Unsupervised Work Behavior Pattern Extraction Based on Hierarchical Probabilistic Model

TL;DR

This paper introduces an unsupervised hierarchical probabilistic model that automatically segments and analyzes worker behaviors in manufacturing, improving accuracy without requiring labeled data.

Contribution

It extends the Gaussian process hidden semi-Markov model (GP-HSMM) to enable unsupervised, multi-granularity behavior pattern extraction with mutual parameter inference.

Findings

Achieved smaller normalized Levenshtein distance (NLD) compared to baseline methods.

Automatically segments continuous motions into meaningful classes.

Demonstrated effectiveness in real production site data.

Abstract

Evolving consumer demands and market trends have led to businesses increasingly embracing a production approach that prioritizes flexibility and customization. Consequently, factory workers must engage in tasks that are more complex than before. Thus, productivity depends on each worker's skills in assembling products. Therefore, analyzing the behavior of a worker is crucial for work improvement. However, manual analysis is time consuming and does not provide quick and accurate feedback. Machine learning have been attempted to automate the analyses; however, most of these methods need several labels for training. To this end, we extend the Gaussian process hidden semi-Markov model (GP-HSMM), to enable the rapid and automated analysis of worker behavior without pre-training. The model does not require labeled data and can automatically and accurately segment continuous motions into motion classes. The proposed model is a probabilistic model that hierarchically connects GP-HSMM and HSMM, enabling the extraction of behavioral patterns with different granularities. Furthermore, it mutually infers the parameters between the GP-HSMM and HSMM, resulting in accurate motion pattern extraction. We applied the proposed method to motion data in which workers assembled products at an actual production site. The accuracy of behavior pattern extraction was evaluated using normalized Levenshtein distance (NLD). The smaller the value of NLD, the more accurate is the pattern extraction. The NLD of motion patterns captured by GP-HSMM and HSMM layers in our proposed method was 0.50 and 0.33, respectively, which are the smallest compared to that of the baseline methods.