AIA
Claims 1-20 examined
Amended none
Canceled none
New none
CON of 17166563 filed 3 Feb 2021
Provisional 62983877 filed 20 March 2020
Related
18367914 filed 09/13/2023 Con of 17107087 filed 11/30/2020 now US Pat 11790268
17166563 filed 02/03/2021, Prov 62983877 filed 03/02/2020 now US Pat 12182728
17340335 filed on 06/07/2021 is CIP of 17166563 filed 02/03/2021
Response to Remarks
Examiner thanks attorney Laureanti for the response to advance prosecution
Applicant amendment remarks fully considered but unfortunately not fully persuasive.
103
A/B is already in Wick; see below.
101
As to applicant argument that
No abstract idea
Examiner
The A/B simulation amendment is an abstract idea (see Wikipedia and Merriam-Webster dictionary). Applicant is “separating the wheat from the chaff”, as the idiom goes, via the abstract idea of A/B testing.
Deconfounding is to separate A from B. A/B testing is to deconfound.
PNG
media_image1.png
691
1295
media_image1.png
Greyscale
PNG
media_image2.png
283
759
media_image2.png
Greyscale
As to applicant argument that
Not organizing human activity
Examiner
Applicant is simulating demand, human demand.
As to applicant argument that
Integrates into a practical application
Examiner
Applicant simply implements an idea by computer.
As to applicant argument that
Not math
Examiner
A proof or formula is not dispositive. Deconfounding is math regardless of a formula or proof. And the complexity of ‘many’ (remarks p11 bottom) supply chain problems is just anecdotal and doesn’t tell us anything about this claim.
As to applicant argument that
Not Practically performed in the mind
Examiner
That depends on the amount of data and the machine learning. Regression with few data points can be done in the mind or with pencil and paper. Carl Friederich Gauss 1777-1855.
As to applicant argument that
Claim must use a computer
Examiner
That sometimes a computer is used as in Langley is not dispositive on the question whether ML always requires a computer. MPEP 2106.05f,g
As to applicant argument that
Neural network
Examiner
Not claimed
Discerning causation from correlation and determining the actual cause and classification of A versus B (22:25) is the same thing as the deconfounding. Wick3 “Confounding … randomized controlled trials”(Wick3 p7) .
As to applicant argument that
Ex parte Desjardins
Examiner
Applicant is not improving computer functionality or an improvement to other technology or a technical field but rather computer implementing an abstract idea using a computer as a tool. The Desjardins Appeals Review Panel credited benefits of reduced storage, reduced system complexity and streamlining and perseveration of performance attributes, overcoming the problem of catastrophic forgetting are unrelated to the Applicant’s post-solution activity of “transmitting … instructions”. Appellant has a business problem. Appellant provides a business solution. Setting a price is a business dictate and fundamental economics. It’s the same as saying increase capacity to supply (as in the supply and demand of fundamental economics)
During prosecution, applicant has an opportunity and a duty to amend ambiguous claims to clearly and precisely define the metes and bounds of the claimed invention. The claim places the public on notice of the scope of the patentee’s right to exclude. See, e.g., Johnson & Johnston Assoc. Inc. v. R.E. Serv. Co., 285 F.3d 1046, 1052, 62 USPQ2d 1225, 1228 (Fed. Cir. 2002) (en banc). As stated in Halliburton Energy Servs., Inc. v. M-I LLC, 514 F.3d 1244, 1255, 85 USPQ2d 1654, 1663 (CAFC 2008):
“We note that the patent drafter is in the best position to resolve the ambiguity in the patent claims, and it is highly desirable that patent examiners demand that applicants do so in appropriate circumstances so that the patent can be amended during prosecution rather than attempting to resolve the ambiguity in litigation”
CLAIM REJECTIONS - 35 USC § 101
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. The Claim(s) is/are directed to one or more abstract idea(s). The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the abstract idea(s).
Step 1
The claims fall w/i the four 101 statutory categories (1 process 8 machine 15 article of manufacture).
Step 2a
The invention identifies cause (factor) of effect (demand) – what causes of economic effect?
The claims predict demand for setting price.
Alice
clearinghouse
computer implemented
Bilski
hedge
computer implemented
Ultramercial
Advertising
computer implemented
Here
simulate demand via A/B testing for setting price
computer implemented
Organizing Human Activity (training, training, predicting demand - fundamental economics and sales, marketing, advertising activity)
Math
Mental steps (concepts performed in the human mind including observation, evaluation, judgement, opinion)
Applicant takes an idea and then applies it with generic additional elements generally applied --with computer and machine learning.
PNG
media_image3.png
211
235
media_image3.png
Greyscale
PNG
media_image4.png
260
218
media_image4.png
Greyscale
This fundamental concept of subtracting systematic error is math applied to marketing data for organizing human activity. All the Applicant’s other steps and math funneled toward calculating demand. This is organizing and manipulating information through mathematical correlations (organizing human activity and mathematical relationship/formula). DECONFOUNDING IS OLD MATH. From www.en.Wikipedia.org/wiki/Confounding. Applicant simply applies it (implement by generic additional elements generally applied namely computer & machine learning). Training/processing with machine learning is an idea itself of organizing information through mathematical correlations, using categories to organize, store and transmit information. Machine learning is old and well-known (NPL: “Approaches to Machine Learning, P. Langley at Carnegie-Mellon University (1984) and the references it refers to from more than a half-century ago).
PNG
media_image5.png
129
387
media_image5.png
Greyscale
Exemplary Claim 1
1. A computer-implemented method for predicting a demand-shaping effect, comprising:
transferring, by a computer comprising a processor and a memory, historical supply chain data by conducting a randomized controlled A/B trial
deconfounding, by the computer, the historical supply chain data;
training, using cyclic boosting by the computer, one or more price-demand elasticity models using training data and the deconfounded historical supply chain data, wherein the training identifies one or more causal factors;
forecasting, using the one or more trained price-demand elasticity models by the computer, demand for an item at a location over a defined time period;
predicting, using the one or more trained price-demand elasticity models, one or more individual causal effects of a demand-shaping action by:
predicting, by the computer, using the one or more trained price-demand elasticity models, a first demand for the item at the location over the defined time period based, at least in part, on a first price; and
predicting, by the computer, using the one or more trained price-demand elasticity models, a second demand for the item at the location over the defined time period based, at least in part, on a second price; and
setting, by the computer, a price for the item at the location over the defined time period to shape product demand.
[Generic additional element]
+
Certain Methods Of Organizing Human Behavior, Math, Mental Steps
bold = idea not bold = apply it, generic additional element
Alice
clearinghouse
computer implemented
Bilski
hedge
computer implemented
Ultramercial
Advertising
computer implemented
Here
simulate demand via A/B testing for setting price
computer implemented
Simulating can be done without a device (Merriam-Webster 3a, below).
Or with a simulating device (Merriam-Webster (3b, below).
PNG
media_image2.png
283
759
media_image2.png
Greyscale
The claim simulates, determines or calculates an effect on demand
This is known by other names:
difference (determine what difference it would make to do this instead of that, A instead of B) or
marginal return (determine effect of doing this instead of that).
The claim is simulating demand.
Appellant Claims An Abstract Idea
What (amount of) difference does it make (A/B, e.g. hiring … not hiring)?
