Handle rating scale conversions between Documents rated using API and documents rated using Static relevancy training

Handle rating scale conversions between Documents rated using API and documents rated using Static relevancy training.

We are an OEM partner of IBM and have built a Chatbot integration with Watson Discovery search.

The end Users of Chatbot rate individual documents that turn up in search from Chatbot using a rating scale of 1 Star to 5 Star.

We convert the Star rating as 2, 4, 6, 8, 10 and then use the Discovery create training example API https://cloud.ibm.com/apidocs/discovery?code=java#createtrainingexample for adding a Discovery Training example based on the Chatbot end User rating.

The rating 2, 4, 6. 8, 10 is passed as relevance parameter of the Training Example passed to the Discovery API.

Besides rating using API as above, our Customer's want to also use static relevancy training.

However once Discovery documents are rated based on Chatbot end User rating as above, in Discovery UI when looking at queries to be rated such documents show the error "Rated with incompatible scale".

We located a IBM document https://www.ibm.com/support/pages/why-does-rated-incompatible-scale-error-occur which mentions that if we plan to rate the document with both API as well as Discovery tooling, then the documents must be rated as 0 (Not relevant) or 10 (Relevant). This means end User can not provide graded rating to provide relative usefulness of a document.

The above looks like an artificial restriction. Any rating number between 0 to 10 or in general any arbitrary rating scale should be compatible in terms of rating scale for documents rated by API and documents rated by Discovery tooling. Discovery should be able to handle rating scale conversion between documents rated using API and documents rated using Static relevancy training.

This will help Customers leverage rating from API as well as Static relevancy training without any restriction on the rating scale.