We have developed a unique behavioral analysis artificial intelligence (AI) using the company’s Maisart^®* AI technology.

Even without prior machine learning, the new technology can detect slight differences in human motions that people do not readily notice, and can be useful for analyzing human behavior in various fields, such as analyzing the motions of assembly-line workers to help eliminate unnecessary motions and thereby improve productivity.

When analyzing assembly work performed in factories, Maisart^® analyzes the operation based on the 3D positioning of both hands of each worker measured by sensors.

(ⅰ) Estimation of motion element boundaries
In the beginning, the AI pays attention to motions that are repeated in a given order, such as attaching a part and screwing it into place. It divides the measurement data equally as the initial value and temporarily sets boundaries for each motion. Next, it extracts the waveform for each motion and compares it with the measurement data to update and determine motion boundaries.

(ⅱ) Determination of standard operation patterns
Estimated motions are aligned to automatically determine standard motion patterns. Motions are expressed in different colors along with the standard time that is determined for each.

(ⅲ) Detection of non-standard behavior
Non-standard behavior can be detected by comparing the motion pattern extracted from measurement data with the standard motion pattern.

Behavioral analysis is performed at high speed in just a few seconds or minutes, to provide rapid feedback on increasing workers’ efficiency.

Applications in various fields other than factories will be explored by leveraging the technology’s capability to function without prior machine learning.