Avoiding supporting evidence processing when evidence scoring does not affect final ranking of a candidate answer
US10147050B2 · kind B2 · utility
0Cited by
3References
12Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Sep 22, 2015 |
| Grant date | Dec 4, 2018 |
| Priority date | — |
| Expiry date | Dec 10, 2035 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04L45/08
- WIPO fieldDigital communication
- WIPO sectorElectrical engineering
Abstract
Methods to provide selective supporting evidence processing by applying a first machine learning (ML) model to a first candidate answer to generate a first confidence score that does not consider supporting evidence for the first candidate answer, determining, from a second ML model, an expected contribution of processing supporting evidence for the first candidate answer, and upon determining that the expected contribution does not exceed a specified threshold, skipping supporting evidence processing for the first candidate answer.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.