# US 12,222,989 B2 · System and method for generating a recommendation > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,222,989 B2 - Document ID: US12222989B2 - Status: Granted - Kind: B2 - Application number: 18/342,307 - Filed: 2023-06-27 - Published: 2023-10-26 - Granted: 2025-02-11 - Earliest claimed: 2019-10-17 - Assignees: The Toronto-Dominion Bank - Applicants: The Toronto-Dominion Bank - Inventors: Mansi Rastogi; Jane Holtslander; Michael Doyle; Kristopher Okera Gibbs; Tonja Selena Launen; Alla Chichkina; Ellen Rebecca Heise; Anna Anatolievna Sakoun; Seonaid Marlaine Eggett; Paul Thomas McGhee; Chantale Oliveira; Mary Ann Duarte - Web page: https://patentgrep.com/patent/US12222989B2 ## CPC - G06F 16/9035: Filtering based on additional data, e.g. user or group profiles - G06F 16/9536: Search customisation based on social or collaborative filtering - G06Q 20/108: {Remote banking, e.g. home banking} - G06Q 20/229: {Hierarchy of users of accounts} - G06Q 20/4014: {Identity check for transactions} - G06Q 30/0256: {User search} - G06Q 30/0271: {Personalized advertisement} - 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 A method of generating recommendations for a collective profile, the collective profile being linked to a first profile and a second profile. The method may include authenticating a login request from an end user device in association with the collective profile based on credentials associated with the first profile, identifying a query from among a plurality of queries and transmit the query to the end user device, receiving a response to the query, determining that the response is not inconsistent with one or more earlier responses received in association with the second profile and, in response, refining at least one attribute or goal in the collective profile based on the response to generate and store a refined collective profile, and determining whether the refined collective profile results in a new recommendation and, if so, outputting the new recommendation. ## Claims ### Claim 1 A server computer system comprising: a persistent storage containing at least a first user profile including a query history indicating queries asked and answered in association with the first user profile and including an order of unasked queries based on quantified relevance; a processor coupled to the persistent storage; and a memory coupled to the processor, the memory storing instructions that, when executed, are to cause the processor to: authenticate a login request from an end user device in association with the first user profile; retrieve the first user profile including the query history; identify a query from among the unasked queries based on it having a highest quantified relevance and transmit the query to the end user device; receive a response to the query; determine that the response alters a relevance ranking of one or more queries in in remaining unasked queries; and, as a result, re-order the remaining unasked queries. ### Claim 2 (depends on 1) The server computer system of claim 1, wherein the instructions, when executed, are to further cause the processor to transmit a most relevant query from the remaining unasked queries. ### Claim 3 (depends on 2) The server computer system of claim 2, wherein the instructions, when executed, are to further cause the processor to receive a reply to the most relevant query and determine that the query process is to stop in association with a current session. ### Claim 4 (depends on 3) The server computer system of claim 3, wherein the instructions, when executed, are to cause the processor to determine that the query process is to stop is based on the system having sent a maximum count of queries for the current session despite there being additional remaining unasked queries. ### Claim 5 (depends on 3) The server computer system of claim 3, wherein the instructions, when executed, are to cause the processor to determine that the query process is to stop is based on no remaining unasked queries having a respective quantified relevance higher than a minimum threshold. ### Claim 6 (depends on 3) The server computer system of claim 3, wherein the instructions, when executed, are to further cause the processor to: update the first user profile based on the reply; determine that the updated first user profile triggers a recommendation; and, transmit the recommendation to the end user device. ### Claim 7 (depends on 1) The server computer system of claim 1, wherein the questions asked and answered in association with the first user profile were obtained through a different end user device in association with a collective profile. ### Claim 8 (depends on 1) The server computer system of claim 1, wherein the instructions, when executed, are to further cause the processor to detect a change in an account associated the first user profile, wherein the change causes a re-initiation of at least a portion of the query process. ### Claim 9 (depends on 8) The server computer system of claim 8, wherein the change in the account is a change in a past pattern of activity in the account. ### Claim 10 (depends on 1) The server computer system of claim 1, wherein the first user profile is associated with one or more social media accounts, and wherein the instructions, when executed, are to further cause the processor to: mine social media data from the one or more social media accounts; identify from the social media data an event; and, in response to the event, re-initiate at least a portion of the query process. ### Claim 11 A computer-implemented method comprising: authenticating a login request from an end user device in association with a first user profile; retrieving the first user profile including a query history indicating queries asked and answered in association with the first user profile and including an order of unasked queries based on quantified relevance; identifying a query from among the unasked queries based on it having a highest quantified relevance and transmitting the query to the end user device; receiving a response to the query; determining that the response alters a relevance ranking of one or more queries in remaining unasked queries; and, as a result, re-ordering the remaining unasked queries. ### Claim 12 (depends on 11) The computer-implemented method of claim 11, further comprising transmitting a most relevant query from the remaining unasked queries. ### Claim 13 (depends on 12) The computer-implemented method of claim 12, further comprising receiving a reply to the most relevant query and determining that the query process is to stop in association with a current session. ### Claim 14 (depends on 13) The computer-implemented method of claim 13, wherein determining that the query process is to stop is based on having sent a maximum count of queries for the current session despite there being additional remaining unasked queries. ### Claim 15 (depends on 13) The computer-implemented method of claim 13, wherein determining that the query process is to stop is based on no remaining unasked queries having a respective quantified relevance higher than a minimum threshold. ### Claim 16 (depends on 13) The computer-implemented method of claim 13, further comprising updating the first user profile based on the reply; determining that the updated first user profile triggers a recommendation; and, transmitting the recommendation to the end user device. ### Claim 17 (depends on 11) The computer-implemented method of claim 11, wherein the questions asked and answered in association with the first user profile were obtained through a different end user device in association with a collective profile. ### Claim 18 (depends on 11) The computer-implemented method of claim 11, further comprising detecting a change in an account associated the first user profile, wherein the change causes a re-initiation of at least a portion of the query process. ### Claim 19 (depends on 18) The computer-implemented method of claim 18, wherein the change in the account is a change in a past pattern of activity in the account. ### Claim 20 (depends on 11) The computer-implemented method of claim 11, wherein the first user profile is associated with one or more social media accounts, and further comprising: mining social media data from the one or more social media accounts; identifying from the social media data an event; and, in response to the event, re-initiating at least a portion of the query process. ### Claim 21 A non-transitory computer-readable storage medium storing instructions, that, when executed by a processor of a computer system, cause the computer system to: store, in memory, a first user profile including a query history indicating queries asked and answered in association with the first user profile and including an order of unasked queries based on quantified relevance; authenticate a login request from an end user device in association with the first user profile; retrieve the first user profile including the query history; identify a query from among the unasked queries based on it having a highest quantified relevance and transmit the query to the end user device; receive a response to the query; determine that the response alters a relevance ranking of one or more queries in in remaining unasked queries; and, as a result, re-order the remaining unasked queries.