# US 2025/0168006 A1 · Application of interaction modeling for lambda triggering of authorization > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2025/0168006 A1 - Document ID: US20250168006A1 - Status: Published application - Kind: A1 - Application number: 19/033,771 - Filed: 2025-01-22 - Published: 2025-05-22 - Earliest claimed: 2022-05-11 - Assignees: Truist Bank - Applicants: Truist Bank - Inventors: Peter Eric Sutherland; Laurence Henry Lipsmeyer; Nelson Joseph Erb - Web page: https://patentgrep.com/patent/US20250168006A1 ## CPC - H04L 9/0894: {Escrow, recovery or storing of secret information, e.g. secret key escrow or cryptographic key storage} - H04L 9/3228: {One-time or temporary data, i.e. information which is sent for every authentication or authorization, e.g. one-time-password, one-time-token or one-time-key} - G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue - H04L 9/3226: {using a predetermined code, e.g. password, passphrase or PIN (network architectures or network communication protocols for supporting authentication of entities using passwords in a packet data network H04L63/083)} - H04L 63/105: {Multiple levels of security} - G10L 2015/221: {Announcement of recognition results} - G10L 2015/223: {Execution procedure of a spoken command} - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract A conversational interface receives a conversational request for an action which requires step-up authentication; responds to the user using conversational AI with a warning that an additional step is required; transmits the authorization intent and the spoken submission to a virtual private cloud (VPC), and in response to confirmation of the spoken submission, authenticates the user, thereby authorizing the requested action; and receives a confirmation of validation of the passphrase and that the action is being or will be performed. ## Claims ### Claim 1 A conversational interface system for step-up authentication using spoken passphrases, the system comprising: at least one processor; a communication interface communicatively coupled to the at least one processor; and a memory device storing executable code that, when executed, causes the processor to: receive, by an interface device, a conversational request for an action; derive, by the interface device, an intent from the conversational request by comparing the intent to a collection of intents stored by an interaction model, the deriving including determining the intent requires step-up authentication; initiate, by the interface device and based on the determination, a step-up authentication process that includes a response using conversational artificial intelligence (AI) that includes a warning that an additional authentication step is required, the additional authentication step including an interaction with a virtual private cloud (VPC); receive, by the interface device and in response to the warning, a spoken input that includes a passphrase, the passphrase having been communicated to a computing device of a user from a passphrase service of a datacenter communicatively connected to the interface device, the passphrase service having generated the passphrase using a spoken passphrase dictionary; determine, by the interface device, a spoken intent of the spoken input an initiation intent for an interaction with the VPC; generate, by the interface device, an authorization intent using an interaction model; transmit, by the interface device, the authorization intent and the spoken input to the VPC, wherein the authorization intent and spoken input are transmitted to the datacenter using one or more application programming interfaces (APIs) for validation of the spoken input; and receive, by the interface device from the passphrase service of the datacenter, a confirmation validating the spoken input, the spoken input having been validated by the passphrase service of the datacenter to include the passphrase generated by the passphrase service of the datacenter, wherein the confirmation facilitates authenticating the user and authorizing the action of the conversational request. ### Claim 2 (depends on 1) The system of claim 1, wherein the passphrase is generated, via the spoken passphrase dictionary, by random selection of a plurality of words from the spoken passphrase dictionary. ### Claim 3 (depends on 1) The system of claim 1, wherein the spoken input is received by the interface device asynchronously from the passphrase communicated to computing device of the user. ### Claim 4 (depends on 3) The system of claim 3, wherein up to one hour of time has passed between transmission of the passphrase to the computing device and receiving the spoken input. ### Claim 5 (depends on 1) The system of claim 1, wherein the passphrase has been communicated to the computing device using a communication medium selected from the group consisting of SMS, text, email, and app push notification. ### Claim 6 (depends on 1) The system of claim 1, wherein the passphrase is a one-use passphrase that will be invalid if used more than once. ### Claim 7 (depends on 1) The system of claim 1, wherein the passphrase expires after a predetermined period of time after transmission to the computing device of the user. ### Claim 8 (depends on 1) The system of claim 1, wherein the spoken passphrase dictionary includes words that are subject to removal from the dictionary by the passphrase service if the words are identified as causing confusion with other words. ### Claim 9 (depends on 1) The system of claim 1, wherein the passphrase comprises at least three words randomly selected from the spoken passphrase dictionary. ### Claim 10 A method for step-up authentication for using spoken passphrases, the method comprising: receiving, by an interface device, a conversational request for an action; deriving, by the interface device, an intent