DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 5 Nov 2025 has been entered.
The following is a non-final office action in response to the amendment filed 5 Nov 2025.
The application has a related PCT/US22/51577, filed 12/01/2022.
Applicant’s amendments to Claim 1, 8 and 15 have been received and are acknowledged.
Claims 1-20 have been examined and are pending.
Response to Arguments
Applicant's arguments filed 5 Nov 2025 have been fully considered but they are not persuasive.
With regard to the rejections under 35 USC 112 (b), Examiner withdraws the rejections in view of Applicant’s response.
With regard to the rejections under 35 USC 101. Applicant argues: (1) Referencing Claim 3 of Example 47, Applicant argues that the instant recited claims integrate the judicial exception into a practical application. Applicant further asserts that the recited claims provide “….particular method of deduplicating duplicate accounts that goes beyond mere data deletion to implement a comprehensive technological control system…describes the following technical problem: "If account data becomes duplicated and financial balances are not correct, underwriting procedures may be incorrect. …become overexposed and overextend a credit limit to an entity." See Specification, 11. The claims seek to improve current technology by implementing a coordinated technological response that extends beyond simple data cleanup. … provides "intelligent and automated deduplication of data in computing systems and database storages, …more up-to-date and accurate data for data processing systems. …improved performance of computing systems, reduces data storages of duplicate data, and provides faster and automated data deduplication." See Specification, 18. …The amended claims incorporate tangible technological improvements that go beyond data manipulation…dynamic adjust of account restrictions serves as a technological control mechanism…represents technological improvements computing systems, not passive data management… ” Further the newly amended claim language is representative of a practical application of the exception (Applicant’s response, 12-14)
. (2) Referencing Example 48, Claims 2 and 3, Applicant further asserts that the “final limitation’ is integrated into “a practical application “ and “provides a technical improve to challenges in distributed financial computing systems.. (Applicant’s response, 14).
Examiner respectfully disagrees. As noted below and previously, the instant recited claims do not overcome the rejections under 35 USC 101. Applicant’s own arguments state that the recited claims utilize the recited technology (i.e. machine learning model engines) which is recited a generic/ high level to “apply it” / improve an abstract idea (i.e. deduplication) . ( See MPEP 2106.05 (d) and (f)) Further, as recited, the claims recite technology as generic computing elements which are recited at a high level. As such the claims are not ‘significantly more’ than the abstract idea. Use of generic computing elements in order to apply an abstract idea for data accuracy is not dispositive of patent eligibility. Multiple imputation is a known statistical method for finding missing data. Using a data processing technique (i.e. multiple imputation strategies) to process data using machine learning/ machine learning algorithms recited at a high level of generality is at most an improvement to an abstract idea. This is not an improvement to technology. Contrary to Applicant’s assertion, the newly amended claim language addresses a business challenge and is at most an improvement to the abstract idea, not a technological improvement. An improvement to the abstract idea is still an abstract idea.(Applicant’s Response, 1, 2) Applicant’s arguments are not persuasive.
With regard to the rejections under 35 USC 103, Applicant argues that the prior art of Dirac as cited fails to disclose “…discovering collisions between accounts involved in financial transactions …” and “multiple imputation strategies” and that the Dirac model is not used to “ check for collisions” rather alternate representation 7030 is used. (Applicant’s response, 15). Applicant further asserts that independent claims 8 and 15 and claims dependent on the independent claims overcome the prior art for the same reason as stated for independent claim 1.
Examiner respectfully disagree. Applicant is arguing the claim language more narrowly than what has been recited or disclosed. All terms must be interpreted using broadest reasonable interpretation. For example, arguably Dirac 7030 ‘corresponds’ to a training model. Applicant’s arguments are not commensurate with the scope of the claims. As such, Applicant’s arguments are not persuasive.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-20 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Claims 1, 8 and 15 include the limitation of: “
….and dynamically adjusting an account restriction associated with the second account.
However, the specification provides no support for “….
… and dynamically adjusting an account restriction associated with the second account. …;
Applicant is requested to provide reference from the original disclosure to support the above recitations. Claims dependent on rejected independent claims are rejected by virtue of their dependency on a rejected independent claim.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter.
