CN109982106A - A kind of video recommendation method, server, client and electronic equipment - Google Patents
A kind of video recommendation method, server, client and electronic equipment Download PDFInfo
- Publication number
- CN109982106A CN109982106A CN201910357558.8A CN201910357558A CN109982106A CN 109982106 A CN109982106 A CN 109982106A CN 201910357558 A CN201910357558 A CN 201910357558A CN 109982106 A CN109982106 A CN 109982106A
- Authority
- CN
- China
- Prior art keywords
- video
- information
- target
- pictorial information
- page
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/232—Content retrieval operation locally within server, e.g. reading video streams from disk arrays
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/435—Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/81—Monomedia components thereof
- H04N21/8126—Monomedia components thereof involving additional data, e.g. news, sports, stocks, weather forecasts
- H04N21/8133—Monomedia components thereof involving additional data, e.g. news, sports, stocks, weather forecasts specifically related to the content, e.g. biography of the actors in a movie, detailed information about an article seen in a video program
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/85—Assembly of content; Generation of multimedia applications
- H04N21/858—Linking data to content, e.g. by linking an URL to a video object, by creating a hotspot
- H04N21/8586—Linking data to content, e.g. by linking an URL to a video object, by creating a hotspot by using a URL
Abstract
The present invention provides a kind of video recommendation method, server, client and electronic equipment, this method comprises: obtaining pictorial information；Determine in the mapping relations that obtain in advance with the matched Target key frames of the pictorial information, and obtain include the Target key frames target video；Wherein, the mapping relations include the corresponding relationship between the Target key frames and target video；The information of the target video is sent to client.In this way, server will be sent to client with the target video that pictorial information matches, to recommend the video to match with pictorial information for user, saves user and carry out the time for searching video manually according to pictorial information, improve video acquisition efficiency.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of video recommendation method, server, client and electronics
Equipment.
Background technique
With the rapid development of information technology, the presentation mode of information is more and more abundant, for example, using video, audio or
The mode of person's text carries information.People can by terminal device (such as computer, mobile phone, tablet computer etc.) at any time with
The acquisition information on ground.
Currently, user is when through article in terminal device reading page, if to view corresponding to the figure in article
Frequently interested, need manually to search video corresponding to figure, in search procedure, need to consume a large amount of time and
Energy influences video acquisition efficiency.
Summary of the invention
The embodiment of the present invention provides a kind of video recommendation method, server, client and electronic equipment, to solve to use at present
Family needs manually to search video corresponding to the picture in the page, so that the lower problem of video acquisition efficiency.
In a first aspect, being applied to server the embodiment of the invention provides a kind of video recommendation method, comprising:
Obtain pictorial information；
Determine that and it includes described for obtaining with the matched Target key frames of the pictorial information in the mapping relations that obtain in advance
The target video of Target key frames；Wherein, the mapping relations include corresponding between the Target key frames and target video
Relationship；
The information of the target video is sent to client.
Second aspect, the embodiment of the invention also provides video recommendation methods, are applied to client, comprising:
Pictorial information is sent to server；
Receive the information for the target video that the server is sent；
Wherein, the target video is determined according in mapping relations with the matched Target key frames of the pictorial information,
The mapping relations include the corresponding relationship between the Target key frames of video and target video.
The third aspect, the embodiment of the present invention also provide a kind of server, comprising:
Module is obtained, for obtaining pictorial information；
Determining module, for determine in the mapping relations that obtain in advance with the matched Target key frames of the pictorial information,
And obtain the target video including the Target key frames；Wherein, the mapping relations include the Target key frames and target
Corresponding relationship between video；
Sending module, for sending the information of the target video to client.
Fourth aspect, the embodiment of the present invention also provide a kind of client, comprising:
Sending module, for sending pictorial information to server；
Receiving module, for receiving the information for the target video that the server is sent；
Wherein, the target video is determined according in mapping relations with the matched Target key frames of the pictorial information,
The mapping relations include the corresponding relationship between the Target key frames of video and target video.
5th aspect the embodiment of the invention also provides a kind of electronic equipment, including processor, memory and is stored in institute
The computer program that can be run on memory and on the processor is stated, when the computer program is executed by the processor
Realize above-mentioned first aspect video recommendation method or second aspect video recommendation method the step of.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer
Program, which is characterized in that the computer program realizes the video recommendation method of above-mentioned first aspect when being executed by processor, or
The step of video recommendation method of person's second aspect.
The embodiment of the present invention, by obtaining pictorial information；Determine in the mapping relations that obtain in advance with the pictorial information
Matched Target key frames, and obtain the target video including the Target key frames；Wherein, the mapping relations include described
Corresponding relationship between Target key frames and target video；The information of the target video is sent to client.In this way, server
It will be sent to client with the target video that pictorial information matches, to recommend the video to match with pictorial information for user,
It saves user and carries out the time for searching video manually according to pictorial information, improve video acquisition efficiency.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, needed in being described below to the embodiment of the present invention
Attached drawing to be used is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention,
For those of ordinary skill in the art, without any creative labor, it can also obtain according to these attached drawings
Obtain other attached drawings.
Fig. 1 is one of the flow diagram of video recommendation method provided in an embodiment of the present invention；
Fig. 2 is the two of the flow diagram of video recommendation method provided in an embodiment of the present invention；
Fig. 3 is the three of the flow diagram of video recommendation method provided in an embodiment of the present invention；
Fig. 4 is the four of the flow diagram of video recommendation method provided in an embodiment of the present invention；
Fig. 4 a is one of page listings schematic diagram provided in an embodiment of the present invention；
Fig. 4 b is the two of page listings schematic diagram provided in an embodiment of the present invention；
Fig. 5 is the structural schematic diagram of server provided in an embodiment of the present invention；
Fig. 6 is the structural schematic diagram of client provided in an embodiment of the present invention；
Fig. 7 is the structural schematic diagram of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
It is a kind of one of the flow chart of video recommendation method provided in an embodiment of the present invention referring to Fig. 1, Fig. 1, such as Fig. 1 institute
Show, video recommendation method provided in this embodiment, be applied to server, comprising the following steps:
Step 101 obtains pictorial information.
Pictorial information is the information that can be used for characterizing picture, for example, the colouring information etc. of the texture information of picture, picture
Deng.The picture that pictorial information is characterized can be the picture in the page.In this step, server can obtain picture by client
The pictorial information that information, i.e. reception client are sent can also obtain the page when server sends content of pages to client
The pictorial information of middle picture, it is not limited here.The page can be webpage.
