Imagine that you are scrolling through a page, and see a section of the page highlighted. The text in that area matches an interest profile that you recently created, or it’s along the same topics that you’ve been searching through. Or it is somehow conceptually related to whatever you searched for that may have brought you to this page.
A patent application from the Palo Alto Research Center describes how something like this might work. Instead of highlighting only keywords, the following suggests ways to highlight sentences and sections of web pages that related in some conceptual manner to something that you may be searching for.
Method for automatically performing conceptual highlighting in electronic text
The inventors named in the patent are:
Continue reading Conceptual Highlighting in Electronic Text
I’ve been taking a look at personalized recommendations systems recently, and one of the systems that I remember from earlier days on the web was for music, through a service known as Firefly. I’ve always wondered whatever happened to the service, and the people behind it.
I know that at one point, the company providing this service was partnered with Yahoo, and then it was later purchased by Microsoft. This personalized system was originally developed at MIT, and was incorporated into a business in 1995, by graduate students and Professor Patti Maes. Some of the technology developed by the company transformed into Microsoft’s Passport system.
Wired has a nice write up of the company in an article titled Firefly’s Dim Light Snuffed Out
In an article from this past May, Pitchfork also discusses some of those early days, when the professor turned to her students for some music recommendations because she didn’t like what was playing on Boston radio at the time, in Chris Dahlen’s Better Than We Know Ourselves. The article also looks at some more recent music recommendation systems.
Continue reading An Early Personalized Recommendation System – Firefly
There are a couple of mysteries associated with Google’s local search. One of them is, “How does the search engine decide which web pages should be associated with a specific business and location?” The second is, “What location should be associated with a business?”
If you’ve tried to get a page to rank well in local search, some of the details of this post may not surprise you. If you’ve tried to unravel the mystery of why a business is associated with an old address, and noticed that the old address still appears all over the pages of the business web site, some of the details won’t come as a shock.
Google introduced some new ideas on what it means to be an authoritative source for local search in a patent application that was published this week.
Some Local Optimization Tips Pre-Patent
Continue reading Authority Documents for Google’s Local Search
Imagine a regional magazine writes up a number of reviews of restaurants from a certain city neighborhood, on a web page, and those reviews provide information for each restaurant about their hours, specialties, locations, wine lists, menu choices – but all of the reviews are on one page.
This kind of information would be great for a local search site to collect and show to users looking for places to eat in that area. Except that all of those reviews are on the same page – how does the search engine identify which information goes with which restaurant?
And if they can make that kind of distinction, can they use the process developed for more than just local search?
Continue reading Google and Document Segmentation Indexing for Local Search
A search engine manually checking ads to be served with search results, or on web pages could be a pretty labor intensive proposition. What’s the best way to automate such a process?
And what about followup checks on the advertisments, and the landing pages that they may point to?
A new patent application from Google, published today, describes how such an automated system might work.
Inventors: Gregory Joseph Badros, Robert J. Stets, and Lucy Zhang
US Patent Application 20060149623
Published July 6, 2006
Filed: December 30, 2004
An advertisement for use with an online ad serving system may be automatically checked for compliance with one or more policies of the online ad serving system. If the advertisement is approved, then it is allowed by be served by the ad serving system. Follow up checks of the advertisement may be scheduled. One follow up check may be to test a landing page of the advertisement for compliance with policies. If the advertisement is not approved, hints for making the ad comply with one or more violated policies may be provided to an advertiser associated with the ad, and/or an ad serving system customer service representative. Determining whether or not to approve the advertisement may include determining violations of one or more policies by the advertisement, and, for each of the violations, determining whether or not to exempt the violation.
Continue reading Automated Search Ad Approval Process
I’m a big fan of location based web sites for businesses that serve one geographic area, but I find that many of those aren’t optimized very well for search engines, and many of the business owners behind them don’t take steps to make those sites easily found in search engines.
Many of those site owners also don’t seem to consider using paid search advertising to draw more attention to their sites, or their businesses.
A new patent application from Google looks at some of the reasons why local advertising hasn’t taken off on the web, and tries to come up with some solutions, based upon the use of mobile phones, internet connected PDAs, and other handheld devices.
Here are three reasons why the inventors of this patent claim that local advertisers aren’t enthusiastic about advertising on the the web:
Continue reading Google Ads on Handheld Devices, For Local Area Advertisements
Can Google provide us with a new approach to how we commute to and from work, and travel to other destinations?
It’s something that they appear to be working upon.
In one of my previous lines of employment, I had a twenty minute commute that often took closer to an hour, based upon traffic.
One approach was to take public transportation, which was very convenient because the place to catch the bus was nearby both home and work, but this took a fairly long time. Another was to leave early in the morning to avoid the crush of traffic, and to take less traveled alternative routes in the evening. Leaving early meant arriving early, but it was better than sitting in traffic. Taking alternative routes sometimes resulted in surprising delays, and travel times that weren’t significant improvements.
Imagine being able to quickly and easily gauge how much traffic was on different routes at different times, and to be provided with viable alternative routes. That’s the focus of a new patent application from Google.
Inventors: Henry Rowley and Shumeet Baluja
US Patent Application 20060149461
Assigned to Google
Published July 6, 2006
Filed December 31, 2004
Continue reading Ending Gridlock with Google Driving Assistance (Zipdash Re-Emerges)
From the nice-to-finally-see-an-update department, comes news that Google has updated the list of papers from Googlers over at Google Labs.
The good folks over at ResourceShelf noted the appearance of new papers over there earlier today. Sadly, many of the papers listed aren’t available, but instead link to Google searches for the names of the documents.
A New Personalized Recommendation System
One paper that is available, and looks to be worth a look is Retroactive Answering of Search Queries, (pdf) from Beverly Yang and Glen Jeh, which was presented at the WWW 2006, in Edinburgh, Scotland.
Continue reading New Papers at Google Labs