CN108509611A - Method and apparatus for pushed information - Google Patents
Method and apparatus for pushed information Download PDFInfo
- Publication number
- CN108509611A CN108509611A CN201810295444.0A CN201810295444A CN108509611A CN 108509611 A CN108509611 A CN 108509611A CN 201810295444 A CN201810295444 A CN 201810295444A CN 108509611 A CN108509611 A CN 108509611A
- Authority
- CN
- China
- Prior art keywords
- information
- candidate information
- target video
- facial image
- identity
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
Abstract
The embodiment of the present application discloses the method and apparatus for pushed information.One specific implementation mode of this method includes：Facial image in tracing detection target video；Based on the facial image in face information set and the target video, first personage's identity associated by the facial image in the target video is determined, wherein the face information aggregate includes face information associated with piece identity's mark；According to the correspondence of the candidate information pre-established and piece identity's mark, from candidate information set, candidate information corresponding with the first personage identity is chosen as the first candidate information；Push first candidate information.The embodiment, which realizes, is imbued with targetedly information push.
Description
Technical field
The invention relates to field of computer technology, the more particularly, to method and apparatus of pushed information.
Background technology
Information pushes, and is by certain technical standard or agreement, on the internet by pushing away also known as " Web broadcast "
The information that user needs is sent to reduce a technology of information overload.Information advancing technique by active push information to user,
User can be reduced the time spent in being searched on network.
Invention content
The embodiment of the present application proposes the method and apparatus for pushed information.
In a first aspect, the embodiment of the present application provides a kind of method for pushed information, this method includes：Tracing detection
Facial image in target video；Based on the facial image in face information set and above-mentioned target video, above-mentioned target is determined
First personage's identity associated by facial image in video, wherein above-mentioned face information set includes and piece identity
Identify associated face information；According to the correspondence of the candidate information pre-established and piece identity's mark, believe from candidate
In breath set, candidate information corresponding with above-mentioned first personage identity is chosen as the first candidate information；Push above-mentioned
One candidate information.
In some embodiments, the above-mentioned facial image based in face information set and above-mentioned target video, in determination
First personage's identity associated by the facial image in target video is stated, including：In response to detecting above-mentioned target video
In facial image indicate at least two personages, to indicate that the facial image of same personage distributes character recognition and label；According to each individual
Object identifies corresponding facial image number, determines that predetermined number target person identifies, wherein the corresponding people of each character recognition and label
Face image number is：The number of facial image in above-mentioned target video, to be assigned to the character recognition and label；For each target person
Object identifies, and according to above-mentioned face information set and the facial image for being assigned to target person mark, determination is assigned to the target
First personage's identity associated by the facial image of character recognition and label.
In some embodiments, the above method further includes：In response to detecting that the pause for being directed to above-mentioned target video plays
Operation determines the target video frame shown when above-mentioned target video pause；Based on above-mentioned face information set, above-mentioned target is determined
The second piece identity mark associated by facial image in video frame.
In some embodiments, the above method further includes：According to above-mentioned correspondence, from above-mentioned candidate information set,
Candidate information corresponding with above-mentioned second piece identity mark is chosen as the second candidate information；Push the above-mentioned second candidate letter
Breath.
In some embodiments, the above method further includes：Optical character identification is carried out to above-mentioned target video frame, in determination
State the text information in target video frame；According to above-mentioned text information, from above-mentioned candidate information set, chooses candidate information and make
For third candidate information；Push above-mentioned third candidate information.
In some embodiments, above-mentioned that optical character identification is carried out to above-mentioned target video frame, determine above-mentioned target video
Text information in frame, including：In response to detecting that above-mentioned target video frame includes at least one of following：Barrage and subtitle, from
It is determined in above-mentioned target video frame at least one of following：Barrage text information and caption character information.
In some embodiments, above-mentioned according to above-mentioned text information, from above-mentioned candidate information set, it is candidate to choose third
Information, including：Extract the keyword in above-mentioned barrage text information and/or above-mentioned caption character information；According to what is pre-established
The correspondence of keyword and candidate information chooses time corresponding with the keyword extracted from above-mentioned candidate information set
Select information as third candidate information.
In some embodiments, the above method further includes：Associated by the facial image in above-mentioned target video
One piece identity identifies, and establishes incidence relation information, wherein above-mentioned incidence relation information is used to indicate first personage's identity
Between incidence relation.
In some embodiments, the above method further includes：Above-mentioned incidence relation information is increased into the association pre-established
In relation information set, wherein the incidence relation information in above-mentioned incidence relation information aggregate is used to indicate at least two personages
Incidence relation between identity.
In some embodiments, the above method further includes：From above-mentioned incidence relation information aggregate, determine with it is following at least
One the 4th piece identity with incidence relation identifies：First personage's identity, above-mentioned second piece identity mark and on
State third personage's identity；According to above-mentioned correspondence, from above-mentioned candidate information set, above-mentioned 4th piece identity is chosen
Corresponding candidate information is identified as the 4th candidate information；Push above-mentioned 4th candidate information.
Second aspect, the embodiment of the present application provide a kind of device for pushed information, which includes：Detection is single
Member, the facial image being configured in tracing detection target video；First determination unit is configured to be based on face information set
With the facial image in above-mentioned target video, the first piece identity mark associated by the facial image in above-mentioned target video is determined
Know, wherein above-mentioned face information set includes face information associated with piece identity's mark；First selection unit, configuration
For the correspondence according to the candidate information that pre-establishes and piece identity's mark, from candidate information set, choose with it is upper
The corresponding candidate information of first personage's identity is stated as the first candidate information；First push unit, is configured in push
State the first candidate information.
In some embodiments, the first determination unit is also configured to：In response to detecting the people in above-mentioned target video
Face image indicates at least two personages, to indicate that the facial image of same personage distributes character recognition and label；According to each character recognition and label
Corresponding facial image number determines that predetermined number target person identifies, wherein the corresponding facial image of each character recognition and label
Number is：The number of facial image in above-mentioned target video, to be assigned to the character recognition and label；For each target person mark
Know, according to above-mentioned face information set and the facial image for being assigned to target person mark, determination is assigned to the target person
First personage's identity associated by the facial image of mark.
In some embodiments, above-mentioned apparatus further includes：Second determination unit is configured in response to detecting for upper
The pause play operation for stating target video determines the target video frame shown when above-mentioned target video pause；Third determination unit,
It is configured to be based on above-mentioned face information set, determines second personage's body associated by the facial image in above-mentioned target video frame
Part mark.
In some embodiments, above-mentioned apparatus further includes：Second selection unit is configured to according to above-mentioned correspondence,
From above-mentioned candidate information set, candidate information corresponding with above-mentioned second piece identity mark is chosen as the second candidate letter
Breath；Second push unit is configured to push above-mentioned second candidate information.
In some embodiments, above-mentioned apparatus further includes：4th determination unit, be configured to above-mentioned target video frame into
Row optical character identification determines the text information in above-mentioned target video frame；Third selection unit is configured to according to above-mentioned text
Word information chooses candidate information as third candidate information from above-mentioned candidate information set；Third push unit, configuration are used
In the above-mentioned third candidate information of push.
