CN107105340A - People information methods, devices and systems are shown in video based on artificial intelligence - Google Patents

People information methods, devices and systems are shown in video based on artificial intelligence Download PDF

Info

Publication number
CN107105340A
CN107105340A CN201710168987.1A CN201710168987A CN107105340A CN 107105340 A CN107105340 A CN 107105340A CN 201710168987 A CN201710168987 A CN 201710168987A CN 107105340 A CN107105340 A CN 107105340A
Authority
CN
China
Prior art keywords
picture
personage
relevant information
identified
server
Prior art date
Application number
CN201710168987.1A
Other languages
Chinese (zh)
Inventor
程高飞
孙祥平
郭丛敏
杨少宁
郑啸天
Original Assignee
百度在线网络技术(北京)有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 百度在线网络技术(北京)有限公司 filed Critical 百度在线网络技术(北京)有限公司
Priority to CN201710168987.1A priority Critical patent/CN107105340A/en
Publication of CN107105340A publication Critical patent/CN107105340A/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/00221Acquiring or recognising human faces, facial parts, facial sketches, facial expressions
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/22Procedures used during a speech recognition process, e.g. man-machine dialogue
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43Processing 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
    • H04N21/435Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43Processing 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
    • H04N21/44Processing 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
    • H04N21/44008Processing 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 proposes show people information methods, devices and systems in a kind of video based on artificial intelligence, wherein, this is based on showing that people information method includes in the video of artificial intelligence:Instructed according to the person recognition of reception, sectional drawing is carried out to TV picture, to obtain the picture to be identified with face;Picture to be identified is sent to server, so that server carries out recognition of face to picture to be identified, and according to the relevant information of personage in face recognition result acquisition picture to be identified, and return to the relevant information of personage;The relevant information of personage is shown in video screen.People information method is shown in the video based on artificial intelligence of the present invention, so that user need not switch the relevant information that other equipment checks personage, the relevant information of personage can be checked on the tv screen, reduce the complexity of user's operation, the efficiency that user obtains information is improved, the Experience Degree of user is improved.

