Google patents method to steer AI output using specific data styles
Google describes a technique for machine learning models that uses a secondary grid, or matrix, to guide how the model processes input data. This grid assigns each piece of input to a specific training data style, ensuring the final output matches the characteristics of that particular style.
In the filing’s own words
A method includes obtaining an input matrix and determining a domain index matrix that includes, for each respective input value of the input matrix, a corresponding domain index value that indicates a corresponding training data distribution of a plurality of training data distributions. The method also includes providing the input matrix and the domain index matrix to a machine learning model that has been trained using the plurality of training data distributions, where each respective training data distribution is associated with a different attribute. The method further includes generating, by the machine learning model and based on the input and the domain index matrices, an output matrix that includes, for each respective input value, a corresponding output value generated based on (i) the respective input value and (ii) the corresponding domain index value such that the corresponding output value exhibits the attribute of the corresponding training data distribution.
What exactly they claim (claim 1)
1. A computer-implemented method comprising: obtaining an input matrix representing one or more features of input data; determining a plurality of domain index values that are respectively associated with a plurality of training data distributions; generating a domain index matrix comprising the plurality of domain index values; providing the input matrix and the domain index matrix to a machine learning model that has been trained to generate output matrices using the plurality of training data distributions that are respectively associated with the plurality of domain index values in the domain index matrix; and generating, by the machine learning model and based on the input matrix and the domain index matrix, an output matrix that represents one or more features of output data.
Facts
- Company
- Google (Google LLC)
- Official title
- Generation of Machine Learning Outputs Using a Domain Index Matrix to Control a Relative Contribution of Multiple Different Training Data Sets
- Publication number
- US20260289987A1
- Application number
- 19688301
- Filed
- May 26, 2026
- Published
- Sep 24, 2026
- Inventors
- 1
- Claims
- 20
Classified under
G06V 10/7788 Physics & computingG06V 10/771 Physics & computingMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents AI tool that turns messy emergency notes into clear messages Sep 3, 2026
- Google patents AI that clicks through apps to finish tasks for you Sep 24, 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.