System and method for accelerating user agent chats
AssigneeNuance Communications, Inc.
InventorsPaul Joseph Vozila, Peter Stubley, Jean-Francois Beaumont, Ding Liu, William F. Ganong, III
Life of this patent
Estimating the term…
Abstract
A method, computer program product, and computer system for identifying, by a computing device, a model for predicting conversational phrases for a communication between at least a first user and a second user. The model may be trained based upon, at least in part, an attribute associated with the second user. At least one conversational phrase may be predicted for the communication between the first user and the second user. The at least one conversational phrase may be provided to the second user as an optional phrase to be sent to the first user.
Claims20
A computer-implemented method comprising:
- identifying, by a computing device, a model for predicting conversational phrases for a communication between at least a first user and a second user;
- training the model using long-short term memories (LSTMs) based upon, at least in part, an attribute associated with the second user;
- predicting at least one conversational phrase for the communication between the first user and the second user based upon, at least in part, the model and the attribute associated with the second user, wherein the attribute includes a modification, by the second user, with a previously predicted conversational phrase provided to the second user, wherein the modification includes a deletion of one or more elements of the predicted at least one conversational phrase;
- providing the at least one conversational phrase to both the first user based upon the LSTMs being updated with the modification and the modification being stored in a memory and the second user as an optional phrase before the second user has sent the at least one conversational phrase to the first user;
- and
- sending at least one of the at least one conversational phrase and another conversational phrase to the first user based upon, at least in part, providing the at least one conversational phrase to both the first user and the second user as the optional phrase.
A computer program product residing on a non-transitory computer readable storage medium having a plurality of instructions stored thereon which, when executed across one or more processors, causes at least a portion of the one or more processors to perform operations comprising:
- identifying, by a computing device, a model for predicting conversational phrases for a communication between at least a first user and a second user;
- training the model using long-short term memories (LSTMs) based upon, at least in part, an attribute associated with the second user;
- predicting at least one conversational phrase for the communication between the first user and the second user based upon, at least in part, the model and the attribute associated with the second user, wherein the attribute includes a modification, by the second user, with a previously predicted conversational phrase provided to the second user, wherein the modification includes a deletion of one or more elements of the predicted at least one conversational phrase;
- providing the at least one conversational phrase to both the first user based upon the LSTMs being updated with the modification and the modification being stored in a memory and the second user as an optional phrase before the second user has sent the at least one conversational phrase to the first user;
- and
- sending at least one of the at least one conversational phrase and another conversational phrase to the first user based upon, at least in part, providing the at least one conversational phrase to both the first user and the second user as the optional phrase.
A computing system including one or more processors and one or more memories configured to perform operations comprising:
- identifying, by a computing device, a model for predicting conversational phrases for a communication between at least a first user and a second user;
- training the model using long-short term memories (LSTMs) based upon, at least in part, an attribute associated with the second user;
- predicting at least one conversational phrase for the communication between the first user and the second user based upon, at least in part, the model and the attribute associated with the second user, wherein the attribute includes a modification, by the second user, with a previously predicted conversational phrase provided to the second user, wherein the modification includes a deletion of one or more elements of the predicted at least one conversational phrase;
- providing the at least one conversational phrase to both the first user based upon the LSTMs being updated with the modification and the modification being stored in a memory and the second user as an optional phrase before the second user has sent the at least one conversational phrase to the first user;
- and
- sending at least one of the at least one conversational phrase and another conversational phrase to the first user based upon, at least in part, providing the at least one conversational phrase to both the first user and the second user as the optional phrase.
Dependencies are inferred from the claim text.