# US 12,216,632 B2 · Search engine optimization by selective indexing > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,216,632 B2 - Document ID: US12216632B2 - Status: Granted - Kind: B2 - Application number: 18/516,184 - Filed: 2023-11-21 - Published: 2024-03-14 - Granted: 2025-02-04 - Earliest claimed: 2015-06-30 - Assignees: eBay Inc. - Applicants: eBay Inc. - Inventors: Satya Voleti; Ganesh Talele; Atiq ul Islam; Ritu Goel - Web page: https://patentgrep.com/patent/US12216632B2 ## CPC - G06F 16/2228: {Indexing structures} - G06F 16/951: Indexing; Web crawling techniques - G06F 16/958: Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking - G06N 20/00: Machine learning - G06N 20/20: Ensemble learning - G06Q 30/0623: {by investigating goods or services} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR ## Abstract Example embodiments involve a system and methods for identifying valuable view item pages for search engine optimization. The system and methods provide an improvement over existing systems, which do nothing to identify or select valuable view item pages for use in driving traffic from display sites. The system and methods described herein improve the earlier system by predicting the probability of future traffic for a given product based on a number of product level factors as input variables, and identifying a selection of view item pages corresponding to the products with the probability of the highest future traffic in order to maximize the driving natural search traffic to a linked site of the corresponding view item page. ## Claims ### Claim 1 A system comprising: one or more processors; and a memory coupled to the one or more processors and storing instructions that, when executed by the one or more processors, cause the system to perform operations comprising: calculating, for an item, a search traffic value indicating a probability of future traffic for the item; based on the search traffic value, assigning the item an index status, the index status indicating whether to assign an index tag to one or more pages corresponding to the item; identifying, from a database, a first page corresponding to the item; based on the index status, assigning the index tag to the first page, the index tag providing an indication to return the first page in response to a search for the item; and returning the first page based on a search request for the item and the index tag assigned to the first page. ### Claim 2 (depends on 1) The system of claim 1, wherein the operations further comprise: generating a machine learned model data object based at least in part on a portion of item level factors of a set of pages for the item; and training the machine learned model object, wherein calculating the search traffic value comprises using the trained machine learned model data object to calculate the search traffic value. ### Claim 3 (depends on 2) The system of claim 2, wherein the machine learned model data object comprises a gradient boosted machine model. ### Claim 4 (depends on 1) The system of claim 1, wherein the calculating comprises identifying a set of item level factors corresponding to the probability of future traffic, wherein the calculating the search traffic value is based at least in part on the set of item level factors. ### Claim 5 (depends on 1) The system of claim 1, wherein the operations further comprise: identifying a second page for a second item; determining to assign a no-index tag to the second page for the second item based on a second search traffic value associated with the second page failing to satisfy a threshold search traffic value; and assigning the no-index tag to the second page for the second item, the no-index tag providing an indication to refrain from returning the second page in response to user search. ### Claim 6 (depends on 1) The system of claim 1, wherein the operations further comprise: identifying, from a database and the first page for the item, a set of input variables associated with the item, wherein calculating the search traffic value is further based at least in part on the set of input variables associated with the item. ### Claim 7 (depends on 1) The system of claim 1, wherein assigning the index status is based on determining that the search traffic value for the item transgresses a threshold value. ### Claim 8 A method comprising: calculating, for an item, a search traffic value indicating a probability of future traffic for the item; based on the search traffic value, assigning an index status, the index status indicating whether to assign an index tag to one or more pages corresponding to the item; identifying, from a database, a first page corresponding to the item; based on the index status, assigning an index tag to the first page, the index tag providing an indication to return the first page in response to a search for the item; and returning the first page based on a search request for the item and the index tag assigned to the at least one page. ### Claim 9 (depends on 8) The method of claim 8, further comprising: generating a machine learned model data object based at least in part on a portion of item level factors of a set of pages for the item; and training the machine learned model object, wherein calculating the search traffic value comprises using the trained machine learned model data object to calculate the search traffic value. ### Claim 10 (depends on 9) The method of claim 9, wherein the machine learned model data object comprises a gradient boosted machine model. ### Claim 11 (depends on 8) The method of claim 8, wherein the calculating comprises identifying a set of item level factors corresponding to the probability of future traffic, wherein the calculating the search traffic value is based at least in part on the set of item level factors. ### Claim 12 (depends on 8) The method of claim 8, further comprising: identifying a second page for a second item; determining to assign a no-index tag to the second page for the second item based on a second search traffic value associated with the second page failing to satisfy a threshold search traffic value; and assigning the no-index tag to the second page for the second item, the no-index tag providing an indication to refrain from returning the second page in response to user search. ### Claim 13 (depends on 8) The method of claim 8, further comprising: identifying, from a database and the first page for the item, a set of input variables associated with the item, wherein calculating the search traffic value is further based at least in part on the set of input variables associated with the item. ### Claim 14 (depends on 8) The method of claim 8, wherein assigning the index status is based on determining that the search traffic value for the item transgresses a threshold value. ### Claim 15 A non-transitory machine-readable medium storing instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising: calculating, for an item, a search traffic value indicating a probability of future traffic for the item; based on the search traffic value, assigning the item an index status, the index status indicating whether to assign an index tag to one or more pages corresponding to the item; identifying, from a database, a first page corresponding to the item; based on the index status, assigning an index tag to the first page, the index tag providing an indication to return the first page in response to a search for the item; and returning the first page based on a search request for the item and the index tag assigned to the at least one page. ### Claim 16 (depends on 15) The machine-readable medium of claim 15, wherein the operations further comprise: generating a machine learned model data object based at least in part on a portion of item level factors of a set of pages for the item; and training the machine learned model object, wherein calculating the search traffic value comprises using the trained machine learned model data object to calculate the search traffic value. ### Claim 17 (depends on 16) The machine-readable medium of claim 16, wherein the machine learned model data object comprises a gradient boosted machine model. ### Claim 18 (depends on 15) The machine-readable medium of claim 15, wherein the calculating comprises identifying a set of item level factors corresponding to the probability of future traffic, wherein the calculating the search traffic value is based at least in part on the set of item level factors. ### Claim 19 (depends on 15) The machine-readable medium of claim 15, wherein the operations further comprise: identifying a second page for the item or a second item; determining to assign a no-index tag to the second page for the item or the second item based on a second search traffic value associated with the second page failing to satisfy a threshold search traffic value; and assigning the no-index tag to the second page for the item or the second item, the no-index tag providing an indication to refrain from returning the second page in response to user search. ### Claim 20 (depends on 15) The machine-readable medium of claim 15, wherein the operations further comprise: identifying, from a database and the first page for the item, a set of input variables associated with the item, wherein calculating the search traffic value is further based at least in part on the set of input variables associated with the item.