CN110290403A - Network video bumper advertisements playback method and system - Google Patents
Network video bumper advertisements playback method and system Download PDFInfo
- Publication number
- CN110290403A CN110290403A CN201910610717.0A CN201910610717A CN110290403A CN 110290403 A CN110290403 A CN 110290403A CN 201910610717 A CN201910610717 A CN 201910610717A CN 110290403 A CN110290403 A CN 110290403A
- Authority
- CN
- China
- Prior art keywords
- source
- advertisement
- real
- matching degree
- highest
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000000007 visual effect Effects 0.000 claims description 21
- 238000012552 review Methods 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 6
- 235000013399 edible fruits Nutrition 0.000 claims description 2
- 206010049976 Impatience Diseases 0.000 abstract description 7
- 239000000284 extract Substances 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000013361 beverage Nutrition 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 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]
- H04N21/20—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
- H04N21/23424—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving splicing one content stream with another content stream, e.g. for inserting or substituting an advertisement
-
- 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
- H04N21/266—Channel or content management, e.g. generation and management of keys and entitlement messages in a conditional access system, merging a VOD unicast channel into a multicast channel
- H04N21/2668—Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4662—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms
- H04N21/4665—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms involving classification methods, e.g. Decision trees
-
- 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
- H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
- H04N21/4756—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for rating content, e.g. scoring a recommended movie
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/81—Monomedia components thereof
- H04N21/812—Monomedia components thereof involving advertisement data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/81—Monomedia components thereof
- H04N21/8126—Monomedia components thereof involving additional data, e.g. news, sports, stocks, weather forecasts
- H04N21/8133—Monomedia components thereof involving additional data, e.g. news, sports, stocks, weather forecasts specifically related to the content, e.g. biography of the actors in a movie, detailed information about an article seen in a video program
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Marketing (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The present invention provides a kind of network video bumper advertisements playback method and system, is related to technical field of network video.The present invention is by classifying to advertisement source and real-time video source, the highest advertisement source of matching degree is intercutted for real-time video source, the intrinsic advertisement in original broadcast medium is replaced, changes the unreasonable situation of advertisement pushing in traditional broadcast media, and then the user experience is improved.The present invention adds comment text related with commodity in the advertisement source period in the form of barrage simultaneously, high degree evokes the interest of user, user is effectively relieved and is watching the impatience generated when advertisement, improve user's viewing experience, user is reduced to the avoidance degree of advertisement, improves the validity of advertisement broadcasting.
Description
Technical field
The present invention relates to technical field of network video, and in particular to a kind of network video bumper advertisements playback method and is
System.
Background technique
With the development of mobile technology and portable device, network video, which has become, meets personal information and entertainment requirements
Ideal style.Current video website, in order to increase the income of website usually before target video starts or be playing
When intercut the advertisement video of particular vendor.
Existing video website generally can force user to finish watching video bumper advertisements, unless user charges become video website
Member, skip advertising service by purchase and can just be directly entered positive.
However, in this fashion, user passively watches advertisement, and as advertisement source duration is increasingly longer, user experience
Also worse and worse, it is relatively low to play validity for advertisement.
Summary of the invention
(1) the technical issues of solving
In view of the deficiencies of the prior art, the present invention provides a kind of network video bumper advertisements playback method and system, solutions
Advertisement of having determined plays the low technical problem of validity.
(2) technical solution
In order to achieve the above object, the present invention is achieved by the following technical programs:
The present invention provides a kind of network video bumper advertisements playback method, and the method is executed by video playing platform, packet
Include following steps:
S1, multiple advertisement sources are obtained, and ad classification is carried out to the multiple advertisement source, obtain ad classification as a result, base
Ad classification database is constructed in the ad classification result；
S2, classify to real-time video source, obtain visual classification result；
S3, found out from the ad classification database with the highest advertisement source of visual classification result matching degree,
And the highest advertisement source of the matching degree is dissolved into the real-time video source, it obtains incorporating the highest advertisement source of matching degree
Real-time video source；
S4, the real-time video source based on the involvement highest advertisement source of matching degree, it is highest wide to calculate the matching degree
The similarity of the comment text of commodity involved in announcement source；
S5, the duration based on similarity and the highest advertisement source of matching degree select several comment texts；It will choose
Comment text be loaded into the form of barrage in the highest advertisement source of the matching degree, obtain real-time view of the advertisement source with barrage
Frequency source；
S6, the advertisement source is recompiled and is exported with the real-time video source of barrage.
