Systems and methods for intent prediction and usage

A system comprising at least one computer including a processor, wherein the at least one computer is configured to:

• receive a voice-based contact;
• convert the voice-based contact into a text string using a speech-to-text engine;
• tokenize the text string into utterance tokens based on white space, special characters, and one or more of known phrases and parts of speech;
• vectorize the utterance tokens into feature vectors;
• provide the utterance tokens and feature vectors to a machine learning model as an input layer to the machine learning model, wherein the machine learning model is a convolutional neural network (“CNN”) comprising the input layer, a hidden layer, and an output layer with a size of number of intents to classify;
• receive, as output from the machine learning model, a predicted intent;
• format a query of a content repository, wherein the query includes the predicted intent;
• receive, based on the query, an artifact from the content repository, wherein the artifact is indexed in the content repository by the predicted intent;
• and
• displaying the artifact via an interface to a support agent.

A non-transitory computer readable storage medium, including instructions stored thereon, which instructions, when read and executed by one or more computer processors, cause the one or more computer processors to perform steps comprising:

• receiving a voice-based contact;
• converting the voice-based contact into a text string using a speech-to-text engine;
• tokenizing the text string into utterance tokens based on white space, special characters, and one or more of known phrases and parts of speech;
• vectorizing the utterance tokens into feature vectors;
• providing the utterance tokens and feature vectors to a machine learning model as an input layer to the machine learning model, wherein the machine learning model is a convolutional neural network (“CNN”) comprising the input layer, a hidden layer, and an output layer with a size of number of intents to classify;
• receiving, as output from the machine learning model, a predicted intent;
• formatting a query of a content repository, wherein the query includes the predicted intent;
• receiving, based on the query, an artifact from the content repository, wherein the artifact is indexed in the content repository by the predicted intent;
• and
• displaying the artifact via an interface to a support agent.