out to the image information in the first multimedia messages of the user acquired in current time, is obtained
Gender information and portrait expression information;
Voice messaging in first multimedia messages acquired in current time is analyzed, the fluctuation of voice decibel is obtained
Status information and crucial type of emotion information.
Further, it is described according to the key message to first multimedia messages of the user currently to speak
It is handled specifically:
Mood model library is called, according to the gender information, portrait expression information, voice decibel fluctuation status, crucial feelings
Thread type information and rhythm of the heart fluctuation status information are matched with the mood model in the mood model library, obtain current time
Personage's mood in first multimedia messages, and default mood animation associated with personage's mood and virtual spy
Effect;
By the institute with the default mood animation of personage's mood associated and virtual special efficacy and the user at current time
It states the first multimedia messages to be integrated, obtains the second multimedia messages corresponding to the user.
Further, also include: when obtaining first multimedia messages of each user, corresponding synchronous acquisition use
The rhythm of the heart fluctuation status information at family;Later, mood model library is called, according to the gender information, portrait expression information, voice point
Shellfish fluctuation status, crucial type of emotion information and the rhythm of the heart fluctuation status information of the user and the mood in the mood model library
Model is matched, and obtains personage's mood in the first multimedia messages described in current time, and with personage's mood phase
Associated default mood animation and virtual special efficacy;It then, will be with the default mood animation of personage's mood associated and virtually
First multimedia messages of this of special efficacy and current time user integrate, and obtain more than second matchmaker corresponding to the user
Body information.
In another aspect, a kind of device for enhancing video tastes, includes:
Module is obtained, is configured as obtaining the first multimedia messages;
Identification module is configured as identification key message;
Processing module is configured as handling first multimedia messages according to the key message, with
To the second multimedia messages;
Further, also include: display module is configured as showing second multimedia messages.
Further, first multimedia messages include image information and voice messaging.
Further, also include: face identification unit is configured as believing the first multimedia acquired in current time
Image information in breath carries out recognition of face, obtains gender information and portrait expression information;
Voice recognition unit, be configured as to the voice messaging in the first multimedia messages acquired in current time into
Row analysis obtains voice decibel fluctuation status information and crucial type of emotion information;
Matching unit is configured as calling mood model library, according to the gender information, portrait expression information, voice
Decibel fluctuation status and crucial type of emotion information are matched with the mood model in the mood model library, when obtaining current
Carve personage's mood in first multimedia messages, and default mood animation associated with personage's mood and virtual
Special efficacy;
Integrated unit, be configured as by with the default mood animation and virtual special efficacy of personage's mood associated with work as
First multimedia messages at preceding moment are integrated, and the second multimedia messages are obtained.
Fourth aspect, a kind of electric terminal equipment include: processor, memory and are stored on the memory simultaneously
The computer program that can be run on the processor, the processor realize enhancing as described above when executing described program
The method of video tastes.
Compared with prior art, the present invention having the advantage that
The present invention identifies key message, according to the key message to described first by obtaining the first multimedia messages
Multimedia messages are handled, to obtain the second multimedia messages and show;And particularly by obtaining the first multimedia letter
Breath, first multimedia messages include image information and voice messaging;To the first multimedia messages acquired in current time
In image information carry out recognition of face, obtain gender information and portrait expression information to acquired in current time more than first
Voice messaging in media information is analyzed, and voice decibel fluctuation status information and crucial type of emotion information are obtained;It adjusts
With mood model library, according to the gender information, portrait expression information, voice decibel fluctuation status and crucial type of emotion information
It is matched with the mood model in the mood model library, obtains personage's feelings in the first multimedia messages described in current time
Thread, and default mood animation associated with personage's mood and virtual special efficacy;By with personage's mood associated
Default mood animation and virtual special efficacy and first multimedia messages at current time are integrated, and the second multimedia letter is obtained
Breath;Show second multimedia messages.Wherein, the present invention can be with the video in when automatic identification video communication or recorded video
User's portrait in picture independently analyzes the mood of user in conjunction with recognition of face and speech recognition, and uses automatically for current time
The suitable virtual mood animation of mood matching at family and virtual special efficacy, and by the virtual mood animation and virtual Special display effect with
Family end is shown, user experience and interest are increased.Also, the present invention can also increase rhythm of the heart identification, by by the heart
Rule identifies obtained rhythm of the heart fluctuation status information and speech recognition, and the functions such as facial image identification are combined, further mention
It is high that matched accuracy is analyzed to active user's mood.The present disclosure additionally applies in more people's video communications, increases and regarded in more people
When frequency communicates, is combined by carrying out the identification of portrait lip reading and speech recognition to multiple users in video pictures, orient and work as
The user that the preceding moment is speaking, and the mood of the user is analyzed, it is its matching virtual mood animation and virtual special efficacy, and show
In the user terminal of each user, user video experience interest is further enhanced.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of the method for enhancing video tastes that first embodiment of the invention provides;
Fig. 2 is a kind of flow diagram of the method for enhancing video tastes that second embodiment of the invention provides;
Fig. 3 is a kind of flow diagram of the method for enhancing video tastes that third embodiment of the invention provides;
Fig. 4 is a kind of flow diagram of the method for enhancing video tastes that fourth embodiment of the invention provides;
Fig. 5 is a kind of structural block diagram of the device for enhancing video tastes that fifth embodiment of the invention provides;
Fig. 6 is a kind of structural block diagram of the device for enhancing video tastes that sixth embodiment of the invention provides;
Fig. 7 is a kind of structural block diagram of the device for enhancing video tastes that seventh embodiment of the invention provides;
Fig. 8 is a kind of structural block diagram for electric terminal equipment that eighth embodiment of the invention provides.
