Abstract: Systems and methods for automated, degradation-resistant, tuning of machine-learning (“ML”) models are provided. The systems and methods may identify an inoperative input utterance, retrieve a feature set associated with the inoperative input utterance, and generate an updated utterance-feature-intent (“UFI”) mapping based on the retrieved feature set. The systems and methods may retrain the ML model using the updated UFI mapping, and compare the accuracy of the system after the retraining and before the retraining. In a scenario where the accuracy of the system does not improve, the systems and methods may amplify the updated UFI mapping. In a scenario where the accuracy of the system does improve, the systems and methods may deploy the updated UFI mapping.

Abstract: A device that is configured to establish a network connection between a user and an agent. The device is further configured to identify a first issue type for the user and to identify a first resolution type provided by the agent based on a conversation between the user and the agent. The device is further configured to identify a performance score from a resolution mapping based on a combination of the first issue type and the first resolution type. The device is further configured to identify a first knowledge area that is associated with the first issue type and to update a first knowledge score that is associated with the first knowledge area in a performance record for the agent based on the performance score. The device is further configured to send a recommendation to the agent based at least in part on the performance score.

Abstract: A device that is configured to assign users to an issue cluster based on issue types for the users. The device is further configured to identify available agents and to assign each available agent to one or more knowledge area clusters based on knowledge scores. A knowledge score indicates an expertise level for an agent in a knowledge area. The device is further configured to identify an issue cluster that is associated with an issue type and to identify a user from the issue cluster. The device is further configured to identify a knowledge area cluster that is associated with the issue type and to identify an agent from the knowledge area cluster. The device is further configured to establish a network connection between a user device associated with the user and a user device associated with the agent.

Abstract: A device that is configured to assign users to an issue cluster based on issue types for the users. The device is further configured to identify available agents and to assign each available agent to one or more knowledge area clusters based on knowledge scores. A knowledge score indicates an expertise level for an agent in a knowledge area. The device is further configured to identify an issue cluster that is associated with an issue type and to identify a user from the issue cluster. The device is further configured to identify a knowledge area cluster that is associated with the issue type and to identify an agent from the knowledge area cluster. The device is further configured to establish a network connection between a user device associated with the user and a user device associated with the agent.

Abstract: A device that is configured to establish a network connection between a user and an agent. The device is further configured to identify a first issue type for the user and to identify a first resolution type provided by the agent based on a conversation between the user and the agent. The device is further configured to identify a performance score from a resolution mapping based on a combination of the first issue type and the first resolution type. The device is further configured to identify a first knowledge area that is associated with the first issue type and to update a first knowledge score that is associated with the first knowledge area in a performance record for the agent based on the performance score. The device is further configured to send a recommendation to the agent based at least in part on the performance score.

Abstract: According to certain embodiments, a system comprises interface circuitry and processing circuitry. The processing circuitry receives an input via the interface circuitry. The input is based on an utterance of a user, and the processing circuitry uses a probabilistic engine to determine one or more candidate intents associated with the utterance. The processing circuitry determines a number of the one or more candidate intents that exceed a threshold. If the number of candidate intents that exceed the threshold does not equal one, the processing circuitry uses a deterministic engine to compare the input to a set of regular expression patterns. If the input matches one of the regular expression patterns, the processing circuitry uses the matching regular expression pattern to determine the intent of the utterance. The interface circuitry communicates the intent of the utterance as an output.

Abstract: A method for blending uncompiled source files and compiled binaries in a single Runtime container. The method may include receiving data at a configuration database. The method may include invoking a scheduler. The method may include determining whether it is time to rerun the software code referenced by the Runtime container. The method may include performing a hash function on source files comprising content and logic. The method may include retrieving source files that include updated hash signatures. The method may include storing an in-memory equivalent of the source files. The method may include invoking a class loader for each source file that has been parsed successfully. The method may include storing, for each successfully loaded source file, a name and reference location. The method may include loading classes based on received names. The method may include compiling the binaries and implementing the logic referenced by the received names.

Abstract: A method for receiving and responding to user input is provided. The user input may be input via a user interface. The method may include receiving input from a user via the user interface. The method may also include transmitting the input to a response determination module. The response determination module may determine a system response to the input. The method may include displaying the system response to the user via the user interface. The method may include receiving an indication from the user that the system response is less than a predetermined threshold level of responsiveness. The method may include dividing the input into component terms and displaying the component terms on the user interface. The method may include enabling the user to eliminate component terms from the input in order to improve responsiveness of the system response, and receiving a selection of eliminated component terms.

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: Systems and methods for automated, degradation-resistant, tuning of machine-learning (“ML”) models are provided. The systems and methods may identify an inoperative input utterance, retrieve a feature set associated with the inoperative input utterance, and generate an updated utterance-feature-intent (“UFI”) mapping based on the retrieved feature set. The systems and methods may retrain the ML model using the updated UFI mapping, and compare the accuracy of the system after the retraining and before the retraining. In a scenario where the accuracy of the system does not improve, the systems and methods may amplify the updated UFI mapping. In a scenario where the accuracy of the system does improve, the systems and methods may deploy the updated UFI mapping.

