CN116614679B - Optimization processing method and system for short video advertisement delivery - Google Patents
Optimization processing method and system for short video advertisement delivery Download PDFInfo
- Publication number
- CN116614679B CN116614679B CN202310488720.6A CN202310488720A CN116614679B CN 116614679 B CN116614679 B CN 116614679B CN 202310488720 A CN202310488720 A CN 202310488720A CN 116614679 B CN116614679 B CN 116614679B
- Authority
- CN
- China
- Prior art keywords
- area
- video
- advertisement
- preference
- article
- 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.)
- Active
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 9
- 238000003672 processing method Methods 0.000 title abstract description 7
- 238000000034 method Methods 0.000 claims abstract description 37
- 238000007781 pre-processing Methods 0.000 claims description 41
- 238000009826 distribution Methods 0.000 claims description 33
- 238000004364 calculation method Methods 0.000 claims description 27
- 238000012216 screening Methods 0.000 claims description 23
- 238000006243 chemical reaction Methods 0.000 claims description 14
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000007547 defect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 238000002716 delivery method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related 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]
- H04N21/40—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
- H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
-
- 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
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/845—Structuring of content, e.g. decomposing content into time segments
- H04N21/8456—Structuring of content, e.g. decomposing content into time segments by decomposing the content in the time domain, e.g. in time segments
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Business, Economics & Management (AREA)
- Marketing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an optimization processing method and system for short video advertisement delivery, and relates to the technical field of advertisement delivery, wherein the processing system comprises a preference acquisition module, a video processing module and an advertisement adjustment module; the preference acquisition module is used for acquiring preference video information and preference advertisement information of a user; the video processing module is used for analyzing and processing preference video information of the user, and the video processing module is also used for analyzing and processing preference advertisement information of the user; the advertisement adjusting module is used for classifying advertisements to be put, obtaining the putting quantity proportion of the advertisements to be put, and outputting the putting adjusting result, so that the problem that the short video advertisement putting is not effective due to the fact that the existing putting method cannot effectively analyze the preference of the short video advertisement of the user in the prior art is solved.
Description
Technical Field
The invention relates to the technical field of advertisement delivery, in particular to an optimization processing method and system for short video advertisement delivery.
Background
The short video is a short video, is an internet content transmission mode, and is a video which is transmitted on the new internet media for a period of time within 5 minutes; with the popularization of mobile terminals and the acceleration of networks, short and quick mass propagation contents gradually get the favor of various large platforms, vermicelli and capital; short video advertisements are also presented, which have the advantages of short time, more content, fast speed, low cost, etc.
In the prior art, when analyzing the viewing preference of the user, the analyzed video data includes a lot of invalid information, for example: the video watched by the user briefly is not watched substantially, and meanwhile, when the video data is analyzed, only the inherent label of the video is usually extracted, and the effective information existing in the video is extracted insufficiently, so that the preference of the user cannot be analyzed accurately, and the following short video advertisement pushing has defects, so that the short video advertisement is not effective, and an optimized processing system for short video advertisement is lacking to solve the problems.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention aims to provide an optimized processing system for short video advertisement delivery, by extracting the effectiveness of videos and then carrying out feature analysis on the extracted videos, the accuracy and effectiveness of analysis can be improved, invalid information is screened out, the problems that the acquisition and analysis of user preference and associated preference in the prior art are insufficient, the existing delivery method cannot effectively analyze the preference of the short video advertisement of the user, and therefore, defects exist on the follow-up short video advertisement delivery, and the short video advertisement delivery is not effective are solved.
In order to achieve the above object, the present invention is realized by the following technical scheme: an optimized processing system for short video advertisement delivery comprises a preference acquisition module, a video processing module and an advertisement adjustment module;
the preference acquisition module is used for acquiring preference video information and preference advertisement information of a user;
the video processing module is used for analyzing and processing preference video information of a user, firstly obtaining preference video of the user, slicing the preference video to obtain slice pictures, then dividing object identification areas and identifying objects of the slice pictures to obtain associated object information in different areas, finally calculating the associated object information to obtain object associated value sorting, and obtaining an associated label according to the object associated value sorting;
The associated article information comprises article occurrence times and article first occurrence time;
the video processing module is also used for analyzing and processing the preference advertisement information of the user, and obtaining a first label, a second label, a third label and a fourth label according to the playing progress of the user on different short video advertisements;
the advertisement adjustment module is used for optimizing the delivery of short video advertisements to users according to the relevance labels to obtain advertisements to be delivered; and classifying the advertisements to be put according to the first label, the second label, the third label and the fourth label obtained by the video processing module, obtaining the put quantity ratio of the advertisements to be put, and outputting a put adjustment result.
Further, the preference acquisition module comprises a preference video acquisition unit and a preference advertisement acquisition unit; the preference video acquisition unit is configured with a preference video acquisition strategy comprising:
acquiring the playing progress of a user on the short video, setting the video with the playing progress exceeding the short video progress threshold as a user preference video, and acquiring a user preference video label;
the preferred advertisement acquisition unit is further configured with a preferred advertisement acquisition policy comprising: and acquiring the playing progress of the short video advertisement watched by the user and the video tag of the short video advertisement.
