Development of voice and other interaction applications
AssigneeVoicify, LLC
InventorsJeffrey K. McMahon, Robert T. Naughton, Nicholas G. Laidlaw, Alexander M. Dunn, Gavin Berkowitz
Life of this patent
Estimating the term…
Abstract
Among other things, a developer of an interaction application for an enterprise can create items of content to be provided to an assistant platform for use in responses to requests of end-users. The developer can deploy the interaction application using defined items of content and an available general interaction model including intents and sample utterances having slots. The developer can deploy the interaction application without requiring the developer to formulate any of the intents, sample utterances, or slots of the general interaction model.
Claims20
A machine-based method comprising:
- storing a set of available general utterance patterns for inclusion in an interaction application, each of the available general utterance patterns spanning a set of one or more sample utterances that correspond to the available general utterance pattern,
- applying machine learning techniques to at least one of stored sample utterances, stored general utterance patterns, or sample utterances proposed by developers of other interaction applications, to identify additional general utterance patterns, and
- generating an augmented set of available general utterance patterns by including the additional general utterance patterns in the stored set of available general utterance patterns, wherein the augmented set of available general utterance patterns is usable for computationally determining intents corresponding to requests from end users.
A tangible memory storing instructions that, when executed by a processor, cause the processor to perform operations comprising:
- storing a set of available general utterance patterns for inclusion in an interaction application, each of the available general utterance patterns spanning a set of one or more sample utterances that correspond to the available general utterance pattern,
- applying machine learning techniques to at least one of stored sample utterances, stored general utterance patterns, or sample utterances proposed by developers of other interaction applications, to identify additional general utterance patterns, and
- generating an augmented set of available general utterance patterns by including the additional general utterance patterns in the stored set of available general utterance patterns, wherein the augmented set of available general utterance patterns is usable for computationally determining intents corresponding to requests from end users.
Dependencies are inferred from the claim text.