Step 102 determines in the mapping relations that obtain in advance with the matched Target key frames of the pictorial information, and obtains
Target video including the Target key frames；Wherein, the mapping relations include the Target key frames and target video it
Between corresponding relationship.
Specifically, mapping relations are the corresponding relationship between the key frame and video of video.Specifically, mapping relations are view
Corresponding relationship between the key frame information and video information of frequency passes through pair between the key frame information and video information of video
It should be related to, can get the corresponding relationship between the key frame and video of video.The acquisition process of mapping relations includes:
Extract the key frame of video；
The characteristic information of key frame is extracted, to obtain the key frame information of video；
Determine the corresponding relationship between the key frame information and the video information；
According to the corresponding relationship between the key frame information and video information of video, obtain video key frame and video it
Between corresponding relationship.
It when extracting the key frame of video, can be configured according to the actual situation, for example, every 1 second one frame of extraction is as pass
Key frame, does not limit specific implementation here.Video may include multiple key frames.Key frame information is for characterizing key frame
Information, for example, key frame information can be the texture information or colouring information etc. of key frame, it is not limited here.Video letter
Breath may include the title of video, capacity, storage location etc..
It is to match pictorial information with key frame information when being matched in mapping relations according to pictorial information,
Then key frame corresponding to the key frame information that matching is obtained determines target according to Target key frames as Target key frames
Video.It may include identical key frame in different videos, for example, every collection all includes identical sheet head in collection of TV plays
Point, so that a key frame can correspond to multiple videos.
Step 103, the information that the target video is sent to client.
The information of the target video of acquisition is sent to client, to recommend the view to match with pictorial information for user
Frequently.The information of target video includes the access address of target video, and client can get target video, example by access address
Such as, user can watch target video, user does not have to manual according to pictorial information at this time by clicking access address on the client
Video retrieval is carried out, video acquisition is high-efficient, improves user experience.In addition, the information of target video can also include target
The brief introduction of video knows more information convenient for user.
In the present embodiment, pictorial information is obtained；It determines matched with the pictorial information in the mapping relations obtained in advance
Target key frames, and obtain the target video including the Target key frames；Wherein, the mapping relations include that the target is closed
Corresponding relationship between key frame and target video；The information of the target video is sent to client.In this way, server will be with figure
The target video that piece information matches is sent to client, to recommend the video to match with pictorial information for user, saves and uses
Family carries out the time for searching video manually according to pictorial information, improves video acquisition efficiency.
Referring to fig. 2, Fig. 2 is the two of the flow chart of a kind of video recommendation method provided in an embodiment of the present invention, such as Fig. 2 institute
Show, video recommendation method provided in this embodiment, be applied to server, comprising the following steps:
Step 201 obtains one or more pictorial informations.
Pictorial information is the information that can be used for characterizing picture, for example, the colouring information etc. of the texture information of picture, picture
Deng.In this step, server can obtain pictorial information, the i.e. pictorial information of reception client transmission by client, can also
To obtain the pictorial information of picture in the page, it is not limited here when server sends content of pages to client.The page can
For webpage.
In this step, server obtains one or more pictorial informations, that is, obtains the picture letter of one or more picture
Breath.The corresponding pictorial information of every picture.
Step 202 is determined with the matched key frame of one pictorial information in the mapping relations, described true to obtain
The corresponding video of fixed key frame, to obtain video set；Alternatively, determining in the mapping relations and in the multiple pictorial information
The matched key frame of each pictorial information, the corresponding video of key frame to obtain the determination, and obtain video set.
Step 202- step 203 is a kind of implementation of step 102.In this step, when getting picture letter
When breath, matched according to a pictorial information in mapping relations, to be matched to and the matched pass of one pictorial information
Key frame finally gets video set according to matched key frame.
When getting multiple pictorial informations, obtained respectively according to each pictorial information in the multiple pictorial information crucial
Frame, and video corresponding with key frame is determined according to key frame.It include all videos obtained according to key frame in video set.
N number of video in the video set is determined as the target video by step 203, and N is positive integer.
Select N number of video as target video from video set, N is positive integer.When determining target video, can be used as
Under type is determined:
In the case where getting one pictorial information, the history cumulative number that the target video is retrieved is high
In the history cumulative number that other videos are detected；Wherein, other described videos are in the video set except the target regards
Video except frequency.
Specifically, video set is obtained according to a pictorial information when getting a pictorial information, it will be in video set
The high video of the history cumulative number being detected is determined as target video.For example, if one pictorial information is picture letter
A is ceased, is video 1 and video 2 according to the video that pictorial information A is determined, the history of video 1 is retrieved, and (i.e. history is accumulative secondary for number
Number) be 20,000 times, the history of video 2 be retrieved number (i.e. history cumulative number) be 30,000 times, history that video 2 is retrieved is accumulative
Number is greater than the history cumulative number that video 3 is retrieved, and video 2 is more likely the video for meeting user demand, therefore, will be regarded
Frequently 2 user is recommended as target video, the precision of recommendation can be improved.
In the case where getting the multiple pictorial information, under type such as can be used and determine target video:
The number that the target video is retrieved in the video set is higher than the number that other videos are detected；
Alternatively, display position of the picture of the corresponding pictorial information of the target video in the page is located at other videos pair
Before display position of the picture for the pictorial information answered in the page；
Alternatively, the phase of the target video corresponding text information and the text information in the key frame of the target video
It is higher than the similarity of the text information in the key frame of the corresponding text information of other videos and other videos like degree,
In, the corresponding text information of the target video is the picture position of pictorial information corresponding with the target video in the page
Text of the distance set in pre-determined distance；
Wherein, other described videos are the video in the video set in addition to the target video.
Specifically, in the case where getting multiple pictorial informations, according to different pictorial informations, phase may be got
Same video, at this point, the video will appear repeatedly in video set.For example, if the multiple pictorial information includes pictorial information A
With pictorial information B, it is video 1 and video 2 according to the video that pictorial information A is determined, is view according to the video that pictorial information B is determined
Frequently 1 and video 3, then the number that video 1 is retrieved is 2 times, the number that video 2 and video 3 are retrieved in video set
It is 1 time, i.e., in video set, the number that video 1 is retrieved is higher than time that other videos (video 2 and video 3) are retrieved
Number, then video 1 can be determined as target video.