Preferably, the step S1 specifically:
S101, multiple advertisement sources are obtained and traverse the multiple advertisement source automatically, extract the advertisement of the multiple advertisement source
Source key frame；
S102, it is based on the advertisement source key-frame extraction characteristic of advertisement；
S103, classified based on the characteristic of advertisement to the multiple advertisement source, obtain ad classification result；
S104, corresponding label information is added based on the ad classification result, constructs ad classification database.
Preferably, the step S2 specifically:
S201, real-time video source is decoded；
S202, video source key frame is extracted based on decoded real-time video source；
S203, video source key-frame extraction video features are based on；
S204, classified based on the video features to the video source, obtain visual classification result.
Preferably, the step S3 specifically:
Lookup and the highest label information of the visual classification result matching degree in the ad classification database,
Obtain the highest advertisement source of matching degree corresponding with the label information, and by the obtained highest advertisement source of the matching degree into
Row decodes and is dissolved into the real-time video source, obtains the real-time video source for incorporating the highest advertisement source of matching degree.
Preferably, the step S4 specifically:
All historical review texts for obtaining commodity involved by the highest advertisement source of matching degree are calculated using TF-IDF algorithm
The similarity of historical review text.
Preferably, the step S5 specifically:
S501, the size based on the comment text similarity obtain comment text to be added, are deposited into advertiser and judge
By in database；
S502, according to advertisement source duration by several comment texts to be added in promotion item comment database with barrage
Form be added to broadcasting period of the advertisement source, obtain real-time video source of the advertisement source with barrage.
The present invention also provides a kind of network video bumper advertisements play systems, comprising:
Ad classification Database Unit, the ad classification Database Unit are used to obtain multiple advertisement sources, and to described
Multiple advertisement sources carry out ad classification, obtain ad classification as a result, constructing ad classification data based on the ad classification result
Library；
Video source taxon, the video source taxon obtain video point for classifying to real-time video source
Class result；
Unit is intercutted, the unit that intercuts from the ad classification database for finding out and the visual classification knot
The highest advertisement source of fruit matching degree, and the highest advertisement source of the matching degree is dissolved into the real-time video source, melted
Enter the real-time video source of the highest advertisement source of matching degree；
Similarity calculated, the similarity calculated are used for based on the involvement highest advertisement source of matching degree
Real-time video source calculates the similarity of the comment text of commodity involved in the highest advertisement source of the matching degree；
Comment text adding unit, the comment adding unit are used for based on similarity and the highest advertisement source of matching degree
Duration selects several comment texts；It is highest that the comment text chosen is loaded into the matching degree in the form of barrage
In advertisement source, real-time video source of the advertisement source with barrage is obtained；
Encoding output unit, the encoding output unit are used to carry out weight with the real-time video source of barrage to the advertisement source
It is newly encoded and export.
(3) beneficial effect
The present invention provides a kind of network video bumper advertisements playback method and systems.Compared with prior art, have with
It is lower the utility model has the advantages that
1, it is highest to intercut matching degree for real-time video source by classifying to advertisement source and real-time video source by the present invention
Advertisement source replaces the intrinsic advertisement in original broadcast medium, changes the unreasonable situation of advertisement pushing in traditional broadcast media,
And then the user experience is improved.
2, the present invention adds comment text related with commodity in the advertisement source period in the form of barrage, and high degree evokes
The interest of user is effectively relieved user and is watching the impatience generated when advertisement, improves user's viewing experience, reduce use
Family improves the validity of advertisement broadcasting to the avoidance degree of advertisement.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of block diagram of network video bumper advertisements playback method of the embodiment of the present invention；
Fig. 2 is a kind of block diagram of network video bumper advertisements play system of the embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, to the technology in the embodiment of the present invention
Scheme is clearly and completely described, it is clear that and described embodiments are some of the embodiments of the present invention, rather than whole
Embodiment.Based on the embodiments of the present invention, those of ordinary skill in the art are obtained without creative efforts
The every other embodiment obtained, shall fall within the protection scope of the present invention.