from the conversational request by comparing the intent to a collection of intents stored by an interaction model, the deriving including determining the intent requires step-up authentication; initiating, by the interface device and based on the determination, a step-up authentication process that includes a response using conversational artificial intelligence (AI) that includes a warning that an additional authentication step is required, the additional authentication step including an interaction with a virtual private cloud (VPC); receiving, by the interface device and in response to the warning, a spoken input that includes a passphrase, the passphrase having been communicated to a computing device of a user from a passphrase service of a datacenter communicatively connected to the interface device, the passphrase service having generated the passphrase using a spoken passphrase dictionary; determining, by the interface device, a spoken intent of the spoken input an initiation intent for an interaction with the VPC; generating, by the interface device, an authorization intent using an interaction model; transmitting, by the interface device, the authorization intent and the spoken input to the VPC, wherein the authorization intent and spoken input are transmitted to the datacenter using one or more application programming interfaces (APIs) for validation of the spoken input; and receiving, by the interface device from the passphrase service of the datacenter, a confirmation validating the spoken input, the spoken input having been validated by the passphrase service of the datacenter to include the passphrase generated by the passphrase service of the datacenter, wherein the confirmation facilitates authenticating the user and authorizing the action of the conversational request. ### Claim 11 (depends on 10) The method of claim 10, wherein the passphrase is generated, via the spoken passphrase dictionary, by random selection of a plurality of words from the spoken passphrase dictionary. ### Claim 12 (depends on 10) The method of claim 10, wherein the spoken input is received by the interface device asynchronously from the passphrase communicated to computing device of the user. ### Claim 13 (depends on 12) The method of claim 12, wherein up to one hour of time has passed between transmission of the passphrase to the computing device and receiving the spoken input. ### Claim 14 (depends on 10) The method of claim 10, wherein the passphrase has been communicated to the computing device using a communication medium selected from the group consisting of SMS, text, email, and app push notification. ### Claim 15 (depends on 10) The method of claim 10, wherein the passphrase is a one-use passphrase that will be invalid if used more than once. ### Claim 16 (depends on 10) The method of claim 10, wherein the passphrase expires after a predetermined period of time after transmission to the computing device of the user. ### Claim 17 A conversational interface system for step-up authentication using spoken passphrases, the system comprising: at least one processor; a communication interface communicatively coupled to the at least one processor; and a memory device storing executable code that, when executed, causes the processor to: receive, by an interface device, a conversational request for an action, the conversational request being received after performing an initial authentication of a user, the initial authentication being based on user information of the user; derive, by the interface device, an intent from the conversational request by comparing the intent to a collection of intents stored by an interaction model, the deriving including determining the intent requires step-up authentication; initiate, by the interface device and based on the determination, a step-up authentication process that includes a response using conversational artificial intelligence (AI) that includes a warning that an additional authentication step is required, the additional authentication step including an interaction with a virtual private cloud (VPC); receive, by the interface device and in response to the warning, a spoken input that includes a passphrase, the passphrase having been communicated to a computing device of the user from a passphrase service of a datacenter communicatively connected to the interface device, and based thereon determine, by the interface device, that an interaction with the virtual private cloud is to be initiated; initiate, by the interface device, the interaction with the VPC; generate an authorization intent using an interaction model, the authorization intent including at least a portion of the user information of the user; transmit, by the interface device and via one or more application programming interfaces (APIs), the authorization intent and the spoken input that includes the passphrase to the VPC for validation of the passphrase; receive, by the interface device from the passphrase service of the datacenter, a confirmation validating the spoken input, the spoken input having been validated by the passphrase service of the datacenter to include the passphrase generated by the passphrase service of the datacenter; and authenticate, based on receiving the confirmation, the user to facilitate implementing the action of the conversational request. ### Claim 18 (depends on 17) The system of claim 17, wherein the passphrase is a one-use passphrase that will be invalid if used more than once. ### Claim 19 (depends on 17) The system of claim 17, wherein the passphrase expires after a predetermined period of time after transmission to the computing device of the user. ### Claim 20 (depends on 17) The system of claim 17, wherein the passphrase comprises at least three words randomly selected from a spoken passphrase dictionary utilized by the passphrase service of the datacenter.