Further, the video processing module comprises a preference video processing unit, an associated article preprocessing unit and a preference advertisement processing unit, wherein the preference video processing unit is configured with a preference video processing strategy, and the preference video processing strategy comprises: slicing the watched part of the obtained user preference video, performing relevance area division on all pictures obtained through slicing, dividing the pictures into a first object recognition area, a second object recognition area and a third object recognition area, performing object recognition analysis on objects appearing in the first object recognition area, the second object recognition area and the third object recognition area respectively, and marking the objects identified in the first object recognition area as W1P1 to W1Pn; the articles identified in the second identification area are marked as W2P1 to W2Pm; the articles identified in the third identification area are marked as W3P1 to W3Pk; wherein n, m and k are positive integers;
setting the articles which have no movement in position and repeatedly appear in each slice as non-associated articles;
obtaining a video tag, and setting an article related to the tag as a tag article;
screening out non-associated articles and labeled articles, setting the rest articles as associated articles, counting the occurrence time, occurrence times and occurrence areas of the associated articles in a video, substituting the occurrence time and the occurrence times of the associated articles in the video into a first article identification area calculation formula, a second article identification area calculation formula and a third article identification area calculation formula respectively according to the occurrence areas of the associated articles, carrying out association calculation to obtain association values, and carrying out association sequencing on the association values from large to small;
And screening the relevance articles with relevance ordered in the first three, acquiring the labels and the video labels of the relevance articles ordered in the first three, and setting the labels as relevance labels.
Further, the associated article preprocessing unit is configured with a first preprocessing strategy and a second preprocessing strategy;
the first preprocessing strategy comprises the following steps: randomly selecting a plurality of slice pictures of different videos, and dividing the slice pictures by using a first dividing method, wherein the first dividing method comprises the following steps: the method comprises the steps of obtaining a first to-be-determined area through reducing the frame of a slice picture according to a first proportion, obtaining a second to-be-determined area through reducing the frame of the slice picture according to a second proportion, setting the first to-be-determined area as a first pretreatment area, setting an area between the first to-be-determined area and the second to-be-determined area as a second pretreatment area, and setting an area between the second to-be-determined area and the frame of the slice picture as a third pretreatment area, wherein the first proportion is smaller than the second proportion;
screening objects appearing in the first pretreatment area, the second pretreatment area and the third pretreatment area by manpower, setting the objects related to the video as effective objects, respectively counting the effective object distribution rates in the first pretreatment area, the second pretreatment area and the third pretreatment area of a plurality of slice pictures, acquiring the difference values of the effective object distribution rates in the first pretreatment area, the second pretreatment area and the third pretreatment area, and setting the difference values as first difference values;
The second preprocessing strategy comprises the following steps: randomly selecting a plurality of slice pictures of different videos, and dividing the slice pictures by using a second dividing method, wherein the second dividing method comprises the following steps: the frame of the slice picture is reduced according to a third proportion to obtain a third to-be-determined area, the third to-be-determined area is set to be a fourth preprocessing area, and an area between the third to-be-determined area and the frame of the slice picture is set to be a fifth preprocessing area; the fourth preprocessing area is close to the center of the picture, and the area of the fourth preprocessing area is larger than that of the fifth preprocessing area; dividing the fourth pretreatment area into a sixth pretreatment area and a seventh pretreatment area according to the upper and lower directions, wherein the areas of the sixth pretreatment area and the seventh pretreatment area are equal;
screening the articles appearing in the slice images by manpower, setting the articles related to the video as effective articles, respectively counting the effective article distribution rates in a fifth pretreatment area, a sixth pretreatment area and a seventh pretreatment area of a plurality of slice images, acquiring the difference values of the effective article distribution rates in the fifth pretreatment area, the sixth pretreatment area and the seventh pretreatment area, and setting the difference values as second difference values;
The associated article preprocessing unit is further configured with a distribution rate comparison strategy, and the distribution rate comparison strategy comprises: comparing the first difference value with the second difference value, and dividing the relevance area by using a dividing method with large difference value;
dividing the relevance area to obtain three pretreatment areas, and sequentially setting the three pretreatment areas into a first object identification area, a second object identification area and a third object identification area according to the effective object distribution rate from large to small;
and obtaining the article relevance weights of the first article identification area, the second article identification area and the third article identification area according to the effective article distribution rates in the first article identification area, the second article identification area and the third article identification area.
Further, the first recognition area calculation formula is configured asWherein M1 is the correlation value of the first object recognition area, A 1 And (3) the article relevance weight of the first article identification area, B is a time conversion coefficient, t is the first appearance time of the article, and C is the appearance times of the article.
Further, the second recognition area calculation formula is configured asWherein M2 is the correlation value of the second object recognition area, A 2 And (3) the article relevance weight of the second article identification area, B is a time conversion coefficient, t is the first appearance time of the article, and C is the appearance times of the article.
Further, the third recognition area calculation formula is configured asWherein M3 is the correlation value of the third object recognition area, A 3 And (3) the article relevance weight of the third article identification area, B is a time conversion coefficient, t is the first appearance time of the article, and C is the appearance times of the article.
Further, the preferred advertisement processing unit is configured with a preferred advertisement processing policy, the preferred advertisement processing policy comprising: setting a first advertisement playing progress and a second advertisement playing progress; the first advertisement playing progress is smaller than the second advertisement playing progress;
setting short video advertisements with the watching progress of the user smaller than the playing progress of the first advertisements as first user preference short video advertisements, acquiring labels of the first user preference short video advertisements, and setting the labels as first labels;
setting short video advertisements with the watching progress of the user being greater than or equal to that of the first advertisement and smaller than that of the second advertisement as second user preference short video advertisements, acquiring labels of the second user preference short video advertisements, and setting the labels as second labels;
setting short video advertisements with the user watching progress being greater than or equal to the second advertisement playing progress as third user preference short video advertisements, acquiring labels of the third user preference short video advertisements, and setting the labels as third labels;
Obtaining the connection times of the user clicking advertisements, setting the advertisements corresponding to the user clicking links as fourth user preference short video advertisements, obtaining the labels of the fourth user preference short video advertisements, and setting the labels as fourth labels.
Further, the advertisement adjustment module is configured with an advertisement adjustment policy, the advertisement adjustment policy comprising: screening advertisements according to the relevance labels, setting the advertisements conforming to the relevance labels as advertisements to be put, and acquiring a first label, a second label, a third label and a fourth label; classifying advertisements to be placed according to the first label, the second label, the third label and the fourth label, classifying the advertisements to be placed into a first type advertisement, a second type advertisement, a third type advertisement and a fourth type advertisement, distributing and adjusting the placed quantity of the first type advertisement, the second type advertisement, the third type advertisement and the fourth type advertisement, and outputting a placed adjustment result.
