CN106600343A - Method and system for managing online video advertisement associated with video content - Google Patents
Method and system for managing online video advertisement associated with video content Download PDFInfo
- Publication number
- CN106600343A CN106600343A CN201611259468.8A CN201611259468A CN106600343A CN 106600343 A CN106600343 A CN 106600343A CN 201611259468 A CN201611259468 A CN 201611259468A CN 106600343 A CN106600343 A CN 106600343A
- Authority
- CN
- China
- Prior art keywords
- content
- video
- module
- targeted advertisements
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
- G06F16/43—Querying
- G06F16/435—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0242—Determining effectiveness of advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a method and system for managing online video advertisements associated with video content. The method includes the following steps: a video server receiving a broadcast request targeted at an object video transmitted by a client; the video server analyzing the content of each frame picture of the object video, extracting content information, and establishing a content information database; establishing an advertisement database having key word information; with content characteristics in the content information as key words, screening object advertisements in the advertisement database; collecting attention statistics on the screen object advertisements, and associating the object advertisement with the highest attention with the content information; and transmitting the object advertisement and the object video to the client. According to the invention, the method associates the video content with the advertisement so as to push the advertisement associated with the video content to views, and increases users' attention to advertisement. According to the invention, the method increases click rate of the advertisement, is conducive to the promotion of advertisement companies, and reduces the operation cost of the video services.
Description
Technical field
The present invention relates to Online Video service technology field, more particularly to a kind of Online Video advertisement of video content association
Management method and system.
Background technology
With the rise of the Internet, Internet advertising also has been widely used for each website, provides for web site operator
One good interests growth point.Usual way is advertisement putting to be carried out with Keywords matching strategy and is evaluated, i.e.,
The content of the page that the Advertisement Server of network side is browsed to user is analyzed, and extracts the key word for meeting condition, and
Key word is matched with advertisement in advertisement base, and the advertisement of matching is returned to into webpage, be then presented to the use for browsing
Family.
Between common advertising message matching, assessment so, many supported web page information do not support other video media forms
Advertisement, with certain limitation, additionally, some ad contents are not almost associated with video content, it is impossible to realize advertisement
Effectively click volume, causes profitability weak, directly jeopardizes the existence of video service website.Existing number of patent application
201110388765.3 the Online Video advertising management method of disclosed video content association, although it is embedding that it realizes video ads
Enter, ad content is associated with video, but by advertisement user cannot be attracted to click on, user clicks on broadcasting of the advertisement to video imitates
Fruit therefore effectively limits ad click amount without impact, additionally, the advertisement of the video website input in the technology is than more random,
Cannot realize effectively being pushed the higher advertisement of attention rate, so as to profitability relatively low, the video website operating cost of website
It is higher.
The content of the invention
In order to solve prior art although realize video ads be embedded in, ad content is associated with video, but cannot be led to
Crossing advertisement attracts user to click on, and user clicks on advertisement to the result of broadcast of video without impact, therefore effectively limits ad click
Amount, additionally, the advertisement of the video website input in the technology is than more random, it is impossible to which realization is had the higher advertisement of attention rate
Effect is pushed, profitability relatively low so as to website, the problems such as video website operating cost is higher, the invention provides one kind can be carried
The Online Video advertisement management method and system of the video content association of the effective click volume of advertisement in high video.
Concrete technical scheme of the present invention is as follows：
The invention provides a kind of video ads management method based on video content, the management method includes following step
Suddenly：
S1, video server receive the playing request for target video that client sends；
S2, video server carry out content analysis to each frame picture of the target video, extract content information, set up
Content information storehouse, the content information includes the positional information of content characteristic and the content characteristic in the stream of video frames；
S3, advertising database of the foundation with key word information；
S4, with the content characteristic in the content information in step S2 as key word, in the advertising database
Middle screening targeted advertisements；
S5, the targeted advertisements for filtering out are carried out attention rate statistics, and by targeted advertisements described in attention rate highest
Associate with the content information；
S6, the targeted advertisements are sent to the client with the target video.
Further, in step S2, video server carries out content analysis to each frame picture of the target video, tool
Body method includes：
S2-1：Each frame picture of target video described in Text region is obtaining the word content of the target video；
S2-2：Content characteristic is extracted in the word content to acquisition；
S2-3：Position of the content characteristic in the target video is carried out to encode forming position information；
S2-4：Positional information of the content characteristic with the content characteristic in the stream of video frames is associated in being formed
Appearance information, some content informations set up content information storehouse.
Further, the advertising database with key word information is set up in step S3 also includes that client demand updates tool
The step of having the advertising database of key word information.
