Root cause pattern recognition based model training
US12050509B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jan 27, 2021 |
| Grant date | Jul 30, 2024 |
| Priority date | — |
| Expiry date | Nov 14, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Examples provide a system and method for retraining a machine learning (ML) algorithm associated with a trained model using root cause pattern recognition. The system analyzes the results of parsing unstructured data and identifies a root cause pattern causing the trained model to underperform when parsing data including the identified pattern. Examples of data including the pattern are created for use in retraining the model to correctly detect and parse data following the identified pattern. Once retrained, the model is able to parse unstructured data, including data having the identified pattern, in accordance with expected performance metrics. The system automatically identifies parsing errors, identifies the root cause patterns for these errors and retrains the models to correctly handle those patterns for more accurate and efficient handing of unstructured data by trained models.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.