Browse Prior Art Database

A Method of Proactive Program Selection Integrated with Interest Learning Service

IP.com Disclosure Number: IPCOM000249353D
Publication Date: 2017-Feb-20
Document File: 3 page(s) / 80K

Publishing Venue

The IP.com Prior Art Database

Abstract

Disclosed are a method and system for proactive program selection integrated with an interest-learning service for tracking a user’s activities, extracting and highlighting the user’s events and points of interest, checking and prioritizing available channels and programs, and iteratively predicting and recommending the most suitable program to the user based on the deep learning.

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

1

A Method of Proactive Program Selection Integrated with Interest Learning Service

With interactive media, the output is a direct result of user input; it relies upon user participation. Interactive media is an essential component of Internet of Things (IoT) services. The media sources have the same purpose, but the user's input adds interaction and brings interesting features to the system for better enjoyment.

The main problem with interactive media systems is the huge number of options. Selecting a program to watch out of hundreds of available television channels, for example, can be overwhelming and difficult for a user. This is especially true when the user has limited time in which to select and consume the content (e.g., two hours). A user might spend a disproportionate amount to time searching for and selecting a program, and then not have enough time to actually watch it.

A system or method is needed to define a proactive program selection method integrated with interest-learning services for purifying existing interactive media programs.

Existing IoT concept analysis systems and solutions can monitor, analyze, and then leverage interactive media data. Monitoring and obtaining a user’s points of interest on interactive media is not a new topic, and some methods exist in this area. However, there is not an ideal way to interactively adjust, purify, and improve an interactive media service based on users' interest-learning service.

The novel contribution is a method and system for proactive program selection integrated with an interest-learning service for tracking a user’s activities, extracting and highlighting the user’s events and points of interest, checking and prioritizing available channels and programs, and iteratively predicting and recommending the most suitable program to the user based on the deep learning.

The major components and key steps for implementation follow: (Figure 1) 1. User Information Monitor 2. User Interested Event Extractor 3. Module-Status Update Daemon 4. Video Program Monitor 5. User Interested Program Predictor 6. Interested Program Recommender 7. Prediction Satisfaction Feedback Handler

Figure 1: Information monitor

2

Information Monitor: This module is for monitoring and collecting the user's daily activities and other related information from smart devices. The system then stores the information for later analysis. Collected information may include, but is not limited to:

· Voice: record the user’s audio communication through microphones · Video: track the user’s daily activities and events through any kind of cameras · Daily route: track the user’s daily travel routes · Internet network status: track the user’s Internet browsing

Based on the collected information, the system generates an Activity List for the user. ...