Further, in step S5, the targeted advertisements for filtering out are carried out into attention rate statistics, and by attention rate highest
The targeted advertisements associate with the content information, concrete grammar includes：
S5-1：Some concern factors for evaluating the targeted advertisements are preset, and weight is given to the concern factor
Value, the concern factor includes number of clicks, number of visits or browsing time；
S5-2：The concern factor and the corresponding weighted value of the concern factor are instructed to convolutional neural networks model
Practice, obtain concern value model；
S5-3：The some described targeted advertisements for filtering out are separately input in the concern value model, the mesh is obtained
The concern value of mark advertisement；
S5-4：Some targeted advertisements are set up into the attention rate sequence table of sort descending according to the concern value；
S5-5：Targeted advertisements described in attention rate highest in the attention rate sequence table are associated with the content information.
Further, the advertisement management method is further comprising the steps of：
S7, the client are inserted into the targeted advertisements as wicket in the frame picture of the target video；
When S8, the viewing target video, the content letter of each frame picture in target video described in Text region
Breath, and the targeted advertisements of association are pushed.
Further, the management method also includes：When watching the target video, the video server is effectively recognized
Whether the targeted advertisements are clicked, when recognizing the targeted advertisements and being clicked, effectively improve adding for the target video
Carry or cache speed.
Present invention also offers a kind of video ads management system based on video content, including video server and with
Advertising database and client that the video server communicates, the advertising database internal memory contains some to be played wide
Accuse, the advertisement to be played contains keyword label, the video server includes memory module, the playing request for communicating
Receiver module, content analysis module；
Some videos to be played are preserved in the memory module；The playing request receiver module is used to receive client
The playing request for target video for sending；The content analysis module is used to enter each frame picture of the target video
Row content analysis, extract content information, set up content information storehouse；
The advertising database includes retrieval module, and the retrieval module is used to be analyzed according to the content analysis module
The content characteristic of the content information for arriving is key word, and in the advertising database targeted advertisements are screened；
The video server also includes relevance module, data transmission blocks, and the relevance module is used for institute
State the retrieval targeted advertisements that filter out of module to associate with the content information；
The data transmission blocks are used to the targeted advertisements are sent to the client with the target video.
Further, the content analysis module includes that the word recognition unit for communicating, feature extraction unit, position are compiled
Code unit, information synthesis unit；
The word recognition unit obtains the target video for recognizing each frame picture of the target video
Word content；The feature extraction unit is used to extract content characteristic in the word content to obtaining；It is described position encoded
Unit is used for the position to the content characteristic in the target video to carry out encoding forming position information；Described information synthesizes
Unit is used for the positional information by the content characteristic with the content characteristic in the stream of video frames and associates to form content letter
Breath, some content informations set up content information storehouse.
Further, the advertising database also includes factor presetting module, the weights communicated with the retrieval module
Model building module, concern value acquisition module, order module, screening module；
The factor presetting module is used to preset some concern factors for evaluating the targeted advertisements, and to the pass
The note factor gives weighted value；
The weights model building module is used for the concern factor and the corresponding weighted value of the concern factor to volume
Product neural network model is trained acquisition concern value model；
The concern value acquisition module is used to for some described targeted advertisements for filtering out to be separately input into the concern value
In model, the concern value of the targeted advertisements is obtained；
The order module is used to that some targeted advertisements to be set up the attention rate of sort descending according to the concern value
Sequence table；
The screening module is used to filter out targeted advertisements described in attention rate highest in the attention rate sequence table, and
Send to relevance module.
Beneficial effects of the present invention are as follows：The method that the present invention is provided can be associated video content with advertisement, from
And by the advertisement pushing related to video content to spectators, improve attention rate of the user to advertisement, so as to allow users to from
The advertisement product of decorrelation, the method not only increases ad click amount, is conducive to gray popularization, and reduce video
Service Operation cost, it is practical；Additionally, the system structure that the present invention is provided is simple, can be effectively higher by user's attention rate
Advertisement be associated with video related content, structure design is simple, easy to use.
Description of the drawings
Fig. 1 is a kind of method flow schematic diagram of the video ads management method based on video content described in embodiment 1；
Fig. 2 shows for the flow process of step S2 in a kind of video ads management method based on video content described in embodiment 2
It is intended to；
Fig. 3 shows for the flow process of step S5 in a kind of video ads management method based on video content described in embodiment 2
It is intended to；
Fig. 4 is a kind of structural representation of the video ads management system based on video content described in embodiment 4；
Fig. 5 is a kind of structured flowchart of the video ads management system based on video content described in embodiment 4；
Fig. 6 is content analysis module in a kind of video ads management system based on video content described in embodiment 5
Structured flowchart；
Fig. 7 is a kind of structured flowchart of the video ads management system based on video content described in embodiment 5.
Wherein：1st, video server；101st, memory module；102nd, playing request receiver module；103rd, content analysis module；
1031st, word recognition unit；1032nd, feature extraction unit；1033rd, position encoded unit；1034th, information synthesis unit；104、
Relevance module；105th, data transmission blocks；2nd, advertising database；201st, module is retrieved；202nd, factor presetting module；203、
Weights model building module；204th, concern value acquisition module；205th, order module；206th, screening module；3rd, client.
Specific embodiment
Below in conjunction with the accompanying drawings the present invention is described in further detail with following examples.
