CN110446104A - Method for processing video frequency, device and storage medium - Google Patents
Method for processing video frequency, device and storage medium Download PDFInfo
- Publication number
- CN110446104A CN110446104A CN201910817479.0A CN201910817479A CN110446104A CN 110446104 A CN110446104 A CN 110446104A CN 201910817479 A CN201910817479 A CN 201910817479A CN 110446104 A CN110446104 A CN 110446104A
- Authority
- CN
- China
- Prior art keywords
- video
- target
- target object
- information
- role
- 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
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/431—Generation of visual interfaces for content selection or interaction; Content or additional data rendering
- H04N21/4312—Generation of visual interfaces for content selection or interaction; Content or additional data rendering involving specific graphical features, e.g. screen layout, special fonts or colors, blinking icons, highlights or animations
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream, rendering scenes according to MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream
Abstract
The present invention provides a kind of method for processing video frequency, device and storage mediums;Method includes: the broadcast interface by target video, receives Object identifying instruction, and the Object identifying instruction is used to indicate the object identified in the target video;It is instructed based on the Object identifying, determines the target object in the target video;The identification request for sending the corresponding target object determines the portrait information of Role Information and the target object of the target object in the target video to request based on the identification;Receive the Role Information returned and the portrait information;By the broadcast interface of the target video, the Role Information and the portrait information is presented.By means of the invention it is possible to rapidly obtain the Role Information and portrait information of target object, the perception experience of user is improved.
Description
Technical field
This application involves field of computer technology more particularly to a kind of method for processing video frequency, device and storage medium.
Background technique
With the popularization of intelligent terminals, viewing video is more and more convenient, and user using intelligent terminal (for example, video
Class client) viewing the videos such as movie and television play or variety show when, often encounter a bit be familiar with but forget drilling for name
Member or star, if or fail the Role Information from the beginning watched in video or video it is more complicated when, often do not remember clearly in video
Certain Role Informations.In order to meet the aspiration to knowledge of user, the relevant technologies need user to suspend video playing, carry out to associated video
Screenshot, then the relative role in screenshot is scanned for by search engine, the tediously long complexity of operating process is brought to user
Bad perception experience.
Summary of the invention
The embodiment of the present invention provides a kind of method for processing video frequency, device and storage medium, can rapidly obtain target pair
The Role Information and portrait information of elephant, improve the perception experience of user.
The embodiment of the present invention provides a kind of method for processing video frequency, comprising:
By the broadcast interface of target video, Object identifying instruction is received, the Object identifying instruction is used to indicate knowledge
Object in the not described target video;
It is instructed based on the Object identifying, determines the target object in the target video;
The identification request for sending the corresponding target object determines that the target object exists to request based on the identification
The portrait information of Role Information and the target object in the target video;
Receive the Role Information returned and the portrait information;
By the broadcast interface of the target video, the Role Information and the portrait information is presented.
The embodiment of the present invention also provides a kind of video process apparatus, comprising:
Receiving unit receives Object identifying instruction for the broadcast interface by target video, and the Object identifying refers to
Enable the object for being used to indicate and identifying in the target video;
Determination unit determines the target object in the target video for instructing based on the Object identifying;
Transmission unit, the identification request for sending the corresponding target object determine institute to request based on the identification
State the portrait information of Role Information and the target object of the target object in the target video;
Receiving unit, for receiving the Role Information returned and the portrait information;
The Role Information and portrait letter is presented for passing through the broadcast interface of the target video in display unit
Breath.
In above scheme, the determination unit is also used to instruct in response to the Object identifying, obtains the target video
Video frame images corresponding to currently playing interface;
Object identifying is carried out to the video frame images, determines that the quantity for the object for including in the video frame images is one
When a, using the object for including in the video frame images as the target object.
In above scheme, the determination unit is also used to determine that the quantity for the object for including in the video frame images is
When multiple, the Object Selection interface of corresponding multiple objects is presented;
In response to the Object Selection instruction received by the Object Selection interface, the Object Selection is instructed signified
Show the object selected as the target object.
In above scheme, the transmission unit is also used to send the identification request of the corresponding target object, the identification
Request carries the frame image of the target object, feature extraction is carried out with the frame image to the target object, by the spy of extraction
Sign is compared with the role characteristic for corresponding to the target video in video library, determines the target object in the target video
In role and return to corresponding Role Information;
Receive the Role Information returned.
In above scheme, the transmission unit is also used to send the identification request of the corresponding target object, the identification
Request carries the frame image of the target object, feature extraction is carried out with the frame image to the target object, by the spy of extraction
It levies and is compared with the feature in portrait information bank, determine the portrait information of the target object and return to the portrait information;
Obtain the role characteristic of the target video;
The role characteristic of the target video is sent, described in determining based on the role characteristic and the portrait information
Role of the target object in the target video simultaneously returns to corresponding Role Information;
Receive the Role Information returned.
In above scheme, the display unit is also used to the Role Information and the portrait to the target object
Information carries out integration processing, obtains the load card of the target object;
By the broadcast interface of the target video, the load card of the target object is presented.
In above scheme, at least one interaction key of the relevant target object, institute are set in the load card
Stating device further includes interactive unit:
The interactive unit, for determining the clicking operation institute in response to the clicking operation for the interaction key
The interactive information of the correspondence of the instruction target object, the interactive information incline to the emotion of the target object for characterizing
To;
The interactive information of the corresponding target object is sent, to realize the pass of the interactive information Yu the target object
Connection.
The embodiment of the present invention also provides a kind of video process apparatus, comprising:
Memory, for storing executable instruction;
Processor when for executing the executable instruction stored in the memory, is realized provided in an embodiment of the present invention
Method for processing video frequency.
The embodiment of the present invention also provides a kind of storage medium, is stored with executable instruction, when for causing processor to execute,
Realize method for processing video frequency provided in an embodiment of the present invention.
The embodiment of the present invention has the advantages that
Instructed by the broadcast interface Object identifying of target video, determine the target object in target video, and based on pair
It answers the identification of target object to request, determines the portrait letter of Role Information and target object of the target object in target video
Breath;By the broadcast interface of target video, Role Information and portrait information is presented;It so, it is possible by a key operation, rapidly
The Role Information and portrait information of target object are obtained, and user will not be interrupted and watch video, so that the sight of user be substantially improved
Sense experience;Also, for video playing client, user's viscosity can be also promoted, customer churn is reduced.
