VARIOUS METHODS AND APPARATUSES FOR AN ENGINE THAT PAIRS ADVERTISEMENTS WITH VIDEO FILES

• US 20090119169A1
• Filed: 09/30/2008
• Published: 05/07/2009
• Est. Priority Date: 10/02/2007
• Status: Abandoned Application

• Current Assignee: RhythmOne LLC (Nexxen International Ltd.)
• Original Assignee: Blinkx Incorporated (Nexxen International Ltd.)
• Inventors: Beadle, Andrew James, Stockdale, Jack, Scheybeler, Matt, Chandratillake, Suranga
• Application Number:
  US12/241,763
• Publication Number:
  US 20090119169A1
• Time in Patent Office: Days
• US Class Current: 705/14.460
• CPC Class Codes: G06F 16/78 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/7844 using original textual content or text extracted from visual content or transcript of audio data
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0247 Calculate past, present or future revenues
• CPC Class Codes: H04N 21/23418 involving operations for analysing video streams, e.g. detecting features or characteristics television picture signal circuitry for scene change detection H04N5/147; filtering for image enhancement G06T5/00; methods or arrangements for recognising scenes G06V20/00; arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59
• CPC Class Codes: H04N 21/26603 for automatically generating descriptors from content, e.g. when it is not made available by its provider, using content analysis techniques
• CPC Class Codes: H04N 21/4622 Retrieving content or additional data from different sources, e.g. from a broadcast channel and the Internet web site content organization and management for information retrieval from the Internet G06F16/958; transmission by internet of broadcast information H04H60/82; stock exchange data over packet-switching network H04L12/1804; push services including data channel over packet-switching network H04L12/1859
• CPC Class Codes: H04N 21/812 involving advertisement data advertising per se G06Q30/02
• CPC Class Codes: H04N 21/84 Generation or processing of descriptive data, e.g. content descriptors systems specially adapted for using meta-information in broadcast systems H04H60/73

Abstract

A system to pair advertisements with media files is described. A request is processed to find one or more relevant advertisements and determine when to display each relevant advertisement at a temporally contextual point within a video file when the video file is played on a web page. The video file'"'"'s key concepts and timing information are retrieved from a database. A request is generated for advertisements that contextually match the content in the key conceptual points found in the content of the video file. The timing information is retrieved regarding when the key conceptual points, relevant to returned advertisements that contextually match, chronologically appear in the video file. Contextual relevant advertisements are supplied with temporal information on when the placement of advertisements is most contextually relevant to the content being played in the video file.

Claims

1. An apparatus, characterized in that:

a contextual engine hosted on a first server, the contextual engine is configured to reference data on one or more video files stored in a memory of the contextual engine as well as to send each video file not previously analyzed to one or more content analysis tools to determine a content within that video file and then store the video file'"'"'s content characteristics in a database, wherein the contextual engine has a communication link to a web page having a video player, which is hosted on a second server, and at least one of the web page and the video player is configured to make a request to and send information associated with a video file about to be played on the video player across a network to the contextual engine for matching of a content within the video file to be played on the video player and content of one or more advertisements selected from two or more advertisement networks, wherein the contextual engine sends back across the network to the second server hosting the video player both identifying information on one or more contextually matched advertisements to display with the video file when the video player plays the video file on the web page and temporal information on when a placement of the contextually matched advertisements is contextually relevant to the content being played in the video file.

2. The apparatus of claim 1, wherein upon receiving the request from the video player, the contextual engine communicates to the video player hosted on the web page when a key conceptual point most relevant to a content of a first contextually matched advertisement occurs in the playing video file so the video player can display the first contextually matched advertisement at a best time during the playing of the video file.

3. The apparatus of claim 2, wherein the contextual engine communicates across the network to at least one of the web page and the video player to display the first contextually relevant advertisements at multiple discrete points in time within the played video based on a preference on record made by the web page administrator.