Embodiment 1
As shown in figure 1, the embodiment of the present invention 1 provides a kind of video ads management method based on video content, it is described
Management method is comprised the following steps：
S1, video server 1 receive the playing request for target video that client 3 sends；User passes through client 3
The request for playing video is sent to the video server 1, video server 1 is received after the certification to subscription client 3
Playing request.
S2, each frame picture of 1 pair of target video of video server carry out content analysis, extract content information, build
Vertical content information storehouse, the content information includes the position letter of content characteristic and the content characteristic in the stream of video frames
Breath；
Video server 1 receive video upload when, one by one by each frame picture of Text region uploaded videos
Hold, and content is analyzed, extract content information, set up content information storehouse, the content information of each frame picture includes frame
Content characteristic and the frame picture in picture is located at the positional information in the stream of video frames, and is protected according to positional information
Deposit.
S3, advertising database 2 of the foundation with key word information；The internal memory of advertising database 2 contains some advertisers and carries
For advertising items, each advertising items is stored in advertising database 2 by search engine of key word, during retrieval advertisement,
Advertisement search is carried out by search key, convenient inquiry improves search efficiency.
S4, with the content characteristic in the content information in step S2 as key word, in the advertising database 2
Middle screening targeted advertisements；By obtaining key word in the content information in the frame picture of video, by the key word in advertisement
The advertising items related to the content information in frame picture are inquired about in data base 2.
S5, the targeted advertisements for filtering out are carried out attention rate statistics, and by targeted advertisements described in attention rate highest
Associate with the content information；If retrieving many advertisements, targeted advertisements are arranged by attention rate, by attention rate
Higher targeted advertisements are associated with the content information of the frame picture, so as to when video playback, when there is relevant content information,
Natural advertisement, so as to the higher targeted advertisements of attention rate are pushed to into user, effectively improves the click volume of advertisement.
S6, the targeted advertisements are sent to the client 3 with the target video.Client 3 receives targeted advertisements
And target video, when target video is played, the targeted advertisements automatic push associated with the frame picture of video go out, so as to be shown to
User.
The present invention not only realizes video ads and is embedded in, and the advertisement for pushing is associated with content information in video, effectively
Attract user's concern advertisement, by attention rate of the historic user to advertisement, associate attention rate higher mesh during video playback first
Mark advertisement, so as to improve click volume of the user to advertisement, is easy to gray advertisement promotion, improves user to advertisement
Solution, while improve the profitability of website, reduces the operating cost of video website, realizes win-win situation.
Embodiment 2
As shown in Fig. 2 the embodiment of the present invention 2 is on the basis of embodiment 1, and in further defining step S2, video clothes
Each frame picture of business 1 pair of target video of device carries out content analysis, and concrete grammar includes：
S2-1：Each frame picture of target video described in Text region is obtaining the word content of the target video；It is logical
Cross the word content of each frame picture of Text region video.
S2-2：Content characteristic is extracted in the word content to acquisition；The word that key is extracted from word content is special
Levy, content characteristic can be key word or key word.
S2-3：Position of the content characteristic in the target video is carried out to encode forming position information；To extract
Key word or the position of the content characteristic with corresponding frame of video in the video flowing such as key word encoded, determine that position is believed
Breath, so as to efficient association.
S2-4：Positional information of the content characteristic with the content characteristic in the stream of video frames is associated in being formed
Appearance information, some content informations set up content information storehouse, and content information includes content characteristic and positional information, positional information
As content characteristic in stream of video frames corresponding frame picture it is position encoded, in case information entanglement.
Further, the advertising database 2 with key word information is set up in step S3 also to update including the demand of client 3
The step of advertising database 2 with key word information.When some key word information of demand of client 3, if ad data
There is no advertisement associated therewith or similar in storehouse 2, then need constantly to update advertising database 2, it is continuous according to video content
By the abundantization of advertising database 2, consequently facilitating advertisement promotion.
As shown in figure 3, needing further exist for explanation, in order to improve attention rate of the user to advertisement, in step S5, will sieve
The targeted advertisements selected carry out attention rate statistics, and targeted advertisements described in attention rate highest and the content information are closed
Connection, concrete grammar includes：
S5-1：Some concern factors for evaluating the targeted advertisements are preset, and weight is given to the concern factor
Value, the concern factor includes number of clicks, number of visits or browsing time；The concern factor of advertisement can be used for evaluating advertisement
Attention rate, respectively to pay close attention to the factor setting weighted value.
S5-2：The concern factor and the corresponding weighted value of the concern factor are instructed to convolutional neural networks model
Practice, obtain concern value model；The concern factor and corresponding weighted value are obtained into concern value module by convolutional neural networks training,
It is trained by convolutional neural networks, it is possible to increase concern value operation efficiency, so as to effectively judge the attention rate of advertisement.
S5-3：The some described targeted advertisements for filtering out are separately input in the concern value model, the mesh is obtained
The concern value of mark advertisement；
S5-4：Some targeted advertisements are set up into the attention rate sequence table of sort descending according to the concern value；
S5-5：Targeted advertisements described in attention rate highest in the attention rate sequence table are associated with the content information.
