US 11,811,592 B2
Automatic generation and modification of contact streams via machine-learning analytics
William Brandon George, Pleasant Grove, UT (US); and Kevin Gary Smith, Lehi, UT (US)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on May 20, 2019, as Appl. No. 16/416,536.
Prior Publication US 2020/0374183 A1, Nov. 26, 2020
Int. Cl. H04L 41/08 (2022.01); G06N 20/00 (2019.01); H04L 41/22 (2022.01); H04L 41/16 (2022.01); H04L 67/50 (2022.01); G06N 7/01 (2023.01)
CPC H04L 41/08 (2013.01) [G06N 7/01 (2023.01); G06N 20/00 (2019.01); H04L 41/16 (2013.01); H04L 41/22 (2013.01); H04L 67/535 (2022.05)] 14 Claims
OG exemplary drawing
 
1. A method in which one or more processing devices perform operations comprising:
accessing a set of contact items to be provided to one or more user devices as a contact stream, where the contact stream includes the set of contact items sequenced for delivery via one or more electronic communication channels;
identifying a success metric indicating one or more of (i) an engagement with the contact stream and (ii) an action within an online environment to be performed following engagement with the contact stream;
applying, to the set of contact items, a machine-learning model that is trained to identify relationships among (i) configuration parameters that control delivery of contact streams and (ii) sequences of actions and outcomes performed within online environments; and
outputting one or more of:
the contact stream and configuration data for controlling the delivery of the contact stream, wherein the configuration data includes configuration parameter values that have been computed by the machine-learning model for achieving the identified success metric, and
a success probability computed by the machine-learning model, the success probability indicating a probability of achieving the identified success metric by creating the contact stream.