In some embodiments, the 4th determination unit is also configured to：In response to detecting that above-mentioned target video frame includes
At least one of below：Barrage and subtitle determine at least one of following from above-mentioned target video frame：Barrage text information and subtitle
Text information.
In some embodiments, third selection unit is also configured to：Extract above-mentioned barrage text information and/or above-mentioned
Keyword in caption character information；According to the correspondence of the keyword and candidate information that pre-establish, from above-mentioned candidate letter
In breath set, candidate information corresponding with the keyword extracted is chosen as third candidate information.
In some embodiments, above-mentioned apparatus further includes：Unit is established, is configured to according to the people in above-mentioned target video
First personage's identity associated by face image, establishes incidence relation information, wherein above-mentioned incidence relation information is used to indicate
Incidence relation between first personage's identity.
In some embodiments, above-mentioned apparatus further includes：Adding unit is configured to increase above-mentioned incidence relation information
Into the incidence relation information aggregate pre-established, wherein the incidence relation information in above-mentioned incidence relation information aggregate is used for
Indicate the incidence relation between at least two piece identities mark.
In some embodiments, above-mentioned apparatus further includes：5th determination unit is configured to from above-mentioned incidence relation information
In set, determines and identified at least one following the 4th piece identity with incidence relation：It is first personage's identity, above-mentioned
Second piece identity identifies and above-mentioned third personage identity；4th selection unit is configured to according to above-mentioned correspondence,
From above-mentioned candidate information set, chooses above-mentioned 4th piece identity and identify corresponding candidate information as the 4th candidate information；
4th push unit is configured to push above-mentioned 4th candidate information.
The third aspect, the embodiment of the present application provide a kind of electronic equipment, which includes：One or more processing
Device；Storage device, for storing one or more programs, when said one or multiple programs are by said one or multiple processors
When execution so that said one or multiple processors realize the method as described in any realization method in first aspect.
Fourth aspect, the embodiment of the present application provide a kind of computer-readable medium, are stored thereon with computer program,
In, the method as described in any realization method in first aspect is realized when which is executed by processor.
Method and apparatus provided by the embodiments of the present application for pushed information pass through the people in tracing detection target video
Face image；Later, based on the facial image in face information set and above-mentioned target video, the people in above-mentioned target video is determined
First personage's identity associated by face image, wherein above-mentioned face information set includes associated with piece identity's mark
Face information；Later, according to the correspondence of the candidate information pre-established and piece identity's mark, from candidate information set
In, candidate information corresponding with above-mentioned first personage identity is chosen as the first candidate information；Finally, above-mentioned first is pushed
Candidate information, hereby it is achieved that being imbued with targetedly information push.
Description of the drawings
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon：
Fig. 1 is that this application can be applied to exemplary system architecture figures therein；
Fig. 2 is the flow chart according to one embodiment of the method for pushed information of the application；
Fig. 3 is the schematic diagram according to an application scenarios of the method for pushed information of the application；
Fig. 4 is the flow chart according to another embodiment of the method for pushed information of the application；
Fig. 5 A are the flow charts according to the further embodiment of the method for pushed information of the application；
Fig. 5 B are the flow charts according to a kind of optional realization method of step 508 in the application Fig. 5 A；
Fig. 6 is the structural schematic diagram according to one embodiment of the device for pushed information of the application；
Fig. 7 is adapted for the structural representation of the computer system for the terminal device or server of realizing the embodiment of the present application
Figure.
Specific implementation mode
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, is illustrated only in attached drawing and invent relevant part with related.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 shows the implementation of the method for pushed information or the device for pushed information that can apply the application
The exemplary system architecture 100 of example.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 provide communication link medium.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be interacted by network 104 with server 105 with using terminal equipment 101,102,103, to receive or send out
Send message etc..Various telecommunication customer end applications can be installed, such as video playback class is answered on terminal device 101,102,103
With, web browser applications, the application of shopping class, searching class application, instant messaging tools, mailbox client, social platform software
Deng.
Terminal device 101,102,103 can be hardware, can also be software.When terminal device 101,102,103 is hard
Can be the various electronic equipments that there is display screen and support video playing, including but not limited to smart mobile phone, tablet when part
Computer, E-book reader, MP3 player (Moving Picture Experts Group Audio Layer III, dynamic
Image expert's compression standard audio level 3), MP4 (Moving Picture Experts Group Audio Layer IV, move
State image expert's compression standard audio level 4) player, pocket computer on knee and desktop computer etc..When terminal is set
Standby 101,102,103 when being software, may be mounted in above-mentioned cited electronic equipment.Its may be implemented into multiple softwares or
Software module (such as providing Distributed Services), can also be implemented as single software or software module.It does not do herein specific
It limits.
Server 105 can be to provide the server of various services, such as to the video on terminal device 101,102,103
Broadcast message class application provides the background server supported.Background server can analyze the data such as the video identifier that receives
Deng processing, and handling result (such as candidate information) is pushed to terminal device.
It should be noted that server can be hardware, can also be software.When server is hardware, may be implemented
At the distributed server cluster that multiple servers form, individual server can also be implemented as.It, can when server is software
To be implemented as multiple softwares or software module (such as providing Distributed Services), single software or software can also be implemented as
Module.It is not specifically limited herein.
It should be noted that the method for pushed information that the embodiment of the present application is provided generally is held by server 105
Row, correspondingly, the device for pushed information is generally positioned in server 105.Optionally, the embodiment of the present application is provided
Method for information push can also be executed by terminal device 101,102,103, and the device for pushed information is set to
In terminal device 101,102,103.Optionally, the method for information push that the embodiment of the present application is provided can also pass through
Server 105 and terminal device 101,102,103 execute jointly, for example, " facial image in tracing detection target video "
Step can be executed by terminal device 101,102,103, remaining step can be executed by server 105；Correspondingly, for pushing
Each unit in the device of information can correspondingly be placed in server 105 and terminal device 101,102,103.The application couple
This is not limited.
It should be understood that the number of the terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
With continued reference to Fig. 2, it illustrates the flows according to one embodiment of the method for pushed information of the application
200.This is used for the method for pushed information, includes the following steps：
Step 201, the facial image in tracing detection target video.
In the present embodiment, the executive agent (such as server shown in FIG. 1) for being used for the method for pushed information can be with
Track detects the facial image in target video.
In the present embodiment, above-mentioned target video can be that above-mentioned executive agent determines, as method shown in the application
Practice processes video.
Optionally, above-mentioned target video, can above-mentioned executive agent chosen from video collection.
Optionally, user can utilize terminal plays video.The video identifier of institute's video can be sent to above-mentioned by terminal
Executive agent.Above-mentioned executive agent can first receive above-mentioned video identifier.Then, above-mentioned executive agent can be by above-mentioned video
The indicated video of mark, is determined as target video.
In the present embodiment, above-mentioned executive agent can the profit face figure in tracing detection target video in various manners
Picture.
In some optional realization methods of the present embodiment, the facial image tracking mould pre-established can also be utilized
Type, the facial image in tracing detection target video.Facial image trace model is for characterizing video and facial image position-order
Arrange the correspondence of set.Facial image position sequence set may include one or more facial image position sequences.Face
Picture position sequence is used to indicate position of the facial image in each frame of video.It may include the face figure of multiple personages in video
Picture.One personage corresponds to a facial image position sequence.
