Persona tokens

Abstract

Disclosed herein is a service provider system and method to generate a persona token for a user, store the persona token at a restricted access database, and return a persona token identifier to the user. The persona token is used to generate persona insights, that can be provided to an artificial intelligence / machine learning algorithm along with an inquiry. The algorithm may identify goods or services based on the persona insights. Also disclosed herein are system and methods to attribute a user clicking on a product link, retaining and using the product information to link item level details to purchases, and making a purchase on the linked e-commerce / merchant website such that the originating website knows that a purchase ultimately resulted from the clicked ad.

Description

PERSONA TOKENSCROSS REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of and priority under 35 U.S.C. § 119(e) to U.S. Provisional Patent Application Serial No. 63 / 648,167, filed May 15, 2024, entitled “PERSONA TOKENS” and to U.S. Provisional Patent Application Serial No. 63 / 657,023, filed June 6, 2024, entitled “DISCOVER-TO-BUY PAYMENT ATTRIBUTION”, the contents of each are hereby incorporated by reference in their entirety herein.BACKGROUND

[0002] Shopping on the internet is largely the result of targeted searches or discovery through offers, product placement and ads with checkout occurring through the individual merchant’s shopping cart. While there are a number of segment-specific destination sites, the shopping experience can be vastly improved using artificial intelligence (Al) to improve discovery and the checkout process can be simplified if the consumer is not directed to merchant shopping carts.

[0003] Assistant driven commerce has been around for a while. Online marketplaces intended to provide an interface to help discover products across multiple merchants by offering a range of products and services. User preference remains specific to the platform, and is not portable across platforms (e.g., preferences set in a first grocery shopping application are not translated into a second grocery shopping application).SUMMARY

[0004] The present disclosure is related generally to personalized e-commerce methods and systems using data tokens. More particularly, the present disclosure is related to giving attribution for a user clicking on a product link, retaining and using the product information to link item level details to purchases, and making a purchase on the linked e- commerce I merchant website such that the originating website knows that a purchase ultimately resulted from the clicked ad.

[0005] A system of one or more computers can perform particular operations or actions by virtue of having software, firmware, hardware, or a combination of them installed on the system that in operation causes or cause the system to perform the actions. One or more computer programs can perform particular operations or actions by virtue of including instructions that, when executed by data processing apparatus, cause the apparatus toperform the actions. One general embodiment includes a computer-implemented method for enabling personalized commerce. The computer-implemented method also includes receiving, by a service provider system, a request from a commerce application to retrieve product recommendations for a user. The method also includes retrieving, by the service provider system, a persona token associated with the user from a restricted access database. The method also includes generating, by a machine learning model hosted on the service provider system, one or more product recommendations based on persona insights derived from the persona token. The method also includes transmitting the product recommendations to the commerce application for display on a user device. Other embodiments of this aspect include corresponding computer systems, apparatus, and computer programs recorded on one or more computer storage devices, each to perform the actions of the methods.

[0006] One general embodiment includes a method for attributing a purchase event to a digital advertisement interaction. The method also includes receiving, at a service provider system, an indication of a user interaction with a digital advertisement for a product, the user interaction associated with a persona token identifier. The method also includes receiving, at the service provider system, transaction data indicative of a purchase of a product by the user from a resource provider, The method also includes matching the transaction data with the user interaction using the persona token identifier. The method also includes generating attribution data for the matched transaction data, the attribution data indicating that the purchase event is associated with the user interaction of the advertisement. Other embodiments of this aspect include corresponding computer systems, apparatus, and computer programs recorded on one or more computer storage devices, each to perform the actions of the methods.

[0007] A system of one or more computers can perform particular operations or actions by virtue of having software, firmware, hardware, or a combination of them installed on the system that in operation causes or cause the system to perform the actions. One or more computer programs can perform particular operations or actions by virtue of including instructions that, when executed by data processing apparatus, cause the apparatus to perform the actions. One general embodiment includes a system for provisioning and utilizing persona tokens in an Al-powered commerce environment. The system also includes, by execution of the instructions by the processor, to receive a request to generate a persona token for a user, the request may include user consent and at least one of user demographic data, transaction history, or behavioral profile. The system also includes, by execution of the instructions by the processor, to generate a persona token based on the request. The system also includes, by execution of the instructions by the processor, to storethe persona token in association with a persona token identifier in a restricted access database. The system also includes, by execution of the instructions by the processor, to provision the persona token identifier to one or more commerce applications. The system also includes, by execution of the instructions by the processor, to enable use of the persona token to personalize product discovery or checkout experiences for the user in the commerce applications. Other embodiments of this aspect include corresponding computer systems, apparatus, and computer programs recorded on one or more computer storage devices, each to perform the actions of the methods.

[0008] Additional advantages will be set forth in part in the description which follows or may be learned by practice. The advantages will be realized and attained by means of the elements and combinations particularly pointed out in the appended claims. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive, as claimed.BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In the description, for purposes of explanation and not limitation, specific details are set forth, such as particular aspects, procedures, techniques, etc. to provide a thorough understanding of the present technology. However, the present technology may be practiced in other aspects that depart from these specific details.

[0010] The accompanying drawings, where like reference numerals refer to identical or functionally similar elements throughout the separate views, together with the detailed description below, are incorporated in and form part of the specification, and serve to further illustrate aspects of concepts that include the claimed disclosure and explain various principles and advantages of those aspects.

[0011] The apparatuses, systems, and methods disclosed herein have been represented where appropriate by conventional symbols in the drawings, showing only those specific details that are pertinent to understanding the various aspects of the present disclosure so as not to obscure the disclosure with details that will be readily apparent to those of ordinary skill in the art having the benefit of the description herein.

[0012] FIG. 1 is a cross-functional use case flow of a persona token, according to at least one aspect of the present disclosure.

[0013] FIG. 2 illustrates an overview of the search customization using persona tokens, according to various embodiments.

[0014] FIG. 3 illustrates an end-to-end user experience (UX) journey in an Al- powered discover-to-buy services platform, according to at least one aspect of the present disclosure.

[0015] FIG. 4 illustrates the discovery phase where the system discovers products from a merchant application (e.g., commerce application(s)), according to various embodiments.

[0016] FIG. 5 illustrates the discovery phase where the system discovers products from one or more third party applications (e.g., commerce platforms), according to various embodiments.

[0017] FIG. 6 illustrates the discovery phase where the system discovers products from any third party applications (e.g., commerce application(s)), according to various embodiments.

[0018] FIG. 7 illustrates the checkout phase where the user starts a checkout process from a third party application, according to various embodiments.

[0019] FIG. 8 is a cross-functional flow diagram of a discover-to-buy returning user with payment attribution process, according to at least one aspect of the present disclosure.

[0020] FIG. 9 illustrates a discover-to-buy payment attribution system, according to at least one aspect of the present disclosure.

[0021] FIG. 10 is a logic flow diagram of a method, according to at least one aspect of the present disclosure.

[0022] FIG. 11 is a logic flow diagram of a method, according to at least one aspect of the present disclosure.

[0023] FIG. 12 is a logic flow diagram of a method, according to at least one aspect of the present disclosure.

[0024] FIG. 13 is a block diagram of a payment network system, according to at least one aspect of the present disclosure.

[0025] FIG. 14 is a block diagram of a token server computer, according to at least one aspect of the present disclosure.

[0026] FIG. 15 is a block diagram of a computer apparatus with data processing subsystems or components, according to at least one aspect of the present disclosure.

[0027] FIG. 16 is a diagrammatic representation of an example computer system that includes a host machine within which a set of instructions to perform any one or more ofthe methodologies discussed herein may be executed, according to at least one aspect of the present disclosure.DETAILED DESCRIPTION

[0028] The following disclosure may provide exemplary systems, devices, and methods for conducting a financial transaction and related activities. Although reference may be made to such financial transactions in the examples provided below, aspects are not so limited. That is, the systems, methods, and apparatuses may be utilized for any suitable purpose.

[0029] Before discussing specific embodiments, aspects, or examples, some descriptions of terms that may be used herein are provided below.

[0030] Access Device: A device that enables communication with a remote system, such as a merchant computer or transaction processor. It may include POS terminals, smartphones, tablets, PCs, kiosks, ATMs, and similar hardware. Communication may be via contact or contactless methods (e.g., NFC, RF, optical, magnetic stripe). A mobile device used as a POS terminal may be called a mobile POS (mPOS) terminal.

[0031] Access Device: A device that enables communication with a remote system, such as a merchant or transaction processing computer. Examples include POS terminals, mobile phones, PCs, tablets, kiosks, ATMs, and mPOS terminals. Devices may operate via contact or contactless methods, such as NFC, RFID, or barcode.

[0032] Account Credentials: Information used to identify and access an account, including PANs, tokens, expiration dates, CVVs, and personal data. Credentials may be static, dynamic, or both, and are typically stored securely on a user device or accessed via a secure application.

[0033] Account Data: Any data related to user accounts, including account identifiers, transaction history, balances, and issuer information.

[0034] Account Identifier: A unique ID for an account, such as a PAN, token, GIIID, or UUID. It may be original or supplemental and is used in electronic payments.

[0035] Account Token: A substitute for an account identifier (e.g., a PAN), used to complete transactions securely without exposing the original identifier. Tokens may be static or dynamic and are mapped to the PAN in a secure database.

[0036] Acquirer I Acquirer System: A financial institution or its systems authorized to originate transactions and contract with merchants or facilitators. Acquirers may also serve as issuers.

[0037] Agent: An entity appointed by an issuer to perform specific functions such as 3-D Secure authentication. For example, an Access Control Server may act as an agent.

[0038] Al Agent: A software- based entity capable of perceiving its environment, reasoning over data, and autonomously taking actions to achieve specific goals on behalf of a user or system. These agents are defined by their autonomy, operating without constant human supervision; their goal-directed behavior, acting in pursuit of user-defined or learned objectives; and their ability to learn and adapt over time based on new information or feedback. They also interact with their environment by gathering inputs — such as signals, data, or contextual cues — and influencing systems through actions like initiating purchases, scheduling meetings, or querying APIs. In the context of agentic commerce, Al agents can play a highly active role. For example, an agent might monitor price drops on products the user is interested in, evaluate product reviews, seek approval, when necessary (or proceed according to preset user preferences), and complete a purchase securely managing the entire transaction process. “Al agent” also may refer more broadly to agent-based platforms or providers, sometimes called Al assistant providers or generative Al platforms. Examples include companies and services like OpenAI (which offers ChatGPT), Anthropic (creator of Claude), Perplexity (an Al-powered search and answer engine), and Grok by xAl (a model known for performance in math, science, and coding). Depending on context, these platforms may be described as generative Al services, LLM-based tools, conversational Al systems, or agentic Al frameworks — emphasizing their ability to generate responses, engage in dialogue, or act with varying degrees of autonomy. These platforms go beyond simple large language model (LLM) interactions, supporting more complex, goal-oriented behaviors that are integral to the emerging ecosystem of agentic Al.

[0039] Agentic commerce: A model of digital commerce in which autonomous Al agents act on behalf of users to make decisions, initiate purchases, and complete transactions, all based on the user's preferences, consent, and objectives. In this model, Al agents operate with a high degree of autonomy, proactively searching for, recommending, or purchasing products and services that align with the user's needs. These agents rely heavily on user-centric personalization, drawing from a combination of explicit user instructions, historical behavior, and individual preferences to make informed decisions. A critical component of agentic commerce is the privacy-conscious and consent-driven exchange of signals between commercial platforms — such as marketplaces and payment providers — andAl agents. These signals may include user preferences, behavior patterns, and budget constraints, enabling agents to act in a way that respects the user’s intent and privacy. Agentic commerce supports a fully streamlined transaction experience. Al agents can manage the entire purchasing workflow, which may include authenticating the user, comparing products, executing payments, and even coordinating delivery. This hands-free, intelligent approach redefines how consumers interact with digital commerce by shifting agency from the user to a trusted Al assistant.

[0040] Application: Software executed on a device to perform specific functions. Includes mobile, wallet, and payment apps. Applications may expose APIs to support system communication.

[0041] Client I Client Device I User Device: An electronic device (e.g., smartphone, PCS system, appliance) used to initiate transactions or communicate over a network. A client can also refer to the entity operating the device.

