Self-learning methods for automatically generating a summary of a document, knowledge extraction and contextual mapping

• US 8,977,540 B2
• Filed: 01/31/2011
• Issued: 03/10/2015
• Est. Priority Date: 01/31/2011
• Status: Active Grant

• Current Assignee: Syed Yasin
• Original Assignee: Syed Yasin
• Inventors: Yasin, Syed
• Primary Examiner(s): PULLIAS, JESSE SCOTT
• Application Number:
  US13/575,478
• Publication Number:
  US 20120303357A1
• Time in Patent Office: 1,499 Days
• Field of Search: 704/1, 704/9, 704/10
• US Class Current: 704/9
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/345 Summarisation for human users
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/00 Computing arrangements based on specific mathematical models

Abstract

Advance Machine Learning or Unsupervized Machine Learning Techniques are provided that relate to Self-learning processes by which a machine generates a sensible automated summary, extracts knowledge, and extracts contextually related Topics along with the justification that explains “why they are related” automatically without any human intervention or guidance (backed ontology'"'"'s) during the process. Such processes also relate to generating a 360-Degree Contextual Result (360-DCR) using Auto-summary, Knowledge Extraction and Contextual Mapping.

Claims

1. A method for automatically generating Contextual Mapping without human intervention, said method comprising acts of:

using a processor to perform the steps of;

processing and indexing one or more documents to identify topics for each document;

storing the topics identified for each document in a predetermined order as a Topical List (TL) and removing duplicate topics from the TL;

extracting a predefined number of results for each Topic in the TL by searching one Topic at a time in the corresponding index;

extracting a corresponding Topic and Content for each of the retrieved result and storing the extracted Topic and Content in a predetermined order as a Result-List (RL) for analysis;

analyzing the RL for the corresponding topic to extract Related Topics,

analyzing Document Content of the corresponding Related Topic to extract “

how they are related”

phrases from the content; and

clustering the resultant “

Related Topics”

along with their respective sentences that describe their contextual relationship with a given Topic in TL to represent Contextual Mapping.

2. The method as claimed in claim 1, wherein the predefined number of results depends upon at least one of size of data and index size.

3. The method as claimed in claim 1, wherein identifying topic for each document comprises comparing each Important Words (IW) in the document with its file name and Title name, if any of the IW'"'"'s matches than that is defined as a Topic.

4. The method as claimed in claim 3, wherein the IW'"'"'s with highest frequency occurrences in the document is defined as the topic for the document.