Microsoft patents system that uses language models to pull data from web pages
Microsoft describes a system where a language model creates rules to automatically find specific information on websites, apps, or in emails. Once the data is extracted, the system sends it to an API to generate suggestions or alternative options for the user.
In the filing’s own words
Various embodiments discussed herein relate to generating, via a language model, extraction logic to extract parameters from data sources, and using these parameters to generate alternative options or recommendations. Various embodiments operate in offline and/or online/runtime modes. In offline mode, data samples are collected from URLs, webpages, app pages, and/or emails, and extraction logic (for example, regexes, XPath, CSS selectors, or executable code for emails) is generated. The extraction logic is stored with domain-specific metadata for efficient retrieval. In online mode, data sources are detected in real-time, and the stored extraction logic is applied to extracted parameters. The parameters are then passed to an API to determine alternative options or recommendations, which are presented as notifications or contextual suggestions.
What exactly they claim (claim 1)
1. A system comprising: at least one computer processor; and one or more computer storage media storing computer-useable instructions that, when used by the at least one computer processor, cause the at least one computer processor to perform operations comprising: obtaining a data source that includes at least one of: a Uniform Resource Locator (URL), an app page or webpage, or an email; providing the data source and a prompt as input to a language model, wherein the language model generates extraction logic, the extraction logic including at least one of a rule, a pattern, or an instruction defining how information should be extracted from the data source; based at least in part on the language model generating the extraction logic, extracting a parameter from the data source by applying the generated extraction logic to the data source; determining an alternative option or recommendation relative to the parameter by calling an Application Programming Interface (API) and passing the parameter via the API; and based at least in part on the determining of the alternative option or recommendation, generating an output that indicates at least one of: the alternative option or recommendation, or the parameter.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- AUTOMATED EXTRACTION LOGIC GENERATION TO ENHANCE COMPUTING INFORMATION EXTRACTION
- Publication number
- US20260288894A1
- Application number
- 19082917
- Filed
- Mar 18, 2025
- Published
- Sep 24, 2026
- Inventors
- 6
- Claims
- 20
Classified under
G06F 16/9577 Physics & computingG06F 8/43 Physics & computingG06F 40/117 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.