[0042] Communication I Communication Channel: The transfer or receipt of data using wired or wireless, direct or indirect methods. Secure channels may be established with encryption or session keys to protect sensitive data.

[0043] Complete Payment Credentials: All account information needed to complete a transaction, possibly split into public and encrypted parts during transmission.

[0044] Comprising: A term indicating open-ended inclusion in patent claims, synonymous with “including” or “containing.”

[0045] Computing Device I Computer: An electronic device capable of data processing and communication. Includes mobile phones, tablets, desktops, and wearables.

[0046] Consumer I User: An individual associated with one or more accounts or devices. Also known as an account holder or cardholder.

[0047] Credential: Information that verifies identity or authority, such as passwords, codes, ID cards, or certified documents.

[0048] Digital Wallet I Electronic Wallet I Mobile Wallet: A software application or device that stores payment credentials and is used for various digital and physical transactions.

[0049] Electronic Wallet Provider I System / Transaction Processing System: Entities or systems that provide, manage, or authenticate electronic wallet transactions (e.g., Apple Pay, PayPal).

[0050] End-User: A consumer, merchant, or system that interacts with tokenization services, typically as the recipient or originator of a transaction.

[0051] ID&V (Identification and Verification) Method: A technique for verifying that a token replaces a valid PAN, using OTPs, biometrics, PINs, etc.

[0052] Identification Information: Data linked to an account, including PANs, names, expiration dates, and card verification values.

[0053] Interface I API: A software module that processes communications or enables integration between devices, systems, or third parties.

[0054] Issuer I Issuer Institution: A financial entity that provides accounts (e.g., credit or debit) and identifiers (e.g., PANs) to users. Includes systems that authorize transactions.

[0055] Merchant I Merchant System I Merchant Application: An entity offering goods or services and the associated systems or apps used to process transactions.

[0056] Merchant Category Code (MCC): A numeric code classifying a merchant’s business type. MCCs may affect transaction routing or processing fees.

[0057] Mobile Device: A portable device with network capabilities, such as a smartphone, smartwatch, tablet, or wearable. May function as a payment device.

[0058] Online Purchase: A digital or physical purchase made via an online network, typically the Internet.

[0059] Payment Application I Wallet Application: Software that stores and provides payment credentials for use in transactions, either locally or via secure cloud retrieval.

[0060] Payment Device: Any device used for financial transactions, including cards, mobile phones, smartwatches, and key fobs. Can operate via contact or contactless methods.

[0061] Payment Gateway I System I Mobile Application: Systems and software operated by entities that provide payment services to merchants, such as payment authorization or routing.

[0062] Payment Network / Processing Network: Infrastructure used to accept, route, and process payment transactions. Example: VisaNet.

[0063] Payment Token Issuer Identifier: A code (e.g., token BIN) used to identify the issuer of a token and associate it with a corresponding PAN.

[0064] Persona Token: A persona token is a unique, pseudonymous digital identifier that represents an individual within a system, especially in contexts involvingpersonalization, privacy-preserving analytics, or agentic systems. It allows a single user to be consistently recognized across multiple sessions, applications, or platforms without revealing directly identifiable information (e.g., name or email). Persona tokens can link user preferences, behaviors, and transaction history across services to support personalization while maintaining user privacy. They enable Al agents or digital assistants to interact with third-party systems on the user’s behalf using a tokenized identity instead of actual personal data. Persona tokens also facilitate consent-driven data sharing, allowing selective access to user profile attributes or behavioral insights without exposing the user’s full identity. In payment and commerce environments, persona tokens can be used to derive insights from transaction data for use in personalized recommendations or concierge services, acting as a secure stand-in for sensitive account credentials in agent-mediated interactions.

[0065] Portable Financial Device: A payment-enabled device such as a credit card, smartcard, phone, or wearable that contains account data.

[0066] Primary Account Number (PAN): A standardized account number (typically 13-19 digits) assigned to a user’s account, issued within a BIN range.

[0067] Provisioning: The act of enabling data (e.g., tokens) on a device or system, typically performed by an issuer or payment network.

[0068] Server I Server Computer: A computing system that processes data and serves multiple users. May be centralized, virtual, or distributed across different entities.

[0069] System: One or more devices or components (e.g., processors, servers, apps) operating together to perform defined functions.

[0070] Token I Payment Token: A substitute identifier for a PAN, used for secure transactions. May include usage metadata and exist in static or dynamic formats.

[0071] Token Attributes: Data that defines a token’s usage, validity, type, expiration, or related metadata such as device ID or wallet ID.

[0072] Token BIN: A BIN range designated for issuing tokens, not real PANs.

[0073] Token Domain: Defines where and how a token may be used (e.g., by channel, merchant, or entry mode).

[0074] Token Exchange I De-Tokenization: The process of converting a token back into the original PAN, typically performed by authorized systems.

[0075] Token Expiry Date I Lifecycle Expiration: The date / time after which a token is no longer valid. Lifecycle expiration allows tokens to be recycled.

[0076] Token Interoperability: The ability for tokens to function across systems using standard protocols and formats.

[0077] Token Issuer Identifier Range (Issuer BIN Range): A unique range assigned to an issuer for generating tokens, mapped to actual issuer BINs.

[0078] Token Presentment Mode: The method through which a token is submitted, such as QR code, NFC, or e-commerce.

[0079] Token Processing: End-to-end transaction processing using tokens instead of PANs, including authorization and de-tokenization.

[0080] Token Request Message I Indicator: An electronic request for a token, possibly flagged or encrypted, including identifying information.

[0081] Token Requestor ID: A unique ID assigned to an entity requesting tokens, which may vary by domain or use case.

[0082] Token Response Message: A reply to a token request, indicating approval or denial, and containing token details.

[0083] Token Service Provider I System I Vault: An entity or infrastructure responsible for generating, managing, and securely storing tokens and PAN-token mappings.

[0084] Transaction Amount I Data: The monetary value and any associated data of a transaction, including merchant, product, and account details.

[0085] Transaction Service Provider I System: An entity or system that handles transaction authorization and guarantees payment, such as Visa or Mastercard.

[0086] User Information: Data related to the user or device, such as identifiers or device fingerprints.

[0087] Value Credential: Data that represents monetary or promotional value, such as coupons, gift cards, or payment credentials.

[0088] Referring generally to the figures, method and systems of persona token provisioning and use or persona tokens in discovery to buy commerce platforms is shown, according to various implementations.

[0089] In various aspects, this disclosure provides methods and systems to access a data token that can supplement existing search I feed algorithms or be included in new algorithms to enable future shopping assistants and facilitate purchasing from within the native application using stored personal information and payment credentials.

[0090] In part, this disclosure provides searching, advertising, and Al techniques to implement a discover-to-buy payment attribution system. Step changes in Al and large investments being made in Al-powered business models promise to transform the entirety of the discover-to-buy commerce experience. The impact of Al and Large Language Models (LLMs) will be felt in the payments process and where consumers engage with content on social media and other websites hosting digital advertising content. The digital advertising ecosystem, which has operated virtually unchanged for two decades, is poised to go through a generational transformation. Al-powered business models will impact payment networks in the future. Al models require vast amounts of structured data to operate effectively, and payments data, payments-informed insights, and embedded payments experiences are likely to play an outsized role in the future of e-commerce.

[0091] In part, the present disclosure provides techniques for positioning payment network platforms and service offerings in an Al and machine learning powered environment that build on payment network data and the insights it generates. Payment network data and insights may be employed to build and train proprietary Al commerce models to power new consumer and merchant experiences. The payment network data may be formed into simple and “consumable” transaction-based data products (e.g., “data tokens”) that can be ingested millions or billions of times a year across multiple channels and platforms.

[0092] Generative Al is artificial intelligence capable of generating text, images, or other media using generative models. These generative Al systems learn the patterns and structure of their input training data and then “generate” new data that has similar characteristics. Machine learning is able to learn and adapt without explicit instructions using algorithms and statistical models to draw inferences. Although generative Al and machine learning (ML) technologies are different (one being better for content and one being better for numbers), in commercial discover-to-buy applications, these technologies will be used together and for conciseness and clarity of disclosure may be referenced herein as “Al.”

[0093] A consumer discover-to-buy e-commerce experience includes viewing advertising on a hosting website, shopping on an e-commerce website, and fulfilling a payment through a payment network. Consumers will no longer be satisfied with a list of stack-ranked websites after typing a query for an item such as “tennis shoes” into a search bar. Al-powered experiences and more dynamic media-rich interactions (text, voice, video, in app) will change the way users interact with both content and commerce.

[0094] The digital advertising ecosystem is made up of brands (who buy advertisements), the agencies who create and place advertisements (e.g., media buyers), and publishers (who sell advertisement space). The online advertising ecosystem uses“third-party cookies.” Cookies are digital trackers that attach to a user’s browser creating a digital history of the user’s online activities. Cookies have been the primary tool available to brands, ad agencies, and publishers to measure clicks or page views and calculate advertisement rates. The industry, however, has or will be “retiring” use of third-party cookies.

[0095] The loss of “cookies” combined with a rise in Al and natural language experiences (contextual responses versus lists of web sites) will have a disruptive effect on the discover-to-buy experience. Thus, search engine and web browser providers will need to reexamine the consumer online e-commerce experience and introduce new economic models for millions of advertisers (merchants).

[0096] The payment network, and payment processing systems, knows how and where consumers and brands connect and uses Al to change the shopping experience. The payment network provides an Al-powered “shopping experience” in the e-commerce marketplace. The Al-powered commerce experience employs machine-readable “data tokens” with curated data insights that are shared with approved parties on demand. As used herein, a payment network may be part of a service provider network, which may include a tokenization server, and Al module that provide additional functionality.

[0097] In one general aspect, the play-by-play of a consumer’s browsing history may be replaced with “generalized” data insights and audience profiles. A move away from raw data to insights, and the transition from “user activity tracking” to “curated user interests” represents a change in the direction of consumer rights and data protection. Also, a swing toward “machine readable” formats may provide greater compatibility with large-scale AI / ML environments.

[0098] In one general embodiment, the service provider may provide its own insight- driven “data token” and structured data format based on purchase insights. The service provider-issued data token may be utilized (with consumer consent) to inform AI / ML models, augment search queries, optimize advertising, and drive in-application personalization. The service provider may develop an advertisement and payments industry standard for the next generation of “data” tokens.

[0099] The platforms and services for effective stewards of data in an Al-powered environment may include five core modules to build and operate (in an integrated fashion) tokenize datasets, associate them with native commerce experiences, and introduce a new services industry sector. These five modules include: (1) partner set-up during payment network onboarding; (2) pre-transaction identification and consent during payment network user notification; (3) payment network data tokens during payment network token activityand (4) embedded checkout during the payment network token activity during a transaction; and (5) purchase attribution during payment network notification post transaction.

[0100] Referring to FIG. 1 , a discover-to-buy marketplace, shopping assistant, and / or social network system is shown. The use of the persona token includes pre-staging 110, commerce 120, and post-purchase. In various embodiments, the pre-staging steps may be completed in series or in parallel across the consumer user device, the commerce application, and the service provider network. In some embodiment, the service provider network includes the payment network. In some embodiments, the commerce application may be a partner device, partner service provider, or partner server that can securely interact with both the consumer device and the service provider network.

[0101] Pre-staging 110 may include consumer pre-enrollment, consumer login and authentication, onboarding of payment network in a commerce application, consumer consent management, and persona data collection. In some embodiments, during consumer pre-enrollment, the consumer pre-enrolls at the service provider network with personal details. The personal details may include email address, telephone number, legal name, etc. During consumer login, the consumer may login to the commerce application and may be authenticated or identified and verified. Consumer authentication or identification and verification may be completed at the first login, at each login, or intermittently in response to any number of external or internal variables. Consent management may be carried out by an identity and consent API / SDK during onboarding. Finally, persona data creation may include ingesting a machine-readable data token by the commerce application or service provider network for search, advertising and Al systems to personalize results.