Given the Patent Eligibility Guidance (PEG), the claims steps set forth
Mental Processes such as
concepts performed in the human mind (including an observation, evaluation, judgement, opinion)
Certain Methods of Organizing Human Activity such as
fundamental economic principles or practices (including hedging, insurance, mitigating risk)
commercial or legal interactions (including agreements in the form of contracts; legal obligations; advertising, marketing or sales activities or behaviors; business relations)
managing personal behavior or relationships or interactions between people (including social activities, teaching, and following rules or instructions)
MENTAL PROCESS, Concepts Relating To Data Comparisons That Can Be Performed Mentally Or Are Analogous To Human Mental Work
LONG STANDING COMMERCIAL PRACTICE
ORGANIZING HUMAN ACTIVITY
Appellant computer-implements Long Standing Commercial Practice & Basic Economics.
Computer implemented hedging
Bilski
Computer implemented clearinghouse
Alice
Computer implemented mental process, long standing commercial practice, basic economics
HERE
The claim has the abstract idea of A/B testing.
The claim is directed to the idea of deciding a difference it would make doing this not that (“effect … demand”).
Deconfounding is to separate As from B. A/B testing is to deconfound.
PNG
media_image1.png
691
1295
media_image1.png
Greyscale
Here the data label is retail and demand. Applicant is retail and demand forecasting using causal inference machine learning with statistical background subtraction.
Calculating a number (price) is math, like statistical analysis in (SAP America v InvestPic (CAFC 2018). Here, the number relates to marketing, instead of investment there (SAP America v InvestPic (CAFC 2018) p.10 slip opinion).
Still further the limitation is math, calculation based on numbers. The claim presents a calculation based on another calculation, and data gathering, not significantly more.
The independent claims implement the abstract idea by generic computer, generic storage, generic storage, processor. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the claims are directed to an abstract idea with additional generic computer elements do not add a meaningful limitation to the abstract idea because they would be generic in any computer implementation. The claims in ordered combination are just the abstract idea implemented on a computer, the ordered combination spelling out how to computer implement it, Enfish.
Similar to the clearinghouse in Alice and the computer implemented hedge in Bilski, here the idea is applied generally as pointed out by Applicant’s Specification
Prong 1 answered “YES”, the next question in Prong 2 is whether there is an integrated practical application. This judicial exception is not integrated into a practical application.
Applicant takes an idea and then applies it with generic additional elements generally applied --with computer and machine learning.
In particular, the claim recites additional element – computer implemented, computer readable disk or storage, storage device to perform the claim steps. The elements are recited at a high-level of generality (e.g. generic processor performing a generic computer function) such that it amounts no more than mere instructions to apply the exception using a generic computer component. Accordingly, these additional elements do not integrate the abstract idea into a practical application for lack of any meaningful limits on practicing the abstract idea. Applicant uses steps that can be done in the mind followed by extra-solution activity (display). The steps are computer-implemented, but one could do the calculations with pen and paper, abacus, slide-rule etc. The additional elements present only a particular technological environment.
The additional elements are not sufficient to amount to significantly more than the judicial exception because the claims do not provide improvements to another technology or technical field, improvements to the functioning of the computer itself, and do not provide meaningful limitations beyond general linking the use of an abstract idea to a particular technological environment. The limitations (those beyond the abstract idea) do not improve the technical field that the abstract idea limitations invoke. Moreover, these generic limitations do not constitute significantly more because they are simply an attempt to limit the abstract idea to a particular technological environment, not meaningful limitations beyond generally linking the use of an abstract idea to a particular technological environment. See Alice Corp p 16 of slip op. noting that none of the hardware recited "offers a meaningful limitation beyond generally linking ‘the use of the [method] to a particular technological environment', that is implementation via computers" (citing Bilski 561 US at 610).
The limitation of machine learning is a process that under its broadest reasonable interpretation covers performance of the limitation in the mind, but for the recitation of generic computer
Dependent claims
CLAIM 2 9 16
2. The computer-implemented method of claim 1, wherein the historical supply chain data is deconfounded using independence weighting with inverse propensity scores.
CLAIM 3 10 17
3. The computer-implemented method of claim 1, wherein the demand-shaping action further comprises modifying one or more promotion variables to evaluate one or more promotional strategies.
CLAIM 4 11 18
4. The computer-implemented method of claim 1, wherein one or more of the one or more individual causal effects are horizon-independent.
CLAIM 5 12 19
5. The computer-implemented method of claim 1, wherein the one or more individual causal effects comprise parameters corresponding to one or more of: one or more multiplicative effects in one or more first feature bins and one or more different price elasticities in one or more second feature bins.
CLAIM 6 13 20
6. The computer-implemented method of claim 1, wherein the demand-shaping action comprises optimization of one or more of: gross profit, net revenue and maximum product sales.
CLAIM 7 14
7. The computer-implemented method of claim 1, further comprising: controlling, by the computer, one or more product sales by setting one or more product prices at one or more specific values.
CLAIM 2 9 16 the idea itself
CLAIM 3 10 17 the idea itself
CLAIM 4 11 18 the idea itself, and description of data
CLAIM 5 12 18 the idea itself
CLAIM 6 13 20 the idea itself
CLAIM 7 14 the idea itself
Step 2b
Applicant takes an idea and then applies it with generic additional elements generally applied -- with computer and machine learning.
Viewed as a whole, the claim elements do not provide meaningful limitations to transform the abstract idea into a patent eligible application of the abstract idea such that the claims amount to significantly more than the abstract idea itself. The claim limitations do not improve upon the technical field that the abstract idea is applied nor do they improve upon any other technical field. The claimed limitations do not improve upon the functioning of the computer itself. Therefore, the claims are rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
The additional element(s) or combination of elements in the claim(s) other than the abstract idea amount(s) to a ‘computer’, ‘memory’, ‘processor’ ‘server’ which use generic elements, MPEP 2016.05(d). Applicant specification says additional elements are generic.
The claim limitations alone or in ordered combination do not improve upon the technical field to which the abstract idea is applied nor do they improve upon any other technical field. The claimed limitations do not improve upon the functioning of any device itself. Wiley Encyclopedia of Computer Science and Engineering (2009) is a general technical reference with these generic elements, which was already provided to Applicant. The reference is the kind a person of ordinary skill in the art would have “hanging on their wall“, e.g. as a pdf shortcut or icon on wallpaper of one’s computer. Display (presentation) is mentioned 427 times includes display (Wiley p.2261), memory at p. 2263 (mentioned 1700+times in Wiley), database, server p.125, server 610 times (at least e.g. p.1982), processor 639 times (e.g. p. 1242-1243), database 1728 times (e.g. p.1253), storage medium (e.g. p.131), computer (3553 times, e.g. p.283), network (at least p.1700-1707), interface (770 times at least p.1700-1707). The extra-solution activity (display in Wiley).
The additional elements alone or in combination are not sufficient to amount to significantly more than the judicial exception because the claims do not provide improvements to another technology or technical field, improvements to the functioning of the computer itself, and do not provide meaningful limitations beyond generic linking use of an abstract idea to a particular technological environment. Additionally, the claims are directed to an abstract idea with additional generic computer elements that do not add meaningful limitations to the abstract idea because they require no more than a generic computer to perform generic computer functions that are generic activities previously known to the industry. Moreover, these generic limitations do not lead to an integrated practical application because they are simply an attempt to limit the abstract idea to a particular technological environment, not meaningful limitations beyond generally linking the use of an abstract idea to a particular technological environment. See Alice Corp p 16 of slip op. noting that none of the hardware recited "offers a meaningful limitation beyond generally linking ‘the use of the [method] to a particular technological environment', that is implementation via computers"(citing Bilski 561 US at 610). Viewed as a whole, these additional claim elements do not provide meaningful limitations to transform the abstract idea into a patent eligible application of the abstract idea such that the claims amount to an integrated practical application. The claim limitations do not improve upon the technical field that the abstract idea is applied nor do they improve upon any other technical field. The claimed limitations do not improve upon the functioning of the computer itself.
