# US 11,907,343 B2 · Generation of authentication questions based on user-created transaction limitations > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,907,343 B2 - Document ID: US11907343B2 - Status: Granted - Kind: B2 - Application number: 17/314,683 - Filed: 2021-05-07 - Published: 2022-11-10 - Granted: 2024-02-20 - Earliest claimed: 2021-05-07 - Assignees: Capital One Services, LLC - Applicants: Capital One Services, LLC - Inventors: Viraj Chaudhary; David Septimus; Jenny Melendez; Samuel Rapowitz; Tyler Maiman; Joshua Edwards - Web page: https://patentgrep.com/patent/US11907343B2 ## CPC - G06F 21/31: User authentication - G06Q 20/4014: {Identity check for transactions} - G06F 16/24564: {Applying rules; Deductive queries} - G06F 21/45: Structures or tools for the administration of authentication - G06F 21/604: {Tools and structures for managing or administering access control systems} - G06N 3/0499: Feedforward networks - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - G06N 5/022: Knowledge engineering; Knowledge acquisition - G06Q 20/40: Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists - G06Q 20/4016: {involving fraud or risk level assessment in transaction processing} - G06Q 20/405: {Establishing or using transaction specific rules} - G06Q 40/02: Banking, e.g. interest calculation or account maintenance (credit or loans G06Q40/03) - G06F 2221/2103: Challenge-response - 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 - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Methods, systems, and apparatuses are described herein for improving the accuracy of authentication questions using transaction limitations provided by users. A request for access to an account associated with a user may be received from a user device. An account restrictions database may be queried to determine one or more transaction rules associated with the account. The one or more transaction rules may have been created by the user and indicate limitations on financial transactions that may be performed via the account. An authentication question may be generated that is associated with a violation of the one or more transaction rules. The authentication question may be provided to the user device, and a response to the authentication question may be received. Access to the account may be provided to the user device based on the response. ## Claims ### Claim 1 A method comprising: receiving, from a user device, a request for access to an account associated with a user; based on determining that a quantity of one or more user-created transaction rules satisfy a threshold, determining one or more simulated transaction rules for the account by: providing, as input to a trained machine learning model, metadata corresponding to the account, wherein the trained machine learning model is trained based on a plurality of different accounts; and receiving, as output from the trained machine learning model and based on the input, the one or more simulated transaction rules, wherein the simulated one or more transaction rules indicate limitations on financial transactions that may be performed via the account; generating an authentication question associated with a violation of the one or more simulated transaction rules; providing the authentication question to the user device; receiving, from the user device, a response to the authentication question; and providing, based on the response to the authentication question, the user device access to the account. ### Claim 2 (depends on 1) The method of claim 1, wherein generating the authentication question comprises: providing, as input to a second trained machine learning model, the one or more simulated transaction rules, wherein the second trained machine learning model is trained based on a plurality of transaction rules and a plurality of questions based on the plurality of transaction rules; and receiving, as output from the second trained machine learning model and based on the input, the authentication question. ### Claim 3 (depends on 1) The method of claim 1, wherein a first quantity of the one or more simulated transaction rules is greater than a second quantity of the one or more user-created transaction rules. ### Claim 4 (depends on 1) The method of claim 1, wherein determining the one or more simulated transaction rules comprises: providing, as input to a second trained machine learning model, the one or more simulated transaction rules, wherein the second trained machine learning model is trained based on groups of transaction rules; and receiving, as output from the second trained machine learning model and based on the input, additional simulated transaction rules. ### Claim 5 (depends on 1) The method of claim 1, wherein generating the authentication question comprises: querying, using metadata corresponding to the account, an accounts database to determine one or more second accounts similar to the account, wherein generating the authentication question is based on historical transactions associated with the one or more second accounts. ### Claim 6 (depends on 1) The method of claim 1, further comprising: based on the determining that a quantity of the one or more user-created transaction rules satisfy the threshold: processing a transaction history of the account to determine a behavioral trend; and causing output of a recommendation to create a new user-created transaction rule based on the behavioral trend. ### Claim 7 (depends on 1) The method of claim 1, wherein generating the authentication question is further based on a transaction history associated with the account. ### Claim 8 (depends on 1) The method of claim 1, wherein the one or more simulated transaction rules indicate one or more of: that the account is prohibited from conducting a transaction at a vendor; and that the account is prohibited from conducting a transaction during a time period. ### Claim 9 (depends on 1) The method of claim 1, wherein the request for access to the account associated with the user comprises authentication credentials, and wherein providing the user device access to the account is further based on authenticating the authentication credentials. ### Claim 10 A computing device comprising: one or more processors; and memory storing instructions that, when executed by the one or more processors, cause the computing device to: receive, from a user device, a request for access to an account associated with a user; based on determining that a quantity of one or more user-created transaction rules satisfy a threshold, determine one or more simulated transaction rules for the account by: providing, as input to a trained machine learning model, metadata corresponding to the account, wherein the trained machine learning model is trained based on a plurality of different accounts; and receiving, as output from the trained machine learning model and based on the input, the one or more simulated transaction rules, wherein the one or more simulated transaction rules indicate limitations on financial transactions that may be performed via the account; generate an authentication question associated with a violation of the one or more simulated transaction rules; provide the authentication question to the user device; receive, from the user device, a response to the authentication question; and provide, based on the response to the authentication question, the user device access to the account. ### Claim 11 (depends on 10) The computing device of claim 10, wherein the instructions, when executed by the one or more processors, cause the computing device to generate the authentication question by causing the computing device to: provide, as input to a second trained machine learning model, the one or more simulated transaction rules, wherein the second trained machine learning model is trained based on a plurality of transaction rules and a plurality of questions based on the plurality of transaction rules; and receive, as output from the second trained machine learning model and based on the input, the authentication question. ### Claim 12 (depends on 10) The computing device of claim 10, wherein a first quantity of the one or more simulated transaction rules is greater than a second quantity of the one or more user-created transaction rules. ### Claim 13 (depends on 10) The computing device of claim 10, wherein the instructions, when executed by the one or more processors, cause the computing device to determine the one or more simulated transaction rules by causing the computing device to: provide, as input to a second trained machine learning model, the one or more simulated transaction rules, wherein the second trained machine learning model is trained based on groups of transaction rules; and receive, as output from the second trained machine learning model and based on the input, additional simulated transaction rules. ### Claim 14 (depends on 10) The computing device of claim 10, wherein the instructions, when executed by the one or more processors, cause the computing device to generate the authentication question by causing the computing device to: query, using metadata corresponding to the account, an accounts database to determine one or more second accounts similar to the account, wherein generating the authentication question is based on historical transactions associated with the one or more second accounts. ### Claim 15 (depends on 10) The computing device of claim 10, wherein the instructions, when executed by the one or more processors, further cause the computing device to: based on the determining that a quantity of the one or more user-created transaction rules satisfy the threshold: process a transaction history of the account to determine a behavioral trend; and cause output of a recommendation to create a new user-created transaction rule based on the behavioral trend. ### Claim 16 One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause a computing device to: receive, from a user device, a request for access to an account associated with a user; based on determining that a quantity of one or more user-created transaction rules satisfy a threshold, determine one or more simulated transaction rules for the account by: providing, as input to a trained machine learning model, metadata corresponding to the account, wherein the trained machine learning model is trained based on a plurality of different accounts; and receiving, as output from the trained machine learning model and based on the input, the one or more simulated transaction rules, wherein the one or more simulated transaction rules indicate limitations on financial transactions that may be performed via the account; generate an authentication question associated with a violation of the one or more simulated transaction rules; provide the authentication question to the user device; receive, from the user device, a response to the authentication question; and provide, based on the response to the authentication question, the user device access to the account. ### Claim 17 (depends on 16) The computer-readable media of claim 16, wherein the instructions, when executed by the one or more processors, cause the computing device to generate the authentication question by causing the computing device to: provide, as input to a second trained machine learning model, the one or more simulated transaction rules, wherein the second trained machine learning model is trained based on a plurality of transaction rules and a plurality of questions based on the plurality of transaction rules; and receive, as output from the second trained machine learning model and based on the input, the authentication question. ### Claim 18 (depends on 16) The computer-readable media of claim 16, wherein a first quantity of the one or more simulated transaction rules is greater than a second quantity of the one or more user-created transaction rules. ### Claim 19 (depends on 16) The computer-readable media of claim 16, wherein the instructions, when executed by the one or more processors, cause the computing device to determine the one or more simulated transaction rules by causing the computing device to: provide, as input to a second trained machine learning model, the one or more simulated transaction rules, wherein the second trained machine learning model is trained based on groups of transaction rules; and receive, as output from the second trained machine learning model and based on the input, additional simulated transaction rules. ### Claim 20 (depends on 16) The computer-readable media of claim 16, wherein the instructions, when executed by the one or more processors, cause the computing device to generate the authentication question by causing the computing device to: query, using metadata corresponding to the account, an accounts database to determine one or more second accounts similar to the account, wherein generating the authentication question is based on historical transactions associated with the one or more second accounts.