| CPC G06F 16/148 (2019.01) [G06F 16/16 (2019.01); G06N 20/00 (2019.01)] | 21 Claims |
|
1. A method comprising:
receiving, as an input to a machine-learning model, data indicative of user-interaction of a particular user with a generative artificial intelligence (AI) system, the machine learning model being trained to identify one or more topics associated with inputs provided to the machine-learning model;
identifying, by the machine-learning model based on the input, a first context associated with the data indicative of the user-interaction with the generative AI system;
parsing a file system accessible to the machine-learning model to determine that one or more folders within the file system correspond to the first context, the file system comprising multiple folders each corresponding to a separate topic as identified by the machine-learning model from historical interactions of the particular user with the generative AI system, wherein each of the one or more folders stores information related to the corresponding topic as extracted by the machine-learning model from corresponding portions of the historical interactions;
in response to determining that the one or more folders within the file system correspond to the first context, augmenting the data indicative of the interaction based on corresponding information from the one or more folders to generate an augmented prompt for the generative AI system; and
providing the augmented prompt to the generative AI system for the generative AI system to generate a response to the interaction.
|