Detailed description of the invention
Figure 1A is the method for processing video frequency flow diagram that the relevant technologies provide;
Figure 1B is the method for processing video frequency flow diagram that the relevant technologies provide;
Fig. 1 C is the method for processing video frequency flow diagram that the relevant technologies provide;
Fig. 1 D is the method for processing video frequency flow diagram that the relevant technologies provide;
Fig. 1 E is the method for processing video frequency flow diagram that the relevant technologies provide;
Fig. 2 is an optional configuration diagram of processing system for video provided in an embodiment of the present invention;
Fig. 3 is the hardware structural diagram of video process apparatus provided in an embodiment of the present invention;
Fig. 4 is method for processing video frequency flow diagram provided in an embodiment of the present invention;
Fig. 5 is the broadcast interface schematic diagram that video playing client provided in an embodiment of the present invention is presented;
Fig. 6 is the interface schematic diagram of determining target object provided in an embodiment of the present invention;
Fig. 7 is the interface schematic diagram of determining target object provided in an embodiment of the present invention;
Fig. 8 is the display interface schematic diagram of method for processing video frequency provided in an embodiment of the present invention;
Fig. 9 is the display interface schematic diagram of method for processing video frequency provided in an embodiment of the present invention;
Figure 10 is the display interface schematic diagram of method for processing video frequency provided in an embodiment of the present invention;
Figure 11 is method for processing video frequency flow diagram provided in an embodiment of the present invention;
Figure 12 is method for processing video frequency flow diagram provided in an embodiment of the present invention;
Figure 13 is the structural schematic diagram of video process apparatus provided in an embodiment of the present invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention make into
It is described in detail to one step, described embodiment is not construed as limitation of the present invention, and those of ordinary skill in the art are not having
All other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
In the following description, it is related to " some embodiments ", which depict the subsets of all possible embodiments, but can
To understand, " some embodiments " can be the same subsets or different subsets of all possible embodiments, and can not conflict
In the case where be combined with each other.
Unless otherwise defined, all technical and scientific terms used herein and belong to technical field of the invention
The normally understood meaning of technical staff is identical.Term used herein is intended merely to the purpose of the description embodiment of the present invention,
It is not intended to limit the present invention.
Before the embodiment of the present invention is further elaborated, to noun involved in the embodiment of the present invention and term
It is illustrated, noun involved in the embodiment of the present invention and term are suitable for following explanation.
1) client, run in terminal for providing the application program of various services, such as video playing client.
2) portrait information, i.e. user are drawn a portrait, including user interest portrait and user base portrait;Wherein,
User interest portrait, refers to the virtual representations of real user, is built upon a series of target on attribute datas and uses
Family model is used to indicate the interest classification of user;
User base portrait, according to the Real Name of user, gender, age take in situation, reside and log in users' bases such as ground
The information overall picture of the user for the labeling that plinth information goes out.
3) in response to the condition or state relied on for indicating performed operation, when the relied on condition of satisfaction
Or when state, performed one or more operations be can be in real time, it is possible to have the delay of setting;Do not saying especially
In the case where bright, there is no the limitations for executing sequencing for performed multiple operations.
It is the method for processing video frequency flow diagram that the relevant technologies provide referring to Figure 1A-Fig. 1 E, Figure 1A-Fig. 1 E, passes through view
Frequency client end of playing back plays target video, when user wants to know about the relevant information of the target object occurred in target video,
Firstly, intercepting target object using the screenshot tool in video playing client, the picture comprising target object is obtained, is then beaten
Any search engine in such as A~H browser is opened, such as G browser, the picture comprising target object of interception is imported into search
It is scanned in engine, obtains the data information of target object, the data information of obtained target object is finally returned into view
Frequency client end of playing back is presented, in this way, user while understanding the data information of target object, can continue to watch target view
Frequently.
However, as in figs. 1 a-e, above-mentioned method for processing video frequency in the related technology is needed by following steps:
1. screenshot is saved in system photograph album;2. opening G browser searches;3. opening is scanned for picture;It is cut 4. importing
Figure scans for;5. obtaining data information;6. return to video playing client continue viewing and etc. could complete, operation stream
The tediously long complexity of journey brings bad perception to user and experiences;Meanwhile it executing above method needs and being carried out in multiple client
Switching, video playing client user may greatly be lost in this operating process.
Based on this, video playing client end response of the invention is instructed in the broadcast interface Object identifying of target video, really
The target object to set the goal in video sends the identification request of corresponding target object, to determine target object based on identification request
The portrait information of Role Information and target object in target video;And by the broadcast interface of target video, angle is presented
Color information and portrait information;It so, it is possible the Role Information for by a key operation, rapidly obtaining target object and portrait letter
Breath, and user will not be interrupted and watch video, so that the perception experience of user be substantially improved;Also, to video playing client
Speech can also promote user's viscosity, reduce customer churn.
Illustrate the exemplary application for realizing the device of the embodiment of the present invention below, device provided in an embodiment of the present invention can be with
Various types of user terminals such as smart phone, tablet computer, laptop are embodied as, also may be embodied as platform server.
In the following, the exemplary application that terminal will be covered when illustrating that device is embodied as terminal.
Referring to fig. 2, Fig. 2 is an optional configuration diagram of processing system for video 100 provided in an embodiment of the present invention,
An exemplary application is supported to realize, terminal 400 (illustrating terminal 400-1 and terminal 400-2) passes through network 300
Background server 200 is connected, network 300 can be wide area network or local area network, or be combination, use radio chains
Realize data transmission in road.
Terminal 400 (such as terminal 400-1) is provided with video playing client, can pass through video playing client terminal playing mesh
Video is marked, and is provided with Object identifying button, terminal 400 is used for the broadcast interface by target video, receives Object identifying
Instruction, Object identifying instruction are used to indicate the object in identification target video;It is instructed, is determined in target video based on Object identifying
Target object;And the identification for sending corresponding target object is requested to background server 200;
Background server 200 is used to request based on identification, determines Role Information of the target object in the target video,
And the portrait information of target object;And determining Role Information and portrait information are returned into terminal 400;
Terminal 400 receives the Role Information and the portrait information that background server 200 returns, and passes through broadcasting for target video
Interface is put, the Role Information received and portrait information is presented.
It elaborates below to the hardware configuration of the video process apparatus of the embodiment of the present invention, Fig. 3 is that the present invention is implemented
Example provides the composition schematic diagram of video process apparatus, and the device composition shown in Fig. 3 is only an example, should not be to of the invention real
The function and use scope for applying example bring any restrictions.
