[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

WO2016114653A1 - Method and computer system for generating a database of movie metadata relating to a plurality of movies, and in-stream video advertising using the database - Google Patents

Method and computer system for generating a database of movie metadata relating to a plurality of movies, and in-stream video advertising using the database Download PDF

Info

Publication number
WO2016114653A1
WO2016114653A1 PCT/NL2016/050019 NL2016050019W WO2016114653A1 WO 2016114653 A1 WO2016114653 A1 WO 2016114653A1 NL 2016050019 W NL2016050019 W NL 2016050019W WO 2016114653 A1 WO2016114653 A1 WO 2016114653A1
Authority
WO
WIPO (PCT)
Prior art keywords
movie
metadata
movies
user
content provider
Prior art date
Application number
PCT/NL2016/050019
Other languages
French (fr)
Inventor
Michal HÜBSCHMANN
Original Assignee
Relevancy Data Ltd.
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 Relevancy Data Ltd. filed Critical Relevancy Data Ltd.
Publication of WO2016114653A1 publication Critical patent/WO2016114653A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0255—Targeted advertisements based on user history
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0269—Targeted advertisements based on user profile or attribute
    • G06Q30/0271—Personalized advertisement

Definitions

  • the invention relates to the field of in-stream video advertising, and more specifically to a method and computer system for generating a computer-implemented database of movie metadata relating to a plurality of movies.
  • advertisements may be added in- stream to a movie.
  • advertisements are added to the movie stream of the movie as linear ads in the form of e.g. pre-rolls or take-overs, whereby the ad takes over the full video experience for a period of time, and product placements are before, between or after the movie content.
  • advertisements are added to the movie stream as non-linear video ads in the form of e.g. overlays or bugs, whereby ads run in parallel to a movie content experience and do not take over the full movie experience, and product placements are during, over, and within the movie content.
  • the core movie product may have companion ad products tied to it, like text, banners, rich media, and/or video player skins supplementing the movie experience.
  • a database is created that stores one or more attributes (e.g. visual metadata relating to objects, faces, scene classifications, pornography detection, scene segmentation, production quality, fingerprinting) associated with a plurality of videos.
  • attributes e.g. visual metadata relating to objects, faces, scene classifications, pornography detection, scene segmentation, production quality, fingerprinting
  • an advertisement can be selected for display with the video based on matching an advertiser's requirements or campaign parameters with the stored attributes associated with the requested video, with the user's information, or a combination thereof.
  • the displayed advertisement can function as a hyperlink that allows a user to select to receive additional information about the
  • the performance or effectiveness of the selected advertisements can be measured and recorded.
  • Advertisers often target a wrong audience, content providers are not paid (such as based on a cost per click, CPC), and users/viewers may be irritated by less relevant video advertisements.
  • a method of providing, by a computer system through a data communication network, a data stream to a user is provided, e.g. from a movie content provider to the user.
  • the data stream comprises a movie and a video advertisement.
  • the method comprises the steps of:
  • first and second movie metadata relating to each movie of a plurality of movies first movie metadata being retrieved from the movie content provider, and second movie metadata being extracted from the movie;
  • Each movie contains video information, i.e. information relating to visible information contained in the movie, and audio information, i.e. information relating to audible information contained in the movie.
  • the term movie content provider may relate to a party, and to the computer system managed by the party, the computer system containing motion picture data files representing movies. Consequently, herein the term movie may relate to the movie product, and to one or more motion picture data files representing the movie. Furthermore, herein the term user may relate to a party, and to the computer system managed by the party, the computer system being configured to play movies to display their video information and to sound their audio information. Furthermore, herein the term video advertisement may relate to data, including executable program code, image data files, and motion picture data files representing the video advertisement.
  • the movie is associated with first movie metadata which may have been generated for the movie by the movie content provider, or in another way.
  • the first movie metadata may comprise a reference character string assigned to the movie, e.g. by the movie content provider.
  • the first movie metadata may further comprise a URL, a category of the movie, such as "sports", “fashion”, etc., a title, a duration, and other characterizations of the movie.
  • the first movie metadata provided by the movie content provider may be accurate or vague or broad, and may contain errors.
  • a computer system retrieves, from a movie content provider, first movie metadata for a first movie, and stores the first movie metadata in a database system.
  • the computer system may also retrieve, from the same movie content provider or from another movie content provider, first movie metadata for a another, second movie, and store the first movie metadata of the second movie in the database system.
  • the first and second movies may be the same, and yet have different first movie metadata, for example for reason that they are stored at different movie content providers. Even at one and the same movie content provider, first and second movies may be stored having different first movie metadata, and yet being the same, or substantially the same movie.
  • the computer system may further access the movie itself at the movie content provider, including optionally downloading at least part of the movie from the movie content provider.
  • second movie metadata are extracted, and stored in the database system in association with first movie metadata of the movie.
  • the movie itself is not stored in the database system.
  • the second movie metadata may comprise any of: face metadata associated with a face appearing in the movie; logo metadata associated with a logo appearing in the movie; object metadata associated with an object appearing in the movie; audio metadata associated with audio information of the movie, and/or an audio identifier representative for the audio information of the movie; emotion metadata associated with facial expression of a face appearing in the movie; age metadata associated with skin features of a skin appearing in the movie; and gender metadata associated with a gender appearing in the movie.
  • the second movie metadata may further comprise a percentage of time during which the face appears in the movie, and a starting time and ending time of appearance of the face in the movie.
  • the second movie metadata may further comprise logo metadata, then the second movie metadata may further comprise a percentage of time during which the logo appears in the movie, and a starting time and ending time of appearance of the logo in the movie.
  • the second movie metadata may further comprise object metadata, then the second movie metadata may further comprise a percentage of time during which the object appears in the movie, and a starting time and ending time of appearance of the object in the movie.
  • a movie is combined with a specific video advertisement which is highly relevant to a user, i.e. that is in line with his or her liking and interests as much as possible, based on data collected from and about the user.
  • advertisement metadata relating to each video advertisement of a plurality of video advertisements are provided.
  • user profiles of users are maintained by associating first and second movie metadata of movies that the respective users have accessed.
  • the advertisement metadata may comprise any of: a gender of a person for which the advertisement is intended, a percentage of time that a specific face of a specific gender and a specific age appears in the advertisement; a logo that appears in the advertisement; an object that appears in the advertisement; music that sounds in the advertisement; emotion of the advertisement; etc.
  • a request is received from a user for a selected movie, i.e. a movie that is selected by the user according to the request
  • second movie metadata in the maintained user profile is matched to advertisement metadata of the plurality of video advertisements, and based on this matching a selected video advertisement is matched to the selected movie.
  • a data stream is provided to the user, wherein the data stream includes the selected movie and the selected video advertisement.
  • the association of second movie metadata to the user profiles greatly enhances the relevancy of the selected advertisement for the user.
  • the first and second movie metadata of movies after retrieval and extraction thereof, respectively, may be stored in the database system.
