AI Lab Assistant for P&G

Share on facebook
Share on twitter
Share on linkedin
Last week, a consortium of large companies, including P&G, DEME, AB Inbev, Puratos, and Solvay, invited 20 AI companies from all over the world to compete at the inQbet hackathon. Faktion won the first prize with its AI lab assistant.
Play Video

Paper note-taking

Current situation

At Procter & Gamble, R&D Lab Assistants are required to take precise notes on the actions they perform while doing an experiment or mixing a batch. They take notes in a paper lab notebook. After the experiment is done, lab assistants should enter the data from the paper lab notebook into an electronic lab notebook, where it is stored for audit, archive, and data collection purposes.

Digital is needed


Only 18% of the electronic lab notebooks are filled in. That makes a huge 82% incompleteness rate. Workers don’t have the time or neglect to enter the information in a digital format. This leaves P&G open to liability and patent discussions, not to mention a missed opportunity to collect valuable data in a usable form that could lead to new insights.

Artificial Intelligence lab assistant


By using Artificial Intelligence, we can have an AI lab assistant that listens to the worker as (s)he narrates what (s)he is doing. The AI automatically transcribes the text and extracts the relevant information such as the different ingredients used, their exact weight, as well as actions like mixing and checking for dissolution.

For the prototype, we used a speech transcription model based on the Google Cloud Speech API. The NLP models were rather basic for the prototype and will be improved in a next iteration.

Next steps

  • Custom speech recognition model
  • Making the AI conversational
  • Better training of entity extraction
  • Field tests
Jos Polfliet
Metamaze CTO
About the author

Originally a mathematician, Jos has lead Machine Learning and AI implementations all over the world. Over the last years, Jos lead the team that was responsible for developing state-of-the-art Faktion NLU models that have consistently beaten big tech players like Google, IBM and Facebook. Furthermore, Jos has created machine learning models for companies like Hyperloop Transportation Technologies and has developed Pearl, the first AI Jury Member in the world.

Related blog posts

We’re super excited about the maturing Reinforcement Learning (RL) field. Faktion is already applying this technique to optimize customers’ processes. Over the past years, RL agents have collected the best human players’ scalps in increasingly complicated games like Go, Starcraft II, and DOTA 2. Not only did these RL agents outplay the best human players, they often did so in their own style, unrestrained by the human preconception of how to win. Who said AI couldn’t be creative?
With the global artificial intelligence (AI) market expected to be at almost $60 billion by 2025, many applications transform everyday life. Organizations seek ways to sustain their competitiveness in the marketplace by using AI to power what people see online, purchase products, and provide personal recommendations. As consumers realize the benefits of AI to them, they are more willing to share personal data, giving businesses a fantastic opportunity to innovate.
Just like you have general purpose clothes for every day use, there also are a wide variety of specialised clothing that are a better fit for certain situations. The same thing is true for Natural Language Processing pipelines, which is what this blog post is about.


Curious to learn what we can do for you?

Scroll to Top

Inquiry for your POC