In some optional realization methods of the present embodiment, it is the target following skill for tracking target to utilize with facial image
Art carries out face tracking detection.In general, above-mentioned executive agent can analyze each video frame of target video, inspection
Survey facial image.Tracking and detection can intersect to carry out.As an example, in the target facial image that present frame detects,
The facial image that same personage is indicated with target facial image can be tracked in the facial image that next frame detects.
It should be noted that step 201 can detect the facial image for belonging to same personage.But step 201 is not
It can identify and determine that whom this personage is.
Step 202, based on the facial image in face information set and target video, the face figure in target video is determined
As first associated personage's identity.
In the present embodiment, the executive agent (such as server shown in FIG. 1) for being used for the method for pushed information can be with base
Facial image in face information set and above-mentioned target video determines associated by the facial image in above-mentioned target video
First personage's identity.Herein, above-mentioned face information set includes face information associated with piece identity's mark.
In the present embodiment, face information can be the letter for distinguishing a facial image and other facial images
Breath.Optionally, above-mentioned face information can be facial image, can also be facial image feature.
In the present embodiment, above-mentioned piece identity's mark can indicate identity of personage.Piece identity's mark has unique
Property, a personage and other personages can be distinguished.As an example, above-mentioned identity of personage represent this people be Zhang San or
Li Si.Identity of personage mark can be the name of personage, can also be identity coding.
Optionally, face information can be facial image, and above-mentioned executive agent can pass through recognition of face trained in advance
Model determines and the facial image in the matched face information set of facial image in target video.Then by face information
Piece identity's mark associated by facial image in set, is determined as the associated by the facial image in above-mentioned target video
One task identity.
Optionally, face information can be facial image feature.Above-mentioned executive agent can extract in above-mentioned target video
Facial image feature, as target facial image feature.Then, above-mentioned executive agent can by calculate similarity, i.e., on
The similarity for stating target facial image feature and the facial image feature in above-mentioned face information set, determines above-mentioned face information
Face information in set, with above-mentioned facial image characteristic matching.Then by the personage associated by identified face information
Identity is determined as first personage's identity associated by the facial image in above-mentioned target video.
In some optional realization methods of the present embodiment, determine that the face images in the target video are closed
First personage's identity of connection, can also determine first personage's body associated by the part facial image in the target video
Part mark.
In some optional realization methods of the present embodiment, if the facial image instruction in above-mentioned target video is same
Individual can determine first personage's identity information associated by face images in above-mentioned target video.On if
The facial image stated in target video indicates multiple people, can be by the part facial image in above-mentioned target video, and determination is closed
First personage's identity information of connection.
Step 203, according to the correspondence of the candidate information pre-established and piece identity's mark, from candidate information set
In, candidate information corresponding with first personage's identity is chosen as the first candidate information.
In the present embodiment, the executive agent (such as server shown in FIG. 1) for being used for the method for pushed information can root
According to the correspondence of the candidate information pre-established and piece identity's mark, from candidate information set, choose and above-mentioned first
Piece identity identifies corresponding candidate information as the first candidate information.
In the present embodiment, it in candidate information set may include one or more candidate informations.Candidate information can be
Information for displaying.
As an example, above-mentioned candidate information can be the forms such as word, image, video.
As an example, above-mentioned candidate information can be film, TV play, advertisement etc..
In the present embodiment, the correspondence of piece identity's mark and candidate information can be pre-established.As an example, can
To establish the correspondence between performer A and TV play A；The correspondence between performer A and TV play B can be established；It can be with
Establish the correspondence between performer A and advertisement C.
It is appreciated that first personage's identity that step 202 is determined can be utilized, with the people corresponding to candidate information
Object identity is compared, and determines the piece identity mark consistent with first personage's identity.Then, by determining people
The corresponding candidate information of object identity, as candidate information corresponding with first personage's identity.Finally, will with it is the first
The corresponding candidate information of object identity is as the first candidate information.
Step 204, the first candidate information is pushed.
In the present embodiment, the executive agent (such as server shown in FIG. 1) for being used for the method for pushed information can be to
Other electronic equipments push above-mentioned first candidate information.
It is a signal according to the application scenarios of the method for pushed information of the present embodiment with continued reference to Fig. 3, Fig. 3
Figure.In the application scenarios of Fig. 3：
First, user can utilize terminal, video be watched in video playback window 301, for example, TV play A can be watched
The first collection, video pictures (an ancient costume personage) are shown in video playback window 301.Later, terminal can be to service
Device sends video identifier, as an example, video identifier can be " collection of TV play A first ".
Later, server can regard the first collection of video TV play A as target video.Server can be with tracing detection mesh
Mark the facial image in video.As an example, can detect a series of facial images in target video, a series of this face
Image indicates the same personage.
Later, server can determine above-mentioned mesh based on the facial image in face information set and above-mentioned target video
First personage's identity associated by the facial image in video is marked, for example, can " drill with first personage's identity
Member A ".
Later, server can be according to the correspondence of the candidate information pre-established and piece identity's mark, from candidate
In information aggregate, candidate information corresponding with above-mentioned first personage identity is chosen as the first candidate information.For example, can be with
Film A corresponding with " performer A " is chosen as the first candidate information.
After again, server can push above-mentioned first candidate information.For example, server can push film A to terminal.
Finally, terminal can show the content in relation to the first candidate information, as an example, the push content display box of Fig. 3
In 302, it can show and the relevant content of the first candidate information：" performer A " " film A " and user is reminded to click opening film A
Word " put this open link ".
The method that above-described embodiment of the application provides, passes through the facial image in tracing detection target video；Later, base
Facial image in face information set and above-mentioned target video determines associated by the facial image in above-mentioned target video
First personage's identity, wherein above-mentioned face information set includes face information associated with piece identity's mark；It
Afterwards, according to the correspondence of the candidate information that pre-establishes and piece identity's mark, from candidate information set, choose with it is above-mentioned
The corresponding candidate information of first personage's identity is as the first candidate information；Finally, above-mentioned first candidate information is pushed, is realized
It is imbued with targetedly information push.
With further reference to Fig. 4, it illustrates the flows 400 of another embodiment of the method for pushed information.The use
In the flow 400 of the method for pushed information, include the following steps：
Step 401, the facial image in tracing detection target video.
In the present embodiment, the executive agent (such as server shown in FIG. 1) for being used for the method for pushed information can be with
Track detects the facial image in target video.
Step 402, in response to detecting that the facial image in target video indicates at least two personages, to indicate same people
The facial image of object distributes character recognition and label.
In the present embodiment, being used for the executive agent (such as server shown in FIG. 1) of the method for pushed information can ring
Ying Yu detects that the facial image in above-mentioned target video indicates at least two personages, to indicate the facial image point of same personage
With character recognition and label.
As an example, if detecting two serial facial images in step 401, the facial image instruction of each series
One personage.As an example, step 401 detects A series facial image and B series facial images.I.e. A series facial image refers to
Show that same personage, B series facial images indicate same personage.The personage that A series facial image is indicated with B series facial images is not
Together.It can be that A series facial images distribute character recognition and label " personage A ", can be that B series facial images distribute character recognition and label " people
Object B ".It should be noted that herein, not can determine that the identity of personage A or personage B.