Description

People information methods, devices and systems are shown in video based on artificial intelligence
Technical field
The present invention relates to communication technical field, people information side is shown in more particularly to a kind of video based on artificial intelligence Method, device and system.
Background technology
Artificial intelligence (Artificial Intelligence, english abbreviation is AI) is research, developed for simulating, prolonging Stretch and extend a new technological sciences of intelligent theory, method, technology and the application system of people.Artificial intelligence is computer One branch of science, it attempts to understand essence of intelligence, and produces and a kind of new can be done in the similar mode of human intelligence Go out the intelligence machine of reaction, the research in the field includes robot, language identification, image recognition, natural language processing and expert System etc..
With the development of information technology, the various value-added services based on intelligent television also constantly emerge in large numbers, intelligent television end Technology be also continuously updated.
At present, during user checks TV programme by intelligent television, sometimes to the personage in television image Or play the part of performer's generation interest of certain role, now, if user wants to know about unacquainted star or electricity in program Depending on the information of performer in acute film, user needs to obtain the relevant information of the personage by other intelligent terminals such as mobile phone.
In correlation technique, user can obtain the relevant information of personage by two ways, and a kind of mode is that user can pass through Other-end for example surfing Internet with cell phone search certain role be who is drilled, then, using the name of the performer as keyword, with search for The relevant information of the performer.Another way is that user fixes tentatively television image, picks up terminal such as mobile phone shooting picture and is schemed Binary search is initiated as search, and according to image search result, to obtain the relevant information of the performer.Thus, it is possible to find out, use The unacquainted star of family understanding or TV play film collect the process of the information of performer, and the acquisition of information path of user is longer, The information of inconvenience related performer of removal search, it is necessary to which the equipment that switches, interruption watch TV, operation is comparatively laborious, also, user is also Need to be selected from a plurality of search result, waste time and energy.
The content of the invention
It is contemplated that at least solving above-mentioned technical problem to a certain extent.
Therefore, first purpose of the present invention is to propose to show people information side in a kind of video based on artificial intelligence Method so that user need not switch the relevant information that other equipment checks personage, can check the correlation of personage on the tv screen Information, reduces the complexity of user's operation, improves the efficiency that user obtains information, improves the Experience Degree of user.
Second object of the present invention is the device for proposing to show people information in a kind of video based on artificial intelligence.
For up to above-mentioned purpose, embodiment is proposed in a kind of video based on artificial intelligence and shown according to a first aspect of the present invention Let others have a look at thing information approach, comprise the following steps:Instructed according to the person recognition of reception, sectional drawing is carried out to TV picture, with Obtain the picture to be identified with face;The picture to be identified is sent to server, so that the server is treated to described Recognize that picture carries out recognition of face, and the relevant information of personage in the picture to be identified is obtained according to face recognition result, with And return to the relevant information of personage;The relevant information of personage is shown in video screen.
People information method is shown in the video based on artificial intelligence of the embodiment of the present invention, according to the person recognition of reception Instruction carries out sectional drawing to TV picture, and to obtain the picture to be identified with face, picture to be identified is sent to service Device, so that server carries out recognition of face to picture to be identified, and obtains personage in picture to be identified according to face recognition result Relevant information, and return to the relevant information of personage, and show in video screen the relevant information of personage.Thus, make The relevant information that other equipment checks personage need not be switched by obtaining user, and the relevant information of personage can be checked on the tv screen, The complexity of user's operation is reduced, the efficiency that user obtains information is improved, improves the Experience Degree of user.
For up to above-mentioned purpose, second aspect of the present invention embodiment proposes in a kind of video based on artificial intelligence and shows people The device of thing information, including:Sectional drawing processing module, for being instructed according to the person recognition of reception, is carried out to TV picture Sectional drawing, to obtain the picture to be identified with face;First sending module, for the picture to be identified to be sent to service Device, so that the server carries out recognition of face to the picture to be identified, and waits to know according to being obtained face recognition result The relevant information of personage in other picture, and return to the relevant information of personage;Display module, for showing people in video screen The relevant information of thing.
The device of people information is shown in the video based on artificial intelligence of the embodiment of the present invention, is known according to the personage of reception Do not instruct and sectional drawing is carried out to TV picture, to obtain the picture to be identified with face, picture to be identified is sent to clothes Business device, so that server carries out recognition of face to picture to be identified, and obtains people in picture to be identified according to face recognition result The relevant information of thing, and the relevant information of personage is returned, and show in video screen the relevant information of personage.Thus, So that user need not switch the relevant information that other equipment checks personage, the related letter of personage can be checked on the tv screen Breath, reduces the complexity of user's operation, improves the efficiency that user obtains information, improves the Experience Degree of user.
Third aspect present invention embodiment provides the system that people information is shown in a kind of video based on artificial intelligence, Including intelligent television end and server, wherein, the intelligent television end, for being instructed according to the person recognition of reception, to current Television image carries out sectional drawing, to obtain the picture to be identified with face, and the picture to be identified is sent to server, with And the relevant information of personage that the reception server is returned, and show in video screen the relevant information of personage;The server, Personage in the picture to be identified is obtained for carrying out recognition of face to the picture to be identified, and according to face recognition result Relevant information, and to intelligent television end return personage relevant information.
The system that people information is shown in the video based on artificial intelligence of the embodiment of the present invention, intelligent television end is according to connecing The person recognition instruction of receipts carries out sectional drawing to TV picture, to obtain the picture to be identified with face, by figure to be identified Piece is sent to server, and server carries out recognition of face to picture to be identified, and obtains figure to be identified according to face recognition result The relevant information of personage in piece, and to the relevant information of intelligent television end return personage, intelligent television end is in video screen Show the relevant information of personage.As a result, user need not switch the relevant information that other equipment checks personage, in video screen On can check the relevant information of personage, reduce user operation complexity, improve user obtain information efficiency, improve The Experience Degree of user.
Fourth aspect present invention embodiment provides the device that people information is shown in a kind of video based on artificial intelligence, Including:Processor;Memory for storing processor-executable instruction;Wherein, the processor is configured as:Sectional drawing processing Module, for being instructed according to the person recognition of reception, sectional drawing is carried out to TV picture, to be identified with face to obtain Picture;First sending module, for the picture to be identified to be sent to server, so that the server is to described to be identified Picture carries out recognition of face, and according to the relevant information of personage in the face recognition result acquisition picture to be identified, and return The relevant information of the Huis' thing;Display module, the relevant information for showing personage in video screen.
Fifth aspect present invention embodiment provides a kind of nonvolatile computer storage media, and the computer storage is situated between Matter is stored with one or more program, when one or more of programs are performed by an equipment so that the equipment Perform to show people information method in the video based on artificial intelligence of first aspect present invention embodiment.
Sixth aspect present invention embodiment provides a kind of computer program product, when in the computer program product When instruction processing unit is performed, perform in a kind of video based on artificial intelligence and show people information method, methods described includes:Root Instructed according to the person recognition of reception, sectional drawing is carried out to TV picture, to obtain the picture to be identified with face;Will be described Picture to be identified is sent to server, so that the server carries out recognition of face to the picture to be identified, and according to face Recognition result obtains the relevant information of personage in the picture to be identified, and returns to the relevant information of personage;In video screen The relevant information of middle display personage.The additional aspect and advantage of the present invention will be set forth in part in the description, partly will be from Become obvious in following description, or recognized by the practice of the present invention.
Brief description of the drawings
The above-mentioned and/or additional aspect and advantage of the present invention will become from description of the accompanying drawings below to embodiment is combined Substantially and be readily appreciated that, wherein:
Fig. 1 is shows the flow of people information method in the video based on artificial intelligence according to one embodiment of the invention Figure;
Fig. 2 is the refined flow chart that server excavates picture and the corresponding relation of personage;
Fig. 3 a are the schematic diagram one of television image;
Fig. 3 b are the schematic diagram two of television image;
Fig. 4 is shows the stream of people information method in the video based on artificial intelligence according to another embodiment of the present invention Cheng Tu;
Fig. 5 is the schematic diagram of the process of speech recognition in server;
Fig. 6 is the stream that people information method is shown in the video based on artificial intelligence according to another of the invention embodiment Cheng Tu;
Fig. 7 is shows the knot of the device of people information in the video based on artificial intelligence according to one embodiment of the invention Structure schematic diagram;
Fig. 8 is shows the device of people information in the video based on artificial intelligence according to another embodiment of the present invention Structural representation;
Fig. 9 is the device that people information is shown in the video based on artificial intelligence according to another of the invention embodiment Structural representation;
Figure 10 is shows the device of people information in the video based on artificial intelligence according to further embodiment of the present invention Structural representation;
Figure 11 is system that people information is shown in the video based on artificial intelligence according to one embodiment of the invention Structural representation;
Figure 12 is system that people information is shown in the video based on artificial intelligence according to another embodiment of the present invention Structural representation;
Figure 13 be show people information in the video based on artificial intelligence according to a specific embodiment of the invention be The interaction schematic diagram of control terminal, intelligent television end and server in system.
Embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached The embodiment of figure description is exemplary, is only used for explaining the present invention, and is not considered as limiting the invention.
In the description of the invention, it is to be understood that term " multiple " refers to two or more;Term " first ", " second " is only used for describing purpose, and it is not intended that indicating or implying relative importance.
Below with reference to the accompanying drawings describe to show people information side in the video based on artificial intelligence according to embodiments of the present invention Method, device and system.
