US 12,306,742 B2
System and method of determining proximity between different populations
Sergiy Dubynskiy, Kenmore, WA (US); Tatiana Shubin, Redmond, WA (US); Sandhya Shahdeo, Snoqualmie, WA (US); and Poornima Muthukumar, Bothell, WA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Sep. 5, 2021, as Appl. No. 17/467,254.
Prior Publication US 2023/0075564 A1, Mar. 9, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 11/36 (2006.01); G06F 11/3668 (2025.01); G06N 20/00 (2019.01)
CPC G06F 11/3668 (2013.01) [G06N 20/00 (2019.01)] 21 Claims
OG exemplary drawing
 
1. A data processing system comprising:
a processor; and
a memory in communication with the processor, the memory comprising executable instructions that, when executed by the processor, cause the data processing system to perform functions of:
receiving a request to perform a proximity analysis between a first user population and a second user population to determine proximity between the first user population and the second user population by determining a proximity between one or more characteristics of the first user population and one or more characteristics of the second user population, each of the one or more characteristics of the first and second user population referring to one attribute of the first and second user populations;
accessing data related to the one or more characteristics of the first user population and the one or more characteristics of the second user population, wherein the data related to the first user population includes at least one of telemetry data associated with testing of a software application and feedback data;
providing the data related the one or more characteristics of the first user population and the one or more characteristics of the second user population as input to a machine-learning (ML) model for analyzing the data to determine the proximity between the first user population and the second user population;
receiving from the ML model as an output at least one proximity score between the first user population and the second user population; and
providing display data relating to the output to a visualization mechanism for display,
wherein:
the ML model is trained, at least in part, by receiving the feedback data labeled via a data labeling element based on the one attribute of the first and second user populations and by utilizing the labeled feedback data to self-learn, and
the trained ML model computes a similarity measure between at least one of the one or more characteristics of the first user population and one of the one or more characteristics of the second user population to determine the proximity between the first user population and the second user population.