Step 403, according to the corresponding facial image number of each character recognition and label, predetermined number character recognition and label is determined.
In the present embodiment, the executive agent (such as server shown in FIG. 1) for being used for the method for pushed information can root
According to the corresponding facial image number of each character recognition and label, determine that predetermined number target person identifies.
In the present embodiment, the corresponding facial image number of each character recognition and label is：It is in above-mentioned target video, be assigned to
The number of the facial image of the character recognition and label.
As an example, the corresponding facial image number of character recognition and label " personage A " is 50, character recognition and label " personage B " is corresponding
The number of facial image is 20.
Optionally, can be that selection predetermined number is larger according to the corresponding facial image number of each character recognition and label
Facial image number can also be and choose the smaller facial image number of predetermined number.
As an example, predetermined number is one.It can so determine a character recognition and label.
As an example, the corresponding facial image number 50 of character recognition and label " personage A ", also character recognition and label " personage B " are corresponding
Facial image number 20 between, choose larger facial image number 50.By 50 corresponding character recognition and labels " personage A ", really
It is set to target person mark.It should be noted that according to larger facial image number is chosen, target person mark is determined in turn
Candidate information is pushed, the candidate information pushed can more reflect：With the relevant candidate information of high priest in target video.
As an example, the corresponding facial image number 50 of character recognition and label " personage A ", also character recognition and label " personage B " are corresponding
Facial image number 20 between, choose smaller facial image number 20.By 20 corresponding character recognition and labels " personage B ", really
It is set to target person mark.
Optionally, determining target person mark can be one, can also be multiple.It should be noted that according to choosing
Smaller facial image number is taken, determines that target person identifies and then push candidate information, the candidate information pushed more can be anti-
It reflects：With the easy ignored relevant candidate information of personage in target video.
Step 404, each target person is identified, according to face information set and is assigned to target person mark
Facial image determines first personage's identity associated by the facial image for being assigned to target person mark.
In the present embodiment, the executive agent (such as server shown in FIG. 1) for being used for the method for pushed information can be right
It identifies in each target person, according to above-mentioned face information set and the facial image for being assigned to target person mark, determines
It is assigned to first personage's identity associated by the facial image of target person mark.
As an example, the target person determined is identified as " personage A ", according to face information set and " people can be assigned to
The facial image of object A " determines and is assigned to first personage's identity associated by the facial image of " personage A ", for example, can be with
It is " performer A ".
Step 405, according to the correspondence of the candidate information pre-established and piece identity's mark, from candidate information set
In, candidate information corresponding with first personage's identity is chosen as the first candidate information.
In the present embodiment, the executive agent (such as server shown in FIG. 1) for being used for the method for pushed information can root
According to the correspondence of the candidate information pre-established and piece identity's mark, from candidate information set, choose and above-mentioned first
Piece identity identifies corresponding candidate information as the first candidate information.
Step 406, the first candidate information is pushed.
In the present embodiment, being used for the executive agent (such as server shown in FIG. 1) of the method for pushed information can push away
It serves and states the first candidate information.
The concrete operations of step 401, step 405 and step 406 in the present embodiment and step in embodiment shown in Fig. 2
201, the operation of step 203 and step 204 is essentially identical, and details are not described herein.
Figure 4, it is seen that compared with the corresponding embodiments of Fig. 2, the method for pushed information in the present embodiment
Flow 400 highlight：The step of facial image of multiple personages involved in target video is handled.This reality as a result,
Facial image can be screened by applying the scheme of example description, determine that predetermined number target person identifies, then determine the first
Object identity improves pushing speed to reduce treating capacity.
With further reference to Fig. 5 A, it illustrates the flows 500 of another embodiment of the method for pushed information.The use
In the flow 500 of the method for pushed information, include the following steps：
Step 501, the facial image in tracing detection target video.
In the present embodiment, the executive agent (such as server shown in FIG. 1) for being used for the method for pushed information can be with
Track detects the facial image in target video.
Step 502, based on the facial image in face information set and target video, the face figure in target video is determined
As first associated personage's identity.
In the present embodiment, the executive agent (such as server shown in FIG. 1) for being used for the method for pushed information can be with base
Facial image in face information set and above-mentioned target video determines associated by the facial image in above-mentioned target video
First personage's identity.Herein, above-mentioned face information set includes face information associated with piece identity's mark.
Step 503, according to the correspondence of the candidate information pre-established and piece identity's mark, from candidate information set
In, candidate information corresponding with first personage's identity is chosen as the first candidate information.
In the present embodiment, the executive agent (such as server shown in FIG. 1) for being used for the method for pushed information can root
According to the correspondence of the candidate information pre-established and piece identity's mark, from candidate information set, choose and above-mentioned first
Piece identity identifies corresponding candidate information as the first candidate information.
In the present embodiment, the concrete operations of step 501, step 502 and step 503 are walked with embodiment shown in Fig. 2
Rapid 201, the operation of step 202 and step 203 is essentially identical, and details are not described herein.
Step 504, it is directed to the pause play operation of target video in response to detecting, is shown when determining target video pause
Target video frame.
In the present embodiment, being used for the executive agent (such as server shown in FIG. 1) of the method for pushed information can ring
Ying Yu detects the pause play operation for above-mentioned target video, determines the target video shown when above-mentioned target video pause
Frame.
It should be noted that the pause play operation that user makes, it is likely to which user is to suspending target video frame extremely
It is interested.Therefore, target video frame is analyzed, pushed information is carried out, the hobby demand of user can be directed to, is pushed subject to more
True candidate information.
Step 505, it is based on face information set, determines second personage's body associated by the facial image in target video frame
Part mark.
In the present embodiment, the executive agent (such as server shown in FIG. 1) for being used for the method for pushed information can be with base
In above-mentioned face information set, the second piece identity mark associated by the facial image in above-mentioned target video frame is determined.
In the present embodiment, facial image identification can be carried out to target video frame, determines the target in target video frame
The target facial image series which facial image series facial image is in, and this facial image series is determined.
Optionally, if first personage's identity is determined for target facial image series before, and then can be by this
First personage's identity, is determined as target facial image corresponding piece identity mark, and using this personage's identity as
Second piece identity identifies.
It optionally, can be with if unpromising target person face image series determines first personage's identity before
Feature extraction is carried out to one or more of target facial image series facial image, then is obtained with by above-mentioned face information set
To facial image feature matched, determine and the matched face information of target facial image series.It will be obtained by matching
Piece identity's information associated by face information is determined as the second piece identity mark.
Step 506, according to correspondence, from candidate information set, time corresponding with the second piece identity mark is chosen
Select information as the second candidate information.
In the present embodiment, the executive agent (such as server shown in FIG. 1) for being used for the method for pushed information can root
According to above-mentioned correspondence, from above-mentioned candidate information set, candidate information corresponding with above-mentioned second piece identity mark is chosen
As the second candidate information.
Step 507, optical character identification is carried out to target video frame, determines the text information in target video frame.
In the present embodiment, the executive agent (such as server shown in FIG. 1) for being used for the method for pushed information can be right
Above-mentioned target video frame carries out optical character identification, determines the text information in above-mentioned target video frame.
