Microsoft patents search suggestions using parallel AI models
Microsoft describes a system that speeds up search suggestions by sending your query to multiple AI models at the same time. Each model uses a different set of internal data, or 'embedding groups,' to create unique results quickly.
In the filing’s own words
This disclosure describes utilizing a suggestion item system to quickly, accurately, and efficiently generate suggestion items using generative artificial intelligence (AI) models and multiple embedding groups. For example, in response to detecting user input, which is often associated with search queries, the suggestion item system provides the user input to multiple generative AI models or model instances that utilize parallel decoding and distinct embedding groups to generate suggestion items. By using parallel decoding from separate embedding groups, the suggestion item system can quickly provide high-quality, accurate, and unique suggestion items in response to user inputs.
What exactly they claim (claim 1)
1. A computer-implemented method for generating suggestion items using one or more artificial intelligence (AI) models, comprising: based on receiving user input associated with a search query: generating a first suggestion item prompt that includes the user input and a first embedding group identifier; and generating a second suggestion item prompt that includes the user input and a second embedding group identifier, wherein the first embedding group identifier differs from the second embedding group identifier; providing the first suggestion item prompt to a first generative AI model to generate a first suggestion item corresponding to the user input; providing the second suggestion item prompt to a second generative AI model to generate a second suggestion item corresponding to the user input, wherein the first suggestion item prompt and the second suggestion item prompt are provided concurrently; receiving the first suggestion item and the second suggestion item, wherein the first suggestion item generated based on the user input differs from the second suggestion item generated based on the user input; and providing the first suggestion item and the second suggestion item in response to receiving the user input.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- GENERATING CONTENT WITH GENERATIVE ARTIFICIAL INTELLIGENCE (AI) MODELS BY PARALLEL DECODING USING DISAGGREGATED DISTRIBUTIONS
- Publication number
- US20260310694A1
- Application number
- 19212395
- Filed
- May 19, 2025
- Published
- Oct 8, 2026
- Inventors
- 2
- Claims
- 20
Classified under
G06F 16/33295 Physics & computingG06F 16/335 Physics & computingMore from Microsoft in AI & software
- Microsoft patents method to check AI answers against verified facts Oct 20, 2026
- Microsoft patents AI that presents PowerPoint slides for you Sep 3, 2026
- Microsoft patents method to check if LLM answers are based on real data Sep 10, 2026
- Microsoft patents system to blend multiple AI agents into one chat Oct 1, 2026
- Microsoft patents system that answers questions using your screen history Oct 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.