The embodiment of the present application solves advertisement broadcasting by providing a kind of network video bumper advertisements playback method and system
The low technical problem of validity is embodied as real-time video source and intercuts the highest advertisement source of matching degree, at the same the advertisement source period with
The form of barrage adds comment text related with commodity, and high degree evokes the interest of user, user is effectively relieved and is watching
The impatience generated when advertisement improves user's viewing experience, reduces user to the avoidance degree of advertisement, improves advertisement
The validity of broadcasting.
Technical solution in the embodiment of the present application is in order to solve the above technical problems, general thought is as follows: the embodiment of the present invention
Ad classification is carried out by obtaining multiple advertisement sources, and to the multiple advertisement source, obtains ad classification as a result, based on described wide
It accuses classification results and constructs ad classification database；Classify to real-time video source, obtains visual classification result；From the advertisement
Found out in taxonomy database with the highest advertisement source of visual classification result matching degree, and it is the matching degree is highest wide
Announcement source is dissolved into the real-time video source, and the real-time video source for incorporating the highest advertisement source of matching degree is obtained；Melted based on described
The real-time video source for entering the highest advertisement source of matching degree calculates commenting for commodity involved in the highest advertisement source of the matching degree
The similarity of paper sheet；Duration based on similarity and the highest advertisement source of matching degree selects several comment texts；It will selection
Comment text out is loaded into the highest advertisement source of the matching degree in the form of barrage, obtains reality of the advertisement source with barrage
When video source；The advertisement source is recompiled and exported with the real-time video source of barrage.The embodiment of the present invention is real-time
Video source intercuts the highest advertisement source of matching degree, replaces the intrinsic advertisement in original broadcast medium, changes traditional broadcast media
The unreasonable situation of middle advertisement pushing, and then the user experience is improved, meanwhile, the embodiment of the present invention is in the advertisement source period with barrage
Form add related with commodity comment text, high degree evokes the interest of user, and user is effectively relieved and is watching advertisement
When the impatience that generates, improve user's viewing experience, reduce user to the avoidance degree of advertisement, improve advertisement broadcasting
Validity.
In order to better understand the above technical scheme, in conjunction with appended figures and specific embodiments to upper
Technical solution is stated to be described in detail.
The embodiment of the present invention provides a kind of network video bumper advertisements playback method, as shown in Figure 1, the method is by video
Playing platform executes, comprising the following steps:
S1, multiple advertisement sources are obtained, and ad classification is carried out to the multiple advertisement source, obtain ad classification as a result, base
Ad classification database is constructed in the ad classification result；
S2, classify to real-time video source, obtain visual classification result；
S3, found out from the ad classification database with the highest advertisement source of visual classification result matching degree,
And the highest advertisement source of the matching degree is dissolved into the real-time video source, it obtains incorporating the highest advertisement source of matching degree
Real-time video source；
S4, the real-time video source based on the involvement highest advertisement source of matching degree, it is highest wide to calculate the matching degree
The similarity of the comment text of commodity involved in announcement source；
S5, the duration based on similarity and the highest advertisement source of matching degree select several comment texts；It will choose
Comment text be loaded into the form of barrage in the highest advertisement source of the matching degree, obtain real-time view of the advertisement source with barrage
Frequency source；
S6, the advertisement source is recompiled and is exported with the real-time video source of barrage.
The embodiment of the present invention is that the highest advertisement source of matching degree is intercutted in real-time video source, replaces consolidating in original broadcast medium
There is advertisement, changes the unreasonable situation of advertisement pushing in traditional broadcast media, and then the user experience is improved.Meanwhile this hair
Bright embodiment adds comment text related with commodity in the advertisement source period in the form of barrage, and high degree evokes the emerging of user
Interest is effectively relieved user and is watching the impatience generated when advertisement, improves user's viewing experience, reduce user to advertisement
Avoidance degree.
