# US 8,751,435 B2 · System and method for determining client-based user behavioral analytics > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 8,751,435 B2 - Document ID: US8751435B2 - Status: Granted - Kind: B2 - Application number: 12/978,119 - Filed: 2010-12-23 - Published: 2012-06-28 - Granted: 2014-06-10 - Earliest claimed: 2010-12-23 - Assignees: Intel Corporation - Applicants: Krishnamurthy Sridharan; Ashok Sunder Rajan - Inventors: Krishnamurthy Sridharan; Ashok Sunder Rajan - Web page: https://patentgrep.com/patent/US8751435B2 ## CPC - G06Q 30/02: Marketing; Price estimation or determination; Fundraising - 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 A method, system, and device for determining client-based user behavioral analytics includes monitoring for a predetermined behavioral event on a computing device. The predetermined behavioral event may be embodied as any event initiated by the user on the computing device such as the purchase of a product, selection of a web link, navigation to a website, etc. In response to an occurrence of the predetermined behavioral event, an affinity metric and an avidity metric are determined based on a frequency of the occurrences of the predetermined behavioral event. A behavioral index for the user is determined based on the affinity metric and the avidity metric. Additionally, in response to receiving a request for the behavioral index, the computing device may transmit the behavioral index to a content provider server or other remote computer and receive content from the content provider, which has been selected based on the user's behavioral index. ## Claims ### Claim 1 A method comprising: monitoring for a predetermined behavioral event initiated by a user on a client computer; determining, on the client computer, an affinity metric for the predetermined behavioral event in response to an occurrence of the predetermined behavioral event, wherein determining the affinity metric comprises (i) determining a frequency of occurrence of the predetermined behavioral event for each of a plurality of first time periods, (ii) comparing the determined frequencies of occurrence of the predetermined behavioral event, and (iii) determining a historical trend of the frequency of occurrence of the predetermined behavioral event over a second time period equal to the sum of the plurality of first time periods based on the comparison of the determined frequencies; determining, on the client computer, an avidity metric for the predetermined event in response to the occurrence of the predetermined behavioral event, wherein the avidity metric is indicative of a ranking of the frequency of occurrences relative to a predetermined criteria; and determining, on the client computer, a behavioral index for the user based on the affinity metric and the avidity metric. ### Claim 2 (depends on 1) The method of claim 1, further comprising determining the frequency of occurrences of the predetermined behavioral event, wherein the frequency of occurrences is indicative of the number of occurrences during a first time period, and wherein: determining the affinity metric comprises determining the affinity metric based on the frequency of occurrences of the predetermined behavioral event, and determining the avidity metric comprises determining the avidity metric based on the frequency of occurrences of the predetermined behavioral event. ### Claim 3 (depends on 2) The method of claim 2, wherein the affinity metric is indicative of a trend in the frequency of occurrences of the predetermined behavioral event over a second time period, the second time period being a multiple of the first time period. ### Claim 4 (depends on 3) The method of claim 3, wherein determining the affinity metric comprises: assigning a first affinity group to the predetermined behavioral event in response to the frequency of occurrences of the predetermined behavioral event being determined to be decreasing over the second time period; assigning a second affinity group to the predetermined behavioral event in response to the frequency of occurrences of the predetermined behavioral event being determined to be increasing over the second time period; and assigning a third affinity group to the predetermined event in response to the frequency of occurrences of the predetermined behavioral event being determined to be substantially constant over the second time period. ### Claim 5 (depends on 2) The method of claim 2, wherein the avidity metric is indicative of a ranking of a total number of occurrences of the predetermined behavioral event within a second time period relative to a predetermined range of total occurrences, the second time period being a multiple of the first time period. ### Claim 6 (depends on 5) The method of claim 5, wherein determining the avidity metric comprises: assigning a first avidity group to the predetermined event in response to the total number of occurrences of the predetermined behavioral event (i) being greater than a predetermined first percentage of the predetermined range of total occurrences and (ii) being substantially consistent over a third time period, the third period of time being a multiple of the second time period; assigning a second avidity group to the