DETAILED ACTION
Claims 1-20 are presented for examination
This office action is in response to submission of application on 12-DECEMBER-2022.
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 .
Response to Amendment
The amendment filed on 03-FEBURARY-2026 in response to the non-final office action mailed 03-NOVEMBER-2025 has been entered. Claims 1-20 remain pending in the application.
With regards to the double patenting rejection, the examiner acknowledges the applicant’s request to hold the rejection in abeyance.
With regards to the 101 rejection, the rejection to claim 1 has been overcome by the applicant’s amendments.
With regards to the 103 rejections, the applicant’s amendments to the claims have not overcome the rejections to claims 1-20 as newly added prior art sufficiently teaches the newly added limitations of the amended claims.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 1-10 and 14 provisionally rejected on the ground of nonstatutory double patenting as being unpatentable over claims 1-10 and 14 of copending Application No. 18/064742.
This is a provisional nonstatutory double patenting rejection.
Claims 1-10, 14 of the application are compared to claims 1-10, 17 of the copending application 18/064742 in the following table:
Claim 1
A system for identifying at least one determined variable that defines a strong interpolated correlation with indications of a plurality of previous events and to produce, for each determined variable, a determined value that separates values of data associated with the at least one determined variable, the system including a computer with one or more processor and at least one of a memory device and a non-transitory storage device, wherein the one or more processor executes a variable determination program configured to perform steps including:
receive determination data indicative of the plurality of previous events associated with a plurality of users;
identify, utilizing a multiple variable statistical algorithm and the determination data, a plurality of data brackets, each having interpolated correlation with indications of the plurality of previous events;
identify, utilizing decision tree analysis and the plurality of data brackets, the at least one determined variable that defines the strong interpolated correlation with indications of the plurality of previous events;
and generate, utilizing decision tree analysis and the plurality of data brackets, the determined value for each of the at least one determined variable that separates ranges of data associated with the at least one determined variable based on the strong interpolated correlation within the determination data, wherein utilization of each determined value of the at least one determined variable to generate an extrapolated indication associated with a subsequent event rather than input data of a data bracket not indicating the at least one determined variable for the subsequent event increases the fidelity of the extrapolated indication, reduces redundancy within the extrapolated indication, or both.
Claim 1
A system for generating an extrapolated indication associated with a subsequent event, the system including a computer with one or more processor and at least one of a memory device and a non-transitory storage device, wherein the one or more processor executes:
a front-end variable determination program for identifying at least one determined variable that defines a strong interpolated correlation with indications of a plurality of previous events, the front-end variable determination program configured to produce, for each determined variable, a determined value that separates values of data associated with the at least one determined variable, the front-end variable determination program configured to perform steps including:
receive determination data indicative of the plurality of previous events associated with a plurality of users;
identify, utilizing a multiple variable statistical algorithm and the determination data, a plurality of data brackets, each having interpolated correlation with indications of the plurality of previous events;
identify, utilizing decision tree analysis and the plurality of data brackets, the at least one determined variable that defines the strong interpolated correlation with indications of the plurality of previous events;
and generate, utilizing decision tree analysis and the plurality of data brackets, the determined value for each of the at least one determined variable that separates ranges of data associated with the at least one determined variable based on the strong interpolated correlation within the determination data; and a back-end indication program for generating the extrapolated indication associated with the subsequent event, the back-end indication program configured to perform steps including: receive the at least one determined variable identified by the front-end variable determination program and each determined value generated by the front-end variable determination program; receive input data including data associated with the subsequent event and indicative of the at least one determined variable for the subsequent event; and generate the extrapolated indication associated with the subsequent event utilizing the input data, the at least one determined variable, and each determined value, wherein generating the extrapolated indication associated with the subsequent event utilizing the at least one determined variable and each associated determined value increases fidelity of the extrapolated indication associated with the subsequent event, reduces redundancy within the extrapolated indication, or both, and wherein generating an extrapolated indication associated with the subsequent event utilizing input data of a data bracket not indicating the at least one determined variable for the subsequent event increases infidelity in the extrapolated indication, results in an extrapolated indication including excessive redundancy, or both.
Claim 2
The system of claim 1, wherein logistic regression is utilized to identify the plurality of data brackets each having interpolated correlation with indications of the plurality of previous events.
Claim 2
The system of claim 1, wherein logistic regression is utilized to identify the plurality of data brackets each having interpolated correlation with indications of the plurality of previous events.
Claim 3
A system for generating a determined variable and an associated determined value suitable for generating an extrapolated indication associated with a subsequent event, the system including a computer with one or more processor and at least one of a memory device and a non- transitory storage device, wherein the one or more processor executes a variable determination program configured to perform steps including:
receive determination data indicative of a plurality of previous events associated with a plurality of users;
identify, utilizing a multiple variable statistical algorithm and the determination data, a plurality of data brackets, each having interpolated correlation with indications of the plurality of previous events;
identify, utilizing bivariate analysis and the plurality of data brackets, at least one determined variable that defines a strong interpolated correlation with indications of the plurality of previous events;
and and generate, utilizing bivariate analysis and the plurality of data brackets, the associated determined value for each of the at least one determined variable that separates ranges of data associated with the at least one determined variable based on the strong interpolated correlation within the determination data, wherein utilization of each determined value of the at least one determined variable to generate the extrapolated indication associated with a subsequent event rather than input data of a data bracket not indicating the at least one determined variable for the subsequent event increases the fidelity of the extrapolated indication, reduces redundancy within the extrapolated indication, or both.