A method of processing a short video advertisement delivery optimization processing system, the method comprising the steps of:
collecting preference video information and preference advertisement information of a user;
analyzing and processing preference video information of a user, firstly obtaining preference video of the user, and slicing the preference video to obtain slice pictures; dividing object identification areas and identifying objects of the slice pictures to obtain associated object information in different areas, and finally calculating the associated object information to obtain object associated value sequences and obtaining an associated label according to the object associated value sequences;
According to the relevance labels, carrying out short video advertisement delivery optimization on users to obtain advertisements to be delivered;
analyzing and processing the preference advertisement information of the user, and obtaining a first label, a second label, a third label and a fourth label according to the playing progress of the user on different short video advertisements;
classifying advertisements to be put according to the obtained first label, second label, third label and fourth label, obtaining the put quantity ratio of the advertisements to be put, and outputting the put adjustment result.
The invention has the beneficial effects that: firstly, collecting preference video information and preference advertisement information of a user; analyzing and processing the preference video information of the user to obtain the preference video of the user; the method solves the problems that the existing delivery method cannot acquire the effective video, so that the following short video advertisement pushing has defects, and the short video advertisement delivery is not effective;
then slicing the preference video to obtain slice pictures; dividing object identification areas and identifying objects of the slice pictures to obtain associated object information in different areas; analyzing and processing the preference advertisement information of the user, and obtaining a first label, a second label, a third label and a fourth label according to the playing progress of the user on different short video advertisements; comprehensively analyzing the relevance article information to obtain relevance labels; according to the correlation label, the advertisement to be put is selected, the advertisement to be put is classified according to the first label, the second label, the third label and the fourth label, the put quantity proportion of the advertisement to be put is obtained, the advertisement to be put can be accurately divided through analysis processing of the user preference video and the user preference advertisement, accurate short video advertisement content putting can be provided for the user, and the putting effect of the short video advertisement is obvious.
Additional aspects of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the detailed description of non-limiting embodiments, given with reference to the accompanying drawings in which:
FIG. 1 is a functional block diagram of a processing system of the present invention;
FIG. 2 is a schematic diagram of a first pretreatment strategy according to the present invention;
FIG. 3 is a schematic process diagram of a second pretreatment strategy of the present invention;
fig. 4 is a partial flow chart of the processing method of the present invention.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention.
Embodiments of the invention and features of the embodiments may be combined with each other without conflict.
Example 1
Referring to fig. 1, the invention provides an optimization processing system for short video advertisement delivery, which comprises a preference acquisition module, a video processing module and an advertisement adjustment module;
the preference acquisition module is used for acquiring preference video information and preference advertisement information of a user;
the preference acquisition module comprises a preference video acquisition unit and a preference advertisement acquisition unit; the preference video acquisition unit is configured with a preference video acquisition strategy comprising: acquiring the playing progress of a user on the short video, setting the video with the playing progress exceeding the short video progress threshold as a user preference video, and acquiring a user preference video label;
the preferred advertisement acquisition unit is further configured with a preferred advertisement acquisition policy comprising: and acquiring the playing progress of the short video advertisement watched by the user and the video tag of the short video advertisement.
The video processing module is used for analyzing and processing preference video information of a user, firstly obtaining preference video of the user, slicing the preference video to obtain slice pictures, then dividing object identification areas and identifying objects of the slice pictures to obtain associated object information in different areas, finally calculating the associated object information to obtain object associated value sorting, and obtaining an associated label according to the object associated value sorting; the association article information comprises article occurrence times and article first occurrence time;
The video processing module comprises a preference video processing unit, a related article preprocessing unit and a preference advertisement processing unit, wherein the related article preprocessing unit is configured with a first preprocessing strategy and a second preprocessing strategy;
referring to fig. 2, the first preprocessing strategy includes: randomly selecting a plurality of slice pictures of different videos, and dividing the slice pictures by using a first dividing method, wherein the first dividing method comprises the following steps: the method comprises the steps of obtaining a first to-be-determined area through reducing the frame of a slice picture according to a first proportion, obtaining a second to-be-determined area through reducing the frame of the slice picture according to a second proportion, setting the first to-be-determined area as a first pretreatment area, setting an area between the first to-be-determined area and the second to-be-determined area as a second pretreatment area, and setting an area between the second to-be-determined area and the frame of the slice picture as a third pretreatment area, wherein the first proportion is smaller than the second proportion;
screening objects appearing in the first pretreatment area, the second pretreatment area and the third pretreatment area by manpower, setting the objects related to the video as effective objects, respectively counting the effective object distribution rates in the first pretreatment area, the second pretreatment area and the third pretreatment area of a plurality of slice pictures, acquiring the difference values of the effective object distribution rates in the first pretreatment area, the second pretreatment area and the third pretreatment area, and setting the difference values as first difference values;
Referring to fig. 3, the second preprocessing strategy includes: randomly selecting a plurality of slice pictures of different videos, and dividing the slice pictures by using a second dividing method, wherein the second dividing method comprises the following steps: the frame of the slice picture is reduced according to a third proportion to obtain a third to-be-determined area, the third to-be-determined area is set to be a fourth preprocessing area, and an area between the third to-be-determined area and the frame of the slice picture is set to be a fifth preprocessing area; the fourth preprocessing area is close to the center of the picture, and the area of the fourth preprocessing area is larger than that of the fifth preprocessing area; dividing the fourth pretreatment area into a sixth pretreatment area and a seventh pretreatment area according to the upper and lower directions, wherein the areas of the sixth pretreatment area and the seventh pretreatment area are equal;
screening the articles appearing in the slice images by manpower, setting the articles related to the video as effective articles, respectively counting the effective article distribution rates in a fifth pretreatment area, a sixth pretreatment area and a seventh pretreatment area of a plurality of slice images, acquiring the difference values of the effective article distribution rates in the fifth pretreatment area, the sixth pretreatment area and the seventh pretreatment area, and setting the difference values as second difference values;
The associated article preprocessing unit is further configured with a distribution rate comparison strategy, and the distribution rate comparison strategy comprises: comparing the first difference value with the second difference value, and dividing the relevance area by using a dividing method with large difference value; the short video center area is an important area, two different dividing methods are set for comparison and selection, and the problem that the area dividing effect is not obviously set to be invalid due to the fact that the distribution rates of associated objects in the divided areas are consistent can be avoided;
dividing the relevance area to obtain three pretreatment areas, and sequentially setting the three pretreatment areas into a first object identification area, a second object identification area and a third object identification area according to the effective object distribution rate from large to small;
according to the effective article distribution rates in the first article identification area, the second article identification area and the third article identification area, article relevance weights of the first article identification area, the second article identification area and the third article identification area are obtained, specifically, when the first difference value is larger than the second difference value, a first division method is selected to divide the relevance areas, the distribution rate corresponding to the first division method is obtained, and the distribution rate is 0.7, 0.2 and 0.1 from large to small in sequence, and then a first article identification area relevance weight value A is obtained 1 Set to 0.7, the association weight value A of the second object recognition area 2 Set to 0.2, the item association weight A of the third identification area 3 Set to 0.1.
