System and method for wearable indication of personal risk within a workplace

• US 10,032,352 B2
• Filed: 02/27/2017
• Issued: 07/24/2018
• Est. Priority Date: 12/09/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Kozloski, James R., Lynar, Timothy M., Ortiz, Jorge A. M., Wagner, John M.
• Primary Examiner(s): Swarthout, Brent
• Application Number:
  US15/443,394
• Publication Number:
  US 20170169687A1
• Time in Patent Office: 512 Days
• Field of Search: 34053911
• CPC Class Codes: F16P 3/142 using image capturing devices
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 10/0635 Risk analysis of enterprise or organisation activities
• CPC Class Codes: G08B 21/02 Alarms for ensuring the safety of persons
• CPC Class Codes: G08B 21/0453 worn on the body to detect health condition by physiological monitoring, e.g. electrocardiogram, temperature, breathing detecting, measuring or recording for diagnostic purposes A61B5/00
• CPC Class Codes: G08B 21/0492 Sensor dual technology, i.e. two or more technologies collaborate to extract unsafe condition, e.g. video tracking and RFID tracking
• CPC Class Codes: G08B 7/06 using electric transmission , e.g. involving audible and visible signalling through the use of sound and light sources

Abstract

Described herein is a method for alerting of personal risk in the workplace through a wearable indication signifying a risk condition that includes generating a set of workplace predictors of risk relating to accidents, injury, and industrial hygiene, based on at least one worker state that includes at least one of a physical state, a cognitive state, and an emotional state, and alerting a worker endangered by a predicted elevated risk to the existence of the predicted elevated risk by sending a perceivable alert to the worker. A system for alerting of personal workplace risk is also described.

Claims

1. A method for alerting of personal risk in the workplace, comprising:

generating, in computer memory, a set of workplace predictors of risk relating to accidents, injury, and industrial hygiene events based on at least one worker state that includes an emotional state, based on collected information including at least video data to identify one or more emotional traits utilizing a feature extraction technique, by compiling a sequence of states;

determining the existence of an elevated risk utilizing the set of workplace predictors;

identifying workers affected by the elevated risk; and

communicating to the identified workers the existence of the elevated risk through a signal sent to a wearable item on each of the identified workers.

2. The method of claim 1, further comprising:

communicating an instruction from a workplace machine manager to a workplace machine the predicted elevated risk.

3. The method of claim 2, wherein the instruction causes the workplace machine to modify an operation.

4. The method of claim 1, wherein the set of workplace predictors are generated by developing a cognitive suite of workplace hygiene and injury predictors comprising:

categorizing worker states using unsupervised learning from video data and personal wearable data collector analysis;

categorizing sequences of worker states using supervised learning to determine the sequences of worker states that were relevant to an accident event to predict a future accident event; and

compiling the sequence of states that are predictive of an industrial hygiene or workplace injury event from the categorizing of worker states using unsupervised learning and the categorizing of sequences of worker states using supervised learning.

5. The method of claim 1, wherein the at least one worker state further includes a physical state and a cognitive state.

6. The method of claim 1, further comprising communicating an instruction to a machine operated by at least one of the identified workers to modify machine operation as a result of the predicted elevated risk.

7. The method of claim 1, further comprising:

determining a respective worker risk profile and machine use profile for each worker in a set of workers; and

determining one or more areas of training for at least one worker in the set that is appropriate to the worker risk profile and machine use profile for the at least one worker.

8. A system for alerting of personal risk in the workplace, comprising:

one or more servers having a processor;

a workplace hygiene and injury predictor, for predicting a risk of accidents, injury, and industrial hygiene events in the workplace through consideration of categorized information on worker states obtained by unsupervised learning and supervised learning;

an elevated risk determiner, for determining the existence of a predicted risk of an accident, injury, or industrial hygiene event based on at least one worker state that includes an emotional state, based on collected information including at least video data to identify one or more emotional traits utilizing a feature extraction technique, determining the existence of an elevated risk utilizing the workplace hygiene and injury predictors, identifying workers affected by the elevated risk other than the worker responsible for the elevated risk; and

a worker warning manager for sending an instruction to a wearable device on each of the identified workers, wherein the instruction causes each wearable device to generate a perceivable alert.

9. The system of claim 8, wherein the workplace hygiene and injury predictor further comprises a compiler, for compiling a cognitive suite of workplace hygiene and injury predictors generated by:

categorizing worker states using unsupervised learning from video data and personal wearable instrumentation analysis;

categorizing sequences of worker states using supervised learning to determine the corresponding sequences of worker states that were relevant to an accident event to predict a future accident event; and

compiling the sequence of states that are predictive of an industrial hygiene or workplace injury event from the categorizing of worker states using unsupervised learning and the categorizing of sequences of worker states using supervised learning.

10. The system of claim 8, further comprising a video data collector and a worker personal information collector, for collecting information on worker states.

11. The system of claim 8 further comprising a work place machine manager, wherein the workplace machine manager sends instructions to a workplace machine based on a risk profile of a worker.

12. The system of claim 8, further comprising a workplace machine manager, for modifying operation of a workplace machine during a predicted elevated risk condition.

13. The system of claim 8, further comprising a workplace machine manager, for authorizing a workplace machine to return to normal operation when a predicted elevated risk subsides.

14. The system of claim 8, wherein a controller implements decisions made by the worker warning manager.

15. A computer program product alerting of personal risk in the workplace to a worker, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:

generating a set of workplace predictors of risk relating to accidents, injury, and industrial hygiene, based on at least one worker state that includes a cognitive state and an emotional state, based on collected information including at least video data, by compiling a sequence of states that are predictive of an industrial hygiene or workplace injury event;

determining the existence of an elevated risk utilizing the set of workplace predictors;

identifying workers affected by the elevated risk; and

sending an instruction to a wearable device on each of the identified workers.

16. The computer program product of claim 15, wherein the program instructions executable by a computer cause the computer to perform the method including communicating by a workplace machine manager to a workplace machine a predicted elevated risk.

17. The computer program product of claim 15, wherein the program instructions executable by a computer cause the computer to perform the method including generating a set of workplace predictors, wherein the at least one worker state further includes a physical state.

18. The computer program product of claim 15, wherein the program instructions executable by a computer cause the computes to perform the method that includes generating a set of workplace predictors by:

categorizing worker states using unsupervised learning from video data and personal wearable instrumentation analysis;

categorizing sequences of worker states using supervised learning to determine the corresponding sequences of worker states that were relevant to an accident event to predict a future accident event; and

compiling the sequence of states that are predictive of an industrial hygiene or workplace injury event from the categorizing of worker states using unsupervised learning and the categorizing of sequences of worker states using supervised learning.

19. The computer program product of claim 15, wherein the program instructions executable by a computer cause the computer to perform the method including a workplace machine manager authorizing a workplace machine to return to normal operation when a predicted elevated risk subsides.

20. The computer program product of claim 15, wherein the program instructions executable by a computer further comprise communicating an instruction to a machine operated by a worker to modify machine operation as a result of the predicted elevated risk.