Claim 3
A system for generating an extrapolated indication associated with a subsequent event, the system including a computer with one or more processor and at least one of a memory device and a non-transitory storage device, wherein the one or more processor executes:
a front-end variable determination program for identifying at least one determined variable that defines a strong interpolated correlation with indications of a plurality of previous events, the front-end variable determination program configured to produce, for each determined variable, a determined value that separates values of data associated with the at least one determined variable, the front-end variable determination program configured to perform steps including:
receive determination data indicative of the plurality of previous events associated with a plurality of users;
identify, utilizing a multiple variable statistical algorithm and the determination data, a plurality of data brackets, each having interpolated correlation with indications of the plurality of previous events;
identify, utilizing bivariate analysis and the plurality of data brackets, the at least one determined variable that defines the strong interpolated correlation with indications of the plurality of previous events;
and generate, utilizing bivariate analysis and the plurality of data brackets, the determined value for each of the at least one determined variable that separates ranges of data associated with the at least one determined variable based on the strong interpolated correlation within the determination data; and a back-end indication program for generating the extrapolated indication associated with the subsequent event, the back-end indication program configured to perform steps including: receive the at least one determined variable identified by the front-end variable determination program and each determined value generated by the front-end variable determination program; receive input data including data associated with the subsequent event and indicative of the at least one determined variable for the subsequent event; and generate the extrapolated indication associated with the subsequent event utilizing the input data, the at least one determined variable, and each determined value, wherein generating the extrapolated indication associated with the subsequent event utilizing the at least one determined variable and each associated determined value increases fidelity of the extrapolated indication associated with the subsequent event, reduces redundancy within the extrapolated indication, or both, and wherein generating an extrapolated indication associated with the subsequent event utilizing input data of a data bracket not indicating the at least one determined variable for the subsequent event increases infidelity in the extrapolated indication, results in an extrapolated indication including excessive redundancy, or both.
Claim 4
The system of claim 3, wherein logistic regression is utilized to identify the plurality of data brackets each having interpolated correlation with indications of the plurality of previous events.
Claim 4
The system of claim 3, wherein logistic regression is utilized to identify the plurality of data brackets each having interpolated correlation with indications of the plurality of previous events.
Claim 5
The system of claim 3, wherein decision tree analysis is utilized to identify the at least one determined variable that defines the strong interpolated correlation with indications of the plurality of previous events.
Claim 5
The system of claim 3, wherein decision tree analysis is utilized to identify the at least one determined variable that defines the strong interpolated correlation with indications of the plurality of previous events
Claim 6
The system of claim 3, wherein decision tree analysis is utilized to generate each determined value of the at least one determined variable that separates ranges of data associated with the at least one determined variable based on the strong interpolated correlation within the determination data.
Claim 6
The system of claim 3, wherein decision tree analysis is utilized to generate each determined value of the at least one determined variable that separates ranges of data associated with the at least one determined variable based on the strong interpolated correlation within the determination data.
Claim 7
The system of claim 3, wherein each determined value defines a first range of values of data of an associated determined variable indicative of a first level of completion of the plurality of previous events and a second range of values of data of the associated determined variable indicative of a second level of completion of the previous events.
Claim 7
The system of claim 3, wherein each determined value defines a first range of values of data of an associated determined variable indicative of a first level of completion of the plurality of previous events and a second range of values of data of the associated determined variable indicative of a second level of completion of the previous events.
Claim 8
The system of claim 3, wherein the variable determination program is further configured to perform steps including: generate, utilizing bivariate analysis and the plurality of data brackets, a second determined value for the at least one determined variable such that the second determined value separates ranges of data associated with the at least one determined variable based on the strong interpolated correlation within the determination data.
Claim 8
The system of claim 3, wherein the front-end variable determination program is further configured to perform steps including: generate, utilizing bivariate analysis and the plurality of data brackets, a second determined value for the at least one determined variable such that the second determined value separates ranges of data associated with the at least one determined variable based on the strong interpolated correlation within the determination data.
Claim 9
The system of claim 8, wherein the second determined value and the determined value of an associated determined variable define a first range, second range, and a third range of values of data of the associated determined variable, wherein the first range of values of data is indicative of a first level of completion of the plurality of previous events, the second range of values of data is indicative of a second level of completion of the plurality of previous events, and the third range of values of data is indicative of a third level of completion of the plurality of previous events.
Claim 9
The system of claim 8, wherein the second determined value and the determined value of an associated determined variable define a first range, second range, and a third range of values of data of the associated determined variable, wherein the first range of values of data is indicative of a first level of completion of the plurality of previous events, the second range of values of data is indicative of a second level of completion of the plurality of previous events, and the third range of values of data is indicative of a third level of completion of the plurality of previous events.
Claim 10
The system of claim 3, wherein the variable determination program is further configured to perform steps including: generate, utilizing bivariate analysis and the plurality of data brackets, a second determined value for each of the at least one determined variable such that the second determined value and the determined value define two ranges of data associated with each of the at least one determined variable based on the strong interpolated correlation within the determination data.
Claim 10
The system of claim 3, wherein the front-end determination program is further configured to perform steps including: generate, utilizing bivariate analysis and the plurality of data brackets, a second determined value for each of the at least one determined variable such that the second determined value and the determined variable define two ranges of data associated with each of the at least one determined variable based on the strong interpolated correlation within the determination data.
Claim 14
The system of claim 3, wherein the at least one determined variable is indicative of a debt coverage ratio of the plurality of users associated with the plurality of previous events.
Claim 17
The system of claim 3, wherein the at least one determined variable is indicative of a debt coverage ratio of the plurality of users associated with the plurality of previous events.
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 (i.e., changing from AIA to pre-AIA ) 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.
