Compassion, Variety and Cohesion For Methods Of Text Analytics, Writing, Search, User Interfaces

• US 20120166180A1
• Filed: 06/23/2011
• Published: 06/28/2012
• Est. Priority Date: 03/23/2009
• Status: Active Grant

• Current Assignee: Synapsify, Inc.
• Original Assignee: Synapsify, Inc.
• Inventors: Au, Lawrence
• Granted Patent: US 9,213,687 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/237 Lexical tools
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique

Abstract

The present invention increases precision and recall of search engines, while decreasing hardware resources needed, using musical rhythmic analysis to detect sentiment and emotion, using poetic and metaphoric resonances with dictionary meanings, to annotate, distinguish and summarize n-grams of word meanings, then intersecting n-grams to locate mutually salient sentences, using metaphor salience analysis to cluster sentences and paragraphs into automatically named concepts, automatically characterizing quality and depth to which documents describe concepts, using editorial metrics of compassion, variety of perspectives and logical cohesion, to automatically set pricing for written works and their copyrights, and to monitor blogs and social media for newly important concepts, and provide advanced user interfaces.

Claims

1. ) A homeostatic method to automatically calculate economic value of documents input as text, comprising:

compassion, variety and cohesion metrics computed from sentiment valences, semantics, and natural language word-sense disambiguation.

4. ) The method of claim 1, further comprising:

using automatic computations of poetic or metaphor resonance to control and extend natural language word-sense disambiguation.

6. ) the method of claim 1, further comprising:

generating n-grams for clusters of words around verbs, intersecting n-grams to query for and retrieve salient indexed text, to compute compassion using total sentiments of words.

8. ) the method of claim 1, further comprising:

generating n-grams for clusters of words around verbs, intersecting n-grams to query for and retrieve salient indexed text, to

2. ) A search engine method to automatically calculate salience of text, comprising:

sentiment valences and natural language word-sense disambiguation.

5. ) The method of claim 2, further comprising:

using automatic computations of poetic or metaphor resonance to control and extend natural language word-sense disambiguation.

7. ) the method of claim 2, further comprising:

generating n-grams for clusters of words around verbs, intersecting n-grams to query for and retrieve salient indexed text, to compute compassion using total sentiments of words.

3. ) A text analytics method to automatically calculate boundaries of paragraphs, comprising:

sentiment valences and natural language part-of-speech disambiguation.