CN107295361A - A kind of content delivery method - Google Patents
A kind of content delivery method Download PDFInfo
- Publication number
- CN107295361A CN107295361A CN201710480351.0A CN201710480351A CN107295361A CN 107295361 A CN107295361 A CN 107295361A CN 201710480351 A CN201710480351 A CN 201710480351A CN 107295361 A CN107295361 A CN 107295361A
- Authority
- CN
- China
- Prior art keywords
- user
- content
- data
- attribute tags
- push
- 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
- 238000002716 delivery method Methods 0.000 title claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 47
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000013499 data model Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000006116 polymerization reaction Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 11
- 230000006399 behavior Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 239000000203 mixture Substances 0.000 description 5
- 101100368725 Bacillus subtilis (strain 168) tagF gene Proteins 0.000 description 4
- 241001122767 Theaceae Species 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 238000010422 painting Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 239000000344 soap Substances 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000003542 behavioural effect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000686 essence Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 235000004280 healthy diet Nutrition 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/482—End-user interface for program selection
- H04N21/4826—End-user interface for program selection using recommendation lists, e.g. of programs or channels sorted out according to their score
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
- H04N21/26258—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists for generating a list of items to be played back in a given order, e.g. playlist, or scheduling item distribution according to such list
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
- H04N21/44008—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics in the video 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]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/835—Generation of protective data, e.g. certificates
- H04N21/8352—Generation of protective data, e.g. certificates involving content or source identification data, e.g. Unique Material Identifier [UMID]
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Information Transfer Between Computers (AREA)
Abstract
This application provides a kind of content delivery method, this method includes:Receive the view data that applications client is sent;Wherein, the image and/or video that described image data are shot by the applications client according to connected camera device are determined;Described image data are carried out with the attribute tags that data processing obtains the user logged in the applications client;Contents list is pushed according to the generation of the attribute tags of the user;And the push contents list is handed down to the applications client.Present invention also provides the server for realizing content push.
Description
Technical field
The application is related to areas of information technology, more particularly to a kind of content delivery method and device.
Background technology
With the development of internet, the application of intelligent television is more and more extensive, plays in smart home extremely important
Role.Generally, in addition to user actively selects video frequency program, intelligent television can also push some video frequency programs to user
Or advertisement, such as Hot Contents etc., therefore, how to carry out content push also turns into one of hot issue.
The content of the invention
Present application example proposes a kind of content delivery method, including:The view data that applications client is sent is received, its
In, the image and/or video that described image data are shot by the applications client according to connected camera device are determined;
Described image data are carried out with the attribute tags that data processing obtains the user logged in the applications client;According to described
Attribute tags generation pushes contents list;And the push contents list is handed down to the applications client.
Present application example proposes a kind of content push server, including:
Receiving module, the view data for receiving applications client transmission, wherein, described image data are by the application
The image and/or video that client is shot according to connected camera device are determined;
Acquisition module, the use logged in the applications client is obtained for carrying out data processing to described image data
The attribute tags at family;
Determining module, for pushing contents list according to the generation of the attribute tags of the user;And
Sending module, for will push contents list and be handed down to applications client.
By above technical scheme, the figure that camera or external camera device that can be based on terminal device be collected
As analyzing the characteristic of life data of user, the attribute tags of user are obtained, and according to the attribute tags of user in content
The content of matching is searched in storehouse, so as to push some users needs and suitable content to user so that content is pushed away
Send more accurate, it is to avoid user in order to found in huge volumes of content be adapted to oneself content and needs terminal device and server
Between the wasting of resources that causes of frequent interaction.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, without having to pay creative labor, may be used also
To obtain other accompanying drawings according to these accompanying drawings.
Fig. 1 is the system structure diagram of the example of the application one;
Fig. 2 is the content delivery method flow chart of the example of the application one;
Fig. 3 is the method flow diagram that the content and user's matching degree are determined described in the example of the application one;
Fig. 4 is the image-recognizing method flow chart of the example of the application one;
Fig. 5 is the content delivery method flow chart of the example of the application one;
Fig. 6 is the structural representation of the server described in the example of the application one;
Fig. 6 A are the structural representation of the acquisition module 602 described in the example of the application one;
Fig. 6 B are the structural representation of the determining module 603 described in the example of the application one;
Fig. 7 is the composition structure chart of the computing device 700 at the place of server 600 of the example of the application one.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.Based on this
Embodiment in invention, the every other reality that those of ordinary skill in the art are obtained under the premise of creative work is not made
Example is applied, the scope of protection of the invention is belonged to.
In order to succinct and directly perceived on describing, hereafter by describing some representational embodiments come to the solution of the present invention
It is illustrated.Substantial amounts of details is only used for help and understands the solution of the present invention in embodiment.However, it will be apparent that the technology of the present invention
Scheme can be not limited to these details when realizing.In order to avoid unnecessarily having obscured the solution of the present invention, some embodiment party
Formula is not described meticulously, but only gives framework.Hereinafter, " comprising " refers to " include but is not limited to ", " root
According to ... " refer to " according at least to ..., but be not limited to according only to ... ".Hereinafter it is not specifically stated the quantity of a composition
When, it is meant that it can also be multiple that the composition, which can be one, or can be regarded as at least one.
The example of the application proposes a kind of content delivery method, and this method can pass through the terminal devices such as intelligent television
The picture pick-up device shooting image of camera or installation indoors, to collect polytype user data, and to the user of collection
Data carry out data processing so as to obtain the attribute tags of user, and the attribute tags based on obtained user push one to user
It is adapted to the content of the user a bit.On the one hand the above method for pushing can cause content push more accurate, it is to avoid user
In order to which searching is adapted to the content of oneself and frequently interacts what is caused between needs terminal device and server in huge volumes of content
The wasting of resources, on the other hand by collecting for a long time and accumulating user data, can be modified to the operational model of data processing
Make it more and more clear, and then make it that the content pushed is also more and more accurate.
Wherein, in some examples of the application, above-mentioned user data can specifically refer to by terminals such as intelligent televisions
The camera of equipment or the camera device installed indoors shoot the reflection user for collecting and being obtained by image recognition analysis
The data of characteristic of life, for example, data in terms of furnishings, furniture, household electrical appliances, personage and behavior etc..Above-mentioned user
Attribute tags can be specifically the representative user personality obtained according to Users'Data Analysis some keywords, these keywords
The characteristics of user can be reflected to a certain extent and interest.The above can specifically refer to that audio, video, picture etc. are more
Media content, or the content of text such as the news comprising word, article etc. or video/audio/picture etc. and word knot
Close the content for obtaining including information.
Fig. 1 shows the system structure diagram that the content delivery method described in some examples of the application is applicable.Such as Fig. 1
Shown, the system of the application at least includes:Terminal device 11, network 12, one or more servers 13, one or more data
Storehouse 14 and camera device 15.
