| CPC G06F 16/243 (2019.01) [G06F 9/542 (2013.01)] | 20 Claims |
|
1. A computer-implemented method, comprising:
receiving, during a current interaction session of a user with a contact center application, a notification from the contact center application that user interaction events have been generated based on user interaction with the contact center application;
retrieving, during the current interaction session, from an events store and in response to the notification, event information for generated events that have been generated based on user interaction with the contact center application during the current interaction session that have an interaction identifier matching an interaction identifier associated with the current interaction session, wherein event information for a first event lacks semantic meaning for establishing a generative large language model (LLM) artificial intelligence (AI) context for a generative LLM AI engine;
obtaining a contact center application use case definition, from among a plurality of use case definitions for different application types, that includes event descriptions of events that can occur during user interactions with an application type of the contact center application during the use case, wherein the event descriptions include semantic information for the first event for establishing the generative LLM AI context for the generative LLM AI engine;
parsing the contact center application use case definition to locate event descriptions that have a same event identifier as generated events that are included in the event information;
enhancing, during the current interaction session, located event descriptions with event information for corresponding generated events to generate contextualized event information that includes semantic information for the first event for establishing the generative LLM AI context for the generative LLM AI engine;
configuring, during the current interaction session, the generative LLM AI engine by using the contextualized event information as a generative LLM AI context to ground the generative LLM AI engine for the current interaction session;
providing a query to the grounded generative LLM AI engine for the grounded generative LLM AI engine to provide assistance in the current interaction session by answering the query;
receiving a query response from the grounded generative LLM AI engine; and
using the query response in the current interaction session.
|