US 11,880,753 B1
System and method for determining application usage
Chaithanya Yembari, Hyderabad (IN); Sethu Meenakshisundaram, Hyderabad (IN); Ritish Reddy, Hyderabad (IN); Chinmay Panda, Hyderabad (IN); and Vanketesh Kumar, Hyderabad (IN)
Assigned to ZLURI TECHNOLOGIES PRIVATE LIMITED, Hyderabad (IN)
Filed by ZLURI TECHNOLOGIES PRIVATE LIMITED, Hyderabad (IN)
Filed on Dec. 15, 2022, as Appl. No. 18/082,364.
Claims priority of application No. 202241059873 (IN), filed on Oct. 19, 2022.
Int. Cl. G06F 15/16 (2006.01); G06N 20/00 (2019.01); G06F 16/25 (2019.01); H04L 67/50 (2022.01)
CPC G06N 20/00 (2019.01) [G06F 16/258 (2019.01); H04L 67/535 (2022.05)] 18 Claims
OG exemplary drawing
 
1. A method for determining application usage, the method comprising:
receiving, by a processor, activity data for one or more applications from a plurality of sources in a raw format, wherein the activity data corresponds to information on one or more activities performed by a set of users with respect to the one or more applications;
creating, by the processor, master data based on parsing the activity data;
receiving, by the processor, organization data, department data, application data, and billing data from the plurality of sources;
enriching, by the processor, the master data with the organization data, the department data, the application data, and the billing data to generate enriched master data;
dynamically calculating, by the processor, weights for each source of the plurality of sources and for each activity of the one or more activities for an application from the one or more applications using a Machine Learning (ML) algorithm, wherein the weights are calculated by the ML algorithm based on a frequency of the activity data received from each source for each activity;
training, by the processor, a regression model based on the enriched master data and the weights assigned to each source for each activity; and
generating, by the processor, a usage score for the application at a user level, a department level, and an organizational level based on the trained regression model.