Abstract: An on-premises system for pre-processing data for forecasting according to an embodiment includes at least one processor and at least one memory having a plurality of instructions stored thereon that, in response to execution by the at least one processor, causes the on-premises system to receive a request to forecast contact center data using a cloud system, determine a first number of interactions per unit of time for a source interval, determine a second number of units of time in a destination interval, and determine a third number of interactions in the destination interval based on the first number of interactions per unit of time for the source interval and the second number of units of time in the destination interval.

Abstract: A system and method of training a machine-learning (ML) based model by at least one processor may include receiving an initial dataset, including a plurality of annotated data samples; based on the initial dataset, training at least one ML-based first-level model to perform a first-level task; based on training the at least one ML-based first-level model, calculating at least one characteristic, representing, for each data sample, a value of contribution into a training of a ML-based second-level model to perform a second-level task; omitting a subset of data samples from the initial dataset based on the at least one characteristic, to obtain a target dataset; and training ML-based second-level model, to perform the second-level task, based on the target dataset.

Abstract: A method for providing streaming audio over a network from a client to a server associated with a third-party service. The method includes receiving configuration data from a tenant regarding the server. The method may further include establishing a connection with the server via a connection process. The connection process includes sending a connection request that includes: a bidirectional communication protocol configured to transmit data from the client to the server and from the server to the client by reusing an established connection channel; a tenant-Id parameter; and a session-Id parameter. The method may further include implementing an open transaction for initiating the streaming of the audio of the ongoing conversation to the server. The open transaction includes transmitting participant parameters identifying the customer and at least one choice regarding an audio format for the audio streaming.

Abstract: A system for utilizing conversational artificial intelligence (AI) to train contact center agents according to an embodiment includes at least one processor and at least one memory comprising a plurality of instructions stored therein that, in response to execution by the at least one processor, causes the system to place a virtual call from an automated training system to an agent device of an agent, connect the virtual call to a chatbot in response to establishing a communication connection with the agent device, transmit one or more statements from the chatbot, receive, from the agent device, one or more agent responses of the agent corresponding to the one or more statements, and analyze the one or more agent responses to determine one or more training characteristics associated with AI-based contact center training of the agent.

Abstract: A method of dynamic prioritization of collaboration between human and virtual agents according to an embodiment includes generating a priority score for a conversation between a human user and a chat bot, wherein the priority score is based on at least a sentiment of the human user and a temporal aspect of the conversation, providing the priority score to a human agent via an interface for monitoring the priority score, transferring control of the conversation from the chat bot to the human agent based on an interaction of the human agent with the interface, and yielding control of the conversation from the human agent back to the chat bot in response to another interaction of the human agent with the interface.

Abstract: A method for facilitating an interaction with a contact center for a customer relating to a problem with a target object. The method includes receiving images of the target object from the customer and processing the images by: identifying a base object corresponding to the target object; retrieving a base object model, product identification information, and customer service information associated with the base object; analyzing the images by comparing the images of the target object to the base object model to detect changes; based on the detected changes, determining a problem statement related to the interaction; and based on the customer service information and the problem statement, selecting an applicable contact center as the contact center for the interaction. The method includes transmitting a communication that include the problem statement to the contact center to initiate the interaction.

Abstract: A system and method are presented for improvement profile generation in a skills management platform, using past data and a set of KPIs. Variance calculation is performed with a basic variance formula and these values are used to generate a strand. A strand may be defined as a collection of KPIs, each weighted to show the importance of that KPI for that agent type. KPIs can be selected to generate a strand with, and the strand is generated from those KPIs considering the normalized variance of each KPI. An agent's improvement possibilities may also be determined using the generated strand.

Abstract: A method for mining topics discussed in conversations that includes: receiving conversation data; and using a topic mining algorithm to mine topics from the conversation data. The topic mining algorithm includes identifying candidate topics in each of the conversations. The topic mining algorithm further includes identifying the topics of the conversations by: compiling a list of the candidate topics; pruning the list of candidate topics by discarding certain of the candidate topics per a cross-conversation factor that factors usage across all conversations; and identifying the candidate topics remaining on the pruned list of candidate topics as the topics. The topic mining algorithm further includes determining topic groups by grouping the topics according to a degree of semantic similarity between the topics; and associating a list of utterances with the topic groups.

Abstract: A method for deriving a model for a chatbot for predicting entities in a sentence. The sentence is input into a named-entity recognition module and features obtained. A LSTM RNN forward pass and backward pass is performed on the features to obtain a first and second set of results, respectively. A first concatenating is performed on the first set of results and the second set of results. A second concatenation is performed on the first concatenation using output target entities. A connected set of neurons from the second concatenation is obtained. An output is obtained, and a prediction is collected on a next output by summing the outputs previous to that output. The prediction is input into the performing of the second concatenation step, wherein the method is performed cyclically until all outputs have been processed with input predictions.

Abstract: A method of routing interactions to contact center agents according to an embodiment includes identifying an interaction to be routed to a contact center agent, identifying a group of contact center agents as candidates for routing of the interaction, retrieving agent performance data for each candidate agent of the group of contact center agents identified as candidates for routing of the interaction, determining a predicted score for a key performance indicator for each candidate agent based on the agent performance data, determining an occupancy rate of each candidate agent based on the agent performance data, generating a ranking of the candidate agents for routing prioritization based on the predicted score for the key performance indicator for each candidate agent and the occupancy rate of each candidate agent, and signaling a routing device to route the interaction to a selected candidate agent based on the ranking of the candidate agents.

