No expert here, but I assumed the difference was that the model created "hidden connections" that weren't explicitly added by curators.
From what I remember, the Semantic Web was intended to be a big library science type of project, where people described things for computers, so that people could find them. This seems more like computers describing things so that people can find them, and then updating based on how people react.
> Qu’s vector search engine is able to discover hidden connections among products, such as sloped ceilings, ceiling fans, and downrods...
And
> Perhaps Home Depot knows that a particular customer is in the middle of a patio renovation, which instantly narrows the search down to outdoor ceiling fans.
It's not clear to me why that part couldn't be done with conventional searches, but maybe it's something this technological makes it simpler to use. /shrug
I worked on the system. It's a similar idea but it's on e-commerce products and not websites. So you can't use things like page rank when doing product search.
Well semantic web search is less about traditional web search and more about semantic relationships between terms using ontologies.
If you search for "pipe A500", the search engine would deconstruct that. It would see pipes have steel, and a coating for steel, and a grade of steel. It would see A500 is a grade of steel. Pipes don't have a grade A500, but tubes do, and tubes have the other classifications that pipes do. It may then conclude that while 'A500' and 'pipe' are not linked directly, a different term may be very similar and a more direct match ('tube'), and thus return 'A500 tube' results.
It seemed like the machine learning model was building relations between these different concepts and using them to improve the search, but without the intentional taxonomic mapping that semantic web uses. Semantic web is essentially more of a curated database of relationships, whereas the machine learning appears to be using another method to establish the relationships. I wonder if they're not doing basically the same thing.
I'd guess that the primary difference is in the attribute space and specificity.
Home Depot products are specific in odd ways. E.g. an 8' PVC pipe can be shortened on-site, a 3' downrod for a ceiling fan might not be able to. So substitutability is hard.
The part at the beginning where employees manually loaded possible search terms sounds like the semantic web to me. This project uses deep learning to automatically direct a whole space of possible search terms to an item, instead of just missing all the terms that were not manually added.
