Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Detail Action
2. This office action is response to the application filed on . Claims 1-20 are pending in this communication.
Continued Examination Under 37 CFR 1.114
3. 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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 10/10/2025 has been entered.
Response to Amendment
4. This is in response to the amendments filed on 10/10/2025. Claims 1 and 11 have been amended. Claims 1-20 are currently pending and have been considered below.
The 112(b) rejection to the claim 1-20 has been reconsidered and withdrawn.
Response to Arguments
5. Applicant’s arguments filed on 10/10/2025 have been fully considered but they are not persuasive. On the Remarks, Applicant argues that;
Shpurov receives the modeled coefficients or parameters are sent without any restrictions, and are sent directly to the third computing system from the first or second computing system, there is no disclosure that the coefficients or parameters are private to any of the computing systems,
Shpurov does not disclose this element. "writing, by the computer program for the first institution, parameters for the local machine learning model to a distributed ledger in the distributed ledger network as an encrypted private transaction with a trusted entity, ... wherein each of the encrypted private transactions is private to the institution submitting the private transaction and the trusted entity such that only the institution submitting the encrypted private transaction and the trusted entity can access the parameters in the encrypted private transaction."
the proposed combination of Shpurov and Seraj does not disclose all elements of amended claim 1.
The examiner respectfully disagrees.
First, in response to applicant's argument that Shpurov receives the modeled coefficients or parameters are sent without any restrictions, and are sent directly to the third computing system from the first or second computing system, there is no disclosure that the coefficients or parameters are private to any of the computing systems, it is noted that, Shpurov at Para.0074, Para.0070, Para.0093 discloses, “third computing system 302 …. maintain…. policy…to …. encrypted transaction data…. policies may establish a list of financial institution permitted to submit modelling data, and a …. list of financial institution not permitted to submit modelling data”, “third computing system 302 may receive …. modelling data from first computing system 102 …. modelling data … include …. modeled coefficients or parameters “, “each of modelling data … include …. encrypted transaction data…. associated with each of …. computing system” which the examiner interpreted as being the claimed “encrypted private transaction with a trusted entity” because the broadest reasonable interpretation of the claimed “encrypted private transaction with a trusted entity” includes modeling data/encrypted transaction data/ transaction parameters corresponding to first and second computing system, equivalent to the claimed ‘encrypted private transaction’. Because in Shpurov, third computing system 302 maintains policy to encrypted transaction data/ modelling data/ transaction parameters, policies establish a list of financial institution permitted to submit encrypted transaction data/ modelling data/ transaction parameters, which indicates that the modeled coefficients or parameters are sent with restrictions to the third computing system from the first or second computing system [a list of permitted financial institution] and the coefficients or parameters are private to any of the computing systems/permitted financial institution.
Second, in response to applicant's argument that Shpurov does not disclose this element, "writing, by the computer program for the first institution, parameters for the local machine learning model to a distributed ledger in the distributed ledger network as an encrypted private transaction with a trusted entity, ... wherein each of the encrypted private transactions is private to the institution submitting the private transaction and the trusted entity such that only the institution submitting the encrypted private transaction and the trusted entity can access the parameters in the encrypted private transaction", it is noted that, Shpurov at Para.0069, Para.0035, Para.0117 discloses; “first computing system 102…financial institution that submits … modelling data to”, “modelling data …. as an input to a … module … of first computing system 102”, “A computer program…. referred to … a module, a software module…. written in any form of programming language”, which the examiner interpreted as being the claimed “writing, by the computer program for the first institution… " because the broadest reasonable interpretation of the claimed "writing, by the computer program for the first institution….” includes modelling data written in any form of programming language, which is an input to a module/computer program of first computing system 102. Also, Shpurov at Para.0070, Para.0059 discloses; “modelling data …. include …. parameters … specifying a first …. model privately trained by first computing system 102”, “ledger block of a distributed ledger, which may be accessible to participants in a distributed-ledger network, such as first computing system 102”, which the examiner interpreted as being the claimed “writing… parameters for the local machine learning model to a distributed ledger in the distributed ledger network" because the broadest reasonable interpretation of the claimed “writing …. parameters for the local machine learning model to a