Alive Intelligence

Conversational Assistants: go to scale

by Patrick Meyer - Artificial Intelligence Senior Architect & Technical Director, Sopra Steria | minutes read

74% of French companies consider chatbots as a lever for digital transformation and more than a third have already deployed one. By 2020, 80% of them could use a chat assistant. A massive deployment that echoes consumer habits: 69% prefer the bot to a human exchange. The main perceived advantage: saving time. This is a significant advantage in the face of the demand for real time imposed by markets that are increasingly under pressure. To meet this expectation, companies need to accelerate the automation of their business processes. But beware of the pitfalls when going to scale.

64% of companies in France make automation a priority. Similarly, 74% of entities familiar with Robotic Process Automation (RPA) have even already started a reflection or an integration project. Applied to IT, financial or HR departments, RPA would thus make it possible to reproduce manual processing on increasingly large volumes of data. However, these figures need to be put into perspective, as nearly one company in three (29%) still has less than 50% of its processes automated.


Business Automation - NLP: the genesis of the virtual agent

While the technology is not a recent concept, it is now mature enough to foster a high level of understanding of user needs. How can this be achieved? Thanks to Natural Language Processing (NLP). This makes it possible to interact with the machine and to create a new technology: the conversational assistant. At the key: the ability to run RPA scripts and to automate a growing number of questions, like ClaudIA, the virtual assistant for Chorus Pro users by the AIFE (Agence pour l'Informatique Financière de l'Etat). 

Launched in 2017, the chatbot covered all the topics encountered by users the following year, and proved capable of handling two-thirds of the requests. Target for 2020: to reach 90%. It seems a long time ago that the Swedish online bank Nordnet had symbolically "fired" its bot, Amelia, for incompetence... or more precisely its inability to meet customer expectations. The fault lies in a lack of learning. As a result, the bot quickly proved unable to answer the questions it was asked.

How to create the best conversational assistant?

This is where the complexity of a conversational assistant lies: poorly designed or insufficiently "educated" beforehand, it can quickly turn out to be counterproductive. This is why it is essential to model the dialogue, to anticipate the different questions and to teach it how to answer them.

In this sense, most solutions on the market are based on the concept of the decision tree. Thanks to the learning machine, the system detects the user's intention, the class, identifies the "entities" (i.e. the important words contained in the sentences) and generalises the answer to be given, either directly or by asking other questions aimed at obtaining more details. It is on this approach that the dialogue is built.

From then on, five types of wizards appear: e-commerce bots, support bots, information bots, form bots and search bots. What are the elements to be taken into account to create your virtual assistant? First step: find out what the most frequently asked questions are - via FAQs, support tickets for example. Once sorted and categorized, you need to automate 20% of them (20% of the questions covering on average 80% of the total volume of requests).

Then, it is necessary to model the answers: do I need additional information or can I answer directly? Does the sentence already correspond to a detected intention or is this a new area? Finally, is this question punctual or out of context? Whatever the request, it is important to follow a guiding principle: provide a short answer.


From experimentation to scaling up

Once these first two steps have been completed, you are ready to scale up. Nevertheless, be sure to anchor your system in a process of continuous improvement. Indeed, the system cannot live on its own and must constantly be optimized in order to enrich the dialogue and provide increasingly precise answers. The three golden rules of your conversational assistant?  Define a persona, name your bot and indicate its scope of intervention as soon as you connect.

A global vision that allows us to respond to the increasingly high challenges of proximity and customization that companies are facing, especially in times of crisis. In the years to come, virtual assistants will become the preferred companion of consumers. A "virtual clone" capable of knowing precisely the user's profile and context.

Technology alone cannot solve the adoption of virtual assistants. It is through use that they will spread and become indispensable. This is why companies must set up bots capable of communicating with all domains and industrialize the experience acquired. They must then decide upstream of their project to separate each system or to deploy a master bot that will act as a router capable, depending on the issue, of directing the user to the business robot concerned. This is a critical point that you must anticipate when scaling up in view of the diversity and volume of questions envisaged, and which will determine the success of your project... or its failure.

