IndustryNew Search Patent Applications: July 11, 2006 – Google Patent Filings by the Dozen

New Search Patent Applications: July 11, 2006 - Google Patent Filings by the Dozen

Twelve Google patent applications where published this past week, including seven that focus upon geographical information and local search.

(1) How good a match ads may be to the content on pages they are served upon through a program like Adsense. (2) A process for improving the targeting of ads. (3) Real time transportation data for travelers. (4) An exploration of ad layouts. (5) An automated advertising approval process. (6) Reasons for location-based businesses to use local area advertising, including an improved pay-per-call process.

(7) How the most authoritative local search results are identified. (8) The use of visual gap segmentation to separate information on different parts of pages, with implications beyond local search. (9) Ties business locations with regional areas. (10) A method for reducing ambiguity in geographic location. (11) Deciding whether regular or local results might be shown when at least one query term might be geographical in nature. (12) Assigning confidence scores between business identity and location information on a page.

Microsoft adds two more, on the validity of links, and on the validity of anchor text in links. They have very similar names, and cover topics that are related, but the processes involved are very different.

Google

This first patent filing discusses some of the factors that the search engine may look at to determine whether or not an ad served on a page a good match for that page and possibly the category that page may be within, including some user behavior information such as whether or not ads are selected, how long a viewer remains on a page, and if a conversion is made.

Associating features with entities, such as categories of web page documents, and/or weighting such features
Inventors: Ross Koningstein, Stephen Lawrence, and Valentin Spitkovsky
US Patent Application 20060149710
Published July 6, 2006
Filed on December 30, 2004

Abstract

Features that may be used to represent relevance information (e.g., properties, characteristics, etc.) of an entity, such as a document or concept for example, may be associated with the document by accepting an identifier that identifies a document; obtaining search query information (and/or other serving parameter information) related to the document using the document identifier, determining features using the obtained query information (and/or other serving parameter information), and associating the features determined with the document. Weights of such features may be similarly determined. The weights may be determined using scores. The scores may be a function of one or more of whether the document was selected, a user dwell time on a selected document, whether or not a conversion occurred with respect to the document, etc. The document may be a Web page. The features may be n-grams. The relevance information of the document may be used to target the serving of advertisements with the document.

The process detailed in the next patent application aims at improving the relevancy of ads, and helping in suggesting targeted terms by allowing an advertiser to submit broad targeting information. While serving ads using that information, the search engine would log and collect search query terms, and possibly concepts and concept keywords, associated with the serving of the ad, and suggest candidate targeting keywords or phrases to the advertiser from those logs.

Suggesting and/or providing targeting information for advertisements
Inventors: Ross Koningstein
US Patent Application 20060149625
Published July 6, 2006
Filed on December 30, 2004

Abstract

The relevancy of ads may be increased, and opportunities to serve an ad that might otherwise be missed may be exploited by (i) accepting broad targeting information, to be used for serving an ad, from an advertiser, (ii) serving the ad using the broad targeting information, (iii) logging search query terms (or some other information, such as concepts, concept keywords, etc.) associated with the serving of the ad, and (iv) generating one or more candidate targeting keywords or phrases for the ad using the logged search query terms. At least one of the candidate targeting keywords or phrases may be provided as targeting information for the ad. Alternatively, at least one of the candidate targeting keywords or phrases may be presented to the advertiser. Advertiser input with respect to the candidate targeting keyword(s) or phrase(s) presented may then be accepted. Zero or more of the candidate targeting keyword(s) or phrase(s) may be provided as targeting information for the ad, in accordance with the accepted advertiser input. Cost information (e.g., average cost per selection, average cost per conversion, total costs, etc.) may be presented in association with the candidate targeting information.

Traffic assistance similar to that provided by Google acquisition Zipdash is the focus of the next document, and Zipdash is named as a service that would use this process. Some integration of local search and advertising is hinted at in the filing.

Transportation routing
Inventors: Henry Rowley, and Shumeet Baluja
US Patent Application 20060149461
Published July 6, 2006
Filed on December 31, 2004

Abstract

A computer-implemented method of providing personalized route information involves gathering a plurality of past location indicators over time for a wireless client device, determining a future driving objective using the plurality of previously-gathered location indicators, obtaining real-time traffic data for an area proximate to the determined driving objective, and generating a suggested route for the driving objective using the near real-time traffic data.

How are the layouts of ads best optimized? What size fonts are used, and how many ads are displayed on pages? Google explores some of those concepts, and notes that the presentation ideas for ads in the following document also may be used to present news items on search results pages.