distributed ledger in the distributed ledger network” include modelling data including parameters written in any form of programming language in the ledger block of a distributed ledger, which is accessible to participants in a distributed-ledger network, such as first computing system 102 of Shpurov. Moreover, Shpurov at Para.0070, Para.0069, Para.0074, Para.0093 discloses “third computing system 302 …receive …. modelling data …. from first computing system 102 ….”, “centralized authority, such as third computing system 302…., the centralized authority may policies that, when applied to …. financial institution …establishes trust between the …. financial institution”, “third computing system 302 …. maintain…. policy…to …. encrypted transaction data…. policies may establish a list of financial institution permitted to submit modelling data, and a …. list of financial institution not permitted to submit modelling data”, “each of modelling data 122… include …. encrypted transaction data…. associated with … first computing system 102 ….”, which the examiner interpreted as being the claimed “an encrypted private transaction with a trusted entity, ... wherein each of the encrypted private transactions is private to the institution submitting the private transaction and the trusted entity such that only the institution submitting the encrypted private transaction and the trusted entity can access the parameters in the encrypted private transaction”, because modeling data/encrypted transaction data/transaction parameters of Shpurov, is equivalent to [claimed ‘encrypted private transaction‘] corresponding to first and second computing system. Third computing system 302 maintains policy to encrypted transaction data/ modelling data, policies establish a list of financial institution permitted to submit modelling data, which is equivalent to the claimed “an encrypted private transaction with a trusted entity, ... wherein each of the encrypted private transactions is private to the institution submitting the private transaction and the trusted entity such that only the institution submitting the encrypted private transaction and the trusted entity can access the parameters in the encrypted private transaction”.
Finally, in response to applicant's argument that the proposed combination of Shpurov and Seraj does not disclose all elements of amended claim 1, it is noted that, Seraj at Para.0042, Para.0036, Para.0017, Para.0060 discloses; “combine the aggregated results … to generate a …prediction”, “combine individual model predictions”, “…. predictions using one or more ML models”, “the final prediction …. an aggregation of the results from the… nodes”, which the examiner interpreted as being the claimed ‘aggregate the parameters for the …. machine learning model and the parameters for the plurality of other …. machine leaning models into an aggregated machine learning model’. Also, Seraj at Para.0061, Para.0011, Para.0060 discloses;” … the ML model … adjusted …”, “aggregating individual model update “, “…final prediction … an aggregation of the results ….”, which is equivalent to the claimed “updating… the aggregated machine learning model”. In addition, it is noted that, Shpurov in the above-mentioned citations disclose the claimed ‘encrypted private transactions’, ‘parameters for a plurality of other local machine learning models for other institutions of the plurality of institutions. Thus, the proposed combination of Shpurov and Seraj disclose all elements of amended claim 1.
It is clearly indicated that Shpurov and Seraj disclose all elements of amended claim 1. Thus, in view of the above, the examiner maintains that Shpurov and Seraj disclose all elements of claim 1, and the rejection of such is sustained below.
Claim Rejections - 35 USC § 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, 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.
6. Claims 1-2, 5-6, 11-12, 15-17 are rejected under AIA 35 U.S.C. 103 as being unpatentable over Shpurov et al. (US 20200244435 A1) in view of Seraj et al. (US 20210409220 A1)
Regarding Claim 1:
Shpurov discloses:
a. A method for privacy preserving machine learning model sharing, (Para.0006, Para.0042; “The method …. includes …. data associated with a first …. model”, “preserving … access … models privately trained …. by …. computing systems”) comprising:
b. receiving, by a computer program for a first institution (Para.0041; “first computing system 102 …receive the …. transaction data….”) of a plurality of institutions in a distributed ledger network, (Para.0059; “a distributed ledger … accessible to participants in a distributed-ledger network, such as first computing system 102, second computing system 202…”) transaction data for a transaction; (Para.0041; “…. transaction data”)
c. training, by the computer program for the first institution, a local machine learning model using the transaction data; (Para.0070; “first … model privately trained by first computing system 102, e.g., based on…. transaction data”)
