Gartner predicts that “by 2022, 70 percent of white-collar workers will interact with conversational platforms on a daily basis.” As a result, the research group found that more organizations are investing in chatbot development and deployment.

IBM Business Partners like Sopra Steria are making chatbot and virtual assistant technology available to businesses. Sopra Steria, a European leader in digital transformation, has developed an intelligent virtual assistant for organizations across several industries who want to use an AI conversational interface to answer recurrent customer service questions.

Choosing IBM AI technology

In developing our solution, we at Sopra Steria were looking for AI technology that was easy to configure and could support multiple languages and complex dialogs. We created a training set of 2,000 sentences such as “I would like to buy a car,” or “I would like to have a coffee,” and tested 15 different AI solutions. Of all the solutions, we found that IBM AI technologies were the most accurate and could best meet our requirements. We are now using IBM watsonx Assistant, IBM Watson Language Translator, IBM Watson Natural Language Understanding and IBM Watson Text to Speech as the AI foundation for our intelligent virtual assistant accelerator.

We have developed an orchestrator and a front-end interface to manage dialogs and connectivity to external systems and functionalities, such as support for multiple languages. Our solution enables a faster deployment of customer chatbots than any other on the market because of our enhancements.

Sopra Steria developers use Red Hat OpenShift sandbox environments to experiment with new concepts and build applications for the company’s employees. It also uses the Red Hat OpenShift environment to support intelligent virtual assistants and operate other managed services for its customers.

Our intelligent virtual assistant solution is located primarily on the cloud, but it can also be located on site at a client’s location if that is what the client needs. Locating the solution on premises allows us to be able to connect the dialogs easily with internal systems like billing and HR information systems.

Accelerating deployment of the intelligent virtual assistant

The Sopra Steria intelligent virtual assistant accelerator engine enables our solution to be deployed rapidly. There’s an intuitive graphical user interface, so our clients can begin creating dialogs for their chatbots and using it in customer service scenarios almost immediately.

Currently the intelligent virtual assistant is live in 10 sites throughout Europe. In its most mature instance, the solution is processing 80 percent of customer queries. In the first month alone, the solution processed 75,000 conversations. The solution has scaled from 450,000 users to more than one million and a half, with the expectation of supporting three million within the coming year.

Based on 700 user evaluations of the quality of service provided by the intelligent virtual assistant at our most mature client, more than 64 percent of users felt that the treatment had been satisfactory. This is a much higher satisfaction rate than the support provided by another solution that we had implemented in the past, but that did not use watsonx Assistant.

The Sopra Steria solution enables our clients to be available for their customers day and night, while reducing operating costs. It also frees customer service representatives to focus on more complex and high-value customer issues.

Read the case study for more details.