IP Library Granted Patent US 11,657,345
Granted Patent B2
US 11,657,345 · App. 17/210,790 · Granted May 23, 2023

Implementing machine learning to identify, monitor and safely allocate resources to perform a current activity

Inventors: Jennifer M. Hatfield (San Francisco, CA); Jill S. Dhillon (Laguna Niguel, CA); Michael Bender (Rye Brook, NY); Stan Kevin Daley (Atlanta, GA); Jeremy R. Fox (Georgetown, TX)
Assignee: International Business Machines Corporation
G06Q10/06313G06N20/00G06Q10/067G06Q10/0635G06Q10/063112G06Q10/063114G06Q10/063118G06Q10/103
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,657,345
App. No.
17/210,790
Granted
May 23, 2023
Kind
B2
Abstract

In an approach to resource monitoring and allocation recommendation, a computer determines a work activity for a risk assessment. A computer determines one or more resources assigned to the work activity. A computer determines one or more current activities associated with the one or more resources assigned to the work activity. Based on the one or more resources assigned to the work activity and on the one or more current activities associated with the one or more resources assigned to the work activity, a computer determines a confidence level associated with successful completion of the work activity. A computer determines the confidence level does not exceed a pre-defined threshold. A computer determines one or more resource scenarios to improve the confidence level. A computer ranks the one or more resource scenarios. A computer generates a resource allocation recommendation based on the ranked one or more resource scenarios.

Claims (55)

1. A computer implemented method for implementing machine learning in identifying and safely allocating resources to perform a current activity, the computer implemented method comprising:

deploying, on an internet of things platform, a plurality of interconnected sensors comprising: a biometric sensor for detecting a physical condition of a resource, a GPS enabled sensor for identifying a location of the resource, and an air temperature sensor for measuring a current air temperature of an environment in which the resource is located;

determining, by a resource recommendation program executed by one or more hardware processors and coupled to the internet of things platform via a multimedia network, requirements for completing a current activity comprising: required skills, a location where the current activity will be performed, and a deadline associated with completing the current activity;

determining, by the resource recommendation program, respective availability and location of a plurality of resources;

mapping, by the resource recommendation program, the required skills to those skills of the available resources, to predict that the resource among the available resources will be assigned to the current activity;

identifying, using the GPS enabled sensor, that the resource is located near the current activity and is able to perform the current activity;

measuring and recording, by the air temperature sensor, the current air temperature of the environment in which the resource is located;

assessing, by the resource recommendation program, a health status of the resource via the plurality of sensors;

predicting, by the resource recommendation program, a duration of the resource staying at the location of the resource based on physicality factors, historical endurance samples, environmental factors and previously performed similar activities;

determining, by the resource recommendation program using the air temperature sensor, that the resource does not work well in the environment with the current air temperature;

determining, using machine learning, by the resource recommendation program, that a confidence level of the resource in completing the current activity when compared to the previously performed similar activities does not exceed a pre-determined confidence level;

postponing the current activity in the environment, until the current air temperature of the environment is determined safe to perform the current activity;

evaluating, by the resource recommendation program, a plurality of permutations of the plurality of available resources according to a work history of the plurality of available resources, to identify allocation scenarios for additional resources, among the plurality of available resources, to be allocated to the resource in order to speed up progress in meeting the deadline and increase the confidence level in completing the current activity;

ranking, by the resource recommendation program, the allocation scenarios to generate a recommendation for allocating the additional resources to the resource, based on the evaluation, the determined safety, and the health status of the resource as the current activity progresses.

2. The computer implemented method of claim 1 , wherein the additional resources comprise: at least one of a human resource and a physical resource.

3. The computer implemented method of claim 1 , further comprising:

determining, by the resource recommendation program, one or more future activities associated with the plurality of available resources.