d. writing, by the computer program for the first institution, (Para.0069, Para.0035, Para.0117; “first computing system 102…financial institution that submits … modelling data to” first computing system 102 is construed as first institution, “modelling data 118 as an input to a … module … of first computing system 102”, “A computer program …. referred to … a module, a software module…. can be written in any form of programming language”) parameters for the local machine learning model to a distributed ledger in the distributed ledger network (Para.0070, Para.0059; “modelling data …. include …. parameters … specifying a first …. model privately trained by first computing system 102”, “ledger block of a distributed ledger, which may be accessible to participants in a distributed-ledger network, such as first computing system 102”) as an encrypted private transaction with a trusted entity, (Para.0070, Para.0069, Para.0074; “third computing system 302 …receive …. modelling data …. from first computing system 102 ….”, “centralized authority, such as third computing system 302…., the centralized authority may policies that, when applied to …. financial institution …establishes trust between the …. financial institution” centralized authority, such as third computing system is construed as trusted entity, “third computing system 302 …. maintain…. policy…to …. encrypted transaction data…. policies may establish a list of financial institution permitted to submit modelling data, and a …. list of financial institution not permitted to submit modelling data”) wherein the trusted entity is configured to receive the parameters for the local machine learning model (Para.0070, Para.0021; “third computing system 302 …receive …. parameters …specifying a first …. model …. trained by first computing system 102…”, “third computing system 302 …. associated with…. centralized authority….” first model trained by first computing system 102 is construed as local machine learning mode, third computing system 302 associated with centralized authority is construed as the trusted entity) and parameters for a plurality of other local machine learning models for other institutions of the plurality of institutions from the distributed ledger (Para.0070, Para.0071; “parameters …. specifying a first …. model privately trained by first computing system 102”, “parameters …. specifying …. second …. model privately trained by the …. additional computing systems 200”) that are submitted as encrypted private transactions with the trusted entity, (Para.0070, Para 0031, Para.0073; “third computing system …receive … modelling data from first computing system 102 …within …. model data store”, “first computing system 102…. package the … modelling data… stored in …model data store”, “modelling data …. may be encrypted”) …. wherein each of the encrypted private transactions is private to the institution submitting the private transaction and the trusted entity (Para 0070, Para.0093, Para.0012; “third computing system … receive …. modelling data from first computing system 102…”, “each of modelling data 122… include …. encrypted transaction data…. associated with each of the first …. models …. generated by corresponding … first computing system 102 ….”, “the computing systems associated with one or more these financial institutions”) such that only the institution submitting the encrypted private transaction and the trusted entity can access the parameters in the encrypted private transaction; (Para.0075, Para.0031, Para.0074; “third computing system 302 …. access the stored …. modelling data….”, “first computing system 102 …. package …corresponding …. modelling data….”, “third computing system 302 …. maintain…. policy…to …. encrypted transaction data…. policies may establish a list of financial institution permitted to submit modelling data, and a …. list of financial institution not permitted to submit modelling data” third computing system 302 stores/accesses the modeling data/encrypted transaction data/transaction parameters within trained model data store 310, the modelling data is equivalent to [claimed ‘encrypted private transaction‘] corresponding to first and second computing system, because third computing system 302 maintains policy to encrypted transaction data/modelling data, policies establish a list of financial institution permitted to submit modelling data, which is construed as only the institution submitting the encrypted private transaction and the trusted entity can access the parameters in the encrypted private transaction)
e. receiving, by the computer program for the first institution and from the distributed ledger network, (Para.0073, Para.0080; “centralized authority (e.g., third computing system 302) may broadcast …. to first computing system 102”, “first computing system 102…. receive …modelling data … includes … transaction data ….”) the …. parameters for the …. machine learning model; (Para.0080; “… parameters…. corresponding …. of the …. models”)
f. updating, by the computer program for the first institution, the local machine learning model with the …. parameters for the …. machine learning model. (Para.0095, Para.0093; “updated version of the distributed ledger …. corresponding …of the first…. models … corresponding …. of first computing system 102”, “parameters … specifying a corresponding …. first …. model”)
however, Shpurov does not explicitly disclose:
d. …. aggregate the parameters for the …. machine learning model and the parameters for the plurality of other …. machine leaning models into an aggregated machine learning model, and to submit aggregated parameters for the aggregated machine learning model to the distributed ledger network as one or more transactions…. [Shpurov discloses parameters for the local machine learning model…., but Shpurov does not disclose aggregate the parameters for the …. machine learning model and the parameters for the plurality of other …. machine leaning models into an aggregated machine learning model, and to submit aggregated parameters for the aggregated machine learning model to the distributed ledger network as one or more transactions]
e. receiving…. the aggregated parameters for the aggregated machine learning model;
f. updating…. the aggregated machine learning model.
