DATA ANALYSIS USING NATURAL LANGUAGE PROCESSING TO OBTAIN INSIGHTS RELEVANT TO AN ORGANIZATION

• US 20160203217A1
• Filed: 12/19/2015
• Published: 07/14/2016
• Est. Priority Date: 01/05/2015
• Status: Abandoned Application

• Current Assignee: Saama Technologies LLC (Saama Technologies, Inc.)
• Original Assignee: Saama Technologies, Inc.
• Inventors: Anisingaraju, Vidya Sagar, Gnana, Haranath, Gondhali, Ghananeel
• Application Number:
  US14/975,778
• Publication Number:
  US 20160203217A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06Q 10/0637 Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
• CPC Class Codes: G06Q 10/067 Enterprise or organisation modelling
• CPC Class Codes: G16H 40/20 for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms

Abstract

Methods and apparatuses for generating insights for improving a health organization from unstructured and structured data. Natural language processing is employed to process the aggregated data from various data sources to create attributes and contributors. The attributes and weighted contributors are processed with business rules and/or compliance rules to form the insights.

Claims

1. A computer-implemented method for obtaining insights from aggregated data pertaining to a healthcare organization, said aggregated data including at least unstructured data, comprising:

processing said aggregated data using natural language processing to generate a set of attributes, said set of attributes being correlated with metadata pertaining experiences with said health care organization;

processing said aggregated data using natural language processing to generate a set of contributors, said set of contributors pertaining to said set of attributes; and

analyzing, using said set of attributes and said set of contributors, to generate a set of insights, said set of insights representing a set of recommendations to improve at least one attribute in said set of attributes, wherein said set of attributes represent at least one of a set of topics, a set of sentiments, and a set of emotions.

2. The computer-implemented method of claim 1 wherein said natural language processing includes topic analysis and said set of attributes includes said set of topics.

3. The computer-implemented method of claim 1 wherein said natural language processing includes sentiment analysis and said set of attributes includes said set of sentiments.

4. The computer-implemented method of claim 1 wherein said natural language processing includes emotion analysis and said set of attributes includes said set of emotions.

5. The computer-implemented method of claim 1 wherein said analyzing also employs business rules pertaining operation of said health care organization.

6. The computer-implemented method of claim 1 wherein said analyzing also employs regulatory rules.

7. The computer-implemented method of claim 1 wherein said aggregated data comes from multiple data sources.

8. The computer-implemented method of claim 1 wherein said aggregated data includes structured data.

9. The computer-implemented method of claim 1 wherein said unstructured data includes social media data.

10. The computer-implemented method of claim 1 wherein said unstructured data includes blog data.

11. The computer-implemented method of claim 1 wherein said unstructured data includes narrative data obtained from sources internal to said health care organization.

12. The computer-implemented method of claim 1 wherein said analysis employs at least one score associated with another health care organization, said insights includes a recommendation on how to improve a score for said health care organization.

13. The computer-implemented method of claim 1 wherein said analysis employs at least one score associated with another health care organization, said insights includes a benchmark data pertaining to said health care organization.

14. The computer-implemented method of claim 1 wherein said set of contributors are associated with weights prior to said analyzing.

15. A computer-implemented method for analyzing data pertaining to at least a health care organization, said analyzing being responsive to a query, comprising:

aggregating unstructured data from various data sources to form aggregated data; and

processing said aggregated data using natural language processing to generate a set of attributes, wherein said set of attributes are correlated with values of metadata specified in said query, said metadata pertaining experiences with said health care organization that give rise to said unstructured data, wherein said set of attributes represent at least one of a set of topics, a set of sentiments, and a set of emotions.

16. The computer-implemented method of claim 15 wherein said natural language processing includes topic analysis and said set of attributes includes said set of topics.

17. The computer-implemented method of claim 15 wherein said natural language processing includes sentiment analysis and said set of attributes includes said set of sentiments.

18. The computer-implemented method of claim 15 wherein said natural language processing includes emotion analysis and said set of attributes includes said set of emotions.

19. The computer-implemented method of claim 15 wherein said aggregating includes aggregating structured data to form said aggregated data.

20. The computer-implemented method of claim 15 wherein said unstructured data includes social media data.

22. The computer-implemented method of claim 15 wherein said unstructured data includes narrative data obtained from sources internal to said health care organization.

21. The computer-implemented method of claim B1 wherein said unstructured data includes blog data.

23. A computer-implemented method for obtaining recommendations for improvement pertaining to a health care organization, said obtaining recommendations being performed in response to a query, comprising:

aggregating unstructured data from various sources to form aggregated data;

processing said aggregated data using natural language processing to generate a set of attributes, said set of attributes being correlated with values of metadata, said metadata pertaining experiences with said health care organization that give rise to said unstructured data, said values of metadata being specified in said query;

processing said aggregated data using natural language processing to generate a set of contributors, said set of contributors pertaining to said set of attributes; and

analyzing, using said set of attributes and said set of contributors, to generate said recommendations, wherein said set of attributes represent at least one of a set of topics, a set of sentiments, and a set of emotions.