Specific embodiment
It holds as stated in the background art, relatively single on the video communication of the prior art or the experience of recording, interest is not strong.
And user can only be by manually selecting paster, the experience of Lai Jinhang recorded video enhancing.Paster is opposite and for multi-party video
In communication, without this function.When video communication/recorded video, the displaying of user language and countenance is not necessarily that my heart is true
Real emotional state, while current equipment can not capture and show the true heart mood of user.
Based on the studies above, core of the invention thought is to provide a kind of method for enhancing video tastes, comprising: obtains
First multimedia messages identify key message, are handled according to the key message first multimedia messages, to obtain
To the second multimedia messages and show.Particularly by based on speech recognition technology (including voice intensity identify, language and characters
Identification etc.), rhythm of the heart identification technology and face recognition technology (including gender identification, face characteristic identification etc.) analysis are obtained
User emotion in video pictures, intelligence obtain the virtual mood animation to match with the user emotion and virtual special efficacy, go forward side by side
Row display.
A specific embodiment of the invention is described in more detail below in conjunction with schematic diagram.According to following description and
Claims, advantages and features of the invention will become apparent from.It should be noted that attached drawing is all made of very simplified form and
Using non-accurate ratio, only for the purpose of facilitating and clarifying the purpose of the embodiments of the invention.
For clarity, not describing whole features of a practical embodiment.In the following description, it is not described in detail well known function
Energy and structure, because they can make the present invention chaotic due to unnecessary details.It will be understood that in any one embodiment of reality
Exploitation in, it is necessary to make a large amount of implementation details to realize the specific objective of developer, such as according to related system or related quotient
The limitation of industry changes into another embodiment by an embodiment.Additionally, it should think that this development may be multiple
It is miscellaneous and time-consuming, but to those skilled in the art it is only routine work.
It should be noted that attached drawing is all made of very simplified form and using non-accurate ratio, only to convenient, bright
The purpose of one embodiment of the invention is aided in illustrating clearly.
Embodiment one
As shown in Figure 1, including following procedure the present embodiment provides a kind of method for enhancing video tastes: step S1, obtaining
First multimedia messages, first multimedia messages include image information and voice messaging.
Step S2, recognition of face is carried out to the image information in the first multimedia messages acquired in current time, obtained
Gender information and portrait expression information.
The step S2 also includes: pre-establishing face template feature database;The facial image in described image information is extracted,
Call face template feature database, by the facial image and the facial image sample that is stored in the face template feature database into
Row matching, obtains matched facial image sample, and gender information associated with the matched facial image sample and people
As expression information.
The gender information includes: (Z1: male, Z2: women);Expression library is previously provided in the face template feature database
A { a1, a2, a3 ... }, wherein for example: definable a1 includes but is not limited to: laughing, smiles and grins and laughs at;A2 includes but not
It is limited to: angry, angry and ferocious;A3 includes but is not limited to: sorrow crys and wails;To obtain portrait expression information.
Step S3, the voice messaging in the first multimedia messages acquired in current time is analyzed, obtains voice
Decibel fluctuation status information and crucial type of emotion information.
The decibel fluctuation status information includes normal decibel fluctuation status and abnormal decibel fluctuation status;Record institute's predicate
Voice decibel s per second in message breath calculates the first average decibel value S1 in first time interval t1 seconds interval;Calculate the
The second average decibel value S2 in the second time interval value t2 seconds intervals before one time interval t1;It is average to calculate described first
Decibel value S1 and second is averaged the percentage of decibel value S2, obtains average decibel percent value X, judgement, when the average decibel
When percent value X is more than or equal to 0.8x, the obtained decibel fluctuation status information is normal decibel fluctuation status;When described equal
When decibel percent value X is less than 0.8x, the obtained decibel fluctuation status information is abnormal decibel fluctuation status;Wherein, x is
Default decibel threshold.
In the present embodiment, the value of the first time interval t1 is for example are as follows: 5 seconds.The second time interval value t2
Value be, for example, 10 seconds.
The decibel fluctuation status information can also obtain in the following manner, can in advance be divided into sound decibel multiple
Grade, such as: first order S1:10~20 decibel.Second level S2:20~30 decibel.Third level S3:30~40 decibel.The fourth stage
S4:40~50 decibel.Level V S5:50~60 decibel.6th grade of S6:60~70 decibel.7th grade of S7:70~80 decibel;The
Eight grades: greater than 80 decibels.The decibel that the 6th grade of S6 or more includes the 6th grade of S6 is wherein defined, speaking point when outroaring to quarrel
Shellfish corresponds to abnormal decibel fluctuation status.The decibel that the 6th grade of S6 or less does not include the 6th grade of S6 is wherein defined, is chatted to be normal
It when decibel of speaking, that is, correspond to normal decibel fluctuation status.The first average decibel value in first time interval t1 is obtained,
Judge the grade where the first average decibel value, can determine whether that the decibel fluctuation status information is normal point according to the grade
Shellfish fluctuation status or abnormal decibel fluctuation status.