When considering subject matter eligibility under 35 U.S.C. 101, (1) it must be determined whether the claim is directed to one of the four statutory categories of invention, i.e., process, machine, manufacture, or composition of matter. If the claim does fall within one of the statutory categories, (2a) it must then be determined whether the claim is directed to a judicial exception (i.e., law of nature, natural phenomenon, and abstract idea), and if so (2b), it must additionally be determined whether the claim is a patent-eligible application of the exception. If an abstract idea is present in the claim, any element or combination of elements in the claim must be sufficient to ensure that the claim amounts to significantly more than the abstract idea itself. Examples of abstract ideas include fundamental economic practices; certain methods of organizing human activities; an idea itself; and mathematical relationships/formulas. Alice Corporation Pty. Ltd. v. CLS Bank International, et al., 573 U.S. ____ (2014).
The claimed invention is directed to a judicial exception (i.e. a law of nature, a natural phenomenon, or an abstract idea) without significantly more. In the instant case, the claim(s) as a whole, considering all claim elements both individually and in combination, do not amount to significantly more than an abstract idea.
(1) In the instant case, the claims are directed towards a method, non-transitory computer readable medium, and the system of deduplication of accounts using account data collision. In the instant case, Claims 8-14 are directed to a process. Claims 1-7 are directed to a system. Claims 16-20 are directed to a non-transitory computer readable medium.
(2a) Prong 1: Deduplication of accounts using account data collision is categorized in/akin to the abstract idea subject matter grouping of: mental processing and methods of organizing human activity [organizing human activity (commercial or legal interactions (including agreements in the form of contracts; legal obligations; advertising, marketing or sales activities or behaviors; business relations)]. As such, the claims include an abstract idea.
The specific limitations of the invention are (a) identified to encompass the abstract idea include:
1. (Currently Amended) A …comprising:
a …; and
… comprising:
…. account data for a plurality of accounts with a service provider through a network node configured to acquire account data in real time, wherein the account data comprises features that are related to, but independent of, transactions processed using the plurality of accounts, and wherein a format of the account data received for a first one of the plurality of accounts is different than a format of the account data received for a second one of the plurality of accounts;
reformatting the account data received for the plurality of accounts into a standard format;
extracting the features from the account data received for the plurality of accounts;
computing a hash value for each of the features, so as to produce hash values ;
processing the hash values using an account deduplication machine learning (ML) model-based … associated with the service provider;
identifying, using a multiple imputation strategy of the account deduplication ML model-based …, a collision between the hash values, wherein using the multiple imputation strategy comprises:
inputting the hash values into a plurality of machine learning models, machine learning model which corresponds to a different imputation strategy and is trained to check for collisions between the hash values, and
obtaining, from each of the plurality of machine learning models, an indication of collisions, if any, between the hash values;
determining, based on the collision,account is identical to a second hash value of a second one of the features that is associated with a second account;
determining that the account data collision indicates that the first and second accounts are a same account;
deduplicating, with the service provider, the first and second accounts based on determining that the
based on the deduplicating, deleting data corresponding toand dynamically adjusting an account restriction associated with the second account
8. (Currently Amended) A method comprising:
…account data for a plurality of accounts with a service provider, wherein the account data comprises features that are related to transactions processed using the plurality of accounts;
extracting
computing a hash value for each of the features, so as to produce hash values
processing the hash values using an account deduplication machine learning (ML) model-based … associated with the service provider;
identifying, using a multiple imputation strategy of the account deduplication ML model- based …, a collision between the hash values
determining, based on the collision account data collision between a first one of the plurality of accounts, wherein the account data collision are associated with the collision and is representative of a scenario in which a first hash value of a first one of the features that is associated with the first account is identical to a second hash value of a second one of the features that is associated with the second account;
determining that the account data collision indicates that the first and second accounts are a same account;
deduplicating, with the service provider, the first and second accounts based on determining that the
based on the deduplicating, deleting data corresponding toand dynamically adjusting an account restriction associated with the second account
15. (Currently Amended) A … instructions executable to cause a machine to perform operations comprising:
… account data for a plurality of accounts with a service provider, wherein the account data comprises features that are related to transactions processed using the plurality of accounts;
extracting the features from the account data;
computing a hash value for each of the features, so as to produce hash values processing the hash values
identifying, using a multiple imputation strategy of the account deduplication ML model- based …, a collision between the hash values
determining, based on the collision an account data collision between a first one of the plurality of accounts, wherein the account data collision is associated with the collision and is representative of a scenario in which a first hash value of a first one of the features that is associated with the first account is identical to a second hash value of a second one of the features that is associated with the second account;
determining that the account data collision indicates that first and second accounts are a same account;
deduplicating, with the service provider, first and second accounts based on determining that the account data collision indicates that the two of the plurality of accounts first and second accounts are the same account; and
based on the deduplicating, deleting data corresponding toand dynamically adjusting an account restriction associated with the second account
As stated above, this abstract idea falls into the (b) subject matter grouping of: methods of organizing human activity .
