If you search for “pizza,” or “movie times,” or “division of motor vehicles,” there’s a chance that you might want to find information about where to get pizza near you, or to find what films that local movie theatres or showing, or find out more about driver’s licenses in your area. This is true even if you don’t include a specific location with your search.
The query term you used in your search might be considered to be a “regional sensitive query” because you want to find information associated with a specific geographical location. That geographic location might be on a country or province level, within a specific region, at a state level, or even in a more narrow area such as within a specific city.
How would a search engine decide whether a specific search term might be “regionally sensitive” or be a “global query” and have no specific local intent behind it?
A recent patent application from Yahoo explores many ways to look at user data related to searches to attempt to identify whether a query is regionally sensitive or doesn’t have some location-based intent behind it.
The patent application is:
Identifying Regional Sensitive Queries in Web Search
Invented by Ya Zhang, Srinivas Vadrevu, Belle Tseng, Gordon Guo-Zheng Sun, and Xin Li
Assigned to Yahoo!
US Patent Application 20090307198
Published December 10, 2009
Filed: June 10, 2008
A system for determining the intent of query that includes a search engine that receives a first search query, a query/click log module configured to store log data associated with the first search query; and a computational module that generates metric values associated with the first search query based on the log data and that determines that the first search query is one of a regional specific query or a global query based on the metric values, where the metric values reflect a likelihood of local intent of the first search query, and where the search engine provides search results selected in part based on the metric values.
While the patent filing goes into a fair amount of detail on what it might look for to decide whether the intent behind a query involves a location or not, it can be drummed down to data taken from the search engines query log files, such as:
1. How often a query term like “train tickets” is written to include a geographic location, such as “new york train tickets.”
2. How often a searcher might click upon a checkbox requesting the search be confined to a specific geographic region, providing a choice between “search the Web,” or limiting the search to something such as “search within Ireland.”
3. How often searchers click upon a geographic-related search result versus a global search result in response to a query.
Google will often show Google Maps results in response to some queries and not others as well, and will sometimes show “customized location” results based upon our previous search history or aggregated user data from other searchers. Google might be looking at some similar kind of user data.
Added: December 15th – Yahoo announced on their Yahoo Search blog today that they will start showing Yahoo local business results for some queries even when you don’t include a location in a query in their post: Get More Personally Relevant Results When You Search for Local Businesses. They tell us that we might see local listings for searches such as “yoga” or “auto repair” as well. Are they using the process described in this patent filing to determine whether a query has a location intent? It’s a possibility.
26 thoughts on “How Search Engines Might Divine the Intent behind Regional Queries vs. Global Queries”
I realize that I recognize next to nothing about search engine patents, but is it unusual for a patent filing to take 18 months before being published? Just curious…
It’s not unusual at all. Patents applications usually have to be published at some point during the patent process, usually within 18 months from the time of filing, or from a priority date stated on the application. The US code that gives an 18 month requirement for publication is at:
There are some possible exceptions to that 18 month requirement, but that time period is pretty common for patent applications.
Aloha Bill, just wanted to say that while I like these new ideas and features, I really wish they would put more effort into the foundational stuff, such as coming up with a standard for determining the radius of a geographical location. (Adwords has geographical location targeting options, one of which is a map with a default radius, which is correct for my location) Too bad none of these companies applications play well together, if at all.
I donâ€™t want to list examples on the web, but I see a lot of localized and business queries that display map results that are not even in the prescribed radius of my geo location. IMO G is just as bad as Y when it comes to determining what they think is â€œnearbyâ€.
But anyway if you can figure out what I was trying to say you did well. Oh, and now that WIFI is going to be available for my new 2010 Equinox (it will also serve as a mobile hotspot) exactly how are they going to “divine the intent” behind my regional queries?
Merry Christmas Bill!
Aloha to you, too.
I agree with you that it would be nice to see a focus upon improving some of the core foundational aspects of how things like local search work. I tend to focus upon whitepapers and patent filings here, rather than news of improvements to processes, but I see some of the same problems that you do.
The patent filings sometimes go far afield of what the search engines may seem to be doing, but things like patents often get developed as ideas that are generated while working on core features involving ideas that present themselves which may be worth attempting to develop and protect for possible future use.
Google has been showing maps results within search results for queries that people type in that don’t include geographical locations for a while now, but Yahoo hadn’t at least until yesterday. It’s encouraging to see a method like this, incorporating actual user-based data regarding the possible geographical intent behind query terms. Local search is definitely a work in progress, but I’ve been seeing more white papers and patent filings that are attempting take smarter approaches, and rely less on data from outside sources. Hopefully we’ll see some positive changes soon.
Hope you have a Merry Christmas and Happy New Year, too.
Interesting angle to divining intent of local search.
Searches for Auto Repair would in most cases imply a local relevancy factor. As local search is catching on for small businesses now, it seems that Yahoo! is just riding the wave of demand for granular, local information.
Thanks for fishing out the patent language!
I never quite realised how useful keeping an eye on pending patents was until the last couple of posts on here. A glimps into the future perhaps.
It looks like the engines which initially used the web, web content and structure to define search results are now going to add user behavious into that on a massive scale.
As long as they dont start merging my analytics data and other such things into the ways in which they work out their rankings I wont have (many) objections, that would be a step too far
Thanks for the concise update. I’ve always wondered if SERPS are different for users in different locations. It would be much easier, as an online internet services professional, if our clients got the same SERPs as we do. Wishing and hoping… Cheers!
Interesting. Search engine queries grouped into “regional” or “global” categories to determine the person’s intent sounds like a good idea. One small step for search engines, one giant step for searchers.