Fig. 1 is shows the flow of people information method in the video based on artificial intelligence according to one embodiment of the invention Figure., wherein it is desired to show that people information method can be used in explanation, the video based on artificial intelligence of the embodiment In intelligent television, it can also apply in smart television set top box.The embodiment is to show people information method application in video It is described exemplified by intelligent television.
As shown in figure 1, people information method is shown in the video based on artificial intelligence according to embodiments of the present invention, including Following steps.
S11, is instructed according to the person recognition of reception, and sectional drawing is carried out to TV picture, to obtain treating with face Recognize picture.
As a kind of exemplary embodiment, during user watches TV programme by intelligent television, with Family is it should be understood that personage in TV programme or when playing the part of the performer of certain role, user can be connected by being set up with intelligent television The control terminal input person recognition instruction connect.
As a kind of exemplary embodiment, user can input person recognition by voice mode and instruct.
For example, when user has the demand understood to the role performer in TV play film, user can be direct Picking up the input of the voice-input devices such as mobile phone or remote control, " whom this people is", " whom his (she) is" or " introduce The voice messagings such as this people " come to intelligent television input person recognition instruction.
Wherein, control terminal is set such as can be the remote control with speech voice input function, smart mobile phone, tablet personal computer It is standby.
, wherein it is desired to which explanation, control terminal can be set up by the modes such as bluetooth, infrared or WiFi and intelligent television Connection.
, wherein it is desired to explanation, in voice messaging gatherer process, the effect of sound can because of control terminal performance difference, Sound source is to the distance of control terminal distance, and control terminal supports the difference of single microphone or microphone array and become Change.On the whole, control terminal performance is higher, source of sound to control terminal distance it is shorter, using effective microphone array without It is single Mike, the voice messaging that feature is more completely more conducive to identification can be obtained.In order to which the voice messaging for being easy to identification can be obtained, The embodiment can use sound effect good, and the voice messaging of the control terminal reception user using microphone array.
S12, picture to be identified is sent to server, so that server carries out recognition of face, and root to picture to be identified The relevant information of personage in picture to be identified is obtained according to face recognition result, and returns to the relevant information of personage.
Specifically, after the picture to be identified of interception is obtained, intelligent television can send picture to be identified to server.It is right Ying Di, server receives picture to be identified, and generates face characteristic letter corresponding with picture to be identified according to face characteristic model Breath, then, acquired face characteristic information is matched with the face characteristic information of the face picture prestored, and according to The people tag in picture to be identified is determined with result, and obtains the relevant information of personage corresponding with people tag.
Wherein, face characteristic model is that server is generated based on deep neural network training in advance.
As a kind of example, the process for setting up face characteristic model is:By deep neural network to facial Feature Modeling, And the face picture data of magnanimity are obtained, then, model is trained by face picture data, to set up face characteristic mould Type.
, wherein it is desired to understand, the marked people tag of the face picture such as name prestored.
Wherein, the face picture prestored can be stored in the data that the foundation of Kmeans trees is for example layered with Hierarchical clustering methods In storehouse.
For example, after the face characteristic of picture to be identified is obtained, it can lead in the database of the face picture prestored The mode for crossing level lookup carries out similar face retrieval, to obtain the face picture matched with the face characteristic of picture to be identified, And the personage in picture to be identified is determined according to the people tag information of face picture.
In one embodiment of the invention, can be by pre-saving personage it is determined that after personage in picture to be identified The relevant information of correspondence personage is obtained in the corresponding relation of information associated therewith.
Wherein, the relevant information of personage can include the base attribute information of personage, can also include related to personage Other information, for example, the relation between personage and other personages, and the information such as the hot news related to the personage.
Wherein, base attribute information can include the information such as name, sex, summary experience.
, wherein it is desired to understand, needed in order to which accurately personage is identified, in server in advance from magnanimity number It is accurate in excavate picture and the corresponding relation of personage, i.e. to need to obtain the correspondence of high-quality personage and picture in server Relation.
As a kind of exemplary embodiment, server excavates the process of picture and the corresponding relation of personage, such as Fig. 2 institutes Show, detailed process is:
The name information (such as the people's list of file names provided on Baidupedia) of magnanimity can be provided, then, pass through people tag The mode of information carries out automatic fitration to name, then, obtains mass picture (such as the picture on Baidupedia), passes through picture and text Matching process obtain the corresponding picture of correspondence name (wherein, the quantity of picture can for one or multiple), afterwards, pass through people Face characteristic model carries out Face datection and feature extraction, afterwards, by vision similarity algorithm according to the face characteristic extracted Carry out name to disappear qi, to handle duplication of name situation.Then, the picture of same task is filtered by hierarchy clustering method, and Utilize the multistage face vision index of the opencv flann storehouses generation increased income.
S13, shows the relevant information of personage in video screen.
In one embodiment of the invention, can be in the preset areas of video screen in order to not influence the normal viewing of user The relevant information of personage is shown in domain.As a result, user can check personage's while continuing to watch TV programme Relevant information, improves the Experience Degree of user.
Wherein, position of the predeterminable area on intelligent television can be acquiescence, can be set with user oneself.
For example, the position for the display predeterminable area given tacit consent on intelligent television is to show personage in the upper right side of intelligent television Relevant information, user can show the relevant information of personage in the lower left of intelligent television according to demand.
For example, it is assumed that the content shown in some TV play, television image, such as Fig. 3 a are being played in intelligent television It is shown, if user is it should be understood that the relevant information of the performer in the picture, user can be by with speech voice input function The voice messaging of remote control input " whom this people is ", intelligent television receives voice messaging, and carries out speech recognition to voice messaging, And can determine that the corresponding instruction of the voice messaging is person recognition instruction according to voice identification result, now, intelligent television is to working as Preceding television image carries out sectional drawing, and the picture to be identified with face intercepted is sent into server, corresponding server The relevant information of the personage shown in the relevant information of personage, intelligent television is returned to intelligent television, as shown in Figure 3 b.Pass through figure 3b can be seen that the intercepted picture of display in intelligent television, and show the relevant information of personage in the lower section of the picture.Separately Outside, the text message corresponding to the voice messaging that user's input is also shown on video screen is can be seen that by Fig. 3 a.
, wherein it is desired to show that people information method is being obtained in explanation, the video based on artificial intelligence in the implementation During the relevant information for taking personage, without the TV programme pause to broadcasting, i.e., user's viewing TV programme are not interrupted, are used Family can be to inquire about when seeing, and during inquiry, user need not change equipment, you can people is obtained in intelligent television The relevant information of thing.
In one embodiment of the invention, when the relevant information of personage is shown on intelligent television, it can be broadcast with voice The relevant information of journalist's thing.
, wherein it is desired to understand, in the relevant information of intelligent television voice broadcast personage, intelligent television is tentative The TV programme of broadcasting, and at the end of voice broadcast, continue the report of TV programme.
As a kind of exemplary embodiment, the voice broadcast instruction that intelligent television can be inputted according to user is fixed tentatively just In the TV programme of broadcasting, and the relevant information of voice broadcast personage.
Specifically, when user is inconvenient to check the relevant information of the personage shown in intelligent television, user can be with Voice broadcast is inputted by control terminal to intelligent television to instruct, intelligent television instructs tentative TV programme according to voice broadcast Play, and the relevant information of voice broadcast personage, and terminate in voice broadcast, continue to play TV programme.
, wherein it is desired to understand, picture to be identified can include multiple personages, and each personage is using the present embodiment Method obtains the relevant information of correspondence personage.
People information method is shown in the video based on artificial intelligence of the embodiment of the present invention, according to the person recognition of reception Instruction carries out sectional drawing to TV picture, and to obtain the picture to be identified with face, picture to be identified is sent to service Device, so that server carries out recognition of face to picture to be identified, and obtains personage in picture to be identified according to face recognition result Relevant information, and return to the relevant information of personage, and show in video screen the relevant information of personage.Thus, make The relevant information that other equipment checks personage need not be switched by obtaining user, and the relevant information of personage can be checked on the tv screen, The complexity of user's operation is reduced, the efficiency that user obtains information is improved, improves the Experience Degree of user.
Fig. 4 is shows the stream of people information method in the video based on artificial intelligence according to another embodiment of the present invention Cheng Tu., wherein it is desired to which explanation, the embodiment is entered exemplified by showing that people information method is applied in intelligent television in video Row description.
As shown in figure 4, people information method is shown in the video based on artificial intelligence according to embodiments of the present invention, including Following steps.
S41, receives the voice messaging that user is inputted by control terminal.
During user watches TV programme by intelligent television, in user it should be understood that personage in TV programme Or when playing the part of the performer of certain role, user can be referred to by setting up the control terminal being connected input person recognition with intelligent television Order.For example, when user has the demand understood to the role performer in TV play film, user can directly pick up hand " whom this people is to the input of the voice-input device such as machine or remote control", " whom his (she) is" or " introducing this people " Instructed Deng voice messaging to intelligent television input person recognition.
Wherein, control terminal is set such as can be the remote control with speech voice input function, smart mobile phone, tablet personal computer It is standby.
, wherein it is desired to which explanation, control terminal can be set up by the modes such as bluetooth, infrared or WiFi and intelligent television Connection.
S42, voice messaging is sent to server, so that server determines that the corresponding instruction of voice letter refers to for person recognition When making, person recognition instruction is returned.
Specifically, server is after the voice messaging of intelligent television transmission is received, and server carries out language to voice messaging Sound is recognized, and determines whether the corresponding instruction of voice messaging is person recognition instruction according to voice identification result, and it is determined that language When the corresponding instruction of message breath is person recognition instruction, person recognition instruction is returned to intelligent television.