Moreover, these generic limitations do not constitute significantly more because they are simply an attempt to limit the abstract idea to a particular technological environment, not meaningful limitations beyond generally linking the use of an abstract idea to a particular technological environment. See Alice Corp p 16 of slip op. noting that none of the hardware recited "offers a meaningful limitation beyond generally linking ‘the use of the [method] to a particular technological environment', that is implementation via computers"(citing Bilski 561 US at 610).
Moreover, mere recitation of a machine or medium in the preamble does not make a claim statutory under 35 U.S.C. 101, as seen in the Board of Patent Appeals Informative Opinion Ex Parte Langemyr (Appeal 2008-1495). Moreover, mere mention of a piece of a computer or processing device does not confer patentability. Alice Corporation Pty. Ltd. v CLS Bank International ("Alice Corp") 573 US __ (2014). Incorporating the two-step test espoused in its recent decision in Mayo v. Prometheus 566 U.S. ___ (2012), the Court describes a first inquiry as to whether the claims at issue are directed to a patent-ineligible concept. If so, the Court requires a second inquiry as to whether the elements, individually or in combination, “transform” the nature of the claims into a patent-eligible invention. The Court described this second step as a search for an inventive concept, “i.e., an element or combination sufficient to ensure that the patent in practice amounts to significantly more than a patent upon the [ineligible concept] itself.”
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements merely detail generic elements that implement the abstract idea. The generically recited computer elements do not add a meaningful limitation to the abstract idea. The additional element merely instruct that the execution of the abreact idea occurs on other generic technology, but does not offer any disclosure of any additional technology beyond the abstract idea itself. Moreover, the claim steps as an ordered combination do not present significantly more. The claims are not directed to an improvement in computer functionality like in Enfish v Microsoft, but rather to an abstract idea. The claims "do nothing more than spell out what it means to 'apply it on a computer'”, Intellectual Ventures I 792 F.3d p1371 (citing Alice). Nowhere in the claims or specification is there any indication that the computer, processor, medium do something to improved hardware functionality.
The further elements of the claims are merely directed to further abstract ideas and in ordered combination pose a list of abstract ideas, and invoke merely as a tool what is generic. There is no improvement in these items, but rather they are invoked as a tool to solve a business problem (targeted marketing), not a technical problem.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements merely detail generic computer processors and software that implement the abstract idea. The generically recited computer elements do not add a meaningful limitation to the abstract idea because they would be generic in any computer implementation. The additional element merely instruct that the execution of the abstract idea occurs on other generic technology, but does not offer any disclosure of any additional technology beyond the abstract idea itself. Moreover, the claim steps as an ordered combination do not present significantly more. The claims are not directed to an improvement in computer functionality like in Enfish v Microsoft, but rather to an abstract idea. The claims "do nothing more than spell out what it means to 'apply it on a computer'”, Intellectual Ventures I 792 F.3d p1371 (citing Alice). Nowhere in the claims or specification is there any indication that the computer, processor, storage do something nongeneric such that Applicant has improved computer functionality. Applicant presents an idea for which computers are invoked as a tool.
To find some inventive concept, one can look to Applicant's own words in Spec ¶ 2. There, he states the problem addressed is marketing forecasting, RETAIL AND DEMAND FORECASTING.
Here, the claims neither improve the technological infrastructure nor provide particular solutions to challenges. Rather, in ordered combination the claim limitations spell out the steps of calculating using generic technology (storage, computer, storage, processor – at a high level of generality).
In addition to these indisputably generic features, Applicant did not invent any of those features, and the claims do not recite them in a manner that produces a result that overrides the generic use of these known features. DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258 (Fed. Cir. 2014). When viewed as an ordered combination, the proposed claims recite no more than the sort of “perfectly” generic computer components employed in a customary manner that we have held insufficient to transform the abstract idea into a patent-eligible invention. Intellectual Ventures I LLC v. Symantec Corp., 838 F.3d 1307, 1321 (Fed. Cir. 2016). The claims fail step 2b too.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for obviousness rejections in this Office Action:
a) A patent may not be obtained though the invention is not identically disclosed or described as set forth in section 102 of this title, if the differences between the subject matter sought to be patented and the prior art are such that the subject matter as a whole would have been obvious at the time the invention was made to a person having ordinary skill in the art to which said subject matter pertains. Patentability shall not be negatived by the manner in which the invention was made
From www.en.Wikipedia.org/wiki/Confounding
PNG
media_image4.png
260
218
media_image4.png
Greyscale
MPEP 2123: “The use of patents as references is not limited to what the patentees describe as their own inventions or to the problems with which they are concerned. They are part of the literature of the art, relevant for ALL they contain.” In re Heck, 699 F.2d 1331 (Fed. Cir. 1983) A reference may be relied upon for ALL that it would have reasonably suggested to one having ordinary skill the art, including nonpreferred embodiments. Merck & Co. v. Biocraft Laboratories, 874 F.2d 804, 10 USPQ2d 1843 (Fed. Cir.), cert. denied, 493 U.S. 975 (1989).”
Examiner references already provided to applicant
Claims rejected under 35 USC 103 over
Wick (NPL) in view of
Lei US 20190188536 in view of
Wick2 (NPL) in view of
Panlinginis US 20190156357 (NPL)
CLAIM 1 8 15
CLAIM 3 10 17
CLAIM 4 11 18
CLAIM 5 12 18
CLAIM 7 14 20
PNG
media_image6.png
795
1079
media_image6.png
Greyscale
PNG
media_image7.png
980
1103
media_image7.png
Greyscale
CLAIM 1 8 15
1. A computer-implemented method for predicting a demand-shaping effect, comprising:
transferring, by a computer comprising a processor and a memory, historical supply chain data;
deconfounding, by the computer, the historical supply chain data by conducting a randomized controlled A/B trial
training, using cyclic boosting by the computer, one or more price-demand elasticity models using training data and the deconfounded historical supply chain data, wherein the training identifies one or more causal factors;
forecasting, using the one or more trained price-demand elasticity models by the computer, demand for an item at a location over a defined time period;
predicting, using the one or more trained price-demand elasticity models, one or more individual causal effects of a demand-shaping action by:
predicting, by the computer, using the one or more trained price-demand elasticity models, a first demand for the item at the location over the defined time period based, at least in part, on a first price; and
predicting, by the computer, using the one or more trained price-demand elasticity models, a second demand for the item at the location over the defined time period based, at least in part, on a second price; and
setting, by the computer, a price for the item at the location over the defined time period to shape product demand.
Felix Wick: From the Life of a Data Scientist at least 16:00-22:00
https://www.youtube.com/watch?v=Fo0Ne2pYWW4
PNG
media_image8.png
818
1294
media_image8.png
Greyscale
PNG
media_image6.png
795
1079
media_image6.png
Greyscale
Deconfounding ≈ extract “patterns”.
Felix Wick: From the Life of a Data Scientist - YouTube 20:00-21:00 https://www.youtube.com/watch?v=Fo0Ne2pYWW4 “leave some out …. … this is really important … one should always think about if one is developing a new method …. We are coming to the core …. This is something probably everyone knows”
Deconfounding ≈ Wick’s extract “patterns”.
It would have been obvious looking at Wick to search for more by the same guy on the same subject and find Wick2’s deconfounding
Wick2 (NPL: Felix Wick, Michael Feindt, Wick2 Baryon Spectroscopy (Year:2011))
Wick2, 2.1
Wick2 starting at Ch. 2
It would have been obvious to combine Wick/Wick2.
