WO2014094497A1 - 视频内容中自适应投放广告的方法及系统 - Google Patents

视频内容中自适应投放广告的方法及系统 Download PDF

Info

Publication number
WO2014094497A1
WO2014094497A1 PCT/CN2013/085784 CN2013085784W WO2014094497A1 WO 2014094497 A1 WO2014094497 A1 WO 2014094497A1 CN 2013085784 W CN2013085784 W CN 2013085784W WO 2014094497 A1 WO2014094497 A1 WO 2014094497A1
Authority
WO
WIPO (PCT)
Prior art keywords
advertisement content
similarity
video
content
video frame
Prior art date
Application number
PCT/CN2013/085784
Other languages
English (en)
French (fr)
Inventor
朱定局
杨望仙
Original Assignee
深圳先进技术研究院
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 深圳先进技术研究院 filed Critical 深圳先进技术研究院
Publication of WO2014094497A1 publication Critical patent/WO2014094497A1/zh

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25Management 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
    • H04N21/266Channel 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
    • H04N21/2668Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/234Processing of video elementary streams, e.g. splicing of video streams or manipulating encoded video stream scene graphs
    • H04N21/23418Processing 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
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25Management 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
    • H04N21/251Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45Management 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
    • H04N21/458Scheduling content for creating a personalised stream, e.g. by combining a locally stored advertisement with an incoming stream; Updating operations, e.g. for OS modules ; time-related management operations
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/81Monomedia components thereof
    • H04N21/812Monomedia components thereof involving advertisement data