Wherein, in server speech recognition process, as shown in figure 5, being carried out with reference to Fig. 5 to the process of speech recognition Description:
After server obtains voice messaging, server carries out feature extraction to voice messaging, to obtain voice messaging Audio frequency characteristics, and by audio frequency characteristics input decoder, voice identification result is obtained by decoder.In decoder decoding process In, acoustic model, language model and pronunciation dictionary can be used.
Wherein, the main function of acoustic model is that audio frequency characteristics are changed into syllabication.
Wherein, the main function of language model is that syllable is converted into text.
Wherein, pronunciation dictionary then provides a mapping table from syllable to text.
Assuming that representing the voice signal of input with X, W represents word sequence, and what speech recognition process was solved is following ask Topic:
After above formula conversion, it is equal to:
Speech recognition process, is the P (X | W) and P (W) for obtaining maximum respectively, and the P (X | W) for solving maximum is acoustic model The problem of solving, and it is the problem of language model will be solved to solve maximum P (W).
S43, the person recognition instruction that the reception server is returned, carries out sectional drawing to TV picture, has people to obtain The picture to be identified of face.
Specifically, when intelligent television receives the person recognition instruction of server return, intelligent television is to TV Picture carries out sectional drawing, to obtain the picture to be identified with face.
S44, picture to be identified is sent to server, so that server carries out recognition of face, and root to picture to be identified The relevant information of personage in picture to be identified is obtained according to face recognition result, and returns to the relevant information of personage.
, wherein it is desired to which explanation, the explanation to step S12 is also applied for step S44, not repeated herein.
S45, shows the relevant information of personage in video screen.
In one embodiment of the invention, can be in the preset areas of video screen in order to not influence the normal viewing of user The relevant information of personage is shown in domain.As a result, user can check personage's while continuing to watch TV programme Relevant information, improves the Experience Degree of user.
Wherein, position of the predeterminable area on intelligent television can be acquiescence, can be set with user oneself.
For example, the position for the display predeterminable area given tacit consent on intelligent television is to show personage in the upper right side of intelligent television Relevant information, user can show the relevant information of personage in the lower left of intelligent television according to demand.
, wherein it is desired to show that people information method is obtaining the related letter of personage in explanation, the video in the implementation During breath, TV programme are watched without to the pause of the TV programme of broadcasting, i.e., not interrupting user, user can be to look into when seeing Ask, and during inquiry, user need not change equipment, you can the relevant information of personage is obtained in intelligent television.
In one embodiment of the invention, shown on intelligent television after the relevant information of personage, can also according to The voice broadcast instruction of family input, the tentative TV programme played, and the relevant information of voice broadcast personage.
As a kind of exemplary embodiment, be inconvenient to check the related letter of the personage shown in intelligent television in user During breath, user can also input voice broadcast to intelligent television by control terminal and instruct, and intelligent television refers to according to voice broadcast The broadcasting of the tentative TV programme of order, and the relevant information of voice broadcast personage, and terminate in voice broadcast, continue to play TV Program.
People information method is shown in the video based on artificial intelligence of the embodiment of the present invention, user is received by controlling eventually The voice messaging sent is held, and voice messaging is sent to server, server returns to person recognition according to voice messaging and instructed, Intelligent television instructs according to the person recognition of reception and carries out sectional drawing to TV picture, to obtain the figure to be identified with face Piece;Picture to be identified is sent to server, so that server carries out recognition of face to picture to be identified, and according to recognition of face As a result the relevant information of personage in picture to be identified is obtained, and returns to the relevant information of personage, and is shown in video screen Let others have a look at the relevant information of thing.As a result, user need not switch the relevant information that other equipment checks personage, on the tv screen The relevant information of personage can be checked, the complexity of user's operation is reduced, the efficiency that user obtains information is improved, improves The Experience Degree of user.
Fig. 6 is the stream that people information method is shown in the video based on artificial intelligence according to another of the invention embodiment Cheng Tu., wherein it is desired to which explanation, the embodiment is entered exemplified by showing that people information method is applied in intelligent television in video Row description.
As shown in fig. 6, people information method is shown in the video based on artificial intelligence according to embodiments of the present invention, including Following steps.
S61, receives the voice messaging that user is inputted by control terminal.
, wherein it is desired to which explanation, the foregoing explanation to step S41 is also applied for step S51, no longer go to live in the household of one's in-laws on getting married herein State.
S62, speech recognition is carried out to voice messaging, and determine that the corresponding instruction of voice messaging is according to voice identification result It is no to be instructed for person recognition.
Wherein, intelligent television is identical with the process that server carries out speech recognition to voice messaging, foregoing to server pair The description that voice messaging carries out the process of speech recognition is also applied for intelligent television, and here is omitted.
S63, when it is determined that the corresponding instruction of voice messaging is person recognition instruction, sectional drawing is carried out to TV picture, To obtain the picture to be identified with face.
Specifically, when intelligent television receives the person recognition instruction of server return, intelligent television is to TV Picture carries out sectional drawing, to obtain the picture to be identified with face.
S64, picture to be identified is sent to server, so that server carries out recognition of face, and root to picture to be identified The relevant information of personage in picture to be identified is obtained according to face recognition result, and returns to the relevant information of personage.
, wherein it is desired to which explanation, the explanation to step S12 is also applied for step S64, not repeated herein.
S65, shows the relevant information of personage in video screen.
In one embodiment of the invention, can be in the preset areas of video screen in order to not influence the normal viewing of user The relevant information of personage is shown in domain.As a result, user can check personage's while continuing to watch TV programme Relevant information, improves the Experience Degree of user.
Wherein, position of the predeterminable area on intelligent television can be acquiescence, can be set with user oneself.
For example, the position for the display predeterminable area given tacit consent on intelligent television is to show personage in the upper right side of intelligent television Relevant information, user can show the relevant information of personage in the lower left of intelligent television according to demand.
, wherein it is desired to show that people information method is obtaining the related letter of personage in explanation, the video in the implementation During breath, TV programme are watched without to the pause of the TV programme of broadcasting, i.e., not interrupting user, user can be to look into when seeing Ask, and during inquiry, user need not change equipment, you can the relevant information of personage is obtained in intelligent television.
In one embodiment of the invention, shown on intelligent television after the relevant information of personage, can also according to The voice broadcast instruction of family input, the tentative TV programme played, and the relevant information of voice broadcast personage.
As a kind of exemplary embodiment, be inconvenient to check the related letter of the personage shown in intelligent television in user During breath, user can also input voice broadcast to intelligent television by control terminal and instruct, and intelligent television refers to according to voice broadcast The broadcasting of the tentative TV programme of order, and the relevant information of voice broadcast personage, and terminate in voice broadcast, continue to play TV Program.
People information method is shown in the video based on artificial intelligence of the embodiment of the present invention, user is received by controlling eventually The voice messaging sent is held, and when it is determined that the corresponding instruction of voice messaging is person recognition instruction, TV picture is entered Row sectional drawing, to obtain the picture to be identified with face, picture to be identified is sent to server, so that server is to be identified Picture carries out recognition of face, and according to the relevant information of personage in face recognition result acquisition picture to be identified, and return to people The relevant information of thing, and show in video screen the relevant information of personage.As a result, user need not switch other equipment The relevant information of personage is checked, the relevant information of personage can be checked on the tv screen, the complexity of user's operation is reduced, The efficiency that user obtains information is improved, the Experience Degree of user is improved.
In order to realize above-described embodiment, the present invention also proposes to show people information in a kind of video based on artificial intelligence Device.
Fig. 7 is shows the knot of the device of people information in the video based on artificial intelligence according to one embodiment of the invention Structure schematic diagram.
As shown in fig. 7, the device of people information is shown in the video based on artificial intelligence according to embodiments of the present invention, bag Include:Sectional drawing processing module 110, the first sending module 120 and display module 130, wherein:
Sectional drawing processing module 110 is used to be instructed according to the person recognition of reception, sectional drawing is carried out to TV picture, to obtain Take the picture to be identified with face.
First sending module 120 is used to send picture to be identified to server, so that server enters to picture to be identified Row recognition of face, and according to the relevant information of personage in face recognition result acquisition picture to be identified, and return to the phase of personage Close information.
Wherein, the relevant information of personage can include the base attribute information of personage, can also include related to personage Other information, for example, the relation between personage and other personages, and the information such as the hot news related to the personage.
Wherein, base attribute information can include the information such as name, sex, summary experience.
Display module 130 is used for the relevant information that personage is shown in video screen.
In one embodiment of the invention, on the basis of shown in Fig. 7, as shown in figure 8, sectional drawing processing module 110 can With including the first receiving unit 111, the second transmitting element 112 and the first sectional drawing unit 113, wherein:
First receiving unit 111 is used to receive the voice messaging that user is inputted by control terminal.
Wherein, control terminal is set such as can be the remote control with speech voice input function, smart mobile phone, tablet personal computer It is standby.
, wherein it is desired to which explanation, control terminal can be set up by the modes such as bluetooth, infrared or WiFi and intelligent television Connection.
Second transmitting element 112 is used to send voice messaging to server, so that server is it is determined that voice messaging Instruct when being instructed for person recognition, return to person recognition instruction.
First sectional drawing unit 113 is used for the person recognition instruction that the reception server is returned, and TV picture is cut Figure.
In one embodiment of the invention, in order to improve the Experience Degree of user, on the basis shown in Fig. 7, such as Fig. 9 institutes Show, the device also includes broadcasting module 140, wherein, broadcasting module 140 is used for the relevant information of voice broadcast personage.
As a kind of exemplary embodiment, be inconvenient to check the related letter of the personage shown in intelligent television in user During breath, user can also input voice broadcast to intelligent television by control terminal and instruct, and broadcasting module 140 is according to voice broadcast The broadcasting of the tentative TV programme of instruction, and the relevant information of voice broadcast personage, and terminate in voice broadcast, continue to play electricity Depending on program.
