SEO Blog - Internet marketing news and views

SEO Geeks Picks 09; Microsoft Search Patents

Written by David Harry

Wednesday, 06 January 2010 15:52

Ok, so are you getting into the swing of things here? In this, our third instalment of our ‘Top Picks 09’ we’re getting into more patents. Cause yea, I know ya’ll just LOVE this stuff right? Well, hey, the next time you’re researching a given aspect of search, these lists can be very useful reading… Just sayin’

The folks at MS are easily the most active when it comes to search patents… actually, they’re also far more active than Google and Yahoo when it comes to research papers as well. While it hasn’t translated into a better engine or greater market share, they have proven themselves to be capable search engineers.

Once more there are a lot of patents on behavioural data (implicit/explicit user feedback) which is followed by an interest in semantic and query analysis. It does seem search engines are seeking methods outside of the traditional link model… Kudos for that!

Microsoft Patents 2009

Implicit/ Explicit


	Presenting result items based upon user behaviour Ranking and Providing Search Results Based In Part On A Number Of Click-Through Features Dynamic client interaction for search System and method for ranking search results based on tracked user preferences Specifying relevance ranking preferences utilizing search scopes Constricting web query hierarchies from click-through data Using related users data to enhance web search Adaptive dissemination of personalized and contextually relevant information Implicit links search enhancement system and method for search engines using implicit links generated by mining user access patterns Intent aware search Query classification based on query click logs Search system using user behavior data Identifying relevant information souces from user activity Dynamic search with implicit user intention mining System and method for personalized search Method and system for adapting search results to personal information needs

Semantic Analysis


	System and method for identifying base noun phrases Consistent phrase relevance measures Semantic canvas Method and system for performing phrase/word clustering and cluster merging System for automatically annotating training data for a natural language understanding system Method for finding semantically related search engine queries Ranking parser for a natural language processing system Context-based key phrase discovery and similarity measurement utilizing search engine query logs Flexible keyword searching

Query Analysis


	Finding candidate sub-queries from longer queries Query suggestions for no-result web searches Clustering web queries Methods and Systems for Improving a Search Ranking Using Related Queries Detecting zero-result search queries Query graphs indicating related queries Key phrase extraction from query logs Presenting query suggestions based upon content items User query data mining and related techniques Presenting search queries related to navigational queries Identifying on a graphical depiction candidate points and top moving queries Generating training data from click logs

Links


	Query dependent link-based ranking Query dependant link-based ranking using authority scores Calculating web page importance based on a conditional Markov random walk Link based ranking of search results using summaries of result neighbourhoods Look ahead document ranking system

Named Entities (navigational search)


	Determining query term synonyms within query context Domain Dictionary Creation (NLP for non-roman character sets) Word decompounder Integrating external related phrase information into a phrase based indexing IR system Semantic unit recognition Phrase-based generation of document descriptions Segmenting words using scaled probabilities Inferring search category synonyms from user logs

Ranking methods


	Technique to perform relative ranking for search results Ranking model adaptation for searching Ranking search results using biased click distance Search results ranking using editing distance and document information Fast ranked full-text searching Using connectivity distance for relevance feedback in search Document Length as a Static Relevance Feature for Ranking Search Results

Recommendation


	Search query transformation using direct manipulation Providing Suggestions During Formation of a Search Query Bucket-based searching Recommending queries when searching against keywords

Universal Search


	Identifying a web page as belonging to a blog Forum web page clustering based on repetitive regions Adaptive Visual Similarity for Text-Based Image Search Results Re-ranking

Recommendation Engine


	Category suggestions relating to a search

Geo-local


	Mapping network addresses to geographic locations Automobile location based advertising Providing search results for mobile computing devices

Social


	Integration of social networking and merchandising Social Network Powered query refinement and recommendations Rating computation on social networks

Crawling/Indexing


	Link discovery from web scripts Using core word to extract key phrases from documents Mining information based on relationships

Snippets


	Domain aware snippets for search results Query-based snippet clustering for search result grouping

Spam


	Multimedia spam determination using speech conversion

Speech Recognition


	Method of speech recognition using hidden trajectory Hidden Markov Models Method and apparatus for indexing speech Text based search query facilitated speech recognition

Infrastructure


	Search engine dash-board Inverse query engine systems with cache and methods for cache maintenance Acquiring web page information without commitment to downloading the web page Classifying search query traffic High scale adaptive search systems and methods Method for extracting information associated with a search term Vision-based document segmentation

Other


	Method and system for mining information based on relationships Domain knowledge-assisted information processing Generating a labeled hierarchy of mutually disjoint categories from a set of query results Search based on document associations Graph based keyword expansion Quality of web search results using a game Intelligent container index and search Determining relevance of documents to a query based on identifier distance

It seems the folks at MS are also interested in the more general processing aspects of search and not as much the geo/universal stuff. Oh, and the ones on speech recognition for search are also telling. I wonder why Google hasn’t got more in this area? Something to watch for in 2k10.

And there we have it. Next edition (posting shortly) will be for the search related patents from the folks at Yahoo. If you really want to learn more about how engines work, I suggest picking a category and reading up on patents from all 3 of the main engines. This can be a HUGE eye opener to any fastidious optimizer.

Stay Tuned