Abstract: A method for encouraging dialogue between, and promoting transparency of said dialogue, a plurality of telecommunicators is provided. The plurality of telecommunicators may include an end user and an agent. The method includes receiving a request for a dialogue from the end user. The request includes a set of end user log-in credentials associated with the end user. The method further includes identifying the agent associated with a set of agent log-in credentials. The agent may respond to the request. The method also distinguishes the end user from the agent based on the set of end user log-in credentials and the set of agent log-in credentials and then instantiates an instance of telecommunications between the end user and the agent based, at least in part, on the distinguishing. Finally, the method includes monitoring the instantiation and displaying to the agent a live customer sentiment score based on a sentiment model.

Abstract: A method for encouraging dialogue between, and promoting transparency of said dialogue, a plurality of telecommunicators is provided. The plurality of telecommunicators may include an end user and an agent. The method includes receiving a request for a dialogue from the end user. The request includes a set of end user log-in credentials associated with the end user. The method further includes identifying the agent associated with a set of agent log-in credentials. The agent may respond to the request. The method also distinguishes the end user from the agent based on the set of end user log-in credentials and the set of agent log-in credentials and then instantiates an instance of telecommunications between the end user and the agent based, at least in part, on the distinguishing. Finally, the method includes monitoring the instantiation and displaying to the agent a live customer sentiment score based on a sentiment model.

Abstract: A method for encouraging dialogue between, and promoting transparency of said dialogue, a plurality of telecommunicators is provided. The plurality of telecommunicators may include an end user and an agent. The method includes receiving a request for a dialogue from the end user. The request includes a set of end user log-in credentials associated with the end user. The method further includes identifying the agent associated with a set of agent log-in credentials. The agent may respond to the request. The method also distinguishes the end user from the agent based on the set of end user log-in credentials and the set of agent log-in credentials and then instantiates an instance of telecommunications between the end user and the agent based, at least in part, on the distinguishing. Finally, the method includes monitoring the instantiation.

Abstract: Apparatus and methods for gathering information from layered bots. The apparatus may be configured to run an instance of a user-facing bot. The platform may be configured to send to a selected support bot a back-end query. The platform may be configured to receive from the selected support bot an “OPEN” conversation status for the conversation. The platform may be configured to receive, after receiving the “OPEN” conversation status: a response to the back-end query; and a status update for the conversation status. The status update may be “WAITING”. The platform may be configured to repeat (a) through (c) below until the status update is “CLOSED”: (a) acquire from the user a responsive supplemental fact; (b) transmit to the contact bot the responsive supplemental fact; (c) receive from the contact bot: a response to the supplemental fact; and a status update for the conversation status.

Abstract: Aspects of the disclosure relate to supervised machine-learning (“ML”) training platforms for artificial intelligence (“AI”) computer systems. The ML training platform may include isolated update testing. The isolated update testing may feature a plurality of environments with various levels of isolation. The ML training platform may also include bi-directional channels for controlled update propagation.

Abstract: A method for creating binary classification models and using the binary classification models to select candidate training utterances from a plurality of live utterances is provided. The method may include receiving a plurality of intents and associated training utterances. The method may include creating, from the training utterances, a binary classification model for each intent. The binary classification model may include a vector representation of a line of demarcation between utterances associated with the intent and utterances disassociated from the intent. The method may also include receiving live utterances. An intent may be determined for each live utterance. The method may include creating a vector representation of the live utterance. The method may include selecting candidate training utterances based on a comparison between the vector representation of the live utterance and the vector representation included in the binary classification model of the intent determined for the live utterance.

Abstract: A system for extracting verifiable entities from a user-utterance received on an automated calling service is provided. The system may include a receiver configured to receive a user-utterance, a processor and a non-transitory computer-readable media comprising computer-executable instructions. The processor may be configured to execute the instructions which, canonicalize the user-utterance into a plurality of tokens, determine the number of tokens of the user-utterance, and generate, using a sliding-window protocol, a comprehensive number of n-gram sequences from the user-utterance. The processor may be configured to process a plurality of threads of execution that may include a series of actions executed on the n-gram sequences to identify and extract verified entities from the user-utterance.

Abstract: A system for extracting verifiable entities from a user-utterance received on an automated calling service is provided. The system may include a receiver configured to receive a user-utterance, a processor and a non-transitory computer-readable media comprising computer-executable instructions. The processor may be configured to execute the instructions which, canonicalize the user-utterance into a plurality of tokens, determine the number of tokens of the user-utterance, and generate, using a sliding-window protocol, a comprehensive number of n-gram sequences from the user-utterance. The processor may be configured to process a plurality of threads of execution that may include a series of actions executed on the n-gram sequences to identify and extract verified entities from the user-utterance.

Abstract: A method for creating binary classification models and using the binary classification models to select candidate training utterances from a plurality of live utterances is provided. The method may include receiving a plurality of intents and associated training utterances. The method may include creating, from the training utterances, a binary classification model for each intent. The binary classification model may include a vector representation of a line of demarcation between utterances associated with the intent and utterances disassociated from the intent. The method may also include receiving live utterances. An intent may be determined for each live utterance. The method may include creating a vector representation of the live utterance. The method may include selecting candidate training utterances based on a comparison between the vector representation of the live utterance and the vector representation included in the binary classification model of the intent determined for the live utterance.