Granted Patent B2

US 12,450,303 · App. 18/505,854 · Granted Oct 21, 2025

Inventors: Arindam Ghosh (Banagalore, IN); Rajan Madhavan (Foster City, CA); Kanagaraj Ramachandran (Bangalore, IN); Arun Sadayam (Bengaluru, IN)

Assignee: Oracle International Corporation

G06F16/9538G06N20/00

Abstract

Claims (83)

1. One or more non-transitory computer-readable media comprising instructions which, when executed by one or more hardware processors, cause performance of operations comprising:

obtaining a set of characteristics of a target user, the set of characteristics comprising one or more characteristics of the target user;

determining a set of candidate data metrics that are relevant to the target user based on the set of characteristics of the target user, the set of candidate data metrics comprising one or more data metrics;

presenting the set of candidate data metrics as a set of recommended data metrics for generating a visualization in a user dashboard;

receiving user input selecting a particular data metric of the set of recommended data metrics;

generating the visualization based on a set of values associated with the particular data metric; and

presenting the visualization in the user dashboard.

2. The one or more non-transitory computer-readable media of claim 1 , wherein determining a set of candidate data metrics that are relevant to the target user comprises:

obtaining sets of training data, wherein a first set of training data of the sets of training data comprises:

one or more characteristics of a particular user; and

one or more data metrics that are relevant to the particular user;

training a machine learning model based on the sets of training data; and

applying the machine learning model to the set of characteristics of the target user to determine the set of candidate data metrics that are relevant to the target user.

3. The one or more non-transitory computer-readable media of claim 2 , wherein the operations further comprise:

receiving feedback regarding the set of candidate data metrics that are relevant to the target user; and

updating the machine learning model based on the feedback.

4. The one or more non-transitory computer-readable media of claim 1 , wherein the set of characteristics of the target user comprises: target user activity and/or target user interaction with information corresponding to the set of candidate data metrics.

5. The one or more non-transitory computer-readable media of claim 1 , wherein obtaining a set of characteristics of the target user comprises: analyzing content presented by or generated by the target user; and wherein determining a set of candidate data metrics that are relevant to the target user is based on the analyzing of the content presented by or generated by the target user.

6. The one or more non-transitory computer-readable media of claim 1 , wherein the operations further comprise:

creating a multi-dimensional representation of a data set;

utilizing the multi-dimensional representation of the data set to query an application programming interface for the set of values; and

receiving, from the application programming interface, the set of values.

7. The one or more non-transitory computer-readable media of claim 1 , wherein the operations further comprise:

selecting a visualization type for the visualization based on the set of characteristics of the target user by:

obtaining sets of training data, wherein a first set of training data of the sets of training data comprises:

one or more characteristics of a particular user; and

one or more visualization types relevant to the particular user;

training a machine learning model based on the sets of training data; and

applying the machine learning model to the set of characteristics of the target user to select the visualization type.

8. The one or more non-transitory computer-readable media of claim 7 , wherein the operations further comprise:

receiving feedback regarding the visualization type; and

updating the machine learning model based on the feedback.

9. The one or more non-transitory computer-readable media of claim 1 , wherein the operations further comprise:

selecting a visualization type for the visualization based on the particular data metric by:

obtaining sets of training data, wherein a first set of training data of the sets of training data comprises:

one or more data metrics; and

one or more visualization types relevant to the one or more data metrics;

training a machine learning model based on the sets of training data; and

applying the machine learning model to the particular data metric to select the visualization type.

10. The one or more non-transitory computer-readable media of claim 9 , wherein the operations further comprise:

receiving feedback regarding the visualization type; and

updating the machine learning model based on the feedback.

11. A method comprising:

obtaining a set of characteristics of a target user, the set of characteristics comprising one or more characteristics of the target user;

determining a set of candidate data metrics that are relevant to the target user based on the set of characteristics of the target user, the set of candidate data metrics comprising one or more data metrics;

presenting the set of candidate data metrics as a set of recommended data metrics for generating a visualization in a user dashboard;

receiving user input selecting a particular data metric of the set of recommended data metrics;

generating the visualization based on a set of values associated with the particular data metric; and

presenting the visualization in the user dashboard

wherein the method is performed by at least one device including a hardware processor.

12. The method of claim 11 , wherein determining a set of candidate data metrics relevant to the target user comprises:

obtaining sets of training data, wherein a first set of training data of the sets of training data comprises:

one or more characteristics of a particular user; and

one or more data metrics that are relevant to the particular user;

training a machine learning model based on the sets of training data; and

applying the machine learning model to the set of characteristics of the target user to determine the set of candidate data metrics relevant to the target user.

13. The method of claim 12 , further comprising:

receiving feedback regarding the set of candidate data metrics that are relevant to the target user; and

updating the machine learning model based on the feedback.

14. The method of claim 11 , wherein the set of characteristics of the target user comprises: target user activity and/or target user interaction with information corresponding to the set of candidate data metrics that are relevant to the target user.

15. The method of claim 11 , wherein obtaining a set of characteristics of the target user comprises: analyzing content presented by or generated by the target user; and wherein determining a set of candidate data metrics that are relevant to the target user is based on the analyzing of the content presented by or generated by the target user.

16. The method of claim 11 , wherein obtaining a set of characteristics of the target user comprises:

obtaining user input indicating a one or more characteristics of the target user;

using natural language processing to analyze the user input to extract the one or more characteristics of the target user; and

wherein determining the set of candidate data metrics that are relevant to the target user is based on the one or more characteristics of the target user.

17. The method of claim 11 , further comprising:

creating a multi-dimensional representation of a data set;

utilizing the multi-dimensional representation of the data set to query an application programming interface for the set of values; and

receiving, from the application programming interface, the set of values.

18. The method of claim 11 , further comprising:

selecting a visualization type for the visualization based on the set of characteristics of the target user by:

obtaining sets of training data, wherein a first set of training data of the sets of training data comprises:

one or more characteristics of a particular user; and

one or more visualization types relevant to the particular user;

training a second machine learning model based on the sets of training data; and

applying the second machine learning model to the set of characteristics of the target user to select the visualization type.

19. The method of claim 11 , further comprising:

selecting a visualization type for the visualization based on the particular data metric by:

obtaining sets of training data, wherein a first set of training data of the sets of training data comprises:

one or more data metrics; and

one or more visualization types relevant to the one or more data metrics;

training a second machine learning model based on the sets of training data; and

applying the second machine learning model to the particular data metric to select the visualization type.

Assignments (1)

Continuity (1)

References Cited (19)