There has been a lot of speculation about what Navboost is, but to my knowledge no one has identified a suitable patent that could be the original Navboost patent. This 2004 patent is closely aligned with Navboost
So I took the few clues we have about it and identified a couple of likely patents.
The clues I was working with are that Google software engineer Amit Singhal was involved with Navboost and helped invent it. Another clue is that Navboost dates back to 2005. Finally, court documents indicate that Navboost was updated later, so there may be other patents on that, which we’ll get to at some point, but not in this article.
So I deduced that if Amit Singhal was the inventor, there would be a patent named after him, and indeed there is, dating back to 2004.
Of all the patents I saw, the two most interesting were these:
Systems and Methods for Correlating Document Timeliness and Popularity 2004 Interleaving Search Results 2007
This article will cover the first, Systems and Methods for Correlating Document Timeliness and Popularity which dates back to 2004, which aligns with Navboost’s known timeline which dates back to 2005.
The patent does not mention clicks
An interesting quality of this patent is that it doesn’t mention clicks, and I suspect that people looking for the Navboost patent may have missed it because it doesn’t mention clicks.
But the patent deals with concepts related to user interactions and navigation patterns that are references to clicks.
Instances where user clicks are involved in the patent
Selection and retrieval of documents:
The patent describes a process in which a user selects documents (which can be inferred by clicking on them) from search results. These selections are used to determine the popularity of documents.
Assignment of documents to topics:
After users have selected documents (via clicks), they are assigned to one or more topics. This mapping is a key part of the process, as it associates documents with specific areas of interest or subjects.
User browsing patterns:
The patent often refers to user navigation patterns, which include how users interact with documents, such as which documents they choose to click on. These patterns are used to calculate document popularity scores.
It is clear that user clicks are a fundamental part of how the patent is proposed to assess the popularity of documents.
By analyzing which documents users choose to interact with, the system can assign popularity scores to those documents. These scores, in combination with the topic relevance of the documents, are then used to improve the accuracy and relevance of search engine results.
Patent: User interactions are a measure of popularity
Patent US8595225 makes implicit references to “user clicks” in the context of determining the popularity of documents. Heck, popularity is so important to the patent that it’s in the patent name: systems and methods for correlating document timeliness and popularity
User clicks, in this context, refer to user interactions with various documents, such as web pages. These interactions are a critical component in establishing the popularity scores of these documents.
The patent describes a method where the popularity of a document is inferred from users’ browsing patterns, which can only be clicks.
I’d like to stop here and mention that Matt Cutts has commented in a video that popularity and PageRank are two different things. Popularity is about what users tend to prefer and PageRank is about authority as evidenced by links.
Matt defined popularity:
“And so popularity in some sense is a measure of where people go, while PageRank is much more a measure of reputation.”
This 2014 definition fits what this patent is talking about in terms of the popularity of where people go.
Watch Matt Cutts explain how Google separates popularity from true authority
Watch the YouTube video: How does Google separate popularity from authority?
How the patent uses popularity ratings
The patent describes several ways to use popularity scores.
Assigning Popularity Scores:
The patent is about assigning popularity scores to documents based on user interactions, such as frequency of visits or browsing patterns (line 1).
Popularity by topic:
It talks about getting popularity information by topic by correlating the popularity data associated with each document to specific topics (line 5).
Ranking Popularity Score:
The document describes the use of popularity scores to order documents among one or more topics associated with each document (line 13).
Popularity in Document Recovery:
In the context of document retrieval, the patent describes the use of popularity scores to rank documents (line 27).
Determining popularity based on user browsing:
Also mentioned is the process for determining the popularity score of each document, which may involve the use of user navigation patterns (line 37).
These cases demonstrate the patent’s approach to incorporating the popularity of documents, as determined by user interaction (clicks), into the process of ranking and correlating with specific topics.
The approach described in the patent suggests a more dynamic and user-sensitive method for determining the relevance and importance of documents in search engine results.
Navboost assigns ratings to documents
I’ll stop here to also mention that this patent mentions assigning scores to documents, which is how Google executive Eric Lehman described in the test how Navboost worked:
Speaking of the situation where there wasn’t a lot of click data, Lehman stated:
“And so I think Navboost does what’s natural, which is that, in the face of that kind of uncertainty, you take softer action. So you can modify the score of a document, but in a softer way than if you had more data.”
This is another connection to Navboost, as the test description and patent describe using user interaction to score web pages.
The more this patent is analyzed, the more it looks like what the test documents describe as Navboost.
Read the patent here:
Systems and methods for correlating the actuality and popularity of documents
Featured image by Shutterstock/Sabelskaya
[ad_2]
Source link