It, can be according to display of the picture in the page in the case where the picture that pictorial information is characterized is the picture in the page
The video determined according to the pictorial information of picture is screened in position, so that the picture of the corresponding pictorial information of target video exists
Display position in the page is located at before display position of the picture of the corresponding pictorial information of other videos in the page.Example
Such as, the page includes picture A and picture B, and display position of the picture A in the page is located at before picture B, and picture A corresponds to picture letter
A is ceased, picture B corresponds to pictorial information B, is video 1, the video determined according to pictorial information B according to the video that pictorial information A is determined
For video 2.Before being located at picture B due to display position of the picture A in the page, then video 1 can be determined as target video.
When determining target video, text of the picture around the display position of the page can be combined with to be screened.
By text letter of the picture in the text information and video set in the display position pre-determined distance of the page in the key frame of each video
Breath is compared, and determines similarity.The corresponding video of key frame where the high text information of similarity is determined as target video,
The similarity of text information i.e. in the key frame of the corresponding text information of target video and target video is higher than other videos pair
The similarity of text information in the key frame of the text information and other videos answered.
The corresponding text information of the target video is pictorial information corresponding with the target video in the page
Text of the distance of Pictures location in pre-determined distance；The corresponding text information of described other videos be in the page with it is described
Text of the distance of the Pictures location of the corresponding pictorial information of other videos in pre-determined distance.Pictures location is picture in the page
In display position.Pre-determined distance can be configured according to the actual situation, it is not limited here.For example, the page includes picture A,
There is passage to describe " the big disclosure of Spring Festival Gala list " in the display position pre-determined distance of picture A, according to the pictorial information of picture A
Determining video is video 1 and video 2, and the text information in the key frame of video 1 is " Spring Festival Gala list discloses ", the pass of video 2
Text information in key frame is " Spring Festival Gala ".Since text information " Spring Festival Gala list discloses " is similar to " the big disclosure of Spring Festival Gala list "
Degree, is higher than the similarity of " Spring Festival Gala " Yu " the big disclosure of Spring Festival Gala list ", will include the key frame of " Spring Festival Gala list discloses " therefore
Corresponding video is determined as target video, i.e., video 1 is determined as target video.
In the present embodiment, target video is determined above by three kinds of modes, the video in video set can be respectively adopted not
Same screening is according to being screened, and to provide more accurate video recommendations for user, further increases user experience, increases and use
Family viscosity.
Further, the display position in addition to the above-mentioned number being retrieved respectively according to video, picture in webpage, figure
The similarity of text information and key frame near piece display position determines except target video, and video can also be retrieved
To the display position of number, picture in webpage, the text information near picture display position and key frame similarity into
Row combines, to determine target video.
N number of video in the video set is determined as the target video, comprising:
For the video in video set, weight is set；Video is ranked up from big to small according to weight, and will be sorted preceding
N number of video be determined as target video.
In video set, the number that video is retrieved is more, and the weight of video is bigger, for example, if the multiple picture is believed
Breath includes pictorial information A and pictorial information B, is video 1 and video 2 according to the video that pictorial information A is determined, according to pictorial information
The video that B is determined is video 1 and video 3, then the number that video 1 is retrieved is 2 times in video set, video 2 and video
3 numbers being retrieved are 1 time, and the weight of video 1 is greater than video 2 and video 3.
Display position of the corresponding picture of pictorial information in the page is more forward, according to the power for the video that pictorial information determines
It is again bigger.For example, the page includes picture A and picture B, display position of the picture A in the page is located at before picture B, A pairs of picture
It answers pictorial information A, picture B to correspond to pictorial information B, is video 1 according to the video that pictorial information A is determined, it is true according to pictorial information B
Fixed video is video 2.Before being located at picture B due to display position of the picture A in the page, then the power being arranged for video 1
The important weight greater than video 2.
When according to the similarity of text information weight is arranged for video, comprising:
Determine the text information in the page in the display position pre-determined distance of the picture；
Text information in the text information and the first key frame is subjected to similarity mode；First key frame for institute
State one of the matched key frame of each pictorial information in multiple pictorial informations；
Weight is set for the video in video set, wherein similarity is higher, and the weight of the corresponding video of the first key frame is got over
Greatly.
For example, the page includes picture A, there is passage to describe " Spring Festival Gala list in the display position pre-determined distance of picture A
It is big to disclose ", the video according to the determination of the pictorial information of picture A is video 1 and video 2, the text information in the key frame of video 1
For " Spring Festival Gala list discloses ", the text information in the key frame of video 2 is " Spring Festival Gala ".Text information " Spring Festival Gala list discloses " with
The similarity of " the big disclosure of Spring Festival Gala list " is higher than the similarity of " Spring Festival Gala " Yu " the big disclosure of Spring Festival Gala list ", is arranged for video 1
Weight is higher than the weight of video 2.
Above by for the video in video set, weight is set, it can be by number that video is retrieved, picture in webpage
Display position, the text information near picture display position and key frame similarity be combined, it is more comprehensive with use
Screening according to being screened to the video in video set so that the target video determined is more accurate.
Step 204, the information that the target video is sent to client.
The information of the target video of acquisition is sent to client, to recommend the view to match with pictorial information for user
Frequently.The information of target video includes the access address of target video, and client can get target video, example by access address
Such as, user can watch target video, user does not have to manual according to pictorial information at this time by clicking access address on the client
Video retrieval is carried out, video acquisition is high-efficient, improves user experience.In addition, the information of target video can also include target
The brief introduction of video knows more information convenient for user.
In the present embodiment, multiple pictorial informations are obtained；It determines in the mapping relations and in the multiple pictorial information
Each matched key frame of pictorial information, the corresponding video of key frame to obtain the determination, to obtain video set；By the view
N number of video that frequency is concentrated is determined as the target video, and N is positive integer；The information of the target video is sent to client.This
Sample, server screen video after getting the video to match with pictorial information, more accurate to recommend for user
Video, save user according to pictorial information carry out manually search video time, improve video acquisition efficiency.
It is the three of the flow chart of a kind of video recommendation method provided in an embodiment of the present invention referring to Fig. 3, Fig. 3, such as Fig. 3 institute
Show, video recommendation method provided in this embodiment, be applied to client, comprising the following steps:
Step 301 sends pictorial information to server.
Pictorial information is the information that can be used for characterizing picture, for example, the colouring information etc. of the texture information of picture, picture
Deng.The picture that pictorial information is characterized can be the picture in the page.When sending pictorial information to server, can pass through for user
Client actively sends pictorial information to server, can also be client after getting content of pages, be obtained automatically by client
The pictorial information in content of pages is taken, and pictorial information is sent to server.The page can be webpage.