Ad rendering parameters, such as size, style, and/or layout, of online ads
Inventors: Shumeet Baluja, Vibhu Mittal, and Mehran Sahami
US Patent Application 20060149622
Published July 6, 2006
Filed on December 30, 2004

Abstract

Ad rendering parameters for a set of two or more ads may be determined by (a) accepting, for a set of two or more ads, ad information which includes at least one ad feature having a value that depends on ad rendering parameters, and (b) determining ad rendering parameters for at least one ad from the set of two or more ads using the accepted ad information. The act of determining ad rendering parameters may use accepted ad rendering constraints. The ad rendering constraints may include space available for rendering the ads, a footprint available for rendering the ads, and/or a maximum number of ads permitted to be rendered. The act of determining ad rendering parameters may include maximizing a value associated with serving at least one ad from the set of two or more ads with ad rendering parameters subject to the ad rendering constraints. The ad rendering parameters may include sizes of the served ads, and/or a layout of the served ads.

Automating the approval process for paid ads could benefit Google and advertisers. What would such an approval process entail? The next document identifies a number of issues involved in approving an ad, and in followups on advertisements. It also describes a whitelist for exceptions to some of the policies that may keep ads from being approved.

Advertisement approval
Inventors: Gregory Joseph Badros, Robert J. Stets, and Lucy Zhang
US Patent Application 20060149623
Published July 6, 2006
Filed on December 30, 2004

Abstract

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.

Google Local Patent Applications

The following patent applications primarily look at local search, though some of the processes described within them may have broader reaching implications, such as the one on visual segmentation of information on pages.

Businesses associated with a specific location often don’t use paid search as part of their advertising strategy. This first patent application thoughtfully goes into some of the reasons why, and explores ways to make it a more attractive medium, including expanded pay-per-call functionality, as well as providing information such as business hours and types of payment accepted.

Generating and/or serving local area advertisements, such as advertisements for devices with call functionality
Inventors: Shumeet Baluja and Henry A. Rowley
US Patent Application 20060149624
Published July 6, 2006
Filed on December 30, 2004

Abstract

Sets of local, (e.g., online) ads may be generated by obtaining sets of information about (e.g., local) establishments, each set including a business address information and/or a telephone number, (b) determining, for each of the sets, a location using at least one of at least a portion of the business address information and at least a portion of the telephone number, and (c) generating, for each of the sets, an ad that includes targeting information that targets the serving of the ad to queries related to the determined location. A query, including information about a location of a client device, may be accepted and at least one of the generated ads that includes targeting information that targets the location of the client device may be determined.

How does a local search determine which document is the most relevant and authoritative one to return at the top of a local search list? A number of factors are considered in this next set of described processes.

Authoritative document identification
Inventors: Daniel Egnor and Geeta Chaudhry
US Patent Application 20060149800
Published July 6, 2006
Filed on December 30, 2004

Abstract

A system determines documents that are associated with a location, identifies a group of signals associated with each of the documents, and determines authoritativeness of the documents for the location based on the signals.

If you are familiar with Microsoft’s research on VIPS: a VIsion based Page Segmentation Algorithm, some of the ideas in the next document may sound a little familiar. Imagine a page that includes restaurant reviews for a number of restaurants in a city neighborhood. Might the information from that page be segmented, so that reviews for each of the restaurants can be included in results for the right restaurants in a local search? This visual gap approach might be helpful in that endeavor.

The document also notes that this process might be helpful in determining what an image is about, and in indexing them. It also mentions that it could help the search engine understand what the different parts of a page are, and how much value they have (for instance, distinqusihing between content and navigation.)

Document segmentation based on visual gaps
Inventors: Daniel Egnor
US Patent Application 20060149775
Published July 6, 2006
Filed on December 30, 2004

Abstract

A document may be segmented based on a visual model of the document. The visual model is determined according to an amount of visual white space or gaps that are in the document. In one implementation, the visual model is used to identify a hierarchical structure of the document, which may then be used to segment the document.

While a search engine may be able to determine where a business related to a page is located, it may want to associate that location with a geographical region. Something like a Hierarchical Triangular Mesh may be used to help in making that association.

Indexing documents according to geographical relevance
Inventors: Daniel Egnor
US Patent Application 20060149774
Published July 6, 2006
Filed on December 30, 2004

Abstract

A local search engine efficiently indexes documents relevant to a geographical area by indexing, for each document, multiple location identifiers that collectively define an aggregate geographic region. When creating the index, the search engine may determine a set of geographical areas surrounding a geographical area relevant to a document and associate references to the set of geographical areas with the document index.

It’s not always clear what the geographic location of a webpage is, based upon information presented on individual pages, though sometimes that type of information exists on the pages. The process displayed in this next filing tries to take information that may be spread out on a page, and tie it together to identify a location.

