US 12,254,476 B1
Efficient condition-based linking of communication sessions
Wayne Barakat, Novato, CA (US); Thomas E. Gross, San Anselmo, CA (US); Darius Miranda, San Francisco, CA (US); Marria Wairmola Rhodriquez, San Francisco, CA (US); Andres J. Saenz, Redmond, WA (US); Sadie Salim, Albany, CA (US); and Duc M. Trinh, Golden Valley, MN (US)
Assigned to Wells Fargo Bank, N.A., San Francsico, CA (US)
Filed by Wells Fargo Bank, N.A., San Francisco, CA (US)
Filed on Jan. 11, 2021, as Appl. No. 17/146,286.
Application 17/146,286 is a continuation of application No. 15/600,463, filed on May 19, 2017, granted, now 10,891,629.
Claims priority of provisional application 62/492,077, filed on Apr. 28, 2017.
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 30/016 (2023.01); G06F 16/432 (2019.01); G06F 16/435 (2019.01); H04M 3/493 (2006.01)
CPC G06Q 30/016 (2013.01) [G06F 16/433 (2019.01); G06F 16/435 (2019.01); H04M 3/493 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method, comprising:
detecting, by one or more processors coupled to memory, a request for a communication session from a client device, the request identifying a user profile of a user of the client device;
initiating, by the one or more processors, a first electronic communication between the client device and a first computing device of a first representative, responsive to detecting the request for the communication session from the client device, wherein the first representative is selected based on a similarity between the user profile and a first representative profile of the first representative, the electronic communication comprising an audio stream;
determining, by the one or more processors, a sentiment metric during the first electronic communication, the sentiment metric indicating a level of satisfaction during the first electronic communication, wherein determining the sentiment metric comprises extracting, using speech recognition software to analyze the audio stream of the first electronic communication, a tone of voice of the user, and one or more words of a statement made by the user during the first electronic communication;
identifying, by the one or more processors, a second representative suitable for fulfilling the request for the communication session based on the sentiment metric and a similarity between the user profile and a second representative profile of the second representative;
transmitting to the first computing device of the first representative, by the one or more processors, a notification identifying the second representative;
determining, during the communication session, that the sentiment metric has fallen below a predetermined threshold; and
responsive to determining that the sentiment metric has fallen below the predetermined threshold, automatically joining, by the one or more processors, a second computing device of the second representative to the first electronic communication, such that the first electronic communication involves the user, the first representative, and the second representative.