In an analogous reference Seraj discloses:
d. …. aggregate the parameters for the …. machine learning model (Para.0042, Para.0036, Para.0010; “combine the aggregated results … to generate a …prediction”, “combine individual model predictions”, “…. an ML model…. trained …. accepting …. the corresponding predictions…. predictions can be …. set of data ...”) and the parameters for the plurality of other …. machine leaning models (Para.0017, Para.0031; “…. predictions using one or more ML models”, “one or more model…. create …. with their own data”) into an aggregated machine learning model, (Para.0060; “the final prediction …. an aggregation of the results from the computational nodes”) and to submit aggregated parameters for the aggregated machine learning model to the distributed ledger network (Para.0066, Para.0067, Para.0050, Para.0028; “multiple models …. combined into a single prediction”, “single prediction … provided to …”, “… provide … to blockchain devices...”, “Blockchain devices … managed by … distributed ledger”) as one or more transactions, (Para.0027; “transaction data existed … the block…”) ….
e. receiving, … the aggregated parameters for the aggregated machine learning model; (Para.0042, Para.0017;” … combine the aggregated results … to generate a final prediction”, “…. predictions using one or more ML models”) and
f. updating… the aggregated machine learning model. (Para.0061, Para.0011, Para.0060; ” … the ML model … adjusted …”, “aggregating individual model update“, “…final prediction … an aggregation of the results ….”)
Before the effective filing date of the claimed invention, it would have been obvious to one with ordinary skill in the art to modify Shpurov’s method of encrypting transaction data comprises confidential transaction data by enhancing Shpurov’s method to include Seraj’s method to implement predictions using one or more ML models.
The motivation: privacy protection is achieved by aggregating model parameters instead of raw training data, aggregated machine learning model is capable to obtain better predictive performance that is difficult to obtain from any of the machine learning model alone. Also, updating an aggregated machine learning model allows for improved accuracy and relevance by incorporating new data, leading to better predictions as the model adapts to changing patterns and trends over time, ultimately enabling more informed decision-making based on the latest information available.
With respect to independent claim 11, a corresponding reasoning was given earlier in this section with respect to claim 1; therefore, claim 11 is rejected, for similar reasons, under the grounds as set forth for claim 1.
Regarding Claim 2:
Shpurov in view of Seraj discloses:
g. The method of claim 1, wherein the local machine learning
model is trained to detect transaction anomalies. (Shpurov, Para.0098; “…. the first…. privately trained…. models to portions of encrypted transaction data 220, and to generate …. output data …. indicates a likelihood that the particular transaction represents fraudulent activity”)
With respect to dependent claim 12, a corresponding reasoning was given earlier in this section with respect to claim 2; therefore, claim 12 is rejected, for similar reasons, under the grounds as set forth for claim 2.
Regarding Claim 5:
Shpurov discloses:
j. The method of claim 1, wherein the …. Parameters for the …. machine learning model are received in a private transaction. (Para.0074, Para.0070; “third computing system 302 …. maintain…. policy…to …. transaction data…. policies may establish a list of financial institution permitted to submit modelling data”, “modelling data …. include …. parameters … specifying a first …. model privately trained by first computing system 102”)
however, Shpurov does not explicitly disclose:
j. …the aggregated parameters for the aggregated machine learning model are received in a …. transaction.
In an analogous reference Seraj discloses:
j. …the aggregated parameters for the aggregated machine learning model (Para.0036, Para.0013; “combine individual model predictions”, “…. aggregating individual model ... generate a new model… controlled by a single central entity”) are received in a …. transaction. (Para.0032; “the entities are … banks as individual modelers. Each entity …. receive…. transaction history”)
Before the effective filing date of the claimed invention, it would have been obvious to one with ordinary skill in the art to modify Shpurov’s method of encrypting transaction data comprises confidential transaction data by enhancing Shpurov’s method to include Seraj’s method to implement predictions using one or more ML models.
The motivation: is the same as claim 1.
Regarding Claim 6:
Shpurov in view of Seraj discloses:
k. The method of claim 1, wherein the aggregated parameters for the aggregated machine learning model (Seraj, Para.0066; “multiple models … combined into a single prediction …”) comprise updates to the local machine learning model. (Para.0060, Para.0011; “…an aggregation of the results ….”, “aggregating individual model updates”)
With respect to dependent claim 17, a corresponding reasoning was given earlier in this section with respect to claim 6; therefore, claim 17 is rejected, for similar reasons, under the grounds as set forth for claim 6.