Claim 1 is rejected under 35 U.S.C. 103 as being unpatentable over THESLING (U.S. Pub. No. US 20040240578 A1) in view of IGNATYEV (U.S. Pub. No. US 20210132759 A1) in view of POOLE (U.S. Pub. No. US 20230162056 A1)
Regarding claim 1, THESLING teaches the claimed invention, including:
A system for identifying at least one determined variable that defines a strong interpolated correlation with indications of a plurality of previous events and to produce, for each determined variable, a determined value that separates values of data associated with the at least one determined variable, the system including a computer with one or more processor and at least one of a memory device and a non-transitory storage device, ([0155] To identify the IBO value that yields the highest correlation coefficient, an interpolation algorithm is implemented. First, the five correlation coefficients at the five IBO indices are calculated. If the highest three correlation coefficients include indices (0,1,2) or (1,2,3) or (2,3,4), then these three points are fit to a second-order polynomial and an interpolation to estimate the index where the maximum correlation coefficient occurs is performed. From the interpolated index of the maximum, the maximum IBO estimate is obtained by an inverse transform from the five postulated IBO points at the five indices. This latter operation can be implemented in many ways, such as by a look-up table, a polynomial curve fit, etc. (it finds the value of the IBO using interpolation to find the highest correlation. Using interpolation with the IBO means that the IBO must be a variable by definition. Thus the identification is of a variable))
While THESLING does teach determining a variable using interpolation and correlation, it does not explicitly teach:
wherein the one or more processor executes a variable determination program configured to perform steps including: receive, by an integrated module, determination data indicative of the plurality of previous events associated with a plurality of users; identify, by an integrated module via a frontend program utilizing a multiple variable statistical algorithm and the determination data, a plurality of data brackets, wherein each data bracket has a respective interpolated correlation with indications of the plurality of previous events; identify, by an integrated module via a frontend program utilizing decision tree analysis and the plurality of data brackets, the at least one determined variable that defines the strong interpolated correlation with indications of the plurality of previous events; and generate, by an integrated module via a frontend program utilizing decision tree analysis and the plurality of data brackets, the determined value for each of the at least one determined variable that separates ranges of data associated with the at least one determined variable based on the strong interpolated correlation within the determination data, wherein the determined value comprises a debt coverage ratio;
However, in analogous art that similarly teaches variable determination, IGNATYEV teaches:
wherein the one or more processor executes a variable determination program configured to perform steps including: receive, by an integrated module, determination data indicative of the plurality of previous events associated with a plurality of users; ([0054] In one embodiment, a data structure describing the historical event (including any base document) need not be stored in the system log 190. Instead, the data structure describing the historical event is stored in a data store associated with application modules of the integrated business system 135 that may perform operations regarding the event. But, the arrival of the historical event into the integrated business system 135, the storage of the data structure describing the historical event, and all actions taken toward the historical event using the integrated business system 135 by any user or by the system 135 itself are recorded in the system log 190. As discussed above, each historical event is recorded as an entry in the system log 190 with (i) the information to identify the event along with (ii) a timestamp indicating when the event occurred. In one embodiment, the information to identify the event includes an event identifier that is unique to the historical event in order to associate the entry in the system log 190 with the event. (the integrated business system is a frontend integrated module)
[0064] Once the processor has thus parsed the system log of the software platform to identify interactions of the user with each event of the selected type processing at process block 410 completes, and processing continues to process block 415.
[0065] At process block 415, for each event, the processor creates a data structure that describes the interactions with the event based at least in part on (i) the identified interactions and (ii) one or more characteristics of the event. This data structure may be referred to as an event data structure. The creation of the event data structure applies a consistent structure to input and output variables describing the event for provision to a machine learning model. In one embodiment, the output variables included in the event data structure are derived from interactions collected in a collection array associated with that event. In one embodiment, the input variables included in the event data structure are characteristics associated with the event and retrieved from data stores 270, 275 associated with the various modules.) identify, by an integrated module via a frontend program utilizing a multiple variable statistical algorithm and the determination data, a plurality of data brackets, wherein each data bracket has a respective interpolated correlation with indications of the plurality of previous events; ([0066] Process block 415 may commence in response to the processor parsing the indication or the signal that the collection data structure including the collection arrays is ready for further processing into structured data.