In some examples of the application, above-mentioned terminal device 11 can be intelligent television, personal computer (PC), notes
The intelligent mobile terminal equipment such as the intelligent terminals such as this computer or smart mobile phone, PAD or tablet personal computer.Typically
In the case of, various application software can be installed on terminal device 11, watched being used for of being currently needed for using including user
The application software of the word such as the videos such as film, TV programme, programme televised live and news, focus, comment and/or image content.
In description later, describe for convenience, the application software referred to as applications client that user will be used or used.
Network 12 can include cable network and wireless network.As shown in figure 1, in access network side, terminal device 11 can
Wirelessly or wired mode is linked into network 13;And in core net side, server 13 generally by
Wired mode is connected to network 13.Certainly, server 13 can also wirelessly be connected to network 12.
Above-mentioned server 13 is the server of above-mentioned intended application software, for example, it may be multimedia server, such as rise
Interrogate the server of video;Can also be promotion message Platform Server, such as Advertisement Server;Can also provide the user text
Word and/or picture push the content server of content, for example, Tengxun's NEWS SERVER etc..Server 13 and terminal device 11
On applications client provide the user service and content together, for example, playing video, audio, promotion message and video
The services such as program push, word and/or image content push.In addition, server 13 can also be to according to the use being collected into
User data is analyzed, and obtains the attribute tags of user, and the matching for carrying out content according to the attribute tags of user obtains waiting to push away
The content sent.It should be noted that it can also be multiple server sets that above-mentioned server 13, which can be single server apparatus,
The cluster server that group obtains together.
Above-mentioned database 14 is used to store the user data related to above-mentioned intended application software, the account letter of such as user
Breath, the user data of user and attribute tags of user etc..Above-mentioned database 14 can be also used for storing various contents.Number
Can be in the manner shown in figure 1 independently of server 13 according to storehouse 14, server 13 can direct or through the visit of other servers
Ask database 14.Database 14 can also be integrated with server 13.
Above-mentioned camera device 15 is used for shooting image.The camera device 15 can be integrated with terminal device 11, example
Such as, the camera carried on PAD, tablet personal computer, smart mobile phone and intelligent television.The camera device 15 can also be single
Video camera, for example, install camera at home.Now the camera device 15 can by the short haul connection such as bluetooth mode with
Neighbouring terminal device 11 links together, and the image that itself is shot is sent to terminal device 11;Certainly, the camera device 15
Network 12 can also be directly accessed, the image that itself shoots is sent to by server 13 by network 12.
Under the premise of herein, based on the system architecture shown in above-mentioned Fig. 1, the example of the application provides a kind of content push side
Method.Fig. 2 shows the flow chart for the content delivery method that present application example is provided.As shown in Fig. 2 this method can be by server
13 perform, and comprise the following steps:
Step 201:The view data that applications client is sent is received, wherein, above-mentioned view data is by applications client root
The image and/or video shot according to connected camera device is determined.
In some instances, with the intelligent more and more higher of terminal device 11, the outside including shooting is first-class is set
It is standby or the standard configuration of terminal device 11 to be turned into, namely terminal device 11 itself is just integrated with camera device 15.Therefore, eventually
End equipment 11 can collect the view data relevant with user's characteristic of life by being integrated into the camera device 15 of itself,
Such as indoor photo or video.Even if in addition, there is no integrated camera device 15 on terminal device 11, indoors can also
Installation individually images first-class camera device 15 to carry out the collection of image.Moreover, between camera device 15 and terminal device 11
It can be attached by the short haul connection such as WIFI or Zigbee mode or other network communication modes.Then, shooting is set
The image of collection can also be sent to terminal device 11 by standby 15.In this case, the application visitor installed on terminal device 11
View data can be sent to server 13 by family end by network 12, and server 13 can be received to be collected on terminal device 11
Into or single acquired image data of picture pick-up device 15, to carry out subsequent analysis processing.
In some examples of the application, above-mentioned view data can be the camera device 15 or single on terminal device 11
Image file or video file that only camera device 15 is shot, such as bitmap file or jpeg file or other standards
The image file or video file of form.
In other examples of the application, above-mentioned view data can also be the applications client pair on terminal device 11
The image or video that camera device 15 is shot carry out obtaining the number with gathering image-related text formatting after image recognition
According to can for example include furnishings data, furniture data, appliance data, character data and behavioral data etc..Generally,
These data can be one or more keywords.The above-mentioned method to image or video progress image recognition will below
Explanation.
Step 202:The view data received is analyzed and processed, the user's that acquisition is logged in applications client
Attribute tags.
As it was previously stated, in some instances, the view data that server 13 is received is to pass through to obtain after image recognition
The data with image-related text formatting arrived, for example, being the one or more keywords obtained after image recognition.
In other examples, the view data that server 13 is received be image file or video file, then now
Server 13 will carry out image recognition to the image file or video file that are received first, extract with it is received image-related
Text formatting view data, for example can include furnishings data, furniture data, appliance data, character data and
Behavioral data etc..As it was previously stated, these data can be one or more keywords.It is above-mentioned that image or video are schemed
It will be described as knowing method for distinguishing.
Obtained by image recognition with the data of image-related text formatting or from applications client receive with
After the data of image-related text formatting, server 13 can be designated index by the text formatting of acquisition with the user of user
With image-related data as user data a part preserve to the user data for entering to safeguard all users data
In storehouse.Here, as it was previously stated, text formatting can be one or more keywords with image-related data, and can
To be divided into different classifications, for example, any sort or several in furnishings, furniture, household electrical appliances, personage and behavior can be included
Class.Wherein, furnishings, furniture, household electrical appliances, personage and behavior have corresponded to the type belonging to keyword, and under each type,
The descending order of category according to belonging to information, the information of each keyword can include the information of many levels again.
For example, server 13 is received after applications client sends image file, by image recognition technology from above-mentioned
The article of the indoor placements such as calligraphy and painting, body-building apparatus, tea table, sofa can be identified in image file, therefore " word can be extracted
Picture ", " body-building apparatus ", " tea table ", " sofa " this four keywords, and index holding extraction is designated with the user of above-mentioned user
The keyword gone out.In storage, can also classify preservation, such as " calligraphy and painting ", " body-building apparatus " are stored in point of furnishings
Under class, and " tea table ", " sofa " are stored under the classification of furniture.If in addition, can be further by image recognition
Identify that the author of calligraphy and painting either work title or identifies the brand and/or model of body-building apparatus, tea table and sofa,
Keyword then can be gone out according to these information extractions and a part for these keywords as user data is stored in database
In, and the keyword stored is also with different levels.
In addition to the keywords such as indoor furnishings and furniture, image is constantly gathered by picture pick-up device and by terminal
Client device or server 13 in equipment 11 carry out image recognition, can also obtain the character data and behavior number of user
According to.The kinsfolk for obtaining user and sex, age and the behavioral characteristic of each member etc. can for example be analyzed.