In the present embodiment, optical character identification (Optical Character Recognition, OCR), can will scheme
Text conversion as in is at text formatting.Target video frame can be piece image, can be carried out at OCR to target video frame
Reason, determines the text information in target video frame.
In some optional realization methods of the present embodiment, step 507 may include：In response to detecting above-mentioned target
Video frame includes at least one of following：Barrage and subtitle can determine at least one of following from above-mentioned target video frame：Barrage
Text information and caption character information.
It should be noted that barrage text information can embody the mood and cognition of the user of viewing video.Caption character
Information can embody the main contents of video.
Step 508, according to text information, from candidate information set, candidate information is chosen as third candidate information.
In the present embodiment, the executive agent (such as server shown in FIG. 1) for being used for the method for pushed information can root
According to above-mentioned text information, from above-mentioned candidate information set, candidate information is chosen as third candidate information.
It, can will be in above-mentioned text information and candidate information set in some optional realization methods of the present embodiment
Candidate information is matched one by one.For example, information of the above-mentioned candidate information if it is textual form, can select including upper
The candidate information for stating whole text informations, as third candidate information；It can also select including the portion in above-mentioned text information
The candidate information for dividing content, as third candidate information.
In some optional realization methods of the present embodiment, Fig. 5 B are please referred to, it illustrates a kind of realizations of step 508
Mode flow 508, flow 508 may include：
Step 5081, the keyword in barrage text information and/or caption character information is extracted.
In the present embodiment, being used for the executive agent (such as server shown in FIG. 1) of the method for pushed information can carry
Take the keyword in above-mentioned barrage text information and/or above-mentioned caption character information.
For example, barrage text information can be " performer B is good beautiful ", can be " performer B " from the keyword extracted in this.
Step 5082, according to the correspondence of the keyword and candidate information that pre-establish, from candidate information set, choosing
Take candidate information corresponding with the keyword extracted as third candidate information.
In the present embodiment, the executive agent (such as server shown in FIG. 1) for being used for the method for pushed information can root
According to the correspondence of the keyword and candidate information that pre-establish, from above-mentioned candidate information set, selection and the pass extracted
The corresponding candidate information of keyword is as third candidate information.
For example, film B corresponding with keyword " performer B " can be chosen as third candidate from candidate information set
Information.
It should be noted that keyword, and then the candidate information chosen are gone out by caption character information extraction, it can be close to mesh
The content of video is marked, candidate information push is carried out.Keyword, and then the candidate information chosen are extracted by barrage text information,
The mood and cognition that can be close to the users carry out candidate information push.
Step 509, at least one of below push：First candidate information, the second candidate information and third candidate information.
In the present embodiment, being used for the executive agent (such as server shown in FIG. 1) of the method for pushed information can push away
It send at least one of following：First candidate information, the second candidate information and third candidate information.
From figure 5 it can be seen that compared with the corresponding embodiments of Fig. 2, the method for pushed information in the present embodiment
Flow 500 highlight the step of target video frame extremely is suspended to target video, extracts facial image and text information.By
This, the scheme of the present embodiment description introduces more with the relevant information of target video, carries out that the complete of information push can be improved
Face property and accuracy.
In some optional realization methods of the present embodiment, method shown in the present embodiment can also include：According to above-mentioned
First personage's identity associated by facial image in target video, establishes incidence relation information.Herein, above-mentioned association
Relation information is used to indicate the incidence relation between first personage's identity.
As an example, first personage's identity is two " performer A " and " performer B ".Incidence relation information can be established
A, the incidence relation being used to indicate between " performer A " and " performer B ".
In some optional realization methods of the present embodiment, method shown in the present embodiment can also include：By above-mentioned pass
Connection relation information increases in the incidence relation information aggregate pre-established, wherein the pass in above-mentioned incidence relation information aggregate
Connection relation information is used to indicate the incidence relation between at least two piece identities mark.
As an example, incidence relation information A can be added in the incidence relation information aggregate pre-established.
In some optional realization methods of the present embodiment, method shown in the present embodiment can also include：From above-mentioned pass
Join in relation information set, determines and identified at least one following the 4th piece identity with incidence relation：First personage's body
Part mark, above-mentioned second piece identity mark and above-mentioned third personage identity；According to above-mentioned correspondence, from above-mentioned candidate
In information aggregate, chooses above-mentioned 4th piece identity and identify corresponding candidate information as the 4th candidate information；Push above-mentioned
Four candidate informations.
As an example, being directed to first personage's identity " performer A ", can be determined from above-mentioned incidence relation information aggregate
With " performer A " there is the 4th piece identity of incidence relation to identify " performer C ".It is then possible to choose time corresponding with " performer C "
Information film C is selected, as the 4th candidate information.Finally, above-mentioned 4th candidate information is pushed.
It should be noted that the determination identified by the 4th piece identity, may be implemented using between personage and personage
Incidence relation, then determine candidate information.It is thus possible to determine and push more comprehensively candidate information.
With further reference to Fig. 6, as the realization to method shown in above-mentioned each figure, this application provides one kind for pushing letter
One embodiment of the device of breath, the device embodiment is corresponding with embodiment of the method shown in Fig. 2, which can specifically answer
For in various electronic equipments.
As shown in fig. 6, the device 600 for pushed information of the present embodiment includes：Detection unit 601, first determines single
First 602, first selection unit 603 and the first push unit 604；Wherein, detection unit is configured to tracing detection target video
In facial image；First determination unit is configured to based on the facial image in face information set and above-mentioned target video,
Determine first personage's identity associated by the facial image in above-mentioned target video, wherein above-mentioned face information set packet
Include face information associated with piece identity's mark；First selection unit is configured to according to the candidate information pre-established
With the correspondence of piece identity's mark time corresponding with above-mentioned first personage identity is chosen from candidate information set
Select information as the first candidate information；First push unit is configured to push above-mentioned first candidate information.
In some optional realization methods of the present embodiment, the first determination unit is also configured to：In response to detecting
Facial image in above-mentioned target video indicates at least two personages, to indicate that the facial image of same personage distributes personage's mark
Know；According to the corresponding facial image number of each character recognition and label, determine that predetermined number target person identifies, wherein everyone
Object identifies corresponding facial image number：The number of facial image in above-mentioned target video, to be assigned to the character recognition and label；
Each target person is identified, according to above-mentioned face information set and the facial image for being assigned to target person mark, really
Surely it is assigned to first personage's identity associated by the facial image of target person mark.
In some optional realization methods of the present embodiment, above-mentioned apparatus further includes：Second determination unit (not shown),
It is configured to be directed to the pause play operation of above-mentioned target video in response to detecting, be shown when determining above-mentioned target video pause
Target video frame；Third determination unit (not shown) is configured to be based on above-mentioned face information set, determines that above-mentioned target regards
The second piece identity mark associated by facial image in frequency frame.
In some optional realization methods of the present embodiment, above-mentioned apparatus further includes：Second selection unit (not shown),
It is configured to according to above-mentioned correspondence, from above-mentioned candidate information set, chooses corresponding with above-mentioned second piece identity mark
Candidate information as the second candidate information；Second push unit (not shown) is configured to push above-mentioned second candidate information.