Prong 2: When considered individually and in combination, the instant claims are do not integrate the exception into a practical application because the steps of reformatting…extracting…computing… processing …inputting…obtaining…identifying…. determining…, determining…, deduplicating… deleting…adjusting….do not apply, rely on, or use the judicial exception in a manner that that imposes a meaningful limitation on the judicial exception (i.e. the abstract idea).
The instant recited claims including additional elements (i.e. receiving….) do not improve the functioning of the computer or improve another technology or technical field nor do they recite meaningful limitations beyond generally linking the use of an abstract idea to a particular technological environment. The limitations merely recite: “apply it” (or an equivalent) or merely include instructions to implement an abstract idea on a computer or merely uses a computer a as tool to perform an abstract idea or merely add insignificant extra-solution activity to the judicial exception or merely uses generic computing elements to perform well known, routine, and conventional functions or generally link the use of the judicial exception to a particular technological environment or field of use (MPEP 2106.05 (d) and (f))
(2b) In the instant case, Claims 8-14 are directed to a process. Claims 1-7 is/are directed to a system. Claims 16-20 are directed to a non-transitory computer readable medium.
Additionally, the claims (independent and dependent) do not include additional elements that individually or in combination are sufficient to amount to significantly more than the judicial exception of abstract idea (i.e. provide an inventive concept). As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of: (non-transitory memory, hardware processors, machine learning model-based engine) merely uses a computer a as tool to perform an abstract idea or merely uses generic computing elements to perform well known, routine, and conventional functions. (MPEP 2106.05 (d) and (f)) (Specification, [12] machine learning models…processing engine and operations…[17] multi-step or level ML engine and system… [23] processors, memories, [0028] transitory and/or non-transitory memory; database; [33] engine [59-62] processors, [64] software )
The dependent claims have also been examined and do not correct the deficiencies of the independent claims.
It is noted that claim (2-7, 9-14, 16-20) introduces the additional elements of ( wherein clause describing a condition prior to the extracting step…of : determining…, accessing…, extracting.., determining… (Claims 2, 9, and 16); defining.. account distance metrics by: computing… utilizing.. (Claims 3, 10, and 17); wherein clauses further describing the clustering operation as applies… algorithm and further defining account distance metrics (Claims 4, 11, and 18); wherein clause further defining the computing the pairwise account similarity …(Claims 5, 12, 19) wherein clauses describing the service provides a credit limit and deduplicating…(Claims 6, 13, and 20) and wherein clause further describing account data (Claim 7 and 14). This element is not a practical application of the judicial exception because The limitations merely recite: “apply it” (or an equivalent) or merely include instructions to implement an abstract idea on a computer or merely uses a computer a as tool to perform an abstract idea or merely add insignificant extra-solution activity to the judicial exception or merely uses generic computing elements to perform well known, routine, and conventional functions or generally link the use of the judicial exception to a particular technological environment or field of use(MPEP 2106.05 (d) and (f)). Further these limitations taken alone or in combination with the abstract do not amount to significantly more than the abstract idea alone because, these elements amount to mere use of a computer a as tool to perform an abstract idea or merely add insignificant extra-solution activity to the judicial exception or merely uses generic computing elements to perform well known, routine, and conventional functions. (MPEP 2106.05 (d) and (f)) (Specification, [12] machine learning models...processing engine and operations…[17] multi-step or level ML engine and system… [23] processors, memories, [0028] transitory and/or non-transitory memory; database; [33] engine [59-62] processors, [64] software )
Therefore, claims 1-20 are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
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 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.
Claims 1, 8, and 15 are rejected under 35 U.S.C. 103 as being unpatentable over by US 10,963,810 B2, Dirac et al hereinafter referred to as Dirac.