  • This retrieval and extraction may be an autonomous process, wherein one or more movie content providers are scanned to obtain and store first and second movie metadata of a plurality of movies provided by the one or more movie content providers in the database system.
  • user profiles can be maintained in an autonomous process by associating them with the first and second movie metadata that are available in the database system for the movies that have been accessed by the users.
  • the selected movie may be accessed, optionally in real-time, at the movie content provider, and second movie metadata may be extracted from the selected movie and associated to the user profile, before proceeding to match, using second movie metadata in the maintained user profile and advertisement metadata of the plurality of video advertisements, a selected video
  • Movies may be categorized by the same or different movie content providers in their first movie metadata such that a same movie has different first movie metadata. Hence, for each current movie for which first movie metadata are retrieved, it needs to be established whether first movie metadata have already been stored in the database system or not for the same movie.
  • the step of providing first and second movie metadata further comprises: determining from the extracted second movie metadata whether the movie is unique among the plurality of movies, and, if the movie is unique among the plurality of movies, then storing second movie metadata in association with first movie metadata of the movie.
  • the first movie metadata retrieved from a movie content provider are combined with the second movie metadata extracted from the movie.
  • a database system is generated containing only first and second metadata relating to unique movies. Building a database system thus requires relatively low amounts of time and storage space.
  • the step of determining from the extracted second movie metadata whether the movie is unique among the plurality of movies comprises: comparing the extracted second movie metadata of the movie with second movie metadata stored for other movies of the plurality of movies; and determining the movie to be unique among the plurality of movies if no match of the extracted second movie metadata with second movie metadata stored for other movies of the plurality of movies can be established.
  • second movie metadata are not stored in association with first movie metadata of the movie.
  • second metadata of the movie comprise an audio identifier representative for audio information contained in the movie
  • the step of determining whether the movie is unique among the plurality of movies comprises the steps of: assembling an audio identifier representative for audio information of the movie; and comparing the audio identifier of the movie to audio identifiers stored for other movies of the plurality of movies to determine whether the audio identifier of the movie is unique, thereby determining whether the movie is unique to the plurality of movies.
  • Analyzing a movie primarily based on its audio content provides an extremely fast way of accurately discriminating whether or not the movie has already been accessed and analyzed before. Downloading audio information costs little time, and assembling an audio identifier representative of the current movie costs little time, much less time than
  • a consistency between first movie metadata and second movie metadata is determined, and a rating indicating a degree of consistency between first movie metadata and second movie metadata is added to the second movie metadata.
  • a database system which contains highly relevant (first and) second movie metadata that can be used by advertisers, such as the movie content provider or other parties to optimally add one or more advertisements to a movie to target a user/viewer of the movie.
  • Second movie metadata that can be used by advertisers, such as the movie content provider or other parties to optimally add one or more advertisements to a movie to target a user/viewer of the movie.
  • a database system for use in the method of the invention, the database system storing first and second movie metadata relating to each movie of a plurality of movies, wherein first movie metadata have been retrieved from at least one movie content provider, and second movie metadata have been extracted from each movie of the plurality of movies.
  • a computer system for generating first and second metadata relating to each movie of a plurality of movies, and storing the first and second metadata in the database system of the present invention.
  • the computer system comprises computer software on a computer readable medium.
  • the computer software comprises computer instructions configured to enable the computer system to carry out the steps of: retrieving, for each movie of the plurality of movies, first movie metadata from the content provider; storing first movie metadata in the database system; accessing the movie at least partially at the movie content provider; extracting second movie metadata from the current movie; and storing second movie metadata associated with first movie metadata in the database system.
  • the computer software further comprises computer instructions configured to enable the computer system to carry out the steps of: comparing the extracted second movie metadata of the movie with second movie metadata stored in the database system for other movies of the plurality of movies; determining the movie to be unique among the plurality of movies if no match of the extracted second movie metadata with second movie metadata stored for other movies of the plurality of movies can be established; and if the movie is unique among the plurality of movies, then storing second movie metadata in association with first movie metadata of the movie.
  • a computer program product in particular the computer software of the computer system of the invention, comprises the computer instructions of the computer system of the invention.
  • a computer readable medium is provided, storing the computer program product of the invention.
  • Figure 1 schematically depicts a movie content provider and a metadata server coupled to a database system.
  • Figure 2 depicts a flow diagram of a method of generating a computer-implemented database of movie metadata relating to a plurality of movies.
  • Figure 3 depicts a flow diagram of a method of providing a data stream comprising a movie and a video advertisement to a user.
  • FIG. 1 schematically shows at least one movie content server 100 managed by a movie content provider, which movie content server 100 stores movies that can be retrieved through a network 110, such as Internet, by viewers and users 150.
  • a movie content provider is YouTube ® .
  • Each movie contains video information, i.e. information relating to visible information contained in the movie, and audio information, i.e. information relating to audible information contained in the movie.
  • the movie is associated with first movie metadata which may have been generated for the movie by the movie content provider, or may have been provided in another way.
  • a computer system 120 is configured for retrieving the first movie metadata for a specific movie from the movie content server 100 through an application programming interface, API, predefined by the movie content provider.
  • the computer system 120 which may be embodied as at least one server, is configured to store the first movie metadata in a database system 140, which may contain several databases 140-1 , 140-2, 140-3.
  • the computer system 120, and possibly also the database system 140, may be managed by the movie content provider, or by a third party.
  • a step 200 comprises the computer system 120 retrieving, from the at least one movie content server 100 and through network 1 10, first movie metadata for a movie.
  • next step 210 the computer system 120 stores the first movie metadata, FMD, in the database system 140.
  • step 220 which may be before, during or after step 210, the computer system 120 accesses the movie, i.e. the audio information and the video information of the movie, from the movie content server 100.
  • the access may comprise downloading at least part of the movie.
  • next step 230 the computer system 120 extracts second movie metadata from the movie.
  • next step 240 the computer system 120 determines from the extracted second movie metadata whether the movie is unique among other movies from which second movie metadata previously were extracted and stored in the database system 140.
  • the step 240 of determining from the extracted second movie metadata whether the movie is unique among a plurality of movies stored at the movie content server 100 may comprise: comparing the extracted second movie metadata of the movie with second movie metadata stored in the database system 140 for other movies of the plurality of movies; and determining the movie to be unique among the plurality of movies if no match of the extracted second movie metadata with second movie metadata stored in the database system 140 for other movies of the plurality of movies can be established.
  • step 250 the computer system 120 stores second movie metadata, SMD, in association with first movie metadata of the same movie in the database system 140.
