Browse Prior Art Database

System and Method to Remove Contextual Data Upon System Finalization Determination Disclosure Number: IPCOM000236048D
Publication Date: 2014-Apr-03
Document File: 2 page(s) / 42K

Publishing Venue

The Prior Art Database


Disclosed are a system and method to provide real-time analysis of a user’s online activity (e.g., performing searches and viewing content) and determine the user’s interests in order to continually suggest relevant content to the user.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 52% of the total text.

Page 01 of 2

System and Method to Remove Contextual Data Upon System Finalization Determination

Social networking websites present users with potential communities, posts, groups, sites, etc. that may be of interest based on the user's group memberships or search history. This selection is based on user's activity, but not necessarily the user's true interests (e.g., a user might perform a search based on another user's interests). In addition, the social networking applications apply a user's history to assess interests, but do not dynamically adjust to the user's changing interests; some lag time occurs.

The novel contribution is a system and method to provide real-time analysis and improved detection of a user's interests in order to suggest relevant content to the user.

In most social networking applications, users indicate a level of interest about comments, posts, blogs, etc. through a like/dislike flag. This is a better indication of a user's interests. The novel system analyzes this information and then suggests content based on likes/dislikes as the indicators change over time. In addition, when

users indicate that particular content(s) is no longer of interest (e.g., when a

purchase is made), the system dynamically and in real-time recognizes the changes in the user's interests.

The system uses two factors to assess a user's current interests. First, the system detects the user's indication of like/dislike via a social network website. This indication can be calculated as a percentage of user's total interest. For example, the user might be 60% of the time interested in art, but 20% of the time interested in news articles, etc. Therefore, the system applies this proportion of a user's interest to recommend potential communities, posts, groups, or sites (relative to the percentages). Second, the system probes the user to assess whether the interest is valid. This can be performed via the user's purchase history or through an indication from the user that the suggestion based on a particular interest is no longer valid.

To implement this system in a preferred embodiment:

1. A user indicates content of interest through, but not limited to, the following methods:

    • Liking • Disliking • Purchasing • Sharing • Pinning • Posting 2. The system detects a finalization action such as, but not limited to: • Completing a transaction (i.e. e-commerce) that produces a...