Claims 1, 8 and 15
Dirac discloses method, system, and non-transitory computer readable medium comprising: ( See at least Dirac, C118L20-52, Figs 1-75, methods, non-transitory computer readable medium, system, )
receiving account data for a plurality of accounts with a service provider through a network node configured to acquire account data in real time, wherein the account data comprises features that are related to, but independent of, transactions processed using the plurality of accounts, and wherein a format of the account data received for a first one of the plurality of accounts is different than a format of the account data received for a second one of the plurality of accounts; (See at least Dirac, C1L18 financial transaction records…, C8L18-19, real-time data… ; C12L50-55, variety of data types… )
reformatting the account data received for the plurality of accounts into a standard format; (See at least Dirac, Fig. 54… transform variables… not supported… normalize numeric values…)
extracting the features from the account data received for the plurality of accounts; (See at least Dirac, C8L39-45… extracting records from data sources…)
computing a hash value for each of the features, so as to produce hash values ; (See at least Dirac, Fig. 71a and 71b, s; C110L31-58, bloom filter… hash function)
processing the hash values using an account deduplication machine learning (ML) model-based engine associated with the service provider; (See at least Dirac, Fig. 54, 71a and 71b; C77L32-50, Hashmap…. C110L31-C111L30, bloom filter… hash function..Murmur Hash function, Jenkins has function, Fowler-Noll-Vo hash function.. CityHash…)
identifying, using a multiple imputation strategy of the account deduplication ML model-based engine, a collision between the hash values, wherein using the multiple imputation strategy (See at least Dirac, Fig. 54, 71a and 71b; C77L32-50, Hashmap…. C110L17-30, identifying possible duplicates…C110L31-C111L30, bloom filter… hash function..Murmur Hash function, Jenkins has function, Fowler-Noll-Vo hash function.. CityHash…)comprises:
inputting the hash values into a plurality of machine learning models, wherein each machine learning model corresponds to a different imputation strategy and is trained to check for collisions between the hash values, and (See at least Dirac, Fig. 54, 71a and 71b; C16L57-67 fill missing values….C77L32-50, Hashmap…. C110L17-30, identifying possible duplicates…duplicate detector….C110L31-C111L30, bloom filter… hash function..Murmur Hash function, Jenkins has function, Fowler-Noll-Vo hash function.. CityHash…)
determining, based on the collision, (See at least Dirac, Fig. 54, 71a and 71b; C77L32-50, Hashmap…. C110L17-30, identifying possible duplicates…duplicate detector…identifying possible duplicates within a given data set… .C110L31-C111L30, bloom filter… hash function.. detect duplicates….Murmur Hash function, Jenkins has function, Fowler-Noll-Vo hash function.. CityHash…)
determining that the account data collision indicates that the first and second accounts are a same account; (See at least Dirac, C113L59-C114L8, duplicate detector…same data…)
deduplicating, with the service provider, the first and second accounts based on determining that the(See at least Dirac, C113L59-C114L8, duplicate detector…same data…)
based on the deduplicating, deleting data corresponding toand dynamically adjusting an account restriction associated with the second account. ( See at least Dirac, C109L36-67, MLS…duplicates may be removed or deleted…particular responsive action… Claim 5 detect duplicate… responses…Claim 24 detect duplicate…notification… .)
Dirac does not directly disclose the following:
obtaining, from each of the plurality of machine learning models, and an indication of collisions, if any, between the hash values;
However as noted above Dirac does teach the use of multiple/various hash functions to be used in the detection of duplicates.
As such, in view of the interpretation provided above (See rejections under 35 USC 112), it would be obvious to one of ordinary skill in the art before the effective filing to use multiple/various hash functions in the detection and deletion of duplicates.
Claims 2, 3, 6, 7, 9, 10, 13, 14, 16, 17 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over US 10,963,810 B2, Dirac et al hereinafter referred to as Dirac further in view of US 9697248 B1, Ahire hereinafter referred to as Ahire
Claims 2, 9, and 16
Dirac and Ahire disclose the invention as claimed above in Claims 1, 8 and 15.
