The Conversational Agent for Your Marketing Campaigns
With Olivo, Koïos Intelligence intends to revolutionize the marketing industry, but many consumers still don’t fully understand the application.
Published April 10 2022
Since Clippit – the paperclip found in Microsoft Word at the turn of the 1990s – virtual assistant technology has taken giant leaps forward.
Koïos Intelligence is a startup company developing a new generation of intelligent chatbots. Thanks to their research, Koios’ conversational robots have now refined their understanding of language to such an extent that they can now interact with humans in various, complex ways, from managing user messages according to extremely specialized contexts.
Koïos’ conversational agents are designed for the financial sector, especially the insurance world. However, a partnership with another company enabled them to test their application and expertise in a new sector: marketing.
According to Mohamed Hanini, CEO and founder of Koïos Intelligence:
“A lot has been written about dialogue systems because of how complex the underlying processes are. Although there are several solutions on the market today – Siri, Google, Alexa – they remain very general in their abilities, and thus perform very poorly when it comes to classifying intentions in a specific area of interest.
So, developing a conversational agent for the marketing world is very different from doing the same job for the insurance sector. We’ve taken all the expertise we’ve accumulated at Koïos and tried to help Wittycloud automate as many of the ideation processes as possible that are usually done in advertising agencies.”
Wittycloud is a company of ideas. Literally. Its platform, powered by artificial intelligence, helps designers come up with concepts for advertising campaigns. We enter our marketing objectives and press a button to receive suggestions tailored to our needs.
The idea was to create an automated marketing agency. And even though the platform is delivering convincing results for Philippe Larose Cadieux, CEO and co-founder of Wittycloud, there was still something missing: making this digital service more human. The solution seemed straightforward: develop a conversational agent with which you could easily chat. But this ambition came up against a major obstacle: advertising jargon.
“Normally, voice assistants are trained using a very general corpus [of words], dealing with the weather or restaurant reservations,” says Philippe Larose Cadieux. For this technology to be relevant in our reality, we had to get the algorithm to respond intelligently in a marketing’s, specialized context. For example, the word ‘image’ might normally refer to a photo or a drawing; in our field, it’s more often associated with brand image.”
The task was to create a virtual agent that understands the nuances of a particular branch in the business world, and have it respond appropriately to the inputer’s requests. Koïos Intelligence already had promising expertise in this field, as they had designed conversational agents for the insurance sector. Today, these agents are even able to talk to customers over the phone and offer them quotes based on their needs.
“It’s a bit like training human beings,” explains Mohamed Hanini, CEO of Koïos. In elementary school, we learn simple syntax and conjugation. Then, as we go along, we add finer details, tone, and nuances. In the case of a conversational agent, we’ll feed it with an additional layer of data that will enable it to understand a context such as insurance, for example.”
Unfortunately, creating intelligent assistants capable of these nuances proved tedious and costly. As the insurance and marketing fields are constantly changing, being able to update them easily was essential. So the two companies joined forces to do two things.
The first was to develop an “interpreter” tailor made for the world of marketing. This is, in a way, the engine of a virtual agent: the part that authorizes the passage between natural language and machine language. Wittycloud took on the task and produced a kind of “marketing bible” to feed the algorithms. “We relied mainly on content from our users, but also on our own expertise,” explains Philippe Larose Cadieux.
On the other end, Koïos intelligence worked in R&D to optimize the pre-training and tuning phase of their deep networks to integrate Wittycloud’s new layer of information economically and efficiently. In other words, they made qualifying and updating a voice assistant easier and cheaper.
“Lines of business can now be handled completely independently,” explains Hanini. For example, for commercial insurance, or life insurance or car insurance, we can create specialized robots for each line of business. We separate the environments entirely.”
For Wittycloud, these developments represent important steps towards their goal of becoming a new kind of advertising agency. Specifically, one that takes advantage of the possibilities offered by artificial intelligence. For Koïos Intelligence, they hope that this project will open doors in the banking sector.
To read the original article, click here.