Identifying regulator and driver signals in data systems
US11467803B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Sep 11, 2020 |
| Grant date | Oct 11, 2022 |
| Priority date | — |
| Expiry date | Apr 8, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/044
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method of identifying causal relationships between time series may include accessing a hierarchy of nodes in a data structure, where each node in the plurality of nodes may include a time series of data. The method may also include identifying a subset of nodes in the plurality of nodes for which causal relationships may exist in the corresponding time series. The method may additionally include generating a model for each of the subset of nodes, where the model may receive the subset of nodes and generate coefficients indicating how strongly each of the subset of nodes causally affects other nodes in the subset of nodes. The method may further include generating a ranked output of nodes that causally affect a first node in the subset of nodes based on an output of the corresponding model.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.