Each step is described in detail below.
S1, multiple advertisement sources are obtained, and ad classification is carried out to the multiple advertisement source, obtain ad classification as a result, base
Ad classification database is constructed in the ad classification result.Specifically includes the following steps:
S101, multiple advertisement sources are obtained and traverse the multiple advertisement source automatically, extract the advertisement of the multiple advertisement source
Source key frame.In the specific implementation process, video playing platform obtains and stores multiple advertisement sources and traverse automatically the multiple
Advertisement source extracts the advertisement source key frame of multiple advertisement sources.
S102, it is based on the advertisement source key-frame extraction characteristic of advertisement.In the specific implementation process, crucial based on advertisement source
Face, movement, text and article information in frame etc. extract characteristic of advertisement.
S103, classified based on the characteristic of advertisement to the multiple advertisement source, obtain ad classification result.Specific
In implementation process, classified with Monte Carlo decision tree to the characteristic of advertisement by neural network.
S104, corresponding label information is added according to the ad classification result, constructs ad classification database, wherein
Label information includes: game, science and technology, number, movement, travelling, cuisines, beverage, makeups, dress ornament, app etc..
S2, classify to real-time video source, obtain visual classification result.Specifically includes the following steps:
S201, real-time video source is decoded.
S202, video source key frame is extracted based on decoded real-time video source.
S203, video source key-frame extraction video features are based on.In the specific implementation process, based in video source key frame
Face, movement, text and article information etc. extract video features.
S204, classified based on the video features to the video source, obtain visual classification result.It is being embodied
In the process, classified with Monte Carlo decision tree to the video features by neural network.
S3, found out from the ad classification database with the highest advertisement source of visual classification result matching degree,
And the highest advertisement source of the matching degree is dissolved into the real-time video source, it obtains incorporating the highest advertisement source of matching degree
Real-time video source.In the specific implementation process, it searches in the ad classification database and is matched with the visual classification result
The highest label information is spent, the highest advertisement source of matching degree corresponding with the label information, and the institute that will be obtained are obtained
It states the highest advertisement source of matching degree and is decoded and is dissolved into the real-time video source, obtain incorporating the highest advertisement source of matching degree
Real-time video source.
S4, based on obtain incorporate the highest advertisement source of matching degree real-time video source, calculate the highest advertisement source of matching degree
Involved in commodity comment text similarity.In the specific implementation process, it is obtained involved by advertisement source by crawler technology
And all historical review texts of commodity, the similarity of historical review text is calculated using TF-IDF algorithm.It should be noted that
The similarity for calculating historical review text using other modes is also possible, such as clustering algorithm.TF-IDF is described in detail below
The method that algorithm calculates the similarity of historical review text, the specific steps are as follows:
Using item property label as product features text, TF-IDF feature next is carried out to each comment text and is mentioned
It takes and generates.
Firstly, segmenting to product features text and all historical review texts of this commodity, stop words is removed, then with place
The product features text managed and all historical review texts of this commodity establish dictionary, then by processed product features text with
All historical review text-processings of this commodity are indicated at the feature vector of corresponding dictionary.
