Google will take into account your past searches to suggest more relevant queries

Last month, Google announced a number of updates to improve the underlying technology powering Search. Language understanding capabilities introduced this year allow Google to factor your past queries to suggest additional searches.

In the past, searches were largely siloed off as a query would not impact how Google displayed following ones. For example, if you searched for “turkey recipes” and then “carving,” Google would do nothing to associate or personalize the second term to the first. Rather, the search engine would just “use the most common interpretation in ranking results.” 

Moving forward, looking up “carving” after the turkey-related query will offer a new search for “carving turkey” that’s more relevant than just offering a definition. These past-influenced search terms are labeled by Google as “Suggested based on your recent activity.” Overall, this is somewhat similar to Assistant’s support for follow-up questions without restating the topic or subject.

But with this change, we can determine that you’re looking to learn more about preparing and serving a turkey and we’ll provide you with a helpful suggestion at the top of your search results page to get you to what you were actually looking for:

Similarly, Google will factor past searches to suggest new queries (and content suggestions) as part of carousel-based topic exploration:

Say you’re looking for a movie the whole family can enjoy. As you search through family-friendly holiday flicks like The Polar Express and A Christmas Story, Google may detect that you’re exploring related ideas and show a list of similar movies to help you more easily browse for the perfect pick.

The last update will surface “more relevant questions” under the “People also ask” list:

Prior to introducing these features, if you had searched for “how to make a napkin fan,” Google might have helped you discover additional information by showing you similar questions such as “How do you make a cone napkin?” With contextual learning, Google can source even more relevant questions in the “People also ask” section, like “How do you make a turkey out of a cloth napkin?”