A person of ordinary skill in the art wanting to learn about the Life of A Data Scientist would see Wick and consult the works of the same author and find Wick2.
A person of ordinary skill in the art wanting to learn about the Life of A Data Scientist would see Wick, see that a Data Scientist can use the methods just as easily on demand forecasting (21:31) as on physics. It would have been obvious at the time of filing to combine primary reference and the additional reference. One of ordinary skill in the art would have been reasonably prompted to make the combination because the advantage of using influence in an advertising system. One of ordinary skill in the art would have recognized that the results of the combination were predictable. Therefore all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art at the time of the invention. This is Combining Prior Art Elements According to Known Methods.
PNG
media_image9.png
856
1295
media_image9.png
Greyscale
But for deconfounding,
this claim is a repeat MPEP 2144.04 -- doing what’s already done but repeated (second). It’s shown already in art cited against independent claim; e.g. Wick 16:00-18:00. Wick tells listener to repeat, saying “exploit” for one or more causal factors and repeatedly predict or shape demand.
Besides, Wick shows
NOT EXPLICIT in Wick is exact term external causal factors but Wick shows the point in substance (e.g. catalogue 17:04)
Lei US 20190188536
(LEI’536, FIG. 8; ¶¶ [0002] and [0026]: a network of facilities/retail stores that together deliver products to consumers is commonly referred to as a "supply chain" network; a specialized point of sale ("POS") terminal 100 gaenerates the transactional data and historical sales data, e.g., data concerning transactions of each item/SKU at each retail store, used to forecast demand) (LEI’536, FIG. 5; ¶¶ [0065]-[0076]: use the optimized feature sets as input to forecasting algorithms to generate forecasting models; for each training dataset D(i) extracted/pooled from historical sale/supply chain data, one of the following machine learning algorithms are used to produce the model M(i): linear regression, Support Vector Machine ("SVM"), and Artificial Neural Networks ("ANN"); to forecast future1 demand, for each data point x, M(i) is iteratively applied to the input to produce the final results y as follows: y = sum( f(M(i), x) * w'(i) ), where y is the forecasted demand, and f is the function to create the forecast, corresponding to the model)
(LEI’536, FIGS. 6 and 7A-B; ¶¶ [0083]-[0089]: FIG. 6 shows promotion effects for each promotion 1-10, which are product/location specific but not time period specific; FIGS. 7A-B show a comparison of predictions for each week during a 13 week sales period and for a given store/SKU, wherein row 701 provides a baseline demand, row 702 provides seasonality, and rows 702-712 provide an indication (as indicated by an "X"), for each promotion, whether that promotion was active during the corresponding week; row 713 indicates actual sales during the corresponding time period; for the prediction of promotion effects, row 714 indicates the predictions of sales for each week from round A, in which all data points are used using known methods of using all available data; rows 715-719 indicates the predictions/estimated using each of rounds 1-5 for each time period, and row 720 is the average prediction from Rounds 1-5)
NOT EXPLICT IN Wick is shaping
Panlinginis US 20190156357 teaches a system and a method related to demand forecasting (Palinginis, ¶ [0001]), wherein rendering/render/renders, for display on a user interface, a demand prediction feature explanation visualization (Palinginis, 116 in FIGS. 1 and 5A-B; ¶¶ [0044] and [0086]: the predicted demand may be presented to a user through a graphical user interface that enables the user to interactively and iteratively select or refine one or more parameters of the promotion in order to view or adjust factors relevant to the proposed promotion; graphical user interface 500 may be presented on a computer system as a user-friendly, explicit visualization of the predicted demand values generated by of the blended models).
(Palinginis, 118 in FIGS. 1 and 5A-B; ¶¶ [0044] and [0087]-[0091]: the predicted demand may be presented to a user through a graphical user interface that enables the user to interactively and iteratively select or refine one or more parameters of the promotion in order to view or adjust factors relevant to the proposed promotion; graphical user interface 500 may include a parameter input screen 510 configured to enable the user to select or define promotion parameters the user would like to model, e.g., a plurality of parameters for defining a data set, such as sales data related to the SKUs of a particular department/store, target product, and terms of the proposed promotion; one or more promotion analyses may be displayed in a summary interface 520 or a more detailed promotion analysis display 530 for review by the user, e.g., the user may be able to select a promotion identifier 522 and be presented with a graphical representation of predicted demand from the model represented in a business significant series of predicted demand values; also presenting one or more interactive features for enabling the user to drill down into the analysis, see the data from different perspectives, and/or provide other utilities for visualizing, manipulating, or exporting the predicted demand values; e.g., time selector 532 may indicate a plurality of time segments, such as by week or combined for the entire period of the promotion, that may be selected for viewing the performance of the promotion in the various segments; presentation selector 534 may provide a selection of visualization settings for the data, such as waterfall view or table view; metric selector 536 may provide a selection of business metrics against which the modeled promotion can be displayed, such as incremental adjusted margin, incremental sales, and incremental variable contribution of each particular component of the promotion as represented in predicted demand values).
Wick (and LEI’536 ) and Palinginis are analogous art because they are from the same field of endeavor, a system and a method related to demand forecasting. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to apply the teaching of Palinginis to Wick (and LEI’536 ). Motivation for doing so would improve the predicted demand to meet one or more business objectives (Palinginis, ¶ [0044]).
Visualization (at least Wick 43:38 indicates user interface)
It would have been obvious to combine Wick/Lei.
A person of ordinary skill in the art wanting to learn about the Life of A Data Scientist would see Wick, see that a Data Scientist can use the methods just as easily on demand forecasting (21:31) as on physics (Wick tells listener to use teaching from physics in demand prediction 21:00-22:00 Felix Wick: From the Life of a Data Scientist - YouTube). It would have been obvious at the time of filing to combine primary reference and the Lei. One of ordinary skill in the art would have been reasonably prompted to make the combination because the advantage of using influence in an advertising system. One of ordinary skill in the art would have recognized that the results of the combination were predictable. Therefore all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art at the time of the invention. This is Combining Prior Art Elements According to Known Methods.
And applying Data Science to Pricing, Promotion, Dynamic Cataloging, Dynamic Forecasting such as predicting Tomorrow’s Sales or an Insurance Claim instead of the arcane area of physics is obvious Design Incentives or Market Forces Prompting Variations.
This application of Data Science to Business Method instead of Physics is Simple Substitution
PNG
media_image10.png
834
1309
media_image10.png
Greyscale
Deconfounding ≈ Wick’s extract “patterns”.
It would have been obvious looking at Wick to search for more by the same guy on the same subject and find Wick2’s deconfounding
Wick2 (NPL: Felix Wick, Michael Feindt, Wick2 Baryon Spectroscopy (Year:2011))
Wick2, 2.1
Wick2 starting at Ch. 2
It would have been obvious to combine Wick/Wick2.
A person of ordinary skill in the art wanting to learn about the Life of A Data Scientist would see Wick and consult the works of the same author and find Wick2.
A person of ordinary skill in the art wanting to learn about the Life of A Data Scientist would see Wick, see that a Data Scientist can use the methods just as easily on demand forecasting (21:31) as on physics. It would have been obvious at the time of filing to combine primary reference and the additional reference. One of ordinary skill in the art would have been reasonably prompted to make the combination because the advantage of using influence in an advertising system. One of ordinary skill in the art would have recognized that the results of the combination were predictable. Therefore all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art at the time of the invention. This is Combining Prior Art Elements According to Known Methods.
