Focus, understanding and efficiency are the most important factors in education and other intellectual activity. Yet, the 21st century saw the rise of information overload and short attention span. People get distracted, lose focus and understanding of their tasks, which becomes a serious obstacle to productive work.
To solve this, we invented Oken.
Oken measures major cognitive indicators such as the levels of attention, understanding, focus and productivity in real time. Using this information, the technology offers the user advice to increase the productivity of their intellectual activity.
We use eye-tracking to measure the indicators, and we do not need any special equipment. The front camera of the user’s smartphone or computer becomes an eye-scanner itself.
During reading or other work our eyes do not move smoothly: they jump from one thing to another in saccades. The length of these saccade-jumps and their speed, the duration of gaze fixation and the pattern of blinking make it possible to determine the user’s cognitive indicators.
Oken detects these movements and matches the data to the trained machine learning model. Its neural network recognises the specific eye movement patterns for certain cognitive states and returns to the user the result in simple numbers and graphs. We highlight the parts of the text which saw lowered attention and understanding and offer a system of personal recommendations on restoring productivity.
To solve this, we invented Oken.
Oken measures major cognitive indicators such as the levels of attention, understanding, focus and productivity in real time. Using this information, the technology offers the user advice to increase the productivity of their intellectual activity.
We use eye-tracking to measure the indicators, and we do not need any special equipment. The front camera of the user’s smartphone or computer becomes an eye-scanner itself.
During reading or other work our eyes do not move smoothly: they jump from one thing to another in saccades. The length of these saccade-jumps and their speed, the duration of gaze fixation and the pattern of blinking make it possible to determine the user’s cognitive indicators.
Oken detects these movements and matches the data to the trained machine learning model. Its neural network recognises the specific eye movement patterns for certain cognitive states and returns to the user the result in simple numbers and graphs. We highlight the parts of the text which saw lowered attention and understanding and offer a system of personal recommendations on restoring productivity.
About
CEO & Founder
Arsen Revazov, PhD
CPO
Eugene Bagrov, eMBA
CTO
David Dreval, MBA CIO
Team
5
3
8
&
Science
ML
Software development
& Design
& Design
CPO and Project manager
© 2022 Oken Technologies Inc.