Definitions

  • the present invention relates to the field of computers, and in particular, to a method for adaptively placing advertisements in video content and a system for adaptively placing advertisements in video content.
  • the advertisement content is usually played between the video clips, for example, the advertisement time of the television program, the different episodes of the TV series, and the continuous two segments of the network video on demand.
  • the content of the advertisement between the video content and the played advertisement content is usually a predetermined advertisement content, such as a newly-advertised new advertisement or an advertisement determined based on other selection conditions, and whether the advertisement content and the played video are There is no concern about the continuity or relevance of the content. For example, after the car video clip, the advertisement of the alcohol may be played, which makes the insertion of the advertisement content unnatural, affecting the consistency between the video content and the advertisement content. .
  • an object of the present invention is to provide a method for adaptively placing advertisements in video content and a system for adaptively placing advertisements in video content, which can improve video content and advertisements. Coherence between content.
  • a method for adaptively placing advertisements in video content comprising the steps of:
  • the advertisement content with the highest similarity is inserted into the video frame.
  • a system for adaptively placing advertisements in video content including:
  • a video frame reading module configured to read a video frame to be inserted into the advertisement content
  • An object set identification module configured to identify the video frame and a set of objects in a preset number of video frames before the video frame
  • a similarity maximum advertisement content determining module configured to calculate a similarity between each advertisement content in the advertisement content library and the object set, and determine an advertisement content with the greatest similarity
  • An advertisement content insertion module configured to insert the advertisement content with the highest similarity into the video frame.
  • the video frame and the object set in the preset number of video frames before the video frame are identified, and are respectively calculated in the advertisement content library.
  • the similarity between each advertisement content and the object set, and inserting the advertisement content with the highest similarity into the video frame Since the most similar advertisement content has the greatest similarity with the video frame to be inserted into the advertisement content, that is, the advertisement content with the highest similarity is most relevant to the content of the plurality of videos continuously played, the similarity is Inserting the above-mentioned video frame with the largest advertisement content can better make continuity between the content of the played video frame and the advertisement content, thereby improving the consistency between the video content and the advertisement content.
  • Embodiment 1 is a schematic flowchart of Embodiment 1 of a method for adaptively placing an advertisement in a video content according to the present invention
  • Embodiment 2 is a schematic flowchart of Embodiment 2 of a method for adaptively placing an advertisement in a video content according to the present invention
  • Embodiment 3 is a schematic structural diagram of Embodiment 1 of a system for adaptively placing advertisements in a video content according to the present invention
  • Embodiment 4 is a schematic structural diagram of Embodiment 2 of a system for adaptively placing advertisements in the video content of the present invention.
  • FIG. 1 is a schematic flowchart diagram of Embodiment 1 of a method for adaptively placing an advertisement in a video content according to the present invention.
  • the method in the first embodiment includes the following steps:
  • Step S101 Read a video frame of the advertisement content to be inserted
  • Step S102 Identify the video frame and a set of objects in a preset number of video frames before the video frame;
  • Step S103 calculating a similarity between each advertisement content in the advertisement content library and the object set;
  • Step S104 Insert the advertisement content with the highest similarity into the video frame.
  • the video frame and the object set in the preset number of video frames before the video frame are identified, and the advertisement content is separately calculated.
  • the similarity between each advertisement content in the library and the object set, and the advertisement content with the highest similarity is inserted into the video frame. Since the most similar advertisement content has the greatest similarity with the video frame to be inserted into the advertisement content, that is, the advertisement content with the highest similarity is most relevant to the content of the plurality of videos continuously played, the similarity is Inserting the above-mentioned video frame with the largest advertisement content can better make continuity between the content of the played video frame and the advertisement content, thereby improving the consistency between the video content and the advertisement content.
  • the manner of reading the video frame to be inserted into the advertisement content and the method of identifying the object set in the preset number of video frames before the video frame may be performed in any manner that is currently available or may occur in the future.
  • the preset number here can be set according to actual needs, for example, any one of 0, 1, 2, ..., N, and the like.
  • the objects in the object set here may be any kind of objects in these video frames, or may be specific types of objects, such as alcohol, automobiles, household goods, electronic appliances, cosmetics, etc., types of objects.
  • the object of a specific kind can be realized without limitation, and will not be described herein.
  • the specific manner of determining the similarity may be:
  • the similarity between the object set and the current advertisement content is determined according to the similarity between the current advertisement content and each object.
  • the specific comprehensive determination manner may be set based on actual needs, for example, the current advertisement content may be similar to each object.
  • the maximum value in the degree is determined as the similarity between the object set and the current advertisement content, or may be the average of the similarity between the current advertisement content and each object as the similarity between the object set and the current advertisement content, or may be the current advertisement.
  • the weighted average of the similarity between the content and each object is taken as the similarity between the object set and the current advertisement content.
  • the video frame to be inserted into the advertisement content is v;
  • the similarity between each advertisement content aj and the object set T is first calculated and determined.
  • the specific manner of calculating the similarity may adopt any one that has been existing and will appear in the future. Way to proceed.
  • the similarity between the objects and the advertisement content aj is calculated, respectively, so that the similarities s1j, s2j of the objects in the object set and the advertisement content aj are respectively obtained.
  • S3j, ..., snj and then synthesize these similarities, and obtain the similarity sj of the object set and the advertisement content aj.
  • the maximum value of the similarity between each object and the advertisement content aj may be used as the similarity sj between the object set and the advertisement content aj, that is,
  • a weighted average of the similarity between each object and the advertisement content aj may be used as the similarity sj between the object set and the advertisement content aj, that is,
  • k1, k2, k3, ..., kn represent the weighting values of s1j, s2j, s3j, ..., snj, respectively, and the weighting value can be determined according to actual needs.
  • the similarity between other advertisement contents and the object set can be calculated and recorded as s1, s2, s3, ..., sm.
  • the advertisement content corresponding to the maximum similarity smax may be inserted into the video frame v of the advertisement content to be inserted.
  • FIG. 2 is a schematic flowchart of the second embodiment of the method for adaptively placing advertisements in the video content of the present invention.
  • the difference from the first embodiment is mainly that the content is based on the advertisement content in this embodiment.
  • the type of the advertisement is inserted into the video frame in a different manner.
  • the method in the second embodiment includes the following steps:
  • Step S201 Read a video frame of the advertisement content to be inserted
  • Step S202 Identify the video frame and a set of objects in a preset number of video frames before the video frame;
  • Step S203 calculating a similarity between each advertisement content in the advertisement content library and the object set;
