According to an aspect, there is provided a method and an apparatus for determining an allocation decision for at least one elevator. In the solution existing calls are used in an elevator system as a first input in a machine learning module. The first input is processed with the machine learning module to provide a first output comprising a first allocation decision. The first output is then used as a second input in an iterative module. The second input is processed with the iterative module to provide a second output comprising a second allocation decision. The second allocation decision is provided to an elevator control module and to an allocation decision storage for further machine learning module training.

An elevator control system including an elevator management system obtaining meeting information from at least one of a calendar system and a user interface; the elevator management system generating a control command in response to the meeting information; and an elevator controller controlling destinations of one or more elevator cars in response to the control command.

Embodiments of the present invention provide a method, system and computer program product for smart elevator car destination management according to probabilistic destination determination. In an embodiment of the invention, a method for smart elevator car destination management according to probabilistic destination determination includes predicting a set of passengers requesting use of an elevator car in a bank of elevator cars in a building and determining a probability for each of the passengers that each passenger will select as a destination a particular floor in the building. The method also includes grouping ones of the passengers in the set according to a common floor determined to be probable for the grouped ones of the passengers. Finally, the method includes displaying in connection with the bank of elevator cars an assignment of the grouped ones of the passengers to one of the elevator cars in the bank.

Embodiments of the present invention provide a method, system and computer program product for smart elevator car destination management according to probabilistic destination determination. In an embodiment of the invention, a method for smart elevator car destination management according to probabilistic destination determination includes predicting a set of passengers requesting use of an elevator car in a bank of elevator cars in a building and determining a probability for each of the passengers that each passenger will select as a destination a particular floor in the building. The method also includes grouping ones of the passengers in the set according to a common floor determined to be probable for the grouped ones of the passengers. Finally, the method includes displaying in connection with the bank of elevator cars an assignment of the grouped ones of the passengers to one of the elevator cars in the bank.

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.

A system for controlling multidirectional operation of an elevator is disclosed. The system includes a processing subsystem which includes a centralized elevator control module to receive a control signal representative of elevator operation from one or more control units deployed at one or more elevator cabins. A usage pattern generation module utilizes a learning model to learn usage pattern of the one or more elevator cabins. An elevator operation evaluation module identifies deviation of one or more operational parameters associated with the one or more elevator cabins, detects operational failure of the one or more elevator cabins. An elevator rescue module receives rescue command from the centralized elevator control module to initiate rescue process, identifies one or more rescue elevator cabins in proximity to the one or more elevator cabins, activates the one or more rescue elevator cabins identified for transporting a plurality of passengers from source to destination.

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 controlling a lift installation having a plurality of cabins that can each stop at a number of floors may involve assigning calls placed outside the cabins to the cabins by way of a lift controller based on at least one assignment criterion. The method may involve considering a current traffic situation of the lift installation during the assignment. The method may further involve generating and considering a forecast of a future traffic situation of the lift installation during the assignment. The forecast may account for personal information of at least one of a person who is in a predetermined environment of the lift installation, a person who is in a section of the lift installation, a person who enters a predetermined environment of the lift installation, or a person who leaves a predetermined environment of the lift installation.

A movement detection system for a passenger in the present invention includes: a first Bluetooth module (150) mounted in an elevator landing area; and a movement prediction unit (270) configured to predict, based on Bluetooth movement data, that a movement of a passenger in the elevator landing area is a normal movement or an abnormal movement. The movement detection system and a movement detection method in the present invention can automatically detect an abnormal movement of a passenger, and are especially applicable to an elevator system that completes an elevator call operation without an input operation.

An exemplary elevator passenger interface device includes a touch screen configured to allow a passenger to indicate a request for elevator service by touching the screen. An assistance button is positioned near the touch screen. A controller is configured to determine a destination requested by a passenger touching the screen. The controller is also configured to determine whether the assistance button has been manipulated and then to determine a destination requested by a passenger from a subsequent manipulation of the assistance button.