IP Library › Granted Patent US 10,956,655
Granted Patent B2
US 10,956,655 · App. 16/421,465 · Granted Mar 23, 2021

Automated production of data-driven reports with descriptive and rich text and graphical contents

Inventor: Keesup Choe (London, GB)
Assignee: PREDICTX LIMITED
G06F40/106G06F40/186G06F40/56G06Q10/10G06T11/20G06T11/60G06N20/00
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,956,655
App. No.
16/421,465
Filed
May 23, 2019
Granted
Mar 23, 2021
Kind
B2
Examiner
KELLS, ASHER
Art Unit
2144
USPC
715/202
Abstract

Embodiments of the invention automate some of the human report generation process with the application of new AI and machine learning technologies plus the automatic generation of cutting-edge infographics, that is also not aesthetically pleasing but also engage the report reading audience. Aspects of the invention employ specific implementations of natural language generation and the recognition of elements of infographics that complimentary to the natural language generation.

Claims (48)

1. A computer-implemented method for automatically producing data driven reports with descriptive texts and graphical contents comprising:

receiving a request with data input to generate a report for an audience;

identifying a configuration file for the report, said configuration file defining a number of infographics parameters of the report, said infographics parameters comprising: layout of the report, characteristics of the audience of the report, an amount of graphical elements of the report, tenses of the descriptive texts, a format of the descriptive texts in the report, and font settings of the report;

receiving instructions from a user to customize the configuration file;

in response to the received instructions, dynamically generating a map including keys and values in response to a request for generating descriptive texts;

populating a pre-determined request templates with the generated mapped keys and values;

selecting vocabularies from a domain dictionary stored in a data store;

dynamically generating sentences based on the configuration file;

dynamically determining factors of the graphical contents based on the configuration file, wherein the various factors comprise at least: an amount of the graphical contents as a function of the generated sentences, a location of the graphical contents, and a type of the graphical contents;

generating a representation of the graphical contents as a function of the determined factors; and

combining the sentences and the graphical contents as a function of the parameters of the configuration file to generate a report, wherein the report resembles a human-generated natural language narratives for the audience.

2. The computer-implemented method of claim 1 , wherein the human-generated natural language narratives resembles a story.

3. The computer-implemented method of claim 1 , wherein the graphical contents comprise a chart or a graph.

4. The computer-implemented method of claim 1 , wherein generating the representation of the graphical contents comprises generating a chart as a function of the determined factors.

5. The computer-implemented method of claim 4 , further comprising dynamically determining a chart type from a data visualization medium or component, wherein the data visualization medium or component comprising one or more of the following: callout, tiny spline, column chart, line chart, or labelled donut.

6. The computer-implemented method of claim 1 , wherein the data input comprises numerical data in a spreadsheet.

7. A non-transitory computer readable medium having stored there computer-executable instructions generated via machine learning algorithms executing a computer-implemented method for automatically producing data driven reports with descriptive texts and graphical contents, said computer-executable instructions comprising:

receiving a request with data input to generate a report for an audience;

identifying a configuration file for the report, said configuration file defining a number of infographics parameters of the report, said infographics parameters comprising: layout of the report, characteristics of the audience of the report, amount of graphical elements of the report, tenses of the descriptive texts, a format of the descriptive texts in the report, and font settings of the report;

receiving instructions from a user to customize the configuration file;

in response to the received instructions, dynamically generating a map including keys and values in response to a request for generating descriptive texts;

populating a pre-determined request templates with the generated mapped keys and values;

selecting vocabularies from a domain dictionary stored in a data store;

dynamically generating sentences based on the configuration file;

dynamically determining factors of the graphical contents based on the configuration file, wherein the various factors comprise at least: an amount of the graphical contents as a function of the generated sentences, a location of the graphical contents, and a type of the graphical contents;

generating a representation of the graphical contents as a function of the determined factors; and

in response to the machine learning algorithms, combining the sentences and the graphical contents as a function of the parameters of the configuration file to generate a report resembling a human-generated natural language narratives for the audience, wherein the descriptive texts and the graphical contents are presented as a function of the audience.

8. The non-transitory computer readable medium of claim 7 , wherein the graphical contents comprise a chart or a graph.

9. The non-transitory computer readable medium of claim 7 , wherein generating the representation of the graphical contents comprises generating a chart as a function of the determined factors.

10. The non-transitory computer readable medium of claim 9 , further comprising dynamically determining a chart type from a data visualization medium or component, wherein the data visualization medium or component comprising one or more of the following: callout, tiny spline, column chart, line chart, or labelled donut.

11. The non-transitory computer readable medium of claim 7 , wherein the human-generated natural language narratives resembles a story.

12. The non-transitory computer readable medium of claim 7 , wherein the data input comprises numerical data in a spreadsheet.

13. A computer-implemented system for automatically producing data driven reports with descriptive texts and graphical contents comprising:

a processor configured to execute computer-executable instructions for:

receiving a request with data input to generate a report for an audience;

identifying a configuration file for the report, said configuration file defining a number of infographics parameters of the report, said infographics parameters comprising: layout of the report, characteristics of the audience of the report, graphical elements of the report, tenses of the descriptive texts, a format of the descriptive texts in the report, and font settings of the report, wherein the configuration file is customizable by the audience;

in response to the received instructions, dynamically generating a map including keys and values in response to a request for generating descriptive texts;

populating a pre-determined request templates with the generated mapped keys and values;

selecting vocabularies from a domain dictionary stored in a data store;

dynamically generating sentences based on the configuration file;

dynamically determining factors of the graphical contents based on the configuration file, wherein the factors comprise at least: an amount of the graphical contents as a function of the generated sentences, a location of the graphical contents, and a type of the graphical contents;

generating a representation of the graphical contents as a function of the determined factors; and

combining the sentences and the graphical contents as a function of the parameters of the configuration file to generate a report, wherein the report resembles a human-generated natural language narratives for the audience.

14. The computer-implemented system of claim 13 , wherein the human-generated natural language narratives resembles a story.

15. The computer-implemented system of claim 13 , wherein the graphical contents comprise a chart or a graph.

16. The computer-implemented system of claim 13 , wherein generating the representation of the graphical contents comprises generating a chart as a function of the determined factors.

17. The computer-implemented system of claim 16 , further comprising dynamically determining a chart type from a data visualization medium or component, wherein the data visualization medium or component comprising one or more of the following: callout, tiny spline, column chart, line chart, or labelled donut.

18. The computer-implemented system of claim 13 , wherein the data input comprises numerical data in a spreadsheet.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 23, 2019
From: CHOE, KEESUP
To: PREDICTX LIMITED
Reel/Frame 050144/0302 →
Continuity (4)
Continuation PCTUS2019033864 · May 23, 2019
Provisional Application 62676277 · May 24, 2018
Provisional Application 62675711 · May 23, 2018
Related Publication 20200073917A1 · Mar 5, 2020
Cited By (4)
US 12,217,000 US 12,462,107 US 12,499,318 US 12,536,382