Referring to Fig. 3, Fig. 3 is the hardware structural diagram of video process apparatus 30 provided in an embodiment of the present invention, comprising: extremely
A few processor 301, memory 302, user interface 303 and at least one network interface 304.In video process apparatus 30
Various components are coupled by bus system 305.It is appreciated that bus system 305 is for realizing between these components
Connection communication.Bus system 305 further includes power bus, control bus and status signal bus in addition in addition to including data/address bus.
But for the sake of clear explanation, various buses are all designated as bus system 305 in Fig. 3.
Wherein, user interface 303 may include display, keyboard, mouse, trace ball, click wheel, key, key, sense of touch
Plate or touch screen etc..
It is appreciated that memory 302 can be volatile memory or nonvolatile memory, may also comprise volatibility and
Both nonvolatile memories.Wherein, nonvolatile memory can be read-only memory (ROM, Read Only Memory),
Programmable read only memory (PROM, Programmable Read-Only Memory), Erasable Programmable Read Only Memory EPROM
(EPROM, Erasable Programmable Read-Only Memory), flash memory (Flash Memory) etc..Volatibility is deposited
Reservoir can be random access memory (RAM, Random Access Memory), be used as External Cache.By showing
Example property but be not restricted explanation, the RAM of many forms is available, such as static random access memory (SRAM, Static
Random Access Memory), synchronous static random access memory (SSRAM, Synchronous Static Random
Access Memory).The memory 302 of description of the embodiment of the present invention is intended to include depositing for these and any other suitable type
Reservoir.
Memory 302 in the embodiment of the present invention can storing data to support the operation of terminal (such as 400-1).These numbers
According to example include: any computer program for being operated on terminal (such as 400-1), such as operating system and application program.
Wherein, operating system includes various system programs, such as ccf layer, core library layer, driving layer etc., for realizing various basic industry
It is engaged in and handles hardware based task.Application program may include various application programs.
As the example that video process apparatus provided in an embodiment of the present invention uses software and hardware combining to implement, the present invention is implemented
Video process apparatus provided by example can be embodied directly in be combined by the software module that processor 301 executes, and software module can
To be located in storage medium, storage medium is located at memory 302, and processor 301 reads software module in memory 302 and includes
Computer program is completed in conjunction with necessary hardware (e.g., including processor 301 and the other assemblies for being connected to bus 305)
Method for processing video frequency provided in an embodiment of the present invention.
As an example, processor 301 can be a kind of IC chip, and the processing capacity with signal, for example, it is general
Processor, digital signal processor (DSP, Digital Signal Processor) or other programmable logic device are divided
Vertical door or transistor logic, discrete hardware components etc., wherein general processor can be microprocessor or any normal
The processor etc. of rule.
As the example that video process apparatus provided in an embodiment of the present invention uses hardware to implement, the embodiment of the present invention is mentioned
The processor 301 of hardware decoding processor form can be directly used to execute completion, for example, one or more in the device of confession
Application specific integrated circuit (ASIC, Application Specific Integrated Circuit), DSP, programmable logic
Device (PLD, Programmable Logic Device), Complex Programmable Logic Devices (CPLD, Complex
Programmable Logic Device), field programmable gate array (FPGA, Field-Programmable Gate
Array) or other electronic components execute and realize method for processing video frequency provided in an embodiment of the present invention.
Memory 302 in the embodiment of the present invention is for storing various types of data to support video process apparatus 30
Operation.The example of these data includes: any executable instruction for operating on video process apparatus 30, such as executable to refer to
It enables, realizes that the program of the method for processing video frequency of the embodiment of the present invention may be embodied in executable instruction.
The exemplary application and implementation of the device above-mentioned for realizing the embodiment of the present invention will be combined, illustrates to realize of the invention real
The video prescription method of example offer is provided.
Referring to fig. 4, Fig. 4 is method for processing video frequency flow diagram provided in an embodiment of the present invention, will be combined shown in Fig. 4
Step is illustrated.
Step 401: terminal receives Object identifying instruction by the broadcast interface of target video, and Object identifying instruction is used
Object in instruction identification target video.
In practical applications, it is provided with video playing client in terminal, target view is realized by video playing client
The broadcasting of frequency may be provided with Object identifying key at video playing interface, and user, can basis during watching target video
It itself needs to choose whether to trigger the Object identifying key, when user wants to know about the specifying information of target object, can click
Object identifying key and trigger the instruction of corresponding Object identifying, terminal receives object knowledge by the broadcast interface of target video
The object in target video Zhi Ling and then not be identified.
Referring to Fig. 5, Fig. 5 is the broadcast interface schematic diagram that video playing client provided in an embodiment of the present invention is presented, when
User want to know about the object presented on currently playing interface for information about when, can the recognition of face on click play interface press
Button, video playing client receive recognition of face by currently playing interface and instruct, to carry out to the object in target video
Identification.
In actual implementation, terminal may be used also in addition to being identified based on Object identifying instruction to the object in target video
The object in target video is identified based on the default phonetic control command received.
Step 402: being instructed based on Object identifying, determine the target object in target video.
In some embodiments, terminal can be determined as follows the target object in target video:
It is instructed in response to Object identifying, obtains video frame images corresponding to the currently playing interface of target video;To video
Frame image carries out Object identifying, when the quantity for determining the object for including in video frame images is one, will wrap in video frame images
The object contained is as target object.
In actual implementation, when the Object identifying key being arranged on video playing interface when the user clicks, can trigger corresponding
Object identifying instruction, terminal parsing receives Object identifying instruction, obtain the currently playing interface of target video corresponding to view
Frequency frame image, and feature identification is carried out to the video frame images of acquisition, when recognizing in video frame images comprising an object,
The object is determined as target object.
Referring to Fig. 6, Fig. 6 is the interface schematic diagram of determining target object provided in an embodiment of the present invention, and target video is current
Broadcast interface only includes an object, and terminal is instructed in response to the Object identifying that user clicks, and it is currently playing to obtain target video
The video frame images at interface, and recognition of face is carried out to the video frame images of acquisition, the object recognized is determined as target pair
As.
In some embodiments, terminal can also determine target object such as under type:
When determining that the quantity for the object for including in video frame images is multiple, Object Selection circle of corresponding multiple objects is presented
Face;In response to the Object Selection instruction received by Object Selection interface, Object Selection is instructed into the indicated object selected
As target object.
In actual implementation, when terminal determines in video frame images comprising multiple objects, can be presented on broadcast interface
The Object Selection interface of corresponding each object, for example, Object Selection key is arranged in the corresponding position of each object, but user thinks
It is to be understood that the corresponding Object Selection key of the object can be clicked when the information of certain an object, and then Object Selection instruction is triggered, eventually
Termination receives Object Selection instruction, using the indicated object selected of Object Selection instruction as target object.
