PATENT TITLE / NAME

Method and Apparatus for Intent Recognition and Intent Prediction Based on User Interaction and Behavior

WHAT DOES THIS MEAN FOR OUR CLIENTS

In summary, this patent outlines an AI-powered system for improving customer experience in contact centers by predicting user intent and automating next steps, which significantly enhances efficiency and personalization.

ASSOCIATED SWAMPFOX PRODUCT(S)

• Swampfox Intelligent Virtual Assistant™ (IVA): Uses AI powered intent recognition and prediction capabilities to identify customer needs and predict future actions

• Swampfox Intelligent Customer Experience (ICX): Uses these AI features to extract customer intents across various interaction channels (voice, text, chat, etc.) to orchestrate the next best action for the customer, agent assisted or self service.

• Swampfox Intelligent Greeting: Uses Predictive Intent/Actionable Insights to predict customer needs based on previous interactions, CRM integrations and various customer attributes enabling personalized greetings and immediate service suggestions.

SUMMARY

Conventional interactive systems can suffer from a variety of deficiencies. For example, conventional interactive systems such as speech recognition-based systems (e.g., IVR and speech recognition or Intelligent Voice Automation (IVA) systems) allow for the identification of the characteristics of a user’s speech. However, these systems fail to consider the entire context of the incoming user speech, and, as such, do not identify the user’s intent.

By contrast to conventional interactive systems, embodiments of the present innovation relate to a method and apparatus for intent recognition and intent prediction based upon user interaction. Identification of a user’s intent can allow the enterprise to predict the customer’s needs and to tailor future actions and services to these needs. In one arrangement, to improve on the accuracy of determining a user’s intent, a contact center apparatus is configured to identify the intent associated with a user’s interaction data, which can include speech utterances, grammar, past behavior, demographic data, public record data, and/or social media history, for example.

Further, the contact center apparatus can include an AI-driven intent prediction engine which, based on the user’s interaction data (e.g., status, state, location, social platform data, CRM, etc.), can dynamically forecast or predict a next best action that can be provided to the user to enhance the user’s customer experience. For example, the next best action can include the automated rebooking of a flight because the user’s flight status, the automatic handling of a bill payment or payment arrangement if a bill is overdue, or the automatic release of a discount to proactively address a user experience issue.

Further, the next best action can address a user issue prior to the user attempting to contact the enterprise (e.g., company/brand). As such, the contact center apparatus can raise the user experience beyond that achieved with traditional interactive systems. This process can be used for, and is not limited to, reporting as well as subsequent training (e.g., reinforcement) of the model for systems, such as natural language understanding systems. In addition, the embodiment based on the extraction of the intent is able to predict the next best action that can provide a user with the best and most efficient experience with an enterprise.

In one arrangement, embodiments of the innovation relate to, in a contact center apparatus, a method for recognizing user intent associated with user interaction with the contact center apparatus. The method includes receiving user interaction data; performing a feature extraction process on the user interaction data to generate feature data; performing an intent extraction operation on the feature data to extract topics included with the feature data; executing a classification engine on the topics extracted from the feature data to classify a user intent associated with the user interaction data; and directing the user to a corresponding working agent based upon the classified user intent.

In one arrangement, embodiments of the innovation relate to, in a contact center apparatus, a method for predicting user intent associated with user interaction with the contact center apparatus. The method includes receiving user interaction data; transforming the user interaction data into a prediction vector; providing the prediction vector and a prediction model to a framework; and receiving an intent prediction and a confidence score from the framework based upon the prediction vector and the prediction model.

To read more detail about the newly patented approach for Intent Recognition and Intent Prediction Based on User Interaction and Behavior, please follow the link below to read the associated patent.

LINK TO PATENT