/Patent Tracker
GooglePatent applicationAI & softwareInterest 4/10

Google patents method to search specific document groups with AI

Google has filed a patent application for a system that helps users find relevant text within a specific set of documents. The method converts a user's question into a mathematical format and compares it only to pre-processed pieces of text from the chosen document group to find matches.

Why it mattersThis technique could improve how people search through large collections of internal files or specific datasets by limiting the search to relevant areas.

In the filing’s own words

Data indicative of a text query is received. A text embedding for the text query is generated using a machine-learned embedding generation model. A plurality of chunk embeddings respectively generated by the embedding generation model for a plurality of document chunks of the plurality of documents are accessed. The plurality of documents are organized into a plurality of document subsets. Data indicative of selected document subset(s) of the plurality of document subsets is obtained. A similarity search is performed for the text embedding with respect to only chunk embeddings that are associated with document chunks that are included in the selected document subset(s). The similarity search identifies chunk embedding(s) as semantically similar to the text query. Document chunk(s) that correspond to the chunk embedding(s) identified by the similarity search are provided for display within a user interface.

What exactly they claim (claim 1)

1. A computer-implemented method for semantic exploration of a specified subset of a plurality of documents, the method comprising: receiving, by a computing system comprising one or more computing devices, data indicative of a text query; generating, by the computing system using a machine-learned embedding generation model, a text embedding for the text query; accessing, by the computing system, a plurality of chunk embeddings respectively generated by the machine-learned embedding generation model for a plurality of document chunks of the plurality of documents, wherein the plurality of documents are organized into a plurality of document subsets; obtaining, by the computing system, data indicative of one or more selected document subsets of the plurality of document subsets; performing, by the computing system, a similarity search for the text embedding with respect to only chunk embeddings that are associated with document chunks that are included in the one or more selected document subsets, wherein the similarity search identifies one or more of the chunk embeddings as semantically similar to the text query; and providing, by the computing system for display within a user interface, one or more of the plurality of document chunks that correspond to the one or more of the chunk embeddings identified by the similarity search.

Facts

Company
Google (Google LLC)
Official title
Optimizing User Interactions and Task Selection for Large Language Models
Publication number
US20260278007A1
Application number
19469269
Filed
Mar 31, 2023
Published
Sep 17, 2026
Inventors
6
Claims
30

Classified under

G06F 16/90335 Physics & computingG06F 16/90332 Physics & computingG06F 16/93 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.