Data analysis results authoring and peer review

• US 9,563,608 B1
• Filed: 01/29/2016
• Issued: 02/07/2017
• Est. Priority Date: 01/29/2016
• Status: Expired due to Fees

• Current Assignee: AirBNB Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Keahey, T. Alan, Ashtiani, Behrooz, Rope, Daniel J., Wills, Graham J.
• Primary Examiner(s): Guerra-Erazo, Edgar
• Application Number:
  US15/010,590
• Time in Patent Office: 375 Days
• Field of Search: 704/9, 704/10
• US Class Current: 1/1
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G06F 40/194 Calculation of difference between files
• CPC Class Codes: G06F 40/258 Heading extraction; Automatic titling; Numbering
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06T 11/206 Drawing of charts or graphs

Abstract

Techniques are described for a real-time visualization of data in an integrated authoring environment. In one example, a method includes receiving text information. The method also includes comparing the dynamically entered text information against a data source, wherein the comparing comprises applying natural language processing (NLP) to determine one or more assertion statements in the text information that references data from the data source. The method also includes retrieving the referenced data associated with the one or more assertion statements from the data source. The method further includes generating a visual representation of the referenced data associated with the one or more assertion statements. The method also includes displaying the visual representation, wherein the visual representation is integrated with an authoring interface.

Claims

1. A method comprising:

receiving, with one or more processing devices, text information;

comparing, with the one or more processing devices, the received text information against a data source, wherein the comparing comprises applying natural language processing (NLP) to determine one or more assertion statements in the text information that references data from the data source, wherein comparing the received text information against the data source includes dynamically analyzing the received text information as the text information is received;

retrieving, with the one or more processing devices, the referenced data associated with the one or more assertion statements from the data source;

generating, with the one or more processing devices, a visual representation of the referenced data associated with the one or more assertion statements, wherein generating the visual representation comprises generating one or more statistical analyses of the referenced data for determining veracity of the one or more assertion statements, wherein the one or more statistical analyses comprise one or more inferential statistics from the referenced data; and

displaying, with the one or more processing devices, the visual representation, wherein the visual representation is integrated with an authoring interface.

2. The method of claim 1, wherein the data source comprises at least one of:

a corpus, a body of works, a document, an article, a website, or a data collection.

3. The method of claim 1, wherein receiving the text information comprises receiving a user input selecting a text information fragment for review from among the text information.

4. The method of claim 1, wherein generating the visual representation comprises selecting from a group comprising one or more statistical analyses of the referenced data and one or more graphical representations of the referenced data from the data source.

5. The method of claim 1, wherein the visual representation is generated by a chart recommendation system.

6. The method of claim 1, further comprising:

providing, with the one or more processing devices, an interface to enable a user to perform at least one of;

entering text, identifying the information source, changing text, adjusting the data source, or identifying a predetermined threshold of statistical correctness.

7. A computer system comprising:

one or more processors and one or more computer-readable memories, and one or more non-transitory computer-readable storage mediums;

program instructions, stored on at least one of the one or more storage mediums for execution by at least one of the one or more processors via at least one of the one or more memories, to receive text information;

program instructions, stored on at least one of the one or more storage mediums for execution by at least one of the one or more processors via at least one of the one or more memories, to compare the received text information against a data source, wherein the comparing comprises applying natural language processing (NLP) to determine one or more assertion statements in the text information that references data from the data source, wherein comparing the received text information against the data source includes dynamically analyzing the received text information as the text information is received;

program instructions, stored on at least one of the one or more storage mediums for execution by at least one of the one or more processors via at least one of the one or more memories, to retrieve the referenced data associated with the one or more assertion statements from the data source;

program instructions, stored on at least one of the one or more storage mediums for execution by at least one of the one or more processors via at least one of the one or more memories, to generate a visual representation of the referenced data associated with the one or more assertion statements, wherein the program instructions to generate the visual representation comprises program instructions to generate one or more statistical analyses of the referenced data for determining veracity of the one or more assertion statements, wherein the one or more statistical analyses comprise one or more inferential statistics from the referenced data; and

program instructions, stored on at least one of the one or more storage mediums for execution by at least one of the one or more processors via at least one of the one or more memories, to display the visual representation, wherein the display is integrated with an authoring interface.

8. The computer system of claim 7, wherein the data source comprises at least one of:

a corpus, a body of works, a document, an article, a website, or a data collection.

9. The computer system of claim 7, wherein the program instructions to receive the text information comprises program instructions to receive a user input selecting a text information fragment for review from among the text information.

10. The computer system of claim 7, wherein the program instructions to generate the visual representation comprises program instructions to select from a group comprising one or more statistical analyses of the referenced data and one or more graphical representations of the referenced data from the data source.

11. The computer system of claim 7, wherein the program instructions to generate the visual representation comprises program instructions to generate the visual representation by a chart recommendation system.

12. The computer system of claim 7, further comprising:

program instructions, stored on at least one of the one or more storage mediums for execution by at least one of the one or more processors via at least one of the one or more memories, to provide an interface to enable a user to perform at least entering text, identifying the information source, change text, adjust the data source, or identify the predetermined threshold of statistical correctness.

13. A computer program product comprising a non-transitory computer-readable storage medium having program code embodied therewith, the program code executable by a processor to:

receive text information;

compare the text information against a data source, wherein the comparing comprises applying natural language processing (NLP) to determine one or more assertion statements in the text information that references data from the data source, wherein comparing the received text information against the data source includes dynamically analyzing the received text information as the text information is received;

retrieve the referenced data associated with the one or more assertion statements from the data source;

generate a visual representation of the referenced data associated with one or more assertion statements, wherein the program code to generate the visual representation comprises program code to generate one or more statistical analyses of the referenced data for determining veracity of the one or more assertion statements, wherein the one or more statistical analyses comprise one or more inferential statistics from the referenced data; and

display the visual representation, wherein the display is integrated with an authoring interface.

14. The computer program product of claim 13, wherein the data source comprises at least one of:

a corpus, a body of works, a document, an article, a website, or a data collection.

15. The computer program product of claim 13, wherein the program code to receive the text information comprises program code to receive a user input selecting a text information fragment for review from among the text information.

16. The computer program product of claim 13, wherein the program code to generate the visual representation comprises program code to select from a group comprising one or more statistical analyses of the referenced data and one or more graphical representations of the referenced data from the data source.

17. The computer program product of claim 13, wherein the program code to generate the visual representation comprises program code to generate the visual representation by a chart recommendation system.