Question answering for a voice user interface
AssigneeAmazon Technologies, Inc.
InventorsWilliam Folwell Barton, Raluca Teodora Stoian, James Alfred Cuff, Matthew Aaron Cember
Life of this patent
Estimating the term…
Abstract
Techniques for receiving user input and soliciting responses from one or more users are described. A user may speak a question to a system. The system may determine that various question and answering content sources cannot provide an answer to the question. The system may then store data representing the question in a dedicated storage. The system may a topic, to which the question relates and provide the question to users having knowledge on the topic.
Claims21
-20. (canceled)
A method, comprising:
- during a first time period:
- receiving, from a first device, first audio data corresponding to a first utterance,
- performing automatic speech recognition (ASR) processing on the first audio data to generate first text data,
- processing the first text data to determine a first answer to the first utterance is unknown,
- after determining the first answer is unknown, storing the first text data in a dedicated storage,
- determining a first user identifier (ID) representing a first user that spoke the first utterance, and
- associating, in the dedicated storage, the first user ID with the first text data;
- and
- during a second time period after the first time period:
- determining the dedicated storage includes second text data associated with the first text data, the second text data representing second answer to the first utterance, the second answer being provided by a second user,
- determining the first user ID is associated with the first text data, and
- causing the first device to present a notification of the second answer.
A method, comprising:
- receiving, from a first device, first data representing first user input;
- determining the first data corresponds to a first question;
- processing the first data with respect to at least one knowledge source to determine a first answer to the first question is unknown;
- storing second data representing the first question in a dedicated storage;
- determining a first user identifier (ID) corresponding to a first user that originated the first user input;
- associating, in the dedicated storage, the first user ID with the second data;
- after storing the second data, determining a second answer to the first question;
- determining the first user ID is associated with the second data;
- and
- causing the first device to present a notification of the second answer.
A system, comprising:
- at least one processor;
- and
- at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:
- receive, from a first device, first data representing first user input;
- determine the first data corresponds to a first question
- process the first data with respect to at least one knowledge source to determine a first answer to the first question is unknown;
- store second data representing the first question in a dedicated storage;
- determine a first user identifier (ID) corresponding to a user that originated the first user input;
- associate, in the dedicated storage, the first user ID with the second data;
- after storing the second data, determine a second answer to the first question;
- determine the first user ID is associated with the second data;
- and
- cause the first device to present a notification of the second answer.
The computing system of claim 13, wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
- present a list of text data, including the second data, to a second user via a second device;
- receive, from the second device, third data representing the second answer;
- and
- store the third data in the dedicated storage.
Dependencies are inferred from the claim text.