Operations management system and operations management method

An operations management method performed by an operations management system including a processor and a non-transitory memory, the operations management method comprising:

• an acquiring step performed by the processor, the acquiring step including acquiring moving picture data of a person who is repeatedly performing operations;
• a storing step performed by the processor using the non-transitory memory, the storing step including storing multiple operation data sets as information representing, with respect to the operations to be repeated a number of times, respectively, a time series variation in location of at least one point set on a body of the person who is performing the operations on a repeat unit basis, the multiple operation data sets being extracted from the moving picture data;
• a dividing step performed by the processor, the dividing step including dividing each of the multiple operation data sets into a predetermined number of partial data;
• a degree of similarity calculating step performed by the processor;
• and
• an estimating step performed by the processor,
• the multiple operation data sets including a first operation data set and a second operation data set,
• the first operation data set being divided, by performing the dividing step, into a plurality of first partial data, each of the plurality of first partial data being from among the predetermined number of partial data,
• the second operation data set being divided, by performing the dividing step, into a plurality of second partial data, each of the plurality of second partial data being from among the predetermined number of partial data,
• the degree of similarity calculating step including:
• calculating a degree of similarity between each of the plurality of first partial data and second partial data corresponding to the first partial data and belonging to the plurality of second partial data;
• and
• calculating a degree of first operation data set similarity by adding together the respective degrees of similarity that have been calculated with respect to all of the plurality of first partial data,
• the dividing step including making a ratio of respective time lengths of the plurality of first partial data equal to a ratio of respective amounts of time required to have multiple tasks done as defined by operation instructions, and
• the estimating step including estimating, by Bayesian optimization using respective start times of the plurality of first partial data and the degree of first operation data set similarity, one or more division points where the first operation data set is divided to maximize the degree of first operation data set similarity.