Abstract: A method for incorporating an augmented voice communication into a communication routing configuration of a contact center system according to an embodiment includes selecting a vocal avatar, wherein the vocal avatar includes phonetic characteristics having first values, receiving a text communication and input user parameters from an input user, generating the augmented voice communication based on the text communication and the input user parameters, wherein the augmented voice communication includes phonetic characteristics having second values, wherein the first values of the phonetic characteristics of the vocal avatar are different from the second values of the phonetic characteristics of the augmented voice communication, and incorporating the augmented voice communication into the communication routing configuration of the contact center system.

Abstract: A method according to one embodiment includes transmitting, by an enterprise system, a data request for user data stored in a software wallet to a software wallet provider, transmitting, by the software wallet provider, an authorization request to an end user device of the user in association with the data request, creating, by the end user device, a transaction signed with a first private cryptographic key to generate a signed transaction, transmitting, by the end user device, the signed transaction to the software wallet provider, signing, by the software wallet provider, the signed transaction with a second private cryptographic key to generate a multi-signed transaction, transmitting, by the software wallet provider, the multi-signed transaction to the enterprise system, and validating, by the enterprise system, the multi-signed transaction using a public cryptographic key associated with the first private cryptographic key and the second private cryptographic key.

Abstract: A system for performing contact center agent scheduling according to an embodiment includes at least one processor and at least one memory comprising a plurality of instructions stored thereon that, in response to execution by the at least one processor, causes the system to generate a workload forecast indicative of a demand that will be introduced into the contact center in a future planning period based on a workload forecast model and time series data, generate a staffing requirement forecast indicative of a number of agents required to handle the workload forecast based on the workload forecast, one or more service goals, and a staffing requirement model, and perform schedule optimization using column generation to generate an optimized contact center agent shift schedule for a plurality of agents based on the staffing requirement forecast and one or more constraints.

Abstract: A system for estimating a wait time to connect a customer to an agent according to an embodiment includes at least one processor and at least one memory comprising a plurality of instructions stored thereon that, in response to execution by the at least one processor, causes the system to receive incoming interaction data from the customer indicative of a request to estimate the wait time, retrieve historical data indicative of interaction information for one or more interactions that have already been serviced in response to receipt of the request, and generate a wait time estimation based on the historical data.

Abstract: An on-premises system for pre-processing data for forecasting according to an embodiment includes at least one processor and at least one memory having a plurality of instructions stored thereon that, in response to execution by the at least one processor, causes the on-premises system to receive a request to forecast contact center data using a cloud system, determine a first number of interactions per unit of time for a source interval, determine a second number of units of time in a destination interval, and determine a third number of interactions in the destination interval based on the first number of interactions per unit of time for the source interval and the second number of units of time in the destination interval.

Abstract: A method for creating a student model from a teacher model for knowledge distillation. The method including: providing a first model; using a first instance of the first model to create the teacher model by training the first instance of the first model on a training dataset; using a second instance of the first model to create the student model by training the second instance of the first model on a subset of the training dataset; identifying corresponding layers in the teacher model and the student model; for each of the corresponding layers, computing a weight similarity criterion; ranking the corresponding layers according to the weight similarity criterion; selecting, based on the ranking, one or more of the corresponding layers for designation as one or more discard layers; removing from the student model the one or more discard layers.

Abstract: A method for creating a student model from a teacher model for knowledge distillation. The method may include: providing the teacher model trained on a first training dataset; generating candidate student models, wherein each of the candidate student models is a model having a unique permutation of layers derived by randomly selecting one or more layers of the plurality of layers of the teacher model for removing; generating a second training dataset; for each of the candidate student models: providing the second training dataset as inputs; recording outputs generated; and based on the recorded outputs, evaluating a performance according to a predetermined model evaluation criterion; determining which of the candidate student models performed best among the candidate student models based on the predetermined model evaluation criterion; identifying a preferred candidate student model.

Abstract: A method facilitating a cross-channel interaction between a customer and a contact center. The method includes: receiving and conducting a first interaction with the customer; determining a first identifier related to the first interaction; storing, in a database, the first identifier and associating the first identifier with the first interaction; receiving a second interaction from the customer; determining a second identifier related to the second interaction; using the second identifier to check the database to determine if the second interaction is associated with the first interaction; determining, based on the check of the database, that the second interaction is contextually related with the first interaction; and modifying, in response to determining that the second interaction is contextually related to the first interaction, at least one way in which the second interaction is handled by the contact center.

Abstract: A method for managing a queue in a contact center that includes: receiving a previous call from a first customer and determining a unique identifier; tracking a previous queue time; detecting the previous call ending without being connected to an agent; determining the previous wait time accrued; saving in a database a previous call record that includes the previous queue time and the unique identifier; receiving a present call from the first customer and determining a unique identifier; tracking a present queue time; using the unique identifier to check the database to determine the related previous call record; determining the previous queue time; calculating an adjusted total queue time that is the present queue time plus previous queue time; and positioning the first customer in the queue based on the adjusted total queue time.

Abstract: A system and method of automatically discovering unigrams in a speech data element may include receiving a language model that includes a plurality of n-grams, where each n-gram includes one or more unigrams; applying an acoustic machine-learning (ML) model on one or more speech data elements to obtain a character distribution function; applying a greedy decoder on the character distribution function, to predict an initial corpus of unigrams; filtering out one or more unigrams of the initial corpus to obtain a corpus of candidate unigrams, where the candidate unigrams are not included in the language model; analyzing the one or more first speech data elements, to extract at least one n-gram that comprises a candidate unigram; and updating the language model to include the extracted at least one n-gram.