And applying Data Science to Pricing, Promotion, Dynamic Cataloging, Dynamic Forecasting such as predicting Tomorrow’s Sales or an Insurance Claim instead of the arcane area of physics is obvious Design Incentives or Market Forces Prompting Variations.
This application of Data Science to Business Method is Simple Substitution
PNG
media_image11.png
825
1318
media_image11.png
Greyscale
PNG
media_image12.png
830
1302
media_image12.png
Greyscale
PNG
media_image13.png
680
1194
media_image13.png
Greyscale
PNG
media_image14.png
815
1293
media_image14.png
Greyscale
PNG
media_image15.png
921
1392
media_image15.png
Greyscale
PNG
media_image8.png
818
1294
media_image8.png
Greyscale
PNG
media_image16.png
857
1321
media_image16.png
Greyscale
PNG
media_image17.png
814
1317
media_image17.png
Greyscale
PNG
media_image18.png
888
1330
media_image18.png
Greyscale
PNG
media_image19.png
833
1322
media_image19.png
Greyscale
FYI Wikipedia A/B testing (examiner isn’t relying on Official Notice since Wick shows it)
PNG
media_image6.png
795
1079
media_image6.png
Greyscale
PNG
media_image1.png
691
1295
media_image1.png
Greyscale
CLAIM 3 10 17
3. The computer-implemented method of claim 1, wherein the demand-shaping action further comprises
O modifying one or more promotion variables to evaluate one or more promotional strategies.
NOT EXPLICT IN Wick is shaping
Panlinginis US 20190156357 teaches a system and a method related to demand forecasting (Palinginis, ¶ [0001]), wherein rendering/render/renders, for display on a user interface, a demand prediction feature explanation visualization (Palinginis, 116 in FIGS. 1 and 5A-B; ¶¶ [0044] and [0086]: the predicted demand may be presented to a user through a graphical user interface that enables the user to interactively and iteratively select or refine one or more parameters of the promotion in order to view or adjust factors relevant to the proposed promotion; graphical user interface 500 may be presented on a computer system as a user-friendly, explicit visualization of the predicted demand values generated by of the blended models).
(Palinginis, 118 in FIGS. 1 and 5A-B; ¶¶ [0044] and [0087]-[0091]: the predicted demand may be presented to a user through a graphical user interface that enables the user to interactively and iteratively select or refine one or more parameters of the promotion in order to view or adjust factors relevant to the proposed promotion; graphical user interface 500 may include a parameter input screen 510 configured to enable the user to select or define promotion parameters the user would like to model, e.g., a plurality of parameters for defining a data set, such as sales data related to the SKUs of a particular department/store, target product, and terms of the proposed promotion; one or more promotion analyses may be displayed in a summary interface 520 or a more detailed promotion analysis display 530 for review by the user, e.g., the user may be able to select a promotion identifier 522 and be presented with a graphical representation of predicted demand from the model represented in a business significant series of predicted demand values; also presenting one or more interactive features for enabling the user to drill down into the analysis, see the data from different perspectives, and/or provide other utilities for visualizing, manipulating, or exporting the predicted demand values; e.g., time selector 532 may indicate a plurality of time segments, such as by week or combined for the entire period of the promotion, that may be selected for viewing the performance of the promotion in the various segments; presentation selector 534 may provide a selection of visualization settings for the data, such as waterfall view or table view; metric selector 536 may provide a selection of business metrics against which the modeled promotion can be displayed, such as incremental adjusted margin, incremental sales, and incremental variable contribution of each particular component of the promotion as represented in predicted demand values).
Wick (and LEI’536 ) and Palinginis are analogous art because they are from the same field of endeavor, a system and a method related to demand forecasting. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to apply the teaching of Palinginis to Wick (and LEI’536 ). Motivation for doing so would improve the predicted demand to meet one or more business objectives (Palinginis, ¶ [0044]).
Visualization (at least Wick 43:38 indicates user interface)
It would have been obvious to combine Wick/Lei.
A person of ordinary skill in the art wanting to learn about the Life of A Data Scientist would see Wick, see that a Data Scientist can use the methods just as easily on demand forecasting (21:31) as on physics (Wick tells listener to use teaching from physics in demand prediction 21:00-22:00 Felix Wick: From the Life of a Data Scientist - YouTube). It would have been obvious at the time of filing to combine primary reference and the Lei. One of ordinary skill in the art would have been reasonably prompted to make the combination because the advantage of using influence in an advertising system. One of ordinary skill in the art would have recognized that the results of the combination were predictable. Therefore all the claimed elements were known in the prior art and one skilled in the art could have combined the elements as claimed by known methods, and the combination would have yielded nothing more than predictable results to one of ordinary skill in the art at the time of the invention. This is Combining Prior Art Elements According to Known Methods.
And applying Data Science to Pricing, Promotion, Dynamic Cataloging, Dynamic Forecasting such as predicting Tomorrow’s Sales or an Insurance Claim instead of the arcane area of physics is obvious Design Incentives or Market Forces Prompting Variations.
This application of Data Science to Business Method instead of Physics is Simple Substitution
CLAIM 4 11 18
4. The computer-implemented method of claim 1, wherein one or more of the one or more individual causal effects are horizon-independent.
Felix Wick: From the Life of a Data Scientist 19:00-20:00
Felix Wick: From the Life of a Data Scientist at least 16:00-22:00
https://www.youtube.com/watch?v=Fo0Ne2pYWW4
CLAIM 5 12 18
5. The computer-implemented method of claim 1, wherein the one or more individual causal effects comprise
O parameters corresponding to one or more of: one or more multiplicative effects in one or more first feature bins and one or more different price elasticities in one or more second feature bins.