  • Step S204 determining whether the advertisement content with the highest similarity is a still image or a character, and if so, proceeding directly to step S207, and if not, proceeding to step S205;
  • Step S205 determining whether the advertisement content with the highest similarity is a multi-frame video, and if yes, proceeding to step S206;
  • Step S206 inserting the advertisement content with the highest similarity into the frame after the video frame
  • Step S207 Insert the advertisement content with the highest similarity into the background of the video frame.
  • the insertion is implemented based on the difference in the type of the advertisement content, when the advertisement content with the largest similarity is a still image or a text. Inserting the advertisement content with the highest similarity into the background of the video frame.
  • the advertisement content with the largest similarity is a multi-frame video
  • the advertisement content is inserted into the frame after the video frame, and different types are realized. The insertion of the advertising content.
  • the determination is made as to whether or not the still image or the character is determined, and whether or not the multi-frame video is determined.
  • the sequence may not be limited to the above-described sequential determination order.
  • the judgment of still images or texts and multi-frame videos may be performed in either order or simultaneously.
  • the present invention further provides a system for adaptively placing advertisements in video content, and the following is a detailed description of an embodiment of a system for adaptively placing advertisements in the video content of the present invention. .
  • FIG. 3 is a schematic structural diagram of Embodiment 1 of a system for adaptively placing advertisements in the video content of the present invention.
  • the system in the first embodiment includes:
  • a video frame reading module 301 configured to read a video frame to be inserted into the advertisement content
  • the object set identification module 302 is configured to identify the video frame and a set of objects in a preset number of video frames before the video frame;
  • the similarity maximum advertisement content determining module 303 is configured to calculate a similarity between each advertisement content in the advertisement content library and the object set, and determine the advertisement content with the largest similarity;
  • the advertisement content insertion module 304 is configured to insert the advertisement content with the highest similarity into the video frame.
  • the video frame and the object set in the preset number of video frames before the video frame are identified, and the advertisement content is separately calculated.
  • the similarity between each advertisement content in the library and the object set, and the advertisement content with the highest similarity is inserted into the video frame. Since the most similar advertisement content has the greatest similarity with the video frame to be inserted into the advertisement content, that is, the advertisement content with the highest similarity is most relevant to the content of the plurality of videos continuously played, the similarity is Inserting the above-mentioned video frame with the largest advertisement content can better make continuity between the content of the played video frame and the advertisement content, thereby improving the consistency between the video content and the advertisement content.
  • the manner in which the video frame reading module 301 reads the video frame to be inserted into the advertisement content, and the object set identification module 302 identifies the object set in the preset number of video frames before the video frame may be the existing one. Or any way that may occur in the future.
  • the preset number here can be set according to actual needs, for example, any one of 0, 1, 2, ..., N, and the like.
  • the objects in the object set here may be any kind of objects in these video frames, or may be specific types of objects, such as alcohol, automobiles, household goods, electronic appliances, cosmetics, etc., types of objects.
  • the object of a specific kind can be realized without limitation, and will not be described herein.
  • the similarity maximum advertisement content determining module 303 calculates and determines the similarity between each advertisement content in the advertisement content library and the object set, since there are multiple advertisement contents in the advertisement content library, the object has a plurality of objects in a group, and therefore, specific determination The way of similarity can be combined with these multiple objects.
  • the similarity maximum advertisement content determining module 303 may specifically include:
  • a single object similarity determining module 3031 configured to separately calculate a similarity between the current advertising content and each object in the object set;
  • the similarity comprehensive determination module 3032 is configured to comprehensively determine the similarity between the object set and the current advertisement content according to the similarity between the current advertisement content and each of the objects, and according to the similarity between the object set and each advertisement content. Identify the most similar ad content.
  • the similarity comprehensive determination module 3032 comprehensively determines the similarity between the object set and the current advertisement content according to the similarity between the current advertisement content and each object, the specific comprehensive determination manner may be set based on actual needs.
  • the similarity comprehensive determination module 3032 may determine the maximum value of the current advertisement content and the similarity of each object as the similarity between the object set and the current advertisement content.
  • the similarity comprehensive determination module 3032 may be an average of the similarity between the current advertisement content and each object as the similarity between the object set and the current advertisement content.
  • the similarity comprehensive determination module 3032 may also be a weighted average of the similarity between the current advertisement content and each object as the similarity between the object set and the current advertisement content.
  • the similarity comprehensive determination module 3032 can also use other comprehensive determination methods to obtain the similarity between the object set and the current advertisement content, which is not exhaustive.
  • FIG. 4 is a schematic structural diagram of a second embodiment of a system for adaptively placing advertisements in the video content of the present invention.
  • the difference from the first embodiment is mainly that the second embodiment further includes an advertisement content type discriminating module 305.
  • the system in the second embodiment includes:
  • a video frame reading module 301 configured to read a video frame to be inserted into the advertisement content
  • the object set identification module 302 is configured to identify the video frame and a set of objects in a preset number of video frames before the video frame;
  • the similarity maximum advertisement content determining module 303 is configured to calculate a similarity between each advertisement content in the advertisement content library and the object set, and determine the advertisement content with the largest similarity;
  • the advertisement content type discriminating module 305 is configured to determine the type of the advertisement content with the highest similarity
  • the advertisement content insertion module 304 is configured to insert the advertisement content with the highest similarity into the video frame according to the type determined by the advertisement content type discriminating module 305.
  • the advertisement content type discriminating module 305 can be used to determine whether the advertisement content with the highest similarity is a multi-frame video.
  • the advertisement content insertion module 304 can be used in the advertisement content type discriminating module 305.
  • the advertisement content with the highest similarity is inserted after the video frame.
  • the advertisement content type discriminating module 305 can be configured to determine whether the advertisement content with the highest similarity is a still image or a text.
  • the advertisement content insertion module 304 can be used for the advertisement content type.
  • the determination module 305 determines that the advertisement content having the largest similarity is a still image or a character, the advertisement content having the highest similarity is inserted into the background of the video frame.
  • the advertisement content type discriminating module 305 can perform judgment in combination with still images or text, multi-frame video. In the case of other types of advertising content, it may also be based on or in combination with other types to determine the type of similarly largest advertising content.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Image Analysis (AREA)

