« back to news

CVP Customer Virtual Assistant Lab v1

Date
March 2020

Introduction

Customer virtual Assistant is a feature to provide end customers with Human like interactive interface which is simpler compared to traditional IVR and provides splendid experience. For enterprises, it’s an opportunity to phenomenally improve effectiveness of their traditional IVR based systems with lessor IVR handling time and significant reduction in agent transfers. Along with CVA feature, built-in tools have been developed to make CVP solution much more simple, effective and powerful enough to define business outcome based on Vision, requirements and customer experience.  Developers can explore wide amount of tools been provided as part of Call Studio for customization and flexibility to develop Conversational experience for their end customers.

Overview

Customer Virtual Assistant (CVA) feature enables IVR Platform to integrate with cloud-based speech services and provide transformation in the way customers interact for self-serve system’s today. End customer interactions are more human-like that enable customers to express their issues more effectively with detailed context and AI engine interprets precise intent and processes intended node compared to traversing through multiple nodes in traditional IVR. Due to elaborate context available via speech media and intent identification, the IVR application can handle vast amount of scenario’s and respond back appropriately, thereby reducing the calls directed towards actual agents. The effectiveness and efficacy for CVA based IVR can easily be evaluated using stock report under reporting server. Preliminary results shared by different customers for their CVA based IVR, reflect that “Average traversal time” and agent transfers have reduced significantly compared to their traditional IVR. With improved efficiencies for ATT (Average Traversal Time) & reduced Agent transfers increases effectives for end agents as they can focus on real complex issues rather than generic or medium complexity issues. Customer planning to migrate to CVA based IVR can plan migration in phased manner without fully impacting their traditional IVR business logic. In their business logic of traditional IVR, most widely hit node can be identified and converted to CVA node whereas remaining traditional business logic can operate as such. Or alternatively customer can plan to automate complete business logic on CVA based architecture. For more information on speech interfaces supported by CVA based application are covered in next section.

Speech Services

CVA based IVR leverages cloud-based speech services from release 12.5. While validating, focus has been provided to following speech services to interop with CVP solution in optimized manner. Even though, additional services can be added at any point by Cloud vendors however, its strongly recommended to choose one of more of following recommended services from Cloud for production deployments. For complete CVA experience, IVR application leverages all of these services for processing each incoming customer call. Speech services leveraged by CVA are as:

  • Speech to Text: Integration with cloud-based ASR services with your application for Speech Recognition operations. CVA currently supports Google Speech to Text service.
  • Speech to Intent: CVA provides capability of identifying the intent of customer utterances by processing the text received from Speech to Text operations. This cloud-based service is also known generically as Natural Language Understanding (NLU) or Google DialogFlow service.
  • Text to Speech: Integration with cloud-based TTS services in your application for Speech Synthesis operations. This Cloud based service is also known as Google Text to Speech service.

For overall great conversational experience, it is highly recommended to leverage all above services and for customers planning to migrate in phased manner can always leverage above services based on business requirement like “Text to Speech” service alone to be leveraged.

Resources