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 .
Notice to Applicant
The following is a Final Office action to Application Serial Number 18/515,777, filed on November 21, 2023. In response to Examiner’s Office Action of June 5, 2025, Applicant, on September 5, 2025, amended claims 1-8, and added claim 9. Claims 1-9 are pending in this application and have been rejected below.
Response to Amendment
Applicant’s amendments are acknowledged.
Regarding the 35. U.S.C. § 101 rejection, Applicant’s arguments have been
considered and is insufficient to overcome the rejection.
The 35 U.S.C. § 103 rejections are hereby amended pursuant to applicants’ amendments. Updated 35 U.S.C. § 103 rejections have been applied to amended claims. Please refer to the § 103 rejection for further explanation and rationale.
Response to Arguments
Applicant’s arguments filed September 5, 2025 have been fully considered but they are not persuasive and/or are moot in view of the revised rejections. Applicant’s arguments will be addressed herein below in the order in which they appear in the response filed September 5, 2025.
On Pg. 11-13 of the Remarks, regarding 35 U.S.C. § 101 rejections, Applicant states the rejection should be withdrawn as i) exceeding a BRI, as ii) being inconsistent with USPTO SME Example 39 and therefore arbitrary and capricious, and iii) as not
being, in terms of the August 4, 2025 Memorandum, "more likely than not" appropriate. In response, Examiner respectfully disagrees. The amended claims under its broadest reasonable interpretation fall within the Abstract idea grouping of “Mental Processes”- evaluation and “Methods of Organizing Human Activity” – managing commercial interactions. In the Step 2A analysis , Examiner found The claims primarily recite the additional element of using computer components to perform each step. The “device”, “memory”, “processor”, “computer”, and “computer readable medium” is recited at a high-level of generality, such that it amounts no more than mere instructions to apply the exception using a computer component. See MPEP 2106.05(f). Examiner finds the limitations recited in Example 39 are not similar to the amended claim language. Please review the updated 101 analysis for additional detail.
On Pg. 13-16 of the Remarks, regarding 35 U.S.C. § 101 rejections, Applicant states the rejection should be withdrawn at Step 2A Prong 2 because the amended claims represent a practical application and Applicant request a suggested amendment to overcome the rejection. In response, Examiner finds the additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims also fail to recite any improvements to another technology or technical field, improvements to the functioning of the computer itself, use of a particular machine, effecting a transformation or reduction of a particular article to a different state or thing, and/or an additional element applies or uses the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment. Examiner recommends incorporating the algorithm associated with the machine learning modelling and including additional aspects of the use case of the invention similar to the PTO Guidance examples.
On Pg. 16-17 of the Remarks, regarding 35 U.S.C. § 103 rejections. Applicant states the cited references do not disclose amended claim language. In response, new ground(s) of rejection is made necessitated by amendment see MPEP 706.07a where Wang is now applied for Claims 1 and 7-8. Regarding the 35 U.S.C. § 103 rejection, Applicant’s arguments with respect to claims has been considered but are moot in view of the new grounds of rejection.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1, and 7-8 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention. The specification does not disclose an “active prediction model”.
Claims 2-6 and 9 are rejected based on the dependency on claim 1.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1- 9 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Claims 1-9 are directed to predicting demand.
Claim 1 recites a device for predicting demand, Claim 7 recites a method for predicting demand and Claim 8 recites an article of manufacture for predicting demand, which include acquiring a single article prediction model, that predicts a first sales quantity demand of a target product, and a category prediction model, that predicts a second sales quantity of a category including the target product, wherein the single article prediction model and the category prediction model are generated using learning data acquired; determine, based on comparing historical sales data with a first demand prediction of the target product by the single article prediction model, a first accuracy of the single article prediction model, the first accuracy representing accuracy of the first demand prediction of the target product by the single article prediction model; determine, based on comparing the historical sales data with a second demand prediction of the target product by the category prediction model, a second accuracy of the category prediction model, the second accuracy representing accuracy of the second demand prediction of the target product by the category prediction model; determine, based on comparing the first accuracy of the single article prediction model with the second accuracy of the category prediction model, a first one of the single article prediction model and the category prediction model as having a higher accuracy than a second one of the single article prediction model and the category prediction model; adopt, based on determining the first one of the single article prediction model and the category prediction model as having the higher accuracy, the first one of the single article prediction model and the category prediction model as an active prediction model of the target product; and automatically generate an electronic order placement instruction of the target product based on a demand predicted by the active prediction model, the electronic order placement instruction configured to control an automated order placement system to maintain a stock level of the target product.
