Browse Prior Art Database

Method and System for Discovering Offline Interests of Online Users

IP.com Disclosure Number: IPCOM000246612D
Publication Date: 2016-Jun-21
Document File: 2 page(s) / 15K

Publishing Venue

The IP.com Prior Art Database

Related People

Csaba Kecskemeti: INVENTOR [+2]

Abstract

Disclosed is a method and system for discovering properties/interest of online users or a group of users based on the user's offline behavior, thereby enabling discovering properties/interest of a user based on positive and negative feedback of real life actions.

This text was extracted from a Microsoft Word document.
This is the abbreviated version, containing approximately 53% of the total text.

Method and System for Discovering Offline Interests of Online Users

Abstract

Disclosed is a method and system for discovering properties/interest of online users or a group of users based on the user’s offline behavior, thereby enabling discovering properties/interest of a user based on positive and negative feedback of real life actions.

Description

In the current scenario, offline behavior or offline interests of a user cannot be deduced from the user’s online behavior or online activity.  There is a need for discovering a user’s offline interests in the real life scenario.

Disclosed is a method and system for discovering properties/interest of online users or a group of users based on the user’s offline behavior, thereby enabling discovering properties/interest of a user based on positive and negative feedback of real life actions.

In accordance with the method disclosed herein, K Means clustering is employed to investigate geo location information of a given id of an online user from a group of ids, the group of ids associated with each other by a certain logic (like: family/house hold, colleagues).  In K means clustering, K is representative of a certain number of centroids.  In order to define the number of K (number of centroids) as per the method, a naive K search is performed wherein K is increased till the average distance of clusters elements from the centroid and does not fall below a given threshold, thereby avoiding over-clustering.

The geo location information measured by K Means clustering is employed over...