Abstract

一种视频内容中自适应投放广告的方法及系统,该方法包括步骤:读取待插入广告内容的视频帧;识别所述视频帧以及该视频帧之前的预设数目视频帧中的对象集;计算确定广告内容库中各广告内容与所述对象集的相似度;将相似度最大的广告内容插入所述视频帧。根据本发明方案,能够更好地使得播放的视频帧的内容与广告内容之间存在连续性,提高了视频内容与广告内容之间的连贯性。

Description

视频内容中自适应投放广告的方法及系统
【技术领域】
本发明涉及计算机领域,特别涉及一种视频内容中自适应投放广告的方法以及一种视频内容中自适应投放广告的系统。
【背景技术】
随着计算机、互联网等技术日益发展,视频内容的应用也日益广泛,各种视频类应用层出不穷。面对巨大的视频类应用的市场,在视频内容播放时的广告投放方式也应运而生。在目前的视频内容播放时的广告投放方式中,通常是在视频片段之间进行广告内容的播放,例如电视节目的广告时间、电视连续剧的不同剧集之间、网络视频点播时连续的两段视频内容之间,且所播放的广告内容,通常是事先设定的某个广告内容,例如最新投放的新广告、或者基于其他的选择条件所确定的广告,而广告内容是否与所播放的视频内容有连续性或者关联性并不关心,例如,在汽车类视频片段之后可能播放的是酒类的广告,从而导致广告内容的插入很不自然,影响了视频内容与广告内容之间的连贯性。
【发明内容】
基于此,针对上述现有技术中存在的问题,本发明的目的在于提供一种视频内容中自适应投放广告的方法以及一种视频内容中自适应投放广告的系统,其可以提高视频内容与广告内容之间的连贯性。
为达到上述目的,本发明采用以下技术方案:
一种视频内容中自适应投放广告的方法,包括步骤:
读取待插入广告内容的视频帧;
识别所述视频帧以及该视频帧之前的预设数目视频帧中的对象集;
计算确定广告内容库中各广告内容与所述对象集的相似度;
将相似度最大的广告内容插入所述视频帧。
一种视频内容中自适应投放广告的系统,包括:
视频帧读取模块,用于读取待插入广告内容的视频帧;
对象集识别模块,用于识别所述视频帧以及该视频帧之前的预设数目视频帧中的对象集;
相似度最大广告内容确定模块,用于计算确定广告内容库中各广告内容与所述对象集的相似度,确定相似度最大的广告内容;
广告内容插入模块,用于将相似度最大的广告内容插入所述视频帧。
根据本发明方案,其是在读取了待插入广告内容的视频帧之后,识别出该视频帧以及该视频帧之前的预设数目视频帧中的对象集,并分别计算出广告内容库中的各广告内容与该对象集的相似度,将相似度最大的广告内容插入到该视频帧。由于相似度最大的广告内容具有与待插入广告内容的视频帧的最大相似度,也就是说,该相似度最大的广告内容与连续播放的多个视频的内容是最相关的,将该相似度最大的广告内容插入上述视频帧能够更好地使得播放的视频帧的内容与广告内容之间存在连续性,从而提高了视频内容与广告内容之间的连贯性。
【附图说明】
图1是本发明的视频内容中自适应投放广告的方法实施例一的流程示意图;
图2是本发明的视频内容中自适应投放广告的方法实施例二的流程示意图;
图3是本发明的视频内容中自适应投放广告的系统实施例一的结构示意图;
图4是本发明的视频内容中自适应投放广告的系统实施例二的结构示意图。
【具体实施方式】
以下结合其中的较佳实施方式对本发明方案进行详细阐述。在下述说明中,先针对本发明的视频内容中自适应投放广告的方法的实施例进行说明,再针对本发明的视频内容中自适应投放广告的系统的实施例进行说明。
实施例一
图1中示出了本发明的视频内容中自适应投放广告的方法实施例一的流程示意图。
如图1所示,本实施例一中的方法包括步骤:
步骤S101:读取待插入广告内容的视频帧;
步骤S102:识别所述视频帧以及该视频帧之前的预设数目视频帧中的对象集;
步骤S103:计算确定广告内容库中各广告内容与所述对象集的相似度;
步骤S104:将相似度最大的广告内容插入所述视频帧。
根据本实施例中的方案,其是在读取了待插入广告内容的视频帧之后,识别出该视频帧以及该视频帧之前的预设数目视频帧中的对象集,并分别计算出广告内容库中的各广告内容与该对象集的相似度,将相似度最大的广告内容插入到该视频帧。由于相似度最大的广告内容具有与待插入广告内容的视频帧的最大相似度,也就是说,该相似度最大的广告内容与连续播放的多个视频的内容是最相关的,将该相似度最大的广告内容插入上述视频帧能够更好地使得播放的视频帧的内容与广告内容之间存在连续性,从而提高了视频内容与广告内容之间的连贯性。
其中,上述读取待插入广告内容的视频帧的方式、识别该视频帧之前的预设数目视频帧中的对象集的方式可以是采用目前已有的或者将来可能出现的任何一种方式进行。这里的预设数目,可以根据实际需要进行设定,例如0、1、2、……N等中的任意一个自然数。这里的对象集中的对象,可以是这些视频帧中的任何种类的对象,也可以是特定种类的对象,例如酒类、汽车类、生活用品类、电子用品类、化妆品类等等,对象的种类可以不加以限制,也可以实现制成特定种类的对象,在此不予赘述。
在计算确定广告内容库中各广告内容与所述对象集相似度时,由于广告内容库中有多个广告内容,对象集中有多个对象,因此,具体的确定相似度的方式可以是:
分别计算当前广告内容与对象集中各对象的相似度;
根据当前广告内容与各对象的相似度综合确定对象集与当前广告内容的相似度。
在根据当前广告内容与各对象的相似度综合确定对象集与当前广告内容的相似度时,具体的综合确定方式可以基于实际需要进行设定,例如,可以是将当前广告内容与各对象的相似度中的最大值确定为对象集与当前广告内容的相似度,也可以是将当前广告内容与各对象的相似度的平均值作为对象集与当前广告内容的相似度,也可以是将当前广告内容与各对象的相似度的加权平均值作为对象集与当前广告内容的相似度。
在其中一个具体示例中:记上述待插入广告内容的视频帧为v;记上述对象集为T,对象集T中的对象为ti,其中i=1、2、3、……n,n为自然数;记广告内容库为A,广告内容库中的各广告内容记为aj,其中j=1、2、3、……m,m为自然数。
根据上述记录方式,先计算确定出各广告内容aj与对象集T的相似度。
以当前的广告内容aj为例,在计算确定该广告内容aj与对象集T中的各对象ti的相似度sij,具体的计算相似度的方式可以采用目前已有的以及将来出现的任何一种方式进行。
对于对象集T中的各对象t1、t2、t3、……、tn,分别计算这些对象与广告内容aj的相似度,从而分别得到对象集中的各对象与广告内容aj的相似度s1j、s2j、s3j、……、snj,再对这些相似度进行综合,得到对象集与该广告内容aj的相似度sj。
在对相似度进行综合时,在其中一个方式中,可以是将各对象与该广告内容aj的相似度的平均值作为对象集与该广告内容aj的相似度sj,即:
sj=[s1j+s2j+s3j+……+snj]/n。
在相似度进行综合的另外一种方式中,可以是将各对象与该广告内容aj的相似度中的最大值作为对象集与该广告内容aj的相似度sj,即:
sj=max{s1j,s2j,s3j,……,snj}。
在相似度进行综合的另外一种方式中,还可以是将各对象与该广告内容aj的相似度的加权平均值作为对象集与该广告内容aj的相似度sj,即:
sj=[ k1*s1j+k2*s2j+k3*s3j+……+kn*snj]/[k1+k2+k3+……+kn]
其中,k1、k2、k3、……、kn分别表示s1j、s2j、s3j、……、snj的加权值,该加权值可以根据实际需要进行确定。
当然根据实际需要,也可以采用其他的综合判定方式,在此不予穷举。