In some optional realization methods of the present embodiment, above-mentioned apparatus further includes：4th determination unit (not shown),
It is configured to carry out optical character identification to above-mentioned target video frame, determines the text information in above-mentioned target video frame；Third
Selection unit (not shown) is configured to according to above-mentioned text information, from above-mentioned candidate information set, is chosen candidate information and is made
For third candidate information；Third push unit (not shown) is configured to push above-mentioned third candidate information.
In some optional realization methods of the present embodiment, the 4th determination unit (not shown) is also configured to：Response
In detecting that above-mentioned target video frame includes at least one of following：Barrage and subtitle determine following from above-mentioned target video frame
At least one of：Barrage text information and caption character information.
In some optional realization methods of the present embodiment, third selection unit (not shown) is also configured to：Extraction
Keyword in above-mentioned barrage text information and/or above-mentioned caption character information；Believed with candidate according to the keyword pre-established
The correspondence of breath chooses candidate information corresponding with the keyword extracted as third from above-mentioned candidate information set
Candidate information.
In some optional realization methods of the present embodiment, above-mentioned apparatus further includes：Unit (not shown) is established, is configured
For first personage's identity associated by the facial image in above-mentioned target video, incidence relation information is established,
In, above-mentioned incidence relation information is used to indicate the incidence relation between first personage's identity.
In some optional realization methods of the present embodiment, above-mentioned apparatus further includes：Adding unit (not shown), configuration
For above-mentioned incidence relation information to be increased in the incidence relation information aggregate pre-established, wherein above-mentioned incidence relation letter
Incidence relation information in breath set is used to indicate the incidence relation between at least two piece identities mark.
In some optional realization methods of the present embodiment, above-mentioned apparatus further includes：5th determination unit (not shown),
It is configured to from above-mentioned incidence relation information aggregate, determines and at least one following the 4th piece identity with incidence relation
Mark：First personage's identity, above-mentioned second piece identity mark and above-mentioned third personage identity；4th selection unit
(not shown) is configured to according to above-mentioned correspondence, from above-mentioned candidate information set, chooses above-mentioned 4th piece identity mark
Corresponding candidate information is known as the 4th candidate information；4th push unit (not shown) is configured to push above-mentioned 4th time
Select information.
In the present embodiment, detection unit 601, the first determination unit 602, first of the device 600 of pushed information are used for
The specific processing of selection unit 603 and the first push unit 604 and its caused technique effect can correspond to reality with reference to figure 2 respectively
The related description of step 201 in example, step 202, step 203 and step 204 is applied, details are not described herein.
It should be noted that in the device provided by the embodiments of the present application for pushed information the realization details of each unit and
Technique effect can refer to the explanation of other embodiments in the application, and details are not described herein.
Below with reference to Fig. 7, it illustrates the calculating suitable for server or terminal device for realizing the embodiment of the present application
The structural schematic diagram of machine system 700.Server or terminal device shown in Fig. 7 are only an example, should not be to the application reality
The function and use scope for applying example bring any restrictions.
As shown in fig. 7, computer system 700 includes central processing unit (CPU, Central Processing Unit)
701, it can be according to the program being stored in read-only memory (ROM, Read Only Memory) 702 or from storage section
708 programs being loaded into random access storage device (RAM, Random Access Memory) 703 and execute various appropriate
Action and processing.In RAM 703, also it is stored with system 700 and operates required various programs and data.CPU 701、ROM
702 and RAM 703 is connected with each other by bus 704.Input/output (I/O, Input/Output) interface 705 is also connected to
Bus 704.
It is connected to I/O interfaces 705 with lower component：Importation 706 including keyboard, mouse etc.；It is penetrated including such as cathode
Spool (CRT, Cathode Ray Tube), liquid crystal display (LCD, Liquid Crystal Display) etc. and loud speaker
Deng output par, c 707；Storage section 708 including hard disk etc.；And including such as LAN (LAN, Local Area
Network) the communications portion 709 of the network interface card of card, modem etc..Communications portion 709 is via such as internet
Network executes communication process.Driver 710 is also according to needing to be connected to I/O interfaces 705.Detachable media 711, such as disk,
CD, magneto-optic disk, semiconductor memory etc. are mounted on driver 710 as needed, in order to from the calculating read thereon
Machine program is mounted into storage section 708 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed by communications portion 709 from network, and/or from detachable media
711 are mounted.When the computer program is executed by central processing unit (CPU) 701, limited in execution the present processes
Above-mentioned function.It should be noted that the above-mentioned computer-readable medium of the application can be computer-readable signal media or
Computer readable storage medium either the two arbitrarily combines.Computer readable storage medium for example can be --- but
Be not limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or arbitrary above combination.
The more specific example of computer readable storage medium can include but is not limited to：Electrical connection with one or more conducting wires,
Portable computer diskette, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only deposit
Reservoir (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory
Part or above-mentioned any appropriate combination.In this application, computer readable storage medium can any be included or store
The tangible medium of program, the program can be commanded the either device use or in connection of execution system, device.And
In the application, computer-readable signal media may include the data letter propagated in a base band or as a carrier wave part
Number, wherein carrying computer-readable program code.Diversified forms may be used in the data-signal of this propagation, including but not
It is limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer
Any computer-readable medium other than readable storage medium storing program for executing, the computer-readable medium can send, propagate or transmit use
In by instruction execution system, device either device use or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to：Wirelessly, electric wire, optical cable, RF etc., Huo Zheshang
Any appropriate combination stated.
The calculating of the operation for executing the application can be write with one or more programming languages or combinations thereof
Machine program code, above procedure design language include object oriented program language-such as Java, Smalltalk, C+
+, further include conventional procedural programming language-such as " C " language or similar programming language.Program code can
Fully to execute on the user computer, partly execute, executed as an independent software package on the user computer,
Part executes or executes on a remote computer or server completely on the remote computer on the user computer for part.
In situations involving remote computers, remote computer can pass through the network of any kind --- including LAN (LAN)
Or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as utilize Internet service
Provider is connected by internet).
Flow chart in attached drawing and block diagram, it is illustrated that according to the system of the various embodiments of the application, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part for a part for one module, program segment, or code of table, the module, program segment, or code includes one or more uses
The executable instruction of the logic function as defined in realization.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, this is depended on the functions involved.Also it to note
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit can also be arranged in the processor, for example, can be described as：A kind of processor packet
Include detection unit, the first determination unit, the first selection unit and the first push unit.Wherein, the title of these units is at certain
In the case of do not constitute restriction to the unit itself, for example, detection unit is also described as " tracing detection target video
In facial image unit ".
As on the other hand, present invention also provides a kind of computer-readable medium, which can be
Included in device described in above-described embodiment；Can also be individualism, and without be incorporated the device in.Above-mentioned calculating
Machine readable medium carries one or more program, when said one or multiple programs are executed by the device so that should
Device：Facial image in tracing detection target video；Based on the facial image in face information set and above-mentioned target video,
Determine first personage's identity associated by the facial image in above-mentioned target video, wherein above-mentioned face information set packet
Include face information associated with piece identity's mark；The corresponding pass identified with piece identity according to the candidate information pre-established
System chooses candidate information corresponding with above-mentioned first personage identity as the first candidate information from candidate information set；
Push above-mentioned first candidate information.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.People in the art
Member should be appreciated that invention scope involved in the application, however it is not limited to technology made of the specific combination of above-mentioned technical characteristic
Scheme, while should also cover in the case where not departing from foregoing invention design, it is carried out by above-mentioned technical characteristic or its equivalent feature
Other technical solutions of arbitrary combination and formation.Such as features described above has similar work(with (but not limited to) disclosed herein
Can technical characteristic replaced mutually and the technical solution that is formed.
