Browse Prior Art Database

Social network content recommendations based on used device

IP.com Disclosure Number: IPCOM000244286D
Publication Date: 2015-Nov-30
Document File: 4 page(s) / 32K

Publishing Venue

The IP.com Prior Art Database

Abstract

This article describes a method and mechanism for creating separate social interests profiles for each used device. The recommendation engine will use the curretnly used profile and the not used profiles to rearrange the content recommendations in the array of recommendations, which is usually based on aggregated interests profile.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 35% of the total text.

Page 01 of 4

Social network content recommendations based on used device

Social network are an essential part of the social life in the modern world. People are using them for everything and from everywhere. They are accessing their social network accounts from planes, commute trains, homes, offices, and are using a wide variety of devices. The same user can use 3-4 different devices to access the same account of the social network from home, office, commute train, his car, and more. He may use tablet at home, mobile phone in the train, laptop or desktop computer from the office. Other combinations are possible.

The device, which is used is defining in large scale the behavioral pattern of the user within his account in the social network. He may use mobile phone for reading short updates and posting his location. He may use the home tablet for reading recommended articles, and he may use the laptop for searching for things, related to his work.

However, the recommendation engines of the social networks do not distinguish between the different behavioral patterns, and are providing the same recommendations on the content, based primarily on the user interests, and the social graph. Some prior art work suggest to profile the user activities based on the time of day, and day of week, but those can be incorrect, as people as often not following very strict schedules.

    We are suggesting enhancement for the existing recommendations engines, based on fine profiling of user interests per device.

    All social networks have user profiles. User profiles are essential and core part of social network. And the interests are the core part of user profiles. Usually the user profile contains the list of interests or categories, which define what user likes, or may like, what he did or what he most likely will do. The profiles and the interests are set explicitly or created automatically by smart analytics tools. User profile may include the topics (or categories) that the user is interested in, the types of media, the user is listening or watching, preferred content length and more.

    We suggest to enhance the mechanism of automatic profile creation in such a manner that it creates several separated profiles for each user. There will be one aggregated profile of user aggregated interests, which will be based on all the user activities. In addition, separate profiles will be created from the activities performed on different user devices.

For each device the profile will be built in a similar manner, including the same properties, extracted from the user activities. Such properties can be interests, categories, preferred content types (video, audio, text, length of content) etc. However, if the user behavioral pattern differ between his devices, these profile will contain different values for the same properties.

For example: different list of interests, or different preferred media types.

    The result of such a fine profiling is that if the user personal preference...