US 12,267,372 B2
Enabling permissible interactions with applications shared during audio-visual communication sessions
Lee Adcock, Midlothian, VA (US); and Vamsi Kavuri, Glen Allen, VA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Mar. 16, 2023, as Appl. No. 18/185,338.
Prior Publication US 2024/0314180 A1, Sep. 19, 2024
Int. Cl. H04L 65/401 (2022.01); H04L 65/403 (2022.01)
CPC H04L 65/4015 (2013.01) [H04L 65/403 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for enabling permissible interactions with applications shared during audio-visual communication session, the system comprising:
one or more processors; and
one or more non-transitory, computer-readable media comprising instructions that, when executed by the one or more processors, cause operations comprising:
detecting, by a communication application on a first client device during a communication session between a plurality of users, an activation of a sharing function on a second client device, the sharing function enabling sharing a view of a shared application via the communication application;
receiving, from the second client device, parameter data associated with the shared application, the parameter data comprising a type of the shared application and activation instructions for activating the shared application on the first client device, wherein the activation instructions comprise an identifier of a file to access with the shared application;
determining, based on the type of the shared application, one or more permissible interactions for the shared application;
upon activation of the shared application according to the activation instructions, detecting, based on a user input received by the first client device, an interaction with the shared application;
generating a dataset comprising, for the shared application, a plurality of entries comprising a plurality of possible interactions with a plurality of portions of the shared application;
inputting, into a machine learning model, the dataset to obtain a plurality of predictions indicating the one or more permissible interactions for the shared application, wherein the machine learning model has been trained to indicate whether interactions with portions of applications are permissible;
determining that the interaction is a permissible interaction of the one or more permissible interactions for the shared application; and
performing, based on determining that the interaction is permissible and according to the interaction, an action on a portion of the plurality of portions of the shared application.