System and method for mark-up language document rank analysis

Abstract

A system and method for mark-up language document rank analysis that may be performed automatically and that may also determine one or more differences between mark-up language documents with regard to their relative rank.

What is claimed is: 
     
         1 . A method for analyzing a mark-up language document that is indexable by an internet based indexing computer program, the method being performed by a computer, the method comprising: inputting at least one search keyword to the internet based indexing computer program through the internet; receiving a response to said inputting, said response including at least one returned mark-up language document; analyzing said response according to a supervised training procedure; and analyzing the mark-up language document according to said at least one search keyword and said analysis of said response according to said supervised training procedure. 
     
     
         2 . The method of  claim 1 , wherein said inputting said at least one search keyword comprises inputting a plurality of search keywords related to a specific subject, and wherein said analyzing said response comprises determining a difference between the different search keywords in said response by the internet based indexing computer program. 
     
     
         3 . The method of  claim 1 , wherein said analyzing said response according to said supervised training procedure comprises receiving a plurality of returned mark-up language documents, including the target mark-up language document, and a relative rank of each returned mark-up language document; determining a relative rank of the target mark-up language document with regard to said plurality of returned mark-up language documents; and analyzing at least one feature of the target mark-up language in comparison to said plurality of returned mark-up language documents and said relative rank of the target mark-up language document. 
     
     
         4 . The method of  claim 3 , wherein said feature is selected from the group consisting of content, metadata and structure. 
     
     
         5 . The method of  claim 4 , wherein said content is selected from the group consisting of javascript, text, images, any type of media including multimedia, and any other suitable type of content. 
     
     
         6 . The method of  claim 5 , wherein said analyzing said content of the target mark-up language comprising analyzing said returned mark-up language documents to determine a placement of said search keyword therein. 
     
     
         7 . The method of  claim 6 , wherein said analyzing said content further comprises comparing a keyword density of said search keyword in said returned mark-up language documents to a keyword density in the target mark-up language document with regard to said relative rank. 
     
     
         8 . The method of  claim 6 , wherein said analyzing said content further comprises comparing a keyword location of said search keyword in said returned mark-up language documents to a keyword location in the target mark-up language document with regard to said relative rank. 
     
     
         9 . The method of  claim 5 , wherein the mark-up language document is a web page and said analyzing said content further comprises analyzing said content according to a parameter including one or more of keyword use anywhere in the title tag, keyword use as the first word(s) of the title tag, keyword use in the root domain name in the url, keyword use anywhere in the h1 headline tag, keyword use in internal link anchor text on the page, keyword use in external link anchor text on the page, keyword use as the first word(s) in the h1 tag, keyword use in the first 50-100 text words in the document, keyword use in the subdomain name of the url, keyword use in the page name url, keyword use in the page folder, url keyword use in other headline tags (<h2>-<h6>), keyword use in image alternative text, keyword use in image names, keyword use in <b> or <strong> tags, keyword use in list items <li> on the page, keyword use in the page's query parameters, keyword use in <i> or <em> tags, keyword use in the meta description tag, keyword use in the page's file extension, keyword use in comment tags in the web page, keyword use in the meta keywords tag, freshness of page creation, use of links on the page that point to other urls on this domain, frequency of updating page content, use of external-pointing links on the page, query parameters in the url vs. static url format, ratio of code to text in html, existence of a meta description tag, html validation to w3c standards, use of flash elements (or other plug-in content), or use of advertising on the page. 
     
     
         10 . The method of  claim 3  wherein said metadata is selected from the group consisting of a mark-up tag and a description of a mark-up tag. 
     
     
         11 . The method of  claim 9 , wherein said mark-up tag is selected from the group consisting of a metatag, a page title and a section title. 
     
     
         12 . The method of  claim 10 , wherein said analyzing said feature comprises analyzing said metadata of said returned mark-up language documents in comparison to the target mark-up language document with regard to said relative rank. 
     
     
         13 . The method of  claim 11 , wherein said metadata comprises a mark-up language tag or description of said tag, and wherein said analyzing said mark-up language tag or description of said tag further comprises comparing said mark-up language tag or description of said tag in said returned mark-up language documents in comparison to the target mark-up language document with regard to said relative rank. 
     
