Comment by pona-a

How about a naive Bayesian Bag of Words? Just find/scrape/generate with an LLM a large enough corpus of products/services, build the term frequency matrix, calculate class priors and P(term|class) and inference with straightforward application of Bayes theorem.

This particular problem, at least to me, seems trivial, and to use an LLM for anything like this for more than a hundred cases seems incredibly wasteful.