OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answering

TL;DR

OmniQuery is a system that enhances personal memory retrieval by integrating scattered contextual information from multiple memories, enabling it to answer complex questions with 71.5% accuracy, surpassing traditional retrieval methods.

Contribution

The paper introduces OmniQuery, a novel system that augments captured memories with contextual information to answer complex personal questions, leveraging large language models for inference.

Findings

Achieved 71.5% accuracy in answering complex personal questions.

Outperformed conventional RAG systems in human evaluations.

Effectively integrated scattered contextual memories for improved retrieval.

Abstract

People often capture memories through photos, screenshots, and videos. While existing AI-based tools enable querying this data using natural language, they only support retrieving individual pieces of information like certain objects in photos, and struggle with answering more complex queries that involve interpreting interconnected memories like sequential events. We conducted a one-month diary study to collect realistic user queries and generated a taxonomy of necessary contextual information for integrating with captured memories. We then introduce OmniQuery, a novel system that is able to answer complex personal memory-related questions that require extracting and inferring contextual information. OmniQuery augments individual captured memories through integrating scattered contextual information from multiple interconnected memories. Given a question, OmniQuery retrieves relevant augmented memories and uses a large language model (LLM) to generate answers with references. In human evaluations, we show the effectiveness of OmniQuery with an accuracy of 71.5%, outperforming a conventional RAG system by winning or tying for 74.5% of the time.