TF-IDF can be used for text feature weighting, be made of TF and IDF two parts.TF is that this word goes out in a comment
Existing number (counting the number that the word occurs in the comment), it is assumed that d is specific a certain comment text, tnFor n-th of spy
Vocabulary is levied, then the TF value calculation formula of this feature is as follows:
tf(tn, d=NumberofTimes (tn))
IDF is that the number that this word occurs in all historical review texts of the commodity (counts one in all comment texts
The number that a word occurs), it is assumed that D is all comment text set, and d is specific a certain comment text, tnFor n-th of feature
Vocabulary, then the IDF value calculation formula of this feature is as follows:
TF with IDF two parts are multiplied, and can obtain the significance level that a specific Feature Words comment on one.Assuming that
D is all comment text set, and d is specific a certain item comment, tnFor n-th of feature vocabulary, tnThen for the TF- of sample d
IDF value calculation formula is as follows:
fn=tf-idf (tn, d, D) and=tf (tn, d) and × idf (tn, D)
As soon as a comment possesses all multiple features, thus to each comment possess a pile eigenvalue cluster at a feature
Vector.Form is as follows:
FeatureVector={ f1, f2, f3..., fn}
It is then based on the similarity that feature vector calculates historical review text, calculates each comment text of this commodity
The cosine similarity of feature vector and the feature vector of product features text, and result descending is arranged, take topN comment text
This is as comment to be added.Assuming that the feature vector of comment text isThe feature vector of product features text isComment text
The TF-IDF value of this Feature Words is xi, the TF-IDF value of product features Feature Words is yi, then comment text calculating formula of similarity
It is as follows:
S5, the duration based on similarity and the highest advertisement source of matching degree select several comment texts；It will choose
Comment text be loaded into the form of barrage in the highest advertisement source of the matching degree, obtain real-time view of the advertisement source with barrage
Frequency source.Specifically includes the following steps:
S501, the size based on the comment text similarity obtain comment text to be added, are deposited into advertiser and judge
By in database.In the specific implementation process, the comment text that similarity is preceding 100 can be chosen from all historical review texts
As comment text to be added, and the sequence carried out from big to small to the similarity of this 100 comment text arranges, and is deposited into
In promotion item comment database.
S502, according to advertisement source duration by several comment texts to be added in promotion item comment database with barrage
Form be added to broadcasting period of the advertisement source, obtain real-time video source of the advertisement source with barrage.In specific implementation process
In, as some advertisement source when it is 10 seconds a length of, need to choose 30 comment texts to be added be added in the form of barrage it is described
The broadcasting period of advertisement source, then need to be selected from 100 comment texts to be added the sequence of similarity value 30 of 1~30 to
Addition comment text is added to the broadcasting period of the advertisement source in the form of barrage, obtains real-time video of the advertisement source with barrage
Source.
S6, the advertisement source is recompiled and is exported with the real-time video source of barrage, broadcast in video playing platform
Real-time video source of the advertisement source with barrage is put, when playing the advertisement source period, user not can be only seen involved in advertisement source
Commodity comment text conversion barrage, also can be transmitted barrage.
The embodiment of the present invention also provides a kind of network video bumper advertisements play system, as shown in Figure 2, comprising: advertisement point
Class Database Unit, video source taxon intercut unit, similarity calculated, comment text adding unit, coding output
Unit.
Wherein:
Ad classification Database Unit carries out ad classification for obtaining multiple advertisement sources, and to the multiple advertisement source,
Ad classification is obtained as a result, constructing ad classification database based on the ad classification result；
Video source taxon obtains visual classification result for classifying to real-time video source；
Unit is intercutted for finding out from the ad classification database and the visual classification result matching degree highest
Advertisement source, and the highest advertisement source of the matching degree is dissolved into the real-time video source, obtains incorporating matching degree highest
Advertisement source real-time video source；
Similarity calculated is used for based on the real-time video source for incorporating the highest advertisement source of matching degree, described in calculating
The similarity of the comment text of commodity involved in the highest advertisement source of matching degree；
Comment adding unit selects several comment texts for the duration based on similarity and the highest advertisement source of matching degree
This；The comment text chosen is loaded into the highest advertisement source of the matching degree in the form of barrage, advertisement source is obtained
Real-time video source with barrage；
Encoding output unit is for being recompiled and being exported with the real-time video source of barrage to the advertisement source.
In conclusion compared with prior art, have it is following the utility model has the advantages that
1, the embodiment of the present invention is that the highest advertisement source of matching degree is intercutted in real-time video source, is replaced in original broadcast medium
Intrinsic advertisement changes the unreasonable situation of advertisement pushing in traditional broadcast media, and then the user experience is improved.
2, the embodiment of the present invention adds comment text related with commodity, very big journey in the advertisement source period in the form of barrage
Degree evokes the interest of user, and user is effectively relieved and is watching the impatience generated when advertisement, improves user's viewing experience, drops
Low avoidance degree of the user to advertisement improves the validity of advertisement broadcasting.
