Identifying a classification hierarchy using a trained machine learning pipeline
Номер патента: EP4352655A1
Опубликовано: 17-04-2024
Автор(ы): Alberto Polleri, Guodong Chen, Marc Michiel Bron, Rajiv Kumar, Richard Steven BUCHHEIM, Shekhar Agrawal
Принадлежит: Oracle International Corp
Опубликовано: 17-04-2024
Автор(ы): Alberto Polleri, Guodong Chen, Marc Michiel Bron, Rajiv Kumar, Richard Steven BUCHHEIM, Shekhar Agrawal
Принадлежит: Oracle International Corp
Реферат: Techniques are disclosed for using a trained machine learning (ML) pipeline to identify categories associated with target data items even though the identified categories may not already be present in the hierarchy. The ML pipeline may include trained cluster-based and classification-based machine learning models, among others. If the results of the cluster-based and classification-based machine learning models are the same, then the target data items is assigned to a hierarchical classification consistent with the identical results of the machine learning model. An assigned hierarchical classification may be validated by the operation of subsequent trained ML models that determine whether parent and child categories in the identified classification are properly associated with one another.
Machine learned models for search and recommendations
Номер патента: US20240241897A1. Автор: Li Tan,Xiao Xiao,JIAN Li,Haixun Wang,Taesik NA. Владелец: Maplebear Inc. Дата публикации: 2024-07-18.