Claims (19)
1. a kind of method for pushed information, including：
Facial image in tracing detection target video；
Based on the facial image in face information set and the target video, the facial image institute in the target video is determined
Associated first personage identity, wherein the face information set includes face letter associated with piece identity's mark
Breath；
According to the correspondence of the candidate information pre-established and piece identity's mark, from candidate information set, selection and institute
The corresponding candidate information of first personage's identity is stated as the first candidate information；
Push first candidate information.
2. according to the method described in claim 1, wherein, the face based in face information set and the target video
Image determines first personage's identity associated by the facial image in the target video, including：
In response to detecting that the facial image in the target video indicates at least two personages, to indicate the face of same personage
Image distributes character recognition and label；
According to the corresponding facial image number of each character recognition and label, determine that predetermined number target person identifies, wherein everyone
Object identifies corresponding facial image number：The number of facial image in the target video, to be assigned to the character recognition and label；
Each target person is identified, according to the face information set and the face figure for being assigned to target person mark
Picture determines first personage's identity associated by the facial image for being assigned to target person mark.
3. according to the method described in claim 1, wherein, the method further includes：
It is directed to the pause play operation of the target video in response to detecting, determines the mesh shown when the target video pause
Mark video frame；
Based on the face information set, the second piece identity mark associated by the facial image in the target video frame is determined
Know.
4. according to the method described in claim 3, wherein, the method further includes：
According to the correspondence, from the candidate information set, time corresponding with the second piece identity mark is chosen
Select information as the second candidate information；
Push second candidate information.
5. according to the method described in claim 3, wherein, the method further includes：
Optical character identification is carried out to the target video frame, determines the text information in the target video frame；
According to the text information, from the candidate information set, candidate information is chosen as third candidate information；
Push the third candidate information.
6. according to the method described in claim 5, described carry out optical character identification to the target video frame, the mesh is determined
The text information in video frame is marked, including：
In response to detecting that above-mentioned target video frame includes at least one of following：Barrage and subtitle, from the target video frame
It determines at least one of following：Barrage text information and caption character information.
7. it is described according to the text information according to the method described in claim 6, wherein, from the candidate information set,
Third candidate information is chosen, including：
Extract the keyword in the barrage text information and/or the caption character information；
According to the correspondence of the keyword and candidate information that pre-establish, from the candidate information set, chooses and carried
The corresponding candidate information of keyword taken is as third candidate information.
8. according to the method described in claim 2, wherein, the method further includes：
First personage's identity associated by the facial image in the target video, establishes incidence relation information,
In, the incidence relation information is used to indicate the incidence relation between first personage's identity.
9. according to the method described in claim 8, wherein, the method further includes：
The incidence relation information is increased in the incidence relation information aggregate pre-established, wherein the incidence relation letter
Incidence relation information in breath set is used to indicate the incidence relation between at least two piece identities mark.
10. according to the method described in claim 9, wherein, the method further includes：
From the incidence relation information aggregate, determines and marked at least one following the 4th piece identity with incidence relation
Know：First personage's identity, second piece identity mark and the third personage identity；
According to the correspondence, from the candidate information set, chooses the 4th piece identity and identify corresponding candidate
Information is as the 4th candidate information；
Push the 4th candidate information.
11. a kind of device for pushed information, including：
Detection unit, the facial image being configured in tracing detection target video；
First determination unit, is configured to based on the facial image in face information set and the target video, determine described in
First personage's identity associated by facial image in target video, wherein the face information set includes and personage
The associated face information of identity；
First selection unit is configured to the correspondence according to the candidate information pre-established and piece identity's mark, from time
It selects in information aggregate, chooses candidate information corresponding with the first personage identity as the first candidate information；
First push unit is configured to push first candidate information.
12. according to the devices described in claim 11, wherein the first determination unit is also configured to：
In response to detecting that the facial image in the target video indicates at least two personages, to indicate the face of same personage
Image distributes character recognition and label；
According to the corresponding facial image number of each character recognition and label, determine that predetermined number target person identifies, wherein everyone
Object identifies corresponding facial image number：The number of facial image in the target video, to be assigned to the character recognition and label；
Each target person is identified, according to the face information set and the face figure for being assigned to target person mark
Picture determines first personage's identity associated by the facial image for being assigned to target person mark.
13. according to the devices described in claim 11, wherein described device further includes：
Second determination unit is configured to be directed to the pause play operation of the target video in response to detecting, described in determination
The target video frame that target video is shown when suspending；
Third determination unit is configured to be based on the face information set, determines the facial image in the target video frame
Associated the second piece identity mark.
14. device according to claim 13, wherein described device further includes：
Second selection unit is configured to according to the correspondence, from the candidate information set, is chosen and described second
Piece identity identifies corresponding candidate information as the second candidate information；
Second push unit is configured to push second candidate information.
15. device according to claim 13, wherein described device further includes：
4th determination unit is configured to carry out optical character identification to the target video frame, determines the target video frame
In text information；
Third selection unit is configured to according to the text information, from the candidate information set, is chosen candidate information and is made
For third candidate information；
Third push unit is configured to push the third candidate information.
16. device according to claim 15, wherein the 4th determination unit is also configured to：
In response to detecting that above-mentioned target video frame includes at least one of following：Barrage and subtitle, from the target video frame
It determines at least one of following：Barrage text information and caption character information.
17. device according to claim 16, wherein third selection unit is also configured to：
Extract the keyword in the barrage text information and/or the caption character information；
According to the correspondence of the keyword and candidate information that pre-establish, from the candidate information set, chooses and carried
The corresponding candidate information of keyword taken is as third candidate information.
18. a kind of electronic equipment, including：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors so that one or more of processors are real
The now method as described in any in claim 1-10.
