INTELLIGENT VISUALIZATION MUNGING

• US 20170061659A1
• Filed: 08/31/2016
• Published: 03/02/2017
• Est. Priority Date: 08/31/2015
• Status: Active Grant

• Current Assignee: Accenture Global Solutions Limited (Accenture PLC)
• Original Assignee: Accenture Global Solutions Limited (Accenture PLC)
• Inventors: GS Shetterley, Nathan, PURI, Colin Anil, Bynoe, Joseph, Mahler, Paul Justin
• Granted Patent: US 10,565,750 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/23 Updating
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 10/063 Operations research, analysis or management
• CPC Class Codes: G06T 11/206 Drawing of charts or graphs

Abstract

According to examples, intelligent visualization munging may include transforming and enriching data that is to be visualized, determining features of the transformed and enriched data, determining a user role of a user associated with the transformed and enriched data, and a user interaction of the user. Intelligent visualization munging may further include learning a behavior of the user, and analyzing the features, the user role, the user interaction, and a learned behavior model to generate a recommendation that includes a predetermined number of visualizations from a plurality of available visualizations to display the transformed and enriched data. The predetermined number of visualizations is less than the plurality of available visualizations.

Claims

1. An intelligent visualization munging system comprising:

a data loader, executed by at least one hardware processor, to ascertain data that is to be visualized;

a data iterator, executed by the at least one hardware processor, to transform and enrich the ascertained data;

a data feature and role discoverer, executed by the at least one hardware processor, to

determine features of the transformed and enriched data, and

determine a user role of a user associated with the transformed and enriched data, and a user interaction of the user associated with the transformed and enriched data;

a behavior learner, executed by the at least one hardware processor, to

learn a behavior of the user associated with the transformed and enriched data;

a visualization recommender, executed by the at least one hardware processor, to

analyze the features of the transformed and enriched data, the user role of the user associated with the transformed and enriched data, the user interaction of the user associated with the transformed and enriched data, and a learned behavior model to generate a recommendation that includes a predetermined number of visualizations from a plurality of available visualizations to display the transformed and enriched data, wherein the predetermined number of visualizations is less than the plurality of available visualizations, and

receive selection of a visualization from the predetermined number of recommended visualizations; and

a results generator, executed by the at least one hardware processor, to generate a display of the transformed and enriched data using the selected visualization from the predetermined number of recommended visualizations.

2. The intelligent visualization munging system according to claim 1, wherein

the data feature and role discoverer is to

determine a target role of a target associated with the transformed and enriched data, and a target interaction of the target associated with the transformed and enriched data, and

the visualization recommender is to

analyze

the features of the transformed and enriched data,

the user role of the user associated with the transformed and enriched data, and the user interaction of the user associated with the transformed and enriched data,

the target role of the target associated with the transformed and enriched data, and the target interaction of the target associated with the transformed and enriched data, and

the learned behavior model to generate the recommendation that includes the predetermined number of visualizations from the plurality of available visualizations to display the transformed and enriched data.

3. The intelligent visualization munging system according to claim 2, wherein the data feature and role discoverer is to determine the features of the transformed and enriched data by

classifying internet protocol (IP) addresses associated with the transformed and enriched data into source IP and target IP addresses, and

classifying relationships between user roles including the user role and the IP addresses associated with the transformed and enriched data.

4. The intelligent visualization munging system according to claim 1, wherein the data feature and role discoverer is to determine the user role of the user associated with the transformed and enriched data, and the user interaction of the user associated with the transformed and enriched data by

analyzing a user field of the transformed and enriched data to determine an identity of the user,

mapping the identity of the user to an organizational data set, and

determining, based on the mapping of the identity of the user to the organizational data set, the user role of the user associated with the transformed and enriched data.

5. The intelligent visualization munging system according to claim 1, wherein the data iterator is to transform and enrich the ascertained data by performing field division to divide the ascertained data into a plurality of fields.

6. The intelligent visualization munging system according to claim 1, wherein the data iterator is to transform and enrich the ascertained data by obfuscating a user field for the user associated with the transformed and enriched data in the ascertained data.

7. The intelligent visualization munging system according to claim 1, wherein the data iterator is to transform and enrich the ascertained data by

identifying a plurality of timestamp fields in the ascertained data,

identifying, from the plurality of timestamp fields in the ascertained data, a relevant timestamp field, and

transforming field values for the relevant timestamp field to a standardized time format.

8. The intelligent visualization munging system according to claim 1, wherein the behavior learner is to enrich the learned behavior model based on the learned behavior of the user associated with the transformed and enriched data by

applying multinomial logistic regression to the features of the transformed and enriched data, the user role of the user associated with the transformed and enriched data, the user interaction of the user associated with the transformed and enriched data, and the learned behavior of the user associated with the transformed and enriched data, wherein the learned behavior of the user associated with the transformed and enriched data includes the selection of the visualization from the predetermined number of recommended visualizations.

9. A method for intelligent visualization munging, the method comprising:

transforming and enriching, by at least one hardware processor, data that is to be visualized;

determining, by the at least one hardware processor, features of the transformed and enriched data;

determining, by the at least one hardware processor, a user role of a user associated with the transformed and enriched data, and a user interaction of the user associated with the transformed and enriched data;

learning, by the at least one hardware processor, a behavior of the user associated with the transformed and enriched data;

analyzing, by the at least one hardware processor, the features of the transformed and enriched data, the user role of the user associated with the transformed and enriched data, the user interaction of the user associated with the transformed and enriched data, and a learned behavior model;

generating, by the at least one hardware processor, based on the analysis of the features of the transformed and enriched data, the user role of the user associated with the transformed and enriched data, the user interaction of the user associated with the transformed and enriched data, and the learned behavior model, a recommendation that includes a predetermined number of visualizations from a plurality of available visualizations to display the transformed and enriched data, wherein the predetermined number of visualizations is less than the plurality of available visualizations; and

identifying, by the at least one hardware processor, based on the analysis of the features of the transformed and enriched data, the user role of the user associated with the transformed and enriched data, the user interaction of the user associated with the transformed and enriched data, and the learned behavior model, an anomaly in displays of the recommended visualizations.

10. The method according to claim 9, further comprising:

receiving, by the at least one hardware processor, selection of a visualization from the predetermined number of recommended visualizations; and

generating, by the at least one hardware processor, a display of the transformed and enriched data using the selected visualization from the predetermined number of recommended visualizations.

11. The method according to claim 9, further comprising:

determining, by the at least one hardware processor, a target role of a target associated with the transformed and enriched data, and a target interaction of the target associated with the transformed and enriched data, wherein

analyzing the features of the transformed and enriched data, the user role of the user associated with the transformed and enriched data, the user interaction of the user associated with the transformed and enriched data, and the learned behavior model, and

generating, based on the analysis of the features of the transformed and enriched data, the user role of the user associated with the transformed and enriched data, the user interaction of the user associated with the transformed and enriched data, and the learned behavior model, the recommendation that includes the predetermined number of visualizations from the plurality of available visualizations to display the transformed and enriched data, further comprises;

analyzing

the features of the transformed and enriched data,

the user role of the user associated with the transformed and enriched data, and the user interaction of the user associated with the transformed and enriched data,

the target role of the target associated with the transformed and enriched data, and the target interaction of the target associated with the transformed and enriched data, and

the learned behavior model to generate the recommendation that includes the predetermined number of visualizations from the plurality of available visualizations to display the transformed and enriched data.

12. The method according to claim 10, further comprising:

enriching, by the at least one hardware processor, the learned behavior model based on the learned behavior of the user associated with the transformed and enriched data by

applying multinomial logistic regression to the features of the transformed and enriched data, the user role of the user associated with the transformed and enriched data, the user interaction of the user associated with the transformed and enriched data, and the learned behavior of the user associated with the transformed and enriched data, wherein the learned behavior of the user associated with the transformed and enriched data includes the selection of the visualization from the predetermined number of recommended visualizations.

13. The method according to claim 10, further comprising:

generating a new learned behavior model based on the learned behavior of the user associated with the transformed and enriched data by

determining whether a number of selections of non-recommended visualizations exceeds a predetermined selection number threshold within a predetermined time threshold, and

in response to a determination that the number of selections of non-recommended visualizations exceeds the predetermined selection number threshold within the predetermined time threshold

applying multinomial logistic regression to the features of the transformed and enriched data, the user role of the user associated with the transformed and enriched data, the user interaction of the user associated with the transformed and enriched data, and the learned behavior of the user associated with the transformed and enriched data, wherein the learned behavior of the user associated with the transformed and enriched data includes the selection of the non-recommended visualizations.

