Apple has been granted two patents that show the company is looking into ways to improve search results on the Mac’s Spotlight feature. Patent number 2018012803 is for “blending learning models for search support,” while patent number 2018121435 is for “re-ranking search results using blended learning models.” Both involve, among other things, crowd-sourced data.
A query search online begins with a client receiving the query string, which is sent to a search server. The search server receives query string and searches a search index for results that match this query string. The search server then returns the results to the client. In addition, the client can search local data using this query string as well. Each of the results will include a ranking score that is used to rank and present the search results. The search results with a higher ranking are presented higher than results with a lower ranking.
Apple says a challenge with these results is how to present the results. For example, the search results can have a raw ranking, but this ranking may not reflect a user’s preference. In this example, after the client receives and presents the results, the user may engage with some of the results (e.g., click on a link for one of the results and spend time interacting with the website referenced by that link) and may also abandon some of these results.
These engagement results can give an indication of the types of search results a user prefers or doesn’t prefer. What’s more, there are other types of data that can be used to determine which results a user prefers, but this type of data is usually private to the device. Apple thinks it can improve on the process.
Of course, Apple files for — and is granted — lots of patents by the U.S. Patent & Trademark Office. Many are for inventions that never see the light of day. However, you never can tell which ones will materialize in a real product.
Like this article? Consider supporting Apple World Today with a $5 monthly Team AWT membership.
