To return relevant results, we first need to establish what you’re looking for – the intent behind your query. To do this, we build language models to try to decipher how the relatively few words that you enter into the search box match up to the most useful content available.
This involves steps as seemingly simple as recognising and correcting spelling mistakes, and extends to trying our sophisticated synonym system that allows us to find relevant documents even if they don’t contain the exact words that you used. For example, you might have searched for ‘change laptop brightness’ but the manufacturer has written ‘adjust laptop brightness’. Our systems understand that the words and intent are related, and so connect you with the right content. This system took over five years to develop and significantly improves results in over 30% of searches across languages.
Our systems also consider the usability of content. When all things are relatively equal, content that people will find more accessible may perform better.
For example, our systems would look at page experience aspects, such as if content is mobile-friendly, so that those on mobile devices can easily view it. Similarly, they look to see if content loads quickly, also important to mobile users.
5. Context and settings
Information such as your location, past Search history and Search settings all help us to ensure that your results are what is most useful and relevant for you in that moment.