19. a kind of computer-readable medium, is stored thereon with computer program, wherein real when described program is executed by processor
The now method as described in any in claim 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810295444.0A CN108509611B (en) | 2018-03-30 | 2018-03-30 | Method and device for pushing information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810295444.0A CN108509611B (en) | 2018-03-30 | 2018-03-30 | Method and device for pushing information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108509611A true CN108509611A (en) | 2018-09-07 |
| CN108509611B CN108509611B (en) | 2021-11-12 |
Family
ID=63380232
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810295444.0A Active CN108509611B (en) | 2018-03-30 | 2018-03-30 | Method and device for pushing information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108509611B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN109815818A (en) * | 2018-12-25 | 2019-05-28 | 深圳市天彦通信股份有限公司 | Target person method for tracing, system and relevant apparatus |
| CN109886258A (en) * | 2019-02-19 | 2019-06-14 | 新华网(北京)科技有限公司 | The method, apparatus and electronic equipment of the related information of multimedia messages are provided |
| CN110909651A (en) * | 2019-11-15 | 2020-03-24 | 腾讯科技（深圳）有限公司 | Video subject person identification method, device, equipment and readable storage medium |
| CN111259682A (en) * | 2018-11-30 | 2020-06-09 | 百度在线网络技术（北京）有限公司 | Method and device for monitoring the safety of a construction site |
| CN112148833A (en) * | 2019-06-27 | 2020-12-29 | 百度在线网络技术（北京）有限公司 | Information pushing method, server, terminal and electronic equipment |
| WO2021114552A1 (en) * | 2019-12-11 | 2021-06-17 | 北京市商汤科技开发有限公司 | Information processing method and apparatus, electronic device and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103744858A (en) * | 2013-12-11 | 2014-04-23 | 深圳先进技术研究院 | Method and system for pushing information |
| CN103870559A (en) * | 2014-03-06 | 2014-06-18 | 海信集团有限公司 | Method and equipment for obtaining information based on played video |
| CN104239338A (en) * | 2013-06-19 | 2014-12-24 | 阿里巴巴集团控股有限公司 | Information recommendation method and information recommendation device |
| CN104254019A (en) * | 2013-06-28 | 2014-12-31 | 广州华多网络科技有限公司 | Information push result detecting method and information push result detecting system |
| CN104618803A (en) * | 2014-02-26 | 2015-05-13 | 腾讯科技（深圳）有限公司 | Information push method, information push device, terminal and server |
| CN105578222A (en) * | 2016-02-01 | 2016-05-11 | 百度在线网络技术（北京）有限公司 | Information push method and device |
| US20160267543A1 (en) * | 2015-03-12 | 2016-09-15 | WeLink, Inc. | Targeting and channeling digital advertisements to social media users through location-based social monitoring |
| US20170098122A1 (en) * | 2010-06-07 | 2017-04-06 | Affectiva, Inc. | Analysis of image content with associated manipulation of expression presentation |
| CN106845738A (en) * | 2015-12-03 | 2017-06-13 | 小米科技有限责任公司 | Crowd's number method for pushing and device |
| CN107291810A (en) * | 2017-05-18 | 2017-10-24 | 深圳云天励飞技术有限公司 | Data processing method, device and storage medium |
| 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 |
-
2018
- 2018-03-30 CN CN201810295444.0A patent/CN108509611B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170098122A1 (en) * | 2010-06-07 | 2017-04-06 | Affectiva, Inc. | Analysis of image content with associated manipulation of expression presentation |
| CN104239338A (en) * | 2013-06-19 | 2014-12-24 | 阿里巴巴集团控股有限公司 | Information recommendation method and information recommendation device |
| CN104254019A (en) * | 2013-06-28 | 2014-12-31 | 广州华多网络科技有限公司 | Information push result detecting method and information push result detecting system |
| CN103744858A (en) * | 2013-12-11 | 2014-04-23 | 深圳先进技术研究院 | Method and system for pushing information |
| CN104618803A (en) * | 2014-02-26 | 2015-05-13 | 腾讯科技（深圳）有限公司 | Information push method, information push device, terminal and server |
| CN103870559A (en) * | 2014-03-06 | 2014-06-18 | 海信集团有限公司 | Method and equipment for obtaining information based on played video |
| US20160267543A1 (en) * | 2015-03-12 | 2016-09-15 | WeLink, Inc. | Targeting and channeling digital advertisements to social media users through location-based social monitoring |
| CN106845738A (en) * | 2015-12-03 | 2017-06-13 | 小米科技有限责任公司 | Crowd's number method for pushing and device |
| CN105578222A (en) * | 2016-02-01 | 2016-05-11 | 百度在线网络技术（北京）有限公司 | Information push method and device |
| CN107291810A (en) * | 2017-05-18 | 2017-10-24 | 深圳云天励飞技术有限公司 | Data processing method, device and storage medium |
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| 陈洪涛等: "一种新的基于社交关系的相似度传播式推荐算法", 《小型微型计算机系统》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN111259682A (en) * | 2018-11-30 | 2020-06-09 | 百度在线网络技术（北京）有限公司 | Method and device for monitoring the safety of a construction site |
| CN111259682B (en) * | 2018-11-30 | 2023-12-29 | 百度在线网络技术（北京）有限公司 | Method and device for monitoring safety of construction site |
| CN109815818A (en) * | 2018-12-25 | 2019-05-28 | 深圳市天彦通信股份有限公司 | Target person method for tracing, system and relevant apparatus |
| CN109886258A (en) * | 2019-02-19 | 2019-06-14 | 新华网(北京)科技有限公司 | The method, apparatus and electronic equipment of the related information of multimedia messages are provided |
| CN112148833A (en) * | 2019-06-27 | 2020-12-29 | 百度在线网络技术（北京）有限公司 | Information pushing method, server, terminal and electronic equipment |
| CN112148833B (en) * | 2019-06-27 | 2023-08-08 | 百度在线网络技术（北京）有限公司 | Information pushing method, server, terminal and electronic equipment |
| CN110909651A (en) * | 2019-11-15 | 2020-03-24 | 腾讯科技（深圳）有限公司 | Video subject person identification method, device, equipment and readable storage medium |
| CN110909651B (en) * | 2019-11-15 | 2023-12-26 | 腾讯科技（深圳）有限公司 | Method, device and equipment for identifying video main body characters and readable storage medium |
| WO2021114552A1 (en) * | 2019-12-11 | 2021-06-17 | 北京市商汤科技开发有限公司 | Information processing method and apparatus, electronic device and storage medium |
| JP2022516701A (en) * | 2019-12-11 | 2022-03-02 | 北京市商▲湯▼科技▲開▼▲發▼有限公司 | Information processing methods and devices, electronic devices and recording media |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108509611B (en) | 2021-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108509611A (en) | Method and apparatus for pushed information | |
| US10970334B2 (en) | Navigating video scenes using cognitive insights | |
| US10255710B2 (en) | Audio media mood visualization | |
| CN110378732A (en) | Information display method, information correlation method, device, equipment and storage medium | |
| CN108446390A (en) | Method and apparatus for pushed information | |
| CN109919244B (en) | Method and apparatus for generating a scene recognition model | |
| CN109033464A (en) | Method and apparatus for handling information | |
| CN108345387A (en) | Method and apparatus for output information | |
| CN109862100B (en) | Method and device for pushing information | |
| CN108134951A (en) | For recommending the method and apparatus of broadcasting content | |
| CN109618236A (en) | Video comments treating method and apparatus | |
| CN108933730A (en) | Information-pushing method and device | |
| CN109446442A (en) | Method and apparatus for handling information | |
| CN109977839A (en) | Information processing method and device | |
| US20240061899A1 (en) | Conference information query method and apparatus, storage medium, terminal device, and server | |
| CN109255035A (en) | Method and apparatus for constructing knowledge mapping | |
| CN109582825A (en) | Method and apparatus for generating information | |
| CN108446659A (en) | Method and apparatus for detecting facial image | |
| CN109413056A (en) | Method and apparatus for handling information | |
| CN112784103A (en) | Information pushing method and device | |
| CN109241344A (en) | Method and apparatus for handling information | |
| CN111859970A (en) | Method, apparatus, device and medium for processing information | |
| CN109408647A (en) | Method and apparatus for handling information | |
| CN110062116A (en) | Method and apparatus for handling information | |
| CN108898416A (en) | Method and apparatus for generating 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |