Risk-aware management of elevator operations

Patent metadata

Field	Value
Publication number	US-10544007-B2
Application number	US-201715467619-A
Country	US
Kind code	B2
Filing date	Mar 23, 2017
Priority date	Mar 23, 2017
Publication date	Jan 28, 2020
Grant date	Jan 28, 2020

Abstract

Embodiments of the invention are directed to computer-implemented methods, computer systems, and computer program products for operating an elevator car. The method includes receiving first inputs from one or more sensors. The method further includes receiving second inputs from one or more cameras. The method further includes determining the presence of a passenger on the elevator using the first inputs and the second inputs. The method further includes determining a set of characteristics related to the passenger using the first inputs and the second inputs. The method further includes predicting a set of predicted actions of the passenger, using machine-learning techniques. The method further includes determining an action to perform based on the set of predicted actions.

First claim

What is claimed is:

1. A computer-implemented method for operating an elevator car, the method comprising:
receiving, by a processor, first inputs from one or more sensors;
receiving, by the processor, second inputs from one or more cameras;
determining, by the processor, the presence of a known passenger on the elevator using the first inputs and the second inputs;
retrieving, by the processor, a set of attributes related to the known passenger from a knowledge base,
wherein the set of attributes includes at least one of health, age, and interests;
determining, by the processor, a set of characteristics related to the known passenger using the first inputs and the second inputs,
wherein the set of characteristics includes at least one of clothing, height, weight, and gender;
predicting, by the processor, a set of predicted actions of the known passenger, using machine-learning techniques;
determining, by the processor, an action to perform based at least in part on the set of predicted actions,
wherein the action comprises customizing and displaying content based on the set of attributes;
identifying, by repeated actions observed from the second inputs, distinguishing marks of a personal belonging associated with the known passenger; and
in response to receiving an indication that the personal belonging is missing, transmitting information on a suspect passenger observed, from the second inputs, with the personal belonging to a law enforcement agency.

2. The computer-implemented method of claim 1 further comprising:
determining, by the processor, that the known passenger requires assistance; wherein:
the action to perform comprises contacting emergency authorities.

3. The computer-implemented method of claim 2 wherein:
determining that the known passenger requires assistance comprises:
analyzing the first inputs;
analyzing the second inputs; and
comparing the first inputs and second inputs to a historical knowledge base of historical first inputs and second inputs to compute a predicted action of the known passenger to determine that the known passenger requires assistance.

4. The computer-implemented method of claim 2 wherein:
determining that the known passenger requires assistance comprises comparing the inputs from the one or more sensors and the inputs from the one or more cameras to a knowledge base that includes known passenger conditions.

5. The computer-implemented method of claim 4 wherein the inputs from the one or more sensors includes biometric data.

6. The computer-implemented method of claim 1 further comprising:
determining, by the processor, that a passenger is an unknown passenger;
using, by the processor, facial recognition techniques to compare the set of characteristics of the unknown passenger to characteristics of persons of interest.

7. The computer-implemented method of claim 6 wherein:
the action to perform comprises contacting emergency authorities.

8. The computer-implemented method of claim 6 wherein:
the action to perform comprises ceasing the operation of the elevator car in which the unknown person is present.

9. The computer-implemented method of claim 1 further comprising:
comparing, by the processor, performance of the elevator car at a current time to performance of the elevator at a previous time to determine a decrease in performance; wherein:
the action to perform is requesting maintenance of the elevator car.

10. A computer system for operating an elevator car, the system comprising:
a memory; and
a processor system communicatively coupled to the memory;
the processor system configured to:
receive first inputs from one or more sensors; and
receive second inputs from one or more cameras;
determine the presence of a known passenger on the elevator using the first inputs and the second inputs,
retrieve a set of attributes related to the known passenger from a knowledge base,
wherein the set of attributes includes at least one of health, age, and interests;
determine a set of characteristics related to the known passenger using the first inputs and the second inputs,
wherein the set of characteristics includes at least one of clothing, height, weight, and gender;
predict a set of predicted actions of the known passenger, using machine-learning techniques;
determine an action to perform based on the set of predicted actions,
wherein the action comprises customizing and displaying content based on the set of attributes;
identifying, by repeated actions observed from the second inputs, distinguishing marks of a personal belonging associated with the known passenger; and
in response to receiving an indication that the personal belonging is missing, transmitting information on a suspect passenger observed, from the second inputs, with the personal belonging to a law enforcement agency.

11. The computer system of claim 10 wherein the processor is further configured to:
determine that the known passenger requires assistance; wherein:
the action to perform comprises contacting emergency authorities.

12. The computer system of claim 11 wherein:
determining that the known passenger requires assistance comprises:
analyzing the first inputs;
analyzing the second inputs; and
comparing the first inputs and second inputs to a historical knowledge base of historical first inputs and second inputs to compute a predicted action of the known passenger to determine that the known passenger requires assistance.

13. The computer system of claim 11 wherein:
determining that the known passenger requires assistance comprises comparing the inputs from the one or more sensors and the inputs from the one or more cameras to a knowledge base that includes known passenger conditions.

14. The computer system of claim 13 wherein the inputs from the one or more sensors includes biometric data.

15. The computer system of claim 10 wherein the processor is further configured to:
determine that a passenger is an unknown passenger;
use facial recognition techniques to compare the set of characteristics of the unknown passenger to characteristics of persons of interest.

16. The computer system of claim 15 wherein:
the action to perform comprises contacting emergency authorities.

17. The computer system of claim 15 wherein:
the action to perform comprises ceasing the operation of the elevator car in which the unknown person is present.

18. A computer program product comprising:
a computer-readable storage medium having program instructions embodied therewith, the program instructions readable by a processor system to cause the processor system to perform a method comprising:
receiving first inputs from one or more sensors;
receiving second inputs from one or more cameras;
determining the presence of a known passenger on the elevator using the first inputs and the second inputs;
retrieving, by the processor, a set of attributes related to the known passenger from a knowledge base,
wherein the set of attributes includes at least one of health, age, and interests;
determining a set of characteristics related to the known passenger using the first inputs and the second inputs,
wherein the set of characteristics includes at least one of clothing, height, weight, and gender;
predicting a set of predicted actions of the known passenger, using machine-learning techniques;
determining an action to perform based on the set of predicted actions,
wherein the action comprises customizing and displaying content based on the set of attributes;
identi

Assignees

• IBM

Inventors

• Hwang Jinho
• Tak Byungchul
• Vukovic Maja

Classifications

• G06N20/10

  using kernel methods, e.g. support vector machines [SVM] · CPC title

• B66B5/025

  where the abnormal operating condition is caused by human behaviour or misbehaviour, e.g. forcing the doors · CPC title

• G06N5/02

  Knowledge representation; Symbolic representation · CPC title

• B66B5/0012 Primary

  Devices monitoring the users of the elevator system · CPC title

• B66B2201/4676

  for checking authorization of the passengers · CPC title