ASHP's drug information data is very complex in structure and finely tagged. Instead of a traditional algorithmic approach, we are leveraging machine learning to build Sherlock.
We are using AWS's machine learning service called Kendra, which indexes the clinical content, and provide search based on natural language processing. In our testing, it is able to find relevant information with pretty good results. Kendra also has capability for users to rate results so it can become smarter and give better answers over time.
We wrote integration between Kendra and AWS's chat bot service, Lex in a lambda based serverless architecture.
We are using AWS's machine learning service called Kendra, which indexes the clinical content, and provide search based on natural language processing. In our testing, it is able to find relevant information with pretty good results. Kendra also has capability for users to rate results so it can become smarter and give better answers over time.
We wrote integration between Kendra and AWS's chat bot service, Lex in a lambda based serverless architecture.