Method and system for analyzing data using a query answering system

• US 10,176,268 B2
• Filed: 08/14/2017
• Issued: 01/08/2019
• Est. Priority Date: 09/08/2011
• Status: Active Grant

• Current Assignee: Wolfram Alpha LLC (Wolfram Research Incorporated)
• Original Assignee: Wolfram Alpha LLC (Wolfram Research Incorporated)
• Inventors: Wolfram, Stephen, Macura, Wiktor, Pilat, Michael
• Primary Examiner(s): Uddin, Md I
• Application Number:
  US15/676,636
• Publication Number:
  US 20170344654A1
• Time in Patent Office: 512 Days
• Field of Search: 707706, 707708, 707748
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/34 Browsing; Visualisation therefor
• CPC Class Codes: G06F 16/954 Navigation, e.g. using categorised browsing

Abstract

Content data items in a first electronic file that correspond to entities in a database comprising categorized entities are identified. Modified content data items of a second electronic file are generated, the modified content data items indicating how the content data items are to be interpreted by a natural language query answering system. Information in the second electronic file indicating how the content data items are to be interpreted by the natural language query answering system are modified in response to user input. The second electronic file is used by the natural language query answering system to facilitate analysis of a natural language query regarding content in the first electronic file. Results of the analysis using the natural language query answering system are output.

Claims

1. A method, comprising:

analyzing, by one or more computer processors, in response to a natural language query regarding content in a first electronic file received via a web page or display, content data items in the first electronic file to identify content data items in the first electronic file that correspond to entities in a database comprising categorized entities, the database utilized by a natural language query answering system that is implemented by one or more computer processors executing machine readable instructions, wherein analyzing the content data items in the first electronic file includes extracting text from the first electronic file that corresponds to the content data items;

generating, by the one or more computer processors and using the analysis of the content data items in the first electronic file, modified content data items of a second electronic file, the modified content data items corresponding to content data items in the first electronic file modified to indicate how the content data items are to be interpreted by the natural language query answering system, wherein generating the modified content data items includes associating keywords with the content data items in the first electronic file based on rankings of different possible meanings of the content data items, the keywords indicating to the natural language query answering system how the content data items are to be interpreted;

modifying, by the one or more computer processors, information in the second electronic file indicating how the content data items are to be interpreted by the natural language query answering system in response to user input;

analyzing, by the one or more computer processors, the second electronic file using the natural language query answering system to facilitate analysis of the natural language query regarding content in the first electronic file, including analyzing the modified content items with the natural language query answering system; and

outputting, by the one or more computer processors, results of the analysis using the natural language query answering system, the results of the analysis being synthesized and outputted in a format suitable for presentation via a web page or display associated with the natural language query answering system.

2. The method of claim 1, further comprising:

receiving, by the one or more computer processors, the first electronic file via a communication network coupled to the one or more computer processors.

3. The method of claim 1, further comprising:

generating, by the one or more computer processors, the second electronic file according to a format of the first electronic file.

4. The method of claim 1, wherein the first electronic file is a spreadsheet file.

5. The method of claim 1, wherein analyzing the second electronic file comprises:

retrieving, by the one or more computer processors, data from the second electronic file in response to the natural language query regarding content in the first electronic file; and

generating, by the one or more computer processors, electronic display information corresponding the data retrieved from the second electronic file.

6. The method of claim 1, wherein analyzing the second electronic file comprises:

processing, by the one or more computer processors, data from the second electronic file in response to the natural language query regarding content in the first electronic file; and

generating, by the one or more computer processors, electronic display information including the processed data from the second electronic file.

7. The method of claim 1, wherein the natural language query answering system is configured to analyze data in the database comprising categorized entities in response to natural language queries.

8. A non-transitory, tangible computer readable storage medium, or media, having stored thereon machine executable instructions that, when executed by one or computer processors, cause the one or more computer processors to:

analyze, in response to a natural language query regarding content in a first electronic file received via a web page or display, content data items in the first electronic file to identify content data items in the first electronic file that correspond to entities in a database comprising categorized entities, the database utilized by the natural language query answering system that is implemented by one or more computer processors executing machine readable instructions wherein analyzing the content data items in the first electronic file includes extracting text from the first electronic file that corresponds to the content data items;

generate, using the analysis of the content data items in the first electronic file, modified content data items of a second electronic file by associating keywords with content data items in the first electronic file based on rankings of different possible meanings of the content data items, the keywords indicating to the natural language query answering system how the content data items are to be interpreted;

modify information in the second electronic file indicating how the content data items are to be interpreted by the natural language query answering system in response to user input;

analyze the second electronic file using the natural language query answering system to facilitate analysis of the natural language query regarding content in the first electronic file, including analyzing the modified content items with the natural language query answering system; and

output results of the analysis using the natural language query answering system, the results of the analysis being synthesized and output in a format suitable for presentation via a web page or display associated with the natural language query answering system.

