US 12,217,333 B2
Colors as an intelligent service
Hafsa Azaz, Redmond, WA (US); Bryan Allan Coard, Seattle, WA (US); and Vikas Ajay Taskar, Redmond, WA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Aug. 1, 2022, as Appl. No. 17/878,892.
Prior Publication US 2024/0037811 A1, Feb. 1, 2024
Int. Cl. G06T 7/90 (2017.01); G06T 11/00 (2006.01); G06T 11/60 (2006.01); G06V 10/56 (2022.01); G06V 10/70 (2022.01); G06V 10/94 (2022.01)
CPC G06T 11/001 (2013.01) [G06T 7/90 (2017.01); G06T 11/60 (2013.01); G06V 10/56 (2022.01); G06V 10/70 (2022.01); G06V 10/95 (2022.01); G06T 2200/24 (2013.01)] 17 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 color recommendation request from a content editing application, the color recommendation request including color information pertaining to a document being edited by the content editing application;
identifying at least one color using a color selection machine learning (ML) model pretrained to select the at least one color based on the color information in the color recommendation request, the color selection ML model being trained using training data based on telemetry data generated by at least one user of content editing applications, the telemetry data indicating color choices in different contexts made by the at least one user, the color selection ML model being trained to receive the color information as input and output the at least one color; and
providing a color recommendation indicating the at least one color identified by the color selection ML model to the content editing application,
wherein:
the telemetry data includes user-specific telemetry data pertaining to past color choices made by users in interacting with content editing applications, and
the color selection ML model is trained to learn rules for identifying the at least one color for the color recommendation based on the user-specific telemetry data.