predetermined event in response to the total number of occurrences of the predetermined behavioral event (i) being less than a predetermined second percentage of the predetermined range of total occurrences and (ii) being substantially consistent over the third time period; and assigning a third avidity group to the predetermined event in response to the total number of occurrences of the predetermined behavioral event (i) being within the predetermined range of total occurrences and (ii) being substantially inconsistent over the third time period. ### Claim 7 (depends on 6) The method of claim 6, wherein the first percentage is approximately 20% and the second percentage is approximately 80% percent. ### Claim 8 (depends on 5) The method of claim 5, wherein determining the avidity metric comprises determining the avidity metric according to a second order function based on historical data of the frequency of the occurrences of the predetermined behavioral event over a second time period, the second time period being a multiple of the first time period. ### Claim 9 (depends on 1) The method of claim 1, further comprising storing the behavior index on the client computer in a secure location. ### Claim 10 (depends on 1) The method of claim 1, wherein the predetermined behavioral event is an event initiated by the user on the client computer selected from the group consisting of: purchasing a predetermined product, navigating to a predetermined website, and selecting a predetermined hyperlink. ### Claim 11 (depends on 1) The method of claim 1, further comprising: receiving, on the client computer, a request from a content provider for the behavior index; transmitting the behavior index to the content provider in response to the request; and receiving content from the content provider in response to transmitting the behavior index. ### Claim 12 (depends on 1) The method of claim 1, wherein determining an affinity metric, determining an avidity metric, and determining a behavior analytic index are each performed by a secure processor. ### Claim 13 (depends on 12) The method of claim 12, wherein the secure processor is a processor selected from the group consisting of: a trusted platform manager (TPM) processor or an out-of-band processor. ### Claim 14 A computing device comprising: a processor; a memory device electrically coupled to the processor, the memory device including therein a plurality of instructions that, when executed by the processor, result in the processor: monitoring for a predetermined behavioral event initiated by a user on the computing device; updating, in response to an occurrence of the predetermined behavioral event, a frequency of occurrences of the predetermined behavioral event, the frequency of occurrences being indicative of the number of occurrences during a first time period; determining an affinity metric for the predetermined behavioral event based on the frequency of occurrences, wherein determining the affinity metric comprises (i) determining a frequency of occurrence of the predetermined behavioral event for each of a plurality of first time periods, (ii) comparing the determined frequencies of occurrence of the predetermined behavioral event, and (iii) determining a historical trend of the frequency of occurrence of the predetermined behavioral event over a second time period equal to the sum of the plurality of first time periods based on the comparison of the determined frequencies, wherein the second time period being a multiple of the first time period; determining an avidity metric for the predetermined event based on the frequency of occurrences, the avidity metric being indicative of a ranking of a total number of occurrences of the predetermined behavioral event within the second time period relative to a predetermined range of total occurrences; and determining a behavior analytic index for the user based on the affinity metric and the avidity metric. ### Claim 15 (depends on 14) The computing device of claim 14, wherein determining the affinity metric comprises: assigning a first affinity group to the predetermined behavioral event in response to the frequency of occurrences of the predetermined behavioral event being determined to be decreasing over the second time period; assigning a second affinity group to the predetermined behavioral event in response to the frequency of occurrences of the predetermined behavioral event being determined to be increasing over the second time period; assigning a third affinity group to the predetermined event in response to the frequency of occurrences of the predetermined behavioral event being determined to be substantially constant over the second time period; and assigning a fourth affinity group to the predetermined event in response to the frequency of occurrences of the predetermined behavioral event being determined to be substantially zero over the second time period. ### Claim 16 (depends on 14) The computing device of claim 14, wherein determining the avidity metric comprises: assigning a first avidity group to the predetermined event in response to the total number of occurrences of the predetermined behavioral event (i) being greater than a predetermined first percentage of the predetermined range of total