4. A system for implementing machine learning in identifying and safely allocating resources to perform a current activity, the system comprising:

one or more hardware processors;

an internet of things platform, configure to enable:

deploying, a plurality of interconnected sensors comprising: a biometric sensor for detecting a physical condition of a resource, a GPS enabled sensor for identifying a location of the resource, and an air temperature sensor for measuring a current air temperature of an environment in which the resource is located;

a resource recommendation program executed by the one or more hardware processors and coupled to the internet of things platform via a multimedia network, for:

determining, requirements for completing a current activity comprising:

required skills, a location where the current activity will be performed, and a deadline associated with completing the current activity;

determining, respective availability and location of a plurality of resources;

mapping, the required skills to those skills of the available resources, to predict that the resource among the available resources will be assigned to the current activity;

identifying, using the GPS enabled sensor, that the resource is located near the current activity and is able to perform the current activity;

measuring and recording, using the air temperature sensor, the current air temperature of the environment in which the resource is located;

assessing, a health status of the resource via the plurality of sensors;

predicting, a duration of the resource staying at the location of the resource based on physicality factors, historical endurance samples, environmental factors and previously performed similar activities;

determining, using the air temperature sensor, that the resource does not work well in the environment with the current air temperature;

determining, using machine learning, that a confidence level of the resource in completing the current activity when compared to the previously performed similar activities does not exceed a pre-determined confidence level;

postponing the current activity in the environment, until the current air temperature of the environment is determined safe to perform the current activity;

evaluating, a plurality of permutations of the plurality of available resources according to a work history of the plurality of available resources, to identify allocation scenarios for additional resources, among the plurality of available resources, to be allocated to the resource in order to speed up progress in meeting the deadline and increase the confidence level in completing the current activity;

ranking, the allocation scenarios to generate a recommendation for allocating the additional resources to the resource, based on the evaluation, the determined safety, and the health status of the resource as the current activity progresses.

5. The system of claim 4 , wherein the additional resources comprise: at least one of a human resource and a physical resource.

6. The system claim 4 , wherein the resource recommendation program is further executed by the one or more hardware processors for:

determining, one or more future activities associated with the plurality of available resources.

7. A computer program product comprising: a computer readable storage medium and program instructions collectively stored on the computer readable storage medium and executed by one or more hardware processors for:

deploying, on an internet of things platform, a plurality of interconnected sensors comprising: a biometric sensor for detecting a physical condition of a resource, a GPS enabled sensor for identifying a location of the resource, and an air temperature sensor for measuring a current air temperature of an environment in which the resource is located;

determining, using a resource recommendation program coupled to the internet of things platform via a multimedia network, requirements for completing a current activity comprising: required skills, a location where the current activity will be performed, and a deadline associated with completing the current activity;

determining, using the resource recommendation program, respective availability and location of a plurality of resources;

mapping, using the resource recommendation program, the required skills to those skills of the available resources, to predict that the resource among the available resources will be assigned to the current activity;

identifying, using the GPS enabled sensor, that the resource is located near the current activity and is able to perform the current activity;

measuring and recording, using the air temperature sensor, the current air temperature of the environment in which the resource is located;

assessing, using the resource recommendation program, a health status of the resource via the plurality of sensors;

predicting, using the resource recommendation program, a duration of the resource staying at the location of the resource based on physicality factors, historical endurance samples, environmental factors and previously performed similar activities;

determining, using the air temperature sensor, that the resource does not work well in the environment with the current air temperature;

determining, using machine learning, by the resource recommendation program, that a confidence level of the resource in completing the current activity when compared to the previously performed similar activities does not exceed a pre-determined confidence level;

postponing the current activity in the environment, until the current air temperature of the environment is determined safe to perform the current activity;

evaluating, using the resource recommendation program, a plurality of permutations of the plurality of available resources according to a work history of the plurality of available resources, to identify allocation scenarios for additional resources, among the plurality of available resources, to be allocated to the resource in order to speed up progress in meeting the deadline and increase the confidence level in completing the current activity;

ranking, using the resource recommendation program, the allocation scenarios to generate a recommendation for allocating the additional resources to the resource, based on the evaluation, the determined safety, and the health status of the resource as the current activity progresses.

8. The computer program product of claim 7 , wherein the additional resources comprise: at least one of a human resource and a physical resource.

9. The computer program product of claim 7 , wherein the instructions are further executed by the one or more hardware processors for:

determining, one or more future activities associated with the plurality of available resources.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 24, 2021
From: HATFIELD, JENNIFER M.; DHILLON, JILL S.; BENDER, MICHAEL; DALEY, STAN KEVIN; FOX, JEREMY R.
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 055698/0660 →
Continuity (1)
Related Publication 20220309425A1 · Sep 29, 2022
Cited By (1)
US 12,619,933