  • step 260 a next movie is selected at the movie content server 100, and either steps 200-240 or steps 200-250 are performed for the next movie.
  • step 260 the computer system 120 selects a next movie at the movie content server 100, and either steps 200-240 or steps 200-250 are performed for the next movie.
  • first and second metadata are kept in the database system 140, but the movie itself is kept neither at the computer system 120 nor at database system 140.
  • the computer system 120 in step 230 may extract audio information of a current movie.
  • the database system 140 already comprises different audio identifiers in second movie metadata representative for audio information contained in different movies.
  • the step 240 of determining whether the movie is unique to the database system 140 comprises the computer system 120 carrying out the steps of: assembling an audio identifier representative for audio information of the movie; and comparing the audio identifier of the current movie to audio identifiers stored in the database system 140 for other movies to determine whether the audio identifier of the movie is unique in the database system 140, thereby determining whether the second movie metadata of the movie is unique to the database system 140. Retrieving audio information from the movie, and assembling an audio identifier from the audio information can be performed relatively fast, and at the same time the audio identifier provides a unique characterization of the movie.
  • the second movie metadata may comprise other audio metadata associated with audio information of the movie, and may further comprise: face metadata associated with a face appearing in the movie; logo metadata associated with a logo appearing in the movie; object metadata associated with an object appearing in the movie; emotion metadata associated with a facial expression of a face appearing in the movie; age metadata associated with skin features of a skin appearing in the movie; and gender metadata associated with a gender appearing in the movie; each type of metadata as such or in any combination of two or more types of metadata.
  • the second movie metadata may further comprise, for each face, a percentage of time during which the face appears in the movie, and a starting time and ending time of appearance of the face in the movie.
  • the second movie metadata may further comprise, for each logo, a percentage of time during which the logo appears in the movie, and a starting time and ending time of appearance of the logo in the movie.
  • the second movie metadata may further comprise, for each object, a percentage of time during which the object appears in the movie, and a starting time and ending time of appearance of the object in the movie.
  • face metadata may comprise face characteristics, such as relative position of eyes, nose, mouth and ears, color of eyes, and/or color of hair, and may further comprise a name of a person that the face belongs to.
  • logo metadata may comprise a trademark name associated to the logo.
  • Object metadata may comprise a descriptor for the object, such as "car", "house”, etc..
  • second movie metadata may be compared by the computer system to the associated first movie metadata to determine a consistency between first movie metadata and second movie metadata. After such determination, a rating indicating a degree of consistency may be added to second movie metadata. The higher the rating, the higher the degree of consistency, and the more reliable first movie metadata can be considered.
  • user profiles, UPs, of users 150 are maintained. Users of the movie content provider are parties who, through their own computer systems, access selected movies made available at the movie content server 100 for viewing them.
  • first and second movie metadata of the movie are associated to the user profile.
  • First movie metadata may be retrieved from a movie content provider server 100, or from the database system 140.
  • Second movie metadata is retrieved from the database system 140. Accordingly, the user profiles maintained at the movie content provider are enriched at least by the second movie metadata that have been extracted from the movies that the corresponding user actually has accessed.
  • the database system 140 after having processed a plurality of movies, and having stored first movie metadata and second movie metadata for each unique movie, provides one or more databases 140-1 , 140-2, 140-3 which can be used in methods of in-stream video advertising to increase a relevancy of advertisements in relation to movies.
  • a method of providing, by a movie content server 100 through a data communication network 110, a data stream from a movie content provider to a user 150, the data stream comprising a movie and a video advertisement comprises the following steps.
  • step 300 as explained above, first and second movie metadata relating to each movie of a plurality of movies are provided.
  • First movie metadata are or have been retrieved from the movie content provider, and second movie metadata are of have been extracted from the movie.
  • step 310 user profiles of users 150 are maintained by associating first and second movie metadata of a movie to a user profile when the user associated with the user profile has accessed the movie.
  • second movie metadata are retrieved from database system 140 in the maintenance of the user profiles.
  • advertisement metadata relating to each video advertisement of a plurality of video advertisements are provided.
  • the advertisement metadata may be defined by an advertiser who desires to combine his or her advertisement with a movie such that the advertisement is highly relevant for a user accessing the movie, taking into account the user profile and the advertisement metadata.
  • the video advertisement and the advertisement metadata, AMD may be managed by the video content provider.
  • step 330 the content provider receives a request from the user 150 for a selected movie.
  • step 340 a selected video advertisement from the plurality of video advertisements is matched to the selected movie, based on second movie metadata in the maintained user profile and advertisement metadata of the plurality of video advertisements.
  • step 340 can be carried out by the video content provider.
  • second movie metadata can be extracted real-time from the movie, and added to the user profile, following step 330 and preceding step 340.
  • step 350 a data stream is provided to the user, the data stream including the selected movie, and the selected video advertisement.
  • the data stream is provider from the movie content server 100 to the user 150 through the network 110.
  • an advertiser selects, for a video advertisement, advertisement metadata characterizing a type of movie and a type of user based at least on second movie metadata stored in the database system 140. Then, the video advertisement is caused to be associated to the one or more selected movies depending on the user profile of the user selecting the one or more movies. Since the database system 140 comprises, for each movie, extracted second movie metadata that characterize the movie very accurately, the relevancy of the advertisement for the viewer/user of the movie can be very high.
  • the user profiles can be enhanced by not only taking into account the first movie metadata available for a movie, but also taking into account the second movie metadata available for the movie.
  • a video advertisement can be selected based on the user profile, and at least the second movie metadata stored in the database system 140. Then, the video advertisement is caused to be associated to the selected movie when the user retrieves the movie.
  • a method of providing, by a computer system through a data communication network, a data stream comprising a movie and a video advertisement from a movie content provider to a user is disclosed.
  • First movie metadata are retrieved from the movie content provider.
  • Second movie metadata are extracted from the movie.
  • a user profile is maintained by associating first and second movie metadata of a movie to the user profile when the user has accessed the movie.
  • Advertisement metadata relating to each video advertisement of a plurality of video advertisements are provided.
  • a selected video advertisement is matched to the selected movie, using second movie metadata in the maintained user profile and advertisement metadata of the plurality of video advertisements.
  • a data stream including the selected movie and the selected video advertisement is provided to the user.
  • a single processor or other unit may fulfil the functions of several items recited in the claims.
  • program, software application, and the like as used herein are defined as a sequence of instructions designed for execution on a computer system.
  • a program, computer program, or software application may include a subroutine, a function, a procedure, an object method, an object implementation, an executable application, an applet, a servlet, a source code, an object code, a shared library/dynamic load library and/or other sequence of instructions designed for execution on a computer system.
  • a computer program may be stored and/or distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems.
  • a suitable medium such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

