Using a trained model
The following diagram illustrates how Amazon Lookout for Equipment works at inference time:
Let's dive into the different steps of this pipeline:
- New time series are generated: depending on your use case, you might collect new sensor data directly from your piece of equipment or directly access a piece of software such as a historian.
- As you did at training time, you will need to push this fresh data to a location on Amazon S3 (you will see in the following Configuring a scheduler section how this location is configured).
- Your inference scheduler will be configured to run regularly (for instance, every five minutes or every hour). Each time it wakes up, it will look for fresh data and run it against your trained model. Once the model generates new results, the scheduler will store it in JSON format.
- At the end of each scheduler run, the inference results will be...