基于上述同样的方式,可以计算出其他的广告内容与对象集的相似度,分别记为s1、s2、s3、……、sm。
然后,基于这些相似度s1、s2、s3、……、sm中确定出最大相似度smax,smax=max{s1、s2、s3、……、sm},确定出该最大相似度smax对应的广告内容a。
随后,可将该最大相似度smax对应的广告内容插入上述待插入广告内容的视频帧v。
实施例二
图2中示出了本发明的视频内容中自适应投放广告的方法实施例二的流程示意图,在本实施例中,与上述实施例一的不同之处主要在于,本实施例中基于广告内容的类型的不同采用不同的方式将该广告内容插入到视频帧中。
如图2所示,本实施例二中的方法包括步骤:
步骤S201:读取待插入广告内容的视频帧;
步骤S202:识别所述视频帧以及该视频帧之前的预设数目视频帧中的对象集;
步骤S203:计算确定广告内容库中各广告内容与所述对象集的相似度;
步骤S204:判断相似度最大的广告内容是否为静止图像或者文字,若是,直接进入步骤S207,若否,进入步骤S205;
步骤S205:判断该相似度最大的广告内容是否为多帧视频,若是,进入步骤S206;
步骤S206:将该相似度最大的广告内容插入上述视频帧之后的帧;
步骤S207:将该相似度最大的广告内容插入上述视频帧的背景中。
根据本实施例中的方案,其是在将相似度最大的广告内容插入视频帧时,是基于该广告内容的类型的不同来实现插入,当该相似度最大的广告内容是静止图像或者文字时,是将该相似度最大的广告内容插入到视频帧的背景中,当该相似度最大的广告内容是多帧视频时,是将该广告内容插入到该视频帧之后的帧,实现了不同类型的广告内容的插入。
其中,在上述判断广告内容是否为禁止图像或者文字时,以及在判断广告内容是否为多帧视频时,可以采用目前已有的或者将来出现的各种可能的方式进行判断,在此不予详加赘述。
在本实施例的说明中,是以先对是否为静止图像或文字进行判断、再对是否为多帧视频进行判断为例进行说明,基于实际应用需要,可以不限于上述的先后判定顺序,对静止图像或文字、多帧视频的判断可以不分先后顺序,也可以是同时进行。在其中一些具体的应用示例中,还可以是只对视频图像或文字进行判断,也可以只是对多帧视频进行判断,具体的实现方式在此不再详加赘述。
本实施例中的其他技术特征与上述实施例一中的相同,在此不予多加赘述。
根据上述本发明的视频内容中自适应投放广告的方法,本发明还提供一种视频内容中自适应投放广告的系统,以下对本发明的视频内容中自适应投放广告的系统的实施例进行详细说明。
实施例一
图3中示出了本发明的视频内容中自适应投放广告的系统实施例一的结构示意图。
如图3所示,本实施例一中的系统包括有:
视频帧读取模块301,用于读取待插入广告内容的视频帧;
对象集识别模块302,用于识别所述视频帧以及该视频帧之前的预设数目视频帧中的对象集;
相似度最大广告内容确定模块303,用于计算确定广告内容库中各广告内容与所述对象集的相似度,并确定相似度最大的广告内容;
广告内容插入模块304,用于将相似度最大的广告内容插入所述视频帧。
根据本实施例中的方案,其是在读取了待插入广告内容的视频帧之后,识别出该视频帧以及该视频帧之前的预设数目视频帧中的对象集,并分别计算出广告内容库中的各广告内容与该对象集的相似度,将相似度最大的广告内容插入到该视频帧。由于相似度最大的广告内容具有与待插入广告内容的视频帧的最大相似度,也就是说,该相似度最大的广告内容与连续播放的多个视频的内容是最相关的,将该相似度最大的广告内容插入上述视频帧能够更好地使得播放的视频帧的内容与广告内容之间存在连续性,从而提高了视频内容与广告内容之间的连贯性。
其中,上述视频帧读取模块301读取待插入广告内容的视频帧的方式、对象集识别模块302识别该视频帧之前的预设数目视频帧中的对象集的方式可以是采用目前已有的或者将来可能出现的任何一种方式进行。这里的预设数目,可以根据实际需要进行设定,例如0、1、2、……N等中的任意一个自然数。这里的对象集中的对象,可以是这些视频帧中的任何种类的对象,也可以是特定种类的对象,例如酒类、汽车类、生活用品类、电子用品类、化妆品类等等,对象的种类可以不加以限制,也可以实现制成特定种类的对象,在此不予赘述。
相似度最大广告内容确定模块303在计算确定广告内容库中各广告内容与所述对象集相似度时,由于广告内容库中有多个广告内容,对象集中有多个对象,因此,具体的确定相似度的方式可以结合这多个对象来进行。如图3所示,该相似度最大广告内容确定模块303具体可以包括:
单对象相似度确定模块3031,用于分别计算当前广告内容与所述对象集中各对象的相似度;
相似度综合确定模块3032,用于根据当前广告内容与各所述对象的相似度综合确定所述对象集与当前广告内容的相似度,并根据所述对象集与各广告内容的相似度的大小确定相似度最大的广告内容。
相似度综合确定模块3032在根据当前广告内容与各对象的相似度综合确定对象集与当前广告内容的相似度时,具体的综合确定方式可以基于实际需要进行设定。
在其中一种方式中,相似度综合确定模块3032可以是将当前广告内容与各对象的相似度中的最大值确定为对象集与当前广告内容的相似度。
在另一种方式中,相似度综合确定模块3032可以是将当前广告内容与各对象的相似度的平均值作为对象集与当前广告内容的相似度。
在另一种方式中,相似度综合确定模块3032还可以是将当前广告内容与各对象的相似度的加权平均值作为对象集与当前广告内容的相似度。
根据实际需要,相似度综合确定模块3032还可以采用其他的综合判定方式来得到对象集与当前广告内容的相似度,在此不予穷举。
实施例二
图4中示出了本发明的视频内容中自适应投放广告的系统实施例二的结构示意图。在本实施例中,与上述实施例一的不同之处主要在于,本实施例二中还包括有广告内容类型判别模块305。
如图4所示,本实施例二中的系统包括有:
视频帧读取模块301,用于读取待插入广告内容的视频帧;
对象集识别模块302,用于识别所述视频帧以及该视频帧之前的预设数目视频帧中的对象集;
相似度最大广告内容确定模块303,用于计算确定广告内容库中各广告内容与所述对象集的相似度,并确定相似度最大的广告内容;
广告内容类型判别模块305,用于判断所述相似度最大的广告内容的类型;
广告内容插入模块304,用于根据广告内容类型判别模块305判定的类型,将相似度最大的广告内容插入所述视频帧。
在其中一个具体示例中,上述广告内容类型判别模块305,可用于判断上述相似度最大的广告内容是否为多帧视频,此时,上述广告内容插入模块304,可用于在广告内容类型判别模块305判定相似度最大的广告内容为多帧视频时,将相似度最大的广告内容插入上述视频帧之后。
在另一个具体示例中,上述广告内容类型判别模块305,可用于判断上述相似度最大的广告内容是否为静止图像或者文字,此时,上述所述广告内容插入模块304,可用于在广告内容类型判别模块305判定相似度最大的广告内容为静止图像或者文字时,将上述相似度最大的广告内容插入上述视频帧的背景中。
当然,基于实际需要,广告内容类型判别模块305可以结合静止图像或者文字、多帧视频进行判断。在有其他类型的广告内容的情况下,还可以是基于或者结合其他类型对相似对最大的广告内容的类型进行判定。
本实施例二中的其他技术特征与上述实施例一中的相同,在此不予赘述。
以上所述实施例仅表达了本发明的几种实施方式,其描述较为具体和详细,但并不能因此而理解为对本发明专利范围的限制。应当指出的是,对于本领域的普通技术人员来说,在不脱离本发明构思的前提下,还可以做出若干变形和改进,这些都属于本发明的保护范围。因此,本发明专利的保护范围应以所附权利要求为准。

