The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Nov. 23, 2021

Filed:

Mar. 10, 2021
Applicant:

United Services Automobile Association (Usaa), San Antonio, TX (US);

Inventors:

Lambros Petropoulos, San Antonio, TX (US);

James Walter Wisnowski, San Antonio, TX (US);

Andrew Thomas Karl, Aurora, CO (US);

Assignee:
Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
H04M 3/523 (2006.01); G06N 7/00 (2006.01); G06F 17/18 (2006.01); H04M 3/36 (2006.01); H04M 7/00 (2006.01);
U.S. Cl.
CPC ...
H04M 3/5238 (2013.01); G06N 7/00 (2013.01); H04M 3/367 (2013.01); H04M 3/5233 (2013.01); G06F 17/18 (2013.01); H04M 7/006 (2013.01);
Abstract

Techniques are described for forecasting and dynamic routing of incoming routing service requests in a service environment that includes one or more call centers. Implementations apply a doubly stochastic modeling technique to modeling call volumes, call wait times, calling handling times, and/or other parameters in a service environment that includes one or more call centers that include multiple skill codes for the service representatives. By simultaneously modeling on different time scales, such as modeling both inter-day and intra-day correlations, implementations are able to provide an analysis that exploits more of the structure in the data compared to traditional techniques. Implementations can also integrate in other types of time series for other effects that may impact the call volume or other parameters in a service environment, such as exogenous and/or anomalous variables that are independent of other inter-day and/or intra-day trends exhibited in the data.


Find Patent Forward Citations

Loading…