# US 12,216,985 B2 · Analysis and restructuring of web pages of a web site > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,216,985 B2 - Document ID: US12216985B2 - Status: Granted - Kind: B2 - Application number: 18/598,822 - Filed: 2024-03-07 - Published: 2024-06-27 - Granted: 2025-02-04 - Earliest claimed: 2021-10-11 - Assignees: Graphite Growth, Inc. - Applicants: Graphite Growth, Inc. - Inventors: Gregory Druck; Ethan Smith; Marcos Ciarrocchi; Jerick Ordenes - Web page: https://patentgrep.com/patent/US12216985B2 ## CPC - G06F 40/134: Hyperlinking - G06F 16/951: Indexing; Web crawling techniques - G06F 16/953: Querying, e.g. by the use of web search engines - G06F 16/954: Navigation, e.g. using categorised browsing - G06F 16/958: Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking - G06F 40/143: Markup, e.g. Standard Generalized Markup Language [SGML] or Document Type Definition [DTD] - G06F 40/194: Calculation of difference between files - G06F 40/30: Semantic analysis - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A structural analysis system analyzes the pages of a web site, including the content of the pages and their relationships to each other. Based on the analysis, the structural analysis system additionally modifies (or suggests modification of) the web pages of the web site, such as by altering the inter-page linking structure of the web site. This improves the structure of the web site, leading search engines to be able to more quickly find and index its pages, as well as increasing the expected ranking that a search engine would provide to pages of the web site within the set of search results provided by the search engine in response to a user query. ## Claims ### Claim 1 A computer-implemented method for improving a determined search engine ranking of a plurality of pages of a website by analyzing and adjusting a link structure of the website, the method comprising: quantifying degrees of semantic similarity between pairs of pages of the plurality of pages on the website according to a similarity metric; for each page of the plurality of pages of the website: determining a total count of incoming links to the page from other pages of the plurality of pages of the website; determining a total count of outgoing links from the page to other pages of the plurality of pages; determining a relevance score for a modified link structure for the website, the relevance score based on the quantified degrees of semantic similarity between pairs of pages on the website, the total count of incoming links of each page and the total count of outgoing links of each page; and adding additional links between pairs of pages on the website to solve an optimization problem that maximizes the relevance score of the modified link structure for the website. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, further comprising: determining, for each page of the plurality of pages, whether the determined total count of incoming links is less than a threshold number of incoming links, and wherein adding additional links between pairs of pages to solve the optimization problem is additionally based on determining that the respective page has the total count of income links that is at most the threshold number of incoming links. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, further comprising: determining, for each page of the plurality of pages, whether the determined total count of outgoing links is less than a threshold number of outgoing links, and wherein adding additional links between pairs of pages to solve the optimization problem is additionally based on determining that the respective page has the total count of outgoing links that is less than the threshold number of outgoing links. ### Claim 4 (depends on 1) The computer-implemented method of claim 1, wherein quantifying the degrees of the similarity comprises analyzing at least one of page titles, page body text, or page tags. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein adding additional links between pairs of pages to solve the optimization problem comprises optimizing an assignment of the links between pages to maximize an aggregate similarity of pairs of pages on the website. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein adding links between pairs of pages comprises iteratively adding links from a page to a most similar page according to semantic similarity between the pages. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, further comprising computing the total count of incoming links individually for each page by: determining a topic for the page; computing a predicted number of visits for pages having the topic; computing a traffic gap for a page by comparing the predicted number of visits for pages having the topic to an observed actual number of visits for the page; and determining a relevance score for a modified link structure for the website is based on the traffic gap. ### Claim 8 A non-transitory computer-readable storage medium storing instructions for improving a determined search engine ranking of a plurality of pages of a website by analyzing and adjusting a link structure of the website, the instructions, when executed by one or more processors, causing the one or more processors to: quantify degrees of semantic similarity between pairs of pages of the plurality of pages on the website according to a similarity metric; for each page of the plurality of pages of the website: determine a total count of incoming links to the page from other pages of the plurality of pages of the website; determine a total count of outgoing links from the page to other pages of the plurality of pages; determine a relevance score for a modified link structure for the website, the relevance score based on the quantified degrees of semantic similarity between pairs of pages on the website, the total count of incoming links of each page and the total count of outgoing links of each page; and add additional links between pairs of