[0067] The interactions with the events of the selected type of event identified in process block 410 can be considered to be outputs of a function of characteristics associated with the selected type of event. The function for arriving at these outputs may be initially unknown or not recorded in the integrated business system 135. But, because both the historical outputs and the values of the characteristics are recorded in the integrated business system 135, the function can be derived.) identify, by an integrated module via a frontend program utilizing decision tree analysis and the plurality of data brackets, the at least one determined variable that defines the strong interpolated correlation with indications of the plurality of previous events; ([0083] In one embodiment, for each of the possible outcome types, the processor builds and validates a decision tree model. The processor applies the decision tree building algorithm to the training set to build a decision tree model for the possible outcome type. The processor stores the decision tree model in memory or storage. The processor then provides the validation set to the decision tree model to predict the outcome of the outcome type for each interaction data structure of the set. The processor compares the predicted outcomes and the historical outcomes (provided in the interaction data structure). If the predicted and historical outcomes correlate within a predetermined tolerance threshold (for example, no more than 5% difference between the predicted and historical outcomes), the validation is successful, and the processor stores an indication in memory or sends a signal indicating that the model for that outcome type is finalized (ready for use). If the predicted and historical outcomes do not correlate within the predetermined tolerance threshold, (i) the training and validation sets may be re-sampled, and the model re-built and re-validated based on the new training and validation sets, or (ii) the process may abort, and no model will be finalized.) and generate, by an integrated module via a frontend program utilizing decision tree analysis and the plurality of data brackets, the determined value for each of the at least one determined variable that separates ranges of data associated with the at least one determined variable based on the strong interpolated correlation within the determination data, wherein the determined value comprises a debt coverage ratio; and([0085] The built and successfully validated decision tree model is a model of a process applied to events of the selected type by the user to arrive at the value for the outcome type. The decision tree model can now be substituted for the business process/algorithm that the user is manually applying (consciously or not) to events of the selected type. If the set of historic events is an accurate reflection of the user's business logic/algorithm, the decision tree model should predict the same outcome value (within the predetermined tolerance threshold) as the user's manual process for all subsequent events. (the model uses the generate/predicted data to increase accuracy, which in turn reduces redundancy) [0121] In one embodiment, the processor creates an interaction data structure of the form described with reference to process block 415, where the interaction data structure includes (i) an outcome variable for each type of outcome associated with the type of event, and (ii) the characteristic vector C. The processor detects the type of event and retrieves the types of outcome associated with the event type from memory or storage. The processor sets the values of the outcome variables to null for later modification by the machine learning model(s). The processor creates an interaction data structure including the values of each of the outcome variables and the characteristic vector C. The events are now represented as structured data suitable for use with the machine learning model(s). (this shows the generation of the data in more detail) [0072] In one embodiment, the particular set of characteristics associated with the selected type of event is dictated by the type of event. For example, where the event is a sales order, the characteristic information may include variables for (i) customer characteristics (such as customer priority, value of the customer, and customer location) of the customer that the sales order is for, (ii) sales representative characteristics of the sales representative that issued the sales order, (iii) item characteristics (such as inventory availability, item weight, and item size) associated with the items to be sold under the sales order, and (iv) order characteristics (such as desired/target date and monetary value of the order) of the sales order itself. In another example, where the event is a payroll batch, the characteristic information may include variables for (i) employees and employee characteristics, including salary/wages, benefits and other deductions, and tax withholding choices, (ii) timesheets, and (iii) prior payroll batches and payments.)
It would have been obvious to a person skilled in the art before the effective filing date of the
invention to have combined with IGNATYEV‘s data generation and identification and, with THESLING‘s interpolated correlation method, with a reasonable expectation of success, a method that generates data and identifies data, as in IGNATYEV, based on data that was identified using interpolated correlation, as found in THESLING. A person of ordinary skill would have been motivated to lower redundancy (IGNATYEV [0004]).
While THESLING, as modified by IGNATYEV, does teach generating data and analyzing decision trees, it does not explicitly teach:
Generate, by the integrated module via a backend program utilizing each determined value of the at least one determined variable, an extrapolated indication associated with a potential subsequent event, wherein the potential subsequent event is associated with a financial obligation, wherein the extrapolated indication indicates whether a customer is likely to generate the subsequent potential event,
However, in analogous art that similarly handles purchase even history, POOLE teaches:
Generate, by the integrated module via a backend program utilizing each determined value of the at least one determined variable, an extrapolated indication associated with a potential subsequent event, wherein the potential subsequent event is associated with a financial obligation, wherein the extrapolated indication indicates whether a customer is likely to generate the subsequent potential event, ([0046] At step 204B, a likelihood of the user purchasing a product for a next occurrence of the recurring or periodic event may be determined. The likelihood may depend on a number of factors, such as purchase history, products purchased, user feedback, significance of the event, etc. For example, if the user has purchased goods or services for several occurrences of the recurring or periodic event, then the likelihood of the user making a purchase for the next occurrence of the recurring or periodic event may be high. If the user indicates that a transaction or the specific goods or services purchased may not have been satisfactory, and/or that the event was not of significance to the user, then the likelihood of the user making a purchase for the next occurrence of the recurring or periodic event may be low. [0047] At step 205B, upon determining that the likelihood is equal to or exceeds a predetermined likelihood threshold, an indication to the user may be transmitted prior to the next recurrence of the event.)
It would have been obvious to a person skilled in the art before the effective filing date of the
invention to have combined with POOLE‘s indication of user eventss and, with THESLING‘s, as modified by IGNATYEV, interpolated correlation method, with a reasonable expectation of success, a method that finds the likelihood of an event and generates an indication, as in POOLE, based on data that was identified using interpolated correlation, as found in THESLING, as modified by IGNATYEV. A person of ordinary skill would have been motivated to improve indications (POOLE [0004]).
IGNATYEV further teaches:
and wherein the backend program utilizing the at least one determined variable for the extrapolated indication associated with the subsequent event increases the fidelity of the extrapolated indication, reduces redundancy within the extrapolated indication, or both. (([0085] The built and successfully validated decision tree model is a model of a process applied to events of the selected type by the user to arrive at the value for the outcome type. The decision tree model can now be substituted for the business process/algorithm that the user is manually applying (consciously or not) to events of the selected type. If the set of historic events is an accurate reflection of the user's business logic/algorithm, the decision tree model should predict the same outcome value (within the predetermined tolerance threshold) as the user's manual process for all subsequent events. (the model uses the generate/predicted data to increase accuracy, which in turn reduces redundancy))
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over THESLING (U.S. Pub. No. US 20040240578 A1), IGNATYEV (U.S. Pub. No. US 20210132759 A1), POOLE (U.S. Pub. No. US 20230162056 A1) in further view of MARSHALL (U.S. Pub. No. US 20210000442 A1)
Regarding claim 2, while THESLING, as modified by IGNATYEV, does teach a claim 1, which claim 2 is dependent upon, it does not explicitly teach:
The system of claim 1, wherein logistic regression is utilized to identify the plurality of data brackets each having interpolated correlation with indications of the plurality of previous events.