, wherein it is desired to illustrate, the broadcasting module 140 in the device embodiment shown in Fig. 9 is further included in foregoing In Fig. 8 device embodiment, this present invention is not limited.
In one embodiment of the invention, on the basis of shown in Fig. 7, as shown in Figure 10, sectional drawing processing module 110 can With including the second receiving unit 114, the sectional drawing unit 116 of processing unit 115 and second, wherein:
Second receiving unit 114 is used to receive the voice messaging that user is inputted by control terminal.
Processing unit 115 is used to carry out speech recognition to voice messaging, and determines voice messaging according to voice identification result Whether corresponding instruction is person recognition instruction.
Second sectional drawing unit 116 is used to, when the corresponding instruction of voice messaging is person recognition instruction, draw TV Face carries out sectional drawing.
In one embodiment of the invention, in order to not influence the normal viewing of user, display module 110 specifically for: The relevant information of personage is shown in the predeterminable area of video screen.
Wherein, position of the predeterminable area on intelligent television can be acquiescence, can be set with user oneself.
For example, the position for the display predeterminable area given tacit consent on intelligent television is to show personage in the upper right side of intelligent television Relevant information, user can show the relevant information of personage in the lower left of intelligent television according to demand.
, wherein it is desired to which explanation, foregoing to showing explaining for people information method in the video based on artificial intelligence The bright device for being also applied for showing people information in the video based on artificial intelligence of the embodiment, here is omitted.
The device of people information is shown in the video based on artificial intelligence of the embodiment of the present invention, is known according to the personage of reception Do not instruct and sectional drawing is carried out to TV picture, to obtain the picture to be identified with face, picture to be identified is sent to clothes Business device, so that server carries out recognition of face to picture to be identified, and obtains people in picture to be identified according to face recognition result The relevant information of thing, and the relevant information of personage is returned, and show in video screen the relevant information of personage.Thus, So that user need not switch the relevant information that other equipment checks personage, the related letter of personage can be checked on the tv screen Breath, reduces the complexity of user's operation, improves the efficiency that user obtains information, improves the Experience Degree of user.
In order to realize above-described embodiment, the present invention also proposes to show people information in a kind of video based on artificial intelligence System.
Figure 11 is system that people information is shown in the video based on artificial intelligence according to one embodiment of the invention Structural representation.
As shown in figure 11, the system of people information is shown in the video based on artificial intelligence of the embodiment can include intelligence Energy television 10 and server 20, wherein,
Intelligent television end 10 is used to be instructed according to the person recognition of reception, and sectional drawing is carried out to TV picture, to obtain Picture to be identified with face, and picture to be identified is sent to server 20, and the personage that the reception server 20 is returned Relevant information, and show in video screen the relevant information of personage.
Server 20 is used to carry out picture to be identified recognition of face, and obtains picture to be identified according to face recognition result The relevant information of middle personage, and to intelligent television end 10 return personage relevant information.
In one embodiment of the invention, server 20 specifically for:According to face characteristic model generation with it is to be identified The corresponding face characteristic information of picture;Face characteristic information is matched with the face characteristic information of the face picture prestored, And the people tag in picture to be identified is determined according to matching result;Obtain the relevant information of personage corresponding with people tag.
In one embodiment of the invention, on the basis of shown in Figure 11, as shown in figure 12, the system can also include Control terminal 30, wherein, control terminal 30 is used for the voice messaging for receiving user's input.
Intelligent television end 10 receives the voice messaging that user is inputted by control terminal 30, and voice messaging is sent to service Device 20, so that server 20 is when it is determined that the instruction of voice messaging instructs for person recognition, returns to person recognition instruction, Yi Jijie The person recognition instruction that server 20 is returned is received, sectional drawing is carried out to TV picture.
In one embodiment of the invention, intelligent television end 10 is additionally operable to the relevant information of voice broadcast personage.
In one embodiment of the invention, intelligent television end 10 is additionally operable to receive what user was inputted by control terminal 30 Voice messaging, speech recognition is carried out to voice messaging, and whether determine the corresponding instruction of voice messaging according to voice identification result Instruct, and when the corresponding instruction of voice messaging is person recognition instruction, TV picture is cut for person recognition Figure.
In one embodiment of the invention, intelligent television end 10 in the predeterminable area of video screen specifically for showing people The relevant information of thing.
The system that people information is shown in the video based on artificial intelligence of the embodiment of the present invention, intelligent television end is according to connecing The person recognition instruction of receipts carries out sectional drawing to TV picture, to obtain the picture to be identified with face, by figure to be identified Piece is sent to server, and server carries out recognition of face to picture to be identified, and obtains figure to be identified according to face recognition result The relevant information of personage in piece, and to the relevant information of intelligent television end return personage, intelligent television end is in video screen Show the relevant information of personage.As a result, user need not switch the relevant information that other equipment checks personage, in video screen On can check the relevant information of personage, reduce user operation complexity, improve user obtain information efficiency, improve The Experience Degree of user.
Figure 13 be show people information in the video based on artificial intelligence according to a specific embodiment of the invention be The interaction schematic diagram of control terminal, intelligent television end and server in system.
As shown in figure 13, being somebody's turn to do the process based on the system interaction that people information is shown in the video of artificial intelligence is:
S131, control terminal 30 receives the voice messaging of user's input.
S132, control terminal 30 sends voice messaging to intelligent television end 10.
S133, intelligent television end 10 sends the semantic analysis comprising voice messaging to server 20 and asked.
S134, server 20 carries out speech recognition to voice messaging, and determines voice messaging pair according to voice identification result Whether the instruction answered is person recognition instruction, if so, then returning to person recognition instruction to intelligent television end 10.
S135, intelligent television end 10 instructs according to person recognition and carries out sectional drawing to TV picture, has people to obtain The picture to be identified of face.
Picture to be identified is sent to server 20 by S136, intelligent television end 10.
S137, server 20 carries out recognition of face to picture to be identified, and obtains figure to be identified according to face recognition result The relevant information of personage in piece.
S138, server 20 sends the relevant information of personage to intelligent television end 10.
S139, intelligent television end 20 shows the relevant information of personage on the tv screen.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show The description of example " or " some examples " etc. means to combine specific features, structure, material or the spy that the embodiment or example are described Point is contained at least one embodiment of the present invention or example.In this manual, to the schematic representation of above-mentioned term not Identical embodiment or example must be directed to.Moreover, specific features, structure, material or the feature of description can be with office Combined in an appropriate manner in one or more embodiments or example.In addition, in the case of not conflicting, the skill of this area Art personnel can be tied the not be the same as Example or the feature of example and non-be the same as Example or example described in this specification Close and combine.
In addition, term " first ", " second " are only used for describing purpose, and it is not intended that indicating or implying relative importance Or the implicit quantity for indicating indicated technical characteristic.Thus, define " first ", the feature of " second " can express or Implicitly include at least one this feature.In the description of the invention, " multiple " are meant that two or more, unless separately There is clearly specific limit.
Any process described otherwise above or method description are construed as in flow chart or herein, represent to include Module, fragment or the portion of the code of one or more executable instructions for the step of realizing specific logical function or process Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not be by shown or discussion suitable Sequence, including according to involved function by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be of the invention Embodiment person of ordinary skill in the field understood.
Represent in flow charts or logic and/or step described otherwise above herein, for example, being considered use In the order list for the executable instruction for realizing logic function, it may be embodied in any computer-readable medium, for Instruction execution system, device or equipment (such as computer based system including the system of processor or other can be held from instruction The system of row system, device or equipment instruction fetch and execute instruction) use, or combine these instruction execution systems, device or set It is standby and use.For the purpose of this specification, " computer-readable medium " can any can be included, store, communicate, propagate or pass Defeated program is for instruction execution system, device or equipment or the dress for combining these instruction execution systems, device or equipment and using Put.The more specifically example (non-exhaustive list) of computer-readable medium includes following:Electricity with one or more wirings Connecting portion (electronic installation), portable computer diskette box (magnetic device), random access memory (RAM), read-only storage (ROM), erasable edit read-only storage (EPROM or flash memory), fiber device, and portable optic disk is read-only deposits Reservoir (CDROM).In addition, can even is that can be in the paper of printing described program thereon or other are suitable for computer-readable medium Medium, because can then enter edlin, interpretation or if necessary with it for example by carrying out optical scanner to paper or other media His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned In embodiment, the software that multiple steps or method can in memory and by suitable instruction execution system be performed with storage Or firmware is realized.If, and in another embodiment, can be with well known in the art for example, realized with hardware Any one of row technology or their combination are realized:With the logic gates for realizing logic function to data-signal Discrete logic, the application specific integrated circuit with suitable combinational logic gate circuit, programmable gate array (PGA), scene Programmable gate array (FPGA) etc..
Those skilled in the art are appreciated that to realize all or part of step that above-described embodiment method is carried Rapid to can be by program to instruct the hardware of correlation to complete, described program can be stored in a kind of computer-readable storage medium In matter, the program upon execution, including one or a combination set of the step of embodiment of the method.
In addition, each functional unit in each embodiment of the invention can be integrated in a processing module, can also That unit is individually physically present, can also two or more units be integrated in a module.Above-mentioned integrated mould Block can both be realized in the form of hardware, it would however also be possible to employ the form of software function module is realized.The integrated module is such as Fruit is realized using in the form of software function module and as independent production marketing or in use, can also be stored in a computer In read/write memory medium.
Storage medium mentioned above can be read-only storage, disk or CD etc..Although having been shown and retouching above Embodiments of the invention are stated, it is to be understood that above-described embodiment is exemplary, it is impossible to be interpreted as the limit to the present invention System, one of ordinary skill in the art can be changed to above-described embodiment, change, replace and become within the scope of the invention Type.