Regarding Claim 15:
Shpurov discloses:
o. The method of claim 1, wherein… parameters … are submitted to the distributed ledger network as a plurality of private transactions. (Para.0074, Para.0070; “third computing system 302 …. maintain…. policy…to …. transaction data…. policies may establish a list of financial institution permitted to submit modelling data”, “modelling data …. include …. parameters … specifying a first …. model privately trained by first computing system 102”)
however, Shpurov does not explicitly disclose:
o. the aggregated parameters for the aggregated machine learning model are submitted to the distributed ledger network …
In an analogous reference Seraj discloses:
o. the aggregated parameters for the aggregated machine learning model are submitted to the distributed ledger network … (disclosed in claim 1)
Before the effective filing date of the claimed invention, it would have been obvious to one with ordinary skill in the art to modify Shpurov’s method of encrypting transaction data comprises confidential transaction data by enhancing Shpurov’s method to include Seraj’s method to implement predictions using one or more ML models.
The motivation: is the same as claim 1.
Regarding Claim 16:
Shpurov discloses:
p. The method of claim 11, wherein the … parameters for a first institution of the plurality of institutions are different from the …parameters for a second institution of the plurality of institutions. (Para.0020; ”each of first computing system 102 and second computing system 202 … provides financial services to …. customers (e.g., respective ones of a first financial institution and a second financial institution) …. financial services accounts on behalf of corresponding customers …”)
however, Shpurov does not explicitly disclose:
p. …the aggregated parameters for a…. institution of the plurality of institutions ….
In an analogous reference Seraj discloses:
p. …the aggregated parameters for a …. institution of the plurality of institutions … (Para.0013, Para.0031; “aggregating individual model”, “…. Individual model …with their own data”)
Before the effective filing date of the claimed invention, it would have been obvious to one with ordinary skill in the art to modify Shpurov’s method of encrypting transaction data comprises confidential transaction data by enhancing Shpurov’s method to include Seraj’s method to implement predictions using one or more ML models.
The motivation: is the same as claim 1.
Claims 3 and 13 are rejected under AIA 35 U.S.C. 103 as being unpatentable over Shpurov et al. (US 20200244435 A1) in view of Seraj et al. (US 20210409220 A1) and further in view of Munir Mohsin et al. ("DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series", IEEE ACCESS, vol.7, 19 December 2018 (2018-12-19))
Regarding Claim 3:
Shpurov in view of Seraj discloses:
h. The method of claim 1, wherein the… local machine learning model and/or the aggregated machine learning model … (disclosed in claim 1)
however, Shpurov in view of Seraj does not explicitly disclose:
h. …the …. machine learning model comprises a DeepAnT model.
In an analogous reference Munir Mohsin discloses:
h. … the…machine learning model … comprises a DeepAnT model. (Abstract; ”a novel deep learning-based anomaly detection approach (DeepAnT) for time series data”)
Before the effective filing date of the claimed invention, it would have been obvious to one with ordinary skill in the art to modify Shpurov in view of Seraj’s method of encrypting transaction data comprises confidential transaction data by enhancing Shpurov in view of Seraj’s method to include Munir Mohsin’s method for anomaly detection in order to include a DeepAnT model.
The motivation: DeepAnT model can detect a wide range of anomalies, i.e., point anomalies, contextual anomalies, and discords in time series data.
With respect to dependent claim 13, a corresponding reasoning was given earlier in this section with respect to claim 3; therefore, claim 13 is rejected, for similar reasons, under the grounds as set forth for claim 3.
Claims 4 and 14 are rejected under AIA 35 U.S.C. 103 as being unpatentable over Shpurov et al. (US 20200244435 A1) in view of Seraj et al. (US 20210409220 A1) and further in view of Sharad et al. (US 20200285980 A1)
Regarding Claim 4:
Shpurov in view of Seraj discloses:
i. The method of claim 1, wherein …aggregates the parameters into the aggregated machine learning model (disclosed in claim 1) …
however, Shpurov in view of Seraj does not explicitly disclose:
i. … the …. entity aggregates the parameters into the aggregated machine learning model using a secure aggregation protocol.
In an analogous reference Sharad discloses:
i. …entity aggregates the parameters into the aggregated machine learning model …using a secure aggregation protocol. (Para.0019; ”the aggregated group updates are obtained from a locally trained model … all participants … execute a secure aggregation protocol to combine all of their updates … to obtain an aggregated group update”)
Before the effective filing date of the claimed invention, it would have been obvious to one with ordinary skill in the art to modify Shpurov in view of Seraj’s method of encrypting transaction data comprises confidential transaction data by enhancing Shpurov in view of Seraj’s method to include Sharad’s method for performing federated learning in order to include secure aggregation protocol.
