A collaborative scheduling method for high-rise elevators based on Internet of Things is provided. The method includes: obtaining the number of people carried at the current moment of each elevator in the elevator group, the target distance corresponding to the current moment of each elevator, and the number of people waiting at the current moment of each floor; predicting the number of people waiting for the going up and the number of people waiting for the going down at the current moment of each floor based on the monitoring video data of the elevator door every day in the preset historical days, and constructing the corresponding feature vectors of each elevator at the current moment and the corresponding feature vectors of the skyscraper at the current moment, and then obtaining the corresponding state vectors at the current moment, controlling each elevator based on state vector and ES-Reinforcement learning network.

Embodiments herein relate to an elevator system of a facility with multiple floors. The elevator system can comprise elevator cars and an elevator controller. The elevator controller includes a memory and a processor. The memory stores computer program instructions executable by the processor to cause the elevator system to determine a current utilization of the elevator system, automatically activate an adaptive split group operation on a per floor basis when the current utilization of the elevator system is greater than a threshold utilization of the elevator system, and dispatch the elevator cars under the adaptive split group operation in accordance with elevator calls.

An elevator control method for an elevator system including cars movable in an elevator shaft of a building the building being dividable into serving sectors each serving sector including at least one floor to be served by a car, and a recording device for recording car usage data, the recording device being dedicated to the cars, wherein the recording device forwards the car usage data to an elevator controller receiving the car usage data for creating car-logbook-data. The method of division of the serving sectors is decided on evaluation-analysis of the car-logbook-data by gathering and storing the car usage data over a period of time into a memory of the elevator controller and allocating a serving sector in dependency of the evaluation-analysis of the car usage data respectively.

A collaborative scheduling method for high-rise elevators based on Internet of Things is provided. The method includes: obtaining the number of people carried at the current moment of each elevator in the elevator group, the target distance corresponding to the current moment of each elevator, and the number of people waiting at the current moment of each floor; predicting the number of people waiting for the going up and the number of people waiting for the going down at the current moment of each floor based on the monitoring video data of the elevator door every day in the preset historical days, and constructing the corresponding feature vectors of each elevator at the current moment and the corresponding feature vectors of the skyscraper at the current moment, and then obtaining the corresponding state vectors at the current moment, controlling each elevator based on state vector and a reinforcement learning network.

An elevator system for a building comprises an elevator controller and an elevator car movable in an elevator shaft. At least one first floor or first floor area for a first user group and at least one second floor or second floor area for a second user group are defined in the building. A memory device saves this definition and an operating mode assigned thereto for each user group. During operation, a first elevator call is received and analyzed by the elevator controller to determine a first call input floor and/or a first destination floor. An operating mode is ascertained based on the first call input floor and/or the first destination floor. According to this operating mode, the elevator car is controlled by the elevator controller.

A method for positioning a plurality of elevator cars that includes determining an occupant count for each of a plurality of locations, by determining the number of occupants exiting the plurality of elevator cars at each of the plurality of locations and the number of occupants entering the plurality of elevator cars from each of the plurality of locations. The method includes moving at least one of the plurality of elevator cars to a first location with a total occupant count that is greater than the occupant count at each respective location of the plurality of locations when the at least one of the plurality of elevator cars is in an inactive state.

Elevator system passengers are transported in one or more of a plurality of elevator cars. The elevator cars can require different amounts of energy to operate. Passenger trips can be allocated to one car or another car based on the expected energy consumption for the trips in one or the other car.

A method for managing an elevator service to a floor by an elevator system is provided, the method including: generating a first estimation on an aggregate need of an elevator service for a group of individuals in a predefined area, the aggregate need being generated by combining a number of estimations descriptive on a need of the elevator service by each individual at a first instant of time; comparing the first estimation to a first reference value; generating a first control signal to reserve a number of elevators to serve a section the floor belongs to in response to a detection that the first estimation fulfills a condition defined by the first reference value. A control system, an elevator system, and a computer readable medium are also provided.

In an elevator system, floor terminals can be actuated by a control unit in one of at least two operating modes. A screen unit of a floor terminal can generate a user interface with a functional scope dependent on the operating mode. An individual functional scope can be defined for each operating mode. The control unit can determine a local traffic volume at the first floor terminal location. The local traffic volume can be compared with at least one threshold value that is defined for the traffic volume at the first floor terminal to generate a comparison result. A desired operating mode of the first floor terminal can be defined based on the comparison result and the operating mode in which the control unit actuates the first floor terminal. The first floor terminal can be actuated in the defined desired operating mode.

A method for training neural networks to assign calls to elevator cars simulates an environment in which first and second cars move between building floors in reaction to calls indicating desired floors, each simulation including steps: determining a current state of the environment including a current position of each car, a list of current calls and a new call; inputting first and second input data encoding at least a part of the current state into respective first and second neural networks each configured to convert the input data into output values indicating a probability and/or tendency for the cars to be assigned to the new call; determining a selected car using the output values; assigning the new call to the selected car, and determining reward values quantifying a usefulness of the assignment; training the neural networks using past simulation reward values to increase the usefulness of future assignments.