Personalized Intent Automation Using Dynamic Prompt Generation for Machine Learning

← USPTO Patent Applications

PERSONALIZED INTENT AUTOMATION USING DYNAMIC PROMPT GENERATION FOR A MACHINE LEARNING MODEL

Application US20260093975A1 Kind: A1 Apr 02, 2026

Inventors

Rachita RAMESH, Gaurav BUDJADE, Neha JAYAPRAKASH, Nava Teja TUMMALAPALLI, Sujay SUNDARAM

Abstract

Aspects of the present disclosure provide techniques for automated software application guidance. Embodiments include detecting that a trigger event associated with a user has occurred within a software application. Embodiments include aggregating data related to the user from one or more data sources based on recommendable actions associated with the trigger event. Embodiments include generating a prompt for a machine learning model based on the aggregated data, the recommendable actions, and scores associated with the recommendable actions. Embodiments include providing the prompt to the machine learning model. Embodiments include receiving, from the machine learning model in response to the prompt, a recommended action of the recommendable actions. Embodiments include displaying an indication of the recommended action via the software application. Embodiments include receiving feedback from the user with respect to the recommended action and updating one or more of the scores associated with the recommendable actions based on the feedback.

CPC Classifications

G06N 3/08 G06N 3/0475

Filing Date

2024-09-27

Application No.

18900355

View original document →