Claims (10)

  1. 一种视频内容中自适应投放广告的方法,其特征在于,包括步骤:
    读取待插入广告内容的视频帧;
    识别所述视频帧以及该视频帧之前的预设数目视频帧中的对象集;
    计算确定广告内容库中各广告内容与所述对象集的相似度;
    将相似度最大的广告内容插入所述视频帧。
  2. 根据权利要求1所述的视频内容中自适应投放广告的方法,其特征在于,将相似度最大的广告内容插入所述视频帧的方式包括:
    判断所述相似度最大的广告内容是否为多帧视频;
    若是,将所述相似度最大的广告内容插入所述视频帧之后。
  3. 根据权利要求1所述的视频内容中自适应投放广告的方法,其特征在于,将相似度最大的广告内容插入所述视频帧的方式包括:
    判断所述相似度最大的广告内容是否为静止图像或者文字;
    若是,将所述相似度最大的广告内容插入所述视频帧的背景中。
  4. 根据权利要求1至3任意一项所述的视频内容中自适应投放广告的方法,其特征在于,计算确定广告内容库中各广告内容与所述对象集相似度的方式包括:
    分别计算当前广告内容与所述对象集中各对象的相似度;
    根据当前广告内容与各所述对象的相似度综合确定所述对象集与当前广告内容的相似度。
  5. 根据权利要求3所述的视频内容中自适应投放广告的方法,其特征在于:
    将当前广告内容与各所述对象的相似度中的最大值确定为所述对象集与当前广告内容的相似度;
    或者
    将当前广告内容与各所述对象的相似度的平均值作为所述对象集与当前广告内容的相似度;
    或者
    将当前广告内容与各所述对象的相似度的加权平均值作为所述对象集与当前广告内容的相似度。
  6. 一种视频内容中自适应投放广告的系统,其特征在于,包括:
    视频帧读取模块,用于读取待插入广告内容的视频帧;
    对象集识别模块,用于识别所述视频帧以及该视频帧之前的预设数目视频帧中的对象集;
    相似度最大广告内容确定模块,用于计算确定广告内容库中各广告内容与所述对象集的相似度,确定相似度最大的广告内容;
    广告内容插入模块,用于将相似度最大的广告内容插入所述视频帧。
  7. 根据权利要求6所述的视频内容中自适应投放广告的系统,其特征在于:
    还包括广告内容类型判别模块,用于判断所述相似度最大的广告内容是否为多帧视频;
    所述广告内容插入模块,用于在所述广告内容类型判别模块判定所述相似度最大的广告内容为多帧视频时,将所述相似度最大的广告内容插入所述视频帧之后。
  8. 根据权利要求6所述的视频内容中自适应投放广告的系统,其特征在于:
    还包括广告内容类型判别模块,用于判断所述相似度最大的广告内容是否为静止图像或者文字;
    所述广告内容插入模块,用于在所述广告内容类型判别模块判定所述相似度最大的广告内容为静止图像或者文字时,将所述相似度最大的广告内容插入所述视频帧的背景中。
  9. 根据权利要求6至8任意一项所述的视频内容中自适应投放广告的系统,其特征在于,所述相似度比较确定模块具体包括:
    单对象相似度确定模块,用于分别计算当前广告内容与所述对象集中各对象的相似度;
    相似度综合确定模块,用于根据当前广告内容与各所述对象的相似度综合确定所述对象集与当前广告内容的相似度,并根据所述对象集与各广告内容的相似度的大小确定相似度最大的广告内容。
  10. 根据权利要求9所述的视频内容中自适应投放广告的系统,其特征在于:
    所述相似度综合确定单元,用于将当前广告内容与各所述对象的相似度中的最大值确定为所述对象集与当前广告内容的相似度;
    或者
    所述相似度综合确定单元,用于将当前广告内容与各所述对象的相似度的平均值作为所述对象集与当前广告内容的相似度;
    或者
    所述相似度综合确定单元,用于将当前广告内容与各所述对象的相似度的加权平均值作为所述对象集与当前广告内容的相似度。
PCT/CN2013/085784 2012-12-17 2013-10-23 视频内容中自适应投放广告的方法及系统 WO2014094497A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201210548281.5 2012-12-17
CN201210548281.5A CN103024479B (zh) 2012-12-17 2012-12-17 视频内容中自适应投放广告的方法及系统

