DETAILED ACTION
The present application is being examined under the first inventor to file provisions of the AIA . In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
This Office Action is in response Applicant communication filed on 4/16/2026.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 4/16/2026 has been entered.
Claims
Claims 1, 8, 11, 17, and 20 have been amended.
Claims 10 and 19 has been cancelled.
Claims 1-9, 11-18, and 20 are currently pending in the application.
Response to Arguments
103
Applicant’s arguments with respect to claim 1 have been considered but are moot because new references have been added as necessitated by the applicant’s amendments to the claims.
112
The examiner withdraws the previous 112 rejections due to the claim amendments.
Rejections under 35 § U.S.C. 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all
obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-5, 11-14, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over US 20220300976 A1 (“Bhatt”) and US 20210334798 A1 (“Mossoba”).
Per claims 1, 11, and 20, Bhatt discloses:
receiving, by a provider computing system and from a user device, a first request for initiating a first transaction having one or more first parameters (e.g. At 702, the method 700 includes receiving, by a server system 108, payment transaction data associated with a first payment instrument (e.g., payment card 104a) of the user 102. The payment transaction data may include information of a payment transaction performed at a particular merchant. In one embodiment, the payment transaction data may be received in real-time when the payment transaction is being performed by the user 102) (Section [0141] and [0144]);
simulating, by the provider computing system using at least one artificial intelligence (AI) system, one or more transactions separate from the first transaction, wherein each of the one or more simulated transactions are simulated based on at least one of the one or more first parameters of the first transaction included in the request (e.g. Once the GAN model is trained for various combinations of the first payment instrument and one or more second payment instruments, the GAN model is deployed to be utilized in real time, to simulate spending on one of the plurality of payment instruments using spending patterns across other payment instruments of the plurality of payment instruments and determine deviations between the simulated and real spending to find fraudulent payment transactions) (Section [0036], [0049], [0073]-[0075], [0082], [0088], [0142], and [0143]);
identifying, by the provider computing system using the at least one AI system, one or more second parameters of the one or more simulated transactions (e.g. At 706, the method 700 includes predicting, by the server system 108, a simulated univariate payment transaction sequence associated with the first payment instrument such as the payment card 104a based, at least in part, on a first neural network model and the multivariate payment transaction sequence) (Section [0143] and [0144]);
comparing, by the provider computing system using the at least one AI system, the one or more second parameters of the one or more simulated transactions output by the AI system to the one or more first parameters associated with the first transaction included in the request (e.g. At 710, the method 700 includes determining, by the server system 108, that the payment transaction is fraudulent based, at least in part, on a comparison of the simulated univariate payment transaction sequence and the real univariate payment transaction sequence by the second neural network model) (Section [0036], [0144], and [0145]);
determining, by the provider computing system using the at least one AI system, a legitimacy value associated with the first transaction based on the comparison of the one or more second parameters to the one or more first parameters (e.g. Thereafter, the server system is configured to determine that the payment transaction is fraudulent based, at least in part, on a comparison of the simulated univariate payment transaction sequence and the real univariate payment transaction sequence. In particular, the discriminator neural network model is configured to identify a deviation value between the simulated univariate payment transaction sequence and the real univariate payment transaction sequence. The server system is configured to determine the payment transaction being fraudulent when the deviation value is greater than a predetermined threshold value) (Section [0031] and [0032]);
determining, by the provider computing system, a response to the first request based on the legitimacy value associated with the first transaction (e.g. Thereafter, the server system is configured to determine that the payment transaction is fraudulent based, at least in part, on a comparison of the simulated univariate payment transaction sequence and the real univariate payment transaction sequence. In particular, the discriminator neural network model is configured to identify a deviation value between the simulated univariate payment transaction sequence and the real univariate payment transaction sequence. The server system is configured to determine the payment transaction being fraudulent when the deviation value is greater than a predetermined threshold value) (Section [0031] and [0032]).
Although Bhatt discloses simulating transactions similar to a real-time transaction and the comparing parameters from the simulated transactions to parameters of the real-time transaction to determine if the real-time transaction is fraudulent, Bhatt does not specifically disclose:
approving, by the provider computing system in response to the legitimacy value exceeding a predefined legitimacy value, the first request;
processing, by the provider computer system in response to the approval of the first request, the first transaction as indicated by the first request;
transmitting, by the provider computing system to the user device based on the approval of the first request, the response to the first request including an indication that the first transaction is processed.
However Mossoba, in analogous art of using machine learning to validate online payment transactions, discloses:
approving, by the provider computing system, in response to the legitimacy value exceeding a predefined legitimacy value, the first request (e.g. As another example, if the machine learning system were to predict a value of “approve” for the target variable of “decision,” then the machine learning system may provide a different recommendation (e.g., a merchant should approve an online transaction) and/or may perform or cause performance of a different automated action (e.g., generating data indicating approval of the online transaction). In some implementations, the recommendation and/or the automated action may be based on the target variable value having a particular label (e.g., classification, categorization, and/or the like), may be based on whether the target variable value satisfies one or more threshold (e.g., whether the target variable value is greater than a threshold, is less than a threshold, is equal to a threshold, falls within a range of threshold values, and/or the like)) (Section [0028] and [0051);
processing, by the provider computing system in response to the approval of the first request, the first transaction as indicated by the first request (e.g. the processing platform may process that transaction card number, with a fraud model, to determine whether to approve or deny the online transaction. For example, the processing platform may use a fraud model, such as one similar to that described in FIG. 1C, to determine whether to approve or deny the transaction. In some implementations, the processing platform identifies a previous determination that the network address was valid when determining whether to approve or deny the online transaction) (Section [0028] and [0029]);
transmitting, by the provider computing system to the user device based on the approval of the first request, the response to the first request including an indication that the first transaction is processed (e.g. the processing platform may provide, to the client device and/or the merchant server device, data indicating that the online transaction is approved. The merchant server device may perform one or more actions based on determining that the online transaction is approved. For example, the merchant server device may provide notification, to the client device, that the online transaction is approved. The client device may display the notification, indicating that the online transaction has been completed successfully) (Section [0028] and [0029]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the machine learning fraud detection system/process of Bhatt to only approve and process the transaction when the risk score or approval score is above or below a certain threshold, as taught by Mossoba, in order to achieve the predictable result of increasing the security of the system by only allowing transactions to process when a certain level or certainty is achieved.
Per claims 2 and 12, Bhatt/Mossoba discloses all the limitations of claims 1 and 11 above. Bhatt further discloses:
wherein the at least one AI system comprises a generative AI model (e.g. The server system is configured to train one or more generative adversarial network (GAN) models for predicting spending patterns of a payment instrument using spending patterns of other one or more payment instruments associated with a user. A first neural network model and a second neural network model are incorporated in the GAN model. The first neural network model is a generator neural network model and the second neural network model is a discriminator neural network model) (Section [0028]).
Per claims 3 and 13, Bhatt/Mossoba discloses all the limitations of claims 2 and 12 above. Bhatt further discloses:
wherein the provider computing system is further configured to store information associated with the first request to serve as training data for the generative AI model (e.g. At the operation 502, the server system 200 accesses payment transaction data of a plurality of payment instruments (e.g., payment accounts A1, A2, A3) associated with the user 102 from a transaction database 116. The payment transaction data includes, but is not limited to, transaction level behaviors of past payment transactions made using the plurality of payment instruments (e.g., payment accounts A1, A2, A3) at the various merchants (for example, merchant M1, merchant M2, merchant M3). The past payment transactions are performed within a particular time duration (for example, last one year)) (Section [0033], [0100], [0101], [0114]-[0118], and Figs 5A and 5B).
Per claims 4 and 14, Bhatt/Mossoba disclose all the limitations of claims 1 and 11 above. Bhatt further discloses:
wherein the one or more first parameters comprise at least one of: a transaction amount; one or more parties associated with the first transaction; and a transaction method (e.g. Additionally, the data pre-processing engine 218 is configured to generate a real univariate payment transaction sequence of the first payment instrument (e.g., payment card C1) by aggregating one or more payment transactional features (such as, payment transaction amounts) associated with payment transactions using the first payment instrument (e.g., payment card C1) made at a particular merchant (for example merchant M1)) (Section [0031], [0069], [0141], and [0144]).
Per claim 5, Bhatt/Mossoba disclose all the limitations of claim 4 above. Bhatt further discloses:
wherein the one or more parties associated with the first transaction further comprise at least one of: a sending party; and a receiving party (e.g. Additionally, the data pre-processing engine 218 is configured to generate a real univariate payment transaction sequence of the first payment instrument (e.g., payment card C1) by aggregating one or more payment transactional features (such as, payment transaction amounts) associated with payment transactions using the first payment instrument (e.g., payment card C1) made at a particular merchant (for example merchant M1)) (Section [0031], [0069], [0141], and [0144]).
Claims 6 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Bhatt/Mossoba, as applied to claims 1 and 11 above, in further view of US 20180109386 A1 (“Khan”).
Per claims 6 and 15, although Bhatt/Mossoba discloses receiving a request for a first transaction having one or more first parameters, Bhatt/Mossoba do not specifically disclose:
generating, by the provider computing system, a key regarding the first transaction, wherein the key regarding the first transaction is configured to authenticate the first transaction.
However Khan, in analogous art of transaction authentication, discloses:
generating, by the provider computing system, a key regarding the first transaction, wherein the key regarding the first transaction is configured to authenticate the first transaction (e.g. Among other things and to facilitate such a transaction, the digital signature may be accompanied by the contextual data (e.g., custom user approval text, etc.) and configured to validate the private key by decrypting the contextual data and/or transaction data using a public key associated with the user device and/or application running via the user device) (Section [0093]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the first transaction having one or more first parameters of Bhatt/Mossoba to include the use of a key to authenticate the first transaction, as taught by Khan, in order to achieve the predictable result of increasing the security and privacy of the transactions (See Khan Paragraph [0093]).
Claims 7-9 and 16-18 are rejected under 35 U.S.C. 103 as being unpatentable over Bhatt/Mossoba, as applied to claims 1 and 11 above, in further view of US 20190318358 A1 (“Chamberlain”).
Per claims 7 and 16, although Bhatt/Mossoba discloses receiving a request for a first transaction having one or more first parameters, Bhatt/Mossoba do not specifically disclose:
retrieving, by the provider computing system, contextual information related to the first transaction from at least one data source, wherein the contextual information is used to determine at least one of the one or more first parameters.
However Chamberlain, in analogous art of fraud detection, discloses:
retrieving, by the provider computing system, contextual information related to the first transaction from at least one data source, wherein the contextual information is used to determine at least one of the one or more first parameters (e.g. For example, the AI system is configured to proactively determine risks of beneficiaries using context information, notify in real-time or near real-time the customer of the risks before approving the electronic transactions, and detecting mitigating factors from a customer's mitigation activities using context information. In some arrangements, to achieve benefits over conventional systems having databases, tables, and field definitions that are static, the databases described herein may be data-type agnostic and configured to store different information for different users, transaction types, and the like) (Sections [0014], [0055], and [0056]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the first transaction having one or more first parameters of Bhatt/Mossoba to include the use of contextual information to determine the first parameters, as taught by Chamberlain, in order to achieve the predictable result of increasing the reliability of the fraud detection by lowering the number of false positives.
Per claims 8 and 17, Bhatt/Mossoba/Chamberlain disclose all the limitations of claims 7 and 16 above. Bhatt further discloses:
suggesting one or more of the first parameters associated with the first transaction based on at least one of a transaction history or the contextual information (e.g. he multivariate payment transaction sequence represents past payment transactions using the one or more second payment instruments at the particular merchant over a threshold period of time. The server system is configured to aggregate one or more payment transactional features corresponding to the past payment transactions of the one or more second payment instruments to generate the multivariate payment transaction sequence. The one or more payment transactional features may include an amount of spend, a merchant category code (MCC), merchant risk profile, a frequency of purchase at the particular merchant, and an average amount of purchase at the particular merchant) (Sections [0029] and [0030]).
Per claims 9 and 18, although Bhatt/Mossoba discloses comparing first parameters of a payment transaction to parameters of simulated transactions, Bhatt/Mossoba do not specifically disclose:
wherein comparing the one or more second parameters to the one or more first parameters further comprises: receiving an accepted range associated with the one or more first parameters;
determining whether the one or more second parameters fall within the accepted range.
However Chamberlain in analogous art of fraud detection, discloses:
wherein comparing the one or more second parameters to the one or more first parameters further comprises: receiving an accepted range associated with the one or more first parameters (e.g. In some arrangements, the risk is detected if an amount of the transaction exceeds a user or automatically defined threshold) (Section [0040] and [0055]);
determining whether the one or more second parameters fall within the accepted range (e.g. In some arrangements, the risk is detected if an amount of the transaction exceeds a user or automatically defined threshold) (Sections [0040] and [0055]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the deviation value threshold of Bhatt/Mossoba to include a range of values, as taught by Chamberlain, in order to achieve the predictable result of increasing the accuracy of the fraud detection by ensuring that the similarity threshold is between a given range.
Conclusion
The following prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
US Publication Number 20220101192 A1 to Patel teaches a system and method to determine transaction fraud based on input feature vectors and input sequence vectors.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TIMOTHY P SAX whose telephone number is (571) 272-2935. The examiner can normally be reached on M-F 8-4:30.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Patrick McAtee can be reached at (571) 272-7575. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/TS/
Examiner, Art Unit 3698
/PATRICK MCATEE/Supervisory Patent Examiner, Art Unit 3698
Prosecution Insights