Machine learning model dynamic token screening and enhanced response generation
US12400079B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 28, 2025 |
| Grant date | Aug 26, 2025 |
| Priority date | — |
| Expiry date | Apr 28, 2045 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F40/284
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Aspects of the present disclosure relate to dynamic token screening and enhanced response generation using machine learning models. Embodiments include determining, by a machine learning model, a baseline attention weight for each token of a plurality of tokens contained in a text string received as an input to the machine learning model. Embodiments include identifying one or more protected tokens of the plurality of tokens contained in the text string and generating a dropout probability for each protected token of the one or more protected tokens. Embodiments include determining, by the machine learning model, a revised attention weight for each token of the plurality of tokens based on the dropout probability for each protected token. Embodiments include generating, by the machine learning model, an output based on the text string and the revised attention weight for each token. Embodiments include providing the output in response to the input.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.