Felix Wick: From the Life of a Data Scientist at least 16:00-22:00
https://www.youtube.com/watch?v=Fo0Ne2pYWW4
Wick: From the Life of a Data Scientist at least 16:00-22:00 “exploit” ≈ increase, alter, adjust, alter
https://www.youtube.com/watch?v=Fo0Ne2pYWW4
“how different variables behave” says Wick 18:152 and visualize with blood, heat map
see also
Lei US 20190188536
(LEI’536, 870 in FIG. 8; ¶ [0095]: a product forecasting system 870 that forecasts future product demand for one or more products at one or more retail stores) (LEI’536, ¶¶ [0032]-[0039]: use one or more trained models generated from one or more different algorithms and one or more feature sets, and may ultimately combined the forecast from multiple trained models to arrive at a final demand forecast, wherein trained models can include trained linear regression models or supervised machine learning techniques, such as decision or regression trees, Support Vector Machines ("SVM") or neural networks) (LEI’536, ¶¶ [0030] and [0064]: use the automatically determined one or more feature sets to generate one or more trained models generated from one or more different algorithms in order to determine a sales forecast or a demand forecast to achieve a more accurate prediction and a better understanding of the impact a promotion has on demand with less processing cycles)
(LEI’536, 100 in FIG. 1; ¶ [0026]: a specialized point of sale ("POS") terminal 100 generates the transactional data and historical sales data, e.g., data concerning transactions of each item/SKU at each retail store, used to forecast demand) (LEI’536, 202 in FIG. 2; 502 in FIG. 5; ¶¶ [0031], [0041]-[0044], and [0066]-[0068]: historical sales/performance data may include, for example, a number of units of an item sold in each of a plurality of past retail periods as well as associated promotion data; historical item sales data is received for all items for all stores for a particular class/category of products, or for only a single item of interest; all the valid data points are pooled to form a training dataset D with N data points at a given aggregated level; the aggregate levels are typically picked to be low enough to capture the low level details of the merchandise, but also high enough that the data pool is rich enough for a robust estimation of the promotion effects) (LEI’536, FIG. 8; ¶ [0096]: inventory system 820 stores inventory and provides transportation logistics to deliver items to stores 801-804 using trucks 810-813 or some other transportation mechanisms, wherein the inventory system 820 uses input from forecasting system 870 to determine levels of inventories and the amount and timing of the delivery of items to stores 801-804 for a specialized inventory control; ¶ [0099]: each retail location 801-804 sends sales data and historic forecast data to forecasting system 870, wherein the sales data includes inventory depletion statistics for each item, or SKU/UPC for each sales period, typically days, in the previous sales cycles (i.e. weeks), typically 4-7 weeks of inventory cycles)
(LEI’536, FIGS. 3 and 4A; ¶¶ [0041], [0046], and [0063]: historical item sales data is received for all items for all stores for a particular class/category of products, or for only a single item of interest; e.g., the class/category can be "yogurt", "coffee" or "milk", wherein each class has one or more subclasses, all the way down to the SKU or Universal Product Code ("UPC") level, which would be each individual item for sale; e.g., for the class of yogurt, a sub-class could be each brand of yogurt, and further sub-classes could be flavor, size, type ( e.g., Greek or regular), down to an SKU which would correspond to every individual different type of yogurt item sold; the determined feature set that is generated from the functionality of FIG. 2 is for a given product (i.e., category at a given location, such as yogurt in the Baltimore, MD area); i.e., historical item sales data are binning/categorizing according to feature categories, e.g., "yogurt", "coffee" or "milk" as well as "location")
(LEI’536, FIGS. 5-6 and 7A-B; ¶¶ [0068]-[0072], [0076], [0079]-[0083], and [0088]: for each round/iteration, the promotion effects/factors for each promotion/feature is determined during each sales period that the promotion is in effect (e.g., each week of training dataset/each bin); each round/iteration can use linear regression, SVM, neural networks, etc.; after each round/iteration a set of model parameters are generated that describe the training dataset/bin used; to forecast future demand, for each data point x, M(i) is iteratively applied to the input to produce the final results y as follows: y = sum( f(M(i), x) * w'(i) ), where y is the forecasted demand, and f is the function to create the forecast, corresponding to the model) (LEI’536, 208-216 in FIG. 2; ¶¶ [0048]-[0052]: the iterative process will be completed and the optimized feature set is determined when the early stopping metric or the maximum number of iterations has been reached; an algorithm is trained using the training data set from sales history data and using the features of feature test set S (i.e., both the mandatory and optional features) to generate a trained algorithm/model)
(LEI’536, ¶ [0031]: historical sales/performance data may include, for example, a number of units of an item sold in each of a plurality of past retail periods as well as associated promotion data (i.e., for each retail period, which promotions were in effect for that period); i.e., in addition to historical item sales data are binning/categorizing according to feature categories, they are also binning/categorizing according to a retail period) (LEI’536, FIG. 7A-B; ¶¶ [0088]-[0089]: a time-period specific promotion effects for each week during a 13 week sales period; i.e., binning a feature of time period (total of 13 week sales period), wherein each bin has 1 week period of time – the same width)
(LEI’536, FIG. 8; ¶¶ [0002] and [0026]: a network of facilities/retail stores that together deliver products to consumers is commonly referred to as a "supply chain" network; a specialized point of sale ("POS") terminal 100 generates the transactional data and historical sales data, e.g., data concerning transactions of each item/SKU at each retail store, used to forecast demand) (LEI’536, FIG. 5; ¶¶ [0065]-[0076]: use the optimized feature sets as input to forecasting algorithms to generate forecasting models; for each training dataset D(i) extracted/pooled from historical sale/supply chain data, one of the following machine learning algorithms are used to produce the model M(i): linear regression, Support Vector Machine ("SVM"), and Artificial Neural Networks ("ANN"); to forecast future2 demand, for each data point x, M(i) is iteratively applied to the input to produce the final results y as follows: y = sum( f(M(i), x) * w'(i) ), where y is the forecasted demand, and f is the function to create the forecast, corresponding to the model)
(LEI’536, FIGS. 6 and 7A-B; ¶¶ [0083]-[0089]: FIG. 6 shows promotion effects for each promotion 1-10, which are product/location specific but not time period specific; FIGS. 7A-B show a comparison of predictions for each week during a 13 week sales period and for a given store/SKU, wherein row 701 provides a baseline demand, row 702 provides seasonality, and rows 702-712 provide an indication (as indicated by an "X"), for each promotion, whether that promotion was active during the corresponding week; row 713 indicates actual sales during the corresponding time period; for the prediction of promotion effects, row 714 indicates the predictions of sales for each week from round A, in which all data points are used using known methods of using all available data; rows 715-719 indicates the predictions/estimated using each of rounds 1-5 for each time period, and row 720 is the average prediction from Rounds 1-5).
LEI’536 further discloses a non-transitory computer-readable medium (LEI’536, 14 in FIG. 1; ¶¶ [0023]-[0024]: a memory 14 can be comprised of any combination of random access memory ("RAM"), read only memory ("ROM"), static storage such as a magnetic or optical disk, or any other type of computer readable media) embodied with software (LEI’536, FIG. 1; ¶ [0026]: memory 14 stores software modules that provide functionality when executed by processor 22), wherein the software, when executed to perform the method described above (LEI’536, ¶ [0040]: the functionality is implemented by software stored in memory or other computer readable or tangible medium, and executed by a processor).
(LEI’536, FIG. 8; ¶¶ [0002] and [0026]: a network of facilities/retail stores that together deliver products to consumers is commonly referred to as a "supply chain" network; a specialized point of sale ("POS") terminal 100 generates the transactional data and historical sales data, e.g., data concerning transactions of each item/SKU at each retail store, used to forecast demand) (LEI’536, FIG. 5; ¶¶ [0065]-[0076]: use the optimized feature sets as input to forecasting algorithms to generate forecasting models; for each training dataset D(i) extracted/pooled from historical sale/supply chain data, one of the following machine learning algorithms are used to produce the model M(i): linear regression, Support Vector Machine ("SVM"), and Artificial Neural Networks ("ANN"); to forecast future3 demand, for each data point x, M(i) is iteratively applied to the input to produce the final results y as follows: y = sum( f(M(i), x) * w'(i) ), where y is the forecasted demand, and f is the function to create the forecast, corresponding to the model)
(LEI’536, FIGS. 6 and 7A-B; ¶¶ [0083]-[0089]: FIG. 6 shows promotion effects for each promotion 1-10, which are product/location specific but not time period specific; FIGS. 7A-B show a comparison of predictions for each week during a 13 week sales period and for a given store/SKU, wherein row 701 provides a baseline demand, row 702 provides seasonality, and rows 702-712 provide an indication (as indicated by an "X"), for each promotion, whether that promotion was active during the corresponding week; row 713 indicates actual sales during the corresponding time period; for the prediction of promotion effects, row 714 indicates the predictions of sales for each week from round A, in which all data points are used using known methods of using all available data; rows 715-719 indicates the predictions/estimated using each of rounds 1-5 for each time period, and row 720 is the average prediction from Rounds 1-5)
(Palinginis, 116 in FIGS. 1 and 5A-B; ¶¶ [0044] and [0086]: the predicted demand may be presented to a user through a graphical user interface that enables the user to interactively and iteratively select or refine one or more parameters of the promotion in order to view or adjust factors relevant to the proposed promotion; graphical user interface 500 may be presented on a computer system as a user-friendly, explicit visualization of the predicted demand values generated by of the blended models).
