Network based machine learning generated simulations
US10693997B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 15, 2017 |
| Grant date | Jun 23, 2020 |
| Priority date | — |
| Expiry date | Apr 26, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F40/177
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Embodiments of the present disclosure pertain to network based machine learning generated simulations. In one embodiment, the present disclosure includes a computer implemented method comprising sending first code comprising a programmable calculator from a server system to a client system across a network. A data request is sent to a database, the data request configured to retrieve data from the database comprising a plurality of fields and a target field. The retrieved data is processed using a machine learning algorithm to produce a weight for each field of the plurality of fields and a scoring data structure. The fields and the scoring data structure are sent to the client system across the network. A user selects values for the plurality of fields and the programmable calculator is configured based on the scoring data structure to generate a simulated value for the target field based on the user selected values.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.