Referring to Fig. 7, Fig. 7 is the interface schematic diagram of determining target object provided in an embodiment of the present invention, and target video is current
Include 2 objects in broadcast interface, present corresponding Object Selection key beside each object, when the user clicks instruction choosing
When selecting the right side corresponding Object Selection key of schoolgirl, then using right side schoolgirl as target object, and then spy is carried out to right side schoolgirl
Sign identification.
In practical applications, the video frame images that terminal can also will acquire are sent to background server, background server pair
Video frame images carry out feature identifying processing, and when recognizing in video frame images comprising an object, which is determined as
Target object;When recognizing in video frame images comprising multiple objects, the boundary whether identified for each object is sent
Face setting instruction, terminal receive interface setting instruction, generate and present at video playing interface to the object for coping with an object
Key range, user can trigger corresponding Object identifying by clicking a certain Object identifying key and instruct, and terminal is by the object
Identification instruction is sent to background server, and the Object identifying instruction that background server parsing receives determines that the Object identifying refers to
Enable the indicated object selected as target object.
Step 403: the identification request of corresponding target object is sent, to determine target object in target based on identification request
The portrait information of Role Information and target object in video.
In some embodiments, terminal can be determined as follows Role Information of the target object in target video with
And the portrait information of target object:
The identification for sending corresponding target object is requested to background server, and identification request carries the frame image of target object,
So that background server carries out feature extraction to the frame image of target object, target view will be corresponded in the feature of extraction and video library
The role characteristic of frequency is compared, and determines role of the target object in target video and returns to corresponding Role Information to eventually
End;Terminal receives the Role Information returned.
In actual implementation, the identification request for the frame image for carrying target object is sent to background server by terminal,
The identification request that background server parsing receives obtains the frame image of target object, and carries out to the frame image of target object
The feature of extraction is compared with the role characteristic of the correspondence target video in video library, determines target object by feature extraction
Role Information in target video, here, video library are stored with a large amount of video, included at least in video library following information it
One: video type, video name, the Role Information in video;Same type of video can be stored in same video library, into
And video library is divided into different types of video library according to the video type of its storage, for example, TV play video library, film regard
Frequency library, variety video library etc..
Illustratively, target video is TV play, and target object is the personage in TV play, and terminal will carry the personage
The identification request of frame image be sent to background server, background server parsing identification request obtains the frame image of personage, and
Recognition of face is carried out to the frame image of personage to extract to obtain character features, TV play name of the background server based on target video
Claim, find corresponding TV play from TV play video library, and by multiple performers in the character features of extraction and the TV play
Feature is compared, can be true when the performer's aspect ratio stored in the character features and TV play video library extracted is to success
Fixed relationship of the personage between the role and other roles in the TV play.
Illustratively, target video is TV play, and target object can also will carry this and move for animal in TV play, terminal
The identification request of the frame image of object is sent to background server, and background server parsing identification request obtains the frame image of animal,
And Object identifying is carried out to the frame image of animal and extracts to obtain animal character, TV play name of the background server based on target video
Claim, find corresponding TV play from TV play video library, and by the animal character in the animal character of extraction and the TV play
It is compared, when the animal character stored in the animal character and TV play video library extracted compares successfully, it may be determined that should
Relationship of the animal between the role and other roles in the TV play, for example, determining name of the animal in TV play
And its whose etc. owner be.
In some embodiments, terminal can also be determined as follows Role Information of the target object in target video
And the portrait information of target object:
The identification request of corresponding target object is sent, identification request carries the frame image of target object, to target object
Frame image carry out feature extraction, by the feature of extraction with draw a portrait information bank in feature be compared, determine target object
Portrait information simultaneously returns to portrait information;Obtain the role characteristic of target video;The role characteristic of target video is sent, to be based on angle
Color characteristic and portrait information, determine role of the target object in target video and return to corresponding Role Information;It receives and returns
Role Information.
In actual implementation, the identification request for the frame image for carrying target object is sent to background server by terminal,
The identification request that background server parsing receives obtains the frame image of target object, and carries out to the frame image of target object
The feature of extraction is compared with the feature in portrait information bank, determines the portrait information of target object by feature extraction, this
In, portrait information bank is stored with the portrait information of multiple objects, is similar in Baidupedia and is introduced substantially star or pet etc.
Information can determine the portrait information of target object when the aspect ratio in the feature of extraction and portrait information bank is to success, than
Such as, when target object is character, it may be determined that play name, the native place, date of birth, graduation institute of the performer of the role
School, main representative work etc.;When target object is animal character, it may be determined that kind, personality, habit of the animal etc..Terminal is also
Obtain the Role Information of target video, such as cast, role's introduction etc..
Step 404: receiving the Role Information and portrait information of return.
Here, terminal receives Role Information of the target object in target video and its own that background server returns
Portrait information.
Step 405: by the broadcast interface of target video, Role Information and portrait information is presented.
In practical applications, terminal receives Role Information and its own portrait of the target object in target video
After information, can individually be presented by target video picture, for example, when user to the portrait information of target object
Such as fingers and palms or be not desired to understand the portrait information of target object and when only focusing on Role Information of the target object in target video,
Role Information of the target object in target video can only be presented, by broadcast interface to allow user to be best understood from target video
Plot;When user has had to Role Information of the target object in target video at fingertips, and to the portrait of target object
When information is had little understanding, the portrait information of target object can only be presented by broadcast interface.
Terminal can also pass through target after receiving Role Information and the portrait information of its own in target video
Role Information and portrait information is presented in the broadcast interface of video together, and in some embodiments, terminal can be in the following way
The existing Role Information and the portrait information:
Role Information and portrait information to target object carry out integration processing, obtain the load card of target object;It is logical
The load card of target object is presented in the broadcast interface for crossing target video.
Here, terminal is presented the Role Information of target object and portrait information together in the form of load card, referring to
Fig. 8, Fig. 8 are the display interface schematic diagram of method for processing video frequency provided in an embodiment of the present invention, target video shown in Fig. 8
The following information of target object is presented in (TV play: " we are at a distance from disliking ") currently playing interface: in " we and evil
Distance " Role Information in this TV play: Zhang San plays Ying Siyue, and Ying Siyue is to start an undertaking young wait transfer, and personality is optimistic, kind
It is good positive, the relationship of Ying Siyue and other roles are as follows: the elder sister of Ying Sicong, the landlord of Li great Zhi;The portrait information of target object:
Zhang San is born in Taipei, Taiwan on October 21st, 1984, and Chinese songstress, performer, it is super that Zeng Peici in 2008 obtains Second
Grade Avenue of Stars is competed the 6th achievement ....
