Microsoft patents search tool that blends multiple query types for better results
Microsoft describes a system that takes a user's search request and creates several variations of it, such as fixing spelling errors or using different search formats. It assigns importance levels to these variations and combines the results to rank documents more accurately.
In the filing’s own words
A weighted multicategory querying (WMQ) tool generates alternates of an initial query through spelling correction, grammar correction, natural language processing, ambiguous term resolution, term normalization, keyword reordering, synonyms, and similar terms. The WMQ tool generates additional queries in different weighted categories such as keyword combination, query programming language (QPL), metadata, or embedding space. Query result individual topic proximity scores are combined with category weights to calculate a combined topic proximity score, which is employed to rank the query result. Embedding space query weight is increased for queries classified as broad. QPL query weight or metadata query weight is increased for queries which contain part or all of a metadata field name. Language models are leveraged for query generation, topic proximity scoring, or both.
What exactly they claim (claim 1)
1. A method performed by a computing system, the method comprising: generating a first query from a base query, the first query belonging to a first query category; generating a second query from the base query, the second query belonging to a second query category which differs from the first query category, each of the first query category and the second query category including at least one of: a keyword combination category, a query programming language category, or an embedding space category; associating a first query weight with the first query; associating a second query weight with the second query; issuing the first query and in response receiving a query result and receiving a first query result topic proximity score; issuing the second query and in response receiving at least the query result and receiving a second query result topic proximity score; calculating a query result combined topic proximity score from at least the first query result topic proximity score, the first query weight, the second query result topic proximity score, and the second query weight; providing the query result and the query result combined topic proximity score to a results ranker; and utilizing an output of the results ranker by performing at least one of: a document retrieval, a document deduplication, or a risk mitigation action.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- WEIGHTED MULTICATEGORY QUERYING
- Publication number
- US20260277915A1
- Application number
- 19194113
- Filed
- Apr 30, 2025
- Published
- Sep 17, 2026
- Inventors
- 21
- Claims
- 20
Classified under
G06F 16/24578 Physics & computingG06F 16/242 Physics & computingG06F 16/248 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.