4. The apparatus of claim 1, wherein the contextual engine sends a response to the request across the network to the web page on the second server that includes both 1) information regarding the temporal placement of the one or more contextually matched advertisements as well as 2) a positional placement of the advertisements on the web page, were both are relative to the video file being played by the video player.

5. The apparatus of claim 1, further comprising:

a client machine having a browser application resident on the client machine configured to download the web page over the network into a memory of the client machine from the second server upon request from the browser and the client machine displays the web page on a display of the client machine to allow a user of the client machine to make a request to activate the video player to play the video file; and

an on-demand dynamic spider having a communication link to the contextual engine, wherein the contextual engine upon receipt of the information about the video file about to be played, then references a ready index of already analyzed video files stored in the memory of the contextual engine and when the file video is not present in the ready index, then the information about the video file about to be played is passed to the on-demand dynamic spider, where the on-demand dynamic spider is configured to browse the World Wide Web upon request by the contextual engine to find and bring to the contextual engine the video file identified in the request.

6. The apparatus of claim 1, wherein the contextual engine has an output module configured to communicate across the network to as well as an input module configured to receive the request from both a generic video player embedded on the web page hosted on the second server and to a viral video player that is coded to merely play video files specifically coded to work with only that video player type, which is embedded on another web page hosted on a third server.

7. The apparatus of claim 4, wherein the content analysis tools are configured to use at least transcription and visual analysis services to extract key conceptual points about the video file itself from the video file'"'"'s audio and visual tracks, and the extracted key conceptual points are stored in a database and retrieved by the contextual engine from the database.

8. A machine-readable medium having stored therein instructions that, when executed by a processor, cause the machine to perform the following operations, comprising:

processing a request to find one or more relevant advertisements and determine when to display each relevant advertisement at a temporally contextual point within a video file when the video file is played on a web page;

receiving identifying information regarding the video file about to be played on the video player across a network from either a web page or a video player embedded on the web page and the request to find the one or more relevant advertisements;

upon receiving the request, looking up in an existing index for video entities whether key conceptual points of the video file and their timing information are already known;

retrieving the video file'"'"'s key concepts and timing information from a database;

generating a request for advertisements that contextually match the content in the key conceptual points found in the content of the video file;

retrieving the timing information regarding when the key conceptual points that are relevant to returned advertisements chronologically appear in the video file; and

supplying one or more contextually matched advertisements with the timing information on when a placement of the contextually matched advertisements is most contextually relevant to the content being played in the video file.

9. The machine readable medium of claim 8, wherein the key conceptual points are ordered based on their importance and a frequency these contextual points appear in the content of the video file and the key conceptual points include content that appears in the video file, content spoken in the video file, symbols and text appearing in the video file, and Metadata associated with the video file.

10. The machine readable medium of claim 8, containing instructions, which when executed cause the further operations comprising:

generating the request for advertisements that contextually match the content in the key conceptual points found in the content of the video file in parallel to two or more advertisement networks; and

receiving one or more advertisements from the two or more networks of advertising databases in order to display the one or more advertisements when the video file is played, wherein the video player or web page display the one or more advertisements along with the video file played on the web page in one or more locations relative to a window displaying the video file.

11. The machine readable medium of claim 8, containing instructions, which when executed cause the further operations comprising:

retrieving instructions that include

     1) defining how various advertisements are to be positioned relative to the web page or window for the video player,

     2) acceptable times to display the advertisements, before, during, or after, the playing of the video file,

     3) if a certain advertisement type or a certain subject matter is banned,

     4) the web page administrator'"'"'s weighting preferences on revenue to contextual relevance to the content in the video file, and

     5) how many times a particular contextually matched advertisement should appear during a playing of the video file, wherein the contextually matched advertisements to the content in the video file and that match the instructions are sent in a response with the timing information on when those advertisements are relevant within the video file to the web page or the video player that generated the request.

12. The machine readable medium of claim 8, containing instructions, which when executed cause the further operations comprising:

deciphering a revenue generated for displaying a given advertisement and the given advertisement'"'"'s contextual relevance to the content in the video file; and

delivering a combined most relevant and best revenue generating advertisements to the video player or the web page that generated the request.