The preferred video processing unit is configured with a preferred video processing policy comprising: slicing the watched part of the obtained user preference video, performing relevance area division on all pictures obtained through slicing, dividing the pictures into a first object recognition area, a second object recognition area and a third object recognition area, performing object recognition analysis on objects appearing in the first object recognition area, the second object recognition area and the third object recognition area respectively, and marking the objects identified in the first object recognition area as W1P1 to W1Pn; the articles identified in the second identification area are marked as W2P1 to W2Pm; the articles identified in the third identification area are marked as W3P1 to W3Pk; wherein n, m and k are positive integers; the short video has the characteristic of shortness, the user has different receiving amounts of article information in different areas of the video interface, and in the specific implementation process, the video slice pictures are subjected to relevance area division, so that the influence on short video advertisements caused by the fact that articles which are not interested or not noticed by the user are collected can be avoided; specifically, the association degree of the first object recognition area is larger than that of the second object recognition area, and the association degree of the second object recognition area is larger than that of the third object recognition area;
Setting the articles which are not moved in position and repeatedly appear in each slice as non-associated articles, and rejecting the conventional articles such as tables and chairs in a common short video in the specific implementation process to ensure the accuracy of screening the association labels;
obtaining a video tag, and setting an article related to the tag as a tag article;
screening out non-associated articles and labeled articles, setting the rest articles as associated articles, counting the occurrence time, occurrence times and occurrence areas of the associated articles in the video, and substituting the occurrence time and occurrence times of the associated articles in the video into a first article identification area calculation formula, a second article identification area calculation formula and a third article identification area calculation formula respectively according to the occurrence areas of the associated articles to obtain association values; and sorting the relevance values from big to small;
the first object recognition area calculation formula is configured asWherein M1 is the correlation value of the first object recognition area, A 1 The article relevance weight of the first article identification area is B, the time conversion coefficient is B, t is the first appearance time of the article, and C is the occurrence times of the article;
The second recognition area calculation formula is configured asWherein M2 is the correlation value of the second object recognition area, A 2 The article relevance weight of the second article identification area is B, the time conversion coefficient is B, t is the first appearance time of the article, and C is the occurrence times of the article;
the third recognition area calculation formula is configured asWherein M3 is the correlation value of the third object recognition area, A 3 The article relevance weight of the third article identification area is B, the time conversion coefficient is B, t is the first appearance time of the article, and C is the occurrence times of the article; wherein the relevance weights are presented by the relevance itemsWhen the relevance weight is larger, the relevance value is larger, the first appearance time of the relevance article is taken from the time of the short video, the earlier the appearance time of the relevance article in the short video is, the more the appearance times are, the more the relevance article is easily seen by a user, and the relevance value of the relevance article is also larger;
specifically, A 1 Set to 0.7, A 2 Set to 0.2, A 3 Set to 0.1; for example, the appearance area of the related article W1P5 is the first recognition area, the time conversion coefficient is 0.2, the first appearance time is 20s of the short video, and the appearance number is 3; calculating to obtain a correlation value of the correlation article W1P5, wherein the correlation value is 0.525; the occurrence area of the correlation article W3P6 is a third identification area, the time conversion coefficient is 0.2, the first occurrence time is 30s of the short video, and the occurrence times are 5; calculating to obtain a correlation value of 0.167 of the correlation article W3P 6; the relevance rank of the relevance article W1P5 is better than the relevance article W3P6.
And screening the relevance articles with relevance ordered in the first three, acquiring the labels and the video labels of the relevance articles ordered in the first three, and setting the labels as relevance labels.
The video processing module is further configured with a preference advertisement processing unit, and the preference advertisement processing unit is used for analyzing and processing preference advertisement information of a user and obtaining a first label, a second label, a third label and a fourth label according to the playing progress of the user on different short video advertisements;
the preferred advertisement processing unit is configured with a preferred advertisement processing policy comprising: setting a first advertisement playing progress and a second advertisement playing progress; the first advertisement playing progress is smaller than the second advertisement playing progress; specifically, when a user plays short video advertisements, the playing time of the unnecessary short video advertisement types is relatively less, the playing time of the required short video advertisement types is relatively longer, the playing time of the short video advertisements is divided by the user, and the short video advertisement labels which are not required by the user can be screened out;
setting short video advertisements with the watching progress of the user smaller than the playing progress of the first advertisements as first user preference short video advertisements, acquiring labels of the first user preference short video advertisements, and setting the labels as first labels;
Setting short video advertisements with the watching progress of the user being greater than or equal to that of the first advertisement and smaller than that of the second advertisement as second user preference short video advertisements, acquiring labels of the second user preference short video advertisements, and setting the labels as second labels;
setting short video advertisements with the user watching progress being greater than or equal to the second advertisement playing progress as third user preference short video advertisements, acquiring labels of the third user preference short video advertisements, and setting the labels as third labels.