[0102] The payment network onboarding process may include the payment network partner set-up. The payment network with the partner train Al-models on synthetic data. During the Al training data phase, the payment network and the partner train Al-models on synthetic data. The payment network introduces a large pool of synthetic training data that mirrors real payment network system attributes and can be used to train partner Al systems and develop audience profiles for search and advertising platforms. The anonymized synthetic training data is prepared with partner Al systems to work with the payment network “data tokens.”

[0103] Synthetic datasets are artificially generated data that mimic the statistical properties of real-world data but do not contain any actual private information. Developing and managing high quality synthetic data is an important skill for a payment network, which operates in highly regulated environments with sensitive Pll data. In Europe, under GDPR, synthetic data is not automatically considered Pll which allows more freedom to collaborate Iinnovate across partners or build and train third-party services in the cloud. There are many techniques that can be used to generate synthetic datasets. The difficulty is to generate a data set that, while not containing the real data used to generate it, can still be useful for some tasks (e.g., to train a machine learning model for fraud detection, or train an Al model on how to derive marketing recommendations from consumer payments data, as an example).

[0104] Synthetic data is used in lieu of actual transaction records collected by payment network systems to avoid exposure of the data to third parties for Al model training. More limited synthetic data sets designed to mirror the statistical attributes in real data sets are employed to train partners’ Al models. For this technique to be effective, the payment network system can identify the statistical accuracy of its synthetic data sets against real datasets for critical queries (e.g., 98.7%).

[0105] In some embodiments, consent management may include offering the consumer the ability to connect payment network cards and payment network insights to a search engine. During the identification and consent system phase, the payment network introduces a system which can be integrated into partner environment to verify users and capture data-sharing consent. There is a need to know “Jane is Jane” before sharing data OR payment tokens attributes and can be used to train partner Al systems and develop audience profiles for search and advertising platforms. A modified ID&V and consent capture system is tied to dual provisioning of payment tokens and data tokens.

[0106] A user’s data cannot be shared without the user’s consent. In a digital world, however, the system has to verify who the user is. The payment networks have a consent framework and experience in federated identity verification (ID&V) tied to payment tokens, 3DS 2.0 and an emerging alias directory (with the ability to manage DevicelD, email addresses and mobile phone numbers). The assets or capabilities needed to deliver these services may be “packaged” to enable integration into use cases beyond payment. New best practices ranging from OALITH to FIDO Keys may be employed to simplify consumer experience and increase system-level recognition of known customers.

[0107] Identity and consent matters because when a user signs up to an Al service or chat, or registers to receive personalized advertising or custom offers, they may not have made the decision to enter payment credentials or initiate “purchase activity.” The payment network may need to move data-informed products “upstream” and package identity, verification, and consent capabilities in a manner that allows them to be more easily integrated into third party services before payment activity initiated.

[0108] Referring still to FIG. 1, the commerce phase 120 may include predictive commerce, personalized assisted search, and embedded commerce. Predictive commerce may include sending personalized advertisement recommendations to the consumer based on persona tokens. Personalized assisted search may include providing personalized commerce search results based on persona tokens. Embedded commerce may include enabling contextual commerce or single-channel commerce to include direct authorization and full basket clearing messages.

[0109] In some embodiments, embedded commerce from an onboarded commerce partner may include the use of payment tokens. The payment network token activity process uses payment network data tokens during a transaction. The search engine Al-queries, search, and ads are informed by payment network data tokens. The payment network introduces a numeric, machine-readable token for each PAN I user in the payment network system. Training data helps systems understand audiences. Tokens carry generalized payment insights about the users. Machine-readable user insights are presented in a consumable format for Al, search, and ad systems (with consent).

[0110] The payment network token activity process also uses embedded checkout. The search engine checkout experience is enabled by payment network payment tokens. During the embedded checkout process, the payment network updates its click-to-pay API to enable “context based” native checkout experiences without leaving Al-powered environment. To simplify deployment, the payment network can use a “merchant direct” authorization model. Embedded commerce provides a click-to-pay commerce experience processing “full basket” authorizations OBO (or best offer) platforms.

[0111] Data tokens I embedded personas is a hybrid term introduced herein to describe a proposed capability. If synthetic data represent rolled up anonymized insights from the payment network as a whole (the macro), tokenized personas represent generalized insights about an individual user (the micro). Every PAN in the payment network system has attributes and history (including where possible, item level data) that can provide insights about the individual user and their purchase behavior. Some of these attributes are general while some of these attributes are specific to the user. The payment network system has the ability to create a “numeric token” for each card holder which carries structured data (data in a machine-readable format), and this data token can be associated with each PAN when used in digital or (via ISO) face to face environment. Beyond the payment network ecosystem, data-informed tokens may be offered to Al models or search providers as an input for logged in or verified users. “Embedded tokens” are reflective of merchants.Payment network systems have experience in building and managing tokenized data sets for third-party system processing.

[0112] Introduction of payment network system data products in a “consumable token” format, creates something that can be generated automatically and associated with every PAN (or user) in the payment network system. This token format may be shared (with full transparency and consumer consent) with third party Al systems, advertising systems, or risk systems to improve customer experience, reduce fraud, drive effective advertising, or share preferences. What is interesting about creating an externally consumable data format, is the potential to become an industry standard and become “bigger than payments” enabling the payment network system (and bank partners) to communicate generalized user insights with wallets, advertising platforms, search platforms, risk platforms, loyalty platforms, merchant acquirers, etc. for a price.

[0113] In some embodiments, post-purchase 130 as referred to in FIG. 1, may include purchase attribution, which closes the loop on an embedded purchase by sending a payment event notification to an approved third party. In some embodiments, post-purchase 130 may include post-purchase survey including consumer reviews of products, services, and overall experience to be used to improve the overall process.

[0114] The payments network notification process uses purchase attribution post transaction. The payment network payment alerts provide a feedback loop to the partner ad platform. The payment network updates its events API to provide purchase attribution as a “feedback mechanism” to ad, search, and Al systems. The partner will onboard merchants and establish “merchant consent.” The purchase attribution system directs payment alerts to the ad serving platform.

[0115] Purchase attribution is the act of “closing the loop” on a payment network system purchase by sending a payment event notification to a third party. If synthetic data and embedded personas are about projecting what a user might do, purchase attribution provides a “confirmation” of what users did do. The payment network has a variety of systems that enable purchase attribution, from payment alerts (which go to cardholder), purchase matching (which go to a merchant I advertiser) or payment confirmations (which are pushed to wallets to provide notification of completed payment events). Purchase attributions are highly valued, as they help an “approved” third party understand when a payment event has been completed. Purchase attributions can be customized into rich formats (merchant name, amount, currency) or limited to simple less identifiable formats (purchase completed, date & time). Purchase attribution is a “confirmation step” for marketers / advertisers, and the availability of purchase confirmation can dramaticallychange the economic model for large scale ad publishing platforms. Ad impressions may cost $2 per thousand customer impressions, whereas purchase attribution may earn $2 per purchase.

[0116] Purchase attribution is a step in “closing the loop” for advertisers, and large- scale ad publishing platforms that have sought the capability for years. Caution should be taken about exposing purchase attribution data to third parties who are not involved in the payment transaction. As the payment network system introduces new consumer consent frameworks and develops more anonymized data methods (e.g., synthetic data, persona tokens), this disclosure contemplates a more wide-spread implementation of the payment attribution offering.

[0117] When the user clicks on an ad displayed on a social media or e-commerce website, the user is typically redirected to the advertiser’s landing page or website. The landing page or website is designed by the advertiser to provide more information about their product or service, encourage the user to take a specific action (like making a purchase or signing up for a service like a newsletter), or engage with their content in some way. Additionally, the platform hosting the ad may track the click-through behavior for analytics purposes, which can help advertisers understand the effectiveness of their campaigns.

[0118] As used herein, a “persona token” is a token based on a user’s transactional payment history as may be determined by a back-end server of a payment network, for example, to describe what kind of shopper the user is and to determine the likelihood of what the user will shop for and predict what the user is most likely to purchase. The information is tracked and added to an Al machine learning algorithm to generate the persona token. The result is to correlate the user’s click on an item with an actual purchase of the item or a similar item. The purchased item or similar item correlated to the ad click for the item or similar item may be purchased from any merchant and is not limited to purchasing of the item from the merchant website visited by the user as a result of clicking on the ad. The correlation to the ad click may be the user’s actual purchase of the item or similar item or a purchase from a merchant. As a result of the click on an advertised item, the payment network may receive “item data” associated with the user’s click on the ad including, without limitation, the user ID (provided with user consent), cards used by the user to make online e- commerce purchases, the URL of the ad for the item, the SKU data associated with the item, the item website or webpage, the item description, the name of the merchant, among other data that can be associated with the user’s click on the advertised item.

[0119] FIG. 2 illustrates an end-to-end user experience (UX) journey in an Al- powered discover-to-buy services platform, according to at least one aspect of the presentdisclosure. In a discovery phase, as shown in a first screenshot 210 of a mobile device displaying contextual prompts driven by LLM (large language model) during an end-to-end UX journey in an Al-powered discover-to-buy services platform. The discovery phase continues in the second screenshot 220 of the mobile device displaying persona data tokens to help deliver the best recommendations. The checkout phases are shown in the third and fourth screenshots 230, 240 of the mobile device displaying a seamless checkout within the commerce app without needing to go to multiple merchant sites to complete a transaction.

[0120] As shown in FIG. 3, the persona token and / or persona insight generated based on the persona token may be provided to an ML / AI algorithm for identifying goods or services for the user associated with the persona token. The identified goods or services may be filtered by the service provider system that generated the persona token and provided to the user. In a discovery phase, the user may be provided with one or more recommendations 310, and an embedded check-out element managed by the service provider system for completing a transaction including one or more of the recommended items 320, 330. Th receipt may be obtained from the resource provider and provided to the user 340. The user may be kept informed of the various process of the transaction by various notifications 350 (e.g., when the payment is tendered to the resource provider, when the item is shipped, delivered, etc.).

[0121] Embodiments may provide different discovery process models illustrated in FIGS. 4-6. In one model, the service provider may send the user insights (e.g., persona insights) to the commerce app so they can streamline the discovery process, as shown in FIG. 5. In another model, the service provider may use consumer insights and provide recommendations to the commerce app, as shown in FIG. 4. The benefit of the first approach is that it is an easier integration model and may likely apply to a broad addressable market. The benefit of the second approach is that several filters and criteria can be applied that would otherwise be ineligible for sharing.

[0122] For a “basic” data token, the service provider can send “persona” information for each user, so that a commerce app can optimize results. The data from the service provider can be an additional stream of information over and above other sources such as acquired third-party data and first party data on the user.

[0123] In embodiments where the service provider returns product recommendations using an integrated product catalog, the product catalog is integrated into a shopping service, commerce platforms have fed (or the service provider has pulled) the catalog and is easily available to search in real-time. The system may allow several product catalogs tosearch from for a given application. There may be variants where the product catalog may be linked to a specific commerce application.

[0124] In embodiments where the service provider returns a product recommendation using prompt engineering, a general product catalog is referenced based on a large language model (LLM) and web-search to make inferences based on user preferences. In some embodiments, the service provider can apply more filters and relevant searches based on consumer insights, including some proprietary data that is not shared directly with the resource providers. The resource provider can receive the recommendations from the service provider and can filter out some recommendations based on additional information from other sources.

[0125] FIG. 4 illustrates one embodiment of a discovery phase 400 associated with a service provider system 402 that discovers products from a merchant application (e.g., commerce application(s)). The user 404 (e.g., consumer) logs into 406 a commerce application on the user device 408. The commerce application sends 410 a persona token identifier and user preferences to the service provider system 402 to receive the associated persona insights. The service provider system 402 generates 412 relevant insights associated with the persona token and returns 414 the persona insights to the commerce application to be included in existing engines to personalize the consumer experience. The service provider system 402 notifies 416 an authorizing entity 418 (e.g., issuer of a user account) of the persona insight request.