Obtaining the crucial type of emotion information includes following procedure: pre-establishing crucial mood literal pool;To institute's predicate
Message breath carries out speech recognition and obtains text information, calls crucial mood literal pool, by the text information and is stored in described
Text sample in crucial mood literal pool is matched, and obtains matched text sample, and with the matched text sample
Associated key type of emotion.
The key mood literal pool includes but is not limited to: W1:{ " jees ", " too severe ", " praising very much " is " perfect
" ...;W2:{ " tastes bad very much ", " not liking very much ", " plain " ... ... };W3:{ " can manage it ", " being ok ", and " one
As ", " all pretty good " ... ... };W4:{ " I has nothing to do ", " I am fine ", " I does not have anger ", " I sleeps " ... ... }.
Step S4, mood model library is called, according to the gender information, portrait expression information, voice decibel fluctuation status
It is matched, is obtained described in current time more than first with the mood model in the mood model library with crucial type of emotion information
Personage's mood in media information, and default mood animation associated with personage's mood and virtual special efficacy.
Step S5, by with described in the default mood animation of personage's mood associated and virtual special efficacy and current time
First multimedia messages are integrated, and the second multimedia messages are obtained;Step S6, second multimedia messages are shown.
Embodiment two
As shown in Fig. 2, the method based on enhancing video tastes described in embodiment one, enhance video described in the present embodiment two
The method of experience and the difference of the embodiment one are only that: also being included: step S7, being obtained first multimedia messages
When, the synchronous rhythm of the heart fluctuation status information for obtaining the user;Later, S4 is entered step, at this point, the step S4 is to call mood
Model library, according to the gender information, portrait expression information, voice decibel fluctuation status, crucial type of emotion information and described
The rhythm of the heart fluctuation status information of user is matched with the mood model in the mood model library, is obtained described in current time
Personage's mood in one multimedia messages, and default mood animation associated with personage's mood and virtual special efficacy;So
Afterwards, S5 is entered step.
Further, the rhythm of the heart fluctuation status information includes: normal cardiac rhythm fluctuation status and abnormal heart rhythm fluctuation status;
The rhythm of the heart h of the user is persistently recorded, the first mean heart rate value H1 in third time interval t3 seconds intervals is calculated;Calculate third
The second mean heart rate value H2 in the 4th time interval value t4 seconds intervals before time interval t3;Calculate the described first average heart
The percentage of rule value H1 and the second mean heart rate value H2 obtain mean heart rate percent value H, judgement, when the mean heart rate hundred
When ratio H being divided to be more than or equal to 0.8y, the obtained rhythm of the heart fluctuation status information is normal cardiac rhythm fluctuation status;When described average
When rhythm of the heart percent value H is less than 0.8y, the obtained rhythm of the heart fluctuation status information is abnormal heart rhythm fluctuation status;Wherein, y is
Default rhythm of the heart threshold value.
In the present embodiment, the value of the third time interval t3 is for example are as follows: 5 seconds.The second time interval value t4
Value be, for example, 10 seconds.
The rhythm of the heart fluctuation status information can also obtain in the following manner, can in advance be divided into the rhythm of the heart multiple etc.
Grade, such as: it can define, first order H1: < 4 times/5 seconds.Second level H2:4~5 time/5 second.Third level H3:5~5.8 time/5 second.The
Level Four H4:5.8~6.6 time/5 second.Level V H5:6.6~7.5 time/5 second.6th grade of H6:7.5~8.3 time/5 second.7th grade
H7:8.3~9.1 time/5 second.8th grade of H8:9.1~10 time/5 second.9th grade H9: > 10 times/5 seconds.Wherein the first~seven grade
For normal cardiac rhythm fluctuation status, the eight~nine grade is abnormal heart rhythm fluctuation status.When rhythm of the heart average value obtained every 5 seconds is in
Eight grades hereinafter, the rhythm of the heart fluctuation status information is then normal cardiac rhythm fluctuation status;When rhythm of the heart average value obtained every 5 seconds in
8th grade or more includes the 8th grade, and the rhythm of the heart fluctuation status information is then abnormal heart rhythm fluctuation status.