A method of providing, by a computer system through a data communication network, a data stream comprising a movie and a video advertisement from a movie content provider to a user is disclosed. First movie metadata are retrieved from the movie content provider. Second movie metadata are extracted from the movie. A user profile is maintained by associating first and second movie metadata of a movie to the user profile when the user has accessed the movie. Advertisement metadata relating to each video advertisement of a plurality of video advertisements are provided. After receiving a request from the user for a selected movie, a selected video advertisement is matched to the selected movie, using second movie metadata in the maintained user profile and advertisement metadata of the plurality of video advertisements. Adata stream including the selected movie and the selected video advertisement is provided to the user.

Description

Method and computer system for generating a database of movie metadata relating to plurality of movies, and in-stream video advertising using the database
FIELD OF THE INVENTION
The invention relates to the field of in-stream video advertising, and more specifically to a method and computer system for generating a computer-implemented database of movie metadata relating to a plurality of movies.
BACKGROUND OF THE INVENTION
In the digital video advertising market, advertisements, or ads, may be added in- stream to a movie. In a first variant, advertisements are added to the movie stream of the movie as linear ads in the form of e.g. pre-rolls or take-overs, whereby the ad takes over the full video experience for a period of time, and product placements are before, between or after the movie content. In another variant, advertisements are added to the movie stream as non-linear video ads in the form of e.g. overlays or bugs, whereby ads run in parallel to a movie content experience and do not take over the full movie experience, and product placements are during, over, and within the movie content. In both cases, the core movie product may have companion ad products tied to it, like text, banners, rich media, and/or video player skins supplementing the movie experience.
In the digital video advertising market, most buying of digital movies is being done by media agencies on behalf of marketers. Sellers of digital video advertising range from the largest portals and media companies to the most specialized user-generated content sites on the world wide web.
Marketers aim a reaching potential customers by precise targeting of their
advertisements, based on e.g. geography, demographics, contextual web page content and user online behavior. With recent online tools (mostly based on popular search engines), marketers put focus on behavioral targeting. Such behavioral targeting use techniques used by online website publishers and advertisers based on user web-browsing behavior information, in particular, the pages they visit, the amount of time they view each page, the links they click on, the searches they make and the things they interact with. Based on these user activities and other factors, the sites automatically collect data and metadata to create a user profile. Advertisers use these user profiles to put targeted advertisements to content provider's websites for the viewers. To illustrate this, reference US 2011/0251896 A1 discloses systems and methods for automatically matching in real-time an advertisement with a video desired to be viewed by a user. A database is created that stores one or more attributes (e.g. visual metadata relating to objects, faces, scene classifications, pornography detection, scene segmentation, production quality, fingerprinting) associated with a plurality of videos. When a user requests to view an on-line video having associated with it an advertisement, an advertisement can be selected for display with the video based on matching an advertiser's requirements or campaign parameters with the stored attributes associated with the requested video, with the user's information, or a combination thereof. The displayed advertisement can function as a hyperlink that allows a user to select to receive additional information about the
advertisement. The performance or effectiveness of the selected advertisements can be measured and recorded.
However, the needs of the advertiser, content provider and user/viewer are not always met, and the relation is still far from perfect. Advertisers often target a wrong audience, content providers are not paid (such as based on a cost per click, CPC), and users/viewers may be irritated by less relevant video advertisements.
SUMMARY OF THE INVENTION It would be desirable to provide advertisers with a possibility to target users/viewers more precisely, i.e. provide more relevant advertisements associated with movies selected by a user.
To better address this concern, in a first aspect of the invention a method of providing, by a computer system through a data communication network, a data stream to a user is provided, e.g. from a movie content provider to the user. The data stream comprises a movie and a video advertisement. The method comprises the steps of:
providing first and second movie metadata relating to each movie of a plurality of movies, first movie metadata being retrieved from the movie content provider, and second movie metadata being extracted from the movie;
maintaining a user profile of the user by associating first and second movie metadata of a movie to the user profile when the user has accessed the movie;
providing advertisement metadata relating to each video advertisement of a plurality of video advertisements;
receiving a request from the user for a selected movie;
matching, using second movie metadata in the maintained user profile and
advertisement metadata of the plurality of video advertisements, a selected video
advertisement from the plurality of video advertisements to the selected movie; and providing a data stream to the user, the data stream including the selected movie, and the selected video advertisement.
Each movie contains video information, i.e. information relating to visible information contained in the movie, and audio information, i.e. information relating to audible information contained in the movie.
Herein, the term movie content provider may relate to a party, and to the computer system managed by the party, the computer system containing motion picture data files representing movies. Consequently, herein the term movie may relate to the movie product, and to one or more motion picture data files representing the movie. Furthermore, herein the term user may relate to a party, and to the computer system managed by the party, the computer system being configured to play movies to display their video information and to sound their audio information. Furthermore, herein the term video advertisement may relate to data, including executable program code, image data files, and motion picture data files representing the video advertisement.
At a movie content provider, the movie is associated with first movie metadata which may have been generated for the movie by the movie content provider, or in another way.
The first movie metadata may comprise a reference character string assigned to the movie, e.g. by the movie content provider. The first movie metadata may further comprise a URL, a category of the movie, such as "sports", "fashion", etc., a title, a duration, and other characterizations of the movie.
The first movie metadata provided by the movie content provider may be accurate or vague or broad, and may contain errors.
In an aspect, a computer system retrieves, from a movie content provider, first movie metadata for a first movie, and stores the first movie metadata in a database system. The computer system may also retrieve, from the same movie content provider or from another movie content provider, first movie metadata for a another, second movie, and store the first movie metadata of the second movie in the database system. The first and second movies may be the same, and yet have different first movie metadata, for example for reason that they are stored at different movie content providers. Even at one and the same movie content provider, first and second movies may be stored having different first movie metadata, and yet being the same, or substantially the same movie.
The computer system may further access the movie itself at the movie content provider, including optionally downloading at least part of the movie from the movie content provider. From the movie, second movie metadata are extracted, and stored in the database system in association with first movie metadata of the movie. The movie itself is not stored in the database system. The second movie metadata may comprise any of: face metadata associated with a face appearing in the movie; logo metadata associated with a logo appearing in the movie; object metadata associated with an object appearing in the movie; audio metadata associated with audio information of the movie, and/or an audio identifier representative for the audio information of the movie; emotion metadata associated with facial expression of a face appearing in the movie; age metadata associated with skin features of a skin appearing in the movie; and gender metadata associated with a gender appearing in the movie.
If the second movie metadata comprise face metadata, then the second movie metadata may further comprise a percentage of time during which the face appears in the movie, and a starting time and ending time of appearance of the face in the movie. If the second movie metadata comprise logo metadata, then the second movie metadata may further comprise a percentage of time during which the logo appears in the movie, and a starting time and ending time of appearance of the logo in the movie. If the second movie metadata comprise object metadata, then the second movie metadata may further comprise a percentage of time during which the object appears in the movie, and a starting time and ending time of appearance of the object in the movie.
In the method of the present invention, a movie is combined with a specific video advertisement which is highly relevant to a user, i.e. that is in line with his or her liking and interests as much as possible, based on data collected from and about the user. For the purpose of said combination, on the one hand, advertisement metadata relating to each video advertisement of a plurality of video advertisements are provided. On the other hand, user profiles of users are maintained by associating first and second movie metadata of movies that the respective users have accessed.
The advertisement metadata may comprise any of: a gender of a person for which the advertisement is intended, a percentage of time that a specific face of a specific gender and a specific age appears in the advertisement; a logo that appears in the advertisement; an object that appears in the advertisement; music that sounds in the advertisement; emotion of the advertisement; etc.
When a request is received from a user for a selected movie, i.e. a movie that is selected by the user according to the request, second movie metadata in the maintained user profile is matched to advertisement metadata of the plurality of video advertisements, and based on this matching a selected video advertisement is matched to the selected movie. Next, a data stream is provided to the user, wherein the data stream includes the selected movie and the selected video advertisement.