When screening advertisement in advertising database 2 by key word, each sieve can quickly be calculated by concern value module
The concern value of the advertisement selected, then some targeted advertisements are set up the attention rate sequence of sort descending according to the concern value
List, when advertisement is associated with video content information, by the higher advertisement of attention rate in attention rate sequence table and video content information
Association.
Embodiment 3
The embodiment of the present invention 3 is further defined on the basis of embodiment 1, and the advertisement management method also includes following
Step：
S7, the client 3 are inserted into the targeted advertisements as wicket in the frame picture of the target video；
When S8, the viewing target video, the content letter of each frame picture in target video described in Text region
Breath, and the targeted advertisements of association are pushed.
When client 3 carries out video playback, by the advertisement of association with the spring window shape formula and the frame of target video of wicket
Picture is associated, and when a certain frame picture is played to, automatically the advertisement spring window of spring association, carries out advertisement pushing.
The present invention is further defined, and the management method also includes：When watching the target video, the Video service
Device 1 effectively recognizes whether the targeted advertisements are clicked, when recognizing the targeted advertisements and being clicked, effectively improves the mesh
The loading of mark video or caching speed.In order to encourage user to click on targeted advertisements, then when user clicks on targeted advertisements, Neng Gouyou
Effect improves the loading of video or the speed of caching.
Embodiment 4
As shown in Figures 4 and 5, present invention also offers a kind of video ads management system based on video content, including regarding
Frequency server 1 and the advertising database 2 communicated with the video server 1 and client 3, the internal memory of the advertising database 2
Some advertisements to be played are contained, the advertisement to be played contains keyword label, and the video server 1 includes what is communicated
Memory module 101, playing request receiver module 102, content analysis module 103, the client 3 is smart mobile phone, computer etc.
Terminal unit；
Some videos to be played are preserved in the memory module 101；The playing request receiver module 102 is used to receive
The playing request for target video that client 3 sends；The content analysis module 103 is used for each of the target video
Individual frame picture carries out content analysis, extracts content information, sets up content information storehouse；
The advertising database 2 includes retrieval module 201, and the retrieval module 201 is used for according to the content analysis mould
The content characteristic of the content information that the analysis of block 103 is obtained is key word, and in the advertising database 2 target is screened
Advertisement；
The video server 1 also includes relevance module 104, data transmission blocks 105, the relevance module
104 targeted advertisements filtered out for the retrieval module 201 are associated with the content information；The data transmission blocks
105 are used to the targeted advertisements are sent to the client 3 with the target video.
The system that the present invention is provided can be processed video by video server 1, and by advertising database 2
Advertisement is associated with the frame picture of video, and advertisement is inserted in video in the form of the window that bounces during the viewing video of client 3,
Effectively realize advertisement to be embedded in, additionally, advertising database 2 can effectively calculate the concern value of some advertisements, and will can pay close attention to
The higher advertisement of value is associated with the frame picture of video, effectively increases ad click amount, and simultaneity factor structure design is simple, operation
Cost is relatively low.
Embodiment 5
As shown in fig. 6, the embodiment of the present invention 5 further defines the content analysis module on the basis of embodiment 4
103 include that the word recognition unit 1031 for communicating, feature extraction unit 1032, position encoded unit 1033, information synthesize single
Unit 1034；
The word recognition unit 1031 obtains the target and regards for recognizing each frame picture of the target video
The word content of frequency；The feature extraction unit 1032 is used to extract content characteristic in the word content to obtaining；It is described
Position encoded unit 1033 is used for the position to the content characteristic in the target video to carry out encoding forming position information；
Described information synthesis unit 1034 is used for the letter of the position by the content characteristic and the content characteristic in the stream of video frames
Breath association forms content information, and some content informations set up content information storehouse.
The content analysis module 103 passes through word recognition unit 1031, feature extraction unit 1032, position encoded unit
1033rd, information synthesis unit 1034 can effectively by the content information of each frame picture in Text region video.
As shown in fig. 7, needing it is further noted that the advertising database 2 also includes and the retrieval phase of module 201
The factor presetting module 202 of communication, weights model building module 203, concern value acquisition module 204, order module 205, screening
Module 206；
The factor presetting module 202 is used to preset some concern factors for evaluating the targeted advertisements, and to institute
State the concern factor and give weighted value；The weights model building module 203 is used for the concern factor and the concern factor
Corresponding weighted value is trained acquisition concern value model to convolutional neural networks model；The concern value acquisition module 204 is used
In being separately input into some described targeted advertisements for filtering out in the concern value model, the concern of the targeted advertisements is obtained
Value；The order module 205 is used to that some targeted advertisements to be set up the attention rate sequence of sort descending according to the concern value
List；The screening module 206 is used to filter out targeted advertisements described in attention rate highest in the attention rate sequence table, and
Send to relevance module 104.
