Smart Skills Centre
SERIES 4.0 FEATURE COMING SOON |
Overview
The ControliQ Smart skills Centre allows you to set skill level targets for the core tasks completed in your workgroup. This allows you to manage flexibility and contingency to ensure that you have enough skilled team members to complete the required volumes of core work.
You set the targets for the number of team members you require with skills for each task and based on their recent performance when completing the tasks the Smart Skills Centre will provide you with a view of how you are progressing against those targets every month.
To utilise the Smart Skills Centre, you first need to set targets for each of your workgroups core tasks. This target indicates how many team members you require with skills in each task to manage demand.
Search
Core Tasks
Current No. of Skilled Staff
Target
Last Updated
|
Once you have set your targets you can review current progress against them in more detail using the Catalogue. This details the teams progress against target and the individual team members that have skills in each task. When reviewing this data, you have 2 options on how the data will be displayed.
The Core Task View will display the teams progress against targets for each task at the highest level.
View By
Search
Filter
Core Task
Team Target
Last Updated
|
Selecting the icon next to a Core Task name will expand the data further to display the team members linked to the selected workgroup and their skills in that task.
Name
Smart Skill
Confidence Level
Last Completed
Auto Update
Skill Level
Skill Filters
|
The Staff Member View will display the staff members skill in each core task linked to the workgroup at the highest level.
View By
Search
Filter
Staff Member
Last Updated
|
Selecting the icon next to a Team Members name will expand the data further to display the Core Tasks linked to the selected workgroup and their skills in that task.
Task
Team Target
Smart Skill
Confidence Level
Last Completed
Auto Update
Skill Level
|
The skills distribution section of the overview tab gives you a view of the overall skill levels of the team members linked to the selected workgroup across the past 6- or 12-month period. The chart illustrates if the overall skill levels of the team are increasing or decreasing.
Workgroup
Core Tasks
Period
Median Skill Level and Month
|
The Team Targets section of the Overview tab allows you to see how the selected workgroup are progressing against the skills targets they set for their core tasks.
Overview Tiles
Sort By
Core Task Progress to Target
|
Smart Skill levels are based on the previous 90 days of data, and will consider both estimated Task Productivity, and Quality scores if these are recorded for individual team members in ControliQ.
In ControliQ, there are many methods to capturing data. As a result, we cannot simply measure the time between a user hitting +1 in RTM to understand Task Productivity. As an accurate and consistent alternative, we estimate task productivity with the help of machine learning algorithms.
Task Productivity is derived from using the total Core Time for the day, and the history of Work Out recorded that day. This logic is then applied across the entire 90-day period analysed.
Equation: Task Productivity = Task Work Out / Task Core Time
Step 1 Estimate
To solve the equation above, we need to know the Task Core Time.
To do this, we start the estimation process with an initial estimate of 100% Task Productivity for every task.
Steps 2 to 4 Test, Improve and Optimise
Using this initial estimation, we can solve equation (above), and then sum together all of the Task Core Time values for the day and see how close it is to the actual Daily Core Time.
After observing the difference, we iteratively improve on this estimate of 100% Task Productivity, so that the difference in the sum of all Task Core Time and actual Daily Core Time is as close to 0 as possible.
This process of iteratively improving the Task Productivity values and re-testing the difference is made possible using our machine learning algorithm.
The machine learning algorithm will loop through this process, learning with every attempt if the result is getting closer to 0 and will adjust the estimation accordingly. This process will continue until the most stable and best fit result is found. The end result is the most optimal Task Productivity for each task.
To provide the final Smart Skill, we forecast the estimated Task Productivity for the upcoming month using a special moving average. The result is then factored by the ControliQ quality score (if applicable), before being associated with a Skill Banding to derive the Smart Skill of each Staff Member, for each Core Task.
Achieved Task Productivity Range | Suggested Smart Skill Level |
---|---|
0 Staff member has not completed this task | - |
<10% | 1 |
10% - 20% | 2 |
21% - 30% | 3 |
31% - 40% | 4 |
41% - 60% | 5 |
61% - 80% | 6 |
81% - 100% | 7 |
101% - 120% | 8 |
121% - 150% | 9 |
> 150% | 10 |