Automatically suggesting responses to a received message
AssigneeAsapp, Inc.
InventorsGustavo Sapoznik, Shawn Henry
Life of this patent
Estimating the term…
Abstract
A user may respond to a request of another user by entering text, such as a customer service representative responding to a customer. Suggestions of responses may be provided to the responding user so that the responding user may use a suggested response instead of entering text to provide a response. Previous messages between the two users and other information may be used to determine an appropriate suggested response. A conversation feature vector may be determined from previous messages, and response feature vectors may be determined from the conversation feature vector. The response feature vectors may be used to determine an appropriate suggested response.
Claims20
A computer-implemented method for suggesting a response to a received message, the method comprising:
- receiving text of a message from a first user;
- generating a conversation feature vector using a first neural network and the text of the message from the first user;
- generating a first response feature vector using the conversation feature vector and a second neural network;
- generating a first plurality of suggested words using the first response feature vector, wherein the first plurality of words comprises a first suggested word;
- generating a second response feature vector using the first suggested word, the first response feature vector, and the second neural network;
- generating a second plurality of suggested words using the second response feature vector, wherein the second plurality of suggested words comprises a second suggested word;
- generating a suggested response to the message from the first user using the first suggested word and the second suggested word;
- and
- transmitting the suggested response for presenting to a second user.
A system for suggesting a response to a received message, the system comprising:
- at least one server computer comprising at least one processor and at least one memory, the at least one server computer configured to:
- receive text of a message from a first user;
- generate a conversation feature vector using a first neural network and the text of the message from the first user;
- generate a first response feature vector using the conversation feature vector and a second neural network;
- generate a first plurality of suggested words using the first response feature vector, wherein the first plurality of words comprises a first suggested word;
- generate a second response feature vector using the first suggested word, the first response feature vector, and the second neural network;
- generate a second plurality of suggested words using the second response feature vector, wherein the second plurality of suggested words comprises a second suggested word;
- generate a suggested response to the message from the first user using the first suggested word and the second suggested word;
- and
- transmit the suggested response for presenting to a second user.
One or more non-transitory computer-readable media comprising computer executable instructions that, when executed, cause at least one processor to perform actions comprising:
- receiving text of a message from a first user;
- generating a conversation feature vector using a first neural network and the text of the message from the first user;
- generating a first response feature vector using the conversation feature vector and a second neural network;
- generating a first plurality of suggested words using the first response feature vector, wherein the first plurality of words comprises a first suggested word;
- generating a second response feature vector using the first suggested word, the first response feature vector, and the second neural network;
- generating a second plurality of suggested words using the second response feature vector, wherein the second plurality of suggested words comprises a second suggested word;
- generating a suggested response to the message from the first user using the first suggested word and the second suggested word;
- and
- transmitting the suggested response for presenting to a second user.
Dependencies are inferred from the claim text.