Publications (1)

Publication Number Publication Date
WO2014094497A1 true WO2014094497A1 (zh) 2014-06-26

Family

ID=47972538

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2013/085784 WO2014094497A1 (zh) 2012-12-17 2013-10-23 视频内容中自适应投放广告的方法及系统

Country Status (2)

Country Link
CN (1) CN103024479B (zh)
WO (1) WO2014094497A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110769291A (zh) * 2019-11-18 2020-02-07 上海极链网络科技有限公司 一种视频处理方法、装置、电子设备及存储介质
CN111031366A (zh) * 2019-11-29 2020-04-17 深圳市掌众信息技术有限公司 一种在视频中植入广告的方法及系统
CN111160957A (zh) * 2019-12-19 2020-05-15 北京物资学院 一种在线广告传播方法及系统
CN113592545A (zh) * 2021-07-28 2021-11-02 上海爱简网络科技有限公司 线上网络推广数据采集分析方法及系统
CN117556276A (zh) * 2024-01-11 2024-02-13 支付宝(杭州)信息技术有限公司 用于确定文本和视频之间的相似度的方法和装置

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103024479B (zh) * 2012-12-17 2016-03-02 深圳先进技术研究院 视频内容中自适应投放广告的方法及系统
CN105100886B (zh) 2014-04-22 2019-03-15 腾讯科技(北京)有限公司 网络媒介信息的发布控制方法、及装置、服务器和系统
CN105791887A (zh) * 2014-12-23 2016-07-20 腾讯科技(北京)有限公司 一种信息处理方法、客户端及服务器
WO2016137389A1 (en) * 2015-02-24 2016-09-01 Visenze Pte Ltd Method and system for identifying relevant media content
US9872049B1 (en) * 2016-06-30 2018-01-16 SnifferCat, Inc. Systems and methods for dynamic stitching of advertisements
US11272228B2 (en) 2016-06-30 2022-03-08 SnifferCat, Inc. Systems and methods for dynamic stitching of advertisements in live stream content
CN107347125B (zh) * 2016-08-19 2020-04-03 北京市商汤科技开发有限公司 视频图像的处理方法、装置和终端设备
WO2018033156A1 (zh) 2016-08-19 2018-02-22 北京市商汤科技开发有限公司 视频图像的处理方法、装置和电子设备
TWI599221B (zh) * 2016-09-19 2017-09-11 創意引晴(開曼)控股有限公司 以電腦視覺基礎實現的自動廣告中插及播放方法
CN106686404B (zh) * 2016-12-16 2021-02-02 中兴通讯股份有限公司 一种视频分析平台、匹配方法、精准投放广告方法及系统
CN107977244A (zh) * 2017-12-18 2018-05-01 北京奇虎科技有限公司 一种应用开启画面的处理方法和装置
CN108228795A (zh) * 2017-12-29 2018-06-29 北京奇虎科技有限公司 添加业务对象的方法及装置
CN111510746B (zh) * 2019-01-30 2023-01-31 腾讯科技(深圳)有限公司 媒体资源投放方法、装置、存储介质及电子装置
CN111741327B (zh) 2019-03-25 2022-09-02 华为技术有限公司 一种媒体处理方法及媒体服务器
CN110996121A (zh) * 2019-12-11 2020-04-10 北京市商汤科技开发有限公司 信息处理方法及装置、电子设备和存储介质
CN112016968A (zh) * 2020-08-28 2020-12-01 搜索亚洲科技(深圳)有限公司 一种信息推送方法、装置、电子设备及存储介质
CN112822513A (zh) * 2020-12-30 2021-05-18 百视通网络电视技术发展有限责任公司 基于视频内容的广告投放展示方法、设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101714155A (zh) * 2008-10-07 2010-05-26 汤姆森特许公司 用于将广告剪辑插入视频序列的方法以及对应设备
CN102714709A (zh) * 2010-01-21 2012-10-03 爱立信电视公司 通过媒体内容的上下文对准目标的广告
WO2012167568A1 (zh) * 2011-11-23 2012-12-13 华为技术有限公司 视频广告播放方法、设备和系统
CN103024479A (zh) * 2012-12-17 2013-04-03 深圳先进技术研究院 视频内容中自适应投放广告的方法及系统

