Microsoft patents method to extract features from data using wavelets
Microsoft has been granted a patent for a technique that processes digital data by breaking it into small sections called patches. The system uses a transformer model to adjust these patches and then applies wavelet filters to combine them into a new set of training data for prediction models.
In the filing’s own words
Methods, systems, and apparatuses include receiving digital data. Embedded patches are generated using digital data. A transformed patch is generated by applying a transformer block to an embedded patch. Filtered patches are created for the transformed patch by applying wavelet filters to the transformed patch. A combined patch is created by combining the filtered patches. A set of training data is generated using the combined patch. A trained prediction model is generated by applying a prediction model to the set of training data.
What exactly they claim (claim 1)
1. A method comprising: receiving digital data; generating a plurality of embedded patches using the digital data; generating a transformed patch by applying a transformer block to an embedded patch of the plurality of embedded patches; creating a plurality of filtered patches for the transformed patch by applying a plurality of wavelet filters to the transformed patch, wherein the plurality of filtered patches includes a first filtered patch created by applying a first wavelet filter of the plurality of wavelet filters and a second filtered patch created by applying a second wavelet filter of the plurality of wavelet filters; converting the first filtered patch into a filtered probability patch, wherein probability values of the filtered probability patch are proportional to a scale of values of the first filtered patch; creating a combined patch by combining the plurality of filtered patches including the filtered probability patch and the second filtered patch; generating a set of training data using the combined patch; and generating a trained prediction model by applying a prediction model to the set of training data.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- Scalable wavelet transformer-based feature extraction
- Patent number
- US12770059B2
- Application number
- 18155734
- Filed
- Jan 17, 2023
- Granted
- Oct 20, 2026
- Inventors
- 4
- Claims
- 20
Classified under
G06N 20/00 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.