Microsoft patents system that searches mixed security data with natural language
Microsoft describes a method for searching cybersecurity data using natural language, regardless of how the data is stored or queried. The system uses a "data map" to understand relationships between different sources and assigns specific AI agents to handle each part of the search.
In the filing’s own words
Searching heterogeneous cybersecurity data sources is described. A natural language search enables searching across available data sources, independent of underlying storage architectures or query languages. This capability leverages multiple task-specific agents, large language models, and data map representation-based approaches, and enables integration of new data sources into the search process with minimal additional computing resources. The searching includes determining a data map representation for available data sources (which might have different storage architectures or query languages), which indicates relationships between the available data sources. Query intent associated with a query is determined. A query intent task is determined by mapping the query intent to a relevant data source according to the data map representation. A search agent parameterized for searching the relevant data source executes the query intent task. The result of this executed query intent task is used to augment a response to the query.
What exactly they claim (claim 1)
1. A method, comprising: mapping a query intent to a relevant data source according to a data map representation to identify a query intent task, wherein entities and context associated with an input query used to determine the query intent, and the data map representation, indicate relationships between the relevant data source and other available data sources; and executing the query intent task with a search agent parameterized for searching the relevant data source.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- AGENT-BASED SEARCHING OVER HETEROGENEOUS DATA SOURCES
- Publication number
- US20260332628A1
- Application number
- 19728169
- Filed
- Jul 1, 2026
- Published
- Oct 22, 2026
- Inventors
- 7
- Claims
- 20
Classified under
H04L 63/1425 Electricity & electronicsG06F 16/2456 Physics & computingG06F 16/24575 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.