US 12,231,380 B1
Trigger-based transfer of conversations from a chatbot to a human agent
Michael Patrick Rodgers, Lake Oswego, OR (US); and Eric L. Sutton, Naperville, IL (US)
Assigned to Oracle International Corporation, Redwood Shores, CA (US)
Filed by Oracle International Corporation, Redwood Shores, CA (US)
Filed on Oct. 11, 2023, as Appl. No. 18/485,053.
Int. Cl. H04L 51/02 (2022.01); G06F 40/20 (2020.01)
CPC H04L 51/02 (2013.01) [G06F 40/20 (2020.01)] 23 Claims
OG exemplary drawing
 
1. One or more non-transitory computer readable media comprising instructions which, when executed by one or more hardware processors, causes performance of operations comprising:
executing a chatbot for engaging in a chat conversation with a user, wherein executing the chatbot comprises:
generating, using the chatbot, a plurality of outbound messages comprised in the chat conversation, the plurality of outbound messages requesting information corresponding to a service request;
transmitting the plurality of outbound messages to a client device associated with the user;
receiving, from the client device, a plurality of inbound messages comprised in the chat conversation, the plurality of inbound messages comprising the information corresponding to the service request;
based at least on the plurality of inbound messages, detecting that one or more transfer criteria has been met to transfer the chat conversation with the user from the chatbot to a human agent;
wherein the one or more transfer criteria comprises one or more user sentiment criteria,
wherein detecting that the one or more transfer criteria has been met comprises:
determining user sentiment associated with the user based at least on the plurality of inbound messages, and
determining that the user sentiment meets the one or more user sentiment criteria based on at least one of:
i) determining that the user sentiment remains above a first threshold value for a first predetermined duration of time, or
ii) determining that the user sentiment falls below a second threshold value for a second predetermined duration of time;
generating a report, corresponding to the chat conversation, based at least on the plurality of inbound messages;
wherein the report comprises conversation metadata that is (a) derived from an analysis of the chat conversation, (b) is different than the plurality of inbound messages, and (c) is different than the plurality of outbound messages; and
transferring the chat conversation to the human agent at least by:
presenting, to the human agent, the report and a graphical chat interface configured for displaying messages between the human agent and the user; and
presenting interface elements, in association with the graphical chat interface, for receiving user input from the human agent for transmission to the user.