3, the embodiment of the present invention adds comment text related with commodity, Yong Hu in the advertisement source period in the form of barrage
Barrage also can be transmitted in the advertisement source period, further alleviates user and is watching the impatience generated when advertisement, improves advertisement and play
Validity.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to the foregoing embodiments
Invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each implementation
Technical solution documented by example is modified or equivalent replacement of some of the technical features；And these modification or
Replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.
Claims (7)
1. a kind of network video bumper advertisements playback method, which is characterized in that the method is executed by video playing platform, including
Following steps:
S1, multiple advertisement sources are obtained, and ad classification is carried out to the multiple advertisement source, obtain ad classification as a result, based on institute
State ad classification result building ad classification database；
S2, classify to real-time video source, obtain visual classification result；
S3, found out from the ad classification database with the highest advertisement source of visual classification result matching degree, and will
The highest advertisement source of matching degree is dissolved into the real-time video source, obtains incorporating the real-time of the highest advertisement source of matching degree
Video source；
S4, the real-time video source based on the involvement highest advertisement source of matching degree, calculate the highest advertisement source of the matching degree
Involved in commodity comment text similarity；
S5, the duration based on similarity and the highest advertisement source of matching degree select several comment texts；It is commented what is chosen
Paper sheet is loaded into the highest advertisement source of the matching degree in the form of barrage, obtains real-time video of the advertisement source with barrage
Source；
S6, the advertisement source is recompiled and is exported with the real-time video source of barrage.
2. network video bumper advertisements playback method as described in claim 1, which is characterized in that the step S1 specifically:
S101, multiple advertisement sources are obtained and traverse the multiple advertisement source automatically, the advertisement source for extracting the multiple advertisement source is closed
Key frame；
S102, it is based on the advertisement source key-frame extraction characteristic of advertisement；
S103, classified based on the characteristic of advertisement to the multiple advertisement source, obtain ad classification result；
S104, corresponding label information is added based on the ad classification result, constructs ad classification database.
3. network video bumper advertisements playback method as claimed in claim 2, which is characterized in that the step S2 specifically:
S201, real-time video source is decoded；
S202, video source key frame is extracted based on decoded real-time video source；
S203, video source key-frame extraction video features are based on；
S204, classified based on the video features to the video source, obtain visual classification result.
4. network video bumper advertisements playback method as claimed in claim 3, which is characterized in that the step S3 specifically:
Lookup and the highest label information of the visual classification result matching degree, obtain in the ad classification database
The highest advertisement source of matching degree corresponding with the label information, and the obtained highest advertisement source of the matching degree is solved
Code is simultaneously dissolved into the real-time video source, obtains the real-time video source for incorporating the highest advertisement source of matching degree.
5. network video bumper advertisements playback method as claimed in claim 4, which is characterized in that the step S4 specifically:
All historical review texts for obtaining commodity involved by the highest advertisement source of matching degree calculate history using TF-IDF algorithm
The similarity of comment text.
6. network video bumper advertisements playback method as claimed in claim 5, which is characterized in that the step S5 specifically:
S501, the size based on the comment text similarity obtain comment text to be added, are deposited into promotion item comment number
According in library；
S502, according to advertisement source duration by several comment texts to be added in promotion item comment database with the shape of barrage
Formula is added to the broadcasting period of the advertisement source, obtains real-time video source of the advertisement source with barrage.
