Grouping documents based on document concepts

Patent metadata

Field	Value
Publication number	US-10169353-B1
Application number	US-201514926719-A
Country	US
Kind code	B1
Filing date	Oct 29, 2015
Priority date	Oct 30, 2014
Publication date	Jan 1, 2019
Grant date	Jan 1, 2019

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving at least one electronic document, and identifying one or more words, phrases, or patterns used within the electronic document and that are based on a lexicon. Mapping, using a concept library, the one or more words, phrases, or patterns to a concept intended to be conveyed by the one or more words, phrases, or patterns according to the lexicon. Generating concept data based on the mapping, and storing the concept data in association with data identifying the electronic document.

First claim

What is claimed is:

1. A computer-implemented method executed by one or more processors, the method comprising:
receiving at least one electronic document;
identifying, by the one or more processors, one or more words, phrases, or patterns used within the electronic document, the one or more words, phrases, or patterns based on a lexicon;
mapping, by the one or more processors using a concept library, the one or more words, phrases, or patterns to a concept intended to be conveyed by the one or more words, phrases, or patterns according to the lexicon, wherein the concept library comprises two or more lexicons each having a plurality of context entries, each context entry comprising a first set of one or more words, phrases, or patterns from a first lexicon and a second set of one or more different words, phrases, or patterns from a second lexicon, wherein both the first set and second set are mapped to at least one common concept intended to be conveyed by the respective sets of one or more words, phrases, or patterns;
generating, by the one or more processors, concept data based on the mapping; and
storing the concept data associated with the electronic document in a concept index comprising concept data associated with at least one other electronic document that conveys respective concepts according to a different lexicon from the lexicon of the at least one electronic document, the concept index comprising, for each electronic document represented in the concept index, an array of values where each value indicates a presence or absence of a given concept within a respective document irrespective of a particular lexicon used to convey the concept within the document.

2. The method of claim 1 , wherein the concept library is one of a product library, a product feature library, a line of business library, or a life events library.

3. The method of claim 1 , wherein the lexicon is one of a customer lexicon, a customer service representative lexicon, a legal staff lexicon, a marketing staff lexicon, or a technical staff lexicon.

4. The method of claim 1 , wherein the values in the array of values comprise binary data associated with each concept represented in the concept library, the binary data indicating that a respective concept is either present or not present in the respective electronic document.

5. The method of claim 1 , wherein the values in the array of values comprise a concept score for each concept represented in the concept index, each concept score indicating a frequency with each respective concept is conveyed in the respective electronic document.

6. The method of claim 1 , further comprising:
determining, using the concept index, a set of concepts that are conveyed in both a first and a second electronic document based on comparing values from a concept data array associated with the first electronic document to values from a concept data array associated with the second electronic document; and
in response to receiving a user request to compare the first and the second electronic document, providing, for display to the user, the set of concepts that are conveyed in both the first and the second electronic document.

7. The method of claim 1 , further comprising:
determining, using the concept index, a set of concepts that are conveyed in a first electronic document but that are not conveyed in a second electronic document based on comparing values from a concept data array associated with the first electronic document to values from a concept data array associated with the second electronic document; and
in response to receiving a user request to compare the first and the second electronic document, providing, for display to the user, the set of concepts that are conveyed in the first electronic document but that are not conveyed in the second electronic document.

8. A system comprising:
at least one processor; and
at least one data store coupled to the at least one processor having instructions stored thereon which, when executed by the at least one processor, causes the at least one processor to perform operations comprising to perform operations comprising:
receiving at least one electronic document;
identifying one or more words, phrases, or patterns used within the electronic document, the one or more words, phrases, or patterns based on a lexicon;
mapping, using a concept library, the one or more words, phrases, or patterns to a concept intended to be conveyed by the one or more words, phrases, or patterns according to the lexicon, wherein the concept library comprises two or more lexicons each having a plurality of context entries, each context entry comprising a first set of one or more words, phrases, or patterns from a first lexicon and a second set of one or more different words, phrases, or patterns from a second lexicon, wherein both the first set and second set are mapped to at least one common concept intended to be conveyed by the respective sets of one or more words, phrases, or patterns;
generating concept data based on the mapping; and
storing the concept data associated with the electronic document in a concept index comprising concept data associated with at least one other electronic document that conveys respective concepts according to a different lexicon from the lexicon of the at least one electronic document, the concept index comprising, for each electronic document represented in the concept index, an array of values where each value indicates a presence or absence of a given concept within a respective document irrespective of a particular lexicon used to convey the concept within the document.

9. The system of claim 8 , wherein the concept library is one of a product library, a product feature library, a line of business library, or a life events library.

10. The system of claim 8 , wherein the lexicon is one of a customer lexicon, a customer service representative lexicon, a legal staff lexicon, a marketing staff lexicon, or a technical staff lexicon.

11. The system of claim 8 , wherein the values in the array of values comprise binary data associated with each concept represented in the concept library, the binary data indicating that a respective concept is either present or not present in the respective electronic document.

12. The system of claim 8 , wherein the values in the array of values comprise a concept score for each concept represented in the concept index, each concept score indicating a frequency with each respective concept is conveyed in the respective electronic document.

13. The system of claim 8 , wherein the operations further comprise:
determining, using the concept index, a set of concepts that are conveyed in both a first and a second electronic document based on comparing values from a concept data array associated with the first electronic document to values from a concept data array associated with the second electronic document; and
in response to receiving a user request to compare the first and the second electronic document, providing, for display to the user, the set of concepts that are conveyed in both the first and the second electronic document.

14. The system of claim 8 , wherein the one or more processors are further configured to perform operations comprising:
determining, using the concept index, a set of concepts that are conveyed in a first electronic document but that are not conveyed in a second electronic document based on comparing values from a concept data array associated with the first electronic document to values from a concept data array associated with the second electronic document; and
in response to receiving a user re

Assignees

• Usaa

Inventors

• Riley Timothy L
• Young Barrington R

Classifications

• G06F40/284 Primary

  Lexical analysis, e.g. tokenisation or collocates · CPC title

• G06F16/243

  Natural language query formulation · CPC title

• G06F16/93

  Document management systems · CPC title

• G06F16/355

  Creation or modification of classes or clusters · CPC title

• G06F16/156

  Query results presentation · CPC title