US 11,991,308 B2
Call volume prediction
Davide Giovanardi, Stanford, CA (US); and Andrew Miller-Smith, Chicago, IL (US)
Assigned to Zoom Video Communications, Inc., San Jose, CA (US)
Filed by Zoom Video Communications, Inc., San Jose, CA (US)
Filed on Jul. 30, 2021, as Appl. No. 17/390,761.
Prior Publication US 2023/0036270 A1, Feb. 2, 2023
Int. Cl. H04M 3/36 (2006.01); G06N 20/00 (2019.01); H04M 3/523 (2006.01)
CPC H04M 3/362 (2013.01) [G06N 20/00 (2019.01); H04M 3/365 (2013.01); H04M 3/5238 (2013.01); H04M 2203/55 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
accessing a sequence of call volume measurements, wherein each of the call volume measurements is associated with respective metadata, and wherein the respective metadata provides information regarding a time period during which a call volume measurement was made; and
inputting a window of the sequence of call volume measurements with the respective metadata to a machine learning model to obtain a prediction of a call volume, the machine learning model includes embedding functions that are applied to the respective metadata for the call volume measurements in the window, wherein the embedding functions are implemented with a set of parameters that control nonlinear functions applied to a discrete variable of the respective metadata for the call volume measurements in the window to map the discrete variable to a continuous vector space.