US 12,088,546 B2
Systems and methods for reducing network traffic
Shannon Yogerst, New York, NY (US); Purva Shanker, Arlington, VA (US); Tania Cruz Morales, Washington, DC (US); and Haytham Yaghi, Oakton, VA (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Feb. 15, 2023, as Appl. No. 18/169,833.
Prior Publication US 2024/0275748 A1, Aug. 15, 2024
Int. Cl. H04L 51/21 (2022.01); H04L 51/02 (2022.01)
CPC H04L 51/21 (2022.05) [H04L 51/02 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for reducing network traffic between a service and client devices, the system comprising:
one or more processors; and
one or more non-transitory, computer-readable media comprising instructions that, when executed by the one or more processors, cause operations comprising:
receiving a first data stream for a text-based communication between a chatbot associated with a service and a client device associated with a user account, the text-based communication being conducted by the service using a machine learning model to generate service responses from the chatbot to one or more user queries from the client device;
determining whether the first data stream includes an unresolved user query sent from the client device to the chatbot;
in response to determining that the first data stream includes an unresolved user query sent from the client device to the chatbot, determining whether a voice-based communication occurred between an agent associated with the service and the client device after the text-based communication occurred;
in response to determining that a voice-based communication occurred between the agent and the client device after the text-based communication occurred, processing a second data stream for the voice-based communication to determine whether the voice-based communication includes the unresolved user query and a service response from the agent that addresses the unresolved user query; and
in response to determining that the voice-based communication includes the unresolved user query and the service response from the agent, providing the unresolved user query and the service response to update the machine learning model for the chatbot for use during a future text-based communication conducted by the service, wherein:
in response to receiving the unresolved user query during the future text-based communication, the service uses the updated machine learning model to generate an updated service response from the chatbot that addresses the unresolved user query.