By the way that the concern factor and the corresponding weighted value of the concern factor are input into convolutional Neural net in the technical program
Can effectively obtain paying close attention to value model in network model, by paying close attention to value model the concern value of a certain advertisement can be quickly calculated, it is real
The judgement of ad attention is showed, consequently facilitating the higher advertisement of attention rate is associated with video, and then has been pushed to user, met
The demand of user, improves gray income, reduces video website operating cost.
The present invention is not limited to above-mentioned preferred forms, and anyone can show that other are various under the enlightenment of the present invention
The product of form, however, make any change in its shape or structure, it is every with skill identical or similar to the present application
Art scheme, is within the scope of the present invention.
Claims (9)
1. a kind of video ads management method based on video content, it is characterised in that the management method is comprised the following steps：
S1, video server (1) receive the playing request for target video that client (3) sends；
S2, video server (1) carry out content analysis to each frame picture of the target video, extract content information, set up
Content information storehouse, the content information includes the positional information of content characteristic and the content characteristic in the stream of video frames；
S3, advertising database (2) of the foundation with key word information；
S4, with the content characteristic in the content information in step S2 as key word, in the advertising database (2)
Screening targeted advertisements；
S5, the targeted advertisements for filtering out are carried out attention rate statistics, and by targeted advertisements described in attention rate highest and institute
State content information association；
S6, the targeted advertisements and the target video are sent to the client (3).
2. the video ads management method of video content is based on as claimed in claim 1, it is characterised in that in step S2, depending on
Frequency server (1) carries out content analysis to each frame picture of the target video, and concrete grammar includes：
S2-1：Each frame picture of target video described in Text region is obtaining the word content of the target video；
S2-2：Content characteristic is extracted in the word content to acquisition；
S2-3：Position of the content characteristic in the target video is carried out to encode forming position information；
S2-4：Positional information of the content characteristic with the content characteristic in the stream of video frames is associated to form content letter
Breath, some content informations set up content information storehouse.
3. the video ads management method of video content is based on as claimed in claim 1, it is characterised in that set up in step S3
Advertising database (2) with key word information also includes that client (3) demand updates the ad data with key word information
The step of storehouse (2).
4. the video ads management method of video content is based on as claimed in claim 1, it is characterised in that in step S5, will
The targeted advertisements for filtering out carry out attention rate statistics, and by targeted advertisements described in attention rate highest and the content information
Association, concrete grammar includes：
S5-1：Some concern factors for evaluating the targeted advertisements are preset, and weighted value, institute are given to the concern factor
Stating the concern factor includes number of clicks, number of visits or browsing time；
S5-2：The concern factor and the corresponding weighted value of the concern factor are trained to convolutional neural networks model,
Obtain concern value model；
S5-3：The some described targeted advertisements for filtering out are separately input in the concern value model, the target is obtained wide
The concern value of announcement；
S5-4：Some targeted advertisements are set up into the attention rate sequence table of sort descending according to the concern value；
S5-5：Targeted advertisements described in attention rate highest in the attention rate sequence table are associated with the content information.
5. the video ads management method of video content is based on as claimed in claim 1, it is characterised in that the advertising management
Method is further comprising the steps of：
S7, the client (3) are inserted into the targeted advertisements as wicket in the frame picture of the target video；
When S8, the viewing target video, the content information of each frame picture in target video described in Text region, and
The targeted advertisements of association are pushed.
6. the video ads management method of video content is based on as claimed in claim 5, it is characterised in that the management method
Also include：When watching the target video, the video server (1) effectively recognizes whether the targeted advertisements are clicked, when
Recognize the targeted advertisements it is clicked when, effectively improve the target video loading or caching speed.
7. a kind of video ads management system based on video content, it is characterised in that including video server (1) and with institute
Advertising database (2) and client (3) that video server (1) communicates are stated, advertising database (2) internal memory contains some
Advertisement to be played, the advertisement to be played contains keyword label, and the video server (1) is including the storage mould for communicating
Block (101), playing request receiver module (102), content analysis module (103)；
Some videos to be played are preserved in the memory module (101)；The playing request receiver module (102) is for receiving
The playing request for target video that the client (3) sends；The content analysis module (103) is for the target
Each frame picture of video carries out content analysis, extracts content information, sets up content information storehouse；
The advertising database (2) includes retrieval module (201), and retrieval module (201) is for according to the content analysis
The content characteristic of the content information that module (103) analysis is obtained is key word, the sieve in the advertising database (2)
Select targeted advertisements；
The video server (1) also includes relevance module (104), data transmission blocks (105), the relevance mould
Block (104) is associated for the targeted advertisements that retrieval module (201) filters out with the content information；The data are sent out
Module (105) is sent for the targeted advertisements and the target video to be sent to the client (3).