7. a kind of network video bumper advertisements play system characterized by comprising
Ad classification Database Unit, the ad classification Database Unit are used to obtain multiple advertisement sources, and to the multiple
Advertisement source carries out ad classification, obtains ad classification as a result, constructing ad classification database based on the ad classification result；
Video source taxon, the video source taxon obtain visual classification knot for classifying to real-time video source
Fruit；
Unit is intercutted, the unit that intercuts from the ad classification database for finding out and the visual classification result
With the highest advertisement source of degree, and the highest advertisement source of the matching degree is dissolved into the real-time video source, obtains involvement
With the real-time video source for spending highest advertisement source；
Similarity calculated, the similarity calculated are used to incorporate the real-time of the highest advertisement source of matching degree based on described
Video source calculates the similarity of the comment text of commodity involved in the highest advertisement source of the matching degree；
Comment text adding unit, the comment adding unit are used for the duration based on similarity and the highest advertisement source of matching degree
Select several comment texts；The comment text chosen is loaded into the highest advertisement of the matching degree in the form of barrage
On source, real-time video source of the advertisement source with barrage is obtained；
Encoding output unit, the encoding output unit for compiling the advertisement source with the real-time video source of barrage again
Code simultaneously exports.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910610717.0A CN110290403B (en) | 2019-07-08 | 2019-07-08 | Network video paster advertisement playing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910610717.0A CN110290403B (en) | 2019-07-08 | 2019-07-08 | Network video paster advertisement playing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110290403A true CN110290403A (en) | 2019-09-27 |
| CN110290403B CN110290403B (en) | 2021-03-23 |
Family
ID=68020983
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910610717.0A Active CN110290403B (en) | 2019-07-08 | 2019-07-08 | Network video paster advertisement playing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110290403B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112016573A (en) * | 2020-10-16 | 2020-12-01 | 北京世纪好未来教育科技有限公司 | Bullet screen generation method and device, electronic equipment and computer storage medium |
| WO2023138671A1 (en) * | 2022-01-20 | 2023-07-27 | 北京有竹居网络技术有限公司 | Comment processing method, and device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130132996A1 (en) * | 2011-11-22 | 2013-05-23 | Chen-Ming Wu | System and method for displaying product information about advertisement on digital television, and recording medium thereof |
| CN104754418A (en) * | 2015-03-06 | 2015-07-01 | 合一信息技术（北京）有限公司 | Advertisement putting method based on bilibili hikaru |
| CN104811762A (en) * | 2015-04-28 | 2015-07-29 | 柳州市一呼百应科技有限公司 | Internet video advertisement platform |
| CN104808888A (en) * | 2015-04-28 | 2015-07-29 | 柳州市一呼百应科技有限公司 | Interactive advertising platform based on network video |
| US20160350806A1 (en) * | 2015-05-26 | 2016-12-01 | Kwai Wing Egan Lau | Advertising mobile equipment for readers |
| CN106572360A (en) * | 2016-11-11 | 2017-04-19 | 协创数据技术股份有限公司 | Advertisement intercutting device applied to video live streaming |
| 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 |
| CN109003149A (en) * | 2018-10-31 | 2018-12-14 | 科大讯飞股份有限公司 | A kind of barrage advertisement placement method and device |
| CN109640133A (en) * | 2018-12-17 | 2019-04-16 | 杭州柚子街信息科技有限公司 | The information processing method and device of video ads are intercutted in video |
-
2019
- 2019-07-08 CN CN201910610717.0A patent/CN110290403B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130132996A1 (en) * | 2011-11-22 | 2013-05-23 | Chen-Ming Wu | System and method for displaying product information about advertisement on digital television, and recording medium thereof |
| CN104754418A (en) * | 2015-03-06 | 2015-07-01 | 合一信息技术（北京）有限公司 | Advertisement putting method based on bilibili hikaru |
| CN104811762A (en) * | 2015-04-28 | 2015-07-29 | 柳州市一呼百应科技有限公司 | Internet video advertisement platform |
| CN104808888A (en) * | 2015-04-28 | 2015-07-29 | 柳州市一呼百应科技有限公司 | Interactive advertising platform based on network video |
| US20160350806A1 (en) * | 2015-05-26 | 2016-12-01 | Kwai Wing Egan Lau | Advertising mobile equipment for readers |
| CN106572360A (en) * | 2016-11-11 | 2017-04-19 | 协创数据技术股份有限公司 | Advertisement intercutting device applied to video live streaming |
