Table of contents
What is neural matching?
Neural matching is “understanding the intent of a search keyword so that the target page can be displayed even if the search term is not included on the website.”
(reference) https://japan.googleblog.com/2018/09/search20.html
Google explains neural matching on Twitter with the following example:
(https://twitter.com/searchliaison/status/1108776358996369408?s=20)@Google Search Liaison
For example, neural matching helps us understand that a search for “why does my TV look strange” is related to the concept of “the soap opera effect.”
We can then return pages about the soap opera effect, even if the exact words aren’t used…
*What is the soap opera effect?
A feature on your TV that automatically inserts frames between frames to make grainy images appear smoother.
However, while this is a very effective feature when watching sports or other videos where you don’t want to miss a single moment, it may feel strange when watching movies where the number of frames per second is set at 24. It’s a function.
This process of returning keywords in search results by linking them to the concept of search intent is called neural matching.
Difference between neural matching and RankBrain
There is a similar concept called Rank Brain.
Google explains Rank Brain as follows:
(https://twitter.com/searchliaison/status/1108776357880725505?s=20)
RankBrain is an AI-based system Google began using in 2016 to understand how pages are related to concepts.
It means we can better return relevant pages even if they don’t contain the exact words used in a search, by understanding the page is related to other words & concepts…
Although they are similar in concept, the function that understands the content of a web page and what kind of concept the page has is called Rank Brain.
Voice search and neural matching
Neural matching is an attempt to change the pages displayed in search results to those that are in high demand by becoming better able to understand human language.
Voice search is particularly powerful.
Voice search queries are more colloquially based than regular searches.
Using the TV example from earlier, if Google interprets a search for “The TV doesn’t look a bit strange” as “The TV is delivering interesting content,” it will affect the user’s satisfaction with the search results. will decline.
If Google can understand spoken language, it will be able to support voice searches, which are expected to increase in the future.
