Predicting User Behavior in Smart Spaces with LLM-Enhanced Logs and Personalized Prompts

TL;DR

This paper introduces a novel method that uses LLM-enhanced logs and personalized prompts to improve user behavior prediction in smart spaces, effectively capturing individual preferences and rare events.

Contribution

It proposes a new approach combining behavior graphs, personalized prompts, and LLMs to enhance prediction accuracy in smart environments, addressing limitations of existing sequential models.

Findings

Improved prediction accuracy across four real-world datasets.

Enhanced understanding of user intentions, especially for rare events.

Effective integration of domain knowledge via LLMs.

Abstract

Enhancing the intelligence of smart systems, such as smart home, and smart vehicle, and smart grids, critically depends on developing sophisticated planning capabilities that can anticipate the next desired function based on historical interactions. While existing methods view user behaviors as sequential data and apply models like RNNs and Transformers to predict future actions, they often fail to incorporate domain knowledge and capture personalized user preferences. In this paper, we propose a novel approach that incorporates LLM-enhanced logs and personalized prompts. Our approach first constructs a graph that captures individual behavior preferences derived from their interaction histories. This graph effectively transforms into a soft continuous prompt that precedes the sequence of user behaviors. Then our approach leverages the vast general knowledge and robust reasoning capabilities of a pretrained LLM to enrich the oversimplified and incomplete log records. By enhancing these logs semantically, our approach better understands the user's actions and intentions, especially for those rare events in the dataset. We evaluate the method across four real-world datasets from both smart vehicle and smart home settings. The findings validate the effectiveness of our LLM-enhanced description and personalized prompt, shedding light on potential ways to advance the intelligence of smart space.