slawski - 1:27 am on Aug 19, 2012 (gmt 0)

@ 1script

The patent does include a couple of time periods within its description, but those are likely examples only, and an actual period of time that might be used if this is implemented, could differ.

Here are the time periods mentioned:

As shown in FIG. 6, the rank of a document slowly responds to a positive change in its link-based information. After a period of time, the document's rank might settle in on its new steady state (target) value. The time line shown in FIG. 6 may be represented in days in one implementation consistent with the principles of the invention. In other words, it might take approximately 70 days for a change in a document's link-based information to change the rank of the document to its steady state (target) value (e.g., 1.0 in FIG. 6).

The other example of a Rank Transition Function where a page (site, set of associated sites, etc.) might initially drop in rankings also uses a similar example, and total length of time, but initially the rankings drop for the first 20 days:

As shown in FIG. 7, the rank of a document may initially decrease in response to a positive change in its link-based information. After a period of time, the document's rank might rise to its new steady state (target) value. Like FIG. 6, the time line shown in FIG. 7 may be represented in days in one implementation consistent with the principles of the invention. In other words, the document's rank may decrease for a period of approximately 20 days before settling in on its new steady state (target) value (e.g., 1.0 in FIG. 7) in approximately 70 days after a positive change in its link-based information.

Those are two examples actually listed in the patent, but again the time periods that are actually used might differ. The patent also tells us that other random activity might take place within rankings, such as wild fluctuations and other seeming random results.

Note that this might not just impact a single page, but might also impact additional pages that have recognizably related footprints, which might happen in the case of someone creating lots of auto-generated sites.