Here, in particular the association of second movie metadata to the user profiles greatly enhances the relevancy of the selected advertisement for the user. As stated above, the first and second movie metadata of movies, after retrieval and extraction thereof, respectively, may be stored in the database system. This retrieval and extraction may be an autonomous process, wherein one or more movie content providers are scanned to obtain and store first and second movie metadata of a plurality of movies provided by the one or more movie content providers in the database system. Also, user profiles can be maintained in an autonomous process by associating them with the first and second movie metadata that are available in the database system for the movies that have been accessed by the users.
When a user accesses a movie content provider with a request for a selected movie for which no first and second movie metadata have been stored, then the selected movie may be accessed, optionally in real-time, at the movie content provider, and second movie metadata may be extracted from the selected movie and associated to the user profile, before proceeding to match, using second movie metadata in the maintained user profile and advertisement metadata of the plurality of video advertisements, a selected video
advertisement to the selected movie.
Movies may be categorized by the same or different movie content providers in their first movie metadata such that a same movie has different first movie metadata. Hence, for each current movie for which first movie metadata are retrieved, it needs to be established whether first movie metadata have already been stored in the database system or not for the same movie.
Accordingly, in an embodiment, the step of providing first and second movie metadata further comprises: determining from the extracted second movie metadata whether the movie is unique among the plurality of movies, and, if the movie is unique among the plurality of movies, then storing second movie metadata in association with first movie metadata of the movie.
In other words, for each unique movie, the first movie metadata retrieved from a movie content provider, are combined with the second movie metadata extracted from the movie. As a result, a database system is generated containing only first and second metadata relating to unique movies. Building a database system thus requires relatively low amounts of time and storage space.
In an embodiment, the step of determining from the extracted second movie metadata whether the movie is unique among the plurality of movies comprises: comparing the extracted second movie metadata of the movie with second movie metadata stored for other movies of the plurality of movies; and determining the movie to be unique among the plurality of movies if no match of the extracted second movie metadata with second movie metadata stored for other movies of the plurality of movies can be established. In an embodiment, in the step of providing first and second movie metadata, if the movie is not unique among the plurality of movies, then second movie metadata are not stored in association with first movie metadata of the movie.
In an embodiment, taking into account that each movie contains video information and audio information, second metadata of the movie comprise an audio identifier representative for audio information contained in the movie, and the step of determining whether the movie is unique among the plurality of movies comprises the steps of: assembling an audio identifier representative for audio information of the movie; and comparing the audio identifier of the movie to audio identifiers stored for other movies of the plurality of movies to determine whether the audio identifier of the movie is unique, thereby determining whether the movie is unique to the plurality of movies.
Analyzing a movie primarily based on its audio content provides an extremely fast way of accurately discriminating whether or not the movie has already been accessed and analyzed before. Downloading audio information costs little time, and assembling an audio identifier representative of the current movie costs little time, much less time than
downloading video information and analyzing it to determine its uniqueness, such as by determining one or more video identifiers for a current movie and comparing the one or more video identifiers with video identifiers included in second movie metadata representative for video information contained in different movies.
In an embodiment of the method, a consistency between first movie metadata and second movie metadata is determined, and a rating indicating a degree of consistency between first movie metadata and second movie metadata is added to the second movie metadata.
With some or all of the above second movie metadata, a database system is obtained which contains highly relevant (first and) second movie metadata that can be used by advertisers, such as the movie content provider or other parties to optimally add one or more advertisements to a movie to target a user/viewer of the movie. Research has revealed that the tendency to skip a pre-roll video advertisement decreases by some tens of % if the video advertisement is highly relevant to the user and/or the subsequent movie content.
In a second aspect of the invention, a database system for use in the method of the invention is provided, the database system storing first and second movie metadata relating to each movie of a plurality of movies, wherein first movie metadata have been retrieved from at least one movie content provider, and second movie metadata have been extracted from each movie of the plurality of movies.
In a third aspect of the invention, a computer system for generating first and second metadata relating to each movie of a plurality of movies, and storing the first and second metadata in the database system of the present invention is provided. The computer system comprises computer software on a computer readable medium. The computer software comprises computer instructions configured to enable the computer system to carry out the steps of: retrieving, for each movie of the plurality of movies, first movie metadata from the content provider; storing first movie metadata in the database system; accessing the movie at least partially at the movie content provider; extracting second movie metadata from the current movie; and storing second movie metadata associated with first movie metadata in the database system.
In an embodiment of the computer system, the computer software further comprises computer instructions configured to enable the computer system to carry out the steps of: comparing the extracted second movie metadata of the movie with second movie metadata stored in the database system for other movies of the plurality of movies; determining the movie to be unique among the plurality of movies if no match of the extracted second movie metadata with second movie metadata stored for other movies of the plurality of movies can be established; and if the movie is unique among the plurality of movies, then storing second movie metadata in association with first movie metadata of the movie.
In a fourth aspect of the invention, a computer program product, in particular the computer software of the computer system of the invention, comprises the computer instructions of the computer system of the invention.
In a fifth aspect of the invention, a computer readable medium is provided, storing the computer program product of the invention.
These and other aspects of the invention will be more readily appreciated as the same becomes better understood by reference to the following detailed description and considered in connection with the accompanying drawings in which like reference symbols designate like parts.
BRIEF DESCRIPTION OF THE DRAWINGS
Figure 1 schematically depicts a movie content provider and a metadata server coupled to a database system.
Figure 2 depicts a flow diagram of a method of generating a computer-implemented database of movie metadata relating to a plurality of movies.
Figure 3 depicts a flow diagram of a method of providing a data stream comprising a movie and a video advertisement to a user.
DETAILED DESCRIPTION OF EMBODIMENTS Figure 1 schematically shows at least one movie content server 100 managed by a movie content provider, which movie content server 100 stores movies that can be retrieved through a network 110, such as Internet, by viewers and users 150. An example of a movie content provider is YouTube®. Many movie content providers exist.
Each movie contains video information, i.e. information relating to visible information contained in the movie, and audio information, i.e. information relating to audible information contained in the movie. At the movie content server 100, the movie is associated with first movie metadata which may have been generated for the movie by the movie content provider, or may have been provided in another way.
A computer system 120 is configured for retrieving the first movie metadata for a specific movie from the movie content server 100 through an application programming interface, API, predefined by the movie content provider.
The computer system 120, which may be embodied as at least one server, is configured to store the first movie metadata in a database system 140, which may contain several databases 140-1 , 140-2, 140-3. The computer system 120, and possibly also the database system 140, may be managed by the movie content provider, or by a third party.
As illustrated by dashed lines in Figure 1 and by the flow diagram of Figure 2, in a method of generating a computer-implemented database of movie metadata relating to a plurality of movies, a step 200 comprises the computer system 120 retrieving, from the at least one movie content server 100 and through network 1 10, first movie metadata for a movie.
In next step 210, the computer system 120 stores the first movie metadata, FMD, in the database system 140.
In step 220, which may be before, during or after step 210, the computer system 120 accesses the movie, i.e. the audio information and the video information of the movie, from the movie content server 100. The access may comprise downloading at least part of the movie.
In next step 230, the computer system 120 extracts second movie metadata from the movie.
In next step 240, the computer system 120 determines from the extracted second movie metadata whether the movie is unique among other movies from which second movie metadata previously were extracted and stored in the database system 140. In particular, the step 240 of determining from the extracted second movie metadata whether the movie is unique among a plurality of movies stored at the movie content server 100 may comprise: comparing the extracted second movie metadata of the movie with second movie metadata stored in the database system 140 for other movies of the plurality of movies; and determining the movie to be unique among the plurality of movies if no match of the extracted second movie metadata with second movie metadata stored in the database system 140 for other movies of the plurality of movies can be established.
If the computer system 120 determines the current movie to be unique to the database system 140, then in step 250 the computer system 120 stores second movie metadata, SMD, in association with first movie metadata of the same movie in the database system 140. In step 260, a next movie is selected at the movie content server 100, and either steps 200-240 or steps 200-250 are performed for the next movie.
