Systems and methods to train and/or use a machine learning model to generate correspondences between portions of recorded audio content and work unit records of a collaboration environment
US12190292B1 · kind B1 · utility
Assignee
Inventor
Key dates
| Filing date | Feb 17, 2022 |
| Grant date | Jan 7, 2025 |
| Priority date | — |
| Expiry date | Sep 6, 2042 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04N7/155
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
Systems and methods to train a machine learning model to generate correspondences between portions of recorded content and records of a collaboration environment and/or generate correspondences between portions of recorded content and records of a collaboration environment using a trained machine learning model. Exemplary implementations may perform one or more of: manage environment state information maintaining a collaboration environment; obtain correspondence information conveying user-provided correspondences between temporal content of recorded audio content and records; compile the correspondence information and information from records into input/output pairs; train a machine learning model based on the input/output pairs; store the trained machine learning model; provide other information from records and recorded content as input into the trained machine learning model; obtain output from the trained machine learning model including automatically generated correspondence information; and/or other operations.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.