For example, as obtained from table 1 below shows the image gathered by image recognition as live pick up equipment 15 some
The example of a part of user data of user.Wherein, what user was designated that the user generates when server 13 is registered is different from
The mark of other users.Based on user mark, user can pass through the applications client login service device on terminal device 11
13。
User identifies | Furnishings | Calligraphy and painting | Leonardo da Vinci《Mona Lisa Smile》 |
User identifies | Furnishings | Body-building apparatus | Fast that treadmill F65 |
User identifies | Furniture | Tea table | Bright Furniture Stocks Trading Co. |
User identifies | Furniture | Sofa | Bright Furniture Stocks Trading Co. |
User identifies | Personage | Old man | Female, 50-70 Sui |
User identifies | Personage | Children | Man, 7-10 Sui |
User identifies | Personage | Pet | Dog, Labrador |
User identifies | …… | …… | …… |
Table 1
In some instances, server 13 is divided the user data that itself is stored by the data model pre-established
Type of Collective and statistical calculation, obtain the attribute tags of user.For example, server 13 passes through user data shown in above-mentioned table 1
The classification polymerization of big data model and statistics etc. be after computing, can obtain " culture ", " art work collection ", " body-building ", " foster
The attribute tags such as life " and " pet dog ".
, can be with above by the obtained data of the analysis acquired image of picture pick-up device 15 in some examples of the application
Only a part for server and/or the user data of data place storage, can also include user in user data daily
The data produced when carrying out various operations on the internet, for example, the history viewing record of user, historical viewings record, concern
Channel and the data of application installed on its terminal device of user etc..These user data can be used to generate together
The attribute tags of user, so that the attribute tags of user can more precisely embody the characteristic and interest of user.
Step 203:Determined to push content according to the attribute tags of the user, generation pushes contents list.
In some instances, the every content preserved in database can also summarize the category of content with attribute tags
Property.The attribute tags of content are typically the keyword related to the content that these contents are set in dispensing by publisher, example
Such as, related personnel's information such as title, type and author, the publisher of content etc. can be included.These attribute tags are usual
Can as the content mark, be generally used for the classification and retrieval to content.Certainly, the label of content can also be by user
Constantly added during the content is browsed, so that the keyword of content more enriches and comprehensive.Generally, it is interior
The attribute tags of appearance be may be embodied in the title of the content, interior perhaps brief introduction, and institute can be retrieved according to the attribute tags
Content is stated, the attribute tags can be the mixture of any Chinese, English, numeral, or Chinese English digital.In such case
Under, server 13 just can be according to by analyzing the content that the attribute tags for the user that user data is obtained are preserved from itself
In search out the push content matched with the user, and generate push contents list.
In the example of the application, searched out in the content that can be preserved by a variety of methods from itself and the user
The push content matched somebody with somebody.Specific method will be described below.
Step 204:Above-mentioned push contents list is handed down to applications client.
In some examples of the application, the applications client on terminal device 11 is receiving above-mentioned push contents list
Afterwards, displaying the above is pushed into list, so that user can therefrom select itself content interested.
In some examples of the application, server 13 being analyzed user data, search for and matched with user in
Hold and during generation pushes contents list, the mark as the push contents list will be identified using user, with table
The bright push contents list is the push for which user.In this case, server 13 can be arranged according to content is pushed
User corresponding to table identifies to determine to push which applications client contents list is handed down to, particularly as being User logs in
Applications client used in server 13.Particularly if camera device 15 and terminal device 11 be not physically same
The situation of equipment, when server 13 directly receives view data from camera device 15, the view data is by with the user of user
Mark is designated, 13 pairs of user data of server are handled and obtained after the push contents list matched with the user,
The push contents list also will be designated mark with the user of user.Then, server 13 will be corresponding according to contents list is pushed
User mark by push contents list send to corresponding applications client.
Camera or external camera device of this method based on terminal device can be seen that by above technical scheme
The image collected is analyzed the characteristic of life data of user, obtains the attribute tags of user, and according to the attribute of user
Label searches for the content of matching in content library, so as to push some users needs and suitable content to user.
On the one hand the content delivery method can collect user's characteristic of life data, and be pushed away according to the characteristic of life of user progress content
Send so that content push is more accurate, it is to avoid user in order to found in huge volumes of content be adapted to oneself content and needs end
The wasting of resources that frequent interaction between end equipment and server is caused, the another aspect above method can continuously enter
OK, by collecting for a long time and accumulating user data so that big data processing operational model it is more and more clear, and then push it is interior
Hold also more and more accurate.
Further, in some examples of the application, further the reflection of content push can also be adjusted according to user
The content of whole push.Specifically, server 13 can further record user and push content row are shown to terminal device 11
The operation of table, pushes efficient data, and regard the efficient data of the push of generation as number of users according to the operation of user generation
According to a part be stored in the database for safeguarding user data.These push effective during content matching is carried out
Rate data will be applied to the matching of content in turn, then can make it that the content matched is more accurate.Above-mentioned push is efficient
Data can be directed to the content of some type and count obtained data, for example, can be specifically that user clicks on a certain class
Number of times and user that the number of times of the push content of type, the push content of a certain type are pushed click on the push of a certain type
Ratio of number of times that the number of times of content and the push content of the type are pushed etc..
In some instances, can be according to the efficient data of the push of the user, preferentially from pushing efficient highest
Content generation object content list is chosen in the content of type.For example, server 13 once issued sport category to user X pushes content
100 times (or it is 100 that referred to as sport category, which pushes content revealing number), user X above-mentioned sport category is pushed content click on 90 times (or
Person is referred to as sport category and pushes content hits or effective reading number for 90), then for user X, sport category pushes the point of content
It is that the push effective percentage that 0.9, i.e. sport category push content is 0.9 to hit and count/issue several ratios;In another example the Zeng Xiangyong of server 13
Family X issues amusement class and pushes content 100 times, and user X pushes content points to above-mentioned amusement class and hit 5 times, then entertains class and push content
Push effective percentage be 0.05;Equally, server 13 once issued finance and economic to user X and pushes content 100 times, and user X is to above-mentioned
Finance and economic pushes content and clicked on 5 times, then the push effective percentage that finance and economic pushes content is 0.05.Server 13 is according to above physical culture
Class pushes the push effective percentage of content, entertains efficient and finance and economic push content the push effective percentage of push that class pushes content
Value can determine that user X compares the push content of concern sport category, pushing content and finance and economic to amusement class pushes content not
Pay close attention to very much, so as to correct big data processing model, to reduce, amusement class pushes content and finance and economic pushes the push of content,
And increase the push that sport category pushes content.For example, user property label can preferentially be carried out in the content of sport category and interior
The matching of the attribute tags of appearance, so that preferential determine to push content in the content of sport category.