Client can be mobile phone, tablet computer (Tablet Personal Computer), laptop computer (Laptop
Computer), personal digital assistant (personal digital assistant, abbreviation PDA), mobile Internet access device
(Mobile Internet Device, abbreviation MID) or wearable device (Wearable Device) etc..
Step 302, the information for receiving the target video that the server is sent；Wherein, the target video is according to reflecting
Penetrate in relationship and determined with the matched Target key frames of the pictorial information, the mapping relations include video Target key frames with
Corresponding relationship between target video.
The relevant information of mapping relations is for details, reference can be made to the record in step 102, and details are not described herein.
The information of target video includes the access address of target video, and client can get target view by access address
Frequently, for example, user can watch target video, user does not have to believe according to picture at this time by clicking access address on the client
Breath carries out video retrieval manually, and video acquisition is high-efficient, improves user experience.In addition, the information of target video can also wrap
The brief introduction of target video is included, knows more information convenient for user.
Client, can displaying target video on the client after receiving the information of target video of server transmission
Information.If user is in the case that in browsing pages, the pictorial information of the page is sent to server automatically by client, client
End can exist after getting the information of target video in the information of the end position of page insertion target video, such user
When browsing to the end of the page, video can be watched by clicking the information of target video.If user actively will by client
Pictorial information is sent to server, and client, can be on the boundary that client is currently shown after getting the information of target video
The information of displaying target video in face.The display mode of target video can be configured according to the actual situation, it is not limited here.
In the present embodiment, user end to server sends pictorial information；Receive the target video that the server is sent
Information；Wherein, the target video is determined according in mapping relations with the matched Target key frames of the pictorial information, described
Mapping relations include the corresponding relationship between the Target key frames of video and target video.In this way, being sent by obtaining server
The target video to match with pictorial information, can save user according to pictorial information carry out manually search video time, mention
High video acquisition efficiency.
, can be by user by client active transmission when sending pictorial information to server, it can also be automatic by client
It is sent according to after the browsing pages of user acquisition pictorial information to server, that is, described to send pictorial information, packet to server
It includes:
In the case where getting content of pages, the pictorial information of the page is sent to server.
In the present embodiment, client extracts all figures in the page after getting content of pages, and in figure
Invalid figure be filtered, for example, by text figure, logo or trade mark (i.e. Logo figure) filtering finally obtain content of pages
Pictorial information.
In this embodiment, client sends pictorial information from trend server, no in the case where getting content of pages
It needs user to participate in, simplifies user's operation, improve user experience.
Further, referring to fig. 4, Fig. 4 is the four of the flow chart of a kind of video recommendation method provided in an embodiment of the present invention,
As shown in figure 4, video recommendation method provided in this embodiment, is applied to client, comprising the following steps:
Step 401, in the case that the access address of the page gets content of pages in through triggering page listings, to clothes
Business device sends the pictorial information of the page.
It in the present embodiment, include the access address of multiple pages in page listings, access address can be fixed for unified resource
Position symbol (Uniform Resource Locator, abbreviation URL).Client can get content of pages by access address, visitor
All figures in the page are extracted after getting content of pages in family end, and are filtered to the invalid figure in figure, example
Such as, by text figure, logo or trade mark (i.e. Logo figure) filtering, the final pictorial information for obtaining content of pages.
Step 402, the information for receiving the target video that the server is sent；Wherein, the target video is according to reflecting
Penetrate in relationship and determined with the matched Target key frames of the pictorial information, the mapping relations include video Target key frames with
Corresponding relationship between target video.
This step and step 302 are recorded unanimously, and for details, reference can be made to the records in step 302, and this will not be repeated here.
Step 403, the page described in the page listings the side of page info show the letter of the target video
Breath.
Page info may include the title of the page or the partial content of the page.The side of page info can believe for the page
Any side of display position is ceased, for example, the upside of page info display position, downside, left side or right side etc., herein not
It limits.Preferably, the page info of the page described in page listings (entrance that page listings can be regarded as picture and text reading)
Downside displaying target video information.By the information for the target video recommended for user under the page info of the page
Side is shown, can increase the probability that user checks target video, is also more in line with the browsing habit of user from top to bottom.
Page listings such as Fig. 4 a, in Fig. 4 a to be shown on client display interface, wherein page is shown in page listings
The title " upper Spring Festival Gala in XXX continuous 3 years " in face 11, come the header is the title " building Zhuan Liaozhen device downstairs " of the page 12；
User clicks the title of the page 11, and client obtains the content of pages of the page 11 and shows that article lands page；User terminates to browse
Article lands page, and where back page list when page, client shows the target video of acquisition on the downside of the title of the page 11
Information.As shown in Figure 4 b, between the title of the page 11 and the title of the page 12, insert target video information " XXX:
Spring Festival Gala stage is too grand, climbs up three times or meeting is nervous ", the information of target video further includes the surface plot of target video.User
By clicking the information, the corresponding video of the client terminal playing information (i.e. target video), label 33 show target video
Information, label 331 are the play button of target video, can play target video by clicking the play button.
Graph text information still occupies very big specific gravity in information stream distribution, and user has very strong after reading graph text information
Hope see the video resource of related content described in article figure.Currently, user after reading graph text information, needs
Oneself searches relevant video resource (such as TV play, variety show etc.), without Auto-matching according to the figure in article
And recommend the mechanism of user.
Video recommendation method in the application is associated with by pictorial information in article with short-sighted frequency, the foundation of long video resource
Relationship recommends the original video resource of content described in user's article automatically, brings video resource after reading text and graph information
Distribution increases, to meet user demand.
User is clicking to enter certain article reading, if the figure in this article is from some short-sighted frequency or long view
Picture in frequency can then be automatically matched to corresponding video, return to list page after user reads article, can will match to
Video is automatically inserted into after the article read just now, is watched for user.
Video recommendation method in the application, comprising:
Video take out frame and establish image arrive video video finger print searching system, it is to be understood that suggest key frame and
Corresponding relationship between video, i.e. acquisition mapping relations；
Video is retrieved in searching system with picture in article, and therefrom selection and the matched video resource of image content,
It is to be understood that obtaining target video according to pictorial information and mapping relations.