CLAIM 7 14 20
7. The computer-implemented method of claim 1, further comprising:
O controlling, by the computer, one or more product sales by setting one or more product prices at one or more specific values.
Felix Wick: From the Life of a Data Scientist 16:00-18:00
https://www.youtube.com/watch?v=Fo0Ne2pYWW4
PNG
media_image9.png
856
1295
media_image9.png
Greyscale
Wick at least 16:00-20:00
“need to have good models … to understand correlation to the data … understand what happens to it … how correlated to each other …. What would be interesting … what is the correlation to the target and so on … this means you should do 2 dimensional distribution … check … how different variables behave …you can do this with profile blood heat map or whatever … so one example would be something like dis” says Wick 18:152 and visualize with blood, heat map and “adjust features … profile “
Wick 18:00 what correlations are in the data … correlation to the target, do 2d distribution to understand how factors behave”
Wick Visualization ≈ display, Wick 35:00-40:00 send to customer
PNG
media_image11.png
825
1318
media_image11.png
Greyscale
PNG
media_image12.png
830
1302
media_image12.png
Greyscale
Felix Wick: From the Life of a Data Scientist at least 16:00-22:00
https://www.youtube.com/watch?v=Fo0Ne2pYWW4
Claims rejected under 35 USC 103 over Wick/Lei/Wick2/Panlinginis in view of Liu US 20200401643
CLAIM 2 9 16
CLAIM 2 9 16
2. The computer-implemented method of claim 1, wherein the historical supply chain data is deconfounded using independence weighting with inverse propensity scores.
Liu US 20200401643 Abstract ¶ 20 21 77 78 80 85 86 Fig 11 and text
It would have been obvious to combine Wick and Liu since Wick already teaches deconfounding, and it would have been obvious to consult the works of colleagues and find Liu and combine the two for deconfounding by use of inverse propensity score. This is Combining Prior Art Elements According to Known Methods
Claims rejected under 35 USC 103 over Wick/Lei/Wick2/Panlinginis in view of Flach (NPL)
CLAIM 6 13 20
CLAIM 6 13 19
6. The computer-implemented method of claim 1, wherein the demand-shaping action comprises
O optimization of one or more of: gross profit, net revenue and maximum product sales.
Flach (NPL: Machine Learning and Knowledge Discovery in Databases (Year: 2012) p.537-541
[Wingdings font/0xA2] performing, with the server, one or more regularization and smoothing techniques, incorporating the defined one or more specific feature sequences, during the training of the first machine learning model
Flach (NPL: Machine Learning and Knowledge Discovery in Databases (Year: 2012) p.537-541
It would have been obvious to combine Wick and Flach since Wick already teaches machine learning for optimization, and it would have been obvious to consult the works of colleagues and find Flach and combine the two for optimization of gross profit, net revenue, max sales. This is Combining Prior Art Elements According to Known Methods
PNG
media_image6.png
795
1079
media_image6.png
Greyscale
PNG
media_image7.png
980
1103
media_image7.png
Greyscale
Wick: From the Life of a Data Scientist at least 16:00-22:00 “exploit” ≈ increase, alter, adjust, alter
https://www.youtube.com/watch?v=Fo0Ne2pYWW4
“how different variables behave” says Wick 18:152 and visualize with blood, heat map
see also
Lei US 20190188536
(LEI’536, 870 in FIG. 8; ¶ [0095]: a product forecasting system 870 that forecasts future product demand for one or more products at one or more retail stores) (LEI’536, ¶¶ [0032]-[0039]: use one or more trained models generated from one or more different algorithms and one or more feature sets, and may ultimately combined the forecast from multiple trained models to arrive at a final demand forecast, wherein trained models can include trained linear regression models or supervised machine learning techniques, such as decision or regression trees, Support Vector Machines ("SVM") or neural networks) (LEI’536, ¶¶ [0030] and [0064]: use the automatically determined one or more feature sets to generate one or more trained models generated from one or more different algorithms in order to determine a sales forecast or a demand forecast to achieve a more accurate prediction and a better understanding of the impact a promotion has on demand with less processing cycles)
(LEI’536, 100 in FIG. 1; ¶ [0026]: a specialized point of sale ("POS") terminal 100 generates the transactional data and historical sales data, e.g., data concerning transactions of each item/SKU at each retail store, used to forecast demand) (LEI’536, 202 in FIG. 2; 502 in FIG. 5; ¶¶ [0031], [0041]-[0044], and [0066]-[0068]: historical sales/performance data may include, for example, a number of units of an item sold in each of a plurality of past retail periods as well as associated promotion data; historical item sales data is received for all items for all stores for a particular class/category of products, or for only a single item of interest; all the valid data points are pooled to form a training dataset D with N data points at a given aggregated level; the aggregate levels are typically picked to be low enough to capture the low level details of the merchandise, but also high enough that the data pool is rich enough for a robust estimation of the promotion effects) (LEI’536, FIG. 8; ¶ [0096]: inventory system 820 stores inventory and provides transportation logistics to deliver items to stores 801-804 using trucks 810-813 or some other transportation mechanisms, wherein the inventory system 820 uses input from forecasting system 870 to determine levels of inventories and the amount and timing of the delivery of items to stores 801-804 for a specialized inventory control; ¶ [0099]: each retail location 801-804 sends sales data and historic forecast data to forecasting system 870, wherein the sales data includes inventory depletion statistics for each item, or SKU/UPC for each sales period, typically days, in the previous sales cycles (i.e. weeks), typically 4-7 weeks of inventory cycles)
(LEI’536, FIGS. 3 and 4A; ¶¶ [0041], [0046], and [0063]: historical item sales data is received for all items for all stores for a particular class/category of products, or for only a single item of interest; e.g., the class/category can be "yogurt", "coffee" or "milk", wherein each class has one or more subclasses, all the way down to the SKU or Universal Product Code ("UPC") level, which would be each individual item for sale; e.g., for the class of yogurt, a sub-class could be each brand of yogurt, and further sub-classes could be flavor, size, type ( e.g., Greek or regular), down to an SKU which would correspond to every individual different type of yogurt item sold; the determined feature set that is generated from the functionality of FIG. 2 is for a given product (i.e., category at a given location, such as yogurt in the Baltimore, MD area); i.e., historical item sales data are binning/categorizing according to feature categories, e.g., "yogurt", "coffee" or "milk" as well as "location")
(LEI’536, FIGS. 5-6 and 7A-B; ¶¶ [0068]-[0072], [0076], [0079]-[0083], and [0088]: for each round/iteration, the promotion effects/factors for each promotion/feature is determined during each sales period that the promotion is in effect (e.g., each week of training dataset/each bin); each round/iteration can use linear regression, SVM, neural networks, etc.; after each round/iteration a set of model parameters are generated that describe the training dataset/bin used; to forecast future demand, for each data point x, M(i) is iteratively applied to the input to produce the final results y as follows: y = sum( f(M(i), x) * w'(i) ), where y is the forecasted demand, and f is the function to create the forecast, corresponding to the model) (LEI’536, 208-216 in FIG. 2; ¶¶ [0048]-[0052]: the iterative process will be completed and the optimized feature set is determined when the early stopping metric or the maximum number of iterations has been reached; an algorithm is trained using the training data set from sales history data and using the features of feature test set S (i.e., both the mandatory and optional features) to generate a trained algorithm/model)
(LEI’536, ¶ [0031]: historical sales/performance data may include, for example, a number of units of an item sold in each of a plurality of past retail periods as well as associated promotion data (i.e., for each retail period, which promotions were in effect for that period); i.e., in addition to historical item sales data are binning/categorizing according to feature categories, they are also binning/categorizing according to a retail period) (LEI’536, FIG. 7A-B; ¶¶ [0088]-[0089]: a time-period specific promotion effects for each week during a 13 week sales period; i.e., binning a feature of time period (total of 13 week sales period), wherein each bin has 1 week period of time – the same width)
(LEI’536, FIG. 8; ¶¶ [0002] and [0026]: a network of facilities/retail stores that together deliver products to consumers is commonly referred to as a "supply chain" network; a specialized point of sale ("POS") terminal 100 generates the transactional data and historical sales data, e.g., data concerning transactions of each item/SKU at each retail store, used to forecast demand) (LEI’536, FIG. 5; ¶¶ [0065]-[0076]: use the optimized feature sets as input to forecasting algorithms to generate forecasting models; for each training dataset D(i) extracted/pooled from historical sale/supply chain data, one of the following machine learning algorithms are used to produce the model M(i): linear regression, Support Vector Machine ("SVM"), and Artificial Neural Networks ("ANN"); to forecast future4 demand, for each data point x, M(i) is iteratively applied to the input to produce the final results y as follows: y = sum( f(M(i), x) * w'(i) ), where y is the forecasted demand, and f is the function to create the forecast, corresponding to the model)
(LEI’536, FIGS. 6 and 7A-B; ¶¶ [0083]-[0089]: FIG. 6 shows promotion effects for each promotion 1-10, which are product/location specific but not time period specific; FIGS. 7A-B show a comparison of predictions for each week during a 13 week sales period and for a given store/SKU, wherein row 701 provides a baseline demand, row 702 provides seasonality, and rows 702-712 provide an indication (as indicated by an "X"), for each promotion, whether that promotion was active during the corresponding week; row 713 indicates actual sales during the corresponding time period; for the prediction of promotion effects, row 714 indicates the predictions of sales for each week from round A, in which all data points are used using known methods of using all available data; rows 715-719 indicates the predictions/estimated using each of rounds 1-5 for each time period, and row 720 is the average prediction from Rounds 1-5).
