Patent Application: LLM for Calendar Interaction

ChangeBridge: Patent Apps - Business Methods (G06Q)

Published December 1st, 2025

Detected March 26th, 2026

Summary

The USPTO has published a patent application (US20260087460A1) detailing a method using large language models (LLMs) to process calendar data and respond to user queries. The application, filed by Felix Weissenberger, Eric Stavarache, and Henry Dlhopolsky, aims to reduce the extent of calendar-related interactions.

View original document View source feed page

What changed

This document is a patent application (US20260087460A1) filed with the USPTO, describing a system that utilizes large language models (LLMs) to process structured calendar data and generate natural language responses to user queries. The proposed method involves priming an LLM with calendar data representations to improve the accuracy and relevance of its outputs, thereby reducing direct user interaction with calendar interfaces.

As this is a patent application, it does not impose immediate regulatory obligations on businesses. However, companies involved in developing AI-powered productivity tools, calendar applications, or natural language processing interfaces should monitor this and similar patent filings. Successful patent grants could lead to licensing requirements or influence the design of future commercial products in this space.

Source document (simplified)

← USPTO Patent Applications

USING LARGE LANGUAGE MODEL IN REDUCING EXTENT OF CALENDAR RELATED INTERACTION

Application US20260087460A1 Kind: A1 Mar 26, 2026

Inventors

Felix Weissenberger, Eric Stavarache, Henry Dlhopolsky

Abstract

Some implementations process structured calendar data of an electronic calendar for a first user, to generate a natural language representation of the structured calendar data. Versions of those implementations further, in response to receiving a query determined to be relevant to the electronic calendar, prime a large language model (LLM) using a priming input (e.g., process the priming input using the LLM), where the priming input is based on the natural language representation of the structured calendar data. Following priming of the LLM using the priming input, some of those versions process, using the LLM, query input that is based on the query, to generate a LLM output and determine, based on the LLM output, a response to the query. The response can include a natural language response that can be rendered.