Classification of ambiguous geographic references
Inventors: Daniel Egnor
US Patent Application 20060149742
Published July 6, 2006
Filed on December 30, 2004

Abstract

A location classifier generates location information based on textual strings in input text. The location information defines potential geographical relevance of the input text. In determining the location information, the location classifier may receive at least one geo-relevance profile associated with at least one string in the input text, obtain a combined geo-relevance profile for the document from the at least one geo-relevance profile, and determine geographical relevance of the input text based on the combined geo-relevance profile.

Imagine if a search engine could serve either regular web search results or local results. Some search queries could be ambiguous, and may make it difficult to determine whether to serve local search information or general web search results. The inventors of the next document provide some ideas that may reduce some of that ambiguity a little.

Location extraction
Inventors: Daniel Egnor and Lawrence Elias Greenfield
US Patent Application 20060149734
Published July 6, 2006
Filed on December 30, 2004

Abstract

A system receives a search query that includes a set of search terms, determines whether at least one of the search terms corresponds to the name of a geographic area, and determines whether the geographic area corresponds to an unambiguous geographic area when at least one of the search terms corresponds to the name of the geographic area. The system performs a local search, based on one or more of the search terms, to identify documents associated with the geographic area when the geographic area corresponds to an unambiguous geographic area.

The title of this patent application, and the previous one are so similar, that I was concerned they might be duplicates when I uncovered them. The one above attempts to “extract” location information from a query. This next one attempts to “extract” location information from pages being indexed, with confidence scores indicating how likely it is that business information on a page is associated with an address on the same page.

Local item extraction
Inventors: Michael Dennis Riley
US Patent Application 20060149565
Published July 6, 2006
Filed on December 30, 2004

Abstract

A system identifies a document that includes an address and locates business information in the document. The system assigns a confidence score to the business information, where the confidence score relates to a probability that the business information is associated with the address. The system determines whether to associate the business information with the address based on the assigned confidence score.

Microsoft

The titles of two Microsoft patent applications are very similar, but the processes described aren’t. The first one looks at anchor text in links, and the titles to pages those links point to, to see if the anchor text is accurate. The second one looks at links on pages, using the Document Object Model, and tries to determine if they are valid links while simulating the experience of a user of the page viewing it with a browser. This may help a search engine understand dynamic html menus, and view links that may otherwise be unavailable to a search engine crawler.

Methods and apparatus for the evaluation of aspects of a web page
Inventors: Michael A. Starbird
Assigned to Microsoft
US Patent Application 20060150076
Published July 6, 2006
Filed on December 30, 2004

Abstract

Methods and apparatus are provided for evaluating the extent to which link text, representing a hypertext link on a web page, corresponds to a web page referenced by the link. In one embodiment, the link text may be compared to the title of a web page referenced by the link, such as by parsing the link text and page title into individual tokens and comparing the tokens. The extent to which the link text and the page title correspond may be expressed as a percentage of tokens which match. A graphical user interface (GUI) may be provided which presents a visual indication when a minimum percentage of tokens do not match.

Methods and apparatus for evaluating aspects of a web page
Inventors: Ryan Farber
Assigned to Microsoft
US Patent Application 20060150111
Published July 6, 2006
Filed on December 30, 2004

Abstract

An automated method is provided for evaluating the validity of links included in a web page. The web page may contain commands, such as dynamic HTML or other embedded commands, which are configured for execution upon the occurrence of an event, such as a provision of input by a user. According to one embodiment, the method includes causing the links to be generated by simulating the occurrence of the event. Upon the generation of the links, their validity may be determined, and a report may be produced which indicates whether the links are valid.

My usual reminder about patents: Some of the processes and technology described in patents are created in house, and some are developed with the assistance of contractors and partners. A percentage are never developed in a tangible manner, but may serve as a way to attempt to exclude others from using the technology, or even to possibly mislead competitors into exploring an area that they might not have an interest in (sometimes skepticism is good.)

There are times when a Google or Yahoo acquires a company to gain access to the intellectual property of that company, or the intellectual prowess and expertise of that company’s employees. And sometimes patents are just purchased.

Want to comment or discuss? Visit our Search Technology & Relevancy area of the Search Engine Watch Forums.

Resources

The 2023 B2B Superpowers Index
whitepaper | Analytics

The 2023 B2B Superpowers Index

8m
Data Analytics in Marketing
whitepaper | Analytics

Data Analytics in Marketing

10m
The Third-Party Data Deprecation Playbook
whitepaper | Digital Marketing

The Third-Party Data Deprecation Playbook

1y
Utilizing Email To Stop Fraud-eCommerce Client Fraud Case Study
whitepaper | Digital Marketing

Utilizing Email To Stop Fraud-eCommerce Client Fraud Case Study

1y