However, in analogous art that similarly handles a bracket of data, MARSHALL teaches:
The system of claim 1, wherein logistic regression is utilized to identify the plurality of data brackets each having interpolated correlation with indications of the plurality of previous events. ([0163] Logistic regression analysis was then used to identify the optimal array or subset of all the hybrid features)
It would have been obvious to a person skilled in the art before the effective filing date of the
invention to have combined with MARSHALL‘s logistic regression and, with THESLING‘s, as modified by IGNATYEV, data brackets, with a reasonable expectation of success, a method that data generation on data brackets, as in MARSHALL, where the data is used to identify variables, as found in THESLING, as modified by IGNATYEV. A person of ordinary skill would have been motivated to increase accuracy (MARSHALL [0006]).
Claims 3, 5-11, 13, 15, 16, and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over THESLING (U.S. Pub. No. US 20040240578 A1), IGNATYEV (U.S. Pub. No. US 20210132759 A1), POOLE (U.S. Pub. No. US 20230162056 A1) in further view of PENDAULT (U.S. Pub. No. US 20050125474 A1)
Regarding claim 3, THESLING substantially teaches the claimed invention including:
A system for generating a determined variable and an associated determined value suitable for generating an extrapolated indication associated with a subsequent event, the system including a computer with one or more processor and at least one of a memory device and a non- transitory storage device, ([0155] To identify the IBO value that yields the highest correlation coefficient, an interpolation algorithm is implemented. First, the five correlation coefficients at the five IBO indices are calculated. If the highest three correlation coefficients include indices (0,1,2) or (1,2,3) or (2,3,4), then these three points are fit to a second-order polynomial and an interpolation to estimate the index where the maximum correlation coefficient occurs is performed. From the interpolated index of the maximum, the maximum IBO estimate is obtained by an inverse transform from the five postulated IBO points at the five indices. This latter operation can be implemented in many ways, such as by a look-up table, a polynomial curve fit, etc. (it finds the value of the IBO using interpolation to find the highest correlation. Using interpolation with the IBO means that the IBO must be a variable by definition. Thus the identification is of a variable))
While THESLING does teach determining a variable using interpolation and correlation, it does not explicitly teach:
wherein the one or more processor executes a variable determination program configured to perform steps including: receive determination data indicative of a plurality of previous events associated with a plurality of users;
However, in analogous art that similarly teaches variable determination, IGNATYEV teaches:
wherein the one or more processor executes a variable determination program configured to perform steps including: receive determination data indicative of a plurality of previous events associated with a plurality of users; ([0064] Once the processor has thus parsed the system log of the software platform to identify interactions of the user with each event of the selected type processing at process block 410 completes, and processing continues to process block 415.
[0065] At process block 415, for each event, the processor creates a data structure that describes the interactions with the event based at least in part on (i) the identified interactions and (ii) one or more characteristics of the event. This data structure may be referred to as an event data structure. The creation of the event data structure applies a consistent structure to input and output variables describing the event for provision to a machine learning model. In one embodiment, the output variables included in the event data structure are derived from interactions collected in a collection array associated with that event. In one embodiment, the input variables included in the event data structure are characteristics associated with the event and retrieved from data stores 270, 275 associated with the various modules.) identify, utilizing a multiple variable statistical algorithm and the determination data, a plurality of data brackets, each having interpolated correlation with indications of the plurality of previous events; ([0066] Process block 415 may commence in response to the processor parsing the indication or the signal that the collection data structure including the collection arrays is ready for further processing into structured data.
[0067] The interactions with the events of the selected type of event identified in process block 410 can be considered to be outputs of a function of characteristics associated with the selected type of event. The function for arriving at these outputs may be initially unknown or not recorded in the integrated business system 135. But, because both the historical outputs and the values of the characteristics are recorded in the integrated business system 135, the function can be derived.)
It would have been obvious to a person skilled in the art before the effective filing date of the
invention to have combined with IGNATYEV‘s data generation and identification and, with THESLING‘s interpolated correlation method, with a reasonable expectation of success, a method that generates data and identifies data, as in IGNATYEV, based on data that was identified using interpolated correlation, as found in THESLING. A person of ordinary skill would have been motivated to lower redundancy (IGNATYEV [0004]).
While THESLING, as modified by IGNATYEV, does teach identifying data brackets and receives data, it does not explicitly teach:
identify, utilizing bivariate analysis and the plurality of data brackets, at least one determined variable that defines a strong interpolated correlation with indications of the plurality of previous events;
However, in analogous art that similarly teaches finding a variable, PENDAULT teaches:
identify, utilizing bivariate analysis and the plurality of data brackets, at least one determined variable that defines a strong interpolated correlation with indications of the plurality of previous events; ([0096] Another aspect of Gram-Schmidt orthogonalization is to construct a new set of derived features that are orthogonal to the output of the first stage (i.e., the dot products between the output 410 of the first stage and each new derived feature in module 411 should be zero). To accomplish this feat, all that needs to be done is to include the output of the first stage as a regression variable in the linear regression trees for each feature when constructing transformed features 411.
[0097] The resulting linear regression trees would no longer be univariate, they would be bivariate. (it should be further noted that one of ordinary skill could use the bivariate decision trees here in place of the decision trees of IGNATYEV and vice versa))
It would have been obvious to a person skilled in the art before the effective filing date of the
invention to have combined with PENDAULT‘s bivariate analysis identifcation and, with THESLING‘s, as modified by IGNATYEV, interpolated correlation method and data brackets, with a reasonable expectation of success, a method that identifies variables with bivariate analysis, as in PENDAULT, based on data that was identified using interpolated correlation, as found in THESLING, as modified by IGNATYEV. A person of ordinary skill would have been motivated to lower redundancy (PENDAULT [0052]).
IGNATYEV further teaches:
and and generate, utilizing bivariate analysis and the plurality of data brackets, the associated determined value for each of the at least one determined variable that separates ranges of data associated with the at least one determined variable based on the strong interpolated correlation within the determination data, wherein utilization of each determined value of the at least one determined variable to generate the extrapolated indication associated with a subsequent event rather than input data of a data bracket not indicating the at least one determined variable for the subsequent event increases the fidelity of the extrapolated indication, reduces redundancy within the extrapolated indication, or both. ([0085] The built and successfully validated decision tree model is a model of a process applied to events of the selected type by the user to arrive at the value for the outcome type. The decision tree model can now be substituted for the business process/algorithm that the user is manually applying (consciously or not) to events of the selected type. If the set of historic events is an accurate reflection of the user's business logic/algorithm, the decision tree model should predict the same outcome value (within the predetermined tolerance threshold) as the user's manual process for all subsequent events. (the model uses the generate/predicted data to increase accuracy, which in turn reduces redundancy) [0121] In one embodiment, the processor creates an interaction data structure of the form described with reference to process block 415, where the interaction data structure includes (i) an outcome variable for each type of outcome associated with the type of event, and (ii) the characteristic vector C. The processor detects the type of event and retrieves the types of outcome associated with the event type from memory or storage. The processor sets the values of the outcome variables to null for later modification by the machine learning model(s). The processor creates an interaction data structure including the values of each of the outcome variables and the characteristic vector C. The events are now represented as structured data suitable for use with the machine learning model(s). (this shows the generation of the data in more detail))
Regarding claim 5, IGNATYEV further teaches:
The system of claim 3, wherein decision tree analysis is utilized to identify the at least one determined variable that defines the strong interpolated correlation with indications of the plurality of previous events. ([0083] In one embodiment, for each of the possible outcome types, the processor builds and validates a decision tree model. The processor applies the decision tree building algorithm to the training set to build a decision tree model for the possible outcome type. The processor stores the decision tree model in memory or storage. The processor then provides the validation set to the decision tree model to predict the outcome of the outcome type for each interaction data structure of the set. The processor compares the predicted outcomes and the historical outcomes (provided in the interaction data structure). If the predicted and historical outcomes correlate within a predetermined tolerance threshold (for example, no more than 5% difference between the predicted and historical outcomes), the validation is successful, and the processor stores an indication in memory or sends a signal indicating that the model for that outcome type is finalized (ready for use). If the predicted and historical outcomes do not correlate within the predetermined tolerance threshold, (i) the training and validation sets may be re-sampled, and the model re-built and re-validated based on the new training and validation sets, or (ii) the process may abort, and no model will be finalized.)
Regarding claim 6, IGNATYEV further teaches:
The system of claim 3, wherein decision tree analysis is utilized to generate each determined value of the at least one determined variable that separates ranges of data associated with the at least one determined variable based on the strong interpolated correlation within the determination data. ([0085] The built and successfully validated decision tree model is a model of a process applied to events of the selected type by the user to arrive at the value for the outcome type. The decision tree model can now be substituted for the business process/algorithm that the user is manually applying (consciously or not) to events of the selected type. If the set of historic events is an accurate reflection of the user's business logic/algorithm, the decision tree model should predict the same outcome value (within the predetermined tolerance threshold) as the user's manual process for all subsequent events.)
Regarding claim 7, IGNATYEV further teaches:
The system of claim 3, wherein each determined value defines a first range of values of data of an associated determined variable indicative of a first level of completion of the plurality of previous events and a second range of values of data of the associated determined variable indicative of a second level of completion of the previous events. ([0121] In one embodiment, the processor creates an interaction data structure of the form described with reference to process block 415, where the interaction data structure includes (i) an outcome variable for each type of outcome associated with the type of event, and (ii) the characteristic vector C. The processor detects the type of event and retrieves the types of outcome associated with the event type from memory or storage. The processor sets the values of the outcome variables to null for later modification by the machine learning model(s). The processor creates an interaction data structure including the values of each of the outcome variables and the characteristic vector C. The events are now represented as structured data suitable for use with the machine learning model(s).
[0122] Once the interaction data structure is complete, the processor stores an indication in memory or sends a signal that the interaction data structure is complete.
[0123] Once the processor has thus created the subsequent event data structure based on the one or more characteristics of the subsequent event, processing at process block 515 completes, and processing continues to process block 520.)
Regarding claim 8, IGNATYEV further teaches:
The system of claim 3, wherein the variable determination program is further configured to perform steps including: generate, utilizing bivariate analysis and the plurality of data brackets, a second determined value for the at least one determined variable such that the second determined value separates ranges of data associated with the at least one determined variable based on the strong interpolated correlation within the determination data. ([121] The processor creates an interaction data structure including the values of each of the outcome variables and the characteristic vector C. The events are now represented as structured data suitable for use with the machine learning model(s).
[0122] Once the interaction data structure is complete, the processor stores an indication in memory or sends a signal that the interaction data structure is complete.
[0123] Once the processor has thus created the subsequent event data structure based on the one or more characteristics of the subsequent event, processing at process block 515 completes, and processing continues to process block 520.
[0124] At process block 520, the processor evaluates the subsequent event data structure with the model to determine a priority value associated with the process for the subsequent event. The processor may begin processing at process block 520 in response to parsing the indication or signal that the interaction data structure is complete.)