Acquiring the connection times of the user clicking advertisements, setting the advertisements corresponding to the user clicking links as fourth user preference short video advertisements, acquiring the labels of the fourth user preference short video advertisements, and setting the labels as fourth labels; specifically, when a user views a short video advertisement and clicks an advertisement link to jump, the advertisement is judged to be needed by the user, and the short video advertisement tag is recorded.
The advertisement adjustment module is used for optimizing the delivery of the short video advertisement to the user according to the relevance label to obtain the advertisement to be delivered; and classifying the advertisements to be put according to the first label, the second label, the third label and the fourth label obtained by the video processing module, obtaining the put quantity ratio of the advertisements to be put, and outputting a put adjustment result.
The advertisement adjustment module is further configured with an advertisement adjustment policy, the advertisement adjustment policy comprising: screening advertisements according to the relevance labels, setting the advertisements conforming to the relevance labels as advertisements to be put, and acquiring a first label, a second label, a third label and a fourth label; classifying advertisements to be put according to the first label, the second label, the third label and the fourth label, classifying the advertisements to be put into a first type of advertisements, a second type of advertisements, a third type of advertisements and a fourth type of advertisements, distributing and adjusting the put amounts of the first type of advertisements, the second type of advertisements, the third type of advertisements and the fourth type of advertisements, and outputting a put adjustment result, wherein the first type of advertisements account for 10% of the put amount of the advertisements, the second type of advertisements account for 20% of the put amount of the advertisements, the third type of advertisements account for 30% of the put amount of the advertisements, and the fourth type of advertisements account for 50% of the put amount of the advertisements.
Example two
Referring to fig. 4, the invention further provides a processing method of the optimization processing system for short video advertisement delivery, the processing method comprises the following steps:
step S1: collecting preference video information and preference advertisement information of a user;
step S1 further comprises the following sub-steps:
Step S101: acquiring the playing progress of a user on the short video, setting the video with the playing progress exceeding the short video progress threshold as a user preference video, and acquiring a user preference video label;
step S102: and acquiring the playing progress of the short video advertisement watched by the user and the video tag of the short video advertisement.
Step S2: analyzing and processing preference video information of a user;
the step S2 further comprises the following sub-steps:
step S201: randomly selecting a plurality of slice pictures of different videos, and dividing the slice pictures by using a first dividing method, wherein the first dividing method comprises the following steps: the method comprises the steps of obtaining a first to-be-determined area through reducing the frame of a slice picture according to a first proportion, obtaining a second to-be-determined area through reducing the frame of the slice picture according to a second proportion, setting the first to-be-determined area as a first pretreatment area, setting an area between the first to-be-determined area and the second to-be-determined area as a second pretreatment area, and setting an area between the second to-be-determined area and the frame of the slice picture as a third pretreatment area, wherein the first proportion is smaller than the second proportion;
screening objects appearing in the first pretreatment area, the second pretreatment area and the third pretreatment area by manpower, setting the objects related to the video as effective objects, respectively counting the effective object distribution rates in the first pretreatment area, the second pretreatment area and the third pretreatment area of a plurality of slice pictures, acquiring the difference values of the effective object distribution rates in the first pretreatment area, the second pretreatment area and the third pretreatment area, and setting the difference values as first difference values;
Step S202: randomly selecting a plurality of slice pictures of different videos, and dividing the slice pictures by using a second dividing method, wherein the second dividing method comprises the following steps: the frame of the slice picture is reduced according to a third proportion to obtain a third to-be-determined area, the third to-be-determined area is set to be a fourth preprocessing area, and an area between the third to-be-determined area and the frame of the slice picture is set to be a fifth preprocessing area; the fourth preprocessing area is close to the center of the picture, and the area of the fourth preprocessing area is larger than that of the fifth preprocessing area; dividing the fourth pretreatment area into a sixth pretreatment area and a seventh pretreatment area according to the upper and lower directions, wherein the areas of the sixth pretreatment area and the seventh pretreatment area are equal;
screening the articles appearing in the slice images by manpower, setting the articles related to the video as effective articles, respectively counting the effective article distribution rates in a fifth pretreatment area, a sixth pretreatment area and a seventh pretreatment area of a plurality of slice images, acquiring the difference values of the effective article distribution rates in the fifth pretreatment area, the sixth pretreatment area and the seventh pretreatment area, and setting the difference values as second difference values;
Step S203: comparing the first difference value with the second difference value, and dividing the relevance area by using a dividing method with large difference value;
dividing the relevance area to obtain three pretreatment areas, and sequentially setting the three pretreatment areas into a first object identification area, a second object identification area and a third object identification area according to the effective object distribution rate from large to small;
step S204: obtaining article relevance weights of the first article recognition area, the second article recognition area and the third article recognition area according to the effective article distribution rates in the first article recognition area, the second article recognition area and the third article recognition area;
step S205: slicing the watched part of the obtained user preference video, performing relevance area division on all pictures obtained through slicing, dividing the pictures into a first object recognition area, a second object recognition area and a third object recognition area, performing object recognition analysis on objects appearing in the first object recognition area, the second object recognition area and the third object recognition area respectively, and marking the objects identified in the first object recognition area as W1P1 to W1Pn; the articles identified in the second identification area are marked as W2P1 to W2Pm; the articles identified in the third identification area are marked as W3P1 to W3Pk; wherein n, m and k are positive integers;
Step S206: setting the articles which have no movement in position and repeatedly appear in each slice as non-associated articles;
obtaining a video tag, and setting an article related to the tag as a tag article;
step S207: screening out non-associated articles and labeled articles, setting the rest articles as associated articles, counting the occurrence time, occurrence times and occurrence areas of the associated articles in a video, substituting the occurrence time and the occurrence times of the associated articles in the video into a first article identification area calculation formula, a second article identification area calculation formula and a third article identification area calculation formula respectively according to the occurrence areas of the associated articles, carrying out association calculation to obtain association values, and carrying out association sequencing on the association values from large to small;
