Microsoft patents method to organize documents by topic relevance
Microsoft describes a system that groups documents into clusters based on how closely they match a specific topic. It then breaks these groups into smaller subgroups until they are detailed enough to be useful, creating a hierarchical structure. This structure helps computers search, filter, or summarize large collections of text more efficiently.
In the filing’s own words
A topical cluster hierarchy (TCH) is constructed by recursive subclustering of document clusters until a termination condition is detected. The clusters have centroids of topic proximity with respect to at least one user-specified topic. Subclustering starts after thresholds of minimal cluster topic proximity or minimal cluster coherence are met, thus avoiding processing of low-utility clusters. Subclustering terminates when sufficient topic proximity, coherence, or cluster depth is reached. A tool utilizes the TCH to control topic-directed searching, topic-directed filtering, analyzing, summarizing, or categorizing, of documents.
What exactly they claim (claim 1)
1. A method performed by a computing system, the method comprising: calculating a respective centroid of each of a plurality of clusters, each cluster comprising a data structure which represents multiple documents of a corpus; determining a respective topic proximity score for each of the centroids, the topic proximity score representing a proximity of the centroid and its corresponding cluster to a specified topic; constructing a cluster hierarchy by recursively specifying a subcluster of one of the clusters until a termination condition is detected; and utilizing at least the cluster hierarchy to control at least one of: topic-directed searching of the corpus, topic-directed filtering of the corpus, analyzing at least a portion of the corpus, summarizing at least a portion of the corpus, or categorizing at least a portion of the corpus.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- TOPICAL CLUSTER HIERARCHY
- Publication number
- US20260277933A1
- Application number
- 19193420
- Filed
- Apr 29, 2025
- Published
- Sep 17, 2026
- Inventors
- 19
- Claims
- 20
Classified under
G06F 16/285 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.