Machine learning task assignment

Patent metadata

Field	Value
Publication number	US-2019295013-A1
Application number	US-201815935211-A
Country	US
Kind code	A1
Filing date	Mar 26, 2018
Priority date	Mar 26, 2018
Publication date	Sep 26, 2019
Grant date	—

Abstract

A method and system for improving a machine learning task assignment process is provided to address productivity with respect to satisfaction. The method includes connecting hardware devices to a server system. Job related data associated with job roles for individuals is retrieved and associated with a time period. Work related items of the job related data are presented and selections for work related items are retrieved via selectors for the work items. Expected and actual satisfaction ratings for the work related items are received and analyzed in accordance with an order in which they are received. At least one work item is assigned to a user and a specialized memory repository is generated within a portion of a memory device. Results of the assignment are stored within the specialized memory repository. Self-learning software code for executing future task assignment processes is generated and modified based on reported satisfaction ratings.

First claim

What is claimed is:

1 . A machine learning task assignment improvement method comprising:
connecting, by one or more, a hardware device and additional hardware devices to a remote server database system; retrieving, by said one or more processors from said remote server database system, job related data associated with job roles for a plurality of users; initially assigning to said plurality of users, by said one or more processors in response to a command from an authoritative source, work related items of said job related data; presenting, by said one or more processors to a user of said plurality of users, said work related items of said job related data to be performed during a specified time period; receiving, by said one or more processors from said user via sensors of said hardware device, selections for specified work related items of said work related items; receiving, by said one or more processors from additional users of said plurality of users via additional sensors of said additional hardware devices, additional selections for additional work related items of said work related items; receiving, by said one or more processors from said user and said additional users, expected satisfaction ratings for said specified work related items and said additional work related items; first analyzing, by said one or more processors, said selections and said additional selections with respect to said expected satisfaction ratings; first assigning to said user, by said one or more processors based on results of said first analyzing, at least one work item of said selections; second assigning to said additional users, by said one or more processors based on said results of said first analyzing, additional work related items of said additional selections; receiving, by said one or more processors from said user and said additional users, actual satisfaction ratings for said specified work related items and said additional work related items; second analyzing, by said one or more processors, said first selections and said additional selections with respect to said actual satisfaction ratings; generating, by said one or more processors, a specialized memory repository within a specified portion of a hardware memory device; storing, by said one or more processors within said specialized memory repository, results of said first assigning and said second assigning; generating, by said one or more processors from said results of said first assigning, said second assigning, said first analyzing, and said second analyzing, self-learning software code for executing future task assignment processes; and modifying, by said one or more processors based on results of said future task assignment processes, said self-learning software code.

2 . The method of claim 1 , further comprising:
encrypting, by said one or more processors, said self-learning software code resulting in an encrypted self-learning software application; and transmitting, by said one or more processors, said encrypted self-learning software application to said remote server database system.

3 . The method of claim 1 , further comprising:
automatically detecting, by said one or more processors via said sensors and said additional sensors, biometric levels of said user and said additional users, wherein said biometric levels are associated with said expected satisfaction ratings; and automatically detecting, by said one or more processors via said sensors and said additional sensors, additional biometric levels of said user and said additional users, wherein said additional biometric levels are associated with said actual satisfaction ratings; and wherein said first assigning and said second assigning are further based on said biometric levels and said additional satisfaction levels.

4 . The method of claim 3 , further comprising:
associating, by said one or more processors, a specified time period with said job related data; automatically updating, by said one or more processors based on said biometric levels, said self-learning software code.

5 . The method of claim 1 , further comprising:
automatically detecting by said one or more processors, a calibration error of at least one sensor of said sensors and said additional sensors; and automatically calibrating, by said one or more processors, said at least one sensor.

6 . The method of claim 5 , wherein said automatically calibrating comprises calibrating software of said at least one sensor.

7 . The method of claim 5 , wherein said automatically calibrating comprises calibrating hardware of said at least one sensor.

8 . The method of claim 1 , further comprising:
receiving, by said one or more processors from said user and said additional users via a specialized graphical user interface, feedback data associated with said expected satisfaction ratings and said expected satisfaction ratings, wherein said first assigning and said second assigning are further based on said feedback data.

9 . The method of claim 8 , further comprising:
automatically updating, by said one or more processors based on said feedback data, said self-learning software code.

10 . The method of claim 1 , further comprising:
providing at least one support service for at least one of creating, integrating, hosting, maintaining, and deploying computer-readable code in the control hardware, said code being executed by the computer processor to implement: said connecting, said retrieving, said initially assigning, said presenting, said receiving said selections, said receiving said additional selections, said receiving said expected satisfaction ratings, said first analyzing, said first assigning, said second assigning, said receiving said actual satisfaction ratings, said second analyzing, said generating said specialized memory repository, said storing, said generating said self-learning software code, and said modifying.

11 . A computer program product, comprising a computer readable hardware storage device storing a computer readable program code, said computer readable program code comprising an algorithm that when executed by one or more processors implements a machine learning machine learning task assignment improvement method, said method comprising:
connecting, by said one or more processors a hardware device and additional hardware devices to a remote server database system; retrieving, by said one or more processors from said remote server database system, job related data associated with job roles for a plurality of users; initially assigning to said plurality of users, by said one or more processors in response to a command from an authoritative source, work related items of said job related data; presenting, by said one or more processors to a user of said plurality of users, said work related items of said job related data to be performed during a specified time period; receiving, by said one or more processors from said user via sensors of said hardware device, selections for specified work related items of said work related items; receiving, by said one or more processors from additional users of said plurality of users via additional sensors of said additional hardware devices, additional selections for additional work related items of said work related items; receiving, by said one or more processors from said user and said additional users, expected satisfaction ratings for said specified work related items and said additional work related items; first analyzing, by said one or more processors, said selections and said additional selections with respect to said expected satisfaction ratings; first assigning to said user, by said one or more

Assignees

• IBM

Inventors

• Lhota Colleen
• Silva Ashley K
• Davis Aksel
• Sese Jocelyn

Classifications

• G06N20/00

  Machine learning · CPC title

• G06Q10/06311 Primary

  Scheduling, planning or task assignment for a person or group · CPC title

• G06F16/27

  Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor · CPC title

• G06F8/65

  Updates (security arrangements therefor G06F21/57) · CPC title

• G06N99/005

  Physics · mapped topic