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100580693C (zh) * 2008-01-30 2010-01-13 中国科学院计算技术研究所 一种广告检测识别方法及系统
CN101557464B (zh) * 2009-04-01 2013-06-05 深圳市融创天下科技股份有限公司 一种在视频节目播放中动态嵌入其他媒体片段的方法
US9443147B2 (en) * 2010-04-26 2016-09-13 Microsoft Technology Licensing, Llc Enriching online videos by content detection, searching, and information aggregation

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101714155A (zh) * 2008-10-07 2010-05-26 汤姆森特许公司 用于将广告剪辑插入视频序列的方法以及对应设备
CN102714709A (zh) * 2010-01-21 2012-10-03 爱立信电视公司 通过媒体内容的上下文对准目标的广告
WO2012167568A1 (zh) * 2011-11-23 2012-12-13 华为技术有限公司 视频广告播放方法、设备和系统
CN103024479A (zh) * 2012-12-17 2013-04-03 深圳先进技术研究院 视频内容中自适应投放广告的方法及系统

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110769291A (zh) * 2019-11-18 2020-02-07 上海极链网络科技有限公司 一种视频处理方法、装置、电子设备及存储介质
CN111031366A (zh) * 2019-11-29 2020-04-17 深圳市掌众信息技术有限公司 一种在视频中植入广告的方法及系统
CN111031366B (zh) * 2019-11-29 2021-12-17 深圳市掌众信息技术有限公司 一种在视频中植入广告的方法及系统
CN111160957A (zh) * 2019-12-19 2020-05-15 北京物资学院 一种在线广告传播方法及系统
CN113592545A (zh) * 2021-07-28 2021-11-02 上海爱简网络科技有限公司 线上网络推广数据采集分析方法及系统
CN117556276A (zh) * 2024-01-11 2024-02-13 支付宝(杭州)信息技术有限公司 用于确定文本和视频之间的相似度的方法和装置
CN117556276B (zh) * 2024-01-11 2024-05-10 支付宝(杭州)信息技术有限公司 用于确定文本和视频之间的相似度的方法和装置

Also Published As

Publication number Publication date
CN103024479A (zh) 2013-04-03
CN103024479B (zh) 2016-03-02

Similar Documents

Publication Publication Date Title
WO2014094497A1 (zh) 视频内容中自适应投放广告的方法及系统
WO2011059275A2 (en) Method and apparatus for managing data
WO2014146432A1 (zh) 一种冰箱内食品存储控制方法、智能控制终端及冰箱
WO2015043085A1 (zh) 一种视频信息显示方法和装置
WO2016060358A1 (en) Video processing apparatus and method
WO2015076537A1 (ko) 동영상 제공 방법 및 동영상 제공 시스템
WO2012031506A1 (zh) 基于重叠边界的多媒体切片转码方法和系统、存储介质
WO2015196711A1 (zh) 一种资源传播跟踪方法、装置及系统
WO2014058276A1 (en) Apparatus and method for delivering and receiving multimedia data in hybrid network
WO2015096538A1 (zh) 一种多屏互动的方法、装置及机顶盒
WO2016123898A1 (zh) 一种短信管理方法及其移动终端
WO2017164510A2 (ko) 음성 데이터 기반 멀티미디어 콘텐츠 태깅 방법 및 이를 이용한 시스템
WO2016076515A1 (ko) 영상의 주파수 특성 정보를 포함하는 메타 데이터를 생성하는 방법 및 장치
WO2013097488A1 (zh) 图片描述信息插入、读取方法及装置
WO2010076917A2 (en) Operating method of broadcasting receiver storing broadcasting program and broadcasting receiver enabling of the method
WO2018195891A1 (zh) 无参考图像质量评价方法及装置
WO2017028098A1 (zh) 推荐网站时显示技术信息的方法和网站推荐系统
WO2014206190A1 (zh) 一种图片显示方法、装置及机顶盒
WO2017107210A1 (zh) 一种视频软件中广告插入的方法及系统
WO2018023258A1 (zh) 推荐电视频道时的信息推送方法和电视机
WO2017117808A1 (zh) 一种视频网络的存储管理方法及系统
WO2014101556A1 (zh) 一种面向对象的网页广告插入方法和系统
WO2024038962A1 (ko) 멀티 채널 영상의 인코딩 장치
WO2017128145A1 (zh) 影视推荐时的技术信息提示方法和推荐系统
WO2011132973A2 (en) Method and apparatus for transmitting and receiving service discovery information in multimedia transmission system and file structure for the same

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 13866116

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 26/10/2015)

122 Ep: pct application non-entry in european phase

Ref document number: 13866116

Country of ref document: EP

Kind code of ref document: A1