Introduction
Built in partnership with NVIDIA and Microsoft, Blueprint accelerates data labeling by helping to find clusters of unidentified, inconsistently, and confusingly named tags.
- It creates order from unstructured data chaos using multiple AI/ML/NLP techniques to automate tag-to-asset mapping.
- It also automates and accelerates the building of data dictionaries, especially when users have over 1,000 tags to map.
Quick Start
To start your tag-to-asset mapping, access the developer page and select TagBERT. ame your mapping and determine the data source you want to use as a sample. You can either select a topic or upload a sample dataset directly. The dataset must contain at least 1000 records and be organized with time as rows/key and tags as columns/value.
The mapping process will automatically start running with the default parameters after the dataset is validated. You can change any parameters and re-run the process as needed. You will be notified via email when the process is complete.
Once complete, you can view the results or download the output file containing the mapping of tags to clusters.
