A sequence of call volume measurements is accessed, where each of the call volume measurements is associated with respective metadata. The respective metadata may provide information regarding a time period during which a call volume measurement was made. A window of the sequence of call volume measurements with the respective metadata is input to a machine learning model to obtain a prediction of a call volume. The machine learning model includes embedding functions that are applied to the respective metadata for the call volume measurements in the window.

In a predictor device, a method for predicting a metric of a contact center includes receiving contact center operational data associated with a time duration; training a set of algorithms and their available hyperparameters with the contact center operational data to generate a set of data models; generating a score associated with each data model of the set of data models, the score quantifying a performance of each algorithm and its available hyperparameters on the contact center operational data; identifying the data model having the largest score as a best learning model for the time duration; and generating a contact center metric prediction based on the best learning model for the time duration.

A system and apparatus are provided for generating synthetic telephony narrowband data for training an automatic speech recognition model by receiving a broadband audio data file and then initiating a telephony call using a pre-configured telephone provider to play the broadband audio data file in the telephony call and to record and store audio data generated by transmission of the broadband audio data file in the telephony call, thereby generating the synthetic telephony narrowband data file from the broadband audio data file.

A method for generating synthetic telephony narrowband data for training an automatic speech recognition model by receiving a broadband audio data file and then initiating a telephony call using a pre-configured telephone provider to play the broadband audio data file in the telephony call and to record and store audio data generated by transmission of the broadband audio data file in the telephony call, thereby generating the synthetic telephony narrowband data file from the broadband audio data file.

A system and apparatus are provided for generating synthetic telephony narrowband data for training an automatic speech recognition model by receiving a broadband audio data file and then initiating a telephony call using a pre-configured telephone provider to play the broadband audio data file in the telephony call and to record and store audio data generated by transmission of the broadband audio data file in the telephony call, thereby generating the synthetic telephony narrowband data file from the broadband audio data file.

A method for generating synthetic telephony narrowband data for training an automatic speech recognition model by receiving a broadband audio data file and then initiating a telephony call using a pre-configured telephone provider to play the broadband audio data file in the telephony call and to record and store audio data generated by transmission of the broadband audio data file in the telephony call, thereby generating the synthetic telephony narrowband data file from the broadband audio data file.

In a predictor device, a method for predicting a metric of a contact center includes receiving contact center operational data associated with a time duration; training a set of algorithms and their available hyperparameters with the contact center operational data to generate a set of data models; generating a score associated with each data model of the set of data models, the score quantifying a performance of each algorithm and its available hyperparameters on the contact center operational data; identifying the data model having the largest score as a best learning model for the time duration; and generating a contact center metric prediction based on the best learning model for the time duration.

A sequence of call volume measurements is accessed, where each of the call volume measurements is associated with respective metadata. The respective metadata may provide information regarding a time period during which a call volume measurement was made. A window of the sequence of call volume measurements with the respective metadata is input to a machine learning model to obtain a prediction of a call volume. The machine learning model includes embedding functions that are applied to the respective metadata for the call volume measurements in the window.

A method for generating a customer bot and using the customer bot to train agents, where a first process generates the customer bot and a second process uses the customer bot to train the agents. The first process includes: gathering conversation data; mining intents from the conversation data; constructing, from the mined intents, a dialog engine simulating an interaction type; uploading the customer bot to an automated training module for use thereby; and periodically repeating the previous steps so to update the customer bot with recent conversation data. The second process includes: monitoring for triggering events; initiating the training by initiating a virtual communication to a user device of a first agent; connecting the virtual communication to the customer bot; conducting a simulated interaction; and analyzing one or more statements received from the first agent to derive a performance assessment.

A machine learning model (e.g., including a deep learning neural network) with learned embeddings is applied to time series data with associated metadata to obtain predictions of the time series value. For example, a call volume in a period of time may be predicted based on call volume data for a sequence of time bins in a window of preceding time. Time bins may be associated with respective metadata, such as day of week, hour of day, day of month, holiday, part of business cycle, weather, and/or tide. These pieces of metadata may be mapped to embedding vectors using trained embedding functions. The resulting embedding vectors may be input to a neural network along with the corresponding time series data (e.g., call volumes) to make a prediction for future time bin. For example, the prediction may be used to provision servers in a network infrastructure.