Further, the content of above-mentioned push is also and can be not merely directly related with the attribute tags of the user
Content, the common trait of customer group, and each customer group common concern can also be summarized by big data operational model
Content, with derivative more push contents.For example, the regular people that works and rests generally also can especially be closed to health diet
Note, can push some healthy diet class programs or advertisement etc. to they.In another example, general three mouthfuls/family of four is to trip
Content in terms of trip, child-parent education and parent-offspring's activity can compare concern, can push some tourism, Qin Zifang to they
The program in face or advertisement etc..
The push content for determining to match with user according to the attribute tags of user below by specific example in detail
The method of list.
In the example of the application, first, server 13 will be according to the attribute tags and the attribute tags of user of content
The matching degree of user and each content are determined, the push matched with user is then generated according to the matching degree of user and each content
Contents list.
Fig. 3 shows the method flow of content and user's matching degree described in determination described in one example of the application
Figure.As shown in figure 3, this method comprises the following steps:
Following operation is performed respectively for each content:
Step 301:Obtain the attribute tags vector of each content.
Here, the corresponding relation of content and the attribute tags of user can be with as follows:
Content ID1:Tag1, tag2, tag3 ..., tagM
Content ID2:Tag1, tag2, tag3 ..., tagM
Content ID is the mark of content in above formula, such as title etc. is capable of the mark of unique mark the above, and tag is represented
The all properties label of user, wherein, above-mentioned attribute tags are referred to as keyword.Tag1 represents first attribute of user
Label, tag2 represents second attribute tags of user, and tag3 represents the 3rd attribute tags of user, by that analogy, tagM
The m-th attribute tags of user are represented, M represents the quantity of whole attribute tags of all users.All included according to a content
There are the attribute tags of which user, it may be determined that the attribute tags vector corresponding with the content, such as content ID1 includes
Tag1 and tag3, then the attribute tags corresponding with content ID1 vector is (1,0,1,0,0,0 ...).
Step 302:Content and the matching degree of user are determined according to attribute tags vector.
In some examples of the application, 1 number is that can be defined as this interior in the attribute tags of some content vector
Hold the matching degree with user.Because above-mentioned attribute tags vector can reflect some content and the degree of correlation of user, therefore, according to
Attribute tags vector can determine content and the matching degree of user.
Can also be each curriculum offering in some examples of the application except the method for above-mentioned attribute tags vector
One matching degree counter, for recording the matching degree between the content and the attribute tags of user.In operation, can be by it
Initial value is designated as zero.During matching, server 13 is by each attribute tags of the user and some content
Attribute tags are compared one by one, whenever the attribute tags of the user and an attribute tags of the content are identical or phase
When near, the corresponding matching degree counter of the content is added one, until having compared all properties label and the content of the user
Attribute tags.It is above-mentioned identical to refer to that attribute tags are identical on word;It is above-mentioned close to refer to that attribute tags are identical in implication.
For example, the attribute tags of user are " South Korean TV soaps ", the attribute tags that candidate pushes content are also " South Korean TV soaps ", then it is assumed that the two is identical.
In another example, the attribute tags of user are " South Korean TV soaps fan ", and the attribute tags that candidate pushes content are " South Korean TV soaps fan ", and the two is in word
On it is not fully identical, it is but essentially identical in implication, then it is assumed that the two is close.After attribute tags whole is completeer,
The numerical value of the matching degree counter is the matching degree of the user and the content.
Server 13 can obtain the matching degree of the user and all the elements by above-mentioned a variety of methods.Below according to
Family and the matching degree of each content can generate push contents list.
In some examples of the application, server 13 takes according to the obtained user and the matching degree of all the elements
The N number of content of matching degree highest pushes contents list as content, generation is pushed, also i.e. by the N number of content of matching degree highest
Mark, which is added, pushes contents list.Wherein, N is natural number set in advance, to push the content that can be pushed in contents list
Maximum quantity.Certainly, if the quantity that matching degree is more than zero content is less than N, it is big that server can only push matching degree
The content of difference quantity (N-n) is selected in zero content (such as n content), or in the content for being again zero from matching degree.
Now, the mode of selection can be pre-set, for example randomly choose or selected according to number of visits etc..
In other examples of the application, after the matching degree of user and content is determined, server 13 can be with
The corresponding matching degree of all the elements and predetermined threshold value are compared, the threshold value will be more than or equal to matching degree
The mark of content, which is added, to be pushed in contents list.
A certain content can be uniquely determined by the identification server of the above.
In some examples of the application, the order of push content listed in contents list is pushed, can also basis
The content and the matching degree of user are set, for example, being sorted from big to small according to matching degree.
The method that image recognition is carried out by specific example in detail applications client or server 13 again below.
Specific method can with as shown in figure 4, including:
Step 401:The image file is split, each part is obtained.
Wherein, the segmentation to the image file is considered as decision process, decomposited from object view image object and it
Part, part is made up of picture element again.The algorithm of decision-making can be divided into picture point technology and the class of regional development and technology two.Picture point
Technology is that each picture point is classified with threshold method, for example relatively obtaining in character image by picture point gray scale and threshold value
Stroke.Regional development and technology is to utilize Feature detection border, lines, the regions such as texture, some areas grey-scale contrast etc., and uses area
The technologies such as domain growth, merging, decomposition obtain each part of image.
Step 402:Each part is identified, it is determined that each self-corresponding object of each part.
When each part is identified, for each part, according to the shape and ash of the part
Degree information is classified to the structure of the part, and the corresponding object of the part is identified according to the result of classification;Or
Person, for each part, the part and the object model pre-set is matched, known according to the result of matching
The not other corresponding object of the part.
Step 403:Each object is explained, the respective keyword of each object is obtained as the pass of the image file
Keyword.
When being explained to each object, it can be set up with heuristic or human-computer interaction technology combination recognition methods
The hierarchy construction of object view, illustrates to have in object view there is what relation between what object, object.In the situation of three-dimensional object view
Under, it is possible to use the knowledge of the mutual restricting relation of each object in the various Given informations and object view of object view.For example, from two
Shades of gray, texture variations, surface profile wire shaped in dimension image etc. are inferred to the surface trend of three-dimensional object view;Also can basis
Distance measurement information, or the calculating of the depth of field is carried out from the two dimensional images of several different angles, draw describing and explaining for three-dimensional object view.
By above-mentioned segmentation, identification and the processing explained, the keyword of each image file, namely attribute can be extracted
Label, it is possible to all attribute tags are stored according to the form shown in table 1.
It should be noted that the method for the determination method and image recognition of the above and user's matching degree is only one
Citing, the application can also be using other matching process and image-recognizing method without beyond scope of the present application.
The example of the application additionally provides a kind of content delivery method.Fig. 5 shows that the content that present application example is provided is pushed away
The flow chart of delivery method.As shown in figure 5, this method can be performed by terminal device 11, comprise the following steps:
Step 501:Collect view data.