16. The machine readable medium of claim 8, containing instructions, which when executed cause the further operations comprising:

sending at least detected images and words from the content of the video file along with a confidence rating associated with each detected feature to a dynamic reasoning engine.

17. The machine readable medium of claim 8, wherein an internal filter is applied to an initial set of key conceptual points by a contextual engine to filter out conceptual points from the initial set of key conceptual points that statistically have been found to be not particularly relevant or effective conceptual points for advertising.

13. The machine readable medium of claim 13, containing instructions, which when executed cause the further operations comprising:

customize a timing and an appearance of a video advertisement with contextually relevant content being played in the video file, wherein the contextual engine sends the customization information along with the advertisements to the video player or the web page that generated the request.

14. The machine readable medium of claim 13, containing instructions, which when executed cause the further operations comprising:

using transcription and visual analysis services to extract conceptual points about the video file itself from the video file'"'"'s audio and visual tracks and then creating a set of key conceptual points out of the information extracted.

15. The machine readable medium of claim 14, wherein the conceptual points are ordered based on their importance and a frequency these conceptual points appear in the content of the video file and comparing the extracted information from two different sources to better understand the content within the video file and also to be able to annotate when the key conceptual points occur.

18. A system, comprising:

a contextual engine hosted on a first server, the contextual engine is configured to reference data on one or more video files stored in a memory of the contextual engine as well as to send each video file not previously analyzed to one or more content analysis tools to determine a content within that video file and then store the video file'"'"'s content characteristics in a database, wherein the contextual engine has a communication link to a web page having a video player that is hosted on a second server, and at least one of the web page and the video player is configured to make a request to and send information associated with a video file about to be played on the video player across a network to the contextual engine for matching of a content within the video file to be played on the video player and content of one or more advertisements selected from two or more advertisement networks, wherein the contextual engine sends back across the network to the second server hosting the video player and web page both identifying information on one or more contextually matched advertisements to display with the video file when the video player plays the video file on the web page and temporal information on when a placement of the contextually matched advertisements is contextually relevant to the content being played in the video file;

a client machine having a browser application resident on the client machine configured to download the web page over the network into a memory of the client machine from the second server upon request from the browser and the client machine displays the web page on a display of the client machine to allow a user of the client machine to make a request to activate the video player to play the video file; and

an on-demand dynamic spider having a communication link to the contextual engine, wherein the contextual engine upon receipt of the information about the video file about to be played, then references a ready index of already analyzed video files stored in the memory of the contextual engine and when the file video is not present in the ready index, then the information about the video file about to be played is passed to the on-demand dynamic spider, where the on-demand dynamic spider is configured to browse the World Wide Web upon request by the contextual engine to find and bring to the contextual engine the video file identified in the request.

19. The system of claim 18, further comprising:

an advertisement player configured to embed on the web page having the video player, which is hosted on the second server, the advertisement player is configured to make a call to and send information associated with the video file about to be played on the web page across the network to the contextual engine hosted on the first server and is configured to display two or more different types of advertisements, wherein the contextual engine sends a response to the request across the network to the web page on the second server that includes both

     1) information regarding the temporal placement of the one or more contextually matched advertisements as well as

     2) a positional placement of the advertisements on the web page, and

wherein the contextual engine communicates to the video player hosted on the web page when a key conceptual point most relevant to a content of a first contextually matched advertisement occurs in the playing video file so the video player can display the contextually relevant advertisement at a best time during the playing of the video file.

20. The system of claim 19, wherein the contextual engine has an output module configured to communicate across the network to as well as an input module configured to receive the request from both to a generic video player embedded on the web page hosted on the second server and to a viral video player that is coded to merely play video files specifically coded to work with only that video player type, which is embedded on another web page hosted on a third server, and

wherein the content analysis tools are configured to use at least transcription and visual analysis services to extract key conceptual points about the video file itself from the video file'"'"'s audio and visual tracks, and the extracted key conceptual points are stored in a database and retrieved by the contextual engine from the database.