Video finger print searching system establishes other corresponding relationship from key frame of video to videl stage.With in article text
Figure (picture i.e. in article) retrieves many associated videos, in the position of article and retrieves same video according to picture
Picture number determines whether video finally matches.Specific step is as follows:
To all short-sighted frequencies, long video abstract image key frame；
Key-frame extraction feature simultaneously establishes aspect indexing；
All figures are extracted from article；
Invalid figure is identified and filtered, such as: text figure, Logo figure etc.；
Filtered figure extracts feature, and retrieves video；
According to the number that position of the figure in article and video are retrieved, it is filtered video filtering, is finally obtained
The video matched；
After obtaining the matching relationship of article and video according to above-mentioned steps, user when reading article and returning to list page,
The video being matched to can be shown automatically behind article.
In the above process, using the figure information combination figure position of article and the text information on periphery, find matched
Video resource, while matched video resource is ranked up by article information.Completely new Product Experience is brought to user, is solved
The certainly pain spot of user experience promotes user and carries out reasonable traffic transformation to the fluency of information consumption, while increasing short-sighted
The distribution of frequency and long video brings the distribution of video resource to increase, increases use while being basic to promote user experience
Family duration.
It is a kind of structure chart of server provided in an embodiment of the present invention referring to Fig. 5, Fig. 5, as shown in figure 5, the present embodiment
A kind of server 500 is provided, comprising:
Module 501 is obtained, for obtaining pictorial information；
Determining module 502, for determine in the mapping relations that obtain in advance with the matched target critical of the pictorial information
Frame, and obtain the target video including the Target key frames；Wherein, the mapping relations include the Target key frames and mesh
Mark the corresponding relationship between video；
Sending module 503, for sending the information of the target video to client.
Further, the acquisition module 501, is used for:
Obtain one or more pictorial informations；
The determining module 502, comprising:
First determine submodule, for determine in the mapping relations with the matched key frame of one pictorial information,
The corresponding video of key frame to obtain the determination, to obtain video set；Alternatively, determine in the mapping relations with it is described more
The matched key frame of each pictorial information in a pictorial information, the corresponding video of key frame to obtain the determination, to obtain
Video set；
Second determines submodule, and for N number of video in the video set to be determined as the target video, N is positive whole
Number.
Further, in the case where getting one pictorial information, history that the target video is retrieved
Cumulative number is higher than the history cumulative number that other videos are detected；Wherein, other described videos are to remove in the video set
Video except the target video.
Further, in the case where getting the multiple pictorial information, number that the target video is retrieved
The number being detected higher than other videos；
Alternatively,
It is corresponding that display position of the picture of the corresponding pictorial information of the target video in the page is located at other videos
Before display position of the picture of pictorial information in the page；
Alternatively,
The similarity of text information in the key frame of the corresponding text information of target video and the target video
The similarity of text information in the key frame of text information corresponding higher than other videos and other videos, wherein institute
Stating the corresponding text information of target video is the Pictures location of pictorial information corresponding with the target video in the page
Text of the distance in pre-determined distance；
Wherein, other described videos are the video in the video set in addition to the target video.
Server 500 can be realized each process that server is realized in previous embodiment, to avoid repeating, here no longer
It repeats.
The server 500 of the embodiment of the present invention obtains pictorial information；Determine in the mapping relations that obtain in advance with the figure
The Target key frames of piece information matches, and obtain the target video including the Target key frames；Wherein, the mapping relations packet
Include the corresponding relationship between the Target key frames and target video；The information of the target video is sent to client.In this way,
Server will be sent to client with the target video that pictorial information matches, with what is matched for user's recommendation with pictorial information
Video saves user and carries out the time for searching video manually according to pictorial information, improves video acquisition efficiency.
It is a kind of structure chart of client provided in an embodiment of the present invention referring to Fig. 6, Fig. 6, as shown in fig. 6, the present embodiment
A kind of client 600 is provided, comprising:
Sending module 601, for sending pictorial information to server；
Receiving module 602, for receiving the information for the target video that the server is sent；
Wherein, the target video is determined according in mapping relations with the matched Target key frames of the pictorial information,
The mapping relations include the corresponding relationship between the Target key frames of video and target video.
Further, the sending module 601, for sending institute to server in the case where getting content of pages
State the pictorial information of the page.
Further, the sending module 601, the access address for the page in through triggering page listings are got
In the case where content of pages, the pictorial information of the page is sent to server.
The client further includes display module, the side of the page info for the page described in the page listings
Show the information of the target video.
Client 600 can be realized each process that client is realized in previous embodiment, to avoid repeating, here no longer
It repeats.
The client 600 of the embodiment of the present invention sends pictorial information to server；Receive the target that the server is sent
The information of video；Wherein, the target video is according to true with the matched Target key frames of the pictorial information in mapping relations
Fixed, the mapping relations include the corresponding relationship between the Target key frames of video and target video.In this way, by obtaining service
Device send the target video to match with pictorial information, can save user according to pictorial information carry out manually search video when
Between, improve video acquisition efficiency.
It is the structural schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention referring to Fig. 7, Fig. 7.As shown in fig. 7, electric
Sub- equipment 700 includes: processor 701, memory 702 and is stored on the memory 702 and can transport on the processor
Capable computer program, the various components in electronic equipment 700 are coupled by bus system 703.It is understood that total linear system
System 703 is for realizing the connection communication between these components.
In an embodiment of the invention, processor 701, for obtaining pictorial information；
Determine that and it includes described for obtaining with the matched Target key frames of the pictorial information in the mapping relations that obtain in advance
The target video of Target key frames；Wherein, the mapping relations include corresponding between the Target key frames and target video
Relationship；
The information of the target video is sent to client.
Further, processor 701, for obtaining multiple pictorial informations；
Processor 701 is also used to determine in the mapping relations and each pictorial information in the multiple pictorial information
The key frame matched, the corresponding video of key frame to obtain the determination, to obtain video set；It will be N number of in the video set
Video is determined as the target video, and N is positive integer.
Further, in the case where getting one pictorial information, history that the target video is retrieved
Cumulative number is higher than the history cumulative number that other videos are detected；Wherein, other described videos are to remove in the video set
Video except the target video.
Further, in the case where getting the multiple pictorial information, number that the target video is retrieved
The number being detected higher than other videos；
Alternatively,
It is corresponding that display position of the picture of the corresponding pictorial information of the target video in the page is located at other videos
Before display position of the picture of pictorial information in the page；
Alternatively,
The similarity of text information in the key frame of the corresponding text information of target video and the target video
The similarity of text information in the key frame of text information corresponding higher than other videos and other videos, wherein institute
Stating the corresponding text information of target video is the Pictures location of pictorial information corresponding with the target video in the page
Text of the distance in pre-determined distance；
Wherein, other described videos are the video in the video set in addition to the target video.
Electronic equipment 700 can be realized each process that server is realized in previous embodiment, to avoid repeating, here not
It repeats again.
The electronic equipment 700 of the embodiment of the present invention obtains pictorial information；Determine in the mapping relations that obtain in advance with it is described
The matched Target key frames of pictorial information, and obtain the target video including the Target key frames；Wherein, the mapping relations
Including the corresponding relationship between the Target key frames and target video；The information of the target video is sent to client.This
Sample, server will be sent to client with the target video that pictorial information matches, to recommend and pictorial information phase for user
The video matched saves user and carries out the time for searching video manually according to pictorial information, improves video acquisition efficiency.
In another embodiment, processor 701, for sending pictorial information to server；
Receive the information for the target video that the server is sent；
Wherein, the target video is determined according in mapping relations with the matched Target key frames of the pictorial information,
The mapping relations include the corresponding relationship between the Target key frames of video and target video.
Further, processor 701, for sending the page to server in the case where getting content of pages
Pictorial information.
Further, processor 701, the access address for the page in through triggering page listings are got in the page
In the case where appearance, the pictorial information of the page is sent to server.
Processor 701, the side for being also used to the page info of the page described in the page listings show the target
The information of video.
Electronic equipment 700 can be realized each process that client is realized in previous embodiment, to avoid repeating, here not
It repeats again.
The electronic equipment 700 of the embodiment of the present invention sends pictorial information to server；Receive the mesh that the server is sent
Mark the information of video；Wherein, the target video according in mapping relations with the matched Target key frames of the pictorial information
It determines, the mapping relations include the corresponding relationship between the Target key frames of video and target video.In this way, by obtaining clothes
The target video to match with pictorial information that business device is sent can save user and be carried out searching video manually according to pictorial information
Time improves video acquisition efficiency.
The embodiment of the present invention also provides a kind of computer readable storage medium, and meter is stored on computer readable storage medium
Calculation machine program, the computer program realize each process of above-mentioned key element extracting method embodiment when being executed by processor,
And identical technical effect can be reached, to avoid repeating, which is not described herein again.Wherein, the computer readable storage medium,
Such as read-only memory (Read-Only Memory, abbreviation ROM), random access memory (Random Access Memory, letter
Claim RAM), magnetic or disk etc..
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In embodiment provided herein, it should be understood that disclosed device and method can pass through others
Mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the unit, only
A kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or components can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of device or unit
It connects, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.Some or all of unit therein can be selected to realize the embodiment of the present invention according to the actual needs
Purpose.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, ROM, RAM, magnetic or disk etc. are various can store program code
Medium.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be subject to the protection scope in claims.
Claims (16)
1. a kind of video recommendation method is applied to server characterized by comprising
Obtain pictorial information；
Determine that and obtaining includes the target with the matched Target key frames of the pictorial information in the mapping relations that obtain in advance
The target video of key frame；Wherein, the mapping relations include the corresponding relationship between the Target key frames and target video；
The information of the target video is sent to client.
2. the method according to claim 1, wherein the acquisition pictorial information, comprising:
Obtain one or more pictorial informations；
With the matched Target key frames of the pictorial information in the mapping relations that the determination obtains in advance, and it includes described for obtaining
The target video of Target key frames, comprising:
Determine in the mapping relations with the matched key frame of one pictorial information, to obtain the key frame pair of the determination
The video answered, to obtain video set；Alternatively, determine in the mapping relations with each pictorial information in the multiple pictorial information
Matched key frame, the corresponding video of key frame to obtain the determination, to obtain video set；
N number of video in the video set is determined as the target video, N is positive integer.
3. according to the method described in claim 2, it is characterized in that, in the case where getting one pictorial information, institute
It states the history cumulative number that target video is retrieved and is higher than the history cumulative number that other videos are detected；
Wherein, other described videos are the video in the video set in addition to the target video.
4. according to the method described in claim 2, it is characterized in that, in the case where getting the multiple pictorial information, institute
It states the number that target video is retrieved in the video set and is higher than the number that other videos are detected；
Alternatively,
Display position of the picture of the corresponding pictorial information of the target video in the page is located at the corresponding picture of other videos
Before display position of the picture of information in the page；
Alternatively,
The corresponding text information of the target video and the similarity of the text information in the key frame of the target video are higher than
The similarity of text information in the key frame of the corresponding text information of other videos and other videos, wherein the mesh
Marking the corresponding text information of video is with the target video at a distance from the Pictures location of corresponding pictorial information in the page
Text in pre-determined distance；
Wherein, other described videos are the video in the video set in addition to the target video.
5. a kind of video recommendation method is applied to client characterized by comprising
Pictorial information is sent to server；
Receive the information for the target video that the server is sent；
Wherein, the target video is determined according in mapping relations with the matched Target key frames of the pictorial information, described
Mapping relations include the corresponding relationship between the Target key frames of video and target video.
6. according to the method described in claim 5, it is characterized in that, described send pictorial information to server, comprising:
In the case where getting content of pages, the pictorial information of the page is sent to server.
7. according to the method described in claim 5, it is characterized in that, described send pictorial information to server, comprising:
In the case that the access address of the page gets content of pages in through triggering page listings, to described in server transmission
The pictorial information of the page；
After the information for receiving the target video that the server is sent, further includes:
The side of the page info of the page described in the page listings shows the information of the target video.
8. a kind of server characterized by comprising
Module is obtained, for obtaining pictorial information；
Determining module and is obtained for determining in the mapping relations that obtain in advance with the matched Target key frames of the pictorial information
Take the target video including the Target key frames；Wherein, the mapping relations include the Target key frames and target video
Between corresponding relationship；
Sending module, for sending the information of the target video to client.
9. server according to claim 8, which is characterized in that the acquisition module is used for:
Obtain one or more pictorial informations；
The determining module, comprising:
First determine submodule, for determine in the mapping relations with the matched key frame of one pictorial information, to obtain
The corresponding video of the key frame of the determination is taken, to obtain video set；Alternatively, determine in the mapping relations with the multiple figure
The matched key frame of each pictorial information in piece information, the corresponding video of key frame to obtain the determination, to obtain video
Collection；
Second determines submodule, and for N number of video in the video set to be determined as the target video, N is positive integer.
10. server according to claim 9, which is characterized in that in the case where getting one pictorial information,
The history cumulative number that the target video is retrieved is higher than the history cumulative number that other videos are detected；Wherein, institute
Stating other videos is the video in the video set in addition to the target video.
11. server according to claim 9, which is characterized in that in the case where getting the multiple pictorial information,
The number that the target video is retrieved in the video set is higher than the number that other videos are detected；
Alternatively,
Display position of the picture of the corresponding pictorial information of the target video in the page is located at the corresponding picture of other videos
Before display position of the picture of information in the page；
Alternatively,
The corresponding text information of the target video and the similarity of the text information in the key frame of the target video are higher than
The similarity of text information in the key frame of the corresponding text information of other videos and other videos, wherein the mesh
Marking the corresponding text information of video is with the target video at a distance from the Pictures location of corresponding pictorial information in the page
Text in pre-determined distance；
Wherein, other described videos are the video in the video set in addition to the target video.
12. a kind of client characterized by comprising
Sending module, for sending pictorial information to server；
Receiving module, for receiving the information for the target video that the server is sent；
Wherein, the target video is determined according in mapping relations with the matched Target key frames of the pictorial information, described
Mapping relations include the corresponding relationship between the Target key frames of video and target video.
13. client according to claim 12, which is characterized in that the sending module, for getting in the page
In the case where appearance, the pictorial information of the page is sent to server.
14. client according to claim 12, which is characterized in that the sending module, for passing through the triggering page
In the case that the access address of the page gets content of pages in list, the pictorial information of the page is sent to server；
The client further includes display module, and the side of the page info for the page described in the page listings is shown
The information of the target video.
15. a kind of electronic equipment, which is characterized in that including processor, memory and be stored on the memory and can be in institute
The computer program run on processor is stated, such as Claims 1-4 is realized when the computer program is executed by the processor
Any one of described in video recommendation method the step of, alternatively, when the computer program is executed by the processor realize such as
The step of video recommendation method described in any one of claim 5 to 7.
16. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of video recommendation method described in any one of Claims 1-4 is realized when being executed by processor, alternatively, the calculating
The step of video recommendation method described in any one of claim 5 to 7 is realized when machine program is executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910357558.8A CN109982106B (en) | 2019-04-29 | 2019-04-29 | Video recommendation method, server, client and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910357558.8A CN109982106B (en) | 2019-04-29 | 2019-04-29 | Video recommendation method, server, client and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109982106A true CN109982106A (en) | 2019-07-05 |
| CN109982106B CN109982106B (en) | 2021-11-26 |
Family
ID=67087032
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910357558.8A Active CN109982106B (en) | 2019-04-29 | 2019-04-29 | Video recommendation method, server, client and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109982106B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110809187A (en) * | 2019-10-31 | 2020-02-18 | Oppo广东移动通信有限公司 | Video selection method, video selection device, storage medium and electronic equipment |
| CN110909209A (en) * | 2019-11-26 | 2020-03-24 | 北京达佳互联信息技术有限公司 | Live video searching method and device, equipment, server and storage medium |
| CN110909184A (en) * | 2019-11-19 | 2020-03-24 | 北京达佳互联信息技术有限公司 | Multimedia resource display method, device, equipment and medium |
| CN111767814A (en) * | 2020-06-19 | 2020-10-13 | 北京奇艺世纪科技有限公司 | Video determination method and device |
| CN113810735A (en) * | 2020-06-15 | 2021-12-17 | 西安诺瓦星云科技股份有限公司 | Program image generation method and device and service equipment system |
| WO2022237107A1 (en) * | 2021-05-14 | 2022-11-17 | 上海擎感智能科技有限公司 | Video searching method and system, electronic device, and storage medium |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101021857A (en) * | 2006-10-20 | 2007-08-22 | 鲍东山 | Video searching system based on content analysis |
| CN101021855A (en) * | 2006-10-11 | 2007-08-22 | 鲍东山 | Video searching system based on content |
| CN103530357A (en) * | 2013-10-11 | 2014-01-22 | 北京奇艺世纪科技有限公司 | Video retrieval method and system |
| CN104182481A (en) * | 2014-08-05 | 2014-12-03 | 百度在线网络技术（北京）有限公司 | Resource recommendation method and device |
| CN104809120A (en) * | 2014-01-24 | 2015-07-29 | 腾讯科技（深圳）有限公司 | Information processing method and device |
| US20160021179A1 (en) * | 2014-07-18 | 2016-01-21 | Google Inc. | Automated Group Recommendation |
| US20170278546A1 (en) * | 2016-03-25 | 2017-09-28 | Samsung Electronics Co., Ltd. | Method and device for processing multimedia information |
| CN107480155A (en) * | 2016-06-08 | 2017-12-15 | 北京新岸线网络技术有限公司 | A kind of video searching system |
| CN107517393A (en) * | 2016-06-17 | 2017-12-26 | 阿里巴巴集团控股有限公司 | A kind of information-pushing method, apparatus and system |
| CN107862258A (en) * | 2017-10-24 | 2018-03-30 | 广东小天才科技有限公司 | Method of calibration, device, equipment and the storage medium of video Chinese version content |
| CN108012162A (en) * | 2017-12-04 | 2018-05-08 | 北京小米移动软件有限公司 | Content recommendation method and device |
| CN108024145A (en) * | 2017-12-07 | 2018-05-11 | 北京百度网讯科技有限公司 | Video recommendation method, device, computer equipment and storage medium |
| CN108268644A (en) * | 2018-01-22 | 2018-07-10 | 上海哔哩哔哩科技有限公司 | Video searching method, server and video searching system |
| CN108334627A (en) * | 2018-02-12 | 2018-07-27 | 北京百度网讯科技有限公司 | Searching method, device and the computer equipment of new media content |
| CN108416013A (en) * | 2018-03-02 | 2018-08-17 | 北京奇艺世纪科技有限公司 | Video matching, retrieval, classification and recommendation method, apparatus and electronic equipment |
| CN108415935A (en) * | 2018-01-23 | 2018-08-17 | 北京奇虎科技有限公司 | A kind of method, apparatus of push recommendation message |
| CN108446390A (en) * | 2018-03-22 | 2018-08-24 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN108776676A (en) * | 2018-02-02 | 2018-11-09 | 腾讯科技（深圳）有限公司 | Information recommendation method, device, computer-readable medium and electronic equipment |
| CN109271552A (en) * | 2018-08-22 | 2019-01-25 | 北京达佳互联信息技术有限公司 | Pass through the method, apparatus of picture retrieval video, electronic equipment and storage medium |
-
2019
- 2019-04-29 CN CN201910357558.8A patent/CN109982106B/en active Active
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101021855A (en) * | 2006-10-11 | 2007-08-22 | 鲍东山 | Video searching system based on content |
| CN101021857A (en) * | 2006-10-20 | 2007-08-22 | 鲍东山 | Video searching system based on content analysis |
| CN103530357A (en) * | 2013-10-11 | 2014-01-22 | 北京奇艺世纪科技有限公司 | Video retrieval method and system |
| CN104809120A (en) * | 2014-01-24 | 2015-07-29 | 腾讯科技（深圳）有限公司 | Information processing method and device |
| US20160021179A1 (en) * | 2014-07-18 | 2016-01-21 | Google Inc. | Automated Group Recommendation |
| CN104182481A (en) * | 2014-08-05 | 2014-12-03 | 百度在线网络技术（北京）有限公司 | Resource recommendation method and device |
| US20170278546A1 (en) * | 2016-03-25 | 2017-09-28 | Samsung Electronics Co., Ltd. | Method and device for processing multimedia information |
| CN107480155A (en) * | 2016-06-08 | 2017-12-15 | 北京新岸线网络技术有限公司 | A kind of video searching system |
| CN107517393A (en) * | 2016-06-17 | 2017-12-26 | 阿里巴巴集团控股有限公司 | A kind of information-pushing method, apparatus and system |
| CN107862258A (en) * | 2017-10-24 | 2018-03-30 | 广东小天才科技有限公司 | Method of calibration, device, equipment and the storage medium of video Chinese version content |
| CN108012162A (en) * | 2017-12-04 | 2018-05-08 | 北京小米移动软件有限公司 | Content recommendation method and device |
| CN108024145A (en) * | 2017-12-07 | 2018-05-11 | 北京百度网讯科技有限公司 | Video recommendation method, device, computer equipment and storage medium |
| CN108268644A (en) * | 2018-01-22 | 2018-07-10 | 上海哔哩哔哩科技有限公司 | Video searching method, server and video searching system |
| CN108415935A (en) * | 2018-01-23 | 2018-08-17 | 北京奇虎科技有限公司 | A kind of method, apparatus of push recommendation message |
| CN108776676A (en) * | 2018-02-02 | 2018-11-09 | 腾讯科技（深圳）有限公司 | Information recommendation method, device, computer-readable medium and electronic equipment |
| CN108334627A (en) * | 2018-02-12 | 2018-07-27 | 北京百度网讯科技有限公司 | Searching method, device and the computer equipment of new media content |
| CN108416013A (en) * | 2018-03-02 | 2018-08-17 | 北京奇艺世纪科技有限公司 | Video matching, retrieval, classification and recommendation method, apparatus and electronic equipment |
| CN108446390A (en) * | 2018-03-22 | 2018-08-24 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN109271552A (en) * | 2018-08-22 | 2019-01-25 | 北京达佳互联信息技术有限公司 | Pass through the method, apparatus of picture retrieval video, electronic equipment and storage medium |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110809187A (en) * | 2019-10-31 | 2020-02-18 | Oppo广东移动通信有限公司 | Video selection method, video selection device, storage medium and electronic equipment |
| CN110809187B (en) * | 2019-10-31 | 2022-04-05 | Oppo广东移动通信有限公司 | Video selection method, video selection device, storage medium and electronic equipment |
| CN110909184A (en) * | 2019-11-19 | 2020-03-24 | 北京达佳互联信息技术有限公司 | Multimedia resource display method, device, equipment and medium |
| CN110909209A (en) * | 2019-11-26 | 2020-03-24 | 北京达佳互联信息技术有限公司 | Live video searching method and device, equipment, server and storage medium |
| CN110909209B (en) * | 2019-11-26 | 2022-12-27 | 北京达佳互联信息技术有限公司 | Live video searching method and device, equipment, server and storage medium |
| CN113810735A (en) * | 2020-06-15 | 2021-12-17 | 西安诺瓦星云科技股份有限公司 | Program image generation method and device and service equipment system |
| CN111767814A (en) * | 2020-06-19 | 2020-10-13 | 北京奇艺世纪科技有限公司 | Video determination method and device |
| WO2022237107A1 (en) * | 2021-05-14 | 2022-11-17 | 上海擎感智能科技有限公司 | Video searching method and system, electronic device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109982106B (en) | 2021-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109982106A (en) | A kind of video recommendation method, server, client and electronic equipment | |
| CN104239408B (en) | The data access of content based on the image recorded by mobile device | |
| CN107105318B (en) | Video hotspot segment extraction method, user equipment and server | |
| CN104537115B (en) | The heuristic approach and device of user interest | |
| JP4062908B2 (en) | Server device and image display device | |
| KR100849420B1 (en) | Image-based searching system and method therefor | |
| CN1901638B (en) | Apparatus and method for information processing | |
| CN107295361B (en) | A kind of content delivery method | |
| US20190236099A1 (en) | Picture processing method and apparatus, and electronic device | |
| US8234305B2 (en) | Method for determining communicative value | |
| KR101404596B1 (en) | System and method for providing video service based on image data | |
| CN106202260B (en) | Search method and device and search engine | |
| CN103353875B (en) | Media interaction method based on visual search and system | |
| CN106407358B (en) | Image searching method and device and mobile terminal | |
| CN105072460A (en) | Information annotation and association method, system and device based on VCE | |
| CN106961636A (en) | Commodity information recommendation method and device and electronic equipment | |
| CN103605808A (en) | Search-based UGC (user generated content) recommendation method and search-based UGC recommendation system | |
| CN109168047A (en) | Video recommendation method, device, server and storage medium | |
| WO2013131480A1 (en) | Image capturing apparatus based information acquisition method and device, and mobile communication apparatus | |
| CN108388629A (en) | A kind of multimedia information push method, device and electronic equipment | |
| CN104639957A (en) | Mobile multimedia terminal, video program recommendation method and server | |
| CN107491997A (en) | Information-pushing method and system | |
| CN108399232A (en) | A kind of information-pushing method, device and electronic equipment | |
| KR101122737B1 (en) | Apparatus and method for establishing search database for knowledge node coupling structure | |
| CN105760541B (en) | Video is ordered recommended method and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |