Candidate visualization techniques for use with genetic algorithms

• US 10,599,979 B2
• Filed: 04/06/2017
• Issued: 03/24/2020
• Est. Priority Date: 09/23/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Keahey, T. Alan, Rope, Daniel J., Wills, Graham J.
• Primary Examiner(s): Afshar, Kamran
• Assistant Examiner(s): Buss, Benjamin J
• Application Number:
  US15/480,422
• Publication Number:
  US 20170213135A1
• Time in Patent Office: 1,083 Days
• Field of Search: None
• CPC Class Codes: G06N 3/126 Evolutionary algorithms, e.g. genetic algorithms or genetic programming
• CPC Class Codes: G06T 11/206 Drawing of charts or graphs

Abstract

According to one embodiment, a method for generating a plurality of candidate visualizations. The method may include receiving a scenario description. The method may also include collecting a plurality of expert data using a training system based on the received scenario description. The method may further include generating at least one predictive model based on the collected plurality of expert data in order to execute the at least one generated predictive model during an application of a plurality of genetic algorithms.

Claims

1. A computer system for generating a plurality of candidate visualizations, the computer system comprising:

one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising;

receiving, by a processor, a scenario description;

collecting a plurality of expert data using a training system based on the received scenario description, wherein the training system is a bootstrap process, wherein the training system is a cloud-based application that generates and presents hypothetical visualization scenarios to subject matter experts through a graphical user interface with which the subject matter experts interact, and wherein the plurality of expert data comprises metric data, and wherein the plurality of metric data comprises skewness of a field and kurtosis of a field;

generating at least one predictive model based on the plurality of collected expert data, wherein the training system utilizes the at least one predictive model to generate one or more subsequent candidate visualizations;

calculating a fitness score for each of a plurality of candidate visualizations by executing the at least one generated predictive model during an application of a plurality of genetic algorithms; and

generating a next generation of candidate visualizations using the plurality of genetic algorithms by mutating or cross-breeding candidate visualizations with a calculated fitness score that satisfies a preconfigured threshold value.

2. The computer system of claim 1, wherein the plurality of expert data is further selected from a group consisting of a plurality of action data and a plurality of opinion data.

3. The computer system of claim 2, wherein the plurality of action data is metadata that captures aspects of actions that make up the hypothetical visualization scenario, and the plurality of action data is selected from a group consisting of element type, number of elements, shown axes, whether a transpose transform is used, whether polar is used, whether data is stacked, and whether data is clustered.

4. The computer system of claim 2, wherein the plurality of metric data is statistical measurements captured from within the hypothetical visualization scenario or metadata of fields used within the hypothetical visualization scenario, and wherein the plurality of metric data is further selected from a group consisting of field type, total number of fields in the hypothetical visualization scenario, total record count for a field, number of unique categories, robustness measure of field associations, applied sorting, physical size allotted to the visualization, metrics for emotional scoring of visualizations, continuity and direction values, and clutter factor in a spatial layout.

5. The computer system of claim 2, wherein the plurality of opinion data comprises free text opinions regarding the hypothetical visualization scenario provided by subject matter experts, data regarding an applicable business domain, and expertise level of each subject matter expert providing an opinion of the hypothetical visualization scenario, and wherein the plurality of opinion data is selected from a group consisting of whether a subject matter expert chose a specific hypothetical visualization scenario from a group of hypothetical visualization scenarios, an explanation of the business problem addressed by hypothetical visualization scenario, a set of application domains for the hypothetical visualization scenario, a rating scale of the effectiveness of a given hypothetical visualization scenario, and a description of a user'"'"'s expertise in visualizations.

6. The computer system of claim 1, wherein the training system collects the plurality of expert data through at least one of an expert selecting a preferred visualization within a plurality of candidate visualizations and an expert submitting an opinion related to the preferred visualization.

7. The computer system of claim 1, wherein the training system includes at least one of a central data storage facility, a plurality of web-based deployment capabilities, and scalability to a corresponding number of experts using the training system.

8. The computer system of claim 1, further comprising:

updating the training system based on the at least one generated predictive model.

9. The computer system of claim 1, wherein generating the at least one predictive model comprises using boosted decision trees, text categorization, and neural networking.

10. A computer program product for generating a plurality of candidate visualizations, the computer program product comprising:

one or more computer-readable tangible storage medium and program instructions stored on at least one of the one or more tangible storage medium, the program instructions executable by a processor, the program instructions comprising;

program instructions to receive, by a processor, a scenario description;

program instructions to collect a plurality of expert data using a training system based on the received scenario-description, wherein the training system is a bootstrap process, wherein the training system is a cloud-based application that generates and presents hypothetical visualization scenarios to subject matter experts through a graphical user interface with which the subject matter experts interact, and wherein the plurality of expert data comprises metric data, and wherein the plurality of metric data comprises skewness of a field and kurtosis of a field;

program instructions to generate at least one predictive model based on the plurality of collected expert data, wherein the training system utilizes the at least one predictive model to generate one or more subsequent candidate visualizations;

program instructions to calculate a fitness score for each of a plurality of candidate visualizations by executing the at least one generated predictive model during an application of a plurality of genetic algorithms; and

program instructions to generate a next generation of candidate visualizations using the plurality of genetic algorithms by mutating or cross-breeding candidate visualizations with a calculated fitness score that satisfies a preconfigured threshold value.

11. The computer program product of claim 10, wherein the plurality of expert data is further selected from a group consisting of a plurality of action data and a plurality of opinion data.

12. The computer program product of claim 11, wherein the plurality of action data is metadata that captures aspects of actions that make up the hypothetical visualization scenario, and the plurality of action data is selected from a group consisting of element type, number of elements, shown axes, whether a transpose transform is used, whether polar is used, whether data is stacked, and whether data is clustered.

13. The computer program product of claim 11, wherein the plurality of metric data is statistical measurements captured from within the hypothetical visualization scenario or metadata of fields used within the hypothetical visualization scenario, and wherein the plurality of metric data is further selected from a group consisting of field type, total number of fields in the hypothetical visualization scenario, total record count for a field, number of unique categories, robustness measure of field associations, applied sorting, physical size allotted to the visualization, metrics for emotional scoring of visualizations, continuity and direction values, and clutter factor in a spatial layout.

14. The computer program product of claim 11, wherein the plurality of opinion data comprises free text opinions regarding the hypothetical visualization scenario provided by subject matter experts, data regarding an applicable business domain, and expertise level of each subject matter expert providing an opinion of the hypothetical visualization scenario, and wherein the plurality of opinion data is selected from a group consisting of whether a subject matter expert chose a specific hypothetical visualization scenario from a group of hypothetical visualization scenarios, an explanation of the business problem addressed by hypothetical visualization scenario, a set of application domains for the hypothetical visualization scenario, a rating scale of the effectiveness of a given hypothetical visualization scenario, and a description of a user'"'"'s expertise in visualizations.

15. The computer program product of claim 10, wherein the training system collects the plurality of expert data through at least one of an expert selecting a preferred visualization within a plurality of candidate visualizations and an expert submitting an opinion related to the preferred visualization.

16. The computer program product of claim 10, wherein the training system includes at least one of a central data storage facility, a plurality of web-based deployment capabilities, and scalability to a corresponding number of experts using the training system.

17. The computer program product of claim 10, further comprising:

program instructions to update the training system based on the at least one generated predictive model.

18. The computer program product of claim 10, wherein generating the at least one predictive model comprises using boosted decision trees, text categorization, and neural networking.