In some instances, with the intelligent more and more higher of terminal device 11, the outside including shooting is first-class is set
Standby or to turn into the standard configuration of terminal device 11, therefore, in user's using terminal equipment 11 during browsing content, terminal is set
Standby 11 can collect the view data relevant with user by external equipment.Wherein, as it was previously stated, above-mentioned view data can
To be the image or video of picture format.Above-mentioned view data can also be to be carried out after image recognition to the image or video of collection
Obtain with image-related text data, the keyword of such as image etc..
Further, applications client further can also report other kinds of user data to server 13, for example,
The application software that applications client can be installed by terminal device 11 is using the process of above-mentioned application software to obtain user
The data of middle generation, such as obtain the related letter that user browses the record data of article or the public number of concern by wechat
Cease, or user is obtained by Tengxun's video and watch historical record data of media etc..
Step 502:Described image data are sent to server 13, so that it can carry out data to the user data
Processing, so as to obtain the attribute tags of the user, and determines the push content for the user according to the attribute tags of user
List.
Step 503:Push contents list that the reception server 13 is issued simultaneously is shown so that user selects.
The mark of one or more contents is included in above-mentioned push contents list.When user clicks on the mark of some content
Afterwards, applications client will ask the content to server 13, and the mark of content is carried in the request.Server 13 is receiving request
Afterwards, according to the mark of the content wherein carried, the storage address of the content, such as URL are obtained from database
(URL) applications client, and by storage address is fed back to, corresponding content is obtained according to the storage address by applications client.
By above technical scheme can be seen that user of this method based on user data it is required and concern content to
Content that is that user pushes some users needs and being adapted to.On the one hand the content delivery method can cause content push more
Precisely, it is to avoid user in order to found in huge volumes of content be adapted to the content of oneself and between needs terminal device and server
The wasting of resources that frequently interaction is caused, on the other hand by collecting for a long time and accumulating user data so that the fortune of big data processing
Calculation model is more and more clear, and then the content pushed is also more and more accurate.
The method of correspondence above content push, present invention also provides the content push server 600 for realizing the above method.
In some examples of the application, the structure that the above-mentioned server 600 for realizing content delivery method can be as shown in Figure 6
Figure is realized, including receiving module 601, acquisition module 602 and determining module 603, and the function of each module is as follows:
Receiving module 601, the view data for receiving applications client transmission, wherein, above-mentioned view data is by applying
The image and video that client is shot according to connected camera device are determined;
Acquisition module 602, for carrying out data processing to the user data, obtains and is logged in the applications client
User attribute tags;And
Determining module 603, for being determined to push contents list according to the attribute tags of the user;
Sending module 604, for will push contents list and be handed down to applications client.
In some instances, above-mentioned acquisition module 602 can be realized as the structure chart shown in Fig. 6 A, including recognition unit
6021st, storage unit 6022 and acquiring unit 6023, the function of each unit are as follows:
Recognition unit 6021, the view data for the picture format to user carries out image recognition, obtains text formatting
View data;
Storage unit 6022, for using the user of user be designated index by the view data of the text formatting of acquisition as
A part for user data is preserved into database;And
Acquiring unit 6023, the user data preserved in the database is divided by the data model pre-established
Type of Collective and statistical calculation, obtain the attribute tags of the user.
In some instances, above-mentioned determining module 603 can be realized as the structure chart shown in Fig. 6 B, including matching degree determines list
Member 6031 and push contents list generation unit 6032.The function of each unit is as follows:
Matching degree determining unit 6031, the attribute tags for the attribute tags according to the user and any content are true
The fixed content and the matching degree of the user;And
Contents list generation unit 6032 is pushed, in being pushed according to the matching degree generation of the content and the user
Hold list.
Above-mentioned matching degree determining unit 6031 can use foregoing method to determine content and the matching degree of user.
In some instances, the contents list generation unit 6032 that pushes can be to all the elements and of the user
It is ranked up with degree;Pushed being added in described all the elements with the N number of mark for pushing content of user's matching degree highest
In contents list;Wherein, N is natural number set in advance.
In some instances, the contents list generation unit 6032 that pushes can be by all the elements and of the user
It is compared with degree with predetermined threshold value, matching degree is more than or equal into the mark of the content of the threshold value adds in push
Hold in list.
In some examples of the application, above-mentioned receiving module can also be further used for being pushed for described according to user
The operation generation of contents list pushes efficient data;Now, above-mentioned server 600 of stating may further include:Storage unit,
For the effective percentage data that push to be stored into database as a part for user data.
Fig. 7 shows the composition structure chart of the computing device 700 at the place of content push server 600.As shown in fig. 7, should
Computing device includes one or more processor (CPU) 702, communication module 704, memory 706, user interface 710, and
Communication bus 708 for interconnecting these components.
Processor 702 can be received and be sent data by communication module 704 to realize network service and/or local communication.
User interface 710 includes one or more output equipments 712, and it includes one or more loudspeakers and/or one
Or multiple visual displays.User interface 710 also includes one or more input equipments 714, and it is included such as, keyboard, mouse
Mark, voice command input block or loudspeaker, touch screen displays, touch sensitive tablet, posture capture camera or other inputs are pressed
Button or control etc..
Memory 706 can be high-speed random access memory, such as DRAM, SRAM, DDR RAM or other deposit at random
Take solid storage device;Or nonvolatile memory, such as one or more disk storage equipments, optical disc memory apparatus, sudden strain of a muscle
Deposit equipment, or other non-volatile solid-state memory devices.
The executable instruction set of the storage processor 702 of memory 706, including:
Operating system 716, including for handling various basic system services and program for performing hardware dependent tasks;
Using 718, including the various application programs for content push, this application program can realize above-mentioned each example
In handling process, such as can include Fig. 6 shown in content push server 600 in part or all of unit.Each unit
Or at least one module in module 601-603 can be stored with machine-executable instruction.Processor 702 is by performing memory
Machine-executable instruction in 706 in each module 601-603 at least one module, and then above-mentioned each module 601- can be realized
The function of at least one module in 603.
It should be noted that step and module not all in above-mentioned each flow and each structure chart is all necessary, can
To ignore some steps or module according to the actual needs.The execution sequence of each step is not fixed, can be entered as needed
Row adjustment.The division of each module is intended merely to facilitate the division functionally that description is used, and when actually realizing, a module can
Realized with point by multiple modules, the function of multiple modules can also be realized by same module, and these modules can be located at same
In individual equipment, it can also be located in different equipment.
Hardware module in each embodiment can in hardware or hardware platform adds the mode of software to realize.Above-mentioned software
Including machine readable instructions, it is stored in non-volatile memory medium.Therefore, each embodiment can also be presented as software product.
Therefore, some examples of the application additionally provide a kind of computer-readable recording medium, are stored thereon with computer
Instruction, wherein, the computer instruction realizes any figure methods described in above-mentioned Fig. 2-7 when being executed by processor the step of.
