Game Tech, Powder, AI, recognizing the strongest moments

It is a kind of metaverse camera: it captures the real in the virtual so that players can then exchange clips of the best moments experienced during a video game session. To do this, the Parisian start-up Powder has developed an artificial intelligence (AI) for image and emotion recognition. Concretely, the solution, based on the automatic learning It is on deep learningit analyzes in particular the sound dimension. “When players start reacting, when something strong happens, we detect patterns in the sound that we quantify. We therefore obtain an amplitude of emotions from which we can determine a strong emotional moment “, explains Stanislas Coppin, co-founder and CEO of Powder. This recognition is now combined with algorithms “which also allow you to recognize what is said during a match”says the manager. All this to analyze, for example, the laughter or other emotions aroused by the actions of the players.

A growing international audience

To innovate in this sector, the startup’s AI department is working, on the one hand, on the search for new ways of reading video and audio elements to extract information from them and, on the other, on the creation of game analysis models. More than half of Powder’s 45 employees are AI developers, engineers or PhD students.“We have 18 nationalities within our company”says Stanislas Coppin. The challenge is to have a diverse team capable of creating an international product that meets the demands of different markets. In short, to combine talents with different profiles (Engineers, Developers, Designers, Salespeople), to have more and more ideas.

Especially since the start-up continues to grow. Since April 2020, when its application was released on the App Store, it has amassed around three million downloads worldwide. Its clients are mainly in Asia and the United States, countries where this Parisian start-up has been founded since its inception. His ambition? “Our goal is to develop our international audience and then start monetizing, first across the Atlantic and into Asia, while continuing to develop our European market.”says Stanislas Coppin. To this end, the company has already raised a total of 20 million euros and is planning a new round of financing in the coming months to consolidate its mission.

The AWS cloud, a companion for machine learning

To fulfill its ambitions, Powder has relied on the cloud since its creation. Two main reasons for this. First of all, “Ease of installation and administration”analyzes Christian Navelot, co-founder and technical director of Powder. “To manage videos, we need very large storage volumes and fast access times”it develops. “Without the cloud, we would have to manage our machines ourselves, which requires a lot of resources, dedicated network lines, a cold room and considerable costs. This is all the more complicated in times of strong growth “He believes.

But beyond storage, “It is also important to know how to use the right tools in the cloud”, continues Christian Navelot. This is precisely the element that motivated the choice of Amazon Web Services (AWS) which supports the nugget in its development. On the supplier side, a account Manager and a solutions architect are working with the start-up to make better use of the tools in the cloud. “Cost is a real problem for a growing startup like ours. To optimize it, AWS supports us in the periodic evaluation of our needs “summarizes the technical director of Powder.

“In particular, we use Amazon Sage Maker, the cloud-based machine learning platform that offers many artificial intelligence and machine learning services. It allows us to tap into certain tools, for example for the training and industrialization of machine learning models. We are therefore creating a series of models in parallel to be able to refine them, particularly in the event of the release of new seasons of games “details this manager.

Finally, Powder was able to unlock $ 100,000 in credits per year through the Activate program. The key for the start-up is the ability to run multiple tests on the AWS platform. One way, again, to accelerate its rise.