Browse Prior Art Database

A Method and System For Automatically Identify Highlights/Summary of a Text Book

IP.com Disclosure Number: IPCOM000246087D
Publication Date: 2016-May-04
Document File: 2 page(s) / 100K

Publishing Venue

The IP.com Prior Art Database

Abstract

Disclosed is a method and system for automatically identify highlights/summary of a text book. The system takes into account content of the text book along with a reader’s personalized knowledge and stakeholders (such as a teacher and an employee) and history for identifying highlights/summary of the text book.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 74% of the total text.

Page 01 of 2

A Method and System For Automatically Identify Highlights /

/Summary of a Text Book

Summary of a Text Book

Disclosed is a method and system for automatically identify highlights/summary of a text book. The system takes into account content of the text book along with a reader's personalized knowledge and stakeholders (such as a teacher and an employee) and history for identifying highlights/summary of the text book.

Following figure illustrates the block diagram of the system for dynamically identifying highlights/summary of a text book.

Figure

The system includes a concept extraction module that extracts concepts discussed in one or more of sections/pages/paragraphs (termed as learning components) of a text book. The learning components are analyzed by a summarization module to determine one or more learning components that best describe the concept of the text book. The system also takes into account recommendations from teachers/employers for identifying important/critical aspects of the text book. Thereafter, a personalization module automatically adjusts score of sentences by fusing features related to individuals. The system takes into account reader's goal as well as teachers/employee's goal for adjusting scores of sentences.

Subsequently, the system generates the highlights at a density level as preferred by the

1


Page 02 of 2

user. For example at 10% density level, the system is very selective in picking important sentence on the other hand at 90% densi...