Regarding claim 9, IGNATYEV further teaches:
The system of claim 8, wherein the second determined value and the determined value of an associated determined variable define a first range, second range, and a third range of values of data of the associated determined variable, wherein the first range of values of data is indicative of a first level of completion of the plurality of previous events, ([0118] Once the characteristic vector C is populated and associated with a unique identifier of the subsequent event, the processor stores an indication in memory or sends a signal that the characteristic vector is complete.
[0119] Once the processor has thus parsed the data object to identify the one or more characteristics of the subsequent event, processing at process block 510 completes, and processing continues to process block 515.
[0120] At process block 515, the processor creates a subsequent event data structure based on the one or more characteristics of the subsequent event. The processor may begin processing at process block 515 in response to the indication or signal that the characteristic vector is complete.) the second range of values of data is indicative of a second level of completion of the plurality of previous events, ([0122] Once the interaction data structure is complete, the processor stores an indication in memory or sends a signal that the interaction data structure is complete.
[0123] Once the processor has thus created the subsequent event data structure based on the one or more characteristics of the subsequent event, processing at process block 515 completes, and processing continues to process block 520.
[0124] At process block 520, the processor evaluates the subsequent event data structure with the model to determine a priority value associated with the process for the subsequent event. The processor may begin processing at process block 520 in response to parsing the indication or signal that the interaction data structure is complete.)
and the third range of values of data is indicative of a third level of completion of the plurality of previous events. ([0127] Once the processor has thus evaluated the subsequent event data structure with the model to determine the priority value associated with the process for the subsequent event, processing at process block 520 completes, and processing continues to decision block 525.)
Regarding claim 10, IGNATYEV further teaches:
The system of claim 3, wherein the variable determination program is further configured to perform steps including: generate, utilizing bivariate analysis and the plurality of data brackets, a second determined value for each of the at least one determined variable such that the second determined value and the determined value define two ranges of data associated with each of the at least one determined variable based on the strong interpolated correlation within the determination data. ([0117] In one embodiment, the processor parses a data object to identify one or more characteristics of the subsequent event as follows. The processor detects the type of the subsequent event. The processor retrieves from memory or storage (i) the characteristic variables associated with the type of the subsequent event, and (ii) the storage locations in which values for the characteristic variables can be found (as discussed above with reference to process block 415). The processor creates one or more queries to retrieve values of the characteristic variables stored in one or more data objects. The processor executes the one or more queries and stores the returned values of the characteristic variables as the dimensions of a characteristic vector C (as discussed above with reference to process block 415). The processor associates the characteristic vector C with a unique identifier of the subsequent event.)
Regarding claim 11, IGNATYEV further teaches:
The system of claim 3, wherein the step to identify at least one determined variable includes: identify, utilizing decision tree analysis and the plurality of data brackets, a first determined variable that defines a first strong interpolated correlation with indications of the plurality of previous events; ([0083] In one embodiment, for each of the possible outcome types, the processor builds and validates a decision tree model. The processor applies the decision tree building algorithm to the training set to build a decision tree model for the possible outcome type. The processor stores the decision tree model in memory or storage. The processor then provides the validation set to the decision tree model to predict the outcome of the outcome type for each interaction data structure of the set. The processor compares the predicted outcomes and the historical outcomes (provided in the interaction data structure). If the predicted and historical outcomes correlate within a predetermined tolerance threshold [0200] A machine learning model can be fitted to the observed historical purchase orders by the automated process discovery and facilitation server 195. Once a data structure for a historical purchase order is stored in memory, it can be provided to some machine learning model to train the model. For example, a decision tree regression model could be used for predicting numeric delivery speed variable S.) and identify, utilizing decision tree analysis and the plurality of data brackets, a second determined variable that defines a second strong interpolated correlation with indications of the plurality of previous events. ( Also, for example, a decision tree classification model for predicting categorical shipping location variable L. Those models may be fitted to each of the vectors x=(x1, . . . , x7) provided in the data structures of historical purchase orders. In one embodiment, the models may be fitted to the data structures in accordance with the steps described with reference to process block 420 of FIG. 4.)
Regarding claim 13, IGNATYEV further teaches:
The system of claim 3, wherein the step to identify at least one determined variable includes: identify, utilizing bivariate analysis and the plurality of data brackets, a first determined variable that defines a first strong interpolated correlation with indications of the plurality of previous events; identify, utilizing bivariate analysis and the plurality of data brackets, a second determined variable that defines a second strong interpolated correlation with indications of the plurality of previous events; and identify, utilizing bivariate analysis and the plurality of data brackets, a third determined variable that defines a third strong interpolated correlation with indications of the plurality of previous events. ([0121] In one embodiment, the processor creates an interaction data structure of the form described with reference to process block 415, where the interaction data structure includes (i) an outcome variable for each type of outcome associated with the type of event, and (ii) the characteristic vector C. The processor detects the type of event and retrieves the types of outcome associated with the event type from memory or storage. The processor sets the values of the outcome variables to null for later modification by the machine learning model(s). The processor creates an interaction data structure including the values of each of the outcome variables and the characteristic vector C. The events are now represented as structured data suitable for use with the machine learning model(s). )
Regarding claim 16, IGNATYEV further teaches:
The method of claim 15, further comprising: communicating a representation of the at least one determined variable and the associated determined value. ([0121] The processor sets the values of the outcome variables to null for later modification by the machine learning model(s). The processor creates an interaction data structure including the values of each of the outcome variables and the characteristic vector C. The events are now represented as structured data suitable for use with the machine learning model(s). [0123] Once the processor has thus created the subsequent event data structure based on the one or more characteristics of the subsequent event, processing at process block 515 completes, and processing continues to process block 520.)