9. The non-transitory, tangible computer readable storage medium, or media, of claim 8, further storing machine executable instructions that, when executed by the one or computer processors, cause the one or more computer processors to:

receive the first electronic file via a communication network coupled to the one or more computer processors.

10. The non-transitory, tangible computer readable storage medium, or media, of claim 8, further storing machine executable instructions that, when executed by the one or computer processors, cause the one or more computer processors to:

generate the second electronic file according to a format of the first electronic file.

11. The non-transitory, tangible computer readable storage medium, or media, of claim 8, wherein the first electronic file is a spreadsheet file.

12. The non-transitory, tangible computer readable storage medium, or media, of claim 8, further storing machine executable instructions that, when executed by the one or computer processors, cause the one or more computer processors to, as part of analyzing the second electronic file using the natural language query answering system:

retrieve data from the second electronic file in response to the natural language query regarding content in the first electronic file; and

generate electronic display information corresponding the data retrieved from the second electronic file.

13. The non-transitory, tangible computer readable storage medium, or media, of claim 8, further storing machine executable instructions that, when executed by the one or computer processors, cause the one or more computer processors to, as part of analyzing the second electronic file using the natural language query answering system:

process data from the second electronic file in response to the natural language query regarding content in the first electronic file; and

generate electronic display information including the processed data from the second electronic file.

14. The non-transitory, tangible computer readable storage medium, or media, of claim 8, wherein the natural language query answering system is configured to analyze data in the database comprising categorized entities in response to natural language queries.

15. A system, comprising:

one or more computer processors; and

one or more memories coupled to the one or more computer processors, wherein the one or more memories store machine executable instructions that, when executed by the one or computer processors, cause the one or more computer processors to;

implement a natural language query answering system, and

implement an external data pre-processor configured to;

analyze, in response to a natural language query regarding content in a first electronic file received via a web page or display associated with the natural language query answering system, content data items in the first electronic file to identify content data items in the first electronic file that correspond to entities in a database comprising categorized entities, the database utilized by the natural language query answering system that is implemented by one or more computer processors executing machine readable instructions, wherein analyzing the content data items in the first electronic file includes extracting text from the first electronic file that corresponds to the content data items,

generate, using the analysis of the content data items in the first electronic file, modified content data items of a second electronic file by associating keywords with content data items in the first electronic file based on rankings of different possible meanings of the content data items, the keywords indicating to the natural language query answering system how the content data items are to be interpreted, and

modify information in the second electronic file indicating how the content data items are to be interpreted by the natural language query answering system in response to user input;

wherein the natural language query answering system is configured to;

analyze the second electronic file to facilitate analysis of the natural language query regarding content in the first electronic file, including analyzing the modified content items, and

synthesize and output results of the analysis in a format suitable for presentation via a web page or display associated with the natural language query answering system.

16. The system of claim 15, wherein the external data pre-processor configured to:

receive the first electronic file via a communication network coupled to the one or more computer processors.

17. The system of claim 15, wherein the external data pre-processor configured to:

generate the second electronic file according to a format of the first electronic file.

18. The system of claim 15, wherein the first electronic file is a spreadsheet file.

19. The system of claim 15, wherein the natural language query answering system is configured to:

retrieve data from the second electronic file in response to the natural language query regarding content in the first electronic file; and

generate electronic display information corresponding the data retrieved from the second electronic file.

20. The system of claim 15, wherein the natural language query answering system is configured to:

process data from the second electronic file in response to the natural language query regarding content in the first electronic file; and

generate electronic display information including the processed data from the second electronic file.

21. The system of claim 15, wherein the natural language query answering system is configured to analyze data in the database comprising categorized entities in response to natural language queries.

22. The system of claim 15, further comprising the database that stores categorized entities.