公开(公告)号：US11978437B1

公开(公告)日：2024-05-07

申请号：US17119099

申请日：2020-12-11

Applicant: Amazon Technologies, Inc.

Inventor： Govindarajan Sundaram Thattai ,  Qing Ping ,  Feiyang Niu ,  Joel Joseph Chengottusseriyil ,  Prashanth Rajagopal ,  Qiaozi Gao ,  Aishwarya Naresh Reganti ,  Gokhan Tur ,  Dilek Hakkani-Tur ,  Rohit Prasad ,  Premkumar Natarajan

IPC: G10L15/00 ,  G06F16/22 ,  G06F21/62 ,  G10L15/18 ,  G10L15/22 ,  G10L15/30 ,  G10L15/183 ,  G10L15/19

CPC classification number: G10L15/1815 ,  G06F16/22 ,  G06F21/6218 ,  G10L15/22 ,  G10L15/30 ,  G10L15/1822 ,  G10L15/183 ,  G10L15/19 ,  G10L2015/223

Abstract: Devices and techniques are generally described for learning personalized concepts for natural language processing. In various examples, a first natural language input may be received. In some examples, a determination may be made that the first natural language input comprises non-actionable slot data. A dialog session may be initiated with the user. In some examples, first slot data that is indicated by the user during the dialog session may be determined. In various examples, data representing the first slot data may be stored in a database in association with the first natural language input.

公开(公告)号：US20240428787A1

公开(公告)日：2024-12-26

申请号：US18340342

申请日：2023-06-23

Applicant: Amazon Technologies, Inc.

Inventor： Mahdi Namazifar ,  Di Jin ,  Yang Liu ,  Devamanyu Hazarika ,  Dilek Hakkani-Tur ,  Yubin Ge

IPC: G10L15/22 ,  G06F40/295 ,  G10L15/183

Abstract: Techniques for constraining the results of a generative language model to valid information using knowledge-grounded documentation. A generative language model may generate invalid results, including compound entities and incorrect entity relations. The techniques include, for a given user inquiry, determining a set of documented information, from a particular knowledge base, that corresponds to the user inquiry. The techniques further include determining a subgraph from a knowledge graph representing the knowledge base, as well as determining a trie data structure representation of the set of documented information. The user inquiry and subgraph are provided as input to a trained generative language model for generating a response to the user inquiry. The techniques include using the trie data structure to validate that the generated response corresponds to real information from the set of documented information.

公开(公告)号：US11200885B1

公开(公告)日：2021-12-14

申请号：US16219228

申请日：2018-12-13

Applicant: Amazon Technologies, Inc.

Inventor： Arindam Mandal ,  Nikko Strom ,  Angeliki Metallinou ,  Tagyoung Chung ,  Dilek Hakkani-Tur ,  Suranjit Adhikari ,  Sridhar Yadav Manoharan ,  Ankita De ,  Qing Liu ,  Raefer Christopher Gabriel ,  Rohit Prasad

IPC: G10L15/22 ,  G10L21/00 ,  G10L15/06 ,  G10L15/18 ,  G06F16/332

Abstract: A dialog manager receives text data corresponding to a dialog with a user. Entities represented in the text data are identified. Context data relating to the dialog is maintained, which may include prior dialog, prior API calls, user profile information, or other data. Using the text data and the context data, an N-best list of one or more dialog models is selected to process the text data. After processing the text data, the outputs of the N-best models are ranked and a top-scoring output is selected. The top-scoring output may be an API call and/or an audio prompt.

公开(公告)号：US12293758B1

公开(公告)日：2025-05-06

申请号：US18081929

申请日：2022-12-15

Applicant: Amazon Technologies, Inc.

Inventor： Alexandros Papangelis ,  Behnam Hedayatnia ,  Chao Zhao ,  Devamanyu Hazarika ,  Di Jin ,  Dilek Hakkani-Tur ,  Mahdi Namazifar ,  Seokhwan Kim ,  Spandana Gella ,  Yang Liu

IPC: G10L15/22 ,  G10L15/18

Abstract: Techniques for generating opinion-based content responsive to a user input are described. The system may receive a user input, and determine dialog context data corresponding to a dialog between a user and the system, and including the user input. The system may determine generation of content responsive to the user input requires opinion-based knowledge, and may extract entities from the dialog context data, and determine natural language data of a knowledge base that includes entities similar to the extracted entities. The system may processes the natural language data and the dialog context data to determine a subset of the natural language data that is responsive to the user input. The system may generate output data responsive to the user input using the responsive natural language data and the dialog context.

公开(公告)号：US12002458B1

公开(公告)日：2024-06-04

申请号：US17012257

申请日：2020-09-04

Applicant: Amazon Technologies, Inc.

Inventor： Qiaozi Gao ,  Govindarajan Sundaram Thattai ,  Qing Ping ,  Joel Joseph Chengottusseriyil ,  Feiyang Niu ,  Gokhan Tur ,  Dilek Hakkani-Tur

IPC: G10L15/22

CPC classification number: G10L15/22

Abstract: A device capable of autonomous motion may move in an environment and may receive audio data from a microphone. If the device receives a command represented in the audio data that is absent from a set of known commands, the device may prompt the user to explain how to perform the command. The device may save a command template corresponding to the command, which may be used to perform future commands.