kissing-bots

Assessment and AI - dream or far-fetched?

Published by Rob Kurvers on .

The most tried professionals know that assessments of individuals and teams are complex and time-consuming. But can AI and Machine Learning be used to make this complexity into something clear-cut and simple? What information can a robot derive from images, speech, behavior and habits in single and team-run situations? Is this something that can be even more effective and faster than traditional human-analysed questionnaires from just speech and images?

3 cutting-edge tech companies have joined forces to investigate these very questions. At iVinci, we are researching and developing a working installation which makes use of smart software and learning algorithms to perform a team assessment faster and more accurately than any human, and at a much cheaper cost.

Next Generation Assessment – using AI in video analysis

iVinci has been working on all-new observational robotic technology since mid-2019. This bot not only makes it possible to record speech and images of multiple people, but it also enriches that collected data with machine learning.

This means that even large teams working together can be observed, and analysed in an accurate way which will detect human patterns in speech, movement, and even personal mood.

In the past year, our robotic technology has progressed so tremendously that we have been asked to participate in an innovative product in which a group of people in a conditioned environment can be followed. iVinci is working closely with Ixly (www.ixly.nl) and Twain (www.Twain.nl) on this collaborative project.
The AI analysis of data will result in a full script of every conversation within the team. This script will be annotated with speech speed and patterns like intonation and interpreted facial expressions. The richness of the data collected in this way and enriched by our AI software provides an enormous set of data. An important element of this investigational project is to prove the relevance of various data sets for deep assessment purposes. We're confident that these methods are not only faster and cheaper when applied to team assessments, but will provide much higher quality results that are reliable.

This innovation project is funded by the province of Utrecht, which has allocated a subsidy to some of the most cutting-edge innovations in the country. After summer 2020, we will bring more information about the finished product, including the request to participate in various tests.

A Look Into the Future of Gov-2016 » Posts | GovLoop

From mid-July we will publish a series of articles to share technical challenges we have encountered. We will pay attention to image, voice, trigger data and the correct combination of all data.

The next episode is about capturing and enriching images.

At iVinci, we use open source components and like to share what we have discovered. At iVinci we work with the latest technology for audio and image processing. We develop techniques to be used effectively for natural human conversations.

For more information or a specific question, feel free to leave a message.