The motivation: in a machine learning environment, secure aggregation protocol enables computing the sum of client-side model updates without revealing information about individual client updates.
With respect to dependent claim 14, a corresponding reasoning was given earlier in this section with respect to claim 4; therefore, claim 14 is rejected, for similar reasons, under the grounds as set forth for claim 4.
Claims 7-10,18-19 are rejected under AIA 35 U.S.C. 103 as being unpatentable over Shpurov et al. (US 20200244435 A1) in view of Seraj et al. (US 20210409220 A1) and further in view of Jia et al. (US 20200134628 A1)
Regarding Claim 7:
Shpurov in view of Seraj discloses:
l. The method of claim 1, further comprising:
receiving, by the computer program for the first institution, transaction data for a transaction between the first institution and a second institution; (Shpurov, Para.0073, Para.0012; “modelling data … associated with the centralized authority…. centralized authority …. broadcast …. to first computing system 102, …. and any other computing system that participates in the distributed-ledger network”, “transaction data available to the financial institutions, the computing systems associated with …. these financial institutions”) …
providing, by the computer program for the first institution, metadata for the transaction to the trusted entity (Para.0063, Para.0070, Para.0028, Para.0032; “first computing system 102 …publish…. model … parameters”, “third computing system 302 …. receive all or a portion of modelling data …. from first computing system 102’, “each of the … models …. specified, by a corresponding set of ….. parameters”, “sets …include …. transaction data”) … for the first institution, the second institution, and a pair of the first institution and the second institution using the metadata. (Para.0038, Para.0041; “second computing system …. receive transaction data”, “first computing system ….receive the …. transaction data”)….
however, Shpurov in view of Seraj does not explicitly disclose:
l. … generating, by the computer program for the first institution and using the local machine learning model, an anomaly score for the transaction based on the transaction data;
providing, by the computer program for the first institution, metadata for the transaction …. generates anomaly scores for …. institution ……
In an analogous reference Jia discloses:
l. … generating, by the computer program for the first institution (Para.0039; “…. merchant device 140 can execute… a risk score calculated by the risk model 142”) and using the local machine learning model, an anomaly score for the transaction based on the transaction data; (Para.0039, Para.0028; “merchant control actions…. including a risk score ….”, ”output by a risk model as a risk score…. used to identify fraudulent transactions “risk model is construed as local machine learning model; risk score is construed as anomaly score) and
providing, by the computer program for the first institution, metadata for the transaction (Fig.1 and 3, Para.0053; ”The merchant device 140 … making … decisions …. whether to approve the purchase transaction …” From Fig.1, it is clear that risk model 142 resides within merchant device 140, 140 is construed as first institution and also it is seen that the flow of transaction is provided by the merchant device 140) … generates anomaly scores for the …institution, (Fig.1 and 3, Para.0053; ”the risk model 142 …. deciding, based on … scoring, whether the purchase transaction …. being fraudulent.”) …
Before the effective filing date of the claimed invention, it would have been obvious to one with ordinary skill in the art to modify Shpurov in view of Seraj’s method of encrypting transaction data comprises confidential transaction data by enhancing Shpurov in view of Seraj’s method to include Jia’s method of training machine learning models with the plurality of integrated control action models in order to include anomaly score to detect transaction anomalies.
The motivation: An "anomaly score" in the context of transaction acting as a flag to identify potentially fraudulent or anomalous activity; a higher score signifies a greater likelihood of a transaction being anomalous.
With respect to dependent claim 18, a corresponding reasoning was given earlier in this section with respect to claim 7; therefore, claim 18 is rejected, for similar reasons, under the grounds as set forth for claim 7.