In each example, hardware can be realized by the hardware of special hardware or execution machine readable instructions.For example, hardware can be with
It is used to complete specific behaviour for the permanent circuit or logical device (such as application specific processor, such as FPGA or ASIC) that specially design
Make.Hardware can also include PLD or circuit by software provisional configuration (as included general processor or other
Programmable processor) it is used to perform specific operation.
In addition, each example of the application can pass through the data processor by data processing equipment such as computer execution
To realize.Obviously, data processor constitutes the application.In addition, being generally stored inside the data processing in a storage medium
Program by program by directly reading out storage medium or by installing or copying to the storage of data processing equipment by program
Performed in equipment (such as hard disk and/or internal memory).Therefore, such storage medium also constitutes the application, and present invention also provides one
Non-volatile memory medium is planted, wherein the data processor that is stored with, this data processor can be used for performing in the application
State any one of method example example.
The corresponding machine readable instructions of module in Fig. 6 can be such that operating system operated on computer etc. completes here
The some or all of operation of description.Non-volatile computer readable storage medium storing program for executing can be inserted in the expansion board in computer
In set memory or write the memory set in the expanding element being connected with computer.Installed in expansion board or
CPU on person's expanding element etc. can be according to instruction execution part and whole practical operations.
In addition, the device and each module in the application each example can be integrated in a processing unit, can also
That modules are individually physically present, can also two or more devices or module it is integrated in a unit.Above-mentioned collection
Into unit can both have been realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
God is with principle, and any modification, equivalent substitution and improvements done etc. should be included within the scope of protection of the invention.
Claims (14)
1. a kind of content delivery method, wherein, methods described includes:
The view data that applications client is sent is received, wherein, described image data are connected by the applications client according to it
The image and/or video that the camera device connect is shot are determined;
Described image data are carried out with the attribute tags that data processing obtains the user logged in the applications client;
Contents list is pushed according to attribute tags generation;And
The push contents list is handed down to the applications client.
2. according to the method described in claim 1, wherein, described image data include the applications client from picture pick-up device read
Take, the image and/or video shot by the picture pick-up device;
It is described that the attribute tags that data processing obtains the user logged in the applications client are carried out to the user data
Including:
Image recognition is carried out to described image data, the view data of text formatting is obtained;
Index is designated using the user of user to preserve the view data of the text formatting of acquisition as a part for user data
Into database;And
The user data preserved in the database is subjected to classification polymerization by the data model pre-established and statistics is transported
Calculate, obtain the attribute tags of the user.
3. according to the method described in claim 1, wherein, described image data include the view data of text formatting;Wherein, institute
The view data of text formatting is stated by the applications client by recognizing that image and/or video that picture pick-up device is gathered are obtained;
The attribute tags that the data processing acquisition user is carried out to the user data include:
Index is designated using the user of user to preserve the view data of the text formatting of acquisition as a part for user data
Into database;And
The user data preserved in the database is subjected to classification polymerization by the data model pre-established and statistics is transported
Calculate, obtain the attribute tags of the user.
4. according to the method described in claim 1, wherein, it is described according to the attribute tags of the user generation push contents list
Including:
Matching for the content and the user is determined according to the attribute tags of the attribute tags of the user and any content
Degree;And
Contents list is pushed according to the content and the generation of the matching degree of the user.
5. method according to claim 4, wherein, it is described to determine that the content and the matching degree of the user include:
Each candidate for pushing contents list for the candidate pushes content and performs following operation respectively:
For described one matching degree counter of curriculum offering, and its initial value is designated as zero;
Each attribute tags of each attribute tags of the user and the content are compared, when the user's
When one attribute tags of one attribute tags and the content are same or like, the matching degree counter of the content is added 1,
Until having compared all properties label of the user and all properties label of the content;And
The numerical value that the candidate is pushed to the matching degree counter of content is used as candidate push content and of the user
With degree.
6. method according to claim 4, wherein, it is described to determine that the content and the matching degree of the user include:
Following operation is performed respectively for each object content of the object content list:
Obtain the attribute tags vector of each content;And
The content and the matching degree of the user are determined according to attribute tags vector.
7. method according to claim 4, wherein, content is pushed according to the content and the generation of the matching degree of the user
List includes:
All the elements and the matching degree of the user are ranked up;
Itself mark with the N number of content of user's matching degree highest in all the elements is added into the push contents list
In;Wherein, N is natural number set in advance.
8. method according to claim 4, wherein, content is pushed according to the content and the generation of the matching degree of the user
List includes:
All the elements and the matching degree of the user are compared with predetermined threshold value, the matching degree is more than or waited
Added in the mark of the content of the threshold value in the push internal content list.
9. according to the method described in claim 1, wherein, methods described further comprises:
Efficient data are pushed for the operation generation of the push contents list according to user;And
The effective percentage data that push are stored into database as a part for user data.
10. a kind of content push server, wherein, the server includes:
Receiving module, the view data for receiving applications client transmission, wherein, described image data are by the application client
The image and/or video that are shot according to connected camera device is held to determine;
Acquisition module, obtains the user's logged in the applications client for carrying out data processing to described image data
Attribute tags;
Determining module, for pushing contents list according to the generation of the attribute tags of the user;And
Sending module, for will push contents list and be handed down to applications client.
11. server according to claim 10, wherein, the acquisition module includes:
Recognition unit, for carrying out image recognition to view data, obtains the view data of text formatting;
Storage unit, the view data of the text formatting of acquisition is regard as user data for being designated index using the user of user
A part preserve into database;And
Acquiring unit, by the user data preserved in the database by the data model that pre-establishes carry out classification polymerization with
And statistical calculation, obtain the attribute tags of the user.
12. server according to claim 10, wherein, the determining module includes:
Matching degree determining unit, the attribute tags for the attribute tags according to the user and any content are determined in described
Hold the matching degree with the user;And
Contents list generation unit is pushed, contents list is pushed for the matching degree generation according to the content and the user.
13. server according to claim 10, wherein,
The receiving module is further used for pushing efficient number for the operation generation of the push contents list according to user
According to;And
The server further comprises:Storage unit, for pushing efficient data as one of user data using described
Divide and store into database.