Referring to Fig. 9, Fig. 9 is the display interface schematic diagram of method for processing video frequency provided in an embodiment of the present invention, shown in Fig. 9
Target video (TV play: " refreshing dog is 7 first small ") currently playing interface in present the following information of target object: In
Role Information in " refreshing dog is 7 first small " this TV play: Labrador Retriever, play it is small by seven, small seven with mother's millet and Lyu
One is red, Jia Changan Mr. and Mrs live together, and because man and wife's divorce is urged apart, small seven follow Lyu one, good friend: Ah mew, teases at thunderbolt
It is funny ...;The portrait information of target object: Labrador Retriever also known as recovers dog, is a kind of medium-and-large-sized canine, be very suitable to by
It is elected to be the dog kind ... of the seeing-eye dog or subway dog and rescue dogs and other working dogs that often enter and leave public arena.
It should be noted that since video playing interface size is limited, the possibility that video playing interface can be directly presented
Only the part Role Information of target object or portrait information, if it is desired to understand more Role Informations or portrait information, can lead to
It crosses such as drop-down scroll bar or other feasible modes and checks hiding Role Information or portrait information.
In practical applications, can also increase on the Role Information of target object and the load card for information of drawing a portrait for rendering
At least one interaction key of the relevant target object is arranged in interactive operation in load card, in some embodiments,
Terminal can realize being associated with for interactive information and target object in the following way:
In response to the clicking operation for interaction key, the interaction letter of correspondence target object indicated by clicking operation is determined
Breath, the interactive information are used to characterize the Sentiment orientation to target object;The interactive information of corresponding target object is sent, to realize
Interactive information is associated with target object.
In practical applications, Sentiment orientation can be divided into positive emotion (such as play list, thumb up) and negative sense emotion (as point is stepped on
Deng).Think that star beats for list, referring to Figure 10, Figure 10 is the display interface of method for processing video frequency provided in an embodiment of the present invention
Schematic diagram, following information is presented in the broadcast interface in target video shown in Fig. 10: target object is in target video
It gives song recitals, the Role Information of target object: Li Si, English name Veegee, singer, 18 years old;The portrait information of target object:
Li Si in 2014 participated in by company A hold the whole world sign choosing can Shanghai Station, the single of engaging in this profession of " FLIP " as Li Si, still by
Company A has been contracted all ..., and presents interaction key " thumbing up for her ", when the user of viewing target video wants for her point
When praising, corresponding interaction key can be clicked, at this point, clicking operation of the terminal in response to user, determines the mutual of corresponding target object
Dynamic information sends the interactive information of corresponding target object, to realize being associated with for interactive information and target object.
It is instructed by the above method based on the broadcast interface Object identifying of target video, determines the target pair in target video
As, and the identification request based on corresponding target object, determine Role Information and target pair of the target object in target video
The portrait information of elephant;By the broadcast interface of target video, Role Information and portrait information is presented;It so, it is possible through a key
Operation, the Role Information for rapidly obtaining target object and portrait information, and interaction function can be increased, user's sight will not be interrupted
See video;For video playing client, user's viscosity can be also promoted, reduces customer churn, also, remove on load card
Outside displaying essential information, interaction function can also be increased, such as thumbed up, played list, share, so that the perception of user be substantially improved
Experience.
Continue to be illustrated method for processing video frequency provided in an embodiment of the present invention, Figure 11 is provided in an embodiment of the present invention
Method for processing video frequency flow diagram is executed by the video playing client and background server that are arranged in terminal, comprising:
Step 1101: video playing client receives Object identifying instruction, object by the broadcast interface of target video
Identification instruction is used to indicate the object in identification target video.
In practical applications, it is provided with video playing client in terminal, target view is realized by video playing client
The broadcasting of frequency may be provided with Object identifying key at video playing interface, and user, can basis during watching target video
It itself needs to choose whether to trigger the Object identifying key, when user wants to know about the specifying information of target object, can click
Object identifying key and trigger the instruction of corresponding Object identifying, terminal receives object knowledge by the broadcast interface of target video
The object in target video Zhi Ling and then not be identified.
In actual implementation, terminal may be used also in addition to being identified based on Object identifying instruction to the object in target video
The object in target video is identified based on the default phonetic control command received.
Step 1102: video playing client is instructed based on Object identifying, determines the target object in target video.
In actual implementation, video playing client end response is instructed in Object identifying, obtains the currently playing boundary of target video
Video frame images corresponding to face;Object identifying is carried out to video frame images, when determining the object for including in video frame images
When quantity is one, using the object for including in video frame images as target object;When determining pair for including in video frame images
When the quantity of elephant is multiple, the Object Selection interface of corresponding multiple objects is presented;In response to being received by Object Selection interface
Object Selection instruction, using the indicated object selected of Object Selection instruction as target object.
Step 1103: the identification that video playing client sends corresponding target object is requested to background server.
Here, identification request carries the frame image of target object.
Step 1104: background server is requested based on the identification of target object, obtains the frame image of target object.
Here, the identification request for the target object that background server parsing receives, obtains the frame of corresponding target object
Image.
Step 1105: background server carries out feature extraction to the frame image of target object, obtains the feature of target object.
In actual implementation, when target object is people, background server carries out face knowledge to the frame image of target object
Not, corresponding target object feature is obtained.
Step 1106: background server compares the feature for extracting obtained target object and feature in portrait information bank
It is right, determine the portrait information of target object.
Here, portrait information bank is stored with the portrait information of multiple objects, is similar in Baidupedia to star or pet
The essential information of equal descriptions can determine target object when the aspect ratio in the feature of extraction and portrait information bank is to success
Portrait information, for example, when target object be character when, it may be determined that play name, the native place, birth of the performer of the role
Date, graduated school, main representative work etc.;When target object is animal character, it may be determined that kind, personality, the habit of the animal
Property etc..
Step 1107: the role characteristic of video playing client acquisition target video.
Here, video playing client obtains the Role Information of currently playing target video, such as cast, Jiao Sejie
It continues.
Step 1108: the role characteristic of video playing client transmission target video to background server.
Step 1109: the portrait information of role characteristic and target object of the background server based on target video determines mesh
Mark Role Information of the object in target video.
Here, background server can portrait information and target video based on target object cast information, obtain mesh
Mark Role Information of the object in target video and the relation information between other roles.
Step 1110: Role Information and portrait information are carried out integration processing by background server, obtain the letter of target object
Cease card.
