US 11,657,371 B2
Machine-learning-based application for improving digital content delivery
Hongche Liu, Fremont, CA (US); Divya Venugopalan, Redwood City, CA (US); and Shaunak Chatterjee, Sunnyvale, CA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Jun. 8, 2021, as Appl. No. 17/341,687.
Application 17/341,687 is a continuation of application No. 16/019,359, filed on Jun. 26, 2018, granted, now 11,055,668.
Prior Publication US 2021/0295270 A1, Sep. 23, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 10/10 (2023.01); G06Q 10/1053 (2023.01); G06N 20/00 (2019.01); G06F 16/901 (2019.01)
CPC G06Q 10/1053 (2013.01) [G06F 16/9024 (2019.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
generating, by a software application executing at a computer system, a personalized conversation graph for a user of an online service, the personalized conversation graph having a plurality of nodes with each node representing a digital content item for presentation to the user, and one or more edges connecting nodes of the plurality of nodes with each edge of the one or more edges representing a transition between digital content items associated with the nodes connected by the edge, each digital content item comprising an incentive content item and a call-to-action, the generating of the personalized conversation graph being performed using one or more machine learning algorithms;
executing the software application to generate and cause display of a user interface at a client device;
based on an indication of a first action, by the user, received from the client device in response to a prompt, selecting and processing a first node of the personalized conversation graph to cause presentation, in the user interface, of a first incentive content item represented by the first node of the personalized conversation graph and a first call-to-action associated with the first incentive content item; and
in response to an indication of a second action, by the user, received from the client device in response to the first call-to-action, selecting and processing a second node, connected via an edge to the first node in the personalized conversation graph to cause presentation, in the user interface, of a second incentive content item represented by the second node of the personalized conversation graph and a second call-to-action.