Discover our offer Sopra Steria Alive Intelligence

More on this topic
Alive Intelligence

Conversational Assistants: go to scale

| Patrick Meyer

74% of French companies consider chatbots as a lever for digital transformation and more than a third have already deployed one. By 2020, 80% of them could use a chat assistant. A massive deployment that echoes consumer habits: 69% prefer the bot to a human exchange.

Discovery Assessment

How can you use your IT assets to achieve digital transformation?

| Andre Bakland, Simon Herd, Béatrice Rollet

According to Gartner, for every dollar invested in digitalisation in 2020, three dollars will have to be invested in the modernisation of IT assets. Therefore, opting for the right evolution strategy becomes a crucial issue. Read more.

Data et Covid-19

How Data Science can help in a pandemic situation?

| Marlon Cárdenas

With the aim of covering current and future needs of society, Data Science and Artificial Intelligence are seeking to drive the creation of technological solutions that benefit users in their daily lives. Many disciplines are uniting behind this cause, with health sciences to the fore, especially given the current context of the battle against the Covid-19 pandemic.


How holographic technology is helping doctors deliver better care

| Scott Leaman

Long gone are the days when holograms were the stuff of sci-fi movies and video games. Holographic technology is taking the medical world by storm, and by the looks of it, it’s here to stay. So how exactly is this technology helping doctors, and what are the major developments that we expect in the near future?

IA transforms Industry

How will artificial intelligence transform industry?

| Maxime Claisse, Alexis Girin, Benoit Spolidor

Whilst there is no set definition of artificial intelligence as of yet, experts are in agreement that AI can simulate human cognitive capabilities such as perception, reasoning, action, and learning. AI now promises to completely transform the industrial sector – one of its primary applications.


International Paris Air Show: 5 trends to transform aeronautic

| Youssoupha Diop

The 53rd International Paris Air Show 2019 has confirmed the mounting fierce competition in the world of aeronautics. In this context, data, digital tools and artificial intelligence are now understood to be precious bargaining chips to accelerate transformation and turn these challenges into opportunities.


Anticipate cloud migration with FinOps

| Marlène Seif, Béatrice Rollet

Innovative and fast cloud services are crucial to digital transformation initiatives. Whilst there is no textbook model on how to adopt these services, it is nonetheless vital for companies to integrate them as fully optimised services in order to control their ROI.


From product to services: Flying the Aeronautics Industry into the Digital Future

| Philippe Armandon, Gaudérique Garrigue

With increasing travel demand and new competitors entering the market, aircraft manufacturers today are under considerable pressure.


How to control and optimise your cloud costs

| Didier Teixeira, Béatrice Rollet, Frédéric Janicot

Using public cloud services means rethinking your IT financial management. 


ASD S5000F: taking Aircraft MRO to new heights?

| Cyrille Greffe

In the 1990s, the combination of computer-aided design (CAD) and the concept of modular documentation gave rise to the first ASD standards (AeroSpace and Defence Industries Association of Europe).


Application replatforming: the Cloud migration booster

| Benjamin Chossat

Simple set-up, low cost and access to the horizontal elasticity of the Cloud: replatforming is often considered the best solution for porting a business application to the Cloud.


7 key strategies to transform applications with the Cloud

| Benjamin Chossat

How to modernise an application efficiently using the Cloud?

Innovating in pursuit of environmental sustainability

Innovating in pursuit of environmental sustainability

| Siva Niranjan

To attract new business, talent and investment, companies have had to demonstrate their environmental credentials more and more over the past years to wide range of stakeholders including institutional investors, regulators, clients, and employees.

Urban Air Mobility: is the future of mobility be in the air?

Urban Air Mobility: will the future of mobility be in the air?

| David Elmalem, Sébastien Lautier

While the dream of the flying car has often been reserved for science fiction, a very practical and real future is gradually emerging for urban air mobility.

Guidance is the key for adapting DevOps to big business

Guidance is the key for adapting DevOps to big business

| Gauthier Deschamps

DevOps is revolutionising agile transformation for big business. The method was initially focussed on software building but by automating production, it frees up resources so as to better resolve organisational and human malfunctions.


How Blockchain technology can improve Industry 4.0’s cybersecurity

| Alexandre Eich Gozzi

Earlier this year, the world’s largest container shipping company Maersk fell victim to a massive ransomware attack from the infamous NotPetya malware.