| CPC B66B 1/28 (2013.01) [B66B 1/2408 (2013.01); B66B 1/3476 (2013.01); B66B 3/002 (2013.01); G05B 13/0265 (2013.01); G05B 19/4155 (2013.01); G06N 7/01 (2023.01); G06N 20/00 (2019.01); B66B 2201/222 (2013.01); B66B 2201/223 (2013.01); B66B 2201/23 (2013.01); B66B 2201/235 (2013.01); B66B 2201/4661 (2013.01); G05B 2219/45014 (2013.01); G06N 3/084 (2013.01)] | 8 Claims |
|
1. An elevator system comprising:
at least one processor and at least one memory coupled to each other and, when a program stored in the at least one memory is executed by the at least one processor, the at least one processor acts as:
a first acquisition unit configured to acquire an image in a car of an elevator and an image of a landing of the elevator;
a generation unit configured to generate first learning data from the images acquired by the first acquisition unit;
a learning unit configured to perform learning using the first learning data, thereby generating a first learned model used to estimate whether a person on the landing of the elevator gets in the elevator;
an input data generation unit configured to generate input data from a new image including the person on the landing of the elevator acquired by the first acquisition unit;
an estimation unit configured to estimate, by applying the input data to the first learned model, whether the person on the landing of the elevator, which is included in the new image, gets in the elevator, to obtain a first estimation result indicating a probability that the person on the landing gets in the car and a probability that the person on the landing does not get in the car;
a control unit configured to control an operation of the elevator based on the first estimation result; and
a notification unit configured to make a notification in the car of the elevator;
a second acquisition unit configured to acquire an image in the car of the elevator and an image of the landing of the elevator after the notification by the notification unit has been made,
wherein the generation unit is configured to generate second learning data from the image in the car of the elevator and the image of the landing of the elevator acquired by the second acquisition unit after the notification by the notification unit has been made,
wherein the learning unit is configured to perform learning using the second learning data, thereby generating a second learned model used to estimate whether the person on the landing of the elevator gets in the elevator in a case where the notification has been made by the notification unit,
wherein the estimation unit is configured to estimate, by applying the input data generated by the input data generation unit to the second learned model, whether the person on the landing of the elevator, which is included in the new image in the case where the notification has been made by the notification unit, gets in the elevator, to obtain a second estimation result indicating a probability that the person on the landing gets in the car and a probability that the person on the landing does not get in the car in the case where the notification has been made by the notification unit, and
wherein the control unit is configured to control the notification by the notification unit based on the second estimation result of the estimation unit and control the operation of the elevator to stop the car at a floor to which the car of the elevator is called in a case where, in the second estimation result, the probability that the person on the landing gets in the car of the elevator is higher than the probability that the person does not get in.
|