the first object recognition area calculation formula is configured asWherein M1 is the correlation value of the first object recognition area, A 1 The article relevance weight of the first article identification area is B, the time conversion coefficient is B, t is the first appearance time of the article, and C is the occurrence times of the article;
the second recognition area calculation formula is configured asWherein M2 is the correlation value of the second object recognition area, A 2 The article relevance weight of the second article identification area is B, the time conversion coefficient is B, t is the first appearance time of the article, and C is the occurrence times of the article;
The third recognition area calculation formula is configured asWherein M3 is the correlation value of the third object recognition area, A 3 The article relevance weight of the third article identification area is B, the time conversion coefficient is B, t is the first appearance time of the article, and C is the occurrence times of the article;
step S208: screening the relevance articles with relevance ordered in the first three, acquiring the labels and the video labels of the relevance articles ordered in the first three, and setting the labels as relevance labels;
step S3: acquiring an association tag and a short video advertisement, and screening the short video advertisement according to the association tag to acquire an advertisement to be put;
step S4: analyzing and processing the preference advertisement information of the user;
the step S4 further includes the following sub-steps:
step S401: acquiring the playing progress of different short video advertisements by a user;
step S402: setting a first advertisement playing progress and a second advertisement playing progress; the first advertisement playing progress is smaller than the second advertisement playing progress;
step S403: setting short video advertisements with the watching progress of the user smaller than the playing progress of the first advertisements as first user preference short video advertisements, acquiring labels of the first user preference short video advertisements, and setting the labels as first labels;
Step S404: setting short video advertisements with the watching progress of the user being greater than or equal to that of the first advertisement and smaller than that of the second advertisement as second user preference short video advertisements, acquiring labels of the second user preference short video advertisements, and setting the labels as second labels;
step S405: setting short video advertisements with the user watching progress being greater than or equal to the second advertisement playing progress as third user preference short video advertisements, acquiring labels of the third user preference short video advertisements, and setting the labels as third labels;
step S406: obtaining the connection times of the user clicking advertisements, setting the advertisements corresponding to the user clicking links as fourth user preference short video advertisements, obtaining the labels of the fourth user preference short video advertisements, and setting the labels as fourth labels.
Step S5: acquiring a first label, a second label, a third label and a fourth label; classifying advertisements to be placed according to the first label, the second label, the third label and the fourth label, classifying the advertisements to be placed into a first type advertisement, a second type advertisement, a third type advertisement and a fourth type advertisement, distributing and adjusting the placed quantity of the first type advertisement, the second type advertisement, the third type advertisement and the fourth type advertisement, and outputting a placed adjustment result.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media having computer-usable program code embodied therein. The storage medium may be implemented by any type or combination of volatile or nonvolatile Memory devices, such as static random access Memory (Static Random Access Memory, SRAM), electrically erasable Programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), erasable Programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), programmable Read-Only Memory (PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
The above examples are only specific embodiments of the present invention, and are not intended to limit the scope of the present invention, but it should be understood by those skilled in the art that the present invention is not limited thereto, and that the present invention is described in detail with reference to the foregoing examples: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (5)
1. An optimized processing system for short video advertisement delivery is characterized in that the processing system comprises a preference acquisition module, a video processing module and an advertisement adjustment module;
the preference acquisition module is used for acquiring preference video information and preference advertisement information of a user;
the video processing module is used for analyzing and processing preference video information of a user, firstly obtaining preference video of the user, slicing the preference video to obtain slice pictures, then dividing object identification areas and identifying objects of the slice pictures to obtain associated object information in different areas, finally calculating the associated object information to obtain object associated value sorting, and obtaining an associated label according to the object associated value sorting;
The associated article information comprises article occurrence times and article first occurrence time;
the video processing module is also used for analyzing and processing the preference advertisement information of the user, and obtaining a first label, a second label, a third label and a fourth label according to the playing progress of the user on different short video advertisements;
the advertisement adjustment module is used for screening the advertisement according to the relevance label short video advertisement to obtain an advertisement to be screened; classifying advertisements to be put according to the first label, the second label, the third label and the fourth label obtained by the video processing module, obtaining the put quantity ratio of the advertisements to be put, and outputting a put adjustment result;
the video processing module comprises a preference video processing unit, an associated article preprocessing unit and a preference advertisement processing unit, wherein the preference video processing unit is configured with a preference video processing strategy, and the preference video processing strategy comprises the following steps: slicing the watched part of the obtained user preference video, performing relevance area division on all pictures obtained through slicing, dividing the pictures into a first object recognition area, a second object recognition area and a third object recognition area, performing object recognition analysis on objects appearing in the first object recognition area, the second object recognition area and the third object recognition area respectively, and marking the objects identified in the first object recognition area as W1P1 to W1Pn; the articles identified in the second identification area are marked as W2P1 to W2Pm; the articles identified in the third identification area are marked as W3P1 to W3Pk; wherein n, m and k are positive integers;
Setting the articles which have no movement in position and repeatedly appear in each slice as non-associated articles;
obtaining a video tag, and setting an article related to the tag as a tag article;
