Hello,

Our research group at the University of Chicago is trying to implement the inventor's name disambiguation algorithm. We are following the steps described here: https://github.com/PatentsView/PatentsView-Disambiguation

It seems that the algorithm takes as inputs the databases rawassignee, rawinventor, patent, and rawlocation in SQL. Is this correct? If yes, is there an easy way to load all the data into the SQL database?

We thought of downloading all the TSV files and then putting all the data in SQL. However, as we understand you have the data already in SQL, maybe there is an easier way to do it?

We appreciate any guidance you can provide.

Sincerely,

Santiago