Dirac does not directly disclose the following; however, Ahire teaches:
wherein prior to extracting the features, the method further comprises:
determining, based on the account data, that the account deduplication ML model- based engine requires transaction data for the transactions with the account data for the deduplicating; ( See at least Ahire, Fig. 1, 4, and 10; C6L38-C7L62, merging of data, including de-duplication of data; identify set of categories or sub-populations in which new observation below… training data… C8L4-21 de-duplication)
accessing the transaction data for the transactions processed using the plurality of accounts; ( See at least Ahire, Fig. 1, 4, and 10; C8L4-21, a set of credit raw bureau files)
extracting transaction feature data from the transaction data; and ( See at least Ahire, Fig. 1, 4, and 10; C8L4-21, extracted for each pair of trade lines)
determining, based on one or more account distance metrics between the first and second accounts and the account deduplication ML model-based engine, one or more transaction data collisions of the transaction feature data, wherein determining the account data collision is further based on the one or more transaction data collisions. ( See at least Ahire, Fig. 1, 4, and 10; C6L38-C7L62 clustering… distance…match or non-match)
The Supreme Court has supported in KSR International Co. Teleflex Inc. (KSR), 550US___, 82 USPQ2d 1385 (2007), that merely applying a known technique to a known method, yield predictable results, render the claimed invention obvious over such combination. In the instant case, Dirac discloses a method and system of duplicate detection using machine learning including a deletion/removal of duplicates feature. Ahire also discloses a system, CRM and method of using machine learning to deduplicate data. One of ordinary skill in the art would clearly recognize that this combination would lead to a predictable result (i.e. system, CRM and method of using machine learning to deduplicate data including deleting duplicate data). As such the claimed invention is obvious over Dirac /Ahire.
Claims 3, 10 and 17
Dirac and Ahire disclose the invention as claimed above in Claims 2, 9 and 16.
Dirac does not directly disclose the following; however, Ahire teaches:
defining the one or more account distance metrics by:
computing at least one pairwise account similarity of the transaction feature data using an affinity matrix based at least on the features and the transaction feature data; and (See at least Ahire, C7L15-41, form [(x1y1),…(xN, yN)] …feature vector of the with examples and is its label or class…)
utilizing a clustering operation of the account deduplication ML model- based engine with a similarity threshold to identify the first and second accounts. (See at least Ahire, C7, L8-11, clustering…involves the grouping data into categories based on a measure of inherent similarity or distance)
Claims 6, 13 and 20
Dirac and Ahire disclose the invention as claimed above in Claims 1, 8 and 16.
Dirac does not directly disclose the following; however, Ahire teaches:
wherein the service provider extends a credit limit to the two of the first and second accounts, and.(See at least Ahire, C3L26-30, service providers use credit information for account management…in deciding whether to increase the amount of a line of credit…)
wherein the deduplicating comprises at least one of deleting the first account or lowering the credit limit extended to the first and second accounts. (See at least Ahire, Fig. 10, s1060, recording… indication whether the at least two trade lines are duplicates and when the at two trade lines are duplicates, removing at least one the at least two trade lines…)
The Supreme Court has supported in KSR International Co. Teleflex Inc. (KSR), 550US___, 82 USPQ2d 1385 (2007), that merely applying a known technique to a known method, yield predictable results, render the claimed invention obvious over such combination. In the instant case, Dirac discloses a method and system of duplicate detection using machine learning including a deletion/removal of duplicates feature. Ahire also discloses a system, CRM and method of using machine learning to deduplicate data. One of ordinary skill in the art would clearly recognize that this combination would lead to a predictable result (i.e. system, CRM and method of using machine learning to deduplicate data including deleting duplicate data). As such the claimed invention is obvious over Dirac /Ahire.
Claims 7 and 14
Dirac and Ahire disclose the invention as claimed above in Claims 1 and 8.
Dirac does not directly disclose the following; however, Ahire teaches:
wherein the account data comprises at least one of account identifier data, account name data, or account address data, and (See at least Ahire, C2L1 accounts; C2L5 five major component so of credit report...first component account…name, address…Claim 15, attribute include one or more of a date of an account opening, a data repository Source, a high credit amount, a lost or stolen indicator, a bureau identity, a subscriber information, a balance, a payment amount, and a credit limit.)
wherein the account data is obtained from at least one of extracted optical character recognition (OCR) data from an account statement, digitally uploaded account statements, or linked account providers. ( See at least Ahire, Fig. 1, 2 identify an appropriate set of… reports…Fig. 4, and Fig. 1010 industry reports from multiple industry sources; C2L1 accounts; C2L5 five major component so of credit report...second component account…C3L26-32; C3L33-52, credit report… account.. C4L56-67, receiving… industry reports from multiple industry sources…)
The Supreme Court has supported in KSR International Co. Teleflex Inc. (KSR), 550US___, 82 USPQ2d 1385 (2007), that merely applying a known technique to a known method, yield predictable results, render the claimed invention obvious over such combination. In the instant case, Dirac discloses a method and system of duplicate detection using machine learning including a deletion/removal of duplicates feature. Ahire also discloses a system, CRM and method of using machine learning to deduplicate data. One of ordinary skill in the art would clearly recognize that this combination would lead to a predictable result (i.e. system, CRM and method of using machine learning to deduplicate data including deleting duplicate data). As such the claimed invention is obvious over Dirac /Ahire.
