公开(公告)号：US11120799B1

公开(公告)日：2021-09-14

申请号：US16574927

申请日：2019-09-18

Applicant: Amazon Technologies, Inc.

Inventor： Arunachalam Sundararaman ,  Balasubramaniam K Thandu ,  Rajesh Ravindran Nandyaleth ,  Hermilo H Cardenas Juarez ,  Ananth Duggirala

IPC: G10L15/22 ,  G10L15/18

Abstract: Systems and methods for natural language processing policies are disclosed. For example, content such as a response to a user command and/or user input such as a customer review, may be analyzed to determine if the content deviates from one or more content policies and to determine a severity of the content-policy deviation(s). A system may determine a number of content-policy deviations associated with the content and whether the content includes an indicator of a person, such as a pronoun and/or a proper noun. Content that includes multiple content-policy deviations and/or than includes an indicator of a person may be determined to be more severe than other deviated content. Applications associated with deviated content may be ranked and corrective action may be taken based on the ranking.

公开(公告)号：US11763816B1

公开(公告)日：2023-09-19

申请号：US17470241

申请日：2021-09-09

Applicant: Amazon Technologies, Inc.

Inventor： Arunachalam Sundararaman ,  Balasubramaniam K Thandu ,  Rajesh Ravindran Nandyaleth ,  Hermilo H Cardenas Juarez ,  Ananth Duggirala

IPC: G10L15/22 ,  G10L15/18

CPC classification number: G10L15/22 ,  G10L15/1815 ,  G10L2015/223

Abstract: Systems and methods for natural language processing policies are disclosed. For example, content such as a response to a user command and/or user input such as a customer review, may be analyzed to determine if the content deviates from one or more content policies and to determine a severity of the content-policy deviation(s). A system may determine a number of content-policy deviations associated with the content and whether the content includes an indicator of a person, such as a pronoun and/or a proper noun. Content that includes multiple content-policy deviations and/or than includes an indicator of a person may be determined to be more severe than other deviated content. Applications associated with deviated content may be ranked and corrective action may be taken based on the ranking.