LEI’536 further discloses a non-transitory computer-readable medium (LEI’536, 14 in FIG. 1; ¶¶ [0023]-[0024]: a memory 14 can be comprised of any combination of random access memory ("RAM"), read only memory ("ROM"), static storage such as a magnetic or optical disk, or any other type of computer readable media) embodied with software (LEI’536, FIG. 1; ¶ [0026]: memory 14 stores software modules that provide functionality when executed by processor 22), wherein the software, when executed to perform the method described above (LEI’536, ¶ [0040]: the functionality is implemented by software stored in memory or other computer readable or tangible medium, and executed by a processor).
(LEI’536, FIG. 8; ¶¶ [0002] and [0026]: a network of facilities/retail stores that together deliver products to consumers is commonly referred to as a "supply chain" network; a specialized point of sale ("POS") terminal 100 generates the transactional data and historical sales data, e.g., data concerning transactions of each item/SKU at each retail store, used to forecast demand) (LEI’536, FIG. 5; ¶¶ [0065]-[0076]: use the optimized feature sets as input to forecasting algorithms to generate forecasting models; for each training dataset D(i) extracted/pooled from historical sale/supply chain data, one of the following machine learning algorithms are used to produce the model M(i): linear regression, Support Vector Machine ("SVM"), and Artificial Neural Networks ("ANN"); to forecast future5 demand, for each data point x, M(i) is iteratively applied to the input to produce the final results y as follows: y = sum( f(M(i), x) * w'(i) ), where y is the forecasted demand, and f is the function to create the forecast, corresponding to the model)
(LEI’536, FIGS. 6 and 7A-B; ¶¶ [0083]-[0089]: FIG. 6 shows promotion effects for each promotion 1-10, which are product/location specific but not time period specific; FIGS. 7A-B show a comparison of predictions for each week during a 13 week sales period and for a given store/SKU, wherein row 701 provides a baseline demand, row 702 provides seasonality, and rows 702-712 provide an indication (as indicated by an "X"), for each promotion, whether that promotion was active during the corresponding week; row 713 indicates actual sales during the corresponding time period; for the prediction of promotion effects, row 714 indicates the predictions of sales for each week from round A, in which all data points are used using known methods of using all available data; rows 715-719 indicates the predictions/estimated using each of rounds 1-5 for each time period, and row 720 is the average prediction from Rounds 1-5)
(Palinginis, 116 in FIGS. 1 and 5A-B; ¶¶ [0044] and [0086]: the predicted demand may be presented to a user through a graphical user interface that enables the user to interactively and iteratively select or refine one or more parameters of the promotion in order to view or ADJUST factors relevant to the proposed promotion; graphical user interface 500 may be presented on a computer system as a user-friendly, explicit visualization of the predicted demand values generated by of the blended models).
Wick at least 16:00-20:00
“need to have good models … to understand correlation to the data … understand what happens to it … how correlated to each other …. What would be interesting … what is the correlation to the target and so on … this means you should do 2 dimensional distribution … check … how different variables behave …you can do this with profile blood heat map or whatever … so one example would be something like dis” says Wick 18:152 and visualize with blood, heat map and “adjust features … profile “ then Wick shows
PNG
media_image20.png
837
1110
media_image20.png
Greyscale
Wick continues “and you should do some preprocessing … exploit missing values … they can have some information … you can leave some out … coming to the core” 19:00-22:00
Causal factors ≈ ‘influencing factors’
Wick already shows 2 models 21:45 (classification and regression) and w/i each shows 2 bullets.
Wick then goes into training
Deconfounding ≈ extract “patterns”.
PNG
media_image21.png
915
1335
media_image21.png
Greyscale
PNG
media_image22.png
729
1052
media_image22.png
Greyscale
Wick shows supervised, unsupervised and talks about reinforcement
PNG
media_image23.png
729
1118
media_image23.png
Greyscale
And applying Data Science to Pricing, Promotion, Dynamic Cataloging, Dynamic Forecasting such as predicting Tomorrow’s Sales or an Insurance Claim instead of the arcane area of physics is obvious Design Incentives or Market Forces Prompting Variations.
This application of Data Science to Business Method is Simple Substitution
CONCLUSION
Pertinent prior art cited but not relied upon
US20220384052
bbaggot@uspto.gov
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BREFFNI X BAGGOT whose telephone number is (571)272-7154. The examiner can normally be reached M-F 8a-10a, 12p-6p.
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, Waseem Ashraf can be reached at 571-270-3948. 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.
BREFFNI BAGGOT
Primary Examiner
Art Unit 3621
/BREFFNI BAGGOT/Primary Examiner, Art Unit 3621
1 LEI, FIG. 2; 302, 201 in FIGS. 3-4; ¶¶ [0038], [0043], and [0046].
2 See, for example US 2019/0130425 A1 to LEI, filed on 10/31/2017, 201 in FIG. 2; 302 in FIGS. 3-4; ¶¶ [0038], [0043], and [0046].
3 See, for example US 2019/0130425 A1 to LEI et al.., filed on 10/31/2017, 201 in FIG. 2; 302 in FIGS. 3-4; ¶¶ [0038], [0043], and [0046].
4 See, for example US 2019/0130425 A1 to LEI, filed on 10/31/2017, 201 in FIG. 2; 302 in FIGS. 3-4; ¶¶ [0038], [0043], and [0046].
5 See, for example US 2019/0130425 A1 to LEI et al.., filed on 10/31/2017, 201 in FIG. 2; 302 in FIGS. 3-4; ¶¶ [0038], [0043], and [0046].
Prosecution Insights