14. a kind of computer-readable recording medium, is stored thereon with computer instruction, wherein, the computer instruction is processed
The step of device realizes method any one of claim 1 to 9 when performing.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710480351.0A CN107295361B (en) | 2017-06-22 | 2017-06-22 | A kind of content delivery method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710480351.0A CN107295361B (en) | 2017-06-22 | 2017-06-22 | A kind of content delivery method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107295361A true CN107295361A (en) | 2017-10-24 |
CN107295361B CN107295361B (en) | 2019-07-19 |
Family
ID=60097410
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710480351.0A Active CN107295361B (en) | 2017-06-22 | 2017-06-22 | A kind of content delivery method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107295361B (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107948743A (en) * | 2017-11-29 | 2018-04-20 | 腾讯科技(深圳)有限公司 | Video pushing method and its device, storage medium |
CN107959865A (en) * | 2017-11-14 | 2018-04-24 | 广州虎牙信息科技有限公司 | Main broadcaster's method for pushing, device and computer equipment |
CN109522426A (en) * | 2018-12-05 | 2019-03-26 | 北京达佳互联信息技术有限公司 | Multi-medium data recommended method, device, equipment and computer readable storage medium |
CN109522493A (en) * | 2018-09-04 | 2019-03-26 | 西安艾润物联网技术服务有限责任公司 | Information-pushing method and Related product |
CN109688458A (en) * | 2019-01-14 | 2019-04-26 | 四川长虹电器股份有限公司 | The implementation method of smart television cloud desktop operation system based on big data algorithm |
CN110046940A (en) * | 2019-04-22 | 2019-07-23 | 福建工程学院 | A kind of Ads on Vehicles personalized push method and device |
CN111143611A (en) * | 2019-12-31 | 2020-05-12 | 新疆联海创智信息科技有限公司 | Information acquisition method and device |
CN111866528A (en) * | 2020-04-30 | 2020-10-30 | 火币(广州)区块链科技有限公司 | Live program pushing method and readable storage medium |
CN112632370A (en) * | 2020-12-08 | 2021-04-09 | 青岛海尔科技有限公司 | Method, device and equipment for article pushing |
CN113254419A (en) * | 2021-01-19 | 2021-08-13 | 青岛诺顿传媒有限公司 | Internet of things cloud platform management system and method based on big data micro-service |
WO2022000826A1 (en) * | 2020-06-28 | 2022-01-06 | 百度在线网络技术(北京)有限公司 | Video stream processing method and apparatus, and computer device and medium |
Citations (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101001356A (en) * | 2006-12-30 | 2007-07-18 | 上海文广互动电视有限公司 | Contents supply system and method of network TV. |
CN101094335A (en) * | 2006-06-20 | 2007-12-26 | 株式会社日立制作所 | TV program recommender and method thereof |
US20100071005A1 (en) * | 2008-09-18 | 2010-03-18 | Yoshiaki Kusunoki | Program recommendation apparatus |
CN101998161A (en) * | 2009-08-14 | 2011-03-30 | Tcl集团股份有限公司 | Face recognition-based television program watching method |
US20120151370A1 (en) * | 2010-12-10 | 2012-06-14 | Wyse Technology Inc. | Methods and systems for remote desktop session redrawing via http headers |
CN102957743A (en) * | 2012-10-18 | 2013-03-06 | 北京天宇朗通通信设备股份有限公司 | Data pushing method and device |
CN102984219A (en) * | 2012-11-13 | 2013-03-20 | 浙江大学 | Tourism mobile terminal information pushing method based on medial multi-dimensional content expression |
CN103024464A (en) * | 2011-12-31 | 2013-04-03 | 中国科学院计算技术研究所 | System and method for providing information related to video playing content |
CN103164518A (en) * | 2013-03-06 | 2013-06-19 | 杭州九树网络科技有限公司 | Mobile terminal (MT) augmented reality application system and method |
CN103428539A (en) * | 2012-05-15 | 2013-12-04 | 腾讯科技(深圳)有限公司 | Pushed information publishing method and device |
CN103577516A (en) * | 2013-07-01 | 2014-02-12 | 北京百纳威尔科技有限公司 | Method and device for displaying contents |
CN103618918A (en) * | 2013-11-27 | 2014-03-05 | 青岛海信电器股份有限公司 | Method and device for controlling display of smart television |
CN103634617A (en) * | 2013-11-26 | 2014-03-12 | 乐视致新电子科技(天津)有限公司 | Video recommending method and device in intelligent television |
CN103716702A (en) * | 2013-12-17 | 2014-04-09 | 三星电子(中国)研发中心 | Television program recommendation device and method |
CN104010220A (en) * | 2014-04-30 | 2014-08-27 | 小米科技有限责任公司 | Method and device for providing content service |
CN104202718A (en) * | 2014-08-05 | 2014-12-10 | 百度在线网络技术(北京)有限公司 | Method and device for providing information for user |
CN104268187A (en) * | 2014-09-17 | 2015-01-07 | 合一网络技术(北京)有限公司 | User feedback based multi-scenario supported online content optimization system |
CN104301758A (en) * | 2014-10-10 | 2015-01-21 | 安徽华米信息科技有限公司 | Method, device and system for pushing videos |
CN104394471A (en) * | 2014-11-19 | 2015-03-04 | 四川长虹电器股份有限公司 | Method for intelligently recommending favorite program to user |
CN104853230A (en) * | 2015-05-14 | 2015-08-19 | 无锡天脉聚源传媒科技有限公司 | Hot-spot video push method and apparatus |
CN105872790A (en) * | 2015-12-02 | 2016-08-17 | 乐视网信息技术(北京)股份有限公司 | Method and system for recommending audio/video program |
CN105898576A (en) * | 2016-06-17 | 2016-08-24 | 青岛海信传媒网络技术有限公司 | Data recommending method based on television application, and data server |
US20170155963A1 (en) * | 2015-12-01 | 2017-06-01 | Echostar Technologies L.L.C. | Recommend future video recordings for users from audiovisual content |
-
2017
- 2017-06-22 CN CN201710480351.0A patent/CN107295361B/en active Active
Patent Citations (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101094335A (en) * | 2006-06-20 | 2007-12-26 | 株式会社日立制作所 | TV program recommender and method thereof |
CN101001356A (en) * | 2006-12-30 | 2007-07-18 | 上海文广互动电视有限公司 | Contents supply system and method of network TV. |
US20100071005A1 (en) * | 2008-09-18 | 2010-03-18 | Yoshiaki Kusunoki | Program recommendation apparatus |
CN101998161A (en) * | 2009-08-14 | 2011-03-30 | Tcl集团股份有限公司 | Face recognition-based television program watching method |
US20120151370A1 (en) * | 2010-12-10 | 2012-06-14 | Wyse Technology Inc. | Methods and systems for remote desktop session redrawing via http headers |
CN103024464A (en) * | 2011-12-31 | 2013-04-03 | 中国科学院计算技术研究所 | System and method for providing information related to video playing content |
CN103428539A (en) * | 2012-05-15 | 2013-12-04 | 腾讯科技(深圳)有限公司 | Pushed information publishing method and device |
CN102957743A (en) * | 2012-10-18 | 2013-03-06 | 北京天宇朗通通信设备股份有限公司 | Data pushing method and device |
CN102984219A (en) * | 2012-11-13 | 2013-03-20 | 浙江大学 | Tourism mobile terminal information pushing method based on medial multi-dimensional content expression |
