Abstract: There is provided a method that includes obtaining data that describes (a) a situation, (b) a gesture for a response to the situation, (c) a prompt to accompany the response, and (d) a gestural annotation for the response, and utilizing a conversational machine learning technique to train a natural language understanding (NLU) model to address the situation, based on the data.

Abstract: An ambient listening system, includes: an ambient device configure to listen to a conversation between a customer and a sales agent regarding at least one of a desired service and a desired product, and generate an audio stream of the conversation and a unique identifier for the customer; a voice biometrics service module configure to perform at least one of i) identification of the customer based on the audio stream, and ii) voiceprint enrollment of the customer's voice based on the audio stream and the unique identifier for the customer; a business logic module configured to generate at least one business logic output based on at least one of customer's intent and entity extracted from the audio stream; and an automation platform configured to automate, based on the business logic output, the sales agent's workflow related to at least one of customer record, the desired service and the desired product.

Abstract: The provisioning process of the present invention first determines the average number of units of the system resource that are held per call. This parameter is a function of the call model and call-related event holding times. The average number of units is used, along with the Busy Hour Call Attempts to determine the holding rate, Rresource, of that particular call-related event to be allocated memory. The holding rate is then used by ┌Rresource +7{square root over (Rresource)}┐ to determine the number of resources required to be allocated to the call-related event.