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 try to understand what type of information you are looking for. If you used words in your query like 'cooking' or 'pictures', our systems realise that showing recipes or images may best match your intent. If you search in French, most results displayed will be in that language, as it’s likely that is what you want. Our systems can also recognise that many queries have a local intent, so that when you search for 'pizza', you get results about nearby businesses that deliver.

If you search for trending keywords, our systems understand that up-to-date information might be more useful than older pages. This means that when you’re searching for sports scores, company earnings or anything related that's especially new, you’ll see the latest information.

Next, our systems analyse the content to assess whether it contains information that might be relevant to what you are looking for.

The most basic signal that information is relevant is when content contains the same keywords as your search query. For example, with web pages, if those keywords appear on the page, or if they appear in the headings or body of the text, the information might be more relevant.

Beyond looking at keywords, our systems also analyse if content is relevant to a query in other ways. We also use aggregated and anonymised interaction data to assess whether search results are relevant to queries. We transform that data into signals that help our machine-learned systems better estimate relevance. Just think: when you search for 'dogs', you likely don’t want a page with the word 'dogs' on it hundreds of times. With that in mind, algorithms assess if a page contains other relevant content beyond the keyword 'dogs' – such as pictures of dogs, videos or even a list of breeds.

It’s important to note that, while our systems do look for these kind of quantifiable signals to assess relevance, they are not designed to analyse subjective concepts such as the viewpoint or political leaning of a page’s content.

After identifying relevant content, our systems aim to prioritise those that seem most helpful. To do this, they identify signals that can help determine which content demonstrates expertise, authoritativeness and trustworthiness.

For example, one of several factors that we use to help determine this is understanding if other prominent websites link or refer to the content. This has often proven to be a good sign that the information is well trusted. Aggregated feedback from our Search quality evaluation process is used to further refine how our systems discern the quality of information.

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.

We use your country and location to deliver content relevant for your area. For instance, if you’re in Chicago and you search 'football', Google will most likely show you results about American football and the Chicago Bears first. Whereas if you search 'football' in London, Google will show results about football and the Premier League. Search settings are also an important indicator of which results you’re likely to find useful, such as if you set a preferred language or opted in to SafeSearch (a tool that helps filter out explicit results).

Search also includes some features that personalise results based on the activity in your Google Account. For example, if you search for 'events near me' Google may tailor some recommendations to event categories that we think you may be interested in.

These systems are designed to match your interests, but they are not designed to infer sensitive characteristics like your race, religion or political party.

You can control what Search activity is used to improve your Search experience, including adjusting what data is saved to your Google Account, at myaccount.google.com. To disable Search personalisation based on activity in your account, turn off Web & App Activity.

You can also find content preferences like SafeSearch in settings. These help you make a choice about whether Search results include graphic content that may be shocking for some users.