Claims (12)

1. people information method is shown in a kind of video based on artificial intelligence, it is characterised in that comprise the following steps:
Instructed according to the person recognition of reception, sectional drawing is carried out to TV picture, to obtain the picture to be identified with face;
The picture to be identified is sent to server, so that the server carries out recognition of face to the picture to be identified, And the relevant information of personage in the picture to be identified is obtained according to face recognition result, and return to the relevant information of personage;
The relevant information of personage is shown in video screen.
2. the method as described in claim 1, it is characterised in that described to be instructed according to the person recognition of reception, to TV Picture carries out sectional drawing, including:
Receive the voice messaging that user is inputted by control terminal;
The voice messaging is sent to the server, so that the server is it is determined that the instruction of the voice messaging is people During thing identification instruction, person recognition instruction is returned;
The person recognition instruction that the reception server is returned, sectional drawing is carried out to TV picture.
3. the method as described in claim 1, it is characterised in that also include:
The relevant information of personage described in voice broadcast.
4. the method as described in claim 1, it is characterised in that described to be instructed according to the person recognition of input, to TV Picture carries out sectional drawing, including:
Receive the voice messaging that user is inputted by control terminal;
Speech recognition is carried out to the voice messaging, and determines that the corresponding instruction of the voice messaging is according to voice identification result It is no to be instructed for person recognition;
When the corresponding instruction of the voice messaging is person recognition instruction, sectional drawing is carried out to TV picture.
5. the method as described in claim any one of 1-4, it is characterised in that the correlation that personage is shown in video screen Information, including:
The relevant information of personage is shown in the predeterminable area of video screen.
6. the device of people information is shown in a kind of video based on artificial intelligence, it is characterised in that including:
Sectional drawing processing module, for being instructed according to the person recognition of reception, sectional drawing is carried out to TV picture, is had to obtain The picture to be identified of face;
First sending module, for the picture to be identified to be sent to server, so that the server is to described to be identified Picture carries out recognition of face, and according to the relevant information of personage in the face recognition result acquisition picture to be identified, and return The relevant information of the Huis' thing;
Display module, the relevant information for showing personage in video screen.
7. device as claimed in claim 6, it is characterised in that the sectional drawing processing module, including:
First receiving unit, for receiving the voice messaging that user is inputted by control terminal;
Second transmitting element, for the voice messaging to be sent to the server, so that the server is it is determined that described When the instruction of voice messaging is that person recognition is instructed, person recognition instruction is returned;
First sectional drawing unit, the person recognition instruction returned for the reception server, sectional drawing is carried out to TV picture.
8. device as claimed in claim 6, it is characterised in that also include:
Broadcasting module, the relevant information for personage described in voice broadcast.
9. device as claimed in claim 6, it is characterised in that the sectional drawing processing module includes:
Second receiving unit, for receiving the voice messaging that user is inputted by control terminal;
Processing unit, determines that the voice is believed for carrying out speech recognition to the voice messaging, and according to voice identification result Whether the corresponding instruction of breath is person recognition instruction;
Second sectional drawing unit, for when the corresponding instruction of the voice messaging is person recognition instruction, to TV picture Carry out sectional drawing.
10. the device as described in claim any one of 6-9, it is characterised in that the display module, specifically for:
The relevant information of personage is shown in the predeterminable area of video screen.
11. show the system of people information in a kind of video based on artificial intelligence, it is characterised in that including intelligent television end and Server, wherein,
The intelligent television end, for being instructed according to the person recognition of reception, carries out sectional drawing, to obtain tool to TV picture There is a picture to be identified of face, and the picture to be identified is sent to server, and the personage that returns of the reception server Relevant information, and show in video screen the relevant information of personage;
The server, for carrying out recognition of face to the picture to be identified, and is treated according to being obtained face recognition result Recognize picture in personage relevant information, and to intelligent television end return personage relevant information.
12. system as claimed in claim 11, it is characterised in that the server, specifically for:
According to face characteristic model generation face characteristic information corresponding with the picture to be identified;
The face characteristic information is matched with the face characteristic information of the face picture prestored, and it is true according to matching result People tag in the fixed picture to be identified;
Obtain the relevant information of personage corresponding with the people tag.
CN201710168987.1A 2017-03-21 2017-03-21 People information methods, devices and systems are shown in video based on artificial intelligence CN107105340A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710168987.1A CN107105340A (en) 2017-03-21 2017-03-21 People information methods, devices and systems are shown in video based on artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710168987.1A CN107105340A (en) 2017-03-21 2017-03-21 People information methods, devices and systems are shown in video based on artificial intelligence