14. The method according to claim 9, wherein determining the user role of the user associated with the transformed and enriched data, and the user interaction of the user associated with the transformed and enriched data further comprises:

analyzing a user field of the transformed and enriched data to determine an identity of the user;

mapping the identity of the user to an organizational data set; and

determining, based on the mapping of the identity of the user to the organizational data set, the user role of the user associated with the transformed and enriched data.

15. The method according to claim 9, wherein transforming and enriching the data that is to be visualized further comprises at least one of:

performing field division to divide the data that is to be visualized into a plurality of fields; and

obfuscating a user field for the user associated with the transformed and enriched data in the data that is to be visualized.

16. The method according to claim 9, wherein transforming and enriching the data that is to be visualized further comprises:

identifying a plurality of timestamp fields in the data that is to be visualized,

identifying, from the plurality of timestamp fields in the data that is to be visualized, a relevant timestamp field, and

transforming field values for the relevant timestamp field to a standardized time format.

17. A non-transitory computer readable medium having stored thereon machine readable instructions to provide intelligent visualization munging, the machine readable instructions, when executed, cause a processor to:

transform and enrich data that is to be visualized;

determine features of the transformed and enriched data;

determine

at least one of a user role of a user associated with the transformed and enriched data, and a user interaction of the user associated with the transformed and enriched data, and

at least one of a target role of a target associated with the transformed and enriched data, and a target interaction of the target associated with the transformed and enriched data;

learn a behavior of the user associated with the transformed and enriched data;

analyze

the features of the transformed and enriched data,

the at least one of the user role of the user associated with the transformed and enriched data, and the user interaction of the user associated with the transformed and enriched data,

the at least one of the target role of the target associated with the transformed and enriched data, and the target interaction of the target associated with the transformed and enriched data, and

a learned behavior model; and

generate, based on the analysis of the features of the transformed and enriched data, the at least one of the user role of the user associated with the transformed and enriched data, and the user interaction of the user associated with the transformed and enriched data, the at least one of the target role of the target associated with the transformed and enriched data, and the target interaction of the target associated with the transformed and enriched data, and the learned behavior model, a recommendation that includes a predetermined number of visualizations from a plurality of available visualizations to display the transformed and enriched data, wherein the predetermined number of visualizations is less than the plurality of available visualizations.

18. The non-transitory computer readable medium of claim 17, further comprising the machine readable instructions, when executed, further cause the processor to:

receive selection of a visualization from the predetermined number of recommended visualizations; and

generate a display of the transformed and enriched data using the selected visualization from the predetermined number of recommended visualizations.

19. The non-transitory computer readable medium of claim 17, further comprising the machine readable instructions, when executed, further cause the processor to:

enrich the learned behavior model based on the learned behavior of the user associated with the transformed and enriched data by

applying multinomial logistic regression to the features of the transformed and enriched data, the at least one of the user role of the user associated with the transformed and enriched data, and the user interaction of the user associated with the transformed and enriched data, the at least one of the target role of the target associated with the transformed and enriched data, and the target interaction of the target associated with the transformed and enriched data, and the learned behavior of the user associated with the transformed and enriched data, wherein the learned behavior of the user associated with the transformed and enriched data includes a selection of a visualization from the predetermined number of recommended visualizations.

20. The non-transitory computer readable medium of claim 17, further comprising the machine readable instructions, when executed, further cause the processor to:

generate a new learned behavior model based on the learned behavior of the user associated with the transformed and enriched data by

determining whether a number of selections of non-recommended visualizations exceeds a predetermined selection number threshold within a predetermined time threshold, and

in response to a determination that the number of selections of non-recommended visualizations exceeds the predetermined selection number threshold within the predetermined time threshold

applying multinomial logistic regression to the features of the transformed and enriched data, the at least one of the user role of the user associated with the transformed and enriched data, and the user interaction of the user associated with the transformed and enriched data, the at least one of the target role of the target associated with the transformed and enriched data, and the target interaction of the target associated with the transformed and enriched data, and the learned behavior of the user associated with the transformed and enriched data, wherein the learned behavior of the user associated with the transformed and enriched data includes a selection of a non-recommended visualization.