US 12,145,069 B2
Automated prediction of user response states based on traversal behavior
Luke Dicken, San Francisco, CA (US); Johnathan Pagnutti, San Francisco, CA (US); and Yang Wen, San Francisco, CA (US)
Assigned to Zynga Inc., San Francisco, CA (US)
Filed by Zynga Inc., San Francisco, CA (US)
Filed on Jun. 16, 2023, as Appl. No. 18/210,949.
Application 18/210,949 is a continuation of application No. 17/680,565, filed on Feb. 25, 2022, granted, now 11,724,193.
Application 17/680,565 is a continuation of application No. 16/948,496, filed on Sep. 21, 2020, granted, now 11,291,915.
Prior Publication US 2023/0405467 A1, Dec. 21, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. A63F 13/65 (2014.01); A63F 13/67 (2014.01); A63F 13/79 (2014.01); G06N 3/04 (2023.01)
CPC A63F 13/65 (2014.09) [A63F 13/67 (2014.09); A63F 13/79 (2014.09); G06N 3/04 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving behavior data for multiple users of a computer-implemented service provided via an online facility, the behavior data indicating interaction journeys by respective users within the online facility, each interaction journey comprising a sequence of actions selected from a predefined set of actions;
based on the behavior data, compiling behavior graph data in which interaction journeys are represented as respective directed graph structures in which each action in the corresponding sequence of actions is represented as a respective action node;
storing the behavior graph data in a graph database;
accessing label data that indicates assigned associations between a plurality of psychological labels and the behavior graph data, each psychological label pertaining to a respective psychological feature of user experience or user behavior in utilization of the service via the online facility;
using the behavior graph data and the associated label data, training an artificial neural network for automated label prediction, thereby providing a trained neural network; and
using the trained neural network, producing a psychological label prediction for a user based on a particular interaction journey by the user.