screening out non-associated articles and labeled articles, setting the rest articles as associated articles, counting the occurrence time, occurrence times and occurrence areas of the associated articles in a video, substituting the occurrence time and the occurrence times of the associated articles in the video into a first article identification area calculation formula, a second article identification area calculation formula and a third article identification area calculation formula respectively according to the occurrence areas of the associated articles, carrying out association calculation to obtain association values, and carrying out association sequencing on the association values from large to small;
screening the relevance articles with relevance ordered in the first three, acquiring the labels and the video labels of the relevance articles ordered in the first three, and setting the labels as relevance labels;
the associated article preprocessing unit is configured with a first preprocessing strategy and a second preprocessing strategy;
the first preprocessing strategy comprises the following steps: randomly selecting a plurality of slice pictures of different videos, and dividing the slice pictures by using a first dividing method, wherein the first dividing method comprises the following steps: the method comprises the steps of obtaining a first to-be-determined area through reducing the frame of a slice picture according to a first proportion, obtaining a second to-be-determined area through reducing the frame of the slice picture according to a second proportion, setting the first to-be-determined area as a first pretreatment area, setting an area between the first to-be-determined area and the second to-be-determined area as a second pretreatment area, and setting an area between the second to-be-determined area and the frame of the slice picture as a third pretreatment area, wherein the first proportion is smaller than the second proportion;
Screening objects appearing in the first pretreatment area, the second pretreatment area and the third pretreatment area by manpower, setting the objects related to the video as effective objects, respectively counting the effective object distribution rates in the first pretreatment area, the second pretreatment area and the third pretreatment area of a plurality of slice pictures, acquiring the difference values of the effective object distribution rates in the first pretreatment area, the second pretreatment area and the third pretreatment area, and setting the difference values as first difference values;
the second preprocessing strategy comprises the following steps: randomly selecting a plurality of slice pictures of different videos, and dividing the slice pictures by using a second dividing method, wherein the second dividing method comprises the following steps: the frame of the slice picture is reduced according to a third proportion to obtain a third to-be-determined area, the third to-be-determined area is set to be a fourth preprocessing area, and an area between the third to-be-determined area and the frame of the slice picture is set to be a fifth preprocessing area; the fourth preprocessing area is close to the center of the picture, and the area of the fourth preprocessing area is larger than that of the fifth preprocessing area; dividing the fourth pretreatment area into a sixth pretreatment area and a seventh pretreatment area according to the upper and lower directions, wherein the areas of the sixth pretreatment area and the seventh pretreatment area are equal;
Screening the articles appearing in the slice images by manpower, setting the articles related to the video as effective articles, respectively counting the effective article distribution rates in a fifth pretreatment area, a sixth pretreatment area and a seventh pretreatment area of a plurality of slice images, acquiring the difference values of the effective article distribution rates in the fifth pretreatment area, the sixth pretreatment area and the seventh pretreatment area, and setting the difference values as second difference values;
the associated article preprocessing unit is further configured with a distribution rate comparison strategy, and the distribution rate comparison strategy comprises: comparing the first difference value with the second difference value, and dividing the relevance area by using a dividing method with large difference value;
dividing the relevance area to obtain three pretreatment areas, and sequentially setting the three pretreatment areas into a first object identification area, a second object identification area and a third object identification area according to the effective object distribution rate from large to small;
obtaining article relevance weights of the first article recognition area, the second article recognition area and the third article recognition area according to the effective article distribution rates in the first article recognition area, the second article recognition area and the third article recognition area;
the first object recognition area calculation formula is configured as Wherein M1 is the correlation value of the first object recognition area, A 1 The article relevance weight of the first article identification area is B, the time conversion coefficient is B, t is the first appearance time of the article, and C is the occurrence times of the article;
the second recognition area calculation formula is configured asWherein M2 is the correlation value of the second object recognition area, A 2 The article relevance weight of the second article identification area is B, the time conversion coefficient is B, t is the first appearance time of the article, and C is the occurrence times of the article;
the third recognition area calculation formula is configured asWherein M3 is the correlation value of the third object recognition area, A 3 And (3) the article relevance weight of the third article identification area, B is a time conversion coefficient, t is the first appearance time of the article, and C is the appearance times of the article.
2. The optimization processing system for short video advertisement delivery according to claim 1, wherein the preference acquisition module comprises a preference video acquisition unit and a preference advertisement acquisition unit; the preference video acquisition unit is configured with a preference video acquisition strategy comprising:
acquiring the playing progress of a user on the short video, setting the video with the playing progress exceeding the short video progress threshold as a user preference video, and acquiring a user preference video label;
The preferred advertisement acquisition unit is further configured with a preferred advertisement acquisition policy comprising: and acquiring the playing progress of the short video advertisement watched by the user and the video tag of the short video advertisement.
3. The optimized processing system for short video advertisement delivery of claim 2, wherein said preferred advertisement processing unit is configured with preferred advertisement processing policies comprising: setting a first advertisement playing progress and a second advertisement playing progress; the first advertisement playing progress is smaller than the second advertisement playing progress;
setting short video advertisements with the watching progress of the user smaller than the playing progress of the first advertisements as first user preference short video advertisements, acquiring labels of the first user preference short video advertisements, and setting the labels as first labels;
setting short video advertisements with the watching progress of the user being greater than or equal to that of the first advertisement and smaller than that of the second advertisement as second user preference short video advertisements, acquiring labels of the second user preference short video advertisements, and setting the labels as second labels;
setting short video advertisements with the user watching progress being greater than or equal to the second advertisement playing progress as third user preference short video advertisements, acquiring labels of the third user preference short video advertisements, and setting the labels as third labels;
Obtaining the connection times of the user clicking advertisements, setting the advertisements corresponding to the user clicking links as fourth user preference short video advertisements, obtaining the labels of the fourth user preference short video advertisements, and setting the labels as fourth labels.