Regarding claim 15, it comprises of limitations similar to those of claim 3 and is therefore rejected for similar rationale. Regarding claim 18, it comprises of limitations similar to those of claim 8 and is therefore rejected for similar rationale. Regarding claim 19, it comprises of limitations similar to those of claim 11 and is therefore rejected for similar rationale.
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over THESLING (U.S. Pub. No. US 20040240578 A1), IGNATYEV (U.S. Pub. No. US 20210132759 A1), POOLE (U.S. Pub. No. US 20230162056 A1), PENDAULT (U.S. Pub. No. US 20050125474 A1) in further view of MARSHALL (U.S. Pub. No. US 20210000442 A1)
Regarding claim 4, while THESLING, as modified by IGNATYEV and PENDAULT, does teach a claim 3, which claim 4 is dependent upon, it does not explicitly teach:
The system of claim 3, wherein logistic regression is utilized to identify the plurality of data brackets each having interpolated correlation with indications of the plurality of previous events.
However, in analogous art that similarly handles a bracket of data, MARSHALL teaches:
The system of claim 3, wherein logistic regression is utilized to identify the plurality of data brackets each having interpolated correlation with indications of the plurality of previous events. ([0163] Logistic regression analysis was then used to identify the optimal array or subset of all the hybrid features)
It would have been obvious to a person skilled in the art before the effective filing date of the
invention to have combined with MARSHALL‘s logistic regression and, with THESLING‘s, as modified by IGNATYEV and PENDAULT, data brackets, with a reasonable expectation of success, a method that data generation on data brackets, as in MARSHALL, where the data is used to identify variables, as found in THESLING, as modified by IGNATYEV and PENDAULT. A person of ordinary skill would have been motivated to increase accuracy (MARSHALL [0006]).
Claims 12, 14, 17, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over THESLING (U.S. Pub. No. US 20040240578 A1), IGNATYEV (U.S. Pub. No. US 20210132759 A1), POOLE (U.S. Pub. No. US 20230162056 A1), PENDAULT (U.S. Pub. No. US 20050125474 A1) in further view of PARK (K.R. Pub. No. KR 20090001939 A)
Regarding claim 12, while THESLING as modified by IGNATYEV and PENDAULT, does teach claim 11, which claim 12 is dependent upon, it does not explicitly teach:
The system of claim 11, wherein the first determined variable is indicative of a debt coverage ratio of the plurality of users associated with the plurality of previous events, and the second determined variable is indicative of at least one of a cash flow velocity or a percentile change in a deposited balance of the plurality of users associated with the plurality of previous events.
However, in analogous art that similarly handles user data and variables, PARK teaches:
The system of claim 11, wherein the first determined variable is indicative of a debt coverage ratio of the plurality of users associated with the plurality of previous events, and the second determined variable is indicative of at least one of a cash flow velocity or a percentile change in a deposited balance of the plurality of users associated with the plurality of previous events. ((PARK claim 2) And the debt ratio (Debt Service Coverage Ratio) variables, and at least one stress analysis parameters, at least one request bunyangryul level variables, and at least one business profit margin variables, loan-to-value ratio (Loan To Value) variables, and at least one loan repayment priority variables, the weighted average loan term (weighted average Life) cash flow including the variable adequacy risk information)
It would have been obvious to a person skilled in the art before the effective filing date of the invention to have combined with PARK‘s debt data and cash flow and, with THESLING‘s, as modified by IGNATYEV and PENDAULT, user data, with a reasonable expectation of success, a method that tracks debt data, as in PARK, where the data is identified with interpolated correlation, as found in THESLING, as modified by IGNATYEV and PENDAULT. A person of ordinary skill would have been motivated to lower costs (PARK pg. 3, paragraph 7).
Regarding claim 14, PARK further teaches:
The system of claim 3, wherein the at least one determined variable is indicative of a debt coverage ratio of the plurality of users associated with the plurality of previous events. ((pg 22, paragraph 10) The interface provider 1010 connects a predetermined communication channel with the pre-sale real estate finance server 1000 through the interface unit 1005 and registers the pre-sale real estate finance information. Upon request, when the user interface for the cash flow analysis according to the presale-type real estate finance valuation model is requested to the presale-type real estate finance server 1000, the enterprise terminal 1090 inputs predetermined real estate sale business information(or Select one or more user interfaces to be transmitted to the pre-sale real estate finance server 1000 through the network means, and / or extract from a predetermined database (not shown), and the interface unit 1005 Interworking to provide the generated (or extracted) user interface to the enterprise terminal 1090 via the network means.)
Regarding claim 17, it comprises of limitations similar to those of claim 14 and is therefore rejected for similar rationale. Regarding claim 20, it comprises of limitations similar to those of claim 12 and is therefore rejected for similar rationale.
Response to Arguments
Applicant’s arguments filed 03-FEBURARY-2026 have been fully considered, but they are found to be non-persuasive
With regards to the applicant’s remarks regarding the 103 rejection in the non-final action, the applicant argues that the prior art does not teach the newly amended claims 1, 3, and 15. The examiner acknowledges this argument and has adjusted the prior art of IGNATYEV to disclose in part the newly added limitations. Examiner also introduced newly added prior art POOLE to teach the newly added limitations. Further, the examiner has adjusted all dependent claims accordingly.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SKIELER A KOWALIK whose telephone number is (571)272-1850. The examiner can normally be reached 8-5.
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, Mariela D Reyes can be reached at (571)270-1006. 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.
/SKIELER ALEXANDER KOWALIK/Examiner, Art Unit 2142 /Mariela Reyes/Supervisory Patent Examiner, Art Unit 2142
Prosecution Insights