Self-learning methods for automatically generating a summary of a document, knowledge extraction and contextual mapping
First Claim
Patent Images
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.
0 Assignments
0 Petitions
Accused Products
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.
-
Citations
4 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; andclustering the resultant “
Related Topics”
along with their respective sentences that describe their contextual relationship with a given Topic in TL to represent Contextual Mapping.- View Dependent Claims (2, 3, 4)
Specification