8. the video ads management system of video content is based on as claimed in claim 7, it is characterised in that the content analysis
Module (103) includes word recognition unit (1031), feature extraction unit (1032), the position encoded unit for communicating
(1033), information synthesis unit (1034)；
The word recognition unit (1031) obtains the target video for recognizing each frame picture of the target video
Word content；The feature extraction unit (1032) in the word content for obtaining for extracting content characteristic；It is described
Position encoded unit (1033) carries out encoding forming position letter for the position to the content characteristic in the target video
Breath；Described information synthesis unit (1034) is for the position by the content characteristic and the content characteristic in the stream of video frames
Put information association and form content information, some content informations set up content information storehouse.
9. the video ads management system of video content is based on as claimed in claim 7, it is characterised in that the ad data
Storehouse (2) also includes factor presetting module (202), the weights model building module communicated with retrieval module (201)
(203), concern value acquisition module (204), order module (205), screening module (206)；
The factor presetting module (202) for presetting some concern factors for evaluating the targeted advertisements, and to described
The concern factor gives weighted value；
The weights model building module (203) for by it is described concern the factor and the corresponding weighted value of the concern factor to volume
Product neural network model is trained acquisition concern value model；
The concern value acquisition module (204) by some described targeted advertisements for filtering out for being separately input into the concern value
In model, the concern value of the targeted advertisements is obtained；
The order module (205) is for some targeted advertisements to be set up the attention rate of sort descending according to the concern value
Sequence table；
The screening module (206) for filtering out targeted advertisements described in attention rate highest in the attention rate sequence table,
And send to relevance module (104).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611259468.8A CN106600343B (en) | 2016-12-30 | 2016-12-30 | Video content associated online video advertisement management method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611259468.8A CN106600343B (en) | 2016-12-30 | 2016-12-30 | Video content associated online video advertisement management method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106600343A true CN106600343A (en) | 2017-04-26 |
| CN106600343B CN106600343B (en) | 2020-02-14 |
Family
ID=58582793
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611259468.8A Active CN106600343B (en) | 2016-12-30 | 2016-12-30 | Video content associated online video advertisement management method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106600343B (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107657004A (en) * | 2017-09-21 | 2018-02-02 | 广州华多网络科技有限公司 | Video recommendation method, system and equipment |
| 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 |
| CN108108996A (en) * | 2017-11-29 | 2018-06-01 | 北京百度网讯科技有限公司 | Advertisement placement method, device, computer equipment and readable medium in video |
| CN108184153A (en) * | 2017-12-29 | 2018-06-19 | 伟乐视讯科技股份有限公司 | A kind of advertisement insertion system to match with video content and method |
| CN108259949A (en) * | 2018-02-11 | 2018-07-06 | 北京未来媒体科技股份有限公司 | Method, apparatus and electronic equipment are recommended in a kind of advertisement |
| CN108681606A (en) * | 2018-05-25 | 2018-10-19 | 广州钱柜软件科技有限公司 | A kind of storage of the movie program based on big data and extracting method |
| CN109670078A (en) * | 2018-12-21 | 2019-04-23 | 深圳创维数字技术有限公司 | A kind of method, apparatus, equipment and the storage medium of determining video display sequence |
| CN109934611A (en) * | 2017-12-19 | 2019-06-25 | 腾讯科技（深圳）有限公司 | A kind of advertisement placement method, device, equipment and computer storage medium |
| CN110189181A (en) * | 2019-06-10 | 2019-08-30 | 深圳市云企汇财税顾问有限公司 | A kind of accounting system benefited for the advertisement browsing of Online Video APP |
| CN110278466A (en) * | 2019-06-06 | 2019-09-24 | 浙江口碑网络技术有限公司 | Put-on method, device and the equipment of short video ads |
| CN110413114A (en) * | 2019-07-22 | 2019-11-05 | 北京达佳互联信息技术有限公司 | Interaction control method and device under video scene, server, readable storage medium storing program for executing |
| CN110442825A (en) * | 2019-08-13 | 2019-11-12 | 连尚（新昌）网络科技有限公司 | The method and apparatus of information for rendering |
| CN110717790A (en) * | 2019-10-14 | 2020-01-21 | 上海掌门科技有限公司 | Method and equipment for viewing media files |
| CN111263203A (en) * | 2020-02-28 | 2020-06-09 | 宋秀梅 | Video advertisement push priority analysis system |
