How Google may Identify How Related Different Entities Are

A patent granted to Google this week attempts to identify similarities between different types of entities, when it finds information about them on the Web. It refers to these types of similarities as commonalities, as in things they may have in common. Google may use these similarities in a number of ways, such as supplementing search results containing related information based upon results that might be in the same category or possibly located in the same region.

The things identified as common may be for things that are moderately unique, but not completely rare.

The patent say “entities,” but it seems to be focusing upon different businesses that might share some similarities. For example, they refer to a food critic writing about restaurants a few times and tell us that the things such a critic might write about different restaurants might be used to find similarities between those places.

This method describes finding commonalities between entities.
This method describes finding commonalities between entities.

For example, that critic might tell us about two different restaurants that both serve the same types of food, such as specializing in certain types of seafood, or that may be located near each other.

The patent is:

Identifying interesting commonalities between entities
Invented by Tamara I. Stern, Gregory J. Donaker, Jason Lee, Bernhard A. M. Seefeld
Assigned to Google
US Patent 9,116,982
Granted August 25, 2015
Filed: March 14, 2013


Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating descriptions of relationships between entities.

In one aspect, a method includes:

  • Identifying one or more related entities for a particular entity based at least in part on commonalities between the particular entity and the one or more related entities
  • sorting the commonalities according to a measure of uniqueness of each of the commonalities, and
  • identifying a subset of the commonalities having a measure of uniqueness above a lower measure of uniqueness threshold.

The identified subset of commonalities can include one or more commonalities. One or more commonalities can be selected from the subset of commonalities as indicative of a relationship to the particular entity, and a description of the relationship can be identified based on the selected one or more commonalities.


Take Aways

We are told in the patent that sources such as reviews of places might be looked at while also identifying similarities or commonalities from sources like a food critic’s articles or blog posts.

At present, I’m not seeing the kinds of recommendations fo “similar” places in search results, then again, this patent was just granted a few days ago. It’s possible that Google may have developed a process like the one described in this patent, but hasn’t released it to the public yet.

They tell us that the things they might look for similarities about specific entities might be scored on a “uniqueness” score, based upon how frequently those features might show up in a body of information that the entities (or businesses) might be located in. So, a uniqueness score for (entities) like restaurants may be restaurants could be based upon both offer a rare and unique dish such as Spanakopita, or that they share a map location, or that they share the use of some unusual language


The purpose of this patent seems to be to enable Google to offer searchers “similar” places when they perform a search for a particular type of business.

Article Name
How Google may Identify How Related Different Entities Are
A Google patent looks at facts and attributes involving related entities, found at websites associated with those, to find similarities between them.

7 thoughts on “How Google may Identify How Related Different Entities Are”

  1. Hello Bill,
    I first heard about the Google patent stuff at Neil Patel’s blog and i think its a very cool idea.

    However, i also think it will benefit local business the more.

  2. Hi Theodore,

    I’ve been writing about Google patents for a little longer than a decade. I think this one could benefit local businesses tremendously, helping people learn about places that they hadn’t heard of before.

  3. Hello Bill,

    Remember reading about the patent on your blog about Google answers in response to search queries. Finding commonalities between different entities appear to be a step in that direction only, to come up with the well framed and most informative answers apart from various links in the search engine listings.

  4. Hi Cathy,

    This does seem like a good way to provide searchers with some additional results to look at that might be helpful to them.

  5. Great to see local business getting a bit more love finally! Google really needs to help small and local biz like Facebook does if its wants business to use its products more.

  6. Hey Bill, came across your post – i always thought there was a thematic relevance type algo on the way from google and this seems like it could be the start of that. I guess the key is for local Seo’s is how can we use this knowledge to our clients advantage as it’s always a challenge to get the clients competitors to understand how mentioning each others brand can actually benefit each other. WHat are your thoughts?

  7. Hi Mark,

    Your question reminds me of a story of how antique shops in an area I lived in in Delaware helped promote each other. In the lobby of each, they made pamphlets available that showed the other nearby antique shops, contained information about what they specialized in, and had a map to make them easier to find. This made it more likely that they would end up all attracting people who might be interested in making a day of shopping, and who would appreciate information about each of the stores’ specializations. If your favorite shop offered a map that showed off other nearby shops, as if it were a recommendation and endorsement, it reminds me of the saying, “A rising tide lifts all boats.”

Comments are closed.