/Patent Tracker
GooglePatent applicationAI & softwareInterest 6/10

Google patents method to match user queries with relevant documents for LLM tasks

This patent describes a system that takes a user's text query and a selected task, then uses a machine-learned model to find the most relevant pieces of information from a set of documents. It then feeds those specific document chunks into a large language model to generate a more accurate response for the chosen task.

Why it mattersThis could improve how AI assistants handle specific tasks by ensuring they only use the most relevant background information, potentially making their answers more precise and less prone to hallucination.

In the filing’s own words

User interaction information is obtained that is indicative of (a) a text query and (b) a selected task element selected from a plurality of selectable task elements by a user. A text embedding for the text query is generated using a machine-learned embedding generation model. A similarity search is performed for the text embedding with respect to a plurality of chunk embeddings respectively generated by the machine-learned embedding generation model for a plurality of document chunks of a plurality of documents. The similarity search identifies as semantically similar to the text query identified document chunk(s) of the plurality of document chunks. A prompt is processed based on the identified document chunk(s) with the large language model to perform the task associated with the selected task element. A language output is generated with the large language model based on the processing of the prompt.

What exactly they claim (claim 1)

1. A computer-implemented method for facilitating selection of particular language tasks to enhance user interactions with large language models, the method comprising: obtaining, by a computing system comprising one or more computing devices, user interaction information indicative of: (a) a text query comprising at least a portion of a set of text generated by a user through interaction with a text-editing field of a user interface, wherein the user interface comprises the text-editing field and a plurality of selectable task elements respectively associated with a plurality of tasks for a machine-learned large language model; and (b) a selected task element selected from the plurality of selectable task elements by the user; generating, by the computing system using a machine-learned embedding generation model, a text embedding for the text query; performing, by the computing system, a similarity search for the text embedding with respect to a plurality of chunk embeddings respectively generated by the machine-learned embedding generation model for a plurality of document chunks of a plurality of documents, wherein the similarity search identifies as semantically similar to the text query one or more identified document chunks of the plurality of document chunks; processing, by the computing system, a prompt based on the one or more identified document chunks with the machine-learned large language model to perform the task of the plurality of tasks associated with the selected task element; and obtaining, by the computing system, a language output generated by the machine-learned large language model based on the processing of the prompt.

Facts

Company
Google (Google LLC)
Official title
Optimizing Selection of Language Tasks to Enhance Interactions with Large Language Models
Publication number
US20260278290A1
Application number
19469734
Filed
Mar 31, 2023
Published
Sep 17, 2026
Inventors
1
Claims
26

Classified under

G06F 40/40 Physics & computingG06F 16/3344 Physics & computingG06F 40/166 Physics & computingG06F 40/289 Physics & computingG06F 9/451 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Google in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.