US 11,869,016 B1
Multi-channel topic orchestrator
David Charles Hardage, San Antonio, TX (US); Samantha Sprague, Glendale, AZ (US); William Leland Fehlman, Williamsburg, VA (US); Shane Michael Steinert, San Antonio, CA (US); Rajila Vinod, Boerne, TX (US); and George Pinkosky, Round Rock, TX (US)
Assigned to United Services Automobile Association (USAA), San Antonio, TX (US)
Filed by UIPCO, LLC, San Antonio, TX (US)
Filed on May 20, 2019, as Appl. No. 16/417,449.
Int. Cl. G06F 18/2115 (2023.01); G06Q 30/016 (2023.01); G06F 16/9035 (2019.01); H04M 3/53 (2006.01); G06F 16/908 (2019.01); G06F 40/30 (2020.01); G06N 20/00 (2019.01)
CPC G06Q 30/016 (2013.01) [G06F 16/908 (2019.01); G06F 16/9035 (2019.01); G06F 18/2115 (2023.01); G06F 40/30 (2020.01); H04M 3/5307 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
one or more processors; and
one or more memories storing instructions that, when executed by the one or more processors, cause the system to perform a process comprising:
receiving a first set of data from a first data source, wherein the first set of data includes recorded words from people;
receiving a second set of data from a second data source, wherein the second set of data includes recorded words from people;
determining, using the first set of data, a set of topics related to words included in the first set of data,
wherein a total number of topics within the set of topics is based on a pre-determined number;
determining at least one value that describes a similarity between at least a first topic from the set of topics from the first data source and at least a second topic from the set of topics for the second data source;
determining a first time value that describes when the first topic appears in the first data source and a second time value that describes when the second topic appears in the second data source;
determining, based on the similarity between the first topic and the second topic and a time difference between the first time value and the second time value, a predicted time when the first topic will appear in the second data source;
in response to determining the predicted time when the first topic will appear in the second data source, issuing training for at least one customer service representative to respond to one or more questions related to the first topic prior to the predicted time when the first topic will appear in the second data source;
generating, for the first data source and the second data source, a respective first and second timeline that includes the first and second time values, the first topic and the second topic, and an indication that the first topic is similar to or same as the second topic,
wherein the first and second time values fall within a configurable time period for the first timeline and the second timeline, respectively, and
wherein the indication is based on the at least one value being greater than or equal to a pre-determined value; and
sending, to a computer of the at least one customer service representative, the first timeline for the first data source and the second timeline for the second data source, wherein the computer is configured to display the first timeline and the second timeline, respectively.