# US 10,455,034 B2 · Analyzing tracking requests generated by client devices interacting with a website > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,455,034 B2 - Document ID: US10455034B2 - Status: Granted - Kind: B2 - Application number: 15/636,504 - Filed: 2017-06-28 - Published: 2019-01-03 - Granted: 2019-10-22 - Earliest claimed: 2017-06-28 - Assignees: Facebook, Inc. - Applicants: Facebook, Inc. - Inventors: Shiliyang Xu; Aleksey Sergeyevich Fadeev - Web page: https://patentgrep.com/patent/US10455034B2 ## CPC - H04L 67/535: {Tracking the activity of the user (network monitoring arrangements H04L43/00; recording of computer activity G06F11/34)} - G06F 16/24578: {using ranking} - G06F 16/9535: Search customisation based on user profiles and personalisation - G06F 16/9536: Search customisation based on social or collaborative filtering - G06Q 30/0255: {based on user history} - H04L 67/02: based on web technology, e.g. hypertext transfer protocol [HTTP] - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - 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 An online system receives tracking requests from client devices interacting with a website to analyze user interactions with the website. The website provides instructions with web pages sent to a client device that cause the client device to send tracking instructions to the online system. The online system sends requests for web pages to the website, receives a plurality of web pages from the website, and determines a count of distinct web pages provided by the website. The online system determines a score for the website indicating a quality of tracking instructions of the website based on various factors, including an aggregate value based on the distinct webpages of the website that include tracking instructions and the count of distinct web pages provided by the website. Based on this score, the online system generates a report describing a quality of the tracking instructions of the website. ## Claims ### Claim 1 A computer-implemented method comprising: sending, by an online system, a plurality of requests for web pages of a web site; receiving, by the online system, a plurality of web pages from the website, each web page received responsive to a request for web page; determining, by the online system, an estimate of a count of distinct types of web pages provided by the website; receiving, by the online system, a plurality of tracking requests from one or more client devices, each tracking request received responsive to the client device presenting the web page received from the website, the webpage including tracking instructions configured to cause the client device executing the tracking instructions to generate the plurality of tracking requests, each tracking request including a label identifying the webpage; determining, by the online system, an estimate of a count of distinct types of web pages of the website based on the plurality of tracking requests received by the online system from the one or more client devices; determining a score for the website, the score indicating a quality of the tracking instructions of the website based on factors comprising the estimate of the count of the distinct types of web pages of the website that include the tracking instructions, the estimate of the count of distinct types of web pages provided by the website, and a measure of accuracy of labels of web pages obtained from the plurality of tracking requests; and generating a report describing the quality of the tracking instructions of the website based on the score. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein the factors comprise an aggregate value based on the distinct types of web pages of the website that include the tracking instructions. ### Claim 3 (depends on 2) The computer-implemented method of claim 2, wherein the aggregate value based on the distinct types of web pages of the website that include the tracking instructions represents a weighted aggregate of scores associated with web pages of the website that include the tracking instructions, wherein a web page that includes accurate labeling of the web page is weighted higher than a webpage that includes an inaccurate labeling of the web page. ### Claim 4 (depends on 3) The computer-implemented method of claim 3, further comprising: determining whether the web page of the website that includes the tracking instructions includes an accurate label, the determining comprising: predicting a label based on features describing the tracking request corresponding to the web page; comparing the predicted label with a label received from the tracking request; and determining that the tracking instructions of the web page include inaccurate label if the predicted label fails to match the label provided in the tracking instructions. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein the tracking request is received from the client device responsive to the client device rendering the web page for display, wherein rendering the web page causes execution of instructions for sending a tracking request to the online system. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, further comprising: for each of one or more tracking requests associated with the website, determining a signal intent score for the tracking request, the signal intent score indicating a likelihood of a user performing a particular user interaction with the website, the particular user interaction identified as a conversion for the website; and wherein the score for the website is further based on the signal intent scores of the plurality of tracking requests. ### Claim 7 (depends on 6) The computer-implemented method of claim 6, wherein a signal intent score for a tracking request associated with a web page is determined based on an order in which the web page occurs in a session between the client device and the website. ### Claim 8 (depends on 7) The computer-implemented method of claim 7, wherein a signal intent score for a tracking request associated with a web page that occurs later in a session is determined to be higher than a signal intent score for a tracking request associated with a web page that occurs earlier in a session. ### Claim 9 (depends on 1) The computer-implemented method of claim 1, further comprising: associating a particular webpage of the website with a user interaction identified as a conversion for the website; and wherein the score for the website is based on whether a