A production facility monitoring system includes: an information acquirer that acquires information on productivity of one or more production facilities; an information manager that extracts, based on one or more results included in a statistical result of the acquired information, a proposal item satisfying a condition of the statistical result from at least one proposal-item reference table containing proposal items; and a display that displays the extracted proposal item. The production facility monitoring system monitors the productivity.

A work vehicle that operates on a surface comprising an optical sensor. The optical sensor is configured to capture image data that includes a ground material. A non-transitory computer-readable memory is provided for storing operation information. An electronic processor is configured to receive image data captured by the optical sensor, apply an artificial neural network to identify a ground material characteristic based on the image data from the optical sensor, wherein the artificial neural network is trained to receive the image data as input and to produce as the output an indication of the ground material characteristic, access, from the non-transitory computer-readable memory, the operation information corresponding to the ground material characteristic, and adjust an operation of the work vehicle based on the accessed operation information corresponding to the ground material characteristic.

A sensor data input device obtains a plurality of sensor data sequences, each indicating time-series sensor values generated by measuring a work of a working subject using a sensor. A class data generator determines a plurality of intervals obtained by temporally dividing each sensor data sequence based on the sensor values, determines classes of the intervals, each class indicating a type of temporal variations in the sensor values included in one of the intervals, and generates a plurality of first class data sequences for each sensor data sequence, each first class data sequence indicating the intervals and the classes of the sensor data sequence. A class data linker associates the corresponding intervals having an identical class with each other, among the plurality of first class data sequences. A determiner calculates characteristic values of the intervals associated with each other.

The present invention increases the productivity of an entire factory, even of the type that produces different types of products in different quantities using transport vehicles, by performing transport operation control. This transport operation control device is provided with: a spatial distribution measuring unit which measures the spatial distribution of products-in-process being transported by the transport vehicles; and an operation schedule calculation unit which, on the basis of the measured spatial distribution of the group of partly-finished products, calculates an operation schedule that specifies both a route and a frequency of a transport operation to be carried out by each transport vehicle of the transport vehicles, wherein the operation schedule calculation unit determines the timing with which to update the operation schedule, on the basis of changes in a productivity index that is determined from the measured spatial distribution of the products-in-process.

A sensor data input device obtains a plurality of sensor data sequences, each indicating time-series sensor values generated by measuring a work of a working subject using a sensor. A class data generator determines a plurality of intervals obtained by temporally dividing each sensor data sequence based on the sensor values, determines classes of the intervals, each class indicating a type of temporal variations in the sensor values included in one of the intervals, and generates a plurality of first class data sequences for each sensor data sequence, each first class data sequence indicating the intervals and the classes of the sensor data sequence. A class data linker associates the corresponding intervals having an identical class with each other, among the plurality of first class data sequences. A determiner calculates characteristic values of the intervals associated with each other.