Abstract: Apparatus for mapping a user utterance onto a plurality of intents is provided. The apparatus may include an intent training database that includes a plurality of tokens and intents. The apparatus may include a processor. The processor may utilize a token-intent map to generate a token-row map and an intent-column map. The processor may map the plurality of tokens onto a token-intent matrix. The processor may generate a token-cognitive matrix, a cognitive-comprehension matrix and an intent-cognitive matrix from the decomposition. The cognitive-comprehension matrix may be the space of entanglement between the token-cognitive matrix and the intent-cognitive matrix. The processor may reduce the rank of the cognitive-comprehension matrix. The processor may compute a plurality of token vectors from a computation of the token-cognitive matrix and the cognitive-comprehension matrix.

Abstract: A method for receiving and responding to user input is provided. The user input may be input via a user interface. The method may include receiving input from a user via the user interface. The method may also include transmitting the input to a response determination module. The response determination module may determine a system response to the input. The method may include displaying the system response to the user via the user interface. The method may include receiving an indication from the user that the system response is less than a predetermined threshold level of responsiveness. The method may include dividing the input into component terms and displaying the component terms on the user interface. The method may include enabling the user to eliminate component terms from the input in order to improve responsiveness of the system response, and receiving a selection of eliminated component terms.

Abstract: According to certain embodiments, a system comprises interface circuitry and processing circuitry. The processing circuitry receives an input via the interface circuitry. The input is based on an utterance of a user, and the processing circuitry uses a probabilistic engine to determine one or more candidate intents associated with the utterance. The processing circuitry determines a number of the one or more candidate intents that exceed a threshold. If the number of candidate intents that exceed the threshold does not equal one, the processing circuitry uses a deterministic engine to compare the input to a set of regular expression patterns. If the input matches one of the regular expression patterns, the processing circuitry uses the matching regular expression pattern to determine the intent of the utterance. The interface circuitry communicates the intent of the utterance as an output.

Abstract: Apparatus for mapping a user utterance onto a plurality of intents is provided. The apparatus may include an intent training database that includes a plurality of tokens and intents. The apparatus may include a processor. The processor may utilize a token-intent map to generate a token-row map and an intent-column map. The processor may map the plurality of tokens onto a token-intent matrix. The processor may generate a token-cognitive matrix, a cognitive-comprehension matrix and an intent-cognitive matrix from the decomposition. The cognitive-comprehension matrix may be the space of entanglement between the token-cognitive matrix and the intent-cognitive matrix. The processor may reduce the rank of the cognitive-comprehension matrix. The processor may compute a plurality of token vectors from a computation of the token-cognitive matrix and the cognitive-comprehension matrix.

Abstract: According to certain embodiments, a system comprises interface circuitry and processing circuitry. The processing circuitry receives an input via the interface circuitry. The input is based on an utterance of a user, and the processing circuitry uses a probabilistic engine to determine one or more candidate intents associated with the utterance. The processing circuitry determines a number of the one or more candidate intents that exceed a threshold. If the number of candidate intents that exceed the threshold does not equal one, the processing circuitry uses a deterministic engine to compare the input to a set of regular expression patterns. If the input matches one of the regular expression patterns, the processing circuitry uses the matching regular expression pattern to determine the intent of the utterance. The interface circuitry communicates the intent of the utterance as an output.

Abstract: A method for receiving and responding to user input is provided. The user input may be input via a user interface. The method may include receiving input from a user via the user interface. The method may also include transmitting the input to a response determination module. The response determination module may determine a system response to the input. The method may include displaying the system response to the user via the user interface. The method may include receiving an indication from the user that the system response is less than a predetermined threshold level of responsiveness. The method may include dividing the input into component terms and displaying the component terms on the user interface. The method may include enabling the user to eliminate component terms from the input in order to improve responsiveness of the system response, and receiving a selection of eliminated component terms.

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: According to certain embodiments, a system comprises interface circuitry and processing circuitry. The processing circuitry receives an input via the interface circuitry. The input is based on an utterance of a user, and the processing circuitry uses a probabilistic engine to determine one or more candidate intents associated with the utterance. The processing circuitry determines a number of the one or more candidate intents that exceed a threshold. If the number of candidate intents that exceed the threshold does not equal one, the processing circuitry uses a deterministic engine to compare the input to a set of regular expression patterns. If the input matches one of the regular expression patterns, the processing circuitry uses the matching regular expression pattern to determine the intent of the utterance. The interface circuitry communicates the intent of the utterance as an output.

Abstract: Apparatus for mapping a user utterance onto a plurality of intents is provided. The apparatus may include an intent training database that includes a plurality of tokens and intents. The apparatus may include a processor. The processor may utilize a token-intent map to generate a token-row map and an intent-column map. The processor may map the plurality of tokens onto a token-intent matrix. The processor may generate a token-cognitive matrix, a cognitive-comprehension matrix and an intent-cognitive matrix from the decomposition. The cognitive-comprehension matrix may be the space of entanglement between the token-cognitive matrix and the intent-cognitive matrix. The processor may reduce the rank of the cognitive-comprehension matrix. The processor may compute a plurality of token vectors from a computation of the token-cognitive matrix and the cognitive-comprehension matrix.

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.