Prediction engine for a network-based service
US11082529B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 16, 2019 |
| Grant date | Aug 3, 2021 |
| Priority date | — |
| Expiry date | Oct 17, 2039 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04L67/75
- WIPO fieldDigital communication
- WIPO sectorElectrical engineering
Abstract
Service providers can be identified to fulfill service requests of a network-based service. A network system is configured to generate, based on historical data associated with the network-based service, a machine-learned service provider optimization (MLSPO) model for generating service provider optimizations. The optimizations can include action recommendations that optimize one or more service metrics. The MLSPO model can be a reinforcement learning model generated by performing a plurality of simulations utilizing one or more virtual agents. A provider device of a service provider can transmit a set of data to the network system that indicates a current location of the service provider. Based on the current location and the MLSPO model, the network system can generate service provider optimizations. Optimization data can be transmitted to the provider device so that the provider device can display information corresponding to the service provider optimizations.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.