End-To-End Cognitive Elevator Dispatching System

• US 20200130984A1
• Filed: 10/30/2018
• Published: 04/30/2020
• Est. Priority Date: 10/30/2018
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Wang, Wen, Fu, Rong, Cai, Zhuo JP, Sheng, Hao, Yin, Jian Dong, Zhang, Kang ED
• Granted Patent: US 11,697,571 B2
• Time in Patent Office: Days
• CPC Class Codes: B66B 1/2458 For elevator systems with multiple shafts and a single car per shaft
• CPC Class Codes: B66B 1/468 Call registering systems
• CPC Class Codes: B66B 2201/20 Details of the evaluation method for the allocation of a call to an elevator car
• CPC Class Codes: B66B 2201/235 Taking into account predicted future events, e.g. predicted future call inputs
• CPC Class Codes: B66B 2201/243 Distribution of elevator cars, e.g. based on expected future need
• CPC Class Codes: B66B 2201/402 by historical, statistical or predicted traffic data, e.g. by learning
• CPC Class Codes: B66B 2201/403 by real-time traffic data
• CPC Class Codes: B66B 2201/4638 Wherein the call is registered without making physical contact with the elevator system
• CPC Class Codes: B66B 2201/4653 wherein the call is registered using portable devices
• CPC Class Codes: B66B 5/0012 Devices monitoring the users of the elevator system
• CPC Class Codes: G05B 13/027 using neural networks only
• CPC Class Codes: G05B 13/048 using a predictor

Abstract

A method and system for controlling elevator dispatch is provided. User data, including user behavior, is collected from a number of users over a specified time period. Elevator use data for a number of elevators in a building is also collected over the specified time period. Applying the user data and elevator use data, an elevator dispatch model is constructed that predicts future elevator use according to predicted user needs. An elevator control system dispatches the elevators according to the dispatch model. The elevator dispatch model is refined according to feedback data collected from users over a subsequent time period.

Claims

1. A method of controlling elevator dispatch, comprising:

collecting, by a number of input devices, user data from a number of users, wherein the user data includes user behavior over a specified time period;

collecting, by an elevator control system, elevator use data for a number of elevators in a building over the specified time period;

constructing, by a number of processors applying the user data and elevator use data, an elevator dispatch model that predicts future elevator use according to predicted user needs;

dispatching, by the elevator control system, the elevators according to the dispatch model; and

refining, by a number of processors, the elevator dispatch model according to feedback data collected from users over a subsequent time period.

2. The method of claim 1, wherein the feedback data comprises feedback provided directly by users.

3. The method of claim 1, wherein the feedback data comprises indirect feedback extrapolated from user behavior.

4. The method of claim 1, wherein the elevator dispatch model is constructed using at least one of:

a neural network; and

a machine learning algorithm.

5. The method of claim 1, wherein the user data further comprises at least one of:

height;

weight;

gender;

age;

movement speed;

objects to be transported by the user;

predicted departure from the building;

predicted arrival at the building;

urgency of elevator use; and

sensitivity to ambient noise.

6. The method of claim 1, wherein the input devices include at least one of:

mobile telephone;

cameras;

mobile application;

motion sensors; and

internet enabled appliances.

7. The method of claim 1, wherein the elevator dispatch model is constructed and refined using a number of the following factors:

predicted elevator traffic;

predicted intent of elevator trip;

user preference;

user feedback;

user personal information;

real-time user behavior;

real-time elevator use data; and

historical elevator use data.

8. A system for controlling elevator dispatch, comprising:

an elevator control system configured to control movements of a number of elevators in a building and collect data about elevator use;

a bus system in communication with the elevator control system;

an input system connected to the bus system, wherein the input system is configured to receive data from a number of input devices;

a storage device connected to the bus system, wherein the storage device is configured to store input data and program instructions; and

a number of processors connected to the bus system, wherein the processors execute the program instructions to;

collect user data provided by the input system about a number of users, wherein the user data includes user behavior over a specified time period;

collect elevator use data for the elevators in the building over the specified time period;

construct, by applying the user data and elevator use data, an elevator dispatch model that predicts future elevator use according to predicted user needs;

dispatch the elevators in the building according to the dispatch model; and

refine the elevator dispatch model according to user feedback data provided by the input system over a subsequent time period.

9. The system of claim 8, wherein the feedback data comprises feedback provided directly by users and indirect feedback extrapolated from user behavior.

10. The system of claim 8, wherein the elevator dispatch model is constructed using at least one of:

a neural network; and

a machine learning algorithm.

11. The system of claim 8, wherein the user data further comprises at least one of:

height;

weight;

gender;

age;

movement speed;

objects to be transported by the user;

predicted departure from the building;

predicted arrival at the building;

urgency of elevator use; and

sensitivity to ambient noise.

12. The system of claim 8, wherein the input devices include at least one of:

mobile telephone;

cameras;

mobile application;

motion sensors; and

internet enabled appliances.

13. The system of claim 8, wherein the elevator dispatch model is constructed and refined using a number of the following factors:

predicted elevator traffic;

predicted intent of elevator trip;

user preference;

user feedback;

user personal information;

real-time user behavior;

real-time elevator use data; and

historical elevator use data.

14. A computer program product for controlling elevator dispatch, comprising, the computer program product comprising a non-volatile computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform the steps of:

collecting user data from a number of users, wherein the user data includes user behavior over a specified time period;

collecting elevator use data for a number of elevators in a building over the specified time period;

constructing, by applying the user data and elevator use data, an elevator dispatch model that predicts future elevator use according to predicted user needs;

dispatching the elevators according to the dispatch model; and

refining the elevator dispatch model according to feedback data collected from users over a subsequent time period.

15. The computer program product of claim 14, wherein the feedback data comprises feedback provided directly by users.

16. The computer program product of claim 14, wherein the feedback data comprises indirect feedback extrapolated from user behavior.

17. The computer program product of claim 14, wherein the elevator dispatch model is constructed using at least one of:

a neural network; and

a machine learning algorithm.

18. The computer program product of claim 14, wherein the user data further comprises at least one of:

height;

weight;

gender;

age;

movement speed;

objects to be transported by the user;

predicted departure from the building;

predicted arrival at the building;

urgency of elevator use; and

sensitivity to ambient noise.

19. The computer product of claim 14, wherein the input devices include at least one of:

mobile telephone;

cameras;

mobile application;

motion sensors; and

internet enabled appliances.

20. The computer program product of claim 14, wherein the elevator dispatch model is constructed and refined using a number of the following factors:

predicted elevator traffic;

predicted intent of elevator trip;

user preference;

user feedback;

user personal information;

real-time user behavior;

real-time elevator use data; and

historical elevator use data.