Google Relies on Freebase Machine ID Numbers to Label Images in Knowledge Graph
May 3, 2016
The article on Seo by the Sea titled Image Search and Trends in Google Search Using FreeBase Entity Numbers explains the transformation occurring at Google around Freebase Machine ID numbers. Image searching is a complicated business when it comes to differentiating labels. Instead of text strings, Google’s Knowledge Graph is based in Freebase entities, which are able to uniquely evaluate images- without language. The article explains with a quote from Chuck Rosenberg,
“An entity is a way to uniquely identify something in a language-independent way. In English when we encounter the word “jaguar”, it is hard to determine if it represents the animal or the car manufacturer. Entities assign a unique ID to each, removing that ambiguity, in this case “/m/0449p” for the former and “/m/012×34” for the latter.”
Metadata is wonderful stuff, isn’t it? The article concludes by crediting Barbara Starr, a co-administrator of the Lotico San Diego Semantic Web Meetup, with noticing that the Machine ID numbers assigned to Freebase entities now appear in Google Trend’s URLs. Google Trends is a public web facility that enables an exploration of the hive mind by showing what people are currently searching. The Wednesday that President Obama nominated a new Supreme Court Justice, for example, had the top search as Merrick Garland.
Chelsea Kerwin, May 3, 2016
Sponsored by ArnoldIT.com, publisher of the CyberOSINT monograph
New Patent for a Google PageRank Methodology
December 18, 2015
Google recently acquired a patent for a different approach to page ranking, we learn from “Recalculating PageRank” at SEO by the Sea. Though the patent was just granted, the application was submitted back in 2006. Writer Bill Slawski informs us:
“Under this new patent, Google adds a diversified set of trusted pages to act as seed sites. When calculating rankings for pages. Google would calculate a distance from the seed pages to the pages being ranked. A use of a trusted set of seed sites may sound a little like the TrustRank approach developed by Stanford and Yahoo a few years ago as described in Combating Web Spam with TrustRank (pdf). I don’t know what role, if any, the Yahoo paper had on the development of the approach in this patent application, but there seems to be some similarities. The new patent is: Producing a ranking for pages using distances in a Web-link graph.”
The theory behind trusted pages is that “good pages seldom point to bad ones.” The patent’s inventor, Nissan Hajaj, has been a Google senior engineer since 2004. See the write-up for the text of the patent, or navigate straight to the U.S. Patent and Trademark Office’s entry on the subject.
Cynthia Murrell, December 18, 2015
Sponsored by ArnoldIT.com, publisher of the CyberOSINT monograph
-
- Subscribe to Beyond Search
Feature archive
News archive
-