| 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 |
| CN109003149A (en) * | 2018-10-31 | 2018-12-14 | 科大讯飞股份有限公司 | A kind of barrage advertisement placement method and device |
| CN109640133A (en) * | 2018-12-17 | 2019-04-16 | 杭州柚子街信息科技有限公司 | The information processing method and device of video ads are intercutted in video |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112016573A (en) * | 2020-10-16 | 2020-12-01 | 北京世纪好未来教育科技有限公司 | Bullet screen generation method and device, electronic equipment and computer storage medium |
| CN112016573B (en) * | 2020-10-16 | 2021-04-30 | 北京世纪好未来教育科技有限公司 | Bullet screen generation method and device, electronic equipment and computer storage medium |
| WO2023138671A1 (en) * | 2022-01-20 | 2023-07-27 | 北京有竹居网络技术有限公司 | Comment processing method, and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110290403B (en) | 2021-03-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hsu | A personalized English learning recommender system for ESL students | |
| Rangel et al. | Overview of the 3rd Author Profiling Task at PAN 2015 | |
| Dave et al. | Learning the click-through rate for rare/new ads from similar ads | |
| CN103338403A (en) | Broadcasting television system and personalized program recommending method in system | |
| CN103793537A (en) | System for recommending individual music based on multi-dimensional time series analysis and achieving method of system | |
| CN105975472A (en) | Method and device for recommendation | |
| CN111460221B (en) | Comment information processing method and device and electronic equipment | |
| Feng et al. | Mining user-contributed photos for personalized product recommendation | |
| JP5940955B2 (en) | Trend analysis apparatus, method and program | |
| CA2714057A1 (en) | User-targeted advertising | |
| JP2010009307A (en) | Feature word automatic learning system, content linkage type advertisement distribution computer system, retrieval linkage type advertisement distribution computer system and text classification computer system, and computer program and method for them | |
| CN103984741A (en) | Method and system for extracting user attribute information | |
| Yang et al. | Pinterest board recommendation for twitter users | |
| CN108665083A (en) | A kind of method and system for advertisement recommendation for dynamic trajectory model of being drawn a portrait based on user | |
| CN105809275A (en) | Item scoring prediction method and apparatus | |
| CN104268130A (en) | Social advertising facing Twitter feasibility analysis method | |
| Hsu et al. | Predicting movies user ratings with imdb attributes | |
| CN110290403A (en) | Network video bumper advertisements playback method and system | |
| CN103853789A (en) | Method and equipment used for recommending information to user | |
| Sonalitha et al. | Combined text mining: Fuzzy clustering for opinion mining on the traditional culture arts work | |
| Kim et al. | Exploring characteristics of video consuming behaviour in different social media using K-pop videos | |
| CN105005576B (en) | A kind of video website similar users search system and method | |
| KR101124696B1 (en) | Method of advertising based on internet contents related to products | |
| CN105279289A (en) | Personalized music recommendation sorting method based on exponential decay window | |
| Song et al. | Predicting gross box office revenue for domestic films |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220118 Address after: 230001 floor 6, block B, blue diamond Shangjie, No. 335, Suixi Road, Bozhou road street, Luyang District, Hefei City, Anhui Province Patentee after: Hefei Luyang Technology Innovation Group Co.,Ltd. Address before: Tunxi road in Baohe District of Hefei city of Anhui Province, No. 193 230009 Patentee before: Hefei University of Technology |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220919 Address after: Huangshan Future Science and Technology City, No. 59, Meilin Avenue, Huangshan High-tech Industrial Development Zone, Huangshan City, Anhui Province, 245000 Patentee after: Huangshan Science and Technology Innovation Center Co.,Ltd. Address before: 230001 floor 6, block B, blue diamond Shangjie, No. 335, Suixi Road, Bozhou road street, Luyang District, Hefei City, Anhui Province Patentee before: Hefei Luyang Technology Innovation Group Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230324 Address after: 230001 Gujing Baihua mansion, 156 Shou Chun Road, Hefei, Anhui Patentee after: HEFEI HUIZHONG INTELLECTUAL PROPERTY MANAGEMENT Co.,Ltd. Address before: Huangshan Future Science and Technology City, No. 59, Meilin Avenue, Huangshan High-tech Industrial Development Zone, Huangshan City, Anhui Province, 245000 Patentee before: Huangshan Science and Technology Innovation Center Co.,Ltd. |