公开(公告)号：US20250005057A1

公开(公告)日：2025-01-02

申请号：US18344698

申请日：2023-06-29

Applicant: Amazon Technologies, Inc.

Inventor： Sopan Khosla ,  Vinayshekhar Bannihatti Kumar ,  Rashmi Gangadharaiah ,  Deepak Seetharam Nadig ,  James W. Horsley ,  Abhijit S. Barde ,  Brijesh Luckria ,  Fawad Abbas ,  Bhaskar Hosahalli Rangaswamy ,  Michael W. Miller

IPC: G06F16/33 ,  G06F9/54 ,  G06F16/332 ,  G06F16/338 ,  G06F40/30 ,  G06F40/40 ,  G06N20/00

Abstract: Systems and methods are provided for a natural language question answering service to provide answers to natural language questions regarding network-based services or computing domains. The natural language question answering service may receive the natural language question from a customer computing device. An aggregator of the natural language question answering service can retrieve passages from search systems based on the question and generate a prompt. A large language model (LLM) of the natural language question answering service may receive the prompt and provide an answer. The answer may be verified by a verifier of the natural language question answering service. Attribution may be applied to the answers and retrieved passages to produce references, inline citations, and similar questions. A watermarking module of the natural language question answering service may watermark the answer if it is verified.

公开(公告)号：US20250005051A1

公开(公告)日：2025-01-02

申请号：US18344747

申请日：2023-06-29

Applicant: Amazon Technologies, Inc.

Inventor： Sopan Khosla ,  Vinayshekhar Bannihatti Kumar ,  Rashmi Gangadharaiah ,  Deepak Seetharam Nadig ,  James W. Horsley ,  Abhijit S Barde

IPC: G06F16/332 ,  G06F9/54 ,  G06F16/33

Abstract: Systems and methods are provided for a natural language question answering service to provide answers to natural language questions regarding network-based services or computing domains. The natural language question answering service may receive the natural language question from a customer computing device. An aggregator of the natural language question answering service can retrieve passages from search systems based on the question and generate a prompt. A large language model (LLM) of the natural language question answering service may receive the prompt and provide an answer. The answer may be verified by a verifier of the natural language question answering service. Attribution may be applied to the answers and retrieved passages to produce references, inline citations, and similar questions. A watermarking module of the natural language question answering service may watermark the answer if it is verified.

公开(公告)号：US20250103656A1

公开(公告)日：2025-03-27

申请号：US18976213

申请日：2024-12-10

Applicant: Amazon Technologies, Inc.

Inventor： Rashmi Gangadharaiah ,  Jonathan James Pezzino ,  James W. Horsley ,  Mira E Hall

IPC: G06F16/9032 ,  G06F40/35

Abstract: Methods, systems, and computer-readable media for interactive command generation for natural language input are disclosed. A natural language dialog system receives a natural language input for a dialog with a user. The system determines a state representation of the dialog based at least in part on the natural language input. The state representation indicates an operation offered by a service. The system generates a natural language output based at least in part on the natural language input. The natural language output solicits an additional natural language input for the dialog. The system determines an updated state representation of the dialog based at least in part on the additional natural language input and the state representation. The updated state representation indicates parameter value(s) for the operation. Based at least in part on the updated state representation, the system generates a command invoking the operation with the parameter value(s).

公开(公告)号：US12197503B1

公开(公告)日：2025-01-14

申请号：US17039933

申请日：2020-09-30

Applicant: Amazon Technologies, Inc.

Inventor： Rashmi Gangadharaiah ,  Jonathan James Pezzino ,  James W. Horsley ,  Mira E Hall

IPC: G06F16/9032 ,  G06F40/35

Abstract: Methods, systems, and computer-readable media for interactive command generation for natural language input are disclosed. A natural language dialog system receives a natural language input for a dialog with a user. The system determines a state representation of the dialog based at least in part on the natural language input. The state representation indicates an operation offered by a service. The system generates a natural language output based at least in part on the natural language input. The natural language output solicits an additional natural language input for the dialog. The system determines an updated state representation of the dialog based at least in part on the additional natural language input and the state representation. The updated state representation indicates parameter value(s) for the operation. Based at least in part on the updated state representation, the system generates a command invoking the operation with the parameter value(s).

公开(公告)号：US20250005052A1

公开(公告)日：2025-01-02

申请号：US18344756

申请日：2023-06-29

Applicant: Amazon Technologies, Inc.

Inventor： Sopan Khosla ,  Vinayshekhar Bannihatti Kumar ,  Rashmi Gangadharaiah ,  James W. Horsley

IPC: G06F16/332 ,  G06F16/33 ,  G06F21/16 ,  G06F40/126

Abstract: Systems and methods are provided for a natural language question answering service to provide answers to natural language questions regarding network-based services or computing domains. The natural language question answering service may receive the natural language question from a customer computing device. An aggregator of the natural language question answering service can retrieve passages from search systems based on the question and generate a prompt. A large language model (LLM) of the natural language question answering service may receive the prompt and provide an answer. The answer may be verified by a verifier of the natural language question answering service. Attribution may be applied to the answers and retrieved passages to produce references, inline citations, and similar questions. A watermarking module of the natural language question answering service may watermark the answer if it is verified.