公开(公告)号：US11715042B1

公开(公告)日：2023-08-01

申请号：US16389769

申请日：2019-04-19

申请人： Meta Platforms Technologies, LLC

发明人： Honglei Liu ,  Pararth Paresh Shah ,  Wenxuan Li ,  Wenhai Yang ,  Anuj Kumar

IPC分类号： G06N20/20 ,  G06Q50/00 ,  G06N3/08 ,  G06F18/214 ,  G06N3/045

CPC分类号： G06N20/20 ,  G06F18/214 ,  G06N3/045 ,  G06N3/08 ,  G06Q50/01

摘要： In one embodiment, a method includes training a target machine-learning model iteratively by accessing training data of content objects, training an intermediate machine-learning model that outputs contextual evaluation measurements based on the training data, generating state-indications associated with the training data, wherein the state-indications comprise user-intents, system actions, and user actions, training the target machine-learning model based on the contextual evaluation measurements, the state-indications, and an action set comprising possible system actions, extracting rules based on the target machine-learning model by a sequential pattern-mining model, generating synthetic training data based on the rules, updating the training data by adding the synthetic training data to the training data, determining if a completion condition is reached for the training, and if the completion condition is reached returning the target machine-learning model, else repeating the iterative training of the target machine-learning model.

公开(公告)号：US11657333B1

公开(公告)日：2023-05-23

申请号：US16389769

申请日：2019-04-19

申请人： Meta Platforms Technologies, LLC

发明人： Honglei Liu ,  Pararth Paresh Shah ,  Wenxuan Li ,  Wenhai Yang ,  Anuj Kumar

IPC分类号： G06N20/20 ,  G06Q50/00 ,  G06N3/08 ,  G06F18/214 ,  G06N3/045

CPC分类号： G06N20/20 ,  G06F18/214 ,  G06N3/045 ,  G06N3/08 ,  G06Q50/01

摘要： In one embodiment, a method includes training a target machine-learning model iteratively by accessing training data of content objects, training an intermediate machine-learning model that outputs contextual evaluation measurements based on the training data, generating state-indications associated with the training data, wherein the state-indications comprise user-intents, system actions, and user actions, training the target machine-learning model based on the contextual evaluation measurements, the state-indications, and an action set comprising possible system actions, extracting rules based on the target machine-learning model by a sequential pattern-mining model, generating synthetic training data based on the rules, updating the training data by adding the synthetic training data to the training data, determining if a completion condition is reached for the training, and if the completion condition is reached returning the target machine-learning model, else repeating the iterative training of the target machine-learning model.