Intelligent career monitoring and correction in a computing environment

Patent metadata

Field	Value
Publication number	US-11301946-B2
Application number	US-201916551446-A
Country	US
Kind code	B2
Filing date	Aug 26, 2019
Priority date	Aug 26, 2019
Publication date	Apr 12, 2022
Grant date	Apr 12, 2022

Abstract

Embodiments for intelligent career planning assessment in a computing environment by a processor. A career planning pathway of a career planning model for a user may be monitored for achieving a career goal. One or more deviations from the career planning pathway may be identified according a user profile, one or more behaviors of the user, one or more environmental factors, or a combination thereof.

First claim

The invention claimed is:

1. A method, by a processor, for intelligent career planning assessment in a computing environment, comprising:
monitoring a career planning pathway of a career planning model for a user for achieving a career goal, wherein the monitoring is inclusive of implementing a topic modeling operation to classify content produced by the user as relevant and non-relevant to a current portion of the career planning pathway;
identifying one or more changes to one or more environmental factors having positive impacts for achieving the career goal or negative impacts that invalidate the career goal;
identifying one or more deviations from the career planning pathway according to a user profile of the user, one or more behaviors of the user, and the one or more environmental factors, wherein at least one of the one or more deviations is identified by determining a weighted sum of a relevance of the content produced by the user and an overlapping coefficient of the sum to the career planning model is above a predefined threshold;
in conjunction with identifying the one or more deviations, determining the one or more deviations as a failure to complete one or more action steps of the career planning pathway over a defined period of time, wherein the defined period of time is an average time period necessary to complete the one or more action steps performed by one or more alternative users having previously achieved the career goal;
executing machine learning logic to generate, according to the identified one or more deviations, one or more recommendations for the user to continue on the career planning pathway or an alternate career planning pathway;
determining those of the one or more recommendations the user accepted and performed, and correlating those of the accepted one or mo re recommendations to a progression of one or more alternative users having similar deviations to the identified one or more deviations from a similar career planning model to the career planning model of the user; and
executing the machine learning logic to iteratively update the career planning model using feedback identified from the correlation, wherein iteratively updating the career planning model using the feedback includes performing the monitoring of the career planning pathway to ascertain a current validity of the career planning pathway, and updating the machine learning logic to refine the career planning model according to the current validity.

2. The method of claim 1 , further including identifying a series of the one or more action steps for achieving one or more achievement stages required by the career planning pathway.

3. The method of claim 1 , further including identifying the one or more deviations as accumulation of one or more non-related action steps that are irrelevant to the career planning pathway.

4. The method of claim 1 , further including executing the machine learning logic to:
suggest one or more alternative career goals;
suggest one or more additional action steps to increase an amount of time required to complete the career goal;
select one or more of a plurality of valid career path trajectories having greater positive impact upon the user for achieving the career goal as compared to alternative ones of the plurality of valid career path trajectories.

5. A system for intelligent career planning assessment in a computing environment, comprising:
one or more computers with executable instructions that when executed cause the system to:
monitor a career planning pathway of a career planning model for a user for achieving a career goal;
identify one or more changes to one or more environmental factors having positive impacts for achieving the career goal or negative impacts that invalidate the career goal;
identify one or more deviations from the career planning pathway according to a user profile of the user, one or more behaviors of the user, and the one or more environmental factors, wherein at least one of the one or more deviations is identified by determining a weighted sum of a relevance of the content produced by the user and an overlapping coefficient of the sum to the career planning model is above a predefined threshold;
in conjunction with identifying the one or more deviations, determine the one or more deviations as a failure to complete one or more action steps of the career planning pathway over a defined period of time, wherein the defined period of time is an average time period necessary to complete the one or more action steps performed by one or more alternative users having previously achieved the career goal;
execute machine learning logic to generate, according to the identified one or more deviations, one or more recommendations for the user to continue on the career planning pathway or an alternate career planning pathway;
determine those of the one or more recommendations the user accepted and performed, and correlating those of the accepted one or more recommendations to a progression of one or more alternative users having similar deviations to the identified one or more deviations from a similar career planning model to the career planning model of the user; and
execute the machine learning logic to iteratively update the career planning model using feedback identified from the correlation, wherein iteratively updating the career planning model using the feedback includes performing the monitoring of the career Planning pathway to ascertain a current validity of the career planning pathway, and updating the machine learning logic to refine the career planning model according to the current validity.

6. The system of claim 5 , wherein the executable instructions further identify a series of the one or more action steps for achieving one or more achievement stages required by the career planning pathway.

7. The system of claim 5 , wherein the executable instructions further identify the one or more deviations as accumulation of one or more non-related action steps that are irrelevant to the career planning pathway.

8. The system of claim 5 , wherein the executable instructions further execute the machine learning logic to:
suggest one or more alternative career goals;
suggest one or more additional action steps to increase an amount of time required to complete the career goal; and
select one or more of a plurality of valid career path trajectories having greater positive impact upon the user for achieving the career goal as compared to alternative ones of the plurality of valid career path trajectories.

9. A computer program product for intelligent career planning assessment by a processor, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:
an executable portion that monitors a career planning pathway of a career planning model for a user for achieving a career goal;
an executable portion that identifies one or more changes to one or more environmental factors having positive impacts for achieving the career goal or negative impacts that invalidate the career goal;
an executable portion that identifies one or more deviations from the career planning pathway according to a user profile of the user, one or more behaviors of the user, and the one or more environmental factors, wherein at least one of the one or more deviations is identified by determining a weighted sum of a relevance of the content produced by the user and an overlapping coefficient of the sum to the career planning model is above a predefined threshold;
an executable portion that, in conjunction with identifying the one or more deviations, determin

Assignees

• IBM

Inventors

• Alkan Oznur
• Botea Adi
• Daly Elizabeth
• Pedemonte Pablo
• Valente Abel Nicolas

Classifications

• G06Q50/2057 Primary

  Career enhancement or continuing education service · CPC title

• G06F16/9536

  Search customisation based on social or collaborative filtering · CPC title

• G06F16/9535

  Search customisation based on user profiles and personalisation · CPC title