pages on the website to solve an optimization problem that maximizes the relevance score of the modified link structure for the website. ### Claim 9 (depends on 8) The non-transitory computer-readable storage medium of claim 8, wherein the instructions, when executed by the one or more processors, cause the one or more processors to: determining, for each page of the plurality of pages, whether the determined total count of incoming links is less than a threshold number of incoming links, and wherein adding additional links between pairs of pages to solve the optimization problem is additionally based on determining that the respective page has the total count of income links that is at most the threshold number of incoming links. ### Claim 10 (depends on 8) The non-transitory computer-readable storage medium of claim 8, wherein the instructions, when executed by the one or more processors, cause the one or more processors to: determining, for each page of the plurality of pages, whether the determined total count of outgoing links is less than a threshold number of outgoing links, and wherein adding additional links between pairs of pages to solve the optimization problem is additionally based on determining that the respective page has the total count of outgoing links that is less than the threshold number of outgoing links. ### Claim 11 (depends on 8) The non-transitory computer-readable storage medium of claim 8, wherein quantifying the degrees of the similarity further causes the one or more processors to: analyze at least one of page titles, page body text, or page tags. ### Claim 12 (depends on 8) The non-transitory computer-readable storage medium of claim 8, wherein adding additional links between pairs of pages to solve the optimization problem further causes the one or more processors to: optimize an assignment of the links between pages to maximize an aggregate similarity of pairs of pages on the website. ### Claim 13 (depends on 8) The non-transitory computer-readable storage medium of claim 8, wherein adding links between pairs of pages further causes the one or more processors to: iteratively add links from a page to a most similar page according to semantic similarity between the pages. ### Claim 14 (depends on 8) The non-transitory computer-readable storage medium of claim 8, wherein the instructions, when executed by the one or more processors, cause the one or more processors to: compute the total number of incoming links individually for each page by: determining a topic for the page; computing a predicted number of visits for pages having the topic; computing a traffic gap for a page by comparing the predicted number of visits for pages having the topic to an observed actual number of visits for the page; and determining a relevance score for a modified link structure for the website is based on the traffic gap. ### Claim 15 A system comprising: one or more processors; and a non-transitory computer-readable storage medium storing instructions for improving a determined search engine ranking of a plurality of pages of a website by analyzing and adjusting a link structure of the website, the instructions, when executed by one or more processors, causing the one or more processors to: quantify degrees of semantic similarity between pairs of pages of the plurality of pages on the website according to a similarity metric; for each page of the plurality of pages of the website: determine a total count of incoming links to the page from other pages of the plurality of pages of the website; determine a total count of outgoing links from the page to other pages of the plurality of pages; determine a relevance score for a modified link structure for the website, the relevance score based on the quantified degrees of semantic similarity between pairs of pages on the website, the total count of incoming links of each page and the total count of outgoing links of each page; and add additional links between pairs of pages on the website to solve an optimization problem that maximizes the relevance score of the modified link structure for the website. ### Claim 16 (depends on 15) The system of claim 15, wherein the instructions, when executed by the one or more processors, cause the one or more processors to: determining, for each page of the plurality of pages, whether the determined total count of incoming links is less than a threshold number of incoming links, and wherein adding additional links between pairs of pages to solve the optimization problem is additionally based on determining that the respective page has the total count of income links that is at most the threshold number of incoming links. ### Claim 17 (depends on 15) The system of claim 15, wherein the instructions, when executed by the one or more processors, cause the one or more processors to: determining, for each page of the plurality of pages, whether the determined total count of outgoing links is less than a threshold number of outgoing links, and wherein adding additional links between pairs of pages to solve the optimization problem is additionally based on determining that the respective page has the total count of outgoing links that is less than the threshold number of outgoing links. ### Claim 18 (depends on 15) The system of claim 15, wherein quantifying the degrees of the similarity further causes the one or more processors to: analyze at least one of page titles, page body text, or page tags. ### Claim 19 (depends on 15) The system of claim 15, wherein adding additional links between pairs of pages to solve the optimization problem further causes the one or more processors to: optimize an assignment of the links between pages to maximize an aggregate similarity of pairs of pages on the website. ### Claim 20 (depends on 15) The system of claim 15, wherein adding links between pairs of pages further causes the one or more processors to: iteratively add links from a page to a most similar page according to semantic similarity between the pages.