Publications (1)

Publication Number Publication Date
CN107105340A true CN107105340A (en) 2017-08-29

Family

ID=59675094

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710168987.1A CN107105340A (en) 2017-03-21 2017-03-21 People information methods, devices and systems are shown in video based on artificial intelligence

Country Status (1)

Country Link
CN (1) CN107105340A (en)

Cited By (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107527040A (en) * 2017-09-07 2017-12-29 维沃移动通信有限公司 A kind of method and apparatus of recognition of face
CN107730810A (en) * 2017-11-14 2018-02-23 郝思宇 Monitoring method, system in a kind of family room based on image
CN107748879A (en) * 2017-11-16 2018-03-02 百度在线网络技术(北京)有限公司 For obtaining the method and device of face information
CN108040125A (en) * 2017-12-28 2018-05-15 北京陌上花科技有限公司 Content recognition and method for pushing and TV syndrome AI assistant devices
CN108055590A (en) * 2017-12-20 2018-05-18 聚好看科技股份有限公司 The display methods of the graphic user interface of television image sectional drawing
CN108055589A (en) * 2017-12-20 2018-05-18 聚好看科技股份有限公司 Smart television
CN108111898A (en) * 2017-12-20 2018-06-01 聚好看科技股份有限公司 The display methods and smart television of the graphic user interface of television image sectional drawing
CN108259973A (en) * 2017-12-20 2018-07-06 青岛海信电器股份有限公司 The display methods of the graphic user interface of smart television and television image sectional drawing
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
CN108471551A (en) * 2018-03-23 2018-08-31 上海哔哩哔哩科技有限公司 Video main information display methods, device, system and medium based on main body identification
CN108632662A (en) * 2018-05-17 2018-10-09 聚好看科技股份有限公司 TV screenshotss method, apparatus and the equipment for including TV screen video recorder
CN108712667A (en) * 2018-05-17 2018-10-26 聚好看科技股份有限公司 A kind of smart television, its screenshotss application process, device and readable storage medium
CN108924589A (en) * 2018-08-02 2018-11-30 佛山龙眼传媒科技有限公司 Subtitle method of automatic configuration and device
CN108958872A (en) * 2018-07-06 2018-12-07 新疆玖富万卡信息技术有限公司 A kind of image display method and apparatus
CN109005421A (en) * 2018-08-17 2018-12-14 青岛海信电器股份有限公司 Image processing method and device, computer readable storage medium
CN109089132A (en) * 2018-07-26 2018-12-25 青岛聚看云科技有限公司 A kind of information search method and device
CN109151597A (en) * 2018-09-03 2019-01-04 聚好看科技股份有限公司 information display method and device
CN109189289A (en) * 2018-09-03 2019-01-11 聚好看科技股份有限公司 A kind of method and device generating icon based on screenshotss image
CN109413470A (en) * 2018-10-22 2019-03-01 青岛海信电器股份有限公司 A kind of the determination method and terminal device of image to be detected frame
CN109587547A (en) * 2018-12-30 2019-04-05 北京奇艺世纪科技有限公司 The control method for playing back and device of advertisement
CN109697245A (en) * 2018-12-05 2019-04-30 百度在线网络技术(北京)有限公司 Voice search method and device based on video web page
CN109922363A (en) * 2019-03-15 2019-06-21 青岛海信电器股份有限公司 A kind of graphical user interface method and display equipment of display screen shot
CN109996106A (en) * 2017-12-29 2019-07-09 深圳Tcl数字技术有限公司 A kind of method, system and the storage medium of voice control implantation information
WO2020038167A1 (en) * 2018-08-22 2020-02-27 Oppo广东移动通信有限公司 Video image recognition method and apparatus, terminal and storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104184923A (en) * 2014-08-27 2014-12-03 天津三星电子有限公司 System and method used for retrieving figure information in video
US20150006669A1 (en) * 2013-07-01 2015-01-01 Google Inc. Systems and methods for directing information flow
CN104933071A (en) * 2014-03-20 2015-09-23 小米科技有限责任公司 Information retrieval method and corresponding device
CN106021319A (en) * 2016-05-05 2016-10-12 乐视控股(北京)有限公司 Voice interaction method, device and system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150006669A1 (en) * 2013-07-01 2015-01-01 Google Inc. Systems and methods for directing information flow
CN104933071A (en) * 2014-03-20 2015-09-23 小米科技有限责任公司 Information retrieval method and corresponding device
CN104184923A (en) * 2014-08-27 2014-12-03 天津三星电子有限公司 System and method used for retrieving figure information in video
CN106021319A (en) * 2016-05-05 2016-10-12 乐视控股(北京)有限公司 Voice interaction method, device and system

