US 12,445,560 B2
Communication routing based on user characteristics and behavior
Brandon Anthony Scott, San Francisco, CA (US); Aurobind Ravichandran, San Francisco, CA (US); Matthew Surjana Oey, San Francisco, CA (US); and Gregory Shunsuke Wilson, San Francisco, CA (US)
Assigned to ZenPayroll, Inc., San Francisco, CA (US)
Filed by ZenPayroll, Inc., San Francisco, CA (US)
Filed on Jan. 12, 2024, as Appl. No. 18/411,523.
Application 18/411,523 is a continuation of application No. 17/981,478, filed on Nov. 7, 2022, granted, now 11,909,919.
Application 17/981,478 is a continuation of application No. 17/572,479, filed on Jan. 10, 2022, granted, now 11,539,843, issued on Dec. 27, 2022.
Application 17/572,479 is a continuation of application No. 16/835,853, filed on Mar. 31, 2020, granted, now 11,290,596, issued on Mar. 29, 2022.
Prior Publication US 2024/0155057 A1, May 9, 2024
Int. Cl. H04M 3/523 (2006.01); G06N 20/00 (2019.01); H04M 3/42 (2006.01); H04W 12/06 (2021.01)
CPC H04M 3/5235 (2013.01) [G06N 20/00 (2019.01); H04M 3/42059 (2013.01); H04W 12/06 (2013.01); H04M 2203/558 (2013.01); H04M 2203/60 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
accessing, by a communications system, a set of historic activity of historic users with the communications system;
identifying, by the communications system for the historic users, entities within the communications system with which the historic users have established historic communication sessions;
generating, by the communications system, a training set of data based on the accessed set of historic activity, characteristics of the historic users, and the identified entities with which the historic users have established historic communication sessions; and
training, by the communications system, a machine-learned model using the generated training set of data, the machine-learned model configured to, when applied to characteristics and activity of a user, identify an entity within the communications system with which to establish a communication session with the user, the entity identified based at least in part on 1) a portion of an application accessed by the user, 2) an amount of time the user has accessed the portion of the application, 3) a geographic location of the user, and 4) a location of an employer of the user.