Claims 4, 5, 11, 12, 18 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Dirac further in view of Ahire further in view of US 9,753,964 Bl, Marshall et al. hereinafter referred to as Marshall.
Claims 4, 11, and 18
Dirac and Ahire disclose the invention as claimed above in Claims 3, 10 and 18.
Ahire further discloses the techniques of clustering. (See at least Ahire, C7, L8-11, clustering…involves the grouping data into categories based on a measure of inherent similarity or distance)
Dirac and Ahire do not directly disclose the following; however, Marshall teaches:
wherein the clustering operation applies an agglomerative clustering algorithm, and (See at least Marshall, C26L59-61, hierarchical… clusters agglomerate becoming sequentially bigger and fewer…)
wherein the one or more account distance metrics utilize at least one of a Jaccard similarity, a Sorensen-Dice coefficient, or an overlap coefficient. (See at least Marshall, C6L62-C7L10, overlap similarity measures include Jaccard similarity; C16, 24-32, similarity measure may be at least one of Jaccard similarity, Levenshtein similarity, a Szymkiewicz-Simpson overlap coefficient, mutual similarity, a Sorensen-Dice coefficient, or a Tversky similarity index.)
Furthermore, the Supreme Court has supported in KSR International Co. Teleflex Inc. (KSR), 550US___, 82 USPQ2d 1385 (2007), that merely applying a known technique to a known method, yield predictable results, render the claimed invention obvious over such combination. In the instant case, Dirac discloses a method and system of duplicate detection using machine learning including a deletion/removal of duplicates feature. Ahire also discloses a method and system of machine learning based data de-duplication specifically of trade line data. Marshall is a method of similarity clustering including known techniques. One of ordinary skill in the art would clearly recognize that this combination would lead to a predictable result (i.e. method and system of machine learning based data de-duplication specifically of trade line data including using similarity clustering including known techniques). As such the claimed invention is obvious over Dirac/Ahire,/ /Marshall .
Claims 5, 12, and 19
Dirac and Ahire disclose the invention as claimed above in Claims 3, 10 and 18.
Ahire further discloses algorithm analyses of pairs. (See at least Ahire, C7, L15-25, a pair of input object and a desired output value… algorithm analyses the training data and produces an inferred function… ),
Dirac and Ahire do not directly disclose the following; however, Marshall teaches:
wherein the computing the pairwise account similarity comprises generating a hash key for each of the transactions and pairing the plurality of accounts using hash keys . (See at least Marshall, C6L51-63, similarity is defined… by reference to a similarity measure… the degree of pairwise similarity between data item signatures X and Y may be measured using a similarity measure s(X, Y) C8L1-11, hash keys)
Furthermore, the Supreme Court has supported in KSR International Co. Teleflex Inc. (KSR), 550US___, 82 USPQ2d 1385 (2007), that merely applying a known technique to a known method, yield predictable results, render the claimed invention obvious over such combination. In the instant case, Dirac discloses a method and system of duplicate detection using machine learning including a deletion/removal of duplicates feature. Ahire also discloses a method and system of machine learning based data de-duplication specifically of trade line data. Marshall is a method of similarity clustering including known techniques. One of ordinary skill in the art would clearly recognize that this combination would lead to a predictable result (i.e. method and system of machine learning based data de-duplication specifically of trade line data including using similarity clustering including known techniques). As such the claimed invention is obvious over Dirac/Ahire,/ /Marshall. .
Conclusion
12. Any inquiry concerning this communication or earlier communications from the examiner should be directed to ASHA PUTTAIA H whose telephone number is (571)270-1352. The examiner can normally be reached on Monday- Friday 8:00am - 5:00 pm EST.
13. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Abhishek Vyas, can be reached on (571) 270-1836. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
14. 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://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). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ASHA PUTTAIA H/ Primary Examiner, Art Unit 3691