[0126] FIG. 5 illustrates one embodiment of a discovery phase 500 where a service provider system 502 discovers products from one or more third-party applications (e.g., commerce platforms). The user 504 logs into 506 a commerce application on the user device 508. The user 504 may already have a provisioned persona token on the commerce application. The commerce application requests 510 personalized products from the service provider system 502 (e.g., transaction processing entity) by sending user intent, user data, and the persona token identifier. The service provider system 502 identifies the persona token 512 at a restricted access database using the persona token identifier and generates persona insights for the given persona token 512. The service provider system 502 also generates 514 search criteria using an LLM engine and requests product results from one or more commerce platforms 516. The commerce platforms 516 return 518 matched results to the service provider system 502. In some embodiments, the service provider system 502 may build an OBO product catalog service to cache commerce platform data. A module 520 in the service provider system 502 (e.g., the shopping service) consolidates results from the commerce platforms 516 and returns 522 the curated product list to the commerceapplication. The service provider system 502 notifies 524 an authorizing entity 526 (e.g., issuer of a user account) of the persona insight request. The commerce application may present 528 a browsable, personalized product list to the user 504.

[0127] FIG. 6 illustrates one embodiment of a discovery phase 600 where a service provider system 602 discovers products from any third-party applications (e.g., commerce application(s)). The user 604 logs into 606 a commerce application on the user device 608. The user 604 may already have a provisioned persona token on the commerce application. The commerce application requests 610 personalized products from the service provider system 602 (e.g., transaction processing entity) by sending user intent, user data, and persona token identifier. The service provider system 602 identifies the persona token 612 at a restricted access database using the persona token identifier, generates persona insights for the persona token, and generates 614 search criteria and like products for a given commerce application via an LLM engine 616. The LLM engine 616 returns 618 product recommendations to the service provider system 602. The service provider system 602 refines the results provided by the LLM engine 616 and returns 620 refined product recommendations to the commerce application. The service provider system 602 notifies 622 an authorizing entity 624 (e.g., issuer of a user account) of the persona insight request. The commerce application may present 626 a browsable, personalized product list to the user.

[0128] FIG. 7 illustrates one embodiment of a checkout phase 700 where a user 702 starts a checkout process from a third-party application. The user 702 has logged into 704 a commerce application on a user device 706 and has added products to their shopping cart and chosen to check out. The commerce application initiates 708 retrieval of transaction options for the products in the shopping cart based on shipping address, payment product type, etc. A module 710 in the service provider system 712 (e.g., checkout of the shopping service) requests 714 the set of product- and merchant-specific transaction options from the respective commerce platforms 716. The commerce platforms 716 respond 718 with the transaction options. The service provider system 712 responds 720 with transaction options. The commerce application facilitates the checkout user experience to collect / modify the required / optional transaction data for each of the selected products (e.g., shipping options, loyalty, offers) until the user confirms payment 722. The commerce application submits 724 the finalized shopping cart to the service provider including product, payment, and transaction information. The service provider system 712 (via the payment module) initiates 726 payment for each respective commerce platform 716 with required product, payment, and transaction information. The service provider system 712 responds 728 with anindication that payment has been completed so that the commerce application can present 730 order confirmation for purchase(s) to the user.

[0129] In some embodiments, a discover-to-buy marketplace, shopping assistant, or social network system may operate as disclosed in the following example. A commerce application presents a listing of items and / or ads as consumers log in. The consumer may buy one or more recommended items across all the respective merchant commerce platforms. The commerce application personalizes the consumer experience based on service provider insights (e.g., data tokens). The commerce application provides an incontext “buy” experience. The service provider network manages consumer consent, sends payment network insights to improve CTR, and orchestrates payment requests across a merchant’s commerce platform. The commerce platform enables merchant onboarding on the service provider network, orchestrates payments and fulfillment on behalf of merchants, and forwards the transaction to a payment network. The commerce platform sends notifications to a receiver along with fulfillment data (e.g., basket data). The receiver’s application sends a notification to the receiver with fulfillment data. The receiver delivers goods, adjusts inventory, etc. The payment network forwards 830 the transaction to the sender’s bank, and the sender’s bank authorizes 832 the transaction.

[0130] In one embodiment, as shown in FIG. 8, a method 800 of discover-to-buy by a returning user with payment attribution is shown in a cross-functional flow diagram. A user 802 (e.g., consumer) retrieves 804 a persona token from a direct-to-business (D2B) service 806 via a social media / commerce application. The D2B service 806 generates 808 the persona token and sends 810 the persona token to the social media / commerce application 812. The social media / commerce application 812 provides 814 a feed of product offerings to a user device. The user 802 selects 816 an item / product from the feed. The user identity and item / product data are sent 818 to the D2B service 806. The user 802 is redirected 820 to the item / product page within the social media / commerce application. The user 802 sends 820 intent to buy the item / product to the merchant 824. The user 802 selects 826 a payment method and confirms 826 intent to buy. The merchant 824 sends 828 an authorization request to the acquirer 830. The acquirer 830 requests 832 authorization from the payment network 834 and the payment network 834 sends 836 approval back to the acquirer 830. The acquirer 830 sends 838 an authorization response to the merchant 824. The merchant 824 sends 840 payment confirmation to the user 802. The payment network 834 sends 842 payment data to the D2B service 806. The D2B service 806 matches 844 the payment data to the user identity and item / product data. The D2B service 806 adds 846 the matched payment data to machine learning for persona token generation. The D2B service 806 sends 848 the payment attribution to the social media / commerce application 812.

[0131] FIG. 9 illustrates a discover-to-buy payment attribution system 900, according to at least one aspect of the present disclosure. The website (e.g., e-commerce, merchant, or social media websites) serves sponsored advertisement links. When a user clicks on the link and makes a purchase on the linked e-commerce / merchant / social media website, the original website (e-commerce, merchant, social media website) does not know that a purchase ultimately results from the clicked ad. The payment network, however, includes an attribution module to “attribute” or “credit” the purchase automatically. This issue also applies to in-store purchases that occur as a result of a user seeing an ad for a product or service on a website and then physically going into a store to purchase the product or service. In either scenario, the discover-to-buy payment attribution system connects the advertisement to the ultimate purchase.

[0132] Originating websites (e.g., e-commerce, merchant, or social media websites) hosting advertisements may inform a payment network (e.g., a credit card processing network) of a user click on an advertisement or a presentment of the advertisement along with some data about the user. The payment network may use the provided information about the user to determine and match (via transactions that flow through the payment network) if a user who was served a particular advertisement on a website ultimately executed a purchase transaction for the item or service advertised with a particular merchant. Additional analysis may be employed to determine if the purchased item or service was the same or related to the advertised item or service. The analysis may take into account the purchase transaction amount. Further functionality may include updating the advertisements that are served post-purchase to remove the item or service that was already purchased, since the user has already made the purchase, and this may resolve stale advertisements. Additional insights may be gleaned for customized advertisements resulting in determining the likelihood that the user purchased related items or services. For example, if a user purchases a new mattress an algorithm may determine the likelihood of the user purchasing pillows, sheets, or blankets.

[0133] According to aspects of this disclosure, the discover-to-buy payment attribution system 900, as shown in FIG. 9, connects advertisements served on one platform / website with actual transactions occurring in-store or on an e-commerce, merchant, or social media website. The system also incorporates the use of personal tokens containing data about a user and their recent purchases as well as potential future purchases. The system further comprises processing algorithms to compare payment network data with data from platforms hosting advertisements to determine whether a user completed a purchase as a result of seeing an advertisement.

[0134] According to various embodiments, the service provider may define specifications and programs for user applications, product catalogs, and cross-scheme embedded checkout service providers. Resource providers and commerce platforms may embed persona tokens to drive the commerce experience.

[0135] Embodiments provide a virtual assistant interface in text, voice, vision, AR, VR, or combination thereof, to access to wide range of choices to select from (e.g., itineraries, restaurants, products, services), provide ultra-tailored experiences by giving relevant recommendations based on explicit, implied, and subconscious preferences of the user, and enable last mile of purchasing the product or service by facilitating checkout on behalf of the user, while ensuring privacy, transparency, and security within the ecosystem.

[0136] In another embodiment, disclosed herein is a method to create a privacy and consent enabled data token (e.g., persona token) that belongs to the user. Data tokens can be used to customize and enhance the user’s experience with a commerce applicant. The use of data tokens provides various benefits including: (i) the user will be able to control their data and when they want to deploy it to create better user interface experiences, (ii) the platforms and sellers could then use their own custom models, or partner with third parties to create better user interface experiences, (iii) user will be able to create a “you-know-me” experience even if they’ve never interacted with the resource provider.

[0137] According to various embodiments, the user may request a persona token with a service provider, either by interacting with the service provider website / application, over the phone, by filling out a questionnaire or by directly interacting with a representative at the service provider site. The persona token may be generated based on the user’s preferences, prior selections, demographic data, etc. The persona token may be associated with a persona token identifier. The service provider may store the persona token at a restricted access database that is accessible by the service provider and return the persona token identifier to the user. The user may provision their persona token on various resource provider applications or commerce platforms.

[0138] Persona tokens may use history and predictive outlook to optimize user’s experience by curating product recommendations in a commerce application (e.g., a merchant application). By obtaining consent and securing this data into a consumable format called a persona “data” token, the service provider can solve ethical considerations regarding transparency in data usage, addressing biases, consumer consent and guidelines for responsible Al deployment.

[0139] An AI / ML algorithm may generate persona insights based on the persona token. For example, an inquiry about identifying a particular good (e.g., shoes) may beprovided to the AI / ML algorithm, which may run a customized search for the user based on the user’s persona token. The identified goods (e.g., shoes) are most likely to match the user’s preferences as the goods are identified using the persona token.

[0140] According to various embodiments, a persona token is a unique identifier for a user credential (e.g., PAN or a user ID) in a given “domain” (e.g., business entity or a device). The identifier, like payment tokens, can then be used to retrieve the underlying “data”. Participating consumer applications must be able to provision a persona token, so that they can retrieve consumer’s insights and streamline their shopping journey. According to various embodiments, the persona token provisioning may be plugged in to existing tokenization / token provisioning flows, or messages.

[0141] The persona token may be provisioned on a user device (e.g., digital wallet) or on a specific application (e.g., resource provider app or commerce platform app). In some embodiments, the persona tokens are provisioned across “all payment cards associated with the service provider at a given merchant”, as opposed to a payment token that is linked to underlying payment account.

[0142] Persona Tokens provide user-level insights on user behavior to drive enriching and personalized experiences. The service provider is able to identify the cohort spend on a given merchant or a segment, relative to cardholder spend. This data is used to build models to identify cardholder spend propensity.

[0143] Referring now to FIG. 10, disclosed herein is a computer-implemented method for enabling personalized commerce 1000. In such embodiments, the method includes receiving, by a service provider system, a request from a commerce application to retrieve product recommendations for a user 1010, retrieving, by the service provider system, a persona token associated with the user from a restricted access database 1020, generating, by a machine learning model hosted on the service provider system, one or more product recommendations based on persona insights derived from the persona token 1030, and transmitting the product recommendations to the commerce application for display on a user device 1040. In some embodiments, generating one or more product recommendations 1030 may include interpreting contextual signals with a large language model and refining results based on historical purchase behavior.

[0144] In some embodiments, the method may include generating the product recommendations comprises interpreting contextual signals associated with persona token with a large language model and refining results based on user behaviors associated with persona token. In some embodiments, the method may include generating the persona token using synthetic user data reflective of a user’s cohort behavior to preserve privacy. Insuch embodiments, the method may include generating a cohort behavior based on a plurality of user data comprising one or more of user demographic data, transaction history, or user behaviors. In some embodiments, the method may include generating the persona token using one or more of user demographic data, transaction history, or user behaviors, wherein generating comprises privacy-preserving attributes. In the one or more embodiments, user behaviors comprise one or more of browsing history, click-through rate, session duration, previous purchase history, demographic information, user ID, cards used by the user to make online e-commerce purchases, URL of the item, SKU data associated with the item description, item cost, and name of merchant.

[0145] In some embodiments, the method may include receiving, from the commerce application, a user response to a search prompt generated using the persona token, and refining the product recommendations based on the response. In some embodiments, the method may include generating the persona token using synthetic training data reflective of a user's cohort behavior to preserve privacy. In some embodiments, the method may include filtering the product recommendations using platform-specific constraints of the commerce application before transmission. In some embodiments, the method may include caching product data retrieved from third-party platforms to optimize future discovery phases. In some embodiments, the method may include notifying a partner platform of the persona insight request and attributing the request to a tokenized user session.

[0146] Referring now to FIG. 11, disclosed herein is a method for attributing a purchase event to a digital advertisement interaction 1100. In such embodiments, the method includes receiving, at a service provider system, an indication of a user interaction with a digital advertisement for a product 1110, receiving, at the service provider system, transaction data indicative of a purchase of a product by the user from a resource provider 1120, matching the transaction data with the user interaction using the persona token identifier 1130, and generating attribution data for the matched transaction data 1140. In such embodiments, the user interaction is associated with a persona token identifier. In such embodiments, the attribution data indicates that the purchase event is associated with the user interaction of the advertisement.

[0147] In some embodiments, the method may include computing a likelihood score for associating the user interaction with the transaction data based on time of interaction, SKU similarity, and transaction metadata. In some embodiments, the method may include receiving the transaction from a payment network in the form of anonymized purchase event notifications. In some embodiments, the method may include updating a user's persona token based on the attributed purchase to reflect recent purchase behavior. In someembodiments, the attribution data may include merchant name, product category, transaction amount, and timestamp. In some embodiments, the method may include updating, by the service provider system, an advertisement-serving algorithm based on the effectiveness of the attributed purchase event.

[0148] In yet other embodiments, disclosed herein is a system for provisioning and utilizing persona tokens in an Al-powered commerce environment. In such embodiments, the system includes a memory storing instructions and a processor operable to execute the instructions to: receive a request to generate a persona token for a user, generate a persona token based on the request, store the persona token in association with a persona token identifier in a restricted access database, provision the persona token identifier to one or more commerce applications, and enable use of the persona token to personalize product discovery or checkout experiences for the user in the commerce applications. In such embodiments, the request includes user consent and at least one of user demographic data, transaction history, or behavioral profile.

[0149] In some embodiments, the processor may be operable to initiate embedded checkout functionality using payment tokens associated with the user.

[0150] In some embodiments, the system may include a notification module that informs an authorizing entity of a persona insight request triggered by the commerce application.

[0151] In some embodiments, the processor may be operable to generate the persona token using synthetic user data reflective of a user’s cohort behavior to preserve privacy. In some embodiments, the user behavioral profile comprises one or more of browsing history, click-through rate, session duration, previous purchase history, demographic information, user ID, cards used by the user to make online e-commerce purchases, URL of the item, SKU data associated with the item description, item cost, and name of merchant.

[0152] In some embodiments, the processor may be operable to perform cohort analysis across persona tokens to identify purchasing trends and improve conversion of product discovery to product purchase.

[0153] In some embodiments, the system may include a federated identity verification module operable to authenticate user identity prior to provisioning the persona token.

[0154] In some embodiments, the persona token may include machine-readable structured data including inferred preferences, transaction frequency, and merchant affinity.

[0155] In some embodiments, the processor may be operable to deliver purchase attribution insights to third-party analytics platforms in accordance with a consumer consent framework.

[0156] Referring now to FIG. 12, disclosed herein is a method for determining user intent to purchase an item displayed on a social media or e-commerce website 1200. In such embodiments, the method includes receiving a click event indicating user interaction with an item displayed on the social media or e-commerce website 1210, analyzing item details associated with the click to determine whether the item details can be associated to past or future transactions stored by the payment network 1220, and correlating the click event with an actual purchase event of the item by the user within a predetermined time frame 1230.

[0157] In some embodiments the user behavior data includes one or more of browsing history, click-through rate, session duration, previous purchase history, demographic information, user ID, cards used by the user to make online e-commerce purchases, URL of the item, SKU data associated with the item description, item cost, and name of merchant.

[0158] In some embodiments, determining an intent to purchase the item further may include applying machine learning algorithms to the user behavior data to identify patterns indicative of purchase intent. In some embodiments, correlating the click event with an actual purchase event may include matching user identifiers associated with the click event and the purchase event. In some embodiments, determining whether the item details can be associated to past or future transactions may include applying machine learning algorithms to the item data to identify patterns indicative of past or future transactions. In some embodiments, associating item details to past or future transactions may include matching the merchant selling the item to merchant categories sold by merchants in the past and future transactions, and matching prices of the item to the amount of the past and future transactions, analyzing the time of the purchase to match to past and future transactions, and applying cohort analysis to match the type of cardholder that would purchase similar items.

[0159] In some embodiments, the method may further include generating a report indicating the effectiveness of displaying the item on the social media or e-commerce website based on the correlation between click events and actual purchase events. In some embodiments, the item is associated with a product or service.

[0160] In some embodiments, disclosed herein is a method performed by a service provider computer. The method includes receiving input from one or more sources including at least a user, generating a persona token based on the received input, transmitting thepersona token identifier to the user, receiving the persona token from an application server, generating persona insights based on the persona token, transmitting the persona insights to the application server. In some embodiments, the persona token is associated with a persona token identifier. In some embodiments, the persona insights are provided to an AI / ML algorithm for identifying goods or services for the user.

[0161] In some embodiments, the application server is associated with one of a resource provider or a commerce platform that can scan items provided by two or more resource providers.

[0162] In some embodiments, the persona token is generated based on at least one or more user preferences, prior selections, demographic data.

[0163] In some embodiments, the method further includes receiving a request to provision the persona token on a user device. In some embodiments, the persona token is provisioned on a digital wallet or an application executing on the user device, where the application is managed by the application server.

[0164] In some embodiments, the method further includes storing a correspondence between the persona token identifier and the persona token at a restricted access database.

[0165] In some embodiments, the application may be a commerce application associated with a resource provider. In such embodiments, the method may further include generating a search request using an LLM engine, receiving a list of results from the one or more commerce platforms, generating a curated product list from the list of results based on the persona token and additional information available to the service provider computer, and transmitting the curated product list to the commerce application to be displayed to the user. In such embodiments, the search request requests product results from one or more commerce platforms.

[0166] In some embodiments, the application may be a commerce application associated with a resource provider. In such embodiments, the method may further include generating a search criteria and like products for the commerce application via an LLM Engine, receiving a list of results from the LLM engine, generating a curated product list from the list of results based on the persona token and additional information available to the service provider computer, and transmitting the curated product list to the commerce application to be displayed to the user.

[0167] In some embodiments, disclosed herein is a method performed by a service provider computer. In such embodiments, the method includes receiving a persona token enrollment request from a user, generating a persona token, and provisioning the personatoken identifier to the user. In such embodiments, the user is associated with user data on a restricted access database. In such embodiments, the persona token is generated based on at least one or more user preferences, user behaviors, prior selections, demographic data, and purchase history. In such embodiments, the persona token is associated with a persona token identifier.

[0168] In some embodiments, the method may further include receiving a request to provision the persona token associated with the person token identifier to a commerce application executing on a user device and provisioning the persona token to the commerce application executing on the user device. In such embodiments, the persona token is provided to an artificial intelligence algorithm for identifying goods or services for the user by the commerce application.

[0169] In some embodiments, the method may further include authenticating the user on the commerce application before provisioning the persona token to the commerce application.

[0170] In some embodiments, the method may further include computing, from a database of user data, one or more cohort insights from the user data. In such embodiments, user behavior data and user preference data are used independent of user identifiable data in one or more cohort insights.

[0171] In some embodiments, the method may further include storing a correspondence between the persona token identifier and the persona token at the restricted access database.

[0172] In other embodiments, disclosed herein is a method of using a persona token at a commerce application. In such embodiments, the method includes requesting, from a service provider, a persona token being associated with a user, generating one or more personalized recommendations for goods or services based on the persona token, displaying the personalized recommendations on a user device, and receiving one or more actions from the user in response to the personalized recommendations.

[0173] In some embodiments, receiving one or more actions from the user in response to the personalized recommendations may include receiving a click event indicating user interaction with an item displayed from the personalized recommendations, determining an intent to purchase the item, analyzing item details associated with the click event to determine whether the item details can be associated to past or future transactions stored by the service provider, and correlating the click event with an actual purchase event of the item by the user within a predetermined time frame.

[0174] In some embodiments, determining an intent to purchase the item may further include applying machine learning algorithms to user behavior data of the persona token to identify patterns indicative of purchase intent.

[0175] In some embodiments, the user behavior data may include one or more of browsing history, click-through rate, session duration, purchase history, demographic information, user ID, cards used by the user to make online e-commerce purchases, URL of the item, SKU data associated with the item, item description, item cost, and name of merchant.

[0176] In some embodiments, correlating the click event with the actual purchase event may include matching a persona token identifier associated with the click event and a persona token identifier associated with the actual purchase event.

[0177] In some embodiments, determining whether the item details can be associated to past or future transactions may include applying machine learning algorithms to an item data to identify patterns indicative of past or future transactions.

[0178] In some embodiments, associating item details to past or future transactions may include matching a merchant selling the item to merchant categories sold by merchants in the past and future transactions and a matching price of the item to an amount of the past and future transactions, analyzing a time of the purchase to match to past and future transactions, and applying cohort analysis to match a type of cardholder that would purchase similar items.

[0179] In some embodiments, the method may further include, based on a determination of an intent to purchase, requesting authorization, from a payment network, to execute a purchase of the item.

[0180] In some embodiments, the service provider may include the payment network.

[0181] In some embodiments, the method may further include generating a report indicating an effectiveness of displaying the item based on a correlation between click events and actual purchase events.

[0182] In some embodiments, generating one or more personalized recommendations for goods or services based on the persona token may include generating a search prompt using a large language model, receiving a user response to the search prompt, and generating, using the search prompt, the user response, and the persona token, personalized recommendations for goods or services.

[0183] In yet other embodiments, disclosed herein is a system to make and use persona tokens. In such embodiments, the system includes a service provider network including one or more processors and one or more storage devices, the one or more storage devices including a database having user data stored thereon. In such embodiments, the one or more storage devices have stored thereon instructions that when executed cause the one or more processors to: receive a persona token enrollment request from a user, generate a persona token, and provision the persona token identifier to the user; and provision the persona token to a commerce application. In such embodiments, the user is associated with a user data on the database. In such embodiments, the persona token is generated based on at least one or more of user preferences, user behaviors, prior selections, demographic data, and purchase history. In such embodiments, the persona token is associated with a persona token identifier. In such embodiments, the persona token is provided to an artificial intelligence algorithm for identifying goods or services for the user

[0184] In some embodiments, the service provider network may receive, from the commerce application, data of a user purchase event related to the identified goods or services. In such embodiments, the data of a user purchase is stored at the database of user data. In such embodiments, the one or more processors recompute the persona token from the database of user data.

[0185] In some embodiments, the service provider network may further include a payment network.

[0186] In some embodiments, the service provider network may further include instructions to: compute one or more cohort insights from a portion of the user data, wherein user behavior data and user preference data are used independent of the identification data.

[0187] FIG. 13 illustrates a payment network system 1300, according to various embodiments of the present disclosure. The payment network system 1300 facilitates payment transactions between a plurality of entities, including a payment network 1302, an issuer 1304, a cardholder 1306, a merchant 1308, and an acquirer 1310 and forms a part of the digital hospitality experience platform. Each of these entities is communicatively coupled via a communication network 1312, which may include one or more computer systems and network infrastructure (e.g., the Internet, cellular networks, and other wired or wireless communication paths).

[0188] The payment network system 1300 may include one or more server computers, processing subsystems, and network elements to support transaction processing, authorization, and settlement. The payment network system 1300 may route authorization requests and responses between acquirers and issuers and to maintainoperational control over clearing, fraud detection, and risk management workflows. In some embodiments, the payment network includes or is associated with a computer system 1600 as described in FIG. 16 and may operate over a communication system.

[0189] The issuer may be a financial institution (e.g., a bank) that issues payment accounts to consumers. The issuer may be responsible for provisioning an account to a cardholder, which account may be associated with a Primary Account Number (PAN) or other identifier. The issuer is further responsible for performing account-level functions including, but not limited to, authorization of transactions, fraud assessment, and risk management. In certain implementations, the issuer also may act as the acquirer.

[0190] The account holder may access the payment network system using a client device or user device, such as a mobile phone, tablet, laptop, or smart card. The cardholder may initiate a payment transaction with a merchant using the account issued by the issuer. For example, the cardholder may present the account (or a tokenized version thereof) to the merchant using a near field communication (NFC) interface at a point-of-sale terminal. In other embodiments, the merchant may store the PAN or an associated token in a card-on- file system for use in recurring or future transactions.

[0191] Authentication of the account holder may be performed by the issuer using a variety of identity verification mechanisms. In some embodiments, the issuer may use a 3-D Secure Access Control Server (ACS), mobile banking verification, federated login systems, or other authentication mechanisms involving shared secrets, activation codes, or one-time passwords (OTPs). OTPs may be generated and delivered through out-of-band channels, such as secure mobile applications. In certain aspects, static passwords and enrollmentbased verification may be disallowed to enhance security. Preferred OTP implementations may involve codes of 6 to 8 digits, generated using a consistent methodology and delivered securely to a registered device of the account holder.

[0192] The acquirer may be a financial institution or processing system associated with the merchant. The acquirer may be responsible for managing the merchant’s account and may provide services including, but not limited to, authorization request routing, transaction capture, clearing, settlement, and exception handling. In a transaction flow, the acquirer may receive a payment request from the merchant and forward an authorization request message to the issuer via the payment network. The response received from the issuer may be relayed back to the merchant by the acquirer.

[0193] The payment network may handle routing of transaction messages between the acquirer and the issuer. Implementations include, without limitation, the payment networkis responsible for forwarding authorization requests and responses, managing settlement procedures, and implementing transaction logging and fraud detection.

[0194] In certain embodiments, the payment network includes a generative artificial intelligence and machine learning (AI / ML) module 1314. This AI / ML module may analyze real-time transaction data and detect anomalies, usage trends, and potential fraud scenarios associated with transactions conducted over the digital hospitality experience platform. The AI / ML module may generate adaptive risk scores that inform decision-making by the issuer and acquirer and may provide recommendations for modifying authorization rules or tokenization techniques based on contextual transaction attributes, such as merchant category codes, user behavior profiles, or geolocation data.

[0195] The AI / ML module may be implemented as a cloud-based platform within the payment network and may utilize federated learning or secure multiparty computation to maintain data privacy while enabling shared learning across multiple institutions. The system may continuously train on historical data to enhance fraud detection, risk modeling, and authorization performance.

[0196] A system of one or more computers can perform particular operations or actions associated with the digital hospitality experience platform described herein by virtue of having software, firmware, hardware, or a combination of them installed on the system that in operation causes the system to perform the actions. One or more computer programs can perform particular operations or actions by virtue of including instructions that, when executed by data processing apparatus, cause the apparatus to perform the actions. Other embodiments include corresponding computer systems, apparatus, and computer programs recorded on one or more computer storage devices, each to perform the actions of the methods.

[0197] FIG. 14 illustrates a block diagram of a tokenization environment 1400 portion of a token management system, according to at least one aspect of the present disclosure. FIG. 14 illustrates an example tokenization environment 1400 including a token server computer 1402 of a token service provider. The token server computer 1402 may be in communication with a token requesting party 1404. The token requesting party 1404 may operate a token requesting party computer. In some aspects, the token server computer 1402 also may be in communication with a transaction processing network computer 1406 such as, for example, a payment network. In other aspects, the token server computer 1402 may be part of the payment network. In various aspects, the token server computer 1402 is in communication with a payment network token gateway server computer.

[0198] The token server computer 1402 may be responsible for provisioning a token using a provisioning module 1408 in conjunction with a data processor 1410. Provisioning may include creating a token within a token vault 1412 for an account, sending the token to the token requesting party 1404 and sending the token to the token recipient.

[0199] According to aspects directed to payment transactions, the token requesting party 1404 may be an account holder, a payment processing network, an issuer, an acquirer and / or a merchant. Aspects discussed below are directed to the token requesting party 1404 being an issuer or a third party acting on behalf of the issuer. Aspects of the invention, however, are not restricted to a token requestor that is an issuer.

[0200] In some aspects, the token requesting party 1404 may register with the token server computer 1402 using an online portal or a website of the token server computer 1402. The online portal or the website may provide a user interface 1420 to allow the token requesting party 1404 to interact with the token server computer 1402 to control the token generation process.

[0201] Using the user interface 1420, the token requesting party 1404 may request the token server computer 1402 to generate one or more tokens for a plurality of accounts issued, owned and / or managed by the token requesting party 1402.

[0202] The token requesting party 1404 (e.g., a computer operated by the token requesting party 1404) may provide a set of account identifiers to the token server computer 1402. The token server computer 1402 may generate (or determine) a token for the account identifier received from the computer operated by the token requesting party 1404. The generated tokens may be stored at a token vault 1412. The token vault 1412 also may store a mapping between each token and the account identifier identifying the account represented by the token. The token vault 1412 also may be used by the transaction processing network computer 1406 to de-tokenize the token and convert the token to the account number represented by the token when a transaction authorization is processed through the transaction processing network computer 1406. The token vault 1412 also may manage all domain restrictions associated with each token provisioned.

[0203] The token requesting party 1404 also may select, with the data processor 1410 executing a key management module 1414 of the token server computer 1402, an option associated with encryption keys. For example, the token requesting party 1404 may choose to provide the encryption keys to the token server computer 1402 via the key management module 1414. In some aspects, the token requesting party 1404 may choose to leave the key generation to the token server computer 1402. The token server computer 1402 may generate (or determine) the tokensbased on the option associated with the encryption keys. The token server computer 1402 may generate a token associated with at least one encryption key for each account identifier of the set of account identifiers. The token server computer 1402 may store the encryption keys along with the associated tokens in the token vault 1412. The encryption keys may then be provided to a user device of the account holder. The tokens and corresponding encryption keys may be used in tokenized transactions processed by the transaction processing network computer.

[0204] The token requesting party 1404 also may initiate a request to receive a message when a token has been generated and / or provisioned for one of the accounts associated with the token requesting party 1404. The token server computer 1402 may generate a notification using the data processor 1410 executing code in the notification module 1416 based on the notification criteria (e.g., when a token satisfies the notification criteria) provided by the token requesting party 1404. It also may send the notification to the token requesting party 1404. For example, the token requesting party 1404 may request a notification when a token is generated. The notification module 1416 of the token server computer 1402 may generate and send a notification to the token requesting party 1404 when the token is generated. Similarly, the token requesting party 1404 may request a notification when a token is provisioned on a user device. The notification module 1416 of the token server computer 1402 may generate and send a notification to the token requesting party 1404 when the token is provisioned on the user device. For example, the notification module 1416 may be informed by the provisioning module 1408 that the token has been provisioned.

[0205] The token server computer 1402 also may include a risk management module 1418 that can work in conjunction with the data processor 1410 to set up rules for risk decisioning when the token server computer 1402 receives the token provisioning request from the token requesting party 1404. As part of further customization of the token generation process, the token requesting party 1404 may indicate rules for provisioning or processing the token based on a risk assessment associated with a transacting party, a device used in the transaction, or the account itself. In some aspects, the token requesting party 1404 may provide a restriction that is placed on one or more of the generated tokens based on the risk decision making rules.

[0206] The token server computer 1402 shown in FIG. 14 is provided for illustration purposes and should not be construed as limiting. The token server computer 1402 may include more or less components than those illustrated in FIG. 14. For example, the token server computer 1402 may include additional software modules, such as a processingmodule, a lifecycle management module, etc. These and other modules may, in conjunction with the data processor 1410, allow the token server computer 1402 to perform one or more of the following functions: map an account identifier to a token and store the mapping in the token vault with relevant domain restrictions; provision a token from the token vault to a user device; manage (e.g., delete, suspend, resume, etc.) the token both at the token vault and on the user device; generate encryption keys based on the token requesting party's request; manage encryption keys based on predetermined criteria; process tokenized transactions including performing cryptogram validation, domain restriction checks, and validity checks; and perform post-transaction verification processing to verify that transactions and account updates are conducted on the user device after the transaction is processed by the transaction processing network.

[0207] In some aspects, the token server computer 1402 may support contactless payment use cases. This includes support for contactless payment methods using a secure element and Host Card Emulation (HCE)-based payment applications.

[0208] FIG. 15 is a block diagram of a computer apparatus 1500 with data processing subsystems or components, according to at least one aspect of the present disclosure. The subsystems shown in FIG. 15 are interconnected via a system bus 1510. Additional subsystems such as an output device 1518 (e.g., printer, monitor), input device 1526 (e.g., keyboard), storage device 1528 (fixed disk or other memory comprising computer readable media). Peripherals and input / output (I / O) devices, which couple to an I / O controller 1512 (which can be a processor or other suitable controller), can be connected to the computer system by any number of means known in the art, such as a serial port 1524. For example, the serial port or external interface 1530 can be used to connect the computer apparatus to a wide area network such as the Internet, a mouse input device, or a scanner, known as the cloud 1520. The interconnection via system bus allows a processor 1516 (CPU, processing unit, controller, control circuit) to communicate with each subsystem and to control the execution of instructions from system memory 1514 or the storage device (e.g., fixed disk), as well as the exchange of information between subsystems. The system memory and / or the storage device may embody a computer-readable medium. The processor and the system bus may couple various system components including the system memory, such as read only memory 1531 (ROM) and random-access memory 1532 (RAM), to the processor. The computing apparatus can include a cache 1534 of high-speed memory connected directly with, in close proximity to, or integrated as part of the processor.

[0209] The computing system can copy data from the memory, ROM, RAM, and / or storage device to the cache for quick access by the processor. In this way, the cache canprovide a performance boost that avoids processor delays while waiting for data. These and other modules can control the processor to perform various actions. Other system memory may be available for use as well. The memory can include multiple different types of memory with different performance characteristics. The processor can include any general-purpose processor and a hardware module or software module, such as modules 1536 (e.g., MOD 1 - MOD n) stored in the storage device, to control the processor as well as a special-purpose processor where software instructions are incorporated into the actual processor design. The processor may essentially be a completely self-contained computing system, containing multiple cores or processors, a system bus, memory controller, cache, etc. A multi-core processor may be symmetric or asymmetric.

[0210] To enable user interaction with the computer apparatus, the input device can represent any number of input mechanisms, such as a microphone for speech, a touch- protected screen for gesture or graphical input, keyboard, mouse, motion input, speech and so forth. The output device can also be one or more of a number of output mechanisms known to those of skill in the art. In some instances, multimodal systems can enable a user to provide multiple types of input to communicate with the computer apparatus. The external interface (communications interface) can govern and manage the user input and system output. There may be no restriction on operating on any particular hardware arrangement and therefore the basic features here may easily be substituted for improved hardware or firmware arrangements as they are developed.

[0211] The storage device can be a non-volatile memory and can be a hard disk or other types of computer readable media which can store data that are accessible by a computer, such as magnetic cassettes, flash memory cards, solid state memory devices, digital versatile disks, cartridges, random access memory, read only memory, and hybrids thereof.

[0212] As discussed above, the storage device can include the software modules for controlling the processor. Other hardware or software modules are contemplated. The storage device can be connected to the system bus. In some embodiments, a hardware module that performs a particular function can include a software component stored in a computer-readable medium in connection with the necessary hardware components, such as the processor, system bus, output device, and so forth, to carry out the function. For clarity of explanation, in some instances the present technology may be presented as including individual functional blocks comprising devices, device components, steps or routines in a method embodied in software, or combinations of hardware and software.

[0213] Artificial intelligence (Al) and machine learning (ML) modules 1538 embedded within the computer apparatus enables advanced predictive analytics, transforming historical and real-time data into actionable insights. High-performance Tensor Processing Units (TPUs) and Graphical Processing Unites (GPUs), and Central Processing Units (CPUs) support continuous training of Al I ML models that enhance slotting optimization, pick-path efficiency, and demand forecasting. Al-driven algorithms analyze real-time operational data to anticipate potential stockouts, bottlenecks, or equipment failures, allowing the system to adjust task allocations proactively. These Al / ML models are housed on cloud servers 1040, enabling parallel processing and providing adaptive, scalable insights across multiple cloud environments or cloud service providers.

[0214] Leveraging TPUs, GPUs, and CPUs, the computer apparatus continuously trains the ML models to improve the secure agentic commerce system. Al-driven algorithms analyze real-time operational data to enable the system to proactively adjust task allocations and priorities. These Al models are housed on cloud servers, where large datasets can be processed in parallel, providing scalable, adaptive insights to the computer apparatus for managing the secure agentic commerce system.

[0215] FIG. 16 is a diagrammatic representation of an example computer system 1600 that includes a host machine 1602 within which a set of instructions to perform any one or more of the methodologies discussed herein may be executed, according to at least one aspect of the present disclosure. In various aspects, the host machine operates as a standalone device or may be connected (e.g., networked) to other machines. In a networked deployment, the host machine may operate in the capacity of a server or a client machine in a server-client network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. The host machine may be a computer or computing device, a personal computer (PC), a tablet PC, a set-top box (STB), a personal digital assistant (PDA), a cellular telephone, a portable music player (e.g., a portable hard drive audio device such as an Moving Picture Experts Group Audio Layer 3 (MP3) player), a web appliance, a network router, switch or bridge, or any machine capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken by that machine. Further, while only a single machine is illustrated, the term “machine” shall also be taken to include any collection of machines that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methodologies discussed herein.

[0216] The example computer system includes the host machine, running a host operating system (OS) 1604 on a processor or multiple processor(s) / processor core(s) 1606 (e.g., a central processing unit (CPU), a graphics processing unit (GPU), or both), andvarious memory nodes 1608. The host OS may include a hypervisor 1610 which is able to control the functions and / or communicate with a virtual machine (“VM”) 1612 running on machine readable media. The VM also may include a virtual CPU or vCPU 1614. The memory nodes may be linked or pinned to virtual memory nodes or vNodes 1616. When the memory node is linked or pinned to a corresponding vNode, then data may be mapped directly from the memory nodes to the corresponding vNode.

[0217] All the various components shown in the host machine may be connected with and to each other or communicate to each other via a bus (not shown) or via other coupling or communication channels or mechanisms. The host machine may further include a video display, audio device or other peripherals 1618 (e.g., a liquid crystal display (LCD), alpha-numeric input device(s) including, e.g., a keyboard, a cursor control device, e.g., a mouse, a voice recognition or biometric verification unit, an external drive, a signal generation device, e.g., a speaker,) a persistent storage device 1620 (also referred to as disk drive unit), and a network interface device 1622. The host machine may further include a data encryption module (not shown) to encrypt data. The components provided in the host machine are those typically found in computer systems that may be suitable for use with aspects of the present disclosure and are intended to represent a broad category of such computer components that are known in the art. Thus, the computer system can be a server, minicomputer, mainframe computer, or any other computer system. The computer may also include different bus configurations, networked platforms, multi-processor platforms, and the like. Various operating systems may be used including UNIX, LINUX, WINDOWS, QNX ANDROID, IOS, CHROME, TIZEN, and other suitable operating systems.

[0218] The disk drive unit 1624 also may be a Solid-state Drive (SSD), a hard disk drive (HDD) or other includes a computer or machine-readable medium on which is stored one or more sets of instructions and data structures (e.g., data / instructions 1626) embodying or utilizing any one or more of the methodologies or functions described herein. The data / instructions also may reside, completely or at least partially, within the main memory node and / or within the processor(s) during execution thereof by the host machine. The data / instructions may further be transmitted or received over a network 1628 via the network interface device utilizing any one of several well-known transfer protocols (e.g., Hyper Text Transfer Protocol (HTTP)).

[0219] The processor(s) and memory nodes also may comprise machine-readable media. The term “computer-readable medium” or “machine-readable medium” should be taken to include a single medium or multiple medium (e.g., a centralized or distributed database and / or associated caches and servers) that store the one or more sets ofinstructions. The term “computer-readable medium” shall also be taken to include any medium that is capable of storing, encoding, or carrying a set of instructions for execution by the host machine and that causes the host machine to perform any one or more of the methodologies of the present application, or that is capable of storing, encoding, or carrying data structures utilized by or associated with such a set of instructions. The term “computer- readable medium” shall accordingly be taken to include, but not be limited to, solid-state memories, optical and magnetic media, and carrier wave signals. Such media may also include, without limitation, hard disks, floppy disks, flash memory cards, digital video disks, random access memory (RAM), read only memory (ROM), and the like. The example aspects described herein may be implemented in an operating environment comprising software installed on a computer, in hardware, or in a combination of software and hardware.

[0220] Artificial intelligence (Al) and machine learning (ML) modules 1632, may be integrated within the host machine or the computer system, power advanced secure agentic commerce predictive analytics by transforming vast volumes of historical and real-time data into highly actionable operational insights. These intelligent systems are accelerated by high- performance Tensor Processing Units (TPUs), Graphics Processing Units (GPUs), and Central Processing Units (CPUs), which collaboratively support the continuous training and refinement of AI / ML models. This ongoing optimization enables significant improvements in slotting accuracy, pick-path efficiency, and demand forecasting across complex operational environments. The underlying Al models may reside on cloud-based servers 1630, where large-scale data can be processed in parallel, supporting elastic scalability and delivering adaptive, high-resolution insights that empower the secure agentic commerce system.

[0221] By harnessing the combined processing power of TPUs, GPUs, and CPUs, the computer system continuously trains and evolves its machine learning modules to deliver a secure agentic commerce system. The Al algorithms continuously ingest and analyze data to identify signs of potential inefficiencies and provide predictive capability to enable a system for facilitating secure agentic commerce. The computer system also includes an enrollment module to register an agent provider (AP) with a payment network and issue a unique AP identifier. A token module associates a consumer’s payment credential with a token and stores the token at the AP. A communication module injects the token and optional consumer-identifying information into a protocol header for transmission to a merchant. A verification module at the merchant uses a public key from the payment network to authenticate the AP and identify the consumer based on the token. Other embodiments of this aspect include corresponding computer systems, apparatus, and computer programs recorded on one or more computer storage devices, each to perform the actions of the methods.

[0222] Implementations of the computer system for secure agentic commerce may include one or more of the following features. The computer system where the communication protocol may include HTTP, SMTP, or NFC. The communication module may include the AP identifier and consumer identifier in the protocol header and may further include consumer-specific data such as loyalty points or membership details for merchant recognition. The verification module may also support post-transaction features such as notifying the consumer of the purchase, based on the consumer-identifying information associated with the token. This architecture ensures secure and scalable transactions initiated by trusted agents on behalf of consumers, while allowing merchants to maintain transparency, recognize returning consumers, and deliver enhanced customer experiences. Implementations of the described techniques may include hardware, a method or process, or computer software on a computer-accessible medium.

[0223] The Internet service may provide Internet access to one or more computing devices that are coupled to the Internet service, and that the computing devices may include one or more processors, buses, memory devices, display devices, input / output devices, and the like. Furthermore, the Internet service may be coupled to one or more databases, repositories, servers, and the like, which may be utilized to implement any of the various aspects of the disclosure as described herein.

[0224] The computer program instructions also may be loaded onto a computer, a server, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0225] Suitable networks may include or interface with any one or more of, for instance, a local intranet, a PAN (Personal Area Network), a LAN (Local Area Network), a WAN (Wide Area Network), a MAN (Metropolitan Area Network), a virtual private network (VPN), a storage area network (SAN), a frame relay connection, an Advanced Intelligent Network (AIN) connection, a synchronous optical network (SONET) connection, a digital T1 , T3, E1 or E3 line, Digital Data Service (DDS) connection, DSL (Digital Subscriber Line) connection, an Ethernet connection, an ISDN (Integrated Services Digital Network) line, a dial-up port such as a V.90, V.34 or V.34bis analog modem connection, a cable modem, an ATM (Asynchronous Transfer Mode) connection, or an FDDI (Fiber Distributed Data Interface) or CDDI (Copper Distributed Data Interface) connection. Furthermore,communications may also include links to any of a variety of wireless networks, including WAP (Wireless Application Protocol), GPRS (General Packet Radio Service), GSM (Global System for Mobile Communication), CDMA (Code Division Multiple Access) or TDMA (Time Division Multiple Access), cellular phone networks, GPS (Global Positioning System), CDPD (cellular digital packet data), RIM (Research in Motion, Limited) duplex paging network, Bluetooth radio, or an IEEE 802.11 -based radio frequency network. The network can further include or interface with any one or more of an RS-232 serial connection, an IEEE-1394 (Firewire) connection, a Fiber Channel connection, an IrDA (infrared) port, a SCSI (Small Computer Systems Interface) connection, a USB (Universal Serial Bus) connection or other wired or wireless, digital or analog interface or connection, mesh or Digi® networking.

[0226] In general, a cloud-based computing environment is a resource that typically combines the computational power of a large grouping of processors (such as within web servers) and / or that combines the storage capacity of a large grouping of computer memories or storage devices. Systems that provide cloud-based resources may be utilized exclusively by their owners or such systems may be accessible to outside users who deploy applications within the computing infrastructure to obtain the benefit of large computational or storage resources.

[0227] The cloud is formed, for example, by a network of web servers that comprise a plurality of computing devices, such as the host machine, with each server (or at least a plurality thereof) providing processor and / or storage resources. These servers manage workloads provided by multiple users (e.g., cloud resource customers or other users). Typically, each user places workload demands upon the cloud that vary in real-time, sometimes dramatically. The nature and extent of these variations typically depends on the type of business associated with the user.

[0228] It is noteworthy that any hardware platform suitable for performing the processing described herein is suitable for use with the technology. The terms “computer- readable storage medium” and “computer-readable storage media” as used herein refer to any medium or media that participate in providing instructions to a CPU for execution. Such media can take many forms, including, but not limited to, non-volatile media, volatile media, and transmission media. Non-volatile media include, for example, optical or magnetic disks, such as a fixed disk. Volatile media include dynamic memory, such as system RAM. Transmission media include coaxial cables, copper wire and fiber optics, among others, including the wires that comprise one aspect of a bus. Transmission media can also take the form of acoustic or light waves, such as those generated during radio frequency (RF) and infrared (IR) data communications. Common forms of computer-readable media include, forexample, a flexible disk, a hard disk, magnetic tape, any other magnetic medium, a CD-ROM disk, digital video disk (DVD), any other optical medium, any other physical medium with patterns of marks or holes, a RAM, a PROM, an EPROM, an EEPROM, a FLASH EPROM, any other memory chip or data exchange adapter, a carrier wave, or any other medium from which a computer can read.

[0229] Various forms of computer-readable media may be involved in carrying one or more sequences of one or more instructions to a CPU for execution. A bus carries the data to system RAM, from which a CPU retrieves and executes the instructions. The instructions received by system RAM can optionally be stored on a fixed disk either before or after execution by a CPU.

[0230] Computer program code for carrying out operations for aspects of the present technology may be written in any combination of one or more programming languages, including an object-oriented programming language such as Java, Smalltalk, C++, or the like and conventional procedural programming languages, such as the “C” programming language, Go, Python, or other programming languages, including assembly languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0231] The foregoing detailed description has set forth various forms of the systems and / or processes via the use of block diagrams, flowcharts, and / or examples. Insofar as such block diagrams, flowcharts, and / or examples contain one or more functions and / or operations, it will be understood by those within the art that each function and / or operation within such block diagrams, flowcharts, and / or examples can be implemented, individually and / or collectively, by a wide range of hardware, software, firmware, or virtually any combination thereof. Some aspects of the forms disclosed herein, in whole or in part, can be equivalently implemented in integrated circuits, as one or more computer programs running on one or more computers (e.g., as one or more programs running on one or more computer systems), as one or more programs running on one or more processors (e.g., as one or more programs running on one or more microprocessors), as firmware, or as virtually any combination thereof, and that designing the circuitry and / or writing the code for the software and or firmware would be well within the skill of one of skill in the art in light of this disclosure. In addition, the mechanisms of the subject matter described herein are capableof being distributed as one or more program products in a variety of forms, and that an illustrative form of the subject matter described herein applies regardless of the particular type of signal bearing medium used to actually carry out the distribution.

[0232] Instructions used to program logic to perform various disclosed aspects can be stored within a memory in the system, such as dynamic random-access memory (DRAM), cache, flash memory, or other storage. Furthermore, the instructions can be distributed via a network or by way of other computer-readable media. Thus a machine- readable medium may include any mechanism for storing or transmitting information in a form readable by a machine (e.g., a computer), but is not limited to, floppy diskettes, optical disks, compact disc, read-only memory (CD-ROMs), and magneto-optical disks, read-only memory (ROMs), random access memory (RAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic or optical cards, flash memory, or a tangible, machine-readable storage used in the transmission of information over the Internet via electrical, optical, acoustical or other forms of propagated signals (e.g., carrier waves, infrared signals, digital signals, etc.). Accordingly, the non-transitory computer-readable medium includes any type of tangible machine-readable medium suitable for storing or transmitting electronic instructions or information in a form readable by a machine (e.g., a computer).

[0233] Any of the software components or functions described in this application, may be implemented as software code to be executed by a processor using any suitable computer language such as, for example, Python, Java, C++ or Perl using, for example, conventional or object-oriented techniques. The software code may be stored as a series of instructions, or commands on a computer-readable medium, such as RAM, ROM, a magnetic medium such as a hard-drive or a floppy disk, or an optical medium such as a CD- ROM. Any such computer-readable medium may reside on or within a single computational apparatus and may be present on or within different computational apparatuses within a system or network.

[0234] As used in any aspect herein, the term “logic” may refer to an app, software, firmware and / or circuitry may perform any of the aforementioned operations. Software may be embodied as a software package, code, instructions, instruction sets and / or data recorded on non-transitory computer-readable storage medium. Firmware may be embodied as code, instructions or sets of instructions and / or data that are hard-coded (e.g., nonvolatile) in memory devices.

[0235] As used in any aspect herein, the terms “component,” “system,” “module” and the like can refer to a computer-related entity, either hardware, a combination of hardware and software, software, or software in execution.

[0236] As used in any aspect herein, an “algorithm” refers to a self-consistent sequence of steps leading to a desired result, where a “step” refers to a manipulation of physical quantities and / or logic states which may, though need not necessarily, take the form of electrical or magnetic signals capable of being stored, transferred, combined, compared, and otherwise manipulated. It is common usage to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, or the like. These and similar terms may be associated with the appropriate physical quantities and are merely convenient labels applied to these quantities and / or states.

[0237] A network may include a packet switched network. The communication devices may be capable of communicating with each other using a selected packet switched network communications protocol. One example communications protocol may include an Ethernet communications protocol which may be capable of permitting communication using a Transmission Control Protocol / lnternet Protocol (TCP / IP). The Ethernet protocol may comply or be compatible with the Ethernet standard published by the Institute of Electrical and Electronics Engineers (IEEE) titled “IEEE 802.3 Standard”, published in December 2008 and / or later versions of this standard. Alternatively, or additionally, the communication devices may be capable of communicating with each other using an X.25 communications protocol. The X.25 communications protocol may comply or be compatible with a standard promulgated by the International Telecommunication Union-Telecommunication Standardization Sector (ITU-T). Alternatively, or additionally, the communication devices may be capable of communicating with each other using a frame relay communications protocol. The frame relay communications protocol may comply or be compatible with a standard promulgated by Consultative Committee for International Telegraph and Telephone (CCITT) and / or the American National Standards Institute (ANSI). Alternatively, or additionally, the transceivers may be capable of communicating with each other using an Asynchronous Transfer Mode (ATM) communications protocol. The ATM communications protocol may comply or be compatible with an ATM standard published by the ATM Forum titled “ATM-MPLS Network Interworking 2.0” published August 2001 , and / or later versions of this standard. Of course, different and / or after-developed connection-oriented network communication protocols are equally contemplated herein.

[0238] Unless specifically stated otherwise as apparent from the foregoing disclosure, it is appreciated that, throughout the present disclosure, discussions using termssuch as “processing,” “computing,” “calculating,” “determining,” “displaying,” or the like, refer to the action and processes of a computer system, or similar electronic computing device, that manipulates and transforms data represented as physical (electronic) quantities within the computer system's registers and memories into other data similarly represented as physical quantities within the computer system memories or registers or other such information storage, transmission or display devices.

[0239] One or more components may be referred to herein as “configured to,” “configurable to,” “operable / operative to,” “adapted / adaptable,” “able to,” “conformable / conformed to,” etc. The term “configured to” can generally encompass activestate components and / or inactive-state components and / or standby-state components, unless context requires otherwise.

[0240] In general, terms used herein, and especially in the appended claims (e.g., bodies of the appended claims) are generally intended as “open” terms (e.g., the term “including” should be interpreted as “including but not limited to,” the term “having” should be interpreted as “having at least,” the term “includes” should be interpreted as “includes but is not limited to,” etc.). It will be further understood by those within the art that if a specific number of an introduced claim recitation is intended, such an intent will be explicitly recited in the claim, and in the absence of such recitation no such intent is present. For example, as an aid to understanding, the following appended claims may contain usage of the introductory phrases “at least one” and “one or more” to introduce claim recitations.However, the use of such phrases should not be construed to imply that the introduction of a claim recitation by the indefinite articles “a” or “an” limits any particular claim containing such introduced claim recitation to claims containing only one such recitation, even when the same claim includes the introductory phrases “one or more” or “at least one” and indefinite articles such as “a” or “an” (e.g., “a” and / or “an” should typically be interpreted to mean “at least one” or “one or more”); the same holds true for the use of definite articles used to introduce claim recitations.

[0241] In addition, even if a specific number of an introduced claim recitation is explicitly recited, such recitation should typically be interpreted to mean at least the recited number (e.g., the bare recitation of “two recitations,” without other modifiers, typically means at least two recitations, or two or more recitations). Furthermore, in those instances where a convention analogous to “at least one of A, B, and C, etc.” is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., “a system having at least one of A, B, and C” would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together,B and C together, and / or A, B, and C together, etc.). In those instances where a convention analogous to “at least one of A, B, or C, etc.” is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., “a system having at least one of A, B, or C” would include but not be limited to systems that have A alone, B alone, C alone, A and B together, A and C together, B and C together, and / or A, B, and C together, etc.). It will be further understood by those within the art that typically a disjunctive word and / or phrase presenting two or more alternative terms, whether in the description, claims, or drawings, should be understood to contemplate the possibilities of including one of the terms, either of the terms, or both terms unless context dictates otherwise. For example, the phrase “A or B” will be typically understood to include the possibilities of “A” or “B” or “A and B.”

[0242] With respect to the appended claims, recited operations therein may generally be performed in any order. Also, although various operational flow diagrams are presented in a sequence(s), it should be understood that the various operations may be performed in other orders than those which are illustrated or may be performed concurrently. Examples of such alternate orderings may include overlapping, interleaved, interrupted, reordered, incremental, preparatory, supplemental, simultaneous, reverse, or other variant orderings, unless context dictates otherwise. Furthermore, terms like “responsive to,” “related to,” or other past-tense adjectives are generally not intended to exclude such variants, unless context dictates otherwise.

[0243] It is worthy to note that any reference to “one aspect,” “an aspect,” “an exemplification,” “one exemplification,” and the like means that a particular feature, structure, or characteristic described in connection with the aspect is included in at least one aspect. Thus, appearances of the phrases “in one aspect,” “in an aspect,” “in an exemplification,” and “in one exemplification” in various places throughout the specification are not necessarily all referring to the same aspect. Furthermore, the particular features, structures or characteristics may be combined in any suitable manner in one or more aspects.

[0244] As used herein, the singular form of “a”, “an”, and “the” include the plural references unless the context clearly dictates otherwise.

[0245] Any patent application, patent, non-patent publication, or other disclosure material referred to in this specification and / or listed in any Application Data Sheet is incorporated by reference herein, to the extent that the incorporated materials is not inconsistent herewith. As such, and to the extent necessary, the disclosure as explicitly set forth herein supersedes any conflicting material incorporated herein by reference. Any material, or portion thereof, that is said to be incorporated by reference herein, but whichconflicts with existing definitions, statements, or other disclosure material set forth herein will only be incorporated to the extent that no conflict arises between that incorporated material and the existing disclosure material. None is admitted being prior art.

[0246] In summary, numerous benefits have been described which result from employing the concepts described herein. The foregoing description of the one or more forms has been presented for purposes of illustration and description. It is not intended to be exhaustive or limiting to the precise form disclosed. Modifications or variations are possible in light of the above teachings. The one or more forms were chosen and described in order to illustrate principles and practical application to thereby enable one of ordinary skill in the art to utilize the various forms and with various modifications as are suited to the particular use contemplated. It is intended that the claims submitted herewith define the overall scope.

Claims

WHAT IS CLAIMED IS:

1. A computer-implemented method for enabling personalized commerce, the method comprising: receiving, by a service provider system, a request from a commerce application to retrieve product recommendations for a user; retrieving, by the service provider system, a persona token associated with the user from a restricted access database; generating, by a machine learning model hosted on the service provider system, one or more product recommendations based the persona token; and transmitting the product recommendations to the commerce application for display on a user device.

2. The method of claim 1 , wherein generating the product recommendations comprises interpreting contextual signals associated with persona token with a large language model and refining results based on user behaviors associated with persona token.

3. The method of claim 1, comprising generating the persona token using synthetic user data reflective of a user’s cohort behavior to preserve privacy.

4. The method of claim 2, comprising generating a cohort behavior based on a plurality of user data comprising one or more of user demographic data, transaction history, or user behaviors.

5. The method of claim 1 , comprising generating the persona token using one or more of user demographic data, transaction history, or user behaviors, wherein generating comprises privacy-preserving attributes.

6. The method of any one or claims 2-5, wherein user behaviors comprise one or more of browsing history, click-through rate, session duration, previous purchase history, demographic information, user ID, cards used by the user to make online e-commerce purchases, URL of an item, SKU data associated with an item description, item cost, and name of merchant.

7. The method of claim 1, comprising receiving, from the commerce application, a user response to a search prompt generated using the persona token, and refining the product recommendations based on the response.

8. The method of claim 1 , comprising caching product data retrieved from third-party platforms to optimize future discovery phases.

9. The method of claim 1, comprising notifying a partner platform of a persona insight request and attributing the request to a tokenized user session.

10. A method for attributing a purchase event to a digital advertisement interaction, the method comprising: receiving, at a service provider system, an indication of a user interaction with a digital advertisement for a product, the user interaction associated with a persona token identifier; receiving, at the service provider system, transaction data indicative of a purchase of a product by the user from a resource provider; matching the transaction data with the user interaction using the persona token identifier; and generating attribution data for the matched transaction data, the attribution data indicating that the purchase event is associated with the user interaction of the advertisement.

11. The method of claim 10, comprising computing a likelihood score for associating the user interaction with the transaction data based on time of interaction, SKU similarity, and transaction metadata.

12. The method of claim 10, comprising receiving the transaction from a payment network in a form of anonymized purchase event notifications.

13. The method of claim 10, comprising updating a user’s persona token based on the attributed purchase to reflect recent purchase behavior.

14. The method of claim 10, wherein the attribution data comprises merchant name, product category, transaction amount, and timestamp.

15. The method of claim 10, comprising updating, by the service provider system, an advertisement-serving algorithm based on an effectiveness of the attributed purchase event.

16. A system for provisioning and utilizing persona tokens in an Al-powered commerce environment, the system comprising: a memory storing instructions and a processor operable to execute the instructions to: receive a request to generate a persona token for a user, the request comprising user consent and at least one of user demographic data, transaction history, or user behavioral profile; generate a persona token based on the request; store the persona token in association with a persona token identifier in a restricted access database; provision the persona token identifier to one or more commerce applications; and enable use of the persona token to personalize product discovery or checkout experiences for the user in the commerce applications.

17. The system of claim 16, wherein generating the persona token comprises using synthetic user data reflective of a user’s cohort behavior to preserve privacy.

18. The system of claim 16, wherein the user behavioral profile comprises one or more of browsing history, click-through rate, session duration, previous purchase history, demographic information, user ID, cards used by the user to make online e-commerce purchases, URL of an item, SKU data associated with an item description, item cost, and name of merchant.

19. The system of claim 16, wherein the processor is operable to perform cohort analysis across a plurality of persona tokens to identify purchasing trends and improve conversion of product discovery to product purchase.

20. The system of claim 16, wherein the system comprises a federated identity verification module operable to authenticate user identity prior to provisioning the persona token.

Images