If the computer system 120 determines the movie not to be unique to the database system 140, then no storage of extracted second movie metadata in association with first movie metadata of the movie takes place, and in step 260 the computer system 120 selects a next movie at the movie content server 100, and either steps 200-240 or steps 200-250 are performed for the next movie.
Accordingly, for a unique movie that is, and remains, available at the movie content server 100, first and second metadata are kept in the database system 140, but the movie itself is kept neither at the computer system 120 nor at database system 140.
As part of the second movie metadata, the computer system 120 in step 230 may extract audio information of a current movie. The database system 140 already comprises different audio identifiers in second movie metadata representative for audio information contained in different movies. Then, the step 240 of determining whether the movie is unique to the database system 140 comprises the computer system 120 carrying out the steps of: assembling an audio identifier representative for audio information of the movie; and comparing the audio identifier of the current movie to audio identifiers stored in the database system 140 for other movies to determine whether the audio identifier of the movie is unique in the database system 140, thereby determining whether the second movie metadata of the movie is unique to the database system 140. Retrieving audio information from the movie, and assembling an audio identifier from the audio information can be performed relatively fast, and at the same time the audio identifier provides a unique characterization of the movie.
In addition to an audio identifier, the second movie metadata may comprise other audio metadata associated with audio information of the movie, and may further comprise: face metadata associated with a face appearing in the movie; logo metadata associated with a logo appearing in the movie; object metadata associated with an object appearing in the movie; emotion metadata associated with a facial expression of a face appearing in the movie; age metadata associated with skin features of a skin appearing in the movie; and gender metadata associated with a gender appearing in the movie; each type of metadata as such or in any combination of two or more types of metadata.
In particular, if the second movie metadata comprise face metadata, then the second movie metadata may further comprise, for each face, a percentage of time during which the face appears in the movie, and a starting time and ending time of appearance of the face in the movie. If the second movie metadata comprise logo metadata, then the second movie metadata may further comprise, for each logo, a percentage of time during which the logo appears in the movie, and a starting time and ending time of appearance of the logo in the movie. If the second movie metadata comprise object metadata, then the second movie metadata may further comprise, for each object, a percentage of time during which the object appears in the movie, and a starting time and ending time of appearance of the object in the movie.
In order to extract face metadata, logo metadata and/or object metadata from the movie, known video analysis methods, embodied as software, may be used. Then, face metadata may comprise face characteristics, such as relative position of eyes, nose, mouth and ears, color of eyes, and/or color of hair, and may further comprise a name of a person that the face belongs to. Logo metadata may comprise a trademark name associated to the logo. Object metadata may comprise a descriptor for the object, such as "car", "house", etc..
After extraction of second movie metadata from the movie, second movie metadata may be compared by the computer system to the associated first movie metadata to determine a consistency between first movie metadata and second movie metadata. After such determination, a rating indicating a degree of consistency may be added to second movie metadata. The higher the rating, the higher the degree of consistency, and the more reliable first movie metadata can be considered.
At the movie content provider, e.g. at the movie content server 100 or at another server managed by the movie content provider, user profiles, UPs, of users 150 are maintained. Users of the movie content provider are parties who, through their own computer systems, access selected movies made available at the movie content server 100 for viewing them. When a used has accessed a movie, first and second movie metadata of the movie are associated to the user profile. First movie metadata may be retrieved from a movie content provider server 100, or from the database system 140. Second movie metadata is retrieved from the database system 140. Accordingly, the user profiles maintained at the movie content provider are enriched at least by the second movie metadata that have been extracted from the movies that the corresponding user actually has accessed.
The database system 140, after having processed a plurality of movies, and having stored first movie metadata and second movie metadata for each unique movie, provides one or more databases 140-1 , 140-2, 140-3 which can be used in methods of in-stream video advertising to increase a relevancy of advertisements in relation to movies.
Referring to Figures 1 and 3, a method of providing, by a movie content server 100 through a data communication network 110, a data stream from a movie content provider to a user 150, the data stream comprising a movie and a video advertisement, comprises the following steps.
In step 300, as explained above, first and second movie metadata relating to each movie of a plurality of movies are provided. First movie metadata are or have been retrieved from the movie content provider, and second movie metadata are of have been extracted from the movie.
In step 310, as explained above, user profiles of users 150 are maintained by associating first and second movie metadata of a movie to a user profile when the user associated with the user profile has accessed the movie. In an example embodiment, second movie metadata are retrieved from database system 140 in the maintenance of the user profiles.
In step 320, advertisement metadata relating to each video advertisement of a plurality of video advertisements are provided. The advertisement metadata may be defined by an advertiser who desires to combine his or her advertisement with a movie such that the advertisement is highly relevant for a user accessing the movie, taking into account the user profile and the advertisement metadata. The video advertisement and the advertisement metadata, AMD, may be managed by the video content provider.
In step 330, the content provider receives a request from the user 150 for a selected movie.
In step 340, a selected video advertisement from the plurality of video advertisements is matched to the selected movie, based on second movie metadata in the maintained user profile and advertisement metadata of the plurality of video advertisements. In an example embodiment, step 340 can be carried out by the video content provider. In case the selected movie is not known in the database system 140, second movie metadata can be extracted real-time from the movie, and added to the user profile, following step 330 and preceding step 340.
As a result of step 340, in step 350 a data stream is provided to the user, the data stream including the selected movie, and the selected video advertisement. In an example embodiment, the data stream is provider from the movie content server 100 to the user 150 through the network 110.
Accordingly, in a method of in-stream video advertising, an advertiser selects, for a video advertisement, advertisement metadata characterizing a type of movie and a type of user based at least on second movie metadata stored in the database system 140. Then, the video advertisement is caused to be associated to the one or more selected movies depending on the user profile of the user selecting the one or more movies. Since the database system 140 comprises, for each movie, extracted second movie metadata that characterize the movie very accurately, the relevancy of the advertisement for the viewer/user of the movie can be very high.
With the database system 140, the user profiles can be enhanced by not only taking into account the first movie metadata available for a movie, but also taking into account the second movie metadata available for the movie. Thus, in a method of in-stream video advertising, for a user having a user profile, a video advertisement can be selected based on the user profile, and at least the second movie metadata stored in the database system 140. Then, the video advertisement is caused to be associated to the selected movie when the user retrieves the movie.
As explained in detail above, a method of providing, by a computer system through a data communication network, a data stream comprising a movie and a video advertisement from a movie content provider to a user is disclosed. First movie metadata are retrieved from the movie content provider. Second movie metadata are extracted from the movie. A user profile is maintained by associating first and second movie metadata of a movie to the user profile when the user has accessed the movie. Advertisement metadata relating to each video advertisement of a plurality of video advertisements are provided. After receiving a request from the user for a selected movie, a selected video advertisement is matched to the selected movie, using second movie metadata in the maintained user profile and advertisement metadata of the plurality of video advertisements. A data stream including the selected movie and the selected video advertisement is provided to the user.
As required, detailed embodiments of the present invention are disclosed herein; however, it is to be understood that the disclosed embodiments are merely exemplary of the invention, which can be embodied in various forms. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a basis for the claims and as a representative basis for teaching one skilled in the art to variously employ the present invention in virtually any appropriately detailed structure. Further, the terms and phrases used herein are not intended to be limiting, but rather, to provide an understandable description of the invention.
The terms "a" or "an", as used herein, are defined as one or more than one. The term plurality, as used herein, is defined as two or more than two. The term another, as used herein, is defined as at least a second or more. The terms including and/or having, as used herein, are defined as comprising (i.e., open language, not excluding other elements or steps). Any reference signs in the claims should not be construed as limiting the scope of the claims or the invention.
The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. The term coupled, as used herein, is defined as connected, although not necessarily directly, and not necessarily mechanically.
A single processor or other unit may fulfil the functions of several items recited in the claims.
The terms program, software application, and the like as used herein, are defined as a sequence of instructions designed for execution on a computer system. A program, computer program, or software application may include a subroutine, a function, a procedure, an object method, an object implementation, an executable application, an applet, a servlet, a source code, an object code, a shared library/dynamic load library and/or other sequence of instructions designed for execution on a computer system.
A computer program may be stored and/or distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems.