| CN111709762A (en) * | 2020-06-09 | 2020-09-25 | 上海极链网络科技有限公司 | Information matching degree evaluation method, device, equipment and storage medium |
| CN111753135A (en) * | 2020-05-21 | 2020-10-09 | 北京达佳互联信息技术有限公司 | Video display method, device, terminal, server, system and storage medium |
| CN112052353A (en) * | 2020-07-24 | 2020-12-08 | 广州阿凡提电子科技有限公司 | Advertisement video retrieval method and intelligent terminal |
| CN112364056A (en) * | 2020-10-29 | 2021-02-12 | 浙江原初数据科技有限公司 | Automatic fluorescence map playing system and method applied to real-time big data scene |
| CN112822551A (en) * | 2020-02-28 | 2021-05-18 | 宋秀梅 | Video advertisement push priority analysis method |
| CN113055740A (en) * | 2020-04-26 | 2021-06-29 | 杜达亮 | Method and system for identifying and pasting object in video |
| CN113191811A (en) * | 2021-05-10 | 2021-07-30 | 武汉埸葵电子商务有限公司 | Intelligent advertisement pushing method and device and computer readable storage medium |
| CN113888221A (en) * | 2021-10-09 | 2022-01-04 | 北京电子科技职业学院 | Internet platform for sharing content and income |
| CN116614679A (en) * | 2023-05-04 | 2023-08-18 | 武汉精阅数字传媒科技有限公司 | Optimization processing method and system for short video advertisement delivery |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101035294A (en) * | 2007-04-13 | 2007-09-12 | 深圳市融合视讯科技有限公司 | Network advertisement inter-broadcasting method in the video program |
| CN101072340A (en) * | 2007-06-25 | 2007-11-14 | 孟智平 | Method and system for adding advertising information in flow media |
| US20080109844A1 (en) * | 2006-11-02 | 2008-05-08 | Adbrite, Inc. | Playing video content with advertisement |
| CN101184248A (en) * | 2006-12-30 | 2008-05-21 | 腾讯科技（深圳）有限公司 | Method and device for generating video content with advertisement |
| US20110184807A1 (en) * | 2010-01-28 | 2011-07-28 | Futurewei Technologies, Inc. | System and Method for Filtering Targeted Advertisements for Video Content Delivery |
| CN102523533A (en) * | 2011-11-30 | 2012-06-27 | 江苏奇异点网络有限公司 | Management method of online video advertisement related to video content |
| CN104469437A (en) * | 2014-12-23 | 2015-03-25 | 小米科技有限责任公司 | Advertisement pushing method and device |
-
2016
- 2016-12-30 CN CN201611259468.8A patent/CN106600343B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080109844A1 (en) * | 2006-11-02 | 2008-05-08 | Adbrite, Inc. | Playing video content with advertisement |
| CN101184248A (en) * | 2006-12-30 | 2008-05-21 | 腾讯科技（深圳）有限公司 | Method and device for generating video content with advertisement |
| CN101035294A (en) * | 2007-04-13 | 2007-09-12 | 深圳市融合视讯科技有限公司 | Network advertisement inter-broadcasting method in the video program |
| CN101072340A (en) * | 2007-06-25 | 2007-11-14 | 孟智平 | Method and system for adding advertising information in flow media |
| US20110184807A1 (en) * | 2010-01-28 | 2011-07-28 | Futurewei Technologies, Inc. | System and Method for Filtering Targeted Advertisements for Video Content Delivery |
| CN102523533A (en) * | 2011-11-30 | 2012-06-27 | 江苏奇异点网络有限公司 | Management method of online video advertisement related to video content |
| CN104469437A (en) * | 2014-12-23 | 2015-03-25 | 小米科技有限责任公司 | Advertisement pushing method and device |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107657004A (en) * | 2017-09-21 | 2018-02-02 | 广州华多网络科技有限公司 | Video recommendation method, system and equipment |
| CN108108996A (en) * | 2017-11-29 | 2018-06-01 | 北京百度网讯科技有限公司 | Advertisement placement method, device, computer equipment and readable medium in video |
| 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 |
| CN109934611A (en) * | 2017-12-19 | 2019-06-25 | 腾讯科技（深圳）有限公司 | A kind of advertisement placement method, device, equipment and computer storage medium |
| CN109934611B (en) * | 2017-12-19 | 2022-11-29 | 腾讯科技（深圳）有限公司 | Advertisement putting method, device, equipment and computer storage medium |
| CN108184153A (en) * | 2017-12-29 | 2018-06-19 | 伟乐视讯科技股份有限公司 | A kind of advertisement insertion system to match with video content and method |
| CN108259949A (en) * | 2018-02-11 | 2018-07-06 | 北京未来媒体科技股份有限公司 | Method, apparatus and electronic equipment are recommended in a kind of advertisement |
| CN108681606B (en) * | 2018-05-25 | 2021-10-26 | 广州钱柜软件科技有限公司 | Big data-based storage and extraction method for movie programs |
| CN108681606A (en) * | 2018-05-25 | 2018-10-19 | 广州钱柜软件科技有限公司 | A kind of storage of the movie program based on big data and extracting method |
| CN109670078A (en) * | 2018-12-21 | 2019-04-23 | 深圳创维数字技术有限公司 | A kind of method, apparatus, equipment and the storage medium of determining video display sequence |
| CN110278466A (en) * | 2019-06-06 | 2019-09-24 | 浙江口碑网络技术有限公司 | Put-on method, device and the equipment of short video ads |
| CN110278466B (en) * | 2019-06-06 | 2021-08-06 | 浙江口碑网络技术有限公司 | Short video advertisement putting method, device and equipment |
| CN110189181A (en) * | 2019-06-10 | 2019-08-30 | 深圳市云企汇财税顾问有限公司 | A kind of accounting system benefited for the advertisement browsing of Online Video APP |