Here, the Role Information of target object and portrait information are integrated on a load card by background server.
Step 1111: the load card of background server transmission target object to video playing client.
Step 1112: the load card of target object is presented by the broadcast interface of target video in video playing client.
Here, part interface of the video playing client by target video, in the form of load card one logical presentation mesh
Mark the Role Information and portrait information of object.
Step 1113: video playing client end response determines clicking operation meaning in the clicking operation for interaction key
The interactive information of the correspondence target object shown.
In practical applications, can also increase on the Role Information of target object and the load card for information of drawing a portrait for rendering
Interactive operation, is provided at least one interaction key of associated objects object in load card, and user clicks interaction key, meeting
Triggering client determines interactive information.
Step 1114: the interactive information of the corresponding target object of video playing client transmission to background server.
Step 1115: interactive information and target object are associated by background server.
In the following, will illustrate exemplary application of the embodiment of the present invention in an actual application scenarios.
Method for processing video frequency provided in an embodiment of the present invention can be performed in unison with, in reality by client and background server
When border is implemented, it is related to product side and technology side:
1) product side;
In practical applications, client can be video playing client, realize target video by video playing client
Broadcasting, may be provided with Object identifying key (i.e. knowledge face key) at video playing interface, user is in viewing target video
In the process, it can choose whether to trigger the Object identifying key according to their needs, when user wants to know about the specific of target object
When information, Object identifying key can be clicked and trigger the instruction of corresponding Object identifying, terminal by the broadcast interface of target video,
Object identifying is received to instruct and then identify the object in target video.
Basic procedure of the method for processing video frequency provided in an embodiment of the present invention in product side are as follows:
Firstly, user navigates to target person frame, referring to Fig. 5 when watching video;
Secondly, user clicks the Object identifying key on currently playing interface, system is identified, referring to Fig. 6-7;
Finally, people information is presented at currently playing interface in client, referring to Fig. 8-9.
2) technology side;
Referring to Figure 12, Figure 12 is method for processing video frequency flow diagram provided in an embodiment of the present invention, comprising:
Step 1201: client receives Object identifying instruction by the broadcast interface of target video.
Here, in practical applications, user opens video playing client, and collection of drama (i.e. target video) is selected to be seen
It sees.After user clicks the knowledge face button (i.e. Object identifying key) on video playing interface, corresponding Object identifying can be triggered
Instruction.
Step 1202: client is instructed based on Object identifying, determines the target object in target video.
Here, in actual implementation, client end response is instructed in Object identifying, obtains the currently playing interface institute of target video
Corresponding key frame images (i.e. video frame images);Recognition of face is carried out to video frame images, is wrapped when determining in video frame images
When the quantity of the object (i.e. face) contained is one, using the face for including in video frame images as target object;It is regarded when determining
When the quantity for the face for including in frequency frame image is multiple, the selection interface of corresponding multiple faces is presented, user can click interface
Key, using the object selected indicated by key as target object.
Step 1203: the identification that client sends corresponding target object is requested to background server.
Step 1204: background server is requested based on the identification of target object, obtains the frame image of target object.
Here, the identification request for the target object that background server parsing receives, obtains the frame of corresponding target object
Image.
Step 1205: background server carries out Face datection to the frame image of target object, obtains face characteristic information.
Here, background server carries out the face in video clip to scratch picture, positions face region, and then detect and obtain people
Face characteristic information.
Step 1206: the characteristic information in face characteristic information and background data base that background server will test into
Row compares, and determines the Real Name of target object.
Here, the characteristic information that a large amount of bright people or star are stored in background data base, passes through the people that will test
Face characteristic information is compared with the characteristic information in database, and then determines that whom target object is.
Step 1207: background server obtains the picture of target object based on the Real Name of target object by search engine
As information.
Here, portrait information is similar to the basic recommended information in Baidupedia to star, comprising: name, native place, birth
Date, graduated school, main representative work etc..
Step 1208: client obtains the essential information of target video and is sent to background server.
Here, client obtains the essential information of target video (collection of drama watched), comprising: acute name, is played at cast
Role, role introduce substantially.
Step 1209: background server receives the basic messae for the target video that client is sent.
Step 1210: the portrait information for the target object that background server obtains search and the essential information of target video
It is integrated, obtains the load card of target object.
Here, the portrait information (i.e. Baidupedia information) and client for the target object that background server obtains search
Episode information is integrated and is handled, and obtains corresponding load card, and obtained load card is sent to client.
Step 1211: the load card of target object is presented by the broadcast interface of target video in client.
So far, by a key operation, rapidly obtain people information, can allow user do not interrupting viewing video the case where
Under, a key meets the needs of user query and search information, and the curiosity and aspiration to knowledge of user are met with light-weighted operation, is used
Family does not need to toggle in multiple APP clients, experiences more continuous;For client, video user also can be reduced
Loss, promoted user viscosity, to video class product keep user activity have great significance.Also, the embodiment of the present invention mentions
What the key in the method for processing video frequency of confession identified is not limited only to personage, is also possible to animal etc., in addition, removing on load card
Outside displaying essential information, interaction function can also be increased, such as thumbed up, played list, share, so that the perception of user be substantially improved
Experience.
Continue to be illustrated video process apparatus provided in an embodiment of the present invention.Figure 13 is provided in an embodiment of the present invention
The structural schematic diagram of video process apparatus, referring to Figure 13, video process apparatus 13 provided in an embodiment of the present invention includes:
Receiving unit 131 receives Object identifying instruction for the broadcast interface by target video, and the object is known
The object identified in the target video Zhi Ling be used to indicate;
Determination unit 132 determines the target object in the target video for instructing based on the Object identifying;
Transmission unit 133, for sending the identification request of the corresponding target object, to be requested based on the identification, really
The portrait information of fixed Role Information and the target object of the target object in the target video;
Receiving unit 134, for receiving the Role Information returned and the portrait information;
The Role Information and the portrait is presented for passing through the broadcast interface of the target video in display unit 135
Information.
In some embodiments, the determination unit is also used to instruct in response to the Object identifying, obtains the target
Video frame images corresponding to the currently playing interface of video;
Object identifying is carried out to the video frame images, determines that the quantity for the object for including in the video frame images is one
When a, using the object for including in the video frame images as the target object.
In some embodiments, the determination unit is also used to determine the number for the object for including in the video frame images
When amount is multiple, the Object Selection interface of corresponding multiple objects is presented;
In response to the Object Selection instruction received by the Object Selection interface, the Object Selection is instructed signified
Show the object selected as the target object.
In some embodiments, the transmission unit is also used to send the identification request of the corresponding target object, described
Identification request carries the frame image of the target object, carries out feature extraction with the frame image to the target object, will extract
Feature and video library in correspond to the role characteristic of the target video and be compared, determine the target object in the target
Role in video simultaneously returns to corresponding Role Information;
Receive the Role Information returned.
In some embodiments, the transmission unit is also used to send the identification request of the corresponding target object, described
Identification request carries the frame image of the target object, carries out feature extraction with the frame image to the target object, will extract
Feature be compared with the feature in portrait information bank, determine the portrait information of the target object and return to the portrait and believe
Breath;
Obtain the role characteristic of the target video;
The role characteristic of the target video is sent, described in determining based on the role characteristic and the portrait information
Role of the target object in the target video simultaneously returns to corresponding Role Information;
Receive the Role Information returned.
In some embodiments, the display unit is also used to the Role Information of the target object and described
Portrait information carries out integration processing, obtains the load card of the target object;
By the broadcast interface of the target video, the load card of the target object is presented.
In some embodiments, at least one interaction for the relevant target object being arranged in the load card is pressed
Key, described device further include interactive unit:
The interactive unit, for determining the clicking operation institute in response to the clicking operation for the interaction key
The interactive information of the correspondence of the instruction target object, the interactive information incline to the emotion of the target object for characterizing
To;
The interactive information of the corresponding target object is sent, to realize the pass of the interactive information Yu the target object
Connection.
The embodiment of the present invention also provides a kind of video process apparatus, comprising:
Memory, for storing executable instruction;
Processor when for executing the executable instruction stored in the memory, is realized provided in an embodiment of the present invention
Method for processing video frequency.
The embodiment of the present invention also provides a kind of storage medium, is stored with executable instruction, when for causing processor to execute,
Realize method for processing video frequency provided in an embodiment of the present invention.
This can be accomplished by hardware associated with program instructions for all or part of the steps of embodiment, and program above-mentioned can be with
It is stored in a computer readable storage medium, which when being executed, executes step including the steps of the foregoing method embodiments;And
Storage medium above-mentioned includes: movable storage device, random access memory (RAM, Random Access Memory), read-only
The various media that can store program code such as memory (ROM, Read-Only Memory), magnetic or disk.
If alternatively, the above-mentioned integrated unit of the present invention is realized in the form of software function module and as independent product
When selling or using, it also can store in a computer readable storage medium.Based on this understanding, the present invention is implemented
The technical solution of example substantially in other words can be embodied in the form of software products the part that the relevant technologies contribute,
The computer software product is stored in a storage medium, including some instructions are used so that computer equipment (can be with
It is personal computer, server or network equipment etc.) execute all or part of each embodiment the method for the present invention.
And storage medium above-mentioned includes: that movable storage device, RAM, ROM, magnetic or disk etc. are various can store program code
Medium.
The above, only the embodiment of the present invention, are not intended to limit the scope of the present invention.It is all in this hair
Made any modifications, equivalent replacements, and improvements etc. within bright spirit and scope, be all contained in protection scope of the present invention it
It is interior.
Claims (10)
1. a kind of method for processing video frequency, which is characterized in that the described method includes:
By the broadcast interface of target video, Object identifying instruction is received;
It is instructed based on the Object identifying, determines the target object in the target video;
The identification request for sending the corresponding target object determines the target object described to request based on the identification
The portrait information of Role Information and the target object in target video;
Receive the Role Information returned and the portrait information;
By the broadcast interface of the target video, the Role Information and the portrait information is presented.
2. the method as described in claim 1, which is characterized in that it is described to be instructed based on the Object identifying, determine the target
Target object in video, comprising:
It is instructed in response to the Object identifying, obtains video frame images corresponding to the currently playing interface of the target video;
Object identifying is carried out to the video frame images, determines that the quantity for the object for including in the video frame images is one
When, using the object for including in the video frame images as the target object.
3. method according to claim 2, which is characterized in that the method also includes:
When determining that the quantity for the object for including in the video frame images is multiple, the object choosing of corresponding multiple objects is presented
Select interface;
In response to the Object Selection instruction received by the Object Selection interface, the Object Selection is instructed into indicated choosing
The object selected is as the target object.
4. the method as described in claim 1, which is characterized in that the identification request for sending the corresponding target object, with
It is requested based on the identification, determines Role Information of the target object in the target video, comprising:
The identification request of the corresponding target object is sent, the identification request carries the frame image of the target object, with right
The frame image of the target object carries out feature extraction, and the role of the target video will be corresponded in the feature of extraction and video library
Feature is compared, and determines role of the target object in the target video and returns to corresponding Role Information;
Receive the Role Information returned.
5. the method as described in claim 1, which is characterized in that the identification request for sending the corresponding target object, with
It is requested based on the identification, determines Role Information of the target object in the target video, comprising:
The identification request of the corresponding target object is sent, the identification request carries the frame image of the target object, with right
The frame image of the target object carries out feature extraction, the feature of extraction is compared with the feature in portrait information bank, really
The portrait information of the fixed target object simultaneously returns to the portrait information;
Obtain the role characteristic of the target video;
The role characteristic of the target video is sent, to be based on the role characteristic and the portrait information, determines the target
Role of the object in the target video simultaneously returns to corresponding Role Information;
Receive the Role Information returned.
6. the method as described in claim 1, which is characterized in that the presentation Role Information and the portrait information, packet
It includes:
The Role Information and the portrait information to the target object carry out integration processing, obtain the target object
Load card;
By the broadcast interface of the target video, the load card of the target object is presented.
7. method as claimed in claim 6, which is characterized in that the relevant target object is arranged in the load card
At least one interaction key, the method also includes:
In response to the clicking operation for the interaction key, the target object of correspondence indicated by the clicking operation is determined
Interactive information, the interactive information is used to characterize Sentiment orientation to the target object;
The interactive information of the corresponding target object is sent, to realize being associated with for the interactive information and the target object.
8. a kind of video process apparatus, which is characterized in that described device includes:
Receiving unit receives Object identifying instruction for the broadcast interface by target video;
Determination unit determines the target object in the target video for instructing based on the Object identifying;
Transmission unit, the identification request for sending the corresponding target object determine the mesh to request based on the identification
Mark the portrait information of Role Information and the target object of the object in the target video;
Receiving unit, for receiving the Role Information returned and the portrait information;
The Role Information and the portrait information is presented for passing through the broadcast interface of the target video in display unit.