Hi Denver SEO,
You’re welcome. I suspect that local will become even more important to search engines. The recent rumors about Google possibly buying Yelp lend even more weight to the idea. I’ve been wondering if Yahoo would start doing more in this area – I think they needed to.
As I first started looking at more search patents, I wondered if there was value spending so much time with them – and I found the same thing that you just expressed – they can be a look into possible futures.
I have seen a lot of them suggesting ways that user data from search engine query and usage logs could be used to create better search suggestions, to re-rank search results, to try to identify the intent behind queries, and more. Looking past the links and content that publishers have created to what people search for, which pages they select in searchers, where they browse after those searches, how they might annotate pages, and so on, adds a great amount of information to what a search engine might understand when they show search results to people.
It’s possible that some analytics data might play a role in how search engines also perceive the web. If you use Google Analytics, you can make a choice as to whether or not your data is shared to give you a bench mark of what you site is doing compared to other similar sites. That data also helps search engines learn about the Web as well. I’ve been hesitant to give permission for them to use that data myself.
Hi People Finder,
I do like this approach as well. When I search for something like “pizza,” I may not necessarily have a local intent – I may want to find recipes to make my own, or to learn about the history of pizza, or so on, but including some local results along with the broader results is a great thing to do. I think this is a step in the right direction.
Great post Bill!
This is great for local businesses. I cater to local small businesses and this will be a great pitch. I’m glad I came across your blog and found this information. I look forward to more great content Bill.
Bill – I know what you mean, I dont let google do anything more with my data than need be and always make sure I opt out of any sharing of data even if I am not sure what impact this would have or ultimately how they would use it. I think that its a bit of paranoia but possibly well placed.
Google has been showing different results for searchers in different locations for a while. When there’s a possible geographic intent behind a search, there’s a chance that local search results might be blended into the web search results. But, on top of that, the actual web pages you see might be customized so that results that may be more relevant to your location, or your country, or your language preferences may also be different than what others see. And that’s without being logged into personalized search, or explicitly setting a preferred location (like you can do with Google). And Google recently posted on the Official Google Blog that they would be personalizing all searches for all searchers.
The days of seeing the same things in search results as your clients are over, and those results may be even more different if they aren’t located in the same general geographic area as you.
Educating your clients on what search engines are doing with local search and on how they are handling geographic based searches is a great way to help them understand some of the challenges (and opportunities) that they face. Happy Holidays to you, too!
Same here – I opt out of data sharing most of the time as well. It doesn’t hurt to exercise a little rational skepticism now and then. 🙂
Local search terms may have lower search volume but they generally have higher conversion rates as buyers are pre-empted by the very nature of the local search.
And also advertisers will have to keep a very keen eye on the shift between generic phrase searches to local search, and adjust their campaigns accordingly. From an organic SEO standpoint, this means that search campaigns will require more components of local seo, in order to rank at the top.
There is a new trend coming up and we need to stay focused!
It is an interesting area. The point behind this patent and process though is that the search engines are trying to identify queries that might be intended to be a local search even when those queries don’t include a geographic location within them. So, someone searching for “pizza” might end up seeing a number of search results involving pizza places near them. Web site owners that have physical storefronts or offices associated with their sites, or serving areas around their locations are well served by learning more about local search, and incorporating local seo efforts into promoting their sites.
This new re-focusing on “personalized search” should scare small businesses who try to rank highly for local searches. In theory, it will become nearly impossible for a new business with a new site to make an impact – a classic case of the rich get richer.
Our theory is that a small business will essentially need to have a business presence in multiple venues (i.e. – Google Maps, Insiderpages.com, etc.) so that you have multiple opportunities to rise to the top regardless of the “personalized search” filtering. The net effect is that a business has 20 to 30 unique websites with 20 to 30 unique SEO approaches. Otherwise, it will be quite simple for a site to crash to the bottom and stay there.
If this proves to be true, traditional on-page SEO will provide diminishing returns for a small business owner who is either unwilling or unable to provide fresh, relevant content on a daily basis. Is the future of small business websites to simply create a blog or Facebook business page?
I don’t believe that this approach was intended to harm small businesses, and in some ways may be beneficial to them. This particular patent is aimed at recognizing that some searches have a geographical intent, even if a searcher doesn’t include a geographical term in their query. So, someone looking for a local pizzeria on Google or Yahoo types [pizza] into a search box will get some local results in addition to pages that may just rank well for “pizza.”
The personalization, or customization of search results that include showing something like a onebox or other maps or local type of result means that local businesses now have more of an opportunity to appear in those results.
I agree with you that this could potentially spell trouble for businesses only doing “traditional” SEO, but SEO has always been something that has evolved over time, just as the search engines and the Web has.
It makes sense for businesses that want to show up in local search results, or in organic search results (whether as blended local results in those, or as organic search listings), to not only make it very clear on their websites what their address or addresses might be, but also to add listings in places like Google Maps and Insiderpages, etc.
I’m not sure that a blog is completely essential, and it’s even possible to rank well in local search results without having a webpage of their own.
One of the things I have found frustrating about the Google map of business listings is even though I have claimed my listing other people within my company are able to edit the information. It seems somehow my information and this other Realtor in my office have a mixed listing. Originally it was mine but now her information is there as well. I find myself constantly editing the page so that my website remains there!
There are a number of problems and limitations with Google Maps, such as what a search engine might show when there are multiple people sharing an office and a business at a specific location, and they all have different phone numbers, and possibly different web sites as well. That’s a problem that can be confusing offline as well as online, I think as well.
Comments are closed.