Google patent granted: Rank adjustments via click data

  • 0
  • October 31, 2009

Google has this week been granted a patent for adjusting search rankings based on click data for related queries.

The patent, entitled Rank-adjusted content items, talks about the same types of query refinements we discussed earlier this month in the satisfaction rates post and in previous brand update analysis.

In plain English the patent explains that Google may be counting the number of people who search for “insurance” and then search for “”. Google can then analyse the queries and determine whether they are statistically significant enough for to be displayed in the rankings for “insurance”.

Rank-adjusted content items

Click logs and query logs are processed to identify statistical search patterns. A search session is compared to the statistical search patterns. Content items responsive to a query of the search session are identified, and a ranking of the content items is adjusted based on the comparison.

Inventors: Datar; Mayur (Santa Clara, CA), Dhamdhere; Kedar (Sunnyvale, CA), Garg; Ashutosh (Sunnyvale, CA)
Assignee: Google Inc. (Mountain View, CA)
Appl. No.: 11/694,268
Filed: March 30, 2007

Content items, e.g., video and/or audio files, web pages for particular subjects, news articles, etc., can be identified by a search engine in response to a query. The query can include one or more search terms, and the search engine can identify and rank the content items based on the search terms in the query. Typically the content items are displayed according to the rank.

The content items, however, are often identified only in response to a particular query, i.e., the search engine may identify and rank content items to independently for each query. For example, for three different queries, the search, engine may return a particular identification and rank of content items for each particular query, regardless of the other queries. In such implementations, a particular content item that may be highly relevant to a user’s current interests may not be identified and/or highly ranked and presented to the user until the user has conducted multiple searches. Additionally, other users may experience similar challenges when searching for content.


Disclosed herein are systems and methods of identifying content items. In one implementation, click logs and query logs are processed to identify statistical search patterns based on the click logs and query logs. A search session is compared to the statistical search patterns. Content items responsive to a query of the search session are identified, and a ranking of the content items is adjusted based on the comparison.

In another implementation, query paths and content terminuses associated with query paths are identified. Additionally, a context of a search session is identified and a determination of whether the context is related, to one or more of the query paths is made. Content items responsive to a query of the search session are identified based on the determination.

In another implementation, a system includes a mining engine and an adjusting engine. The mining engine mines click logs and query logs to identify query paths and content terminuses associated with the query paths. The adjusting engine adjusts a ranking of content items responsive to a search session query based on the identified query paths and content terminuses.

In one implementation, identification of a context of a search session facilitates the adjusting of a ranking of one or more content items in response to a search session query. The adjustment can, for example, be based on the likelihood that a current user is searching for the rank-adjusted content items because a statistically significant number of prior users that exhibited a similar behavior to the current user selected the rank-adjusted content items.

Patrick Altoft

About Patrick Altoft

Patrick is the Director of Strategy at Branded3 and has spent the last 11 years working on the SEO strategies of some of the UK's largest brands. Patrick’s SEO knowledge and experience is highly regarded by many, and he’s regularly invited to speak at the world’s biggest search conferences and events.

  • PaulB

    It is interesting and something ive thought they may have been thinking about for a while. At the same time i really cant see how they can use user generated data on any kind of large scale. If user clicks did have any kind of serious effect on rankings the black hats would be all over it. Why got to a the trouble of link spamming when you can get your bot farm to click on a few google results to achive ranking?


    • Patrick Altoft

      User data is actually a lot harder to game than link data – think about how hard it is for Google to spot some paid links.

  • Available Domains Blog

    Interesting patent. May serve the searches well.

  • Dave

    User data would be a lot harder to game – don’t forget google already does a (relatively) good job of stopping click fraud with adwords listings.

  • PaulB

    Google is good at detecting click fraud? Not so sure :

  • tag44

    Thanks for the post and for sharing the very resourceful information here.

  • Dave

    Paul – while I agree with you that click fraud still happens, that report from theregister isn’t solely about Google, its figures come from a range of ad networks.

  • PaulB

    I agree that google probably is better than most at detecting click fraud, however there will be one crucial metric missing in serp clicks. When they work out PPC for an add on say adsense they can track if the user who clicked made a sale (if adwords buyer agrees) and this helps them work out visitor quality.

    However with serp CTR they have no idea what happens after the click so would seem to me very hard to measure the quality/likelyhood that the request is a bot.


  • Website Boosting

    Hi, here is a Report how Google deals with Click-Fraud.
    There are 3-steps to prevent Ffraud and over 1.000 People at Google works on this topic. The rate of invalid clicks is described there as < 0.02%.
    I think this paper is worth reading… 😉

  • Pingback: Top 10 Search Posts Of The Week – 06/11/09 | Fusion Unlimited Digital Marketing Blog()

  • The System

    You are all missing the main point. Google already has access to everybodies search behaviour and history. The data mining methods mentioned have already determined, using the law of large numbers and wisdom of crowds, a data set that can be trusted. It’s not something anyone can game on a scale not to be noticed!
    Google can then use this trusted dataset with it’s other trusted datasets such as link popularity to produce a ranking score.

Like what you see? Talk to an Expert