Cited By (30)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107527040A (en) * 2017-09-07 2017-12-29 维沃移动通信有限公司 A kind of method and apparatus of recognition of face
CN107527040B (en) * 2017-09-07 2020-09-29 维沃移动通信有限公司 Face recognition method and device
CN107730810A (en) * 2017-11-14 2018-02-23 郝思宇 Monitoring method, system in a kind of family room based on image
CN107748879A (en) * 2017-11-16 2018-03-02 百度在线网络技术(北京)有限公司 For obtaining the method and device of face information
CN108322806A (en) * 2017-12-20 2018-07-24 青岛海信电器股份有限公司 The display methods of the graphic user interface of smart television and television image sectional drawing
CN108055590A (en) * 2017-12-20 2018-05-18 聚好看科技股份有限公司 The display methods of the graphic user interface of television image sectional drawing
CN108111898A (en) * 2017-12-20 2018-06-01 聚好看科技股份有限公司 The display methods and smart television of the graphic user interface of television image sectional drawing
CN108259973A (en) * 2017-12-20 2018-07-06 青岛海信电器股份有限公司 The display methods of the graphic user interface of smart television and television image sectional drawing
CN108289236A (en) * 2017-12-20 2018-07-17 青岛海信电器股份有限公司 The display methods of the graphic user interface of smart television and television image sectional drawing
WO2019120008A1 (en) * 2017-12-20 2019-06-27 青岛海信电器股份有限公司 Smart television and method for displaying graphical user interface of television screen shot
CN108055589A (en) * 2017-12-20 2018-05-18 聚好看科技股份有限公司 Smart television
CN108040125A (en) * 2017-12-28 2018-05-15 北京陌上花科技有限公司 Content recognition and method for pushing and TV syndrome AI assistant devices
CN109996106A (en) * 2017-12-29 2019-07-09 深圳Tcl数字技术有限公司 A kind of method, system and the storage medium of voice control implantation information
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
CN108471551A (en) * 2018-03-23 2018-08-31 上海哔哩哔哩科技有限公司 Video main information display methods, device, system and medium based on main body identification
CN108712667A (en) * 2018-05-17 2018-10-26 聚好看科技股份有限公司 A kind of smart television, its screenshotss application process, device and readable storage medium
CN108712667B (en) * 2018-05-17 2020-04-10 聚好看科技股份有限公司 Smart television, screen capture application method and device thereof, and readable storage medium
CN108632662A (en) * 2018-05-17 2018-10-09 聚好看科技股份有限公司 TV screenshotss method, apparatus and the equipment for including TV screen video recorder
WO2019218656A1 (en) * 2018-05-17 2019-11-21 聚好看科技股份有限公司 Smart television and screenshot-taking application method therefor, and storage medium
CN108958872A (en) * 2018-07-06 2018-12-07 新疆玖富万卡信息技术有限公司 A kind of image display method and apparatus
CN109089132A (en) * 2018-07-26 2018-12-25 青岛聚看云科技有限公司 A kind of information search method and device
CN108924589A (en) * 2018-08-02 2018-11-30 佛山龙眼传媒科技有限公司 Subtitle method of automatic configuration and device
CN109005421A (en) * 2018-08-17 2018-12-14 青岛海信电器股份有限公司 Image processing method and device, computer readable storage medium
WO2020038167A1 (en) * 2018-08-22 2020-02-27 Oppo广东移动通信有限公司 Video image recognition method and apparatus, terminal and storage medium
CN109189289A (en) * 2018-09-03 2019-01-11 聚好看科技股份有限公司 A kind of method and device generating icon based on screenshotss image
CN109151597A (en) * 2018-09-03 2019-01-04 聚好看科技股份有限公司 information display method and device
CN109413470A (en) * 2018-10-22 2019-03-01 青岛海信电器股份有限公司 A kind of the determination method and terminal device of image to be detected frame
CN109697245A (en) * 2018-12-05 2019-04-30 百度在线网络技术(北京)有限公司 Voice search method and device based on video web page
CN109587547A (en) * 2018-12-30 2019-04-05 北京奇艺世纪科技有限公司 The control method for playing back and device of advertisement
CN109922363A (en) * 2019-03-15 2019-06-21 青岛海信电器股份有限公司 A kind of graphical user interface method and display equipment of display screen shot

Similar Documents

Publication Publication Date Title
DK178888B1 (en) Intelligent automated assistant in a media environment
US9697206B2 (en) System and method for enhancing voice-enabled search based on automated demographic identification
Wöllmer et al. Youtube movie reviews: Sentiment analysis in an audio-visual context
CN107340991B (en) Voice role switching method, device, equipment and storage medium
CN106469212B (en) Man-machine interaction method and device based on artificial intelligence
JP5866728B2 (en) Knowledge information processing server system with image recognition system
Hampapur et al. Virage video engine
CN102117614B (en) Personalized text-to-speech synthesis and personalized speech feature extraction
CN106384593B (en) A kind of conversion of voice messaging, information generating method and device
US8862615B1 (en) Systems and methods for providing information discovery and retrieval
CN1116649C (en) Personalized video classification and retrieval system
US20140036022A1 (en) Providing a conversational video experience
KR101622111B1 (en) Dialog system and conversational method thereof
CN102771115B (en) The video segment recognition methods of network television and context targeted content display methods
CN105120304B (en) Information display method, apparatus and system
JP5557401B2 (en) Broadcast program related information providing apparatus and method
CN103607609B (en) The method for switching languages and device of a kind of TV channel
AU2016320681A1 (en) Intelligent automated assistant for media search and playback
KR20140089861A (en) display apparatus and method for controlling the display apparatus
CN106445156A (en) Method, device and terminal for intelligent home device control based on virtual reality
CN105228050B (en) The method of adjustment and device of earphone sound quality in terminal
KR20140093303A (en) display apparatus and method for controlling the display apparatus
US9230547B2 (en) Metadata extraction of non-transcribed video and audio streams
US20140111689A1 (en) Display device, method of controlling the display device, and information processor to control the display device
KR20140001105A (en) Display apparatus, method for controlling the display apparatus and interactive system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20170829