The present disclosure relates to a method for operating an elevator system, which is embodied as shaft-changing multi-car system. A number of cars is assigned to at least three elevator shafts. The cars can be moved in upwards direction and downwards direction inside the individual elevator shafts, as well as between the individual elevator shafts. A successive reversal of the travel directions of the respective cars occurs hereby.

An information processing apparatus includes a controller configured to predict a state of congestion of an elevator installed in a building and generate, based on the predicted state of congestion, a proposal message to propose a departure time for the building to a user planning to travel to the building.

An elevator system is provided. Aspects includes an elevator car, a sensor affixed to the elevator car, wherein the sensor is operated by a controller, the controller is configured to receive occupancy data associated with the elevator car. The occupancy data is analyzed to determine an occupancy of the elevator car. A first hall call is received and based at least in part on the occupancy and the first hall call, adjusting operation of the elevator car in the elevator system.

A car mover for autonomously moving an elevator car along a lane in a hoistway, including: first and second wheels of the car mover, configured to apply a pinch force against a track therebetween and to rotationally drive along the track, by respective first and second wheel motors of the car mover; and a controller configured to execute: a gap control self-learning module, wherein based on adjustment data, one or more operational parameters applied by one or more of the first and second wheel motors are adjusted; and a gap feedback control module, wherein based on one or more of a first lateral clearance adjacent the first wheel on the track and a second lateral clearance adjacent the second wheel on the track, torque applied by one or more of the first and second wheel motors is increased or decreased.

According to an aspect, there is provided a method for forecasting elevator passenger traffic of an elevator group. The method comprises training a statistical traffic model describing a traffic profile for a specific cycle with historical timestamped origin-destination passenger counts, obtaining timestamped origin-destination passenger counts for a current cycle, generating an elevator passenger traffic forecast based on the trained statistical traffic model and the timestamped origin-destination passenger counts for the current cycle, and outputting the elevator passenger traffic forecast for use by an elevator group control.

Provided are techniques for performing cloud-based elevator dispatching resource management. The techniques include receiving usage information of one or more elevators of an elevator system, obtaining configuration parameters of a controller configured to control the one or more elevators, and analyzing a performance of the one or more elevators based at least in part on the usage information. The techniques also include dynamically updating the configuration parameters of the controller based on the performance and the usage information, storing the configuration parameters and corresponding performance, and operating the one or more elevators based at least in part on the updated configuration parameters.

A control system for controlling motion of elevators of a bank of elevators uses a neural network trained for an extended destination prediction of a person based on a partial trajectory of the person to produce a multinomial of the extended destination prediction. The multinomial has at least two dimensions including a first dimension of destinations of the person and a second dimension of time intervals of the person arriving at the destinations of the first dimension. The control system optimizes a schedule of the bank of elevators based on the multinomial, and further controls the bank of elevators according to the schedule.

A method for determining an allocation decision for at least one elevator includes using an existing calls in an elevator system as a first input in a machine learning module, processing the first input with the machine learning module to provide a first output comprising a first allocation decision, using the first output as a second input in an iterative module, processing the second input with the iterative module to provide a second ouput comprising a second allocation decision, and providing the second allocation decision to an elevator control module and to an allocation decision storage for further machine learning module training.

A method and an apparatus for computing allocation decisions in an elevator system is provided. Historical passenger batch journey data relating to the elevator system is obtained, wherein each passenger batch journey includes an origin and a destination floor of the journey, the number of passengers of the journey and the time of the journey. Historical passenger traffic statistics are constructed based on the passenger batch journey data, and expected calls are modelled based on the passenger traffic statistics. The modelled expected call is taken into account in computing subsequent allocation decisions in the elevator system.

A method for the call allocation in an elevator group uses a call allocation unit of an elevator group control. In the call allocation unit, passenger flow data of the elevator group is used to adapt call allocation parameters to improve the performance of the elevator group. The public traffic data is retrieved from at least one public transportation system, and is used to supplement expected passenger flow data for the adaption of call allocation parameters.