US 11,809,967 B2
Information processing apparatus and method of controlling the same
Kei Tamagawa, Tokyo (JP)
Assigned to Canon Kabushiki Kaisha, Tokyo (JP)
Filed by CANON KABUSHIKI KAISHA, Tokyo (JP)
Filed on Dec. 20, 2019, as Appl. No. 16/722,468.
Claims priority of application No. 2018-243787 (JP), filed on Dec. 26, 2018.
Prior Publication US 2020/0210898 A1, Jul. 2, 2020
Int. Cl. G06N 20/00 (2019.01); H04N 1/00 (2006.01); G06F 17/18 (2006.01)
CPC G06N 20/00 (2019.01) [G06F 17/18 (2013.01); H04N 1/00068 (2013.01)] 15 Claims
OG exemplary drawing
 
1. An information processing apparatus comprising:
at least one processor configured to read out and execute instructions stored in at least one memory to thereby cause the information processing apparatus to function as:
an obtaining unit configured to obtain (i) feature data of workers' activities at a production site and (ii) past result information from the production site;
an estimation model generating unit configured to generate an estimation model using machine learning, the machine learning being based on training data that includes (i) the obtained past result information from the production site and (ii) correct answer data indicating correct answers at time intervals;
an estimation unit configured to generate an estimation result that is an estimate of a work process from the feature data using the estimation model;
a determination unit configured to determine a conversion table based on two types of estimation accuracy in the estimation model, with the conversion table being used to correct the estimation result obtained by using the estimation model; and
a correction unit configured to correct the estimation result based on the conversion table,
wherein the estimation accuracy is determined using (i) a recall value that is a ratio of each work process estimated by the estimation model in each actual work process in the past result information obtained by the obtaining unit, and (ii) a precision value that is a ratio of each actual work process in each work process estimated by the estimation model in the past result information obtained by the obtaining unit.