公开(公告)号：US20240265067A1

公开(公告)日：2024-08-08

申请号：US18105540

申请日：2023-02-03

申请人： Google LLC

发明人： Henry Scott Dlhopolsky ,  David Griesbach

IPC分类号： G06F21/10 ,  G06F16/955 ,  G06Q20/12

CPC分类号： G06F21/1014 ,  G06F16/955 ,  G06Q20/1235

摘要： A method includes generating a first media item identifier for a first media item of a first media item owner, the first media item being associated with one or more media usage options. The method further includes generating, for each of the one or more media usage options, a media usage option identifier. The method further includes receiving a media usage request of a second media item owner. The method further includes, upon determining that the media usage request satisfies one or more criteria pertaining to the selected media usage option, generating a media usage token. The method further includes transmitting the media usage token to a user device of the second media item owner to authorize the second media item owner to include at least a portion of the first media item in a second media item of the second media item owner.

公开(公告)号：US20240193372A1

公开(公告)日：2024-06-13

申请号：US18064230

申请日：2022-12-09

申请人： Google LLC

发明人： Joseph Lange ,  Henry Scott Dlhopolsky ,  Vladimir Vuskovic

IPC分类号： G06F40/35 ,  G06N20/00 ,  G06Q30/02

CPC分类号： G06F40/35 ,  G06N20/00 ,  G06Q30/0281

摘要： A method for dynamically generating training data for a model includes receiving a transcript corresponding to a conversation between a customer and an agent, the transcript comprising a customer input and an agent input. The method includes receiving a logic model including a plurality of responses, each response of the plurality of responses representing a potential reply to the customer input. The method further includes selecting, based on the agent input, a response from the plurality of responses of the logic model. The method includes determining that a similarity score between the selected response and the agent input satisfies a similarity threshold, and, based on determining that the similarity score between the selected response and the agent input satisfies the similarity threshold, training a machine learning model using the customer input and the selected response.