Embodiment three, as shown in figure 3, the method based on enhancing video tastes described in embodiment one and embodiment two, this
The method of enhancing video tastes described in embodiment is suitable for more people's video communications comprising: lead to when multiple users carry out video
When news, step S10, synchronous the first multimedia messages for obtaining each user, first multimedia messages include image information
And voice messaging;Step S20, lip reading identification and speech recognition are carried out to first multimedia messages of each user respectively,
For positioning the user that current time speaking, the first multimedia messages step of the user is determined;Step S30, to current
Image information in the first multimedia messages of the user acquired in moment carries out recognition of face, obtains gender information and people
As expression information;Step S40, the voice messaging in the first multimedia messages acquired in current time is analyzed, is obtained
Voice decibel fluctuation status information and crucial type of emotion information;Step S50, mood model library is called, according to the gender
Information, portrait expression information, voice decibel fluctuation status, crucial type of emotion information and rhythm of the heart fluctuation status information and the feelings
Mood model in thread model library is matched, and personage's mood in the first multimedia messages described in current time is obtained, and
Default mood animation associated with personage's mood and virtual special efficacy;Step S60, by with personage's mood associated
First multimedia messages of default mood animation and virtual special efficacy and the user at current time integrate, and are corresponded to
In the second multimedia messages of the user;Step S70, second multimedia messages are shown at the position of the user window.
Example IV, as shown in figure 4, being based on embodiment three, the present embodiment and the difference of embodiment three are, also include:
Step S80, when obtaining each first multimedia messages, the corresponding synchronous rhythm of the heart fluctuation status information for obtaining the user;
Later, S50 is entered step, at this point, the step S50 is to call mood model library, is believed according to the gender information, portrait expression
Breath, voice decibel fluctuation status, crucial type of emotion information and the rhythm of the heart fluctuation status information of the user and the mood model
Mood model in library is matched, and obtains personage's mood in the first multimedia messages described in current time, and with it is described
The associated default mood animation of personage's mood and virtual special efficacy;Then, S60 is entered step.
Embodiment five, as shown in figure 5, being based on embodiment one, the present embodiment also discloses a kind of dress for enhancing video tastes
It sets, comprising: obtain module 100, be configured as obtaining the first multimedia messages, first multimedia messages include image letter
Breath and voice messaging.Identification module (unlabeled in figure) is configured as identification key message;Processing module (is not marked in figure
Number), it is configured as handling first multimedia messages according to the key message, to obtain the second multimedia letter
Breath;And display module 105, it is configured as showing second multimedia messages.
The identification module includes face identification unit 101 and voice recognition unit 102;The face identification unit 101
For in the first multimedia messages acquired in current time image information carry out recognition of face, obtain gender information and
Portrait expression information.The voice recognition unit 102 is used for the voice in the first multimedia messages acquired in current time
Information is analyzed, and voice decibel fluctuation status information and crucial type of emotion information are obtained.
The processing module includes matching unit 103 and integrated unit 104, and the matching unit 103 is for calling mood
Model library, according to the gender information, portrait expression information, voice decibel fluctuation status and crucial type of emotion information with it is described
Mood model in mood model library is matched, and personage's mood in the first multimedia messages described in current time is obtained, with
And default mood animation associated with personage's mood and virtual special efficacy.The integrated unit 104 is used for will be with the people
First multimedia messages at the default mood animation of principle thread associated and virtual special efficacy and current time are integrated, and are obtained
To the second multimedia messages.
Embodiment six
As shown in fig. 6, being based on embodiment two and embodiment five, the present embodiment and the difference of embodiment five are, include
Rhythm of the heart test module 106 is configured as when obtaining first multimedia messages, the synchronous rhythm of the heart fluctuation for obtaining the user
Status information, and the matching unit 103 is made to call mood model library, according to the gender information, portrait expression information,
Voice decibel fluctuation status, the rhythm of the heart fluctuation status information of crucial type of emotion information and the user and the mood model library
In mood model matched, obtain personage's mood in the first multimedia messages described in current time, and with the people
The associated default mood animation of principle thread and virtual special efficacy.
Embodiment seven
As shown in fig. 7, being based on embodiment three and embodiment six, the difference of the present embodiment and above-described embodiment 6 is, when
When more people's video communications, increase locating unit 107, is configured to first multimedia letter to each user
Breath carries out lip reading identification and speech recognition, for positioning the user that current time speaking, determines more than first matchmaker of the user
Body information Step makes the face identification unit 101, voice recognition unit 102, matching unit 103, integrated unit later
104, display module 105 and rhythm of the heart test module 106 carry out the video image of the user currently to speak oriented
It handles and corresponds to and be shown on each user terminal.
In above-mentioned any one embodiment, second multimedia messages can also be stored, alternatively, being arranged for storing
State the memory module of the second multimedia messages.
Embodiment eight
As shown in figure 8, the enhancing video tastes method described in based on the above embodiment, present embodiment discloses a kind of electronics
Terminal device includes: processor 200, memory 201 and is stored on the memory and can run on the processor
Computer program, the processor 200 realizes any one reality in one~example IV of foregoing embodiments when executing described program
Apply example enhancing video tastes method.
The electric terminal equipment can be mobile phone, game console, computer, tablet device, personal digital assistant
Deng.
The electric terminal equipment further include: power module 202, interactive component 203, communication module 204, sensor module
205 and interface 206.The integrated operation of the usual electric terminal equipment of processor 200, such as with display, call, data are logical
Letter, camera operation and record operate associated operation.Processor 200 may include one or more modules, be convenient for processor
Interaction between 200 and other modules.For example, processor 200 may include multi-media module, to facilitate 203 He of interactive component
Interaction between processor 200.Memory 201 is configured as storing various types of data to support in electric terminal equipment
Operation.The example of these data includes the instruction of any application or method for operating on electric terminal equipment, connection
It is personal data, telephone book data,
Message, picture, video etc..Memory 201 can by any kind of volatibility or non-volatile memory device or
Person's their combination is realized, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM),
Erasable Programmable Read Only Memory EPROM (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic storage
Device, flash memory, disk or CD.
