Microsoft patents method to train AI using sampled data ranges
This patent describes a technique for creating training data for neural networks by sampling specific points from numerical ranges. The system pairs these sampled values with other data points to teach the model to predict a range of outcomes rather than a single exact number.
In the filing’s own words
Methods, systems, and apparatuses include determining a set of data. The set of data includes multiple numerical ranges associated with an embedding and an attribute. The numerical range is sampled to obtain a sample value which is also associated with the embedding and the attribute. A set of sample value training data is generated, the set including the sample value, the associated embedding, and the associated attribute. A trained neural network prediction model is generated by applying a prediction model to the set of sample value training data. A set of input data is applied to the trained neural network prediction model. An output is determined by the trained neural network prediction model based on the set of input data. The output is a predicted range of values based on an output mean and an output standard deviation.
What exactly they claim (claim 1)
1. A method comprising: determining a set of data, the set of data comprising a plurality of numerical ranges, a plurality of embeddings, and a plurality of attributes, wherein a numerical range of the plurality of numerical ranges is associated with at least one embedding of the plurality of embeddings and at least one attribute of the plurality of attributes; sampling the numerical range to obtain a plurality of sample values, wherein a first sample value and a second sample value of the plurality of sample values are different discrete point values sampled from the numerical range and are associated with the at least one embedding and the at least one attribute; generating a set of sample value training data comprising a plurality of sample value training vectors, wherein a first sample value training vector of the plurality of sample value training vectors is based on the first sample value, the at least one associated embedding, and the at least one associated attribute and wherein a second sample value training vector of the plurality of sample value training vectors is based on the second sample value, the at least one associated embedding, and the at least one associated attribute; mapping the set of sample value training data to a sample value tensor using a feature tensorization map; training a neural network prediction model to minimize a loss of an output of the neural network prediction model based on the sample value tensor; and determining, by the trained neural network prediction model, an output based on a set of input data, the set of input data comprising at least one input embedding and at least one input attribute, wherein the output is a predicted range of values based on an output mean and an output standard deviation.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- Generating training data using sampled values
- Patent number
- US12755158B2
- Application number
- 17849506
- Filed
- Jun 24, 2022
- Granted
- Oct 6, 2026
- Inventors
- 5
- Claims
- 20
Classified under
G06N 3/088 Physics & computingG06N 7/01 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.