9. a kind of video process apparatus, which is characterized in that described device includes:
Memory, for storing executable instruction;
Processor when for executing the executable instruction stored in the memory, is realized described in any one of claim 1 to 7
Method for processing video frequency.
10. a kind of storage medium, which is characterized in that being stored with executable instruction, when for causing processor to execute, realizing right
It is required that 1 to 7 described in any item method for processing video frequency.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910817479.0A CN110446104A (en) | 2019-08-30 | 2019-08-30 | Method for processing video frequency, device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910817479.0A CN110446104A (en) | 2019-08-30 | 2019-08-30 | Method for processing video frequency, device and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110446104A true CN110446104A (en) | 2019-11-12 |
Family
ID=68438543
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910817479.0A Pending CN110446104A (en) | 2019-08-30 | 2019-08-30 | Method for processing video frequency, device and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110446104A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111586492A (en) * | 2020-05-27 | 2020-08-25 | 上海极链网络科技有限公司 | Video playing method and device, client device and storage medium |
CN113032521A (en) * | 2021-03-05 | 2021-06-25 | 广州虎牙科技有限公司 | Blind guiding method, blind guiding device, blind guiding equipment and computer readable storage medium |
CN113283480A (en) * | 2021-05-13 | 2021-08-20 | 北京奇艺世纪科技有限公司 | Object identification method and device, electronic equipment and storage medium |
CN114640863A (en) * | 2022-03-04 | 2022-06-17 | 广州方硅信息技术有限公司 | Method, system and device for displaying character information in live broadcast room and computer equipment |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106210808A (en) * | 2016-08-08 | 2016-12-07 | 腾讯科技(深圳)有限公司 | Media information put-on method, terminal, server and system |
CN106534944A (en) * | 2016-11-30 | 2017-03-22 | 北京锤子数码科技有限公司 | Video display method and device |
CN106598998A (en) * | 2015-10-20 | 2017-04-26 | 北京奇虎科技有限公司 | Information acquisition method and information acquisition device |
CN107679156A (en) * | 2017-09-27 | 2018-02-09 | 努比亚技术有限公司 | A kind of video image identification method and terminal, readable storage medium storing program for executing |
CN108401176A (en) * | 2018-02-06 | 2018-08-14 | 北京奇虎科技有限公司 | A kind of method and apparatus for realizing video personage mark |
CN109598188A (en) * | 2018-10-16 | 2019-04-09 | 深圳壹账通智能科技有限公司 | Information-pushing method, device, computer equipment and storage medium |
CN110035314A (en) * | 2019-03-08 | 2019-07-19 | 腾讯科技(深圳)有限公司 | Methods of exhibiting and device, storage medium, the electronic device of information |
-
2019
- 2019-08-30 CN CN201910817479.0A patent/CN110446104A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106598998A (en) * | 2015-10-20 | 2017-04-26 | 北京奇虎科技有限公司 | Information acquisition method and information acquisition device |
CN106210808A (en) * | 2016-08-08 | 2016-12-07 | 腾讯科技(深圳)有限公司 | Media information put-on method, terminal, server and system |
CN106534944A (en) * | 2016-11-30 | 2017-03-22 | 北京锤子数码科技有限公司 | Video display method and device |
CN107679156A (en) * | 2017-09-27 | 2018-02-09 | 努比亚技术有限公司 | A kind of video image identification method and terminal, readable storage medium storing program for executing |
CN108401176A (en) * | 2018-02-06 | 2018-08-14 | 北京奇虎科技有限公司 | A kind of method and apparatus for realizing video personage mark |
CN109598188A (en) * | 2018-10-16 | 2019-04-09 | 深圳壹账通智能科技有限公司 | Information-pushing method, device, computer equipment and storage medium |
CN110035314A (en) * | 2019-03-08 | 2019-07-19 | 腾讯科技(深圳)有限公司 | Methods of exhibiting and device, storage medium, the electronic device of information |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111586492A (en) * | 2020-05-27 | 2020-08-25 | 上海极链网络科技有限公司 | Video playing method and device, client device and storage medium |
CN113032521A (en) * | 2021-03-05 | 2021-06-25 | 广州虎牙科技有限公司 | Blind guiding method, blind guiding device, blind guiding equipment and computer readable storage medium |
CN113283480A (en) * | 2021-05-13 | 2021-08-20 | 北京奇艺世纪科技有限公司 | Object identification method and device, electronic equipment and storage medium |
CN113283480B (en) * | 2021-05-13 | 2023-09-05 | 北京奇艺世纪科技有限公司 | Object identification method and device, electronic equipment and storage medium |
CN114640863A (en) * | 2022-03-04 | 2022-06-17 | 广州方硅信息技术有限公司 | Method, system and device for displaying character information in live broadcast room and computer equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110446104A (en) | Method for processing video frequency, device and storage medium | |
WO2021232978A1 (en) | Video processing method and apparatus, electronic device and computer readable medium | |
CN107105318B (en) | Video hotspot segment extraction method, user equipment and server | |
CN104219559B (en) | Unobvious superposition is launched in video content | |
EP2732383B1 (en) | Methods and systems of providing visual content editing functions | |
EP4343518A1 (en) | Data interaction method and apparatus, device, and storage medium | |
CN107590267B (en) | Information-pushing method and device, terminal and readable storage medium storing program for executing based on picture | |
US10929460B2 (en) | Method and apparatus for storing resource and electronic device | |
CN109218750B (en) | Video content retrieval method, device, storage medium and terminal equipment | |
JPWO2014178219A1 (en) | Information processing apparatus and information processing method | |
CN108446385A (en) | Method and apparatus for generating information | |
CN106909603A (en) | Search information processing method and device | |
CN105005982B (en) | Image procossing including Object Selection | |
CN111432282B (en) | Video recommendation method and device | |
WO2022247220A1 (en) | Interface processing method and apparatus | |
WO2022001600A1 (en) | Information analysis method, apparatus, and device, and storage medium | |
CN113766296B (en) | Live broadcast picture display method and device | |
CN114095749B (en) | Recommendation and live interface display method, computer storage medium and program product | |
CN110366043A (en) | Method for processing video frequency, device, electronic equipment and readable medium | |
CN108304067A (en) | System, method and apparatus for showing information | |
CN110166811A (en) | Processing method, device and the equipment of barrage information | |
CN113204691A (en) | Information display method, device, equipment and medium | |
CN113626624B (en) | Resource identification method and related device | |
CN110019800A (en) | Distribute content processing method, device, computer equipment and storage medium | |
CN109391836B (en) | Supplementing a media stream with additional information |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191112 |