Power module 202 is the various modules with power of electric terminal equipment.Power module 202 may include power supply pipe
Reason system, one or more power supplys and other with for electric terminal equipment generate, manage, and distribute the associated module of electric power.
Interactive component 203 includes the screen of one output interface of offer between electric terminal equipment and user.In some embodiments
In, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel, screen can be by
Touch screen is embodied as, to receive input signal from the user.Touch panel includes one or more touch sensors to sense
Gesture on touch, slide, and touch panel.Touch sensor can not only sense the boundary of a touch or slide action, but also
Detection duration and pressure relevant to touch or slide.In some embodiments, interactive component 203 is including before one
Set camera and/or rear camera.It is such as in a shooting mode or a video mode, preceding when electric terminal equipment is in operation mode
It sets camera and/or rear camera can receive external multi-medium data.Each front camera and rear camera can
Be a fixed optical lens system or have focusing and optical zoom capabilities.
Interactive component 203 further includes that audio-frequency module is configured as output and/or input audio signal.For example, audio-frequency module
Including a microphone (MIC), when electric terminal equipment is in operation mode, such as call model, logging mode and speech recognition
When mode, microphone is configured as receiving external audio signal.The received audio signal can be further stored in storage
Device 201 is sent via communication module 204.In some embodiments, audio-frequency module further includes a loudspeaker, for exporting sound
Frequency signal.The interface that interface 206 is I/O is that interface is provided between processor 200 and peripheral interface module, above-mentioned peripheral interface mould
Block can be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button
And locking press button.
Sensor module 205 includes one or more sensors, for providing the shape of various aspects for electric terminal equipment
State assessment.For example, sensor module 205 can detecte the state that opens/closes of electric terminal equipment, module it is relatively fixed
Position, such as component are the display and keypad of electric terminal equipment, and sensor module 205 can also detect electric terminal equipment
Or the position change of one component of electric terminal equipment, the existence or non-existence that user contacts with electric terminal equipment, electronics are whole
End equipment orientation or acceleration/deceleration and its temperature change.Sensor module 205 may include proximity sensor, be configured to
It detects the presence of nearby objects without any physical contact.Sensor module 205 can also include optical sensor, such as
CMOS or ccd image sensor, for being used in imaging applications.In some embodiments, which can be with
Including acceleration transducer, gyro sensor, Magnetic Sensor, pressure sensor or temperature sensor.Communication module 204 is matched
It is set to convenient for the communication of wired or wireless way between electric terminal equipment and other equipment.Electric terminal equipment can access base
In the wireless network of communication standard, such as WiFi, 2G or 3G or their combination.In one exemplary embodiment, communication module
204 receive broadcast singal or broadcast related information from external broadcasting management system via broadcast channel.It is exemplary at one
In embodiment, communication module 204 further includes near-field communication (NFC) module, to promote short range communication.For example, NFC module can base
In radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band (UWB) technology, bluetooth (BT) technology and its
His technology is realized.
In conclusion the present invention, by step S1, the first multimedia messages of acquisition, first multimedia messages include figure
As information and voice messaging;Step S2, face is carried out to the image information in the first multimedia messages acquired in current time
Identification, obtains gender information and portrait expression information;Step S3, in the first multimedia messages acquired in current time
Voice messaging is analyzed, and voice decibel fluctuation status information and crucial type of emotion information are obtained;Step S4, mood is called
Model library, according to the gender information, portrait expression information, voice decibel fluctuation status and crucial type of emotion information with it is described
Mood model in mood model library is matched, and personage's mood in the first multimedia messages described in current time is obtained, with
And default mood animation associated with personage's mood and virtual special efficacy;It step S5, will be with personage's mood associated
Default mood animation and virtual special efficacy and first multimedia messages at current time integrated, obtain the second multimedia
Information;Step S6, second multimedia messages are shown.Wherein, the present invention can be with automatic identification video communication or recorded video
When in video pictures in user's portrait, the mood of user is independently analyzed in conjunction with recognition of face and speech recognition, and be automatically
The suitable virtual mood animation of mood matching of current time user and virtual special efficacy, and it is by the virtual mood animation and virtually special
Effect is shown in user terminal and is shown, increases user experience and interest.Also, the present invention can also increase rhythm of the heart knowledge
Not, by the way that the rhythm of the heart is identified that obtained rhythm of the heart fluctuation status information and speech recognition, the functions such as facial image identification are tied
It closes, further improves and matched accuracy is analyzed to active user's mood.The present disclosure additionally applies in more people's video communications, increase
When being added in more people's video communications, mutually tied by carrying out the identification of portrait lip reading to multiple users in video pictures with speech recognition
It closes, orients the user that current time speaking, and analyze the mood of the user, be its matching virtual mood animation and virtual
Special efficacy, and it is shown in the user terminal of each user, further enhance user video experience interest.
It is discussed in detail although the contents of the present invention have passed through above preferred embodiment, but it should be appreciated that above-mentioned
Description is not considered as limitation of the present invention.After those skilled in the art have read above content, for of the invention
A variety of modifications and substitutions all will be apparent.Therefore, protection scope of the present invention should be limited to the appended claims.
Claims (20)
1. a kind of method for enhancing video tastes, which is characterized in that include following procedure:
The first multimedia messages are obtained, key message is identified, first multimedia messages is carried out according to the key message
Processing, to obtain the second multimedia messages.
2. the method for enhancing video tastes as described in claim 1, which is characterized in that also include: described in display and/or storage
Second multimedia messages.
3. the method for enhancing video tastes as described in claim 1, which is characterized in that first multimedia messages include figure
As information and voice messaging.
4. the method for enhancing video tastes as described in claim 1, which is characterized in that the identification key message includes: pair
Image information in first multimedia messages acquired in current time carries out recognition of face, obtains gender information and portrait table
Feelings information;
Voice messaging in first multimedia messages acquired in current time is analyzed, voice decibel fluctuation status is obtained
Information and crucial type of emotion information.
5. as described in claim 1 enhancing video tastes method, which is characterized in that it is described according to the key message to institute
The first multimedia messages are stated to be handled further include: call mood model library, according to the gender information, portrait expression information,
Voice decibel fluctuation status and crucial type of emotion information are matched with the mood model in the mood model library, are worked as
Personage's mood in first multimedia messages described in the preceding moment, and default mood animation associated with personage's mood and
Virtual special efficacy;
By first multimedia with the default mood animation of personage's mood associated and virtual special efficacy and current time
Information is integrated, and the second multimedia messages are obtained.
6. the method for enhancing video tastes as claimed in claim 5, which is characterized in that the identification key message is further gone back
Include: pre-establishing face template feature database;
The facial image in described image information is extracted,
Face template feature database is called, by the facial image and the facial image sample being stored in the face template feature database
This is matched, and obtains matched facial image sample, and gender information associated with the matched facial image sample
With portrait expression information.
7. the method for enhancing video tastes as claimed in claim 6, which is characterized in that the decibel fluctuation status information includes
Normal decibel fluctuation status and abnormal decibel fluctuation status;
The voice decibel s per second in the voice messaging is recorded, first calculated in first time interval t1 seconds interval is averaged
Decibel value S1;The second average decibel value S2 in the second time interval value t2 seconds intervals before calculating first time interval t1;
It calculates the described first average decibel value S1 and second be averaged the percentage of decibel value S2, obtains the decibel percent value X that is averaged, sentence
Disconnected, when the average decibel percent value X is more than or equal to 0.8x, the obtained decibel fluctuation status information is normal decibel
Fluctuation status;
When the equal decibel percent value X is less than 0.8x, the obtained decibel fluctuation status information is abnormal decibel fluctuation
State;Wherein, x is default decibel threshold.
8. the method for enhancing video tastes as claimed in claim 7, which is characterized in that obtain the crucial type of emotion information
Include following procedure: pre-establishing crucial mood literal pool;
Speech recognition is carried out to the voice messaging and obtains text information,
Call crucial mood literal pool, by the text information and the text sample that is stored in the crucial mood literal pool into
Row matching obtains matched text sample, and crucial type of emotion associated with the matched text sample.
9. the method for the enhancing video tastes as described in any one of claim 1~8, which is characterized in that also include: obtaining
When taking first multimedia messages, the synchronous rhythm of the heart fluctuation status information for obtaining the user;Later, mood model library is called,
According to the gender information, portrait expression information, voice decibel fluctuation status, crucial type of emotion information and the user the heart
Rule fluctuation status information is matched with the mood model in the mood model library, obtains the first multimedia described in current time
Personage's mood in information, and default mood animation associated with personage's mood and virtual special efficacy;It then, will be with institute
The default mood animation and virtual special efficacy and first multimedia messages at current time for stating personage's mood associated collect
At obtaining the second multimedia messages.
10. the method for enhancing video tastes as claimed in claim 9, which is characterized in that the rhythm of the heart fluctuation status packet
Contain: normal cardiac rhythm fluctuation status and abnormal heart rhythm fluctuation status;
The rhythm of the heart h of the user is persistently recorded, the first mean heart rate value H1 in third time interval t3 seconds intervals is calculated;It calculates
The second mean heart rate value H2 in the 4th time interval value t4 seconds intervals before third time interval t3;It is flat to calculate described first
The percentage of equal rhythm of the heart value H1 and the second mean heart rate value H2, obtain mean heart rate percent value H, judge, when the average heart
When restraining percent value H more than or equal to 0.8y, the obtained rhythm of the heart fluctuation status information is normal cardiac rhythm fluctuation status;
When the mean heart rate percent value H is less than 0.8y, the obtained rhythm of the heart fluctuation status information is abnormal heart rhythm wave
Dynamic state;Wherein, y is default rhythm of the heart threshold value.
11. a kind of method for enhancing video tastes, which is characterized in that include following procedure: when multiple users carry out video communication
When,
Synchronous the first multimedia messages for obtaining each user, first multimedia messages include image information and voice letter
Breath;
The key message for identifying first multimedia messages of each user respectively, according to the key message to currently
First multimedia messages of the user to speak are handled, to obtain the second multimedia messages corresponding to the user, and
It is shown at the position of the user window.
12. the method for enhancing video tastes as claimed in claim 11, which is characterized in that first multimedia messages include
Image information and voice messaging.
13. the method for enhancing video tastes as claimed in claim 12, which is characterized in that described to identify each user's respectively
The key message of first multimedia messages specifically:
Lip reading identification and speech recognition are carried out to first multimedia messages of each user, for positioning current time
The user to speak determines the first multimedia messages of the user;
Recognition of face is carried out to the image information in the first multimedia messages of the user acquired in current time, obtains gender
Information and portrait expression information;
Voice messaging in first multimedia messages acquired in current time is analyzed, voice decibel fluctuation status is obtained
Information and crucial type of emotion information.
14. the method for enhancing video tastes as claimed in claim 13, which is characterized in that described according to the key message pair
First multimedia messages of the user currently to speak are handled specifically:
Mood model library is called, according to the gender information, portrait expression information, voice decibel fluctuation status, crucial mood class
Type information and rhythm of the heart fluctuation status information are matched with the mood model in the mood model library, are obtained described in current time
Personage's mood in first multimedia messages, and default mood animation associated with personage's mood and virtual special efficacy;
By described with the default mood animation of personage's mood associated and virtual special efficacy and the user at current time
One multimedia messages are integrated, and the second multimedia messages corresponding to the user are obtained.
15. the method for enhancing video tastes as claimed in claim 14, which is characterized in that also include: obtaining each user
First multimedia messages when, the corresponding synchronous rhythm of the heart fluctuation status information for obtaining the user;Later, mood model is called
Library, according to the gender information, portrait expression information, voice decibel fluctuation status, crucial type of emotion information and the user
Rhythm of the heart fluctuation status information is matched with the mood model in the mood model library, obtains more than first matchmaker described in current time
Personage's mood in body information, and default mood animation associated with personage's mood and virtual special efficacy;It then, will be with
First multimedia of the default mood animation of personage's mood associated and virtual special efficacy and the user at current time
Information is integrated, and the second multimedia messages corresponding to the user are obtained.
16. it is a kind of enhance video tastes device, characterized by comprising:
Module is obtained, is configured as obtaining the first multimedia messages;
Identification module is configured as identification key message;
Processing module is configured as handling first multimedia messages according to the key message, to obtain
Two multimedia messages.
17. the device of enhancing video tastes as claimed in claim 16, which is characterized in that also include:
Display module is configured as showing second multimedia messages.
18. the device of enhancing video tastes as claimed in claim 17, which is characterized in that first multimedia messages include
Image information and voice messaging.
19. the device of enhancing video tastes as claimed in claim 18, which is characterized in that also include: face identification unit,
It is configured as carrying out recognition of face to the image information in the first multimedia messages acquired in current time, obtains gender information
And portrait expression information;
Voice recognition unit is configured as dividing the voice messaging in the first multimedia messages acquired in current time
Analysis obtains voice decibel fluctuation status information and crucial type of emotion information;
Matching unit is configured as calling mood model library, according to the gender information, portrait expression information, voice decibel
Fluctuation status and crucial type of emotion information are matched with the mood model in the mood model library, obtain current time institute
State personage's mood in the first multimedia messages, and default mood animation associated with personage's mood and virtual spy
Effect;
Integrated unit, be configured as by with the default mood animation of personage's mood associated and virtual special efficacy and it is current when
First multimedia messages carved are integrated, and the second multimedia messages are obtained.
20. a kind of electric terminal equipment is, characterized by comprising: processor, memory and it is stored on the memory simultaneously
The computer program that can be run on the processor, the processor realize such as claim 1~10 when executing described program
Any one of described in enhancing video tastes method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910630024.8A CN110377761A (en) | 2019-07-12 | 2019-07-12 | A kind of method and device enhancing video tastes |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910630024.8A CN110377761A (en) | 2019-07-12 | 2019-07-12 | A kind of method and device enhancing video tastes |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110377761A true CN110377761A (en) | 2019-10-25 |
Family
ID=68252986
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910630024.8A Pending CN110377761A (en) | 2019-07-12 | 2019-07-12 | A kind of method and device enhancing video tastes |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110377761A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111372029A (en) * | 2020-04-17 | 2020-07-03 | 维沃移动通信有限公司 | Video display method and device and electronic equipment |
CN111640199A (en) * | 2020-06-10 | 2020-09-08 | 浙江商汤科技开发有限公司 | AR special effect data generation method and device |
CN111865766A (en) * | 2020-07-20 | 2020-10-30 | 上海博泰悦臻电子设备制造有限公司 | Interactive method, medium, equipment and system based on audio-video transmission |
CN112132095A (en) * | 2020-09-30 | 2020-12-25 | Oppo广东移动通信有限公司 | Dangerous state identification method and device, electronic equipment and storage medium |
WO2022001604A1 (en) * | 2020-06-29 | 2022-01-06 | 北京字节跳动网络技术有限公司 | Data processing method and apparatus, and readable medium and electronic device |
CN114078476A (en) * | 2020-08-21 | 2022-02-22 | 观致汽车有限公司 | Vehicle-mounted character emotion display method and vehicle-mounted character emotion display device |
CN114449297A (en) * | 2020-11-04 | 2022-05-06 | 阿里巴巴集团控股有限公司 | Multimedia information processing method, computing equipment and storage medium |
CN114639395A (en) * | 2020-12-16 | 2022-06-17 | 观致汽车有限公司 | Voice control method and device for vehicle-mounted virtual character and vehicle with voice control device |
WO2023040633A1 (en) * | 2021-09-14 | 2023-03-23 | 北京字跳网络技术有限公司 | Video generation method and apparatus, and terminal device and storage medium |
-
2019
- 2019-07-12 CN CN201910630024.8A patent/CN110377761A/en active Pending
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111372029A (en) * | 2020-04-17 | 2020-07-03 | 维沃移动通信有限公司 | Video display method and device and electronic equipment |
CN111640199A (en) * | 2020-06-10 | 2020-09-08 | 浙江商汤科技开发有限公司 | AR special effect data generation method and device |
CN111640199B (en) * | 2020-06-10 | 2024-01-09 | 浙江商汤科技开发有限公司 | AR special effect data generation method and device |
WO2022001604A1 (en) * | 2020-06-29 | 2022-01-06 | 北京字节跳动网络技术有限公司 | Data processing method and apparatus, and readable medium and electronic device |
CN113934289A (en) * | 2020-06-29 | 2022-01-14 | 北京字节跳动网络技术有限公司 | Data processing method and device, readable medium and electronic equipment |
CN111865766A (en) * | 2020-07-20 | 2020-10-30 | 上海博泰悦臻电子设备制造有限公司 | Interactive method, medium, equipment and system based on audio-video transmission |
CN111865766B (en) * | 2020-07-20 | 2024-02-02 | 博泰车联网科技(上海)股份有限公司 | Interactive method, medium, equipment and system based on audio-video transmission |
CN114078476B (en) * | 2020-08-21 | 2023-12-19 | 观致汽车有限公司 | Vehicle-mounted figure emotion display method and vehicle-mounted figure emotion display device |
CN114078476A (en) * | 2020-08-21 | 2022-02-22 | 观致汽车有限公司 | Vehicle-mounted character emotion display method and vehicle-mounted character emotion display device |
CN112132095A (en) * | 2020-09-30 | 2020-12-25 | Oppo广东移动通信有限公司 | Dangerous state identification method and device, electronic equipment and storage medium |
CN114449297A (en) * | 2020-11-04 | 2022-05-06 | 阿里巴巴集团控股有限公司 | Multimedia information processing method, computing equipment and storage medium |
CN114639395A (en) * | 2020-12-16 | 2022-06-17 | 观致汽车有限公司 | Voice control method and device for vehicle-mounted virtual character and vehicle with voice control device |
WO2023040633A1 (en) * | 2021-09-14 | 2023-03-23 | 北京字跳网络技术有限公司 | Video generation method and apparatus, and terminal device and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110377761A (en) | A kind of method and device enhancing video tastes | |
CN109446876B (en) | Sign language information processing method and device, electronic equipment and readable storage medium | |
CN106339680B (en) | Face key independent positioning method and device | |
CN104954580B (en) | The processing method and processing device of subscriber calendar information | |
US8581953B2 (en) | Method and apparatus for providing animation effect on video telephony call | |
CN107123081A (en) | image processing method, device and terminal | |
CN110188236A (en) | A kind of recommended method of music, apparatus and system | |
CN106791370A (en) | A kind of method and apparatus for shooting photo | |
RU2636580C2 (en) | Method and device for displaying conversational interface | |
CN110517185A (en) | Image processing method, device, electronic equipment and storage medium | |
CN105302315A (en) | Image processing method and device | |
CN104035558A (en) | Terminal device control method and device | |
CN109831636A (en) | Interdynamic video control method, terminal and computer readable storage medium | |
CN107240143A (en) | Bag generation method of expressing one's feelings and device | |
CN106778531A (en) | Face detection method and device | |
EP3340077B1 (en) | Method and apparatus for inputting expression information | |
JPH10187931A (en) | Portrait transmitting and receiving device, portrait communication device and method, and portrait communication program storage medium | |
CN110399934A (en) | A kind of video classification methods, device and electronic equipment | |
CN113032627A (en) | Video classification method and device, storage medium and terminal equipment | |
CN107483826B (en) | The method and apparatus for generating video file | |
CN106791563A (en) | Information transferring method, local device, opposite equip. and system | |
CN108509863A (en) | Information cuing method, device and electronic equipment | |
CN108470321A (en) | U.S. face processing method, device and the storage medium of photo | |
CN112449098B (en) | Shooting method, device, terminal and storage medium | |
CN111341317A (en) | Method and device for evaluating awakening audio data, electronic equipment and 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 |