Regarding Claim 8:
Shpurov in view of Seraj and further in view of Jia discloses:
m. The method of claim 7, further comprising: executing, by the computer program for the first institution, an action (Jia, Fig.1 and 3, Para.0053; ”The merchant device 140 …. making ….. action decisions such as whether to approve the purchase transaction” action decision is construed as an action whether to approve/transaction is good or decline/transaction is fraudulent) in response to the anomaly score exceeding a threshold (Jia,Fig.1 and 3, Para.0053; “the risk score is a number between 0 and 1… is indicative … of the purchase transaction … being fraudulent.” when risk score exceeds 1 or the threshold, it is construed that the transaction is fraudulent), wherein the response comprises stopping the transaction. (Jia, Fig.1 and 3, Para.0053; ”if the purchase transaction …. is… fraudulent… reject/decline the purchase transaction ….” reject/decline the purchase transaction is construed as stopping the transaction in response to detect anomaly or when anomaly score exceeds threshold)
Regarding Claim 9:
Shpurov in view of Seraj and further in view of Jia discloses:
n. The method of claim 7, further comprising: receiving, by the computer program for the first institution and from the trusted entity an alert, (Jia, Fig.1, Para.0037; “the issuing …device … declines the purchase transaction …. and passes corresponding transaction results …back to the… merchant device” the issuing device is construed as trusted entity, merchant device is construed as first institution, issuing device sends the transaction results/alert to merchant device by informing that transaction is declined) wherein the trusted entity generates the alert in response to a real-time anomaly score generated by a real-time anomaly detection engine (Jia, Fig.1 and 3, Para.0053; ”based on real-time scoring if the purchase transaction …is… fraudulent, the issuing bank device …reject/decline the purchase transaction”) exceeding a threshold. (Jia, Fig.1 and 3, Para.0053; “the risk score is a number between 0 and 1… is indicative … of the purchase transaction 125 being fraudulent” when risk score exceeds 1 or the threshold, it is construed that the transaction is fraudulent)
With respect to dependent claim 19, a corresponding reasoning was given earlier in this section with respect to claim 9; therefore, claim 19 is rejected, for similar reasons, under the grounds as set forth for claim 9.
Regarding Claim 10:
Shpurov in view of Seraj and further in view of Jia discloses:
o. The method of claim 9, further comprising: executing, by the computer program for the first institution, an action in response to the real-time anomaly score exceeding a threshold, wherein the response comprises stopping the transaction. (Jia, Fig.1 and 3, Para.0053; ”if the purchase transaction … is… fraudulent… reject/decline the purchase transaction” reject/decline the purchase transaction is construed as stopping the transaction in response to detect anomaly or when anomaly score exceeds threshold (cited in claim 9))
Claims 20 is rejected under AIA 35 U.S.C. 103 as being unpatentable over Shpurov et al. (US 20200244435 A1) in view of Seraj et al. (US 20210409220 A1) also in view of Jia et al. (US 20200134628 A1) and further in view of Siddharth Bhatia et al. (MIDAS: Micro Cluster-Based Detector of Anomalies in Edge Streams, The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20))
Regarding Claim 20:
Shpurov in view of Seraj also in view of Jia discloses:
q. The method of claim 18…
however, Shpurov in view of Seraj also in view of Jia does not explicitly disclose:
q. … the real-time anomaly detection engine executes a Micro Cluster-Based Detector of Anomalies in Edge Streams-F algorithm.
In an analogous reference Siddharth Bhatia discloses:
q. … the real-time anomaly detection engine (Page:3247, under the section’ Scalability’; “MIDAS …allowing real-time anomaly detection”) executes a Microcluster-Based Detector of Anomalies in Edge Streams-F algorithm. (Page:3247, under the section ‘Introduction’; “MIDAS, which detects micro cluster anomalies, or suddenly arriving groups of suspiciously similar edges, in edge streams”)
Before the effective filing date of the claimed invention, it would have been obvious to one with ordinary skill in the art to modify Shpurov in view of Seraj also in view of Jia’s method of encrypting transaction data comprises confidential transaction data by enhancing Shpurov in view of Seraj also in view of Jia’s method to include Siddharth Bhatia’s method for detecting micro cluster anomalies in order to include Micro Cluster-Based Detector of Anomalies with Edge Streams-F algorithm.
The motivation: MIDAS/ Micro Cluster-Based Detector of Anomalies detects micro cluster anomalies, or suddenly arriving groups of suspiciously similar edges, in edge streams, using constant time and memory.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SAYEDA SALMA NAHAR whose telephone number is (703)756-4609. The examiner can normally be reached M-F 12:00 PM to 6:00 PM EST.
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, Amir Mehrmanesh can be reached on (571) 270-3351. 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.
/SAYEDA SALMA NAHAR/Examiner, Art Unit 2491
/SYED M AHSAN/Primary Examiner, Art Unit 2491