Method of and server for retraining machine learning algorithm
US11775573B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 31, 2020 |
| Grant date | Oct 3, 2023 |
| Priority date | — |
| Expiry date | May 30, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V30/413
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
There is provided a method and a server for retraining a machine learning algorithm (MLA), the MLA having been trained to classify documents based on features thereof. A resource having a plurality of content items submitted by users is accessed. At least one content item associated with a document having been presented as a search result by a search engine server in response to a search query is identified. The at least one content item is analyzed based on a set of features to determine if the document has been misclassified by the MLA in response to the search query. In response to determining that the document has been misclassified, a training object is generated based on the misclassified document. Other misclassified documents are identified in a similar manner to obtain a set of training objects. The MLA is then retrained based on the set of training objects.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.