| CN110413114A (en) * | 2019-07-22 | 2019-11-05 | 北京达佳互联信息技术有限公司 | Interaction control method and device under video scene, server, readable storage medium storing program for executing |
| CN110442825A (en) * | 2019-08-13 | 2019-11-12 | 连尚（新昌）网络科技有限公司 | The method and apparatus of information for rendering |
| CN110717790A (en) * | 2019-10-14 | 2020-01-21 | 上海掌门科技有限公司 | Method and equipment for viewing media files |
| WO2021073454A1 (en) * | 2019-10-14 | 2021-04-22 | 上海掌门科技有限公司 | Method and apparatus for viewing media file |
| CN111263203A (en) * | 2020-02-28 | 2020-06-09 | 宋秀梅 | Video advertisement push priority analysis system |
| CN112822551A (en) * | 2020-02-28 | 2021-05-18 | 宋秀梅 | Video advertisement push priority analysis method |
| CN112822551B (en) * | 2020-02-28 | 2022-09-02 | 福州灰度科技有限公司 | Video advertisement push priority analysis method |
| CN113055740A (en) * | 2020-04-26 | 2021-06-29 | 杜达亮 | Method and system for identifying and pasting object in video |
| CN111753135A (en) * | 2020-05-21 | 2020-10-09 | 北京达佳互联信息技术有限公司 | Video display method, device, terminal, server, system and storage medium |
| CN111753135B (en) * | 2020-05-21 | 2024-02-06 | 北京达佳互联信息技术有限公司 | Video display method, device, terminal, server, system and storage medium |
| CN111709762A (en) * | 2020-06-09 | 2020-09-25 | 上海极链网络科技有限公司 | Information matching degree evaluation method, device, equipment and storage medium |
| CN112052353A (en) * | 2020-07-24 | 2020-12-08 | 广州阿凡提电子科技有限公司 | Advertisement video retrieval method and intelligent terminal |
| CN112364056A (en) * | 2020-10-29 | 2021-02-12 | 浙江原初数据科技有限公司 | Automatic fluorescence map playing system and method applied to real-time big data scene |
| CN113191811B (en) * | 2021-05-10 | 2022-07-01 | 北京顶当互动科技有限公司 | Intelligent advertisement pushing method and device and computer readable storage medium |
| CN113191811A (en) * | 2021-05-10 | 2021-07-30 | 武汉埸葵电子商务有限公司 | Intelligent advertisement pushing method and device and computer readable storage medium |
| CN113888221A (en) * | 2021-10-09 | 2022-01-04 | 北京电子科技职业学院 | Internet platform for sharing content and income |
| CN116614679A (en) * | 2023-05-04 | 2023-08-18 | 武汉精阅数字传媒科技有限公司 | Optimization processing method and system for short video advertisement delivery |
| CN116614679B (en) * | 2023-05-04 | 2024-02-09 | 杭州元媒科技有限公司 | Optimization processing method and system for short video advertisement delivery |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106600343B (en) | 2020-02-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106600343A (en) | Method and system for managing online video advertisement associated with video content | |
| CN106561054B (en) | Recommend method and system in a kind of live streaming room for webcast website | |
| CN104699705B (en) | Information-pushing method, server and system | |
| CN103051930B (en) | Based on mobile video recommend method and the system of flow analysis and user behavior analysis | |
| CN101690105B (en) | Method and system for providing targeted information using profile attributes with variable confidence levels in a mobile environment | |
| CN103220305B (en) | Network media information share treatment system and processing method | |
| CN101561825B (en) | Media technology platform system, data acquisition system and network content supplying method | |
| CN105046600A (en) | Personalized information recommendation method and system of televisions for hotels | |
| US20110218859A1 (en) | Method, Apparatus and System for Increasing Website Data Transfer Speed | |
| CN100595765C (en) | Medium player based key words content issue method and system | |
| CN103686375B (en) | Video sharing method and device | |
| US20020038456A1 (en) | Method and system for the automatic production and distribution of media content using the internet | |
| CN107105012A (en) | User profile generation architecture for mobile content-message targeting | |
| CN106504099A (en) | A kind of system for building user's portrait | |
| CN103106208A (en) | Streaming media content recommendation method and system in mobile internet | |
| CN105046601A (en) | User data processing method and system | |
| CN101511055A (en) | Method and device for delivering advertisement | |
| WO2008125038A1 (en) | Method, system and server for transmitting advertisement based on user feature | |
| CN102360364A (en) | Automatic application recommendation method and device | |
| CN101141484A (en) | Method, device and system of processing network directional data | |
| CN101472223A (en) | Method, system and device for embedding advertisement | |
| CN102067631A (en) | System and method for determination and display of personalized distance | |
| CN102298616A (en) | Method and device for providing related sub links in search result | |
| CN101431485A (en) | Method and system for automatically recommending internet information | |
| CN102084387A (en) | Targeted television advertisements selected on the basis of an online user profile and presented with television programs or channels related to that profile |
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 |