Unstructured Report Analysis for a Leading Chemical Manufacturer


The client is a very large, multinational corporation that has been successful in scientific development and materials manufacturing for over a hundred years. They were seeking to expand one of their more technical tools to be accessible to a larger, less technical audience. One of the steps to meet this objective was to extract a plethora of unstructured data from a library of PDF documents and put it into a structured format that their technical tool can utilize. The client’s library of documents describes the processes that they use to evaluate the quality of their products before they are shipped to clients. This includes a recipe of chemistries, steps, methods, tools, and ultimately the precision of the measurement if these procedures are followed. The client wanted to develop an automated tool that extracts specific information, from the library of PDF documents, and have it automatically placed into a predetermined structured format. There are other pieces of information contained in the documents, and in additional text-based sources, that the client was interested in extracting. As a result of this, the client was interested in a solution for the current task that can also be easily extensible and used as part of a framework for completing similar tasks in future. They engaged with Soothsayer to develop this solution.

Interested to see the complete Case Study?

Fill in your details below and we will mail it to you