Google patents shared math layer to speed up search matching
Google has been granted a patent for a computer system that matches questions to answers using a specific neural network design. The system processes questions and answers separately but uses a single, shared mathematical step at the end to compare them, which the filing describes as a way to improve efficiency.
In the filing’s own words
Aspects of the technology provide systems and methods for implementing an asymmetric dual encoder architecture. The architecture includes a token embedder layer section having a first token embedding section associated with a first input and a second token embedding section associated with a second input, and an encoder layer section having a first encoder section receiving token embeddings from the first token embedding section and a second encoder section receiving token embeddings from the second token embedding section. A shared projection layer receives encodings from both the first and second encoder sections and generates a set of projections. An embedding space is configured, based on the set of projections, to generate a question embedding and an answer embedding, in which the question and answer embeddings are used in identifying a set of candidate answers to an input answer.
What exactly they claim (claim 1)
1. A computer-implemented asymmetric dual encoder system, comprising: a token embedder layer section having a first token embedding section associated with a first input and a second token embedding section associated with a second input, wherein the first and second token embedding sections are distinctly parameterized; an encoder layer section having a first encoder section configured to receive token embeddings from the first token embedding section and a second encoder section configured to receive token embeddings from the second token embedding section, wherein the first and second encoder sections are distinctly parameterized; a projection layer configured to receive encodings from both the first and second encoder sections and to generate a set of projections, wherein the projection layer is shared by the asymmetric dual encoder system; and an embedding space configured, based on the set of projections, to generate a question embedding and an answer embedding, the question and answer embeddings for use in identifying a set of candidate answers to an input answer.
Facts
- Company
- Google (Google LLC)
- Official title
- Dual encoder retrieval efficiency with parameter sharing in projection layer
- Patent number
- US12762378B2
- Application number
- 18299841
- Filed
- Apr 13, 2023
- Granted
- Oct 13, 2026
- Inventors
- 6
- Claims
- 21
Classified under
G06N 3/0455 Physics & computingG06F 17/16 Physics & computingG06F 40/279 Physics & computingG06F 40/284 Physics & computingG06F 40/30 Physics & computingG06N 3/045 Physics & computingMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents AI tool that turns messy emergency notes into clear messages Sep 3, 2026
- Google patents AI that clicks through apps to finish tasks for you Sep 24, 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.