CN103164518A (en) * | 2013-03-06 | 2013-06-19 | 杭州九树网络科技有限公司 | Mobile terminal (MT) augmented reality application system and method |
CN103577516A (en) * | 2013-07-01 | 2014-02-12 | 北京百纳威尔科技有限公司 | Method and device for displaying contents |
CN103634617A (en) * | 2013-11-26 | 2014-03-12 | 乐视致新电子科技(天津)有限公司 | Video recommending method and device in intelligent television |
CN103618918A (en) * | 2013-11-27 | 2014-03-05 | 青岛海信电器股份有限公司 | Method and device for controlling display of smart television |
CN103716702A (en) * | 2013-12-17 | 2014-04-09 | 三星电子(中国)研发中心 | Television program recommendation device and method |
CN104010220A (en) * | 2014-04-30 | 2014-08-27 | 小米科技有限责任公司 | Method and device for providing content service |
CN104202718A (en) * | 2014-08-05 | 2014-12-10 | 百度在线网络技术(北京)有限公司 | Method and device for providing information for user |
CN104268187A (en) * | 2014-09-17 | 2015-01-07 | 合一网络技术(北京)有限公司 | User feedback based multi-scenario supported online content optimization system |
CN104301758A (en) * | 2014-10-10 | 2015-01-21 | 安徽华米信息科技有限公司 | Method, device and system for pushing videos |
CN104394471A (en) * | 2014-11-19 | 2015-03-04 | 四川长虹电器股份有限公司 | Method for intelligently recommending favorite program to user |
CN104853230A (en) * | 2015-05-14 | 2015-08-19 | 无锡天脉聚源传媒科技有限公司 | Hot-spot video push method and apparatus |
US20170155963A1 (en) * | 2015-12-01 | 2017-06-01 | Echostar Technologies L.L.C. | Recommend future video recordings for users from audiovisual content |
CN105872790A (en) * | 2015-12-02 | 2016-08-17 | 乐视网信息技术(北京)股份有限公司 | Method and system for recommending audio/video program |
CN105898576A (en) * | 2016-06-17 | 2016-08-24 | 青岛海信传媒网络技术有限公司 | Data recommending method based on television application, and data server |
Non-Patent Citations (1)
Title |
---|
龚静: "《中文文本聚类研究》", 31 March 2012, 中国传媒大学出版社 * |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107959865A (en) * | 2017-11-14 | 2018-04-24 | 广州虎牙信息科技有限公司 | Main broadcaster's method for pushing, device and computer equipment |
CN107948743A (en) * | 2017-11-29 | 2018-04-20 | 腾讯科技(深圳)有限公司 | Video pushing method and its device, storage medium |
CN109522493A (en) * | 2018-09-04 | 2019-03-26 | 西安艾润物联网技术服务有限责任公司 | Information-pushing method and Related product |
CN109522426A (en) * | 2018-12-05 | 2019-03-26 | 北京达佳互联信息技术有限公司 | Multi-medium data recommended method, device, equipment and computer readable storage medium |
CN109688458A (en) * | 2019-01-14 | 2019-04-26 | 四川长虹电器股份有限公司 | The implementation method of smart television cloud desktop operation system based on big data algorithm |
CN110046940A (en) * | 2019-04-22 | 2019-07-23 | 福建工程学院 | A kind of Ads on Vehicles personalized push method and device |
CN111143611A (en) * | 2019-12-31 | 2020-05-12 | 新疆联海创智信息科技有限公司 | Information acquisition method and device |
CN111143611B (en) * | 2019-12-31 | 2024-01-16 | 新疆联海创智信息科技有限公司 | Information acquisition method and device |
CN111866528A (en) * | 2020-04-30 | 2020-10-30 | 火币(广州)区块链科技有限公司 | Live program pushing method and readable storage medium |
WO2022000826A1 (en) * | 2020-06-28 | 2022-01-06 | 百度在线网络技术(北京)有限公司 | Video stream processing method and apparatus, and computer device and medium |
KR20220124813A (en) * | 2020-06-28 | 2022-09-14 | 바이두 온라인 네트웍 테크놀러지 (베이징) 캄파니 리미티드 | Video stream processing method and processing device, computer device, storage medium and computer program |
US20230224528A1 (en) * | 2020-06-28 | 2023-07-13 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method of processing video stream, computer device, and medium |
KR102655662B1 (en) | 2020-06-28 | 2024-04-05 | 바이두 온라인 네트웍 테크놀러지 (베이징) 캄파니 리미티드 | Video stream processing methods and processing devices, computer devices, storage media, and computer programs |
CN112632370A (en) * | 2020-12-08 | 2021-04-09 | 青岛海尔科技有限公司 | Method, device and equipment for article pushing |
CN113254419A (en) * | 2021-01-19 | 2021-08-13 | 青岛诺顿传媒有限公司 | Internet of things cloud platform management system and method based on big data micro-service |
Also Published As
Publication number | Publication date |
---|---|
CN107295361B (en) | 2019-07-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107295361B (en) | A kind of content delivery method | |
US10832738B2 (en) | Computerized system and method for automatically generating high-quality digital content thumbnails from digital video | |
CN107870959B (en) | Providing relevant video scenes in response to a video search query | |
CN108352174B (en) | Electronic device, storage device, and method for image processing | |
US10572565B2 (en) | User behavior models based on source domain | |
CN108028962B (en) | Processing video usage information to deliver advertisements | |
JP6110030B2 (en) | Multimedia resource recommendation method, apparatus, program, and recording medium | |
US11620678B2 (en) | Advertising method, device and system, and computer-readable storage medium | |
US9706008B2 (en) | Method and system for efficient matching of user profiles with audience segments | |
US8370337B2 (en) | Ranking search results using click-based data | |
CN107894998B (en) | Video recommendation method and device | |
CN109388760B (en) | Recommendation label obtaining method, media content recommendation method, device and storage medium | |
CN105847985A (en) | Video recommendation method and device | |
CN105373938A (en) | Method for identifying commodity in video image and displaying information, device and system | |
CN103885951A (en) | Graphics and text information releasing and generating method and graphics and text information releasing and generating device | |
CN103425670B (en) | A kind of method, apparatus and equipment providing a user content recommendation information | |
WO2016201800A1 (en) | Information acquisition method, server, terminal, and method and apparatus for constructing database | |
CN106326391A (en) | Method and device for recommending multimedia resources | |
Mei et al. | ImageSense: Towards contextual image advertising | |
US9449231B2 (en) | Computerized systems and methods for generating models for identifying thumbnail images to promote videos | |
WO2018205845A1 (en) | Data processing method, server, and computer storage medium | |
CN103577593A (en) | Method and system for video aggregation based on microblog hot topics | |
CN104185041B (en) | The automatic generation method and system of video interactive advertisement | |
CN107590267A (en) | Information-pushing method and device, terminal and readable storage medium storing program for executing based on picture | |
CN102930041A (en) | Retrieval result real-time updating method based on user behavior information and system thereof |
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 |