Methods and systems to detect and correct outliers in a dataset stored in a data-storage device
US10474667B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 14, 2017 |
| Grant date | Nov 12, 2019 |
| Priority date | — |
| Expiry date | Apr 4, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F16/951
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Methods and systems are directed to detection and correction of outliers in a dataset stored in a data-storage device. The dataset comprises parameter data that may be stored and organized in the form of a data table with rows and columns of parameter values. Each column of the parameter data is searched for outlier parameter values based on the parameters values in the same column. The parameter data as a whole may be searched for outlier rows of parameter values based on first and second largest variations in the parameter data. Substitute parameter values are determined for the outlier parameter values based on non-outlier parameter values of the parameter data. The substitute parameter values and corresponding outlier parameter values may be displayed in a database management user interface that enables a user to selectively accept or reject each of the substitute parameter values for the corresponding outlier parameter values.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.