Browse Prior Art Database

Method and System for Retargeting Product Sales based on Video Views

IP.com Disclosure Number: IPCOM000239067D
Publication Date: 2014-Oct-08
Document File: 3 page(s) / 68K

Publishing Venue

The IP.com Prior Art Database

Related People

Jeyandran Venugopal: INVENTOR

Abstract

A method and system for retargeting product sales based on video views is disclosed. The method and system collects video viewing data of one or more users. If the videos prominently show up one or more products in some frames, the products are tagged. A tagged product is automatically matched with similar products in a product catalog. The user is accordingly retargeted with an offer specific to the product.

This text was extracted from a Microsoft Word document.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately 52% of the total text.

Method and System for Retargeting Product Sales based on Video Views

Abstract

A method and system for retargeting product sales based on video views is disclosed.  The method and system collects video viewing data of one or more users.  If the videos prominently show up one or more products in some frames, the products are tagged.  A tagged product is automatically matched with similar products in a product catalog.  The user is accordingly retargeted with an offer specific to the product.

Description

Disclosed is a method and system for retargeting product sales based on video views.  Fig. 1 illustrates a flow diagram of the method for retargeting product sales based on video views.

Figure 1

The method and system collects video viewing data of one or more users.  The data is collected from one or more of, but not limited to, web/mobile video player view logs, applications for companion screen viewing or/and smart television (TV) applications embedded in TV sets.  If the videos prominently show up one or more products in some frames of the video, the products are tagged.  A self-service portal can be provided for product sellers to tag related products against video frames as well.  The tagging can be carried out using auto detection through machine learned classifiers.  A product in the video is automatically matched with similar products in the product catalog.  A matching algorithm can match based on category of items detected and/or other elements such as, but not limited to, color, size and shape.  The matching can also be done through a self-service mechanism by advertisers for products that are similar to the tagged products in the video frames.  A match against a product catalog can be maintained.  An associated products catalog can also be built against each video.  For example, if the user watched a red carpet event video at the Oscar ceremony, a catalog is built where all hand purses and dresses associated with the event video are tagged as metadata.  The product tags against video frames are captured based on surfacing, trending and highly viewed videos.  The user is retargeted with an offer specific to the product when the product in the video matches with any product in the product catalog.  If the user buys the product based on the offer, then a part of revenue can be shared by a distribution partner.

Thus, a product sale opportunity is created using a follow through on a video view event of th...