tracking request associated with the particular web page includes a conversion value. ### Claim 10 (depends on 1) The computer-implemented method of claim 1, further comprising: responsive to the score of the website indicating a low quality of the tracking instructions, replacing labels received from tracking requests with predicted labels for generating a report describing user interactions with the website. ### Claim 11 (depends on 1) The computer-implemented method of claim 1, the factors further comprising a measure of accuracy of a label of a web page, wherein the measure of accuracy of the label of the web page is determined by comparing a label identifying the webpage predicted based on features corresponding to the identified web page and a label identifying the webpage received via the tracking request. ### Claim 12 A non-transitory computer readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to perform the steps including: sending, by an online system, a plurality of requests for web pages of a web site; receiving, by the online system, a plurality of web pages from the website, each web page received responsive to a request for web page; determining, by the online system, an estimate of a count of distinct types of web pages provided by the website; receiving, by the online system, a plurality of tracking requests from one or more client devices, each tracking request received responsive to the client device presenting the web page received from the website, the webpage including tracking instructions configured to cause the client device executing the tracking instructions to generate the plurality of tracking requests, each tracking request including a label identifying the webpage; determining, by the online system, an estimate of a count of distinct types of web pages of the website based on the plurality of tracking requests received by the online system from the one or more client devices; determining a score for the website, the score indicating a quality of the tracking instructions of the website based on factors comprising the estimate of the count of the distinct types of web pages of the website that include the tracking instructions, the estimate of the count of distinct types of web pages provided by the website, and a measure of accuracy of labels of web pages obtained from the plurality of tracking requests; and generating a report describing the quality of the tracking instructions of the website based on the score. ### Claim 13 (depends on 12) The non-transitory computer readable storage medium of claim 12, wherein the factors comprise an aggregate value based on the distinct types of web pages of the website that include the tracking instructions. ### Claim 14 (depends on 13) The non-transitory computer readable storage medium of claim 13, wherein the aggregate value based on the distinct types of web pages of the website that include the tracking instructions represents a weighted aggregate of scores associated with web pages of the website that include the tracking instructions, wherein a web page that includes accurate labeling of the web page is weighted higher than a webpage that includes an inaccurate labeling of the web page. ### Claim 15 (depends on 14) The non-transitory computer readable storage medium of claim 14, further comprising: determining whether the web page of the website that includes the tracking instructions includes an accurate label, the determining comprising: predicting a label based on features describing the tracking request corresponding to the web page; comparing the predicted label with a label received from the tracking request; and determining that the tracking instructions of the web page include inaccurate label if the predicted label fails to match the label provided in the tracking instructions. ### Claim 16 (depends on 12) The non-transitory computer readable storage medium of claim 12, wherein the tracking request is received from the client device responsive to the client device rendering the web page for display, wherein rendering the web page causes execution of instructions for sending a tracking request to the online system. ### Claim 17 (depends on 12) The non-transitory computer readable storage medium of claim 12, further comprising: for each of one or more tracking requests associated with the website, determining a signal intent score for the tracking request, the signal intent score indicating a likelihood of a user performing a particular user interaction with the website, the particular user interaction identified as a conversion for the website; and wherein the score for the website is further based on the signal intent scores of the plurality of tracking requests. ### Claim 18 (depends on 17) The non-transitory computer readable storage medium of claim 17, wherein a signal intent score for a tracking request associated with a web page is determined based on an order in which the web page occurs in a session between the client device and the website. ### Claim 19 (depends on 18) The non-transitory computer readable storage medium of claim 18, wherein a signal intent score for a tracking request associated with a web page that occurs later in a session is determined to be higher than a signal intent score for a tracking request associated with a web page that occurs earlier in a session. ### Claim 20 (depends on 12) The non-transitory computer readable storage medium of claim 12, further comprising: associating a particular webpage of the website with a user interaction identified as a conversion for the website; and wherein the score for the website is based on whether a tracking request associated with the particular web page includes a conversion value. ### Claim 21 (depends on 12) The non-transitory computer readable storage medium of claim 12, further comprising: responsive to the score of the website indicating a low quality of the tracking instructions, replacing labels received from tracking requests with predicted labels for generating a report describing user interactions with the website. ### Claim 22 (depends on 12) The non-transitory computer readable storage medium of claim 12, the factors further comprising a measure of accuracy of a label identifying a web page, wherein the measure of accuracy of the label identifying the web page is determined by comparing a label predicted based on features corresponding to the identified web page extracted from the tracking request and a label received in the tracking request.