occurrences and (ii) being substantially consistent over a third time period, the third period of time being a multiple of the second time period; assigning a second avidity group to the predetermined event in response to the total number of occurrences of the predetermined behavioral event (i) being less than a predetermined second percentage of the predetermined range of total occurrences and (ii) being substantially consistent over the third time period; assigning a third avidity group to the predetermined event in response to the total number of occurrences of the predetermined behavioral event (i) being within the predetermined range of total occurrences and (ii) being substantially inconsistent over the third time period; and assigning a fourth avidity group to the predetermined event in response to the total number of occurrences of the predetermined behavioral event (i) being outside the predetermined range of total occurrences and (ii) being substantially consistent over the fourth over the third time period. ### Claim 17 (depends on 14) The computing device of claim 14, wherein the processor is a secure processor selected from the group consisting of: a trusted platform manager (TPM) processor or an out-of-band processor. ### Claim 18 A non-transitory, machine readable medium comprising a plurality of instructions that, in response to being executed, result in a client computer: determining an affinity metric for the predetermined behavioral event in response to an occurrence of a predetermined behavioral event initiated by a user on the client computer, wherein determining the affinity metric comprises (i) determining a frequency of occurrence of the predetermined behavioral event for each of a plurality of first time periods, (ii) comparing the determined frequencies of occurrence of the predetermined behavioral event, and (iii) determining a historical trend of the frequency of occurrence of the predetermined behavioral event over a second time period equal to the sum of the plurality of first time periods based on the comparison of the determined frequencies; determining an avidity metric for the predetermined event in response to the occurrence of the predetermined behavioral event, wherein the avidity metric is indicative of a ranking of the frequency of occurrences relative to a predetermined criteria; determining a behavioral index for the user based on the affinity metric and the avidity metric; transmitting the behavioral index to a content provider server in response to receiving a request from the content provider server for the behavior index request; and receiving content from the content provider server in response to transmitting the behavior index, the content being selected based on the transmitted behavioral index. ### Claim 19 (depends on 18) The non-transitory, machine readable medium of claim 18, wherein the plurality of instructions further result in the client computer updating, in response to the occurrence of the predetermined behavioral event, a frequency of occurrences of the predetermined behavioral event, the frequency of occurrences being indicative of the number of occurrences during a first time period, and wherein determining the affinity metric comprises: assigning a first affinity group to the predetermined behavioral event in response to the frequency of occurrences of the predetermined behavioral event being determined to be decreasing over the second time period; assigning a second affinity group to the predetermined behavioral event in response to the frequency of occurrences of the predetermined behavioral event being determined to be increasing over the second time period; and assigning a third affinity group to the predetermined event in response to the frequency of occurrences of the predetermined behavioral event being determined to be substantially constant over the second time period. ### Claim 20 (depends on 18) The non-transitory, machine readable medium of claim 18, wherein the plurality of instructions further result in the client computer updating, in response to the occurrence of the predetermined behavioral event, a frequency of occurrences of the predetermined behavioral event, the frequency of occurrences being indicative of the number of occurrences during a first time period, and assigning a first avidity group to the predetermined event in response to the total number of occurrences of the predetermined behavioral event (i) being greater than a predetermined first percentage of the predetermined range of total occurrences and (ii) being substantially consistent over a third time period, the third period of time being a multiple of the second time period; assigning a second avidity group to the predetermined event in response to the total number of occurrences of the predetermined behavioral event (i) being less than a predetermined second percentage of the predetermined range of total occurrences and (ii) being substantially consistent over the third time period; and assigning a third avidity group to the predetermined event in response to the total number of occurrences of the predetermined behavioral event (i) being within the predetermined range of total occurrences and (ii) being substantially inconsistent over the third time period.