When I was asked to write an article on data collection software for Quality, I had to pause and think about what exactly data collection is without data analysis and actions. Data collection can only be determined by understanding the resulting actions desired after data analysis.
Today we are bombarded by data from the time we wake up until the time we go to sleep, and we are constantly absorbing it, analyzing it, and making decisions about our lives. The data comes to us through our phones, our computers, the television, conversations with colleagues and friends, and based on that data we make choices or decisions.
In business, we collect data using surveys, measurements, and observations, and from on-line automated sources such as application programming interfaces (APIs). We also collect data based on the analysis of said data that we’ve already collected. This type of analyzed data is generally used to make decisions, such as opportunities for improvement, adjustments to the processes, or in severe cases, rework, and recall.
There are many different methods for collecting the data in an organization, and when I google “data collection software”, it seems like there are endless solutions for all industries. I don’t think any one solution for data collection is better than another, but I do believe that specific types of data collection methods would be preferable for an organization once they have analyzed the type of data required to meet the types of actions or interventions desired.
Rather than focusing on existing data collection methods, I prefer to look at the future of data collection, data analysis, and the resulting actions or interventions. Therefore, I would like to write about the elephant in the room – and that elephant is AI (artificial intelligence).
Artificial intelligence has landed on our doorstep and will change the complete environment of data collection, data analysis, and real-time action. Not only has AI landed, but it is also here to stay, and parts can be used immediately.
AI will provide us with real time measurement and data collection, analysis and then immediate intervention to prevent any out of tolerance conditions. As we inch closer to integrating cameras, machines and servers that can learn and intervene, quality management will become one hundred percent process driven and I suspect nonconformances will eventually be eliminated.
For this to happen, companies must start planning for this inevitable future by investing in the required infrastructure. As a consultant and working with my programmers, I understand that this will involve moving towards a data lakehouse.
However, AI has some immediate offerings for quality management that can be used today. Many organizations struggle with root cause analysis even though there are tools to help them, such as fishbone diagrams and the five whys. Now, there is a new tool, and it is an AI that can be used to help determine the root cause of nonconformities. It’s like having an expert on your team.
For example, I used BING Chat (AI) for a Corrective Action Process to help determine the root cause of a problem experienced by one of my clients, Company ABC, using their real-life corrective action request. I basically copied and pasted the problem description and containment from their Corrective Action Request Form into BING Chat and asked two questions. In less than five seconds, I was presented with answers.
Problem Description: Welding rods were found in the welding department without the material lot number during an internal audit. We tagged them and removed them from the department and put them into quarantine. We recalled the products welded with these rods to have them analyzed for material chemistry.
Question 1: Please comment.
AI Comment: It sounds like you took the appropriate steps to ensure the quality and safety of your products. Is there anything specific you would like to know or discuss about this situation?
Question 2: Please suggest the five whys to determine the root cause.
AI 5-Whys: Sure! The Five Whys is a problem-solving technique that involves asking a series of “Why” questions to identify the root cause of an issue. Here are some example questions you could ask to help find the root cause of the welding rods being found without a material lot number:
- Why were the welding rods found without a material lot number?
- Why was the material lot number not recorded or attached to the welding rods?
- Why was this not caught earlier in the process?
- Why was there no system in place to ensure that all welding rods have a material lot number?
- Why was this system not implemented or followed?
By asking these questions and digging deeper into each answer, you may be able to identify the root cause of the issue and take steps to prevent it from happening again in the future.
Starting today, any company can make use of AI Chats to help solve existing problems using their current data and quality management systems. Furthermore, AI Chat can help write procedures, workflow processes, and even suggest the data to be collected for any given process.
But . . . the more important challenge is to start planning for AI integration into your processes to enable real-time data collection, analysis, and intervention to ensure a consistent process without deviation.
