Elevator Call Prediction Control for Shorter Waiting Times

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Elevators often operate inefficiently due to varying frequencies of calls across different floors in buildings, leading to prolonged waiting times for users, especially when the elevator is far from the call location.

Innovation Solution

An elevator control system that predicts target floors based on historical call data, generating matrices to determine optimal locations using a weighting and scoring system, and moves the elevator proactively to anticipated call areas.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of time

If the elevator remains at its last destination floor or automatically returns to a lobby to await the next call, then the elevator operation is simple and energy consumption is low, but the user waiting time increases and operation efficiency decreases

Engineering Contradiction:
Improveuser waiting timeVSAvoidcontrol system complexity
Core Design Contradiction:
Loss of timeVSDevice complexity

Solution Approach 1:

The control system performs preliminary actions by predicting future call locations based on historical data and proactively moving the elevator to these predicted floors before actual calls occur. This anticipatory approach reduces user waiting time by ensuring the elevator is already positioned near where calls are likely to happen, rather than reacting to calls after they occur.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms by continuously collecting actual call data and comparing it with predicted call locations. This feedback loop allows the system to learn from past performance, refine its prediction algorithms, and improve future predictions, thereby progressively reducing waiting times while maintaining adaptive control.

Inventive Principle:
Principle #23Feedback

2Productivity

If the elevator moves to predicted target floors proactively, then operation efficiency improves and waiting time reduces, but energy consumption increases and control complexity increases

Engineering Contradiction:
Improveelevator operation efficiencyVSAvoidelevator energy consumption
Core Design Contradiction:
ProductivityVSUse of energy by moving object

Solution Approach 1:

The system applies preliminary action by moving the elevator to predicted target floors in advance based on historical call patterns. This proactive positioning improves operation efficiency by reducing idle time and positioning the elevator optimally before calls occur, rather than moving reactively after calls are registered.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The control system dynamically adjusts its behavior by continuously analyzing real-time and historical data to update prediction models. This dynamic adaptation allows the system to optimize movement patterns based on changing usage patterns, improving efficiency while avoiding unnecessary movements that would waste energy.

Inventive Principle:
Principle #15Dynamics

3Measurement precision

If the elevator uses historical call data and prediction algorithms, then call response accuracy improves, but data processing requirements and system complexity increase

Engineering Contradiction:
Improvecall location prediction accuracyVSAvoiddata processing system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system uses feedback by continuously comparing actual call locations with predicted locations, using this information to refine prediction algorithms. This iterative learning process improves prediction accuracy over time while maintaining a manageable level of system complexity through adaptive rather than overly complex processing.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The prediction system performs self-service by automatically analyzing historical data and updating its own prediction models without requiring external intervention. This self-learning capability improves accuracy while keeping the system architecture relatively simple, as the system manages its own complexity through automated data processing and model refinement.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4707213A1Elevator control system and elevator control method
Publication Date: 2026.03.11 HYUNDAI ELEVATOR CO LTD
  • EP4707213A1 patent drawingFigure 1
  • EP4707213A1 patent drawingFigure 2
  • EP4707213A1 patent drawingFigure 3

AI summary

An elevator control system is disclosed. The elevator control system includes: a data processing unit configured to process elevator operation information; a data storage unit configured to store the elevator operation information, the elevator operation information including call-by-call data including a date and time at which each call occurred and a floor on which each call occurred; an analysis unit configured to predict a target floor of an elevator based on the elevator operation information; and an elevator control unit configured to move the elevator to the predicted target floor.