Claims

1. A method of providing, by a computer system through a data communication network, a data stream from a movie content provider to a user, the data stream comprising a movie and a video advertisement, wherein the method comprises the steps of:
providing first and second movie metadata relating to each movie of a plurality of movies, first movie metadata being retrieved from the movie content provider, and second movie metadata being extracted from the movie;
maintaining a user profile of the user by associating first and second movie metadata of a movie to the user profile when the user has accessed the movie;
providing advertisement metadata relating to each video advertisement of a plurality of video advertisements;
receiving a request from the user for a selected movie;
matching, using second movie metadata in the maintained user profile and
advertisement metadata of the plurality of video advertisements, a selected video
advertisement from the plurality of video advertisements to the selected movie; and
providing a data stream to the user, the data stream including the selected movie, and the selected video advertisement.
2. The method according to claim 1 , wherein the step of providing first and second movie metadata comprises:
retrieving, for each movie of the plurality of movies, first movie metadata from a movie content provider;
storing the retrieved first movie metadata;
accessing the movie at the movie content provider; and
extracting second movie metadata from the movie.
3. The method according to claim 2, wherein the step of providing first and second movie metadata further comprises:
determining from the extracted second movie metadata whether the movie is unique among the plurality of movies; and
if the movie is unique among the plurality of movies, then storing second movie metadata in association with first movie metadata of the movie.
4. The method according to claim 3, wherein the step of determining from the extracted second movie metadata whether the movie is unique among the plurality of movies comprises: comparing the extracted second movie metadata of the movie with second movie metadata stored for other movies of the plurality of movies; and
determining the movie to be unique among the plurality of movies if no match of the extracted second movie metadata with second movie metadata stored for other movies of the plurality of movies can be established.
5. The method according to claim 3, wherein, in the step of providing first and second movie metadata, if the movie is not unique among the plurality of movies, then not storing second movie metadata in association with first movie metadata of the movie.
6. The method according to claim 1 , wherein, if no first and second movie metadata have been stored for the selected movie, the matching step is preceded by the steps of:
accessing the selected movie at the movie content provider;
extracting second movie metadata from the selected movie; and
associating second movie metadata to the user profile.
7. The method according to claim 3, wherein each movie contains video information and audio information, and wherein second metadata of the movie comprise an audio identifier representative for audio information contained in the movie, and the step of determining whether the movie is unique among the plurality of movies comprises the steps of:
assembling an audio identifier representative for audio information of the movie; and comparing the audio identifier of the movie to audio identifiers stored for other movies of the plurality of movies to determine whether the audio identifier of the movie is unique, thereby determining whether the movie is unique to the plurality of movies.
8. The method according to any of claims 1 to 7, wherein the second movie metadata comprise any of:
face metadata associated with a face appearing in the movie;
logo metadata associated with a logo appearing in the movie;
object metadata associated with an object appearing in the movie;
audio metadata associated with audio information of the movie;
emotion metadata associated with facial expression of a face appearing in the movie; age metadata associated with skin features of a skin appearing in the movie; and gender metadata associated with a gender appearing in the movie.
9. The method according to claim 8, wherein: if the second movie metadata comprise face metadata, then the second movie metadata further comprise a percentage of time during which the face appears in the movie, and a starting time and ending time of appearance of the face in the movie; and/or
if the second movie metadata comprise logo metadata, then the second movie metadata further comprise a percentage of time during which the logo appears in the movie, and a starting time and ending time of appearance of the logo in the movie; and/or
if the second movie metadata comprise object metadata, then the second movie metadata further comprise a percentage of time during which the object appears in the movie, and a starting time and ending time of appearance of the object in the movie.
10. The method according to any of claims 1 to 9, further comprising:
determining a consistency between first movie metadata and second movie metadata; and
adding a rating to the second movie metadata, the rating indicating a degree of consistency between first movie metadata and second movie metadata.
1 1. A database system for use in the method of any of claims 1-10, the database system storing first and second movie metadata relating to each movie of a plurality of movies, wherein first movie metadata have been retrieved from at least one movie content provider, and second movie metadata have been extracted from each movie of the plurality of movies.
12. A computer system for generating first and second metadata relating to each movie of a plurality of movies, and storing the first and second metadata in the database system of claim 1 1 , the computer system comprising computer software on a computer readable medium, the computer software comprising computer instructions configured to enable the computer system to carry out the steps of:
retrieving, for each movie of the plurality of movies, first movie metadata from the movie content provider;
storing first movie metadata in the database system;
accessing the movie at least partially at the movie content provider;
extracting second movie metadata from the current movie; and
storing second movie metadata associated with first movie metadata in the database system.
13. The computer system according to claim 12, wherein the computer software further comprises computer instructions configured to enable the computer system to carry out the steps of: WO 2016/114653 " " " PCT/NL2016/050019 comparing the extracted second movie metadata of the movie with second movie metadata stored in the database system for other movies of the plurality of movies;
determining the movie to be unique among the plurality of movies if no match of the extracted second movie metadata with second movie metadata stored for other movies of the plurality of movies can be established; and
if the movie is unique among the plurality of movies, then storing second movie metadata in association with first movie metadata of the movie.
14. A computer program product comprising the computer instructions according to claim 12 or 13.
15. A computer readable medium storing the computer program product according to claim 14.
PCT/NL2016/050019 2015-01-12 2016-01-11 Method and computer system for generating a database of movie metadata relating to a plurality of movies, and in-stream video advertising using the database WO2016114653A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
NL2014112 2015-01-12
NL2014112A NL2014112B1 (en) 2015-01-12 2015-01-12 Method and computer system for generating a database of movie metadata relating to a plurality of movies, and in-stream video advertising using the database.

Publications (1)

Publication Number Publication Date
WO2016114653A1 true WO2016114653A1 (en) 2016-07-21

Family

ID=52815232

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/NL2016/050019 WO2016114653A1 (en) 2015-01-12 2016-01-11 Method and computer system for generating a database of movie metadata relating to a plurality of movies, and in-stream video advertising using the database

Country Status (2)

Country Link
NL (1) NL2014112B1 (en)
WO (1) WO2016114653A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018236483A1 (en) * 2017-06-23 2018-12-27 Mastercard International Incorporated Systems and methods for analyzing content affinities from digital wallet transaction data
US10223359B2 (en) 2016-10-10 2019-03-05 The Directv Group, Inc. Determining recommended media programming from sparse consumption data

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110251896A1 (en) 2010-04-09 2011-10-13 Affine Systems, Inc. Systems and methods for matching an advertisement to a video

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20110251896A1 (en) 2010-04-09 2011-10-13 Affine Systems, Inc. Systems and methods for matching an advertisement to a video

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ANONYMOUS: "Acoustic fingerprint - Wikipedia, the free encyclopedia", 3 January 2015 (2015-01-03), pages 1 - 2, XP055210378, Retrieved from the Internet <URL:https://en.wikipedia.org/w/index.php?title=Acoustic_fingerprint&oldid=640807913> [retrieved on 20150831] *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10223359B2 (en) 2016-10-10 2019-03-05 The Directv Group, Inc. Determining recommended media programming from sparse consumption data
US11100157B2 (en) 2016-10-10 2021-08-24 The Directv Group, Inc. Determining recommended media programming from sparse consumption data
WO2018236483A1 (en) * 2017-06-23 2018-12-27 Mastercard International Incorporated Systems and methods for analyzing content affinities from digital wallet transaction data
US10607256B2 (en) 2017-06-23 2020-03-31 Mastercard International Incorporated Systems and methods for analyzing content affinities from digital wallet transaction data

Also Published As

Publication number Publication date
NL2014112B1 (en) 2016-09-30
NL2014112A (en) 2016-09-23

Similar Documents

Publication Publication Date Title
US12010400B2 (en) Methods and apparatus for secondary content analysis and provision within a network
JP6827515B2 (en) Viewing time clustering for video search
US20190364329A1 (en) Non-intrusive media linked and embedded information delivery
US20180144367A1 (en) Method and system for creating user based summaries for content distribution
US9420319B1 (en) Recommendation and purchase options for recommemded products based on associations between a user and consumed digital content
US10516909B2 (en) Method and system for recommending dynamic, adaptive and non-sequentially assembled videos
US20080077952A1 (en) Dynamic Association of Advertisements and Digital Video Content, and Overlay of Advertisements on Content
US20100076841A1 (en) Advertisement repository and advertisement search
US20170132659A1 (en) Potential Revenue of Video Views
US20090287567A1 (en) Method and System for Selecting and Delivering Media Content via the Internet
US20090172727A1 (en) Selecting advertisements to present
US10419784B2 (en) Method and system for serving advertisements during streaming of dynamic, adaptive and non-sequentially assembled video
CN102216945B (en) Networking with media fingerprints
KR20140054486A (en) System and method for online advertisement
US20160036939A1 (en) Selecting Content for Simultaneous Viewing by Multiple Users
KR102370510B1 (en) Video frame selection for targeted content
US8875177B1 (en) Serving video content segments
US20150348098A1 (en) Identifying A Product Placement Opportunity Within A Screenplay
NL2014112B1 (en) Method and computer system for generating a database of movie metadata relating to a plurality of movies, and in-stream video advertising using the database.
WO2016125166A1 (en) Systems and methods for analyzing video and making recommendations
KR102052068B1 (en) System and method for recommanding contents
US20150213486A1 (en) Method and Device For Placing Branded Products As Advertisements Within Media
Bug et al. YouTube fashion videos
US20170200190A1 (en) Dynamically served digital content based on real time event updates
US20230351442A1 (en) System and method for determining a targeted creative from multi-dimensional testing

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: 16713605

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16713605

Country of ref document: EP

Kind code of ref document: A1