4. The optimal processing system for short video advertising as recited in claim 3, wherein the advertisement adjustment module is configured with an advertisement adjustment policy, the advertisement adjustment policy comprising: screening advertisements according to the relevance labels, setting the advertisements conforming to the relevance labels as advertisements to be put, and acquiring a first label, a second label, a third label and a fourth label; classifying advertisements to be placed according to the first label, the second label, the third label and the fourth label, classifying the advertisements to be placed into a first type advertisement, a second type advertisement, a third type advertisement and a fourth type advertisement, distributing and adjusting the placed quantity of the first type advertisement, the second type advertisement, the third type advertisement and the fourth type advertisement, and outputting a placed adjustment result.
5. A method of processing for an optimized processing system for short video advertising as claimed in any one of claims 1-4, said method of processing comprising:
Collecting preference video information and preference advertisement information of a user;
analyzing and processing preference video information of a user, firstly obtaining preference video of the user, and slicing the preference video to obtain slice pictures; dividing object identification areas and identifying objects of the slice pictures to obtain associated object information in different areas, and finally calculating the associated object information to obtain object associated value sequences and obtaining an associated label according to the object associated value sequences;
screening short video advertisements according to the relevance labels to obtain advertisements to be screened;
analyzing and processing the preference advertisement information of the user, and obtaining a first label, a second label, a third label and a fourth label according to the playing progress of the user on different short video advertisements;
classifying advertisements to be put according to the obtained first label, second label, third label and fourth label, obtaining the put quantity ratio of the advertisements to be put, and outputting the put adjustment result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310488720.6A CN116614679B (en) | 2023-05-04 | 2023-05-04 | Optimization processing method and system for short video advertisement delivery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310488720.6A CN116614679B (en) | 2023-05-04 | 2023-05-04 | Optimization processing method and system for short video advertisement delivery |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116614679A CN116614679A (en) | 2023-08-18 |
| CN116614679B true CN116614679B (en) | 2024-02-09 |
Family
ID=87673871
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310488720.6A Active CN116614679B (en) | 2023-05-04 | 2023-05-04 | Optimization processing method and system for short video advertisement delivery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116614679B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106600343A (en) * | 2016-12-30 | 2017-04-26 | 中广热点云科技有限公司 | Method and system for managing online video advertisement associated with video content |
| 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 |
| CN115037969A (en) * | 2022-08-12 | 2022-09-09 | 道有道科技集团股份公司 | Short video advertisement putting intelligent analysis system and method based on data identification |
| CN115375379A (en) * | 2022-10-26 | 2022-11-22 | 承德石油高等专科学校 | Advertisement pushing method and system based on short video platform |
| CN115471872A (en) * | 2022-09-23 | 2022-12-13 | 浙江大华技术股份有限公司 | Behavior detection method and device for distributing advertisement, electronic equipment and storage medium |
-
2023
- 2023-05-04 CN CN202310488720.6A patent/CN116614679B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106600343A (en) * | 2016-12-30 | 2017-04-26 | 中广热点云科技有限公司 | Method and system for managing online video advertisement associated with video content |
| 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 |
| CN115037969A (en) * | 2022-08-12 | 2022-09-09 | 道有道科技集团股份公司 | Short video advertisement putting intelligent analysis system and method based on data identification |
| CN115471872A (en) * | 2022-09-23 | 2022-12-13 | 浙江大华技术股份有限公司 | Behavior detection method and device for distributing advertisement, electronic equipment and storage medium |
| CN115375379A (en) * | 2022-10-26 | 2022-11-22 | 承德石油高等专科学校 | Advertisement pushing method and system based on short video platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116614679A (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110489644B (en) | Information pushing method, information pushing device, computer readable storage medium and computer equipment | |
| CN109672939B (en) | Method and device for marking video content popularity | |
| CN110704674B (en) | Video playing integrity prediction method and device | |
| CN106326391B (en) | Multimedia resource recommendation method and device | |
| CN110737859B (en) | UP master matching method and device | |
| CN106599165B (en) | content recommendation method and server based on playing behavior | |
| CN106649316A (en) | Video pushing method and device | |
| CN106202393B (en) | Media information pushing method and device | |
| CN105139021B (en) | A kind of method and system for realizing TV user Fast Classification based on rough set theory | |
| CN106469202A (en) | A kind of data analysing method of video display big data platform | |
| CN105608125B (en) | Information processing method and server | |
| CN108777701A (en) | A kind of method and device of determining receiver | |
| CN113643070A (en) | Intelligent information pushing method and system based on big data | |
| WO2022007626A1 (en) | Video content recommendation method and apparatus, and computer device | |
| CN107766446A (en) | Method for pushing, device, storage medium and the processor of information | |
| CN104967690A (en) | Information push method and device | |
| Doyle | Television and the development of the data economy: Data analysis, power and the public interest | |
| CN106919692B (en) | Method and device for pushing message | |
| CN116614679B (en) | Optimization processing method and system for short video advertisement delivery | |
| CN115374348A (en) | Information recommendation method, information recommendation device and readable storage medium | |
| CN115834959A (en) | Video recommendation information determination method and device, electronic equipment and medium | |
| CN111932315B (en) | Method and device for data display, electronic equipment and computer readable storage medium | |
| CN112148964B (en) | Information processing and recommending method, system and equipment | |
| CN111382343B (en) | Label system generation method and device | |
| CN106060589A (en) | Method and device for analyzing program information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240117 Address after: Room 408, 2nd Floor, Building 2, Wansheng Commercial City, Tangqi Town, Linping District, Hangzhou City, Zhejiang Province, 311119 Applicant after: Hangzhou Yuanmei Technology Co.,Ltd. Applicant after: Wuhan Jingyue Digital Media Technology Co.,Ltd. Address before: 430074 Department of advertising, Central South University for nationalities, No. 182, Minzu Avenue, Hongshan District, Wuhan City, Hubei Province Applicant before: Wuhan Jingyue Digital Media Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |