Detailed Action
Continued Examination Under 37 CFR 1.114
A request for continued examination (RCE) 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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 December 4, 2025 has been entered.
Acknowledgements
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This action is in reply to the RCE filed on December 4, 2025.
Claims 7 and 15 are cancelled.
Claims 1-6, 8-14, and 16 are pending.
Claims 1-6, 8-14, and 16 are examined.
This Office Action is given Paper No. 20260318 for references purposes only.
Information Disclosure Statement
The Information Disclosure Statement filed on January 8, 2026 has been considered. An initialed copy of the Form 1449 is enclosed herewith.
Claim Rejections - 35 USC § 103
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.
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, 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.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-6, 8-14, and 16 are rejected under 35 U.S.C. 103(a) as being unpatentable over Zhang et al. (US 2023/0107703), in view of Abbassi (US 2024/0296208), and further in view of SUN et al, “Deep Coral: Correlation Alignment for Deep Domain Adaptation” (NPL document #1 from IDS filed on September 5, 2023).
Claim 1, 9
Zhang discloses:
receiving, by a receiver of a processing server (network analysis engine, see [0020]), from a source data provider (other computing devices, e.g. merchant, see [0026]), a source dataset (input data sources, see [0025]) including labeled source data (historical application data, see [0021, 0025]) for electronic payment transactions, said labeled source data being associated with a plurality of source features (e.g. account holder information, email addresses, identification, prior time period, see [0025-0026]) and with a source domain (network, see figure 1A, [0021, 0023]);
receiving, by the receiver of the processing server, a target dataset (new application data, see [0021]) including unlabeled blockchain transaction data (unconnected information, see [0034]) associated with a plurality of target features (e.g. email address, shared application profile information, shared device information, see [0033]) and corresponding to a target domain (network, see figure 1A, [0021]);
combining, by a processor of the processing server, at least a subset of the plurality of source features and at least a subset of the plurality of target features into a combined data layer (edges are generated between nodes with a defined degree of overlap or similarity, see [0021]);
wherein the domain adaptation algorithm (machine learning model based fraud detection engine, see [0021]) being configured to align labeled source features associated with the labeled source data with unlabeled target features associated with the unlabeled blockchain transaction data to identify a set of final features (e.g. sharing similar email addresses, sharing similarity in products requested, or other features, see [0021]);
identifying one or more fraudulent cryptographic currency blockchain transactions (determination of fraud, see [0021]) by applying, by the processor of the processing server, the identified set of final features (e.g. sharing similar email addresses, sharing similarity in products requested, or other features, see [0021]) to the target dataset (new application data, see [0021]).
Zhang does not disclose:
From… network;
Wherein… elements;
Training… value.
Abbassi teaches:
from a blockchain node (node, see figure 1) of a blockchain network (blockchain network, see [0018]);
wherein the processing server (apparatus, see [0004]) communicates between the source data provider (initial node, see [0027]), the blockchain network (blockchain network, see [0018]) and a payment network (payment channel, see [0023]) and wherein the blockchain transaction data includes cryptographic transaction elements (encryption, see [0038]);
training, by the processor of the processing server, a deep neural network (neural network, see [0032-0033]) using a domain adaptation algorithm and the combined data layer until a difference between a CORAL loss and a classification loss (compare the different between two errors, see [0092]) is within a predetermined value (threshold, see [0092]).
Zhang discloses receiving a source dataset, receiving a target dataset, combining subsets of data into a combined data layer, identifying a set of final features, and identifying fraudulent transactions. Zhang does not disclose a blockchain network, a processing server between the source data provider, blockchain network, and a payment network, and training a deep neural network until a noticeable loss, but Abbassi does. It would have been obvious to one of ordinary skill in the art at the effective filing date of the invention to combine the systems and methods for automated fraud detection of Zhang with the blockchain network, a processing server between the source data provider, blockchain network, and a payment network, and training a deep neural network until a noticeable loss of Abbassi because 1) a need exists for presenting account data simply and efficiently to avoid wasting resources and provide fraud detection (see Zhang [0005]); and 2) a need exists for probing channel balances that are quick and reliable (see Abbassi [0003-0004]). Having a blockchain network, a processing server between the source data provider, blockchain network, and a payment network, and training a deep neural network until a noticeable loss will assist in probing channel balances.
Zhang in view of Abbassi discloses the limitations above. Zhang in view of Abbassi does not disclose:
CORAL loss.
Sun teaches:
CORAL loss (equation 6, see p 4).
Zhang in view of Abbassi discloses receiving a source dataset, receiving a target dataset, combining subsets of data into a combined data layer, identifying a set of final features, identifying fraudulent transactions, a blockchain network, a processing server between the source data provider, blockchain network, and a payment network, and training a deep neural network until a noticeable loss, Zhang in view of Abbassi does not disclose a CORAL loss, but Sun does. It would have been obvious to one of ordinary skill in the art at the effective filing date of the invention to combine the systems and methods for automated fraud detection of Zhang, in view of Abbassi, with the CORAL loss of Sun because a need exists for minimizing the difference between source and target correlations (see Sun p 1). Using a CORAL loss can help minimize the difference between source and target correlations.
Claims 2, 10
Furthermore, Zhang discloses:
training, by the processor of the processing server, a first autoencoder (machine learning model, see [0021, 0053]) on the plurality of target features to identify the subset of the plurality of target features.
Claims 3, 11
Furthermore, Zhang discloses:
training, by the processor of the processing server, a second autoencoder (machine learning model, see [0021, 0053]) on the plurality of source features to identify the subset of the plurality of source features.
Claims 4, 12
Furthermore, Sun teaches:
the domain adaptation algorithm is Deep CORAL (Deep CORAL, see p 2).
Claims 5, 13
Furthermore, Zhang discloses:
transmitting, by a transmitter of the processing server, the identified set of final features (key attributes, see [0028-0029]) for application to data associated with the target domain.
Claims 6, 14
Furthermore, Zhang discloses:
the source domain is electronic payment transactions (transactions, e-money transfer, see [0030]).
Furthermore, Abbassi teaches:
the target domain is cryptographic currency blockchain transactions (blockchain transactions, see [0018, 0105]).
Claims 8, 16
Furthermore, Zhang discloses:
receiving, by the receiver of the processing server, a new dataset (new application data, see [0028]) associated with the target domain; and
applying, by the processor of the processing server, the identified set of final features (key attributes, see [0028-0029]) to the new dataset to identify one or more fraudulent (fraud, see [0021]) cryptographic currency blockchain transactions.
Furthermore, Abbassi teaches:
blockchain transactions (blockchain transactions, see [0018, 0105]).
Response to Arguments
101 arguments
Applicant argues that the claimed invention addresses a technical problem inherent in blockchain systems (i.e. the lack of labeled fraud data), and provides a concrete, technical solution using domain adaptation and deep neural network training (i.e. how to enable effective classification of unlabeled cryptographic ledger data using a neural network trained on a different labeled domain) (see RCE p 11).
Examiner has withdrawn the 101 rejection.
103 arguments
Applicant argues that the prior art does not disclose 1) a source dataset including labeled source data for electronic payment transactions from a source data provider, and 2) a target dataset including unlabeled blockchain transaction data from a blockchain node.
Please see revised rejection as Examiner presents new grounds of rejection.
Claim Interpretation
Examiner hereby adopts the following definitions under the broadest reasonable interpretation standard. In accordance with In re Morris, 127 F.3d 1048, 1056, 44 USPQ2d 1023, 1029 (Fed. Cir. 1997), Examiner points to these other sources to support her interpretation of the claims.1 Additionally, these definitions are only a guide to claim terminology since claim terms must be interpreted in context of the surrounding claim language. Finally, the following list is not intended to be exhaustive in any way:
configuration “(1) (A) (software) The arrangement of a computer system or component as defined by the number, nature, and interconnections of its constituent parts.” “(C) The physical and logical elements of an information processing system, the manner in which they are organized and connected, or both. Note: May refer to hardware configuration or software configuration.” IEEE 100 The Authoritative Dictionary of IEEE Standards Terms, 7th Edition, IEEE, Inc., New York, NY, Dec. 2000.
processor “(2) (software) A computer program that includes the compiling, assembling, translating, and related functions for a specific programming language, for example, Cobol processor, Fortran processor.” IEEE 100 The Authoritative Dictionary of IEEE Standards Terms, 7th Edition, IEEE, Inc., New York, NY, Dec. 2000.
server “2. On the Internet or other network, a computer or program that responds to commands from a client.” Computer Dictionary, 3rd Edition, Microsoft Press, Redmond, WA, 1997.
Conclusion
Any inquiry of a general nature or relating to the status of this application or concerning this communication or earlier communications from Examiner should be directed to Chrystina Zelaskiewicz whose telephone number is 571-270-3940. Examiner can normally be reached on Monday-Friday, 9:30am-5:00pm. If attempts to reach the examiner by telephone are unsuccessful, the Examiner’s supervisor, Neha Patel can be reached at 571-270-1492.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://portal.uspto.gov/external/portal/pair <http://pair-direct.uspto.gov>. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866.217.9197 (toll-free).
/CHRYSTINA E ZELASKIEWICZ/
Primary Examiner, Art Unit 3699
1 While most definition(s) are cited because these terms are found in the claims, Examiner may have provided additional definition(s) to help interpret words, phrases, or concepts found in the definitions themselves or in the prior art.