Callbot, NLP, Conversational AI... How to decode artificial intelligence?

Far from being a mere trend, the arrival of artificial intelligence is a veritable revolution in customer relations. It now represents an opportunity for companies to considerably improve the service they offer to users and consumers, by establishing a responsive, seamless customer journey.

To help you better understand the jargon used, we're going to take a look at some of the most frequently used terms that raise a lot of questions.

Artificial Intelligence for an omnichannel journey

For many years now, the telephone has been the most frequently used channel for customers and users expecting an immediate response from companies and organizations. Unfortunately, saturated lines and long waiting times can be particularly irritating, often leading to frustration and deep dissatisfaction.

Thanks to the technologies we've developed, our solutions eliminate repetitive tasks for advisors, leaving them to concentrate on high value-added tasks.

Artificial Intelligence or AI

It's a branch of computer science dedicated to the design of machines capable of performing tasks such as learning or reasoning in the manner of a human brain. The aim is for a machine to imitate the cognitive abilities of a human being. Technically, artificial intelligence is a way of programming that is the complete opposite of traditional development. Instead of starting from the rules and working towards the data, we start from the data and work towards the rules. Artificial intelligence algorithms are capable of conceptualizing rules from data.

AI teaches machines to learn, to recognize their environment and to achieve goals.

It's no longer a matter of coding rules manually, but of letting computers discover them by correlation and classification on the basis of massive amounts of data. In other words, the aim of machine learning is not really to acquire knowledge that has already been formalized, but to understand the structure of data and integrate it into models, notably to automate tasks.

Artificial intelligence is based on Machine Learning and Deep Learning algorithms.

Machine Learning

In the past, rules were programmed to mimic human intelligence, and developers tried to teach computers the minutest details of every decision they had to make.

For example, for a machine to be able to recognize a bird, we would construct recognition rules such as it's an animal with two legs, wings, feathers and flies. Conversely, using artificial intelligence and Machine Learning algorithms, the machine will be provided with a huge quantity of bird images, specifying that each image represents a bird - this is what we call training the algorithm. The computer then analyzes these images to determine their common characteristics, acquiring the ability to recognize a bird by analyzing a new image.

Machine Learning is a set of statistical learning algorithms programmed to search for relationships between data.

Deep learning

Deep Learning is a subset of Machine Learning. It is the result of a combination of the appropriation of knowledge about neural networks and the increasing computing power of computers, which has become available at lower cost. The machine still learns from data, but it is inspired by the workings of the neurons and synapses of the human brain, calling on several layers of processing, each progressively integrating increasingly complex representations of data. Deep learning is revolutionizing visual recognition and natural language processing, for example.

Artificial intelligence has revolutionized the human-machine relationship by taking on skills previously reserved for humans: understanding and using natural language, translation, speech recognition, and so on.

Hybrid advisor or augmented advisor

It's the bot's ability to handle part of the call and switch it to a physical advisor if necessary. But it can also provide the advisor with answers as the conversation progresses, thanks to data analysis. As a result, customer relations become more efficient and relevant.

Enhanced supervisor

This is a technology based on artificial intelligence, enabling real-time supervision of all conversations managed by the conversational agent. The augmented supervisor consists of an automatic, qualitative measurement of conversations.

This value-generating solution enables supervisors either to identify risky conversations and take them over or transfer them, or to capitalize on best practices.

Conversational Artificial Intelligence

Artificial intelligence now makes it possible to set up a speech recognition system and, more generally, words associated with conversational bots to improve the customer experience.

Whether with an advisor or a bot, users want to talk to their customer service as they do on a daily basis, i.e. in "natural" language, not machine or robot language.

To function and establish a fluid dialogue, technologies rely on a natural language processing system. It's time to learn more about how it works.

NLP

NLP, or "Natural Language Processing", is a set of text recognition solutions for understanding words and phrases formulated by users. The aim is to understand a need and respond to it.

In concrete terms, NLP makes it possible to understand what a human being is saying, to process the data contained in the message and to respond in natural language.

NLU

Natural Language Understanding (NLU) involves taking a written or spoken text in natural language and understanding its intentions. It is therefore a subset of NLP.

NLP literally interprets what the customer says or writes, while NLU identifies intentions and deeper meaning.

Paralinguistic Artificial Intelligence

Paralinguistic AI consists in using AI to detect characteristics of a person other than the verbal content spoken: age, gender, tone or even the emotions of a written or spoken conversation.

Emotional AI

Emotional AI is one aspect of paralinguistic AI, but surely one of the most complex and exciting.

It is defined by the ability to detect an emotional state (anger, stress, joy, annoyance...) and to reason by taking these emotions into account.

As robots are not human, they are not naturally endowed with empathy. Emotional AI makes up for this by introducing emotion management into human-machine conversations, so as to respond more appropriately to the customer's needs, taking into account his or her state of mind. In concrete terms, if a customer is angry or in a situation of intense stress, the bot will instantly direct them to a human. Similarly, in writing, using the verbatims and words used by the customer, the bot can deduce an emotional state and provide a contextualized response.

What is a bot? And what's it for?

It's the new buzzword. Every brand wants its bot. Are these automated conversation programs the future of customer relations?

The term "bot" means "robot", which is originally computer software that performs automated tasks to help humans with a specific process.

There are several types of bots:

Conversational Agent

It's a bot with Artificial Intelligence, capable of conversing with a human in natural language via a voice or text channel.

Callbot - Voice robot

The callbot is a conversational voice agent. It answers the phone when consumers call customer service.

As soon as the call is received, the Welcomebot greets, identifies and understands the customer's request, expressed in natural language. If the request can be "automated", the Processingbot takes over its entire processing. If not, the call is transferred to the appropriate advisor.

If the advisors are unavailable, the Overflowbot overflows the calls, which are then transcribed in a structured email to the advisor for asynchronous processing.

Setting up a Callbot is ideal for managing large call flows and reducing customer waiting time on the phone.

This will relieve the pressure on call center phone lines, and enable us to offer available, responsive after-sales service.

Chatbot

It's a conversational agent that, unlike the Callbot, interacts in writing via a website.

There are two types of chatbots: the first is an interface that serves as a complementary communication channel between a customer and a human advisor. The second is a real bot, programmed to respond to requests from users who simply type their queries on their keyboard and "chat" with the bot in a dedicated window. In this case, NLP enables the bot to analyze semantics in order to provide appropriate responses to customer queries.

Messagingbot

It's a conversational agent that also interacts in writing, but on instant messaging applications like Whatsapp or Messenger.

This channel, unlike the first two, gives the user the choice of being instantaneous or asynchronous. They can choose to carry on a live conversation from start to finish, or come back to it later to see the answer given, thanks to the conversation history.

The Messagingbot also induces less formal conversations, for example through the integration of smileys or predefined customer journeys incorporating more empathy. Brands therefore have a strong interest in using this technology to optimize their customer experience, especially in today's ultra-connected world.

The more a brand offers its customers different but interconnected communication channels, the more omnichannel and seamless their experience becomes, which obviously increases their satisfaction and loyalty.