{"id":2407,"date":"2022-02-02T09:55:00","date_gmt":"2022-02-02T09:55:00","guid":{"rendered":"https:\/\/seopolarity.com\/blog\/?p=2407"},"modified":"2022-02-02T16:32:25","modified_gmt":"2022-02-02T16:32:25","slug":"googles-ability-to-interpret-queries-based-on-entity-information-is-revealed-in-a-patent","status":"publish","type":"post","link":"https:\/\/seopolarity.com\/blog\/googles-ability-to-interpret-queries-based-on-entity-information-is-revealed-in-a-patent\/2022\/","title":{"rendered":"Google’s ability to interpret queries based on entity information is revealed in a patent"},"content":{"rendered":"\n

A new Google patent<\/a>, issued on December 28, 2021, focuses on how to interpret queries and solve them using entity information.<\/p>\n\n\n\n

I frequently include references to Google patents in my articles because I spend a lot of time learning from them.<\/p>\n\n\n\n

Patents are filed to describe new inventions and encourage potential competitors to innovate. They provide enough information to prevent others in the same industry from copying the patent filers’ intellectual property.<\/p>\n\n\n\n

We frequently find interesting information about the assumptions that patent creators make about search, searchers, and the Web, which can make the patents an interesting read as well.<\/p>\n\n\n\n

As is customary when I share the highlights of a patent in an article like this, you are encouraged to read the entire patent.<\/p>\n\n\n\n

I try to explain what the patent may cover, but not in such a way that my post appears to be a copy of the patent to indexing<\/a> programs.<\/p>\n\n\n\n

You may recall that Google search engineer Paul Haahr gave a presentation on “How Google Works” at SMX 2016.<\/p>\n\n\n\n

One of the key takeaways was that Google tries to identify when entities appear in search queries submitted by users.<\/p>\n\n\n\n

That statement begs the question of how Google can tell which entity is being referred to in a query.<\/p>\n\n\n\n

Google has filed a patent on the subject, which is the subject of this post.<\/p>\n\n\n\n

How to Improve Queries Interpretation<\/h2>\n\n\n\n

Search has evolved to accept such search queries and return relevant results.<\/p>\n\n\n\n

Some search engines, however, provide search results without understanding the search query.<\/p>\n\n\n\n

In response to [action movie starring Tom Cruise], for example, irrelevant search results such as [Last Action Hero] and [Tom and Jerry] may be returned because a portion of the search query is included in the titles of the pieces of content.<\/p>\n\n\n\n

Understanding the search query can assist the search engine in producing more relevant results.<\/p>\n\n\n\n

What might a search engine make of a query?<\/h2>\n\n\n\n

The following methods are mentioned in the patent:<\/p>\n\n\n\n

  1. Receiving a search domain query.<\/li>
  2. Choosing search terms based on the query<\/li>
  3. Whether a search term corresponds to a name of an entity.<\/li>
  4. Check to see if the entity name is from metadata related to the search domain.<\/li>
  5. Observing that a large number of entity names correspond to at least a portion of the total number of search terms.<\/li>
  6. Choosing an entity type and an entity score for each of the corresponding entity numbers.<\/li>
  7. Finding a number of entity names by removing some matching entity names based on the entity score and contextual information in the search query received.<\/li>
  8. Performing a search in the search domain using the remainder of the entity names.<\/li>
  9. In this case, each entity named in the remaining portion of the number of entity names is searched for in relation to the associated entity type.<\/li><\/ol>\n\n\n\n

    This method of query interpretation can also include:<\/p>\n\n\n\n