Nvidia patents smart document splitting for faster AI search
Nvidia describes a method for breaking documents into uneven chunks based on how similar their content is, rather than using fixed sizes. These chunks are then converted into mathematical codes called embeddings, which allow AI systems to find relevant information more quickly and accurately.
In the filing’s own words
Disclosed are apparatuses, systems, and techniques for efficient retrieval-augmented generation (RAG) processing that uses flexible content-based document segmentation. The techniques include obtaining, using a processing device, content metadata representative of a distribution of content of a document and segmenting, using the content metadata, the document into a plurality of segments, at least two segments of the plurality of segments having different size. The techniques further include processing, using an embedding model, the plurality of segments to generate a plurality of embeddings and storing the plurality of embeddings in a data store.
What exactly they claim (claim 1)
1. A method comprising: obtaining, using a processing device, content metadata representative of a distribution of content of a document; assigning, by a processing device, each of a plurality of units of the document one or more metadata values characterizing association of a respective unit with one or more metadata categories of the content metadata; segmenting, by the processing device, the document into a plurality of segments, wherein each segment of at least a subset of the plurality of segments is obtained by grouping multiple units of the plurality of units of the document, the multiple units characterized by a similarity score above a threshold score, the similarity score computed based on aggregation of similarity values determined from the one or more metadata values assigned to the multiple units; processing, by the processing device executing an embedding model, the plurality of segments to generate a plurality of embeddings, wherein each embedding of the plurality of embeddings is associated with a point in a multi-dimensional embedding space, wherein a number of dimensions of the multi-dimensional embedding space is determined by an architecture of the embedding model, and wherein the embedding model is trained to associate input text strings with points in the multi-dimensional embedding space having a degree of separation that is based on similarity of the input text strings; and storing, by the processing device, the plurality of embeddings in a data store.
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- STRUCTURE-BASED DOCUMENT SEGMENTATION FOR EFFICIENT RETRIEVAL-AUGMENTED AI PROCESSING
- Publication number
- US20260259909A1
- Application number
- 19067671
- Filed
- Feb 28, 2025
- Published
- Sep 3, 2026
- Inventors
- 4
- Claims
- 21
Classified under
G06F 16/334 Physics & computingG06F 16/383 Physics & computingG06F 40/169 Physics & computingMore from Nvidia in AI & software
- Nvidia patents AI coach that analyzes your gameplay to suggest strategies Oct 13, 2026
- Nvidia patents AI system that writes and voices character conversations Sep 10, 2026
- Nvidia patents system that uses AI to find bugs in game videos Sep 17, 2026
- Nvidia patents AI method to make digital characters move realistically Sep 8, 2026
- Nvidia patents AI system that builds image generators from text prompts Sep 15, 2026
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.