     
         14 . The method of  claim 12 , wherein said analyzing said mark-up language tag or description of said tag further comprises providing a plurality of mark-up language tag keywords; searching said mark-up language tag or description of said tag in said returned mark-up language documents for said plurality of mark-up language tag keywords; searching the target mark-up language document for said plurality of mark-up language tag keywords; and comparing the target mark-up language document and said returned mark-up language documents according to said relative rank. 
     
     
         15 . The method of  claim 10 , wherein said analyzing said returned mark-up language documents further comprises determining a location of each mark-up language tag keyword in said returned mark-up language documents; determining a location of each mark-up language tag keyword in the target mark-up language; and comparing said respective locations. 
     
     
         16 . The method of  claim 4 , wherein said structure is selected from the group consisting of location of a plurality of components, use of containers, rules of dynamic web pages, URL. 
     
     
         17 . The method of  claim 3 , wherein said analyzing said plurality of returned mark-up language documents further comprises determining at least one difference in metadata keywords between a lower ranked returned mark-up language document and a higher ranked returned mark-up language document. 
     
     
         18 . The method of  claim 16 , wherein said analyzing said plurality of returned mark-up language documents further comprises determining at least one difference in structure between a lower ranked returned mark-up language document and a higher ranked returned mark-up language document. 
     
     
         19 . The method of  claim 16 , wherein said analyzing said response according to said supervised training procedure further comprises training said supervised training procedure according to a plurality of returned mark-up language documents and according to a relative rank of said plurality of returned mark-up language documents. 
     
     
         20 . The method of  claim 16 , wherein said supervised training procedure comprises, but not limited to, one or more of the following approaches and methods: analytical learning, artificial neural network, Backpropagation, Bayesian analysis, Decision Trees, Case Based Reasoning, Inductive Logic Programming, Gaussian process regression, Kernel estimators, Learning Automata, Minimum message length (decision trees, decision graphs, etc.), Naive bayes classifier, Nearest Neighbor Algorithm, Probably approximately correct learning, Ripple down rules, Symbolic machine learning algorithms, Subsymbolic machine learning algorithms, Support vector machines, Random Forests, Ensembles of Classifiers, Ordinal Classification, Data Pre-processing, Handling imbalanced datasets, Statistical relational learning. 
     
     
         21 . The method of  claim 1 , further comprising determining at least one change to the mark-up language document according to said analyzed response. 
     
     
         22 . The method of  claim 20 , wherein said determining said at least one change comprises one or more of determining a changed content, a changed structure or a changed metadata. 
     
     
         23 . The method of  claim 21 , wherein said determining said at least one change comprises increasing keyword density of at least one keyword in said target mark-up language document. 
     
     
         24 . The method of  claim 21 , further comprising changing the mark-up language document with at least one change by a user; and displaying a result of said at least one change to the mark-up language document to the user. 
     
     
         25 . The method of  claim 23 , wherein said displaying said result to the user comprises indicating an increase or decrease in potential rank of the mark-up language document by the internet based indexing computer program. 
     
     
         26 . The method of  claim 3 , wherein the internet based indexing program comprises a plurality of programs and wherein the method is performed for each of said programs. 
     
     
         27 . The method of  claim 25 , wherein each of said plurality of programs has a separate geographical location and the method is performed separately for each geographical location. 
     
     
         28 . The method of  claim 3 , wherein said feature comprises a plurality of features, the method further comprising performing PCA to reduce a number of features before said analyzing and said comparing are performed. 
     
     
         29 . The method of  claim 3 , wherein said comparing comprises performing a distance measurement; and comparing the target mark-up language document to said plurality of received mark-up language documents according to said distance measurement. 
     
     
         30 . The method of  claim 28 , wherein said distance measurement is selected from the group consisting of L1, LDA (Latent Dirichlet Allocation) and L2. 
     
     
         31 . The method of  claim 1 , further comprising generating a lexicon according to said supervised training. 
     
     
         32 . The method of  claim 21 , further comprising determining an effect of said at least one change on a search engine ranking of said mark-up language document; and comparing actual and predicted search engine rankings to determine whether said effect is expected. 
     
     
         33 . The method of  claim 32 , wherein if said effect has a sufficiently great difference than an expected effect, performing said supervised training again.