As drafted, this is, under its broadest reasonable interpretation, within the Abstract idea grouping of “Mental Processes” – evaluation. The recitation of “device”, “storage device”; “POS server”; “memory”, “processor”, “computer”, and “computer readable medium”, provide nothing in the claim elements to preclude the step from being “Mental Processes”- evaluation. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. The claims primarily recite the additional element of using computer components to perform each step. The “device”, “storage device”; “POS server”; “memory”, “processor”, “computer”, and “computer readable medium” is recited at a high-level of generality, such that it amounts no more than mere instructions to apply the exception using a computer component. See MPEP 2106.05(f). Furthermore, the claim 1, claim 7 and claim 8 recite using one or more “learning” data. The specification discloses the machine learning analysis at a high-level of generality, providing examples of different techniques that may be applied. The general use of a machine learning analysis does not provide a meaningful limitation to transform the abstract idea into a practical application. Therefore, currently, the machine learning is solely used a tool to perform the instructions of the abstract idea.
Accordingly, the additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims also fail to recite any improvements to another technology or technical field, improvements to the functioning of the computer itself, use of a particular machine, effecting a transformation or reduction of a particular article to a different state or thing, and/or an additional element applies or uses the judicial exception in some other meaningful way beyond generally linking the use of the judicial exception to a particular technological environment, such that the claim as a whole is more than a drafting effort designed to monopolize the exception. See 84 Fed. Reg. 55. In particular, there is a lack of improvement to a computer or technical field in prediction analysis.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional elements when considered both individually and as an ordered combination do not amount to significantly more than the abstract idea. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of “device”, “storage device”; “POS server”; “memory”, “processor”, “computer”, and “computer readable medium” is insufficient to amount to significantly more. (See MPEP 2106.05(f) – Mere Instructions to Apply an Exception – “Thus, for example, claims that amount to nothing more than an instruction to apply the abstract idea using a generic computer do not render an abstract idea eligible.” Alice Corp., 134 S. Ct. at 235). Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept.
The claim fails to recite any improvements to another technology or technical field, improvements to the functioning of the computer itself, use of a particular machine, effecting a transformation or reduction of a particular article to a different state or thing, adding unconventional steps that confine the claim to a particular useful application, and/or meaningful limitations beyond generally linking the use of an abstract idea to a particular environment. See 84 Fed. Reg. 55. Viewed individually or as a whole, these additional claim element(s) do not provide meaningful limitation(s) to transform the abstract idea into a patent eligible application of the abstract idea such that the claim(s) amounts to significantly more than the abstract idea itself. With regards to receiving data and step 2B, it is M2106.05(d)- Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information) and Storing and retrieving information in memory, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015).
Examiner concludes that the additional elements in combination fail to amount to significantly more than the abstract idea based on findings that each element merely performs the same function(s) in combination as each element performs separately. The claim is not patent eligible. Thus, taken alone, the additional elements do not amount to significantly more than the above-identified judicial exception (the abstract idea). Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually.
Dependent Claims 2-6 and 9 recite output information of the active prediction model; based on the target product being determined to be a new product, acquire the single article prediction model and the category prediction model as models of a product similar to a target product; based on a prediction result of a demand for each plurality of products including the target product being displayed in a list, display which prediction model predicted the prediction result, the prediction model being one of the single article prediction model and the category prediction model; display an error rate between a prediction result by the active prediction model and an actual value; based on the error rate is equal to or greater than a predetermined value, output an alert; periodically retrain the single article prediction model and the category prediction model using machine learning with updated historical sales data from the POS server, wherein periodically retraining the single article prediction model and the category prediction model refines the automated order placement system by improving an accuracy in adopting the first one of the single article prediction model and the category prediction model as the active prediction model of the target product by refining the first accuracy of the single article prediction model and the second accuracy of the category prediction model; and further narrowing the abstract idea. These recited limitations in the dependent claims do not amount to significantly more than the above-identified judicial exceptions in Claims 1, 7 and 8. Regarding Claims, 2-6, and 9 and the additional elements of “processor” it is M2106.05(d)- Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information). Regarding claim 9 and the additional element of machine learning - the specification discloses the machine learning at a high-level of generality, providing examples of different techniques that may be applied. The general use of a machine learning technique does not provide a meaningful limitation to transform the abstract idea into a practical application. Therefore, currently, the machine learning is solely used a tool to perform the instructions of the abstract idea.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-9 are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al., US Publication No. 20210110461A1, [hereinafter Wang], in view of Wagenblatt, US Publication No. 20140200958 A1, [hereinafter Wagenblatt] and in further view of Harma et al., US Publication No. 20220044148 A1, [hereinafter Harma].
Regarding Claim 1,
Wang teaches
A demand prediction device comprising: a memory storing instructions; and at least one processor configured to execute the instructions to: acquire, from a storage device, a single article prediction model, that predicts a first sales quantity of a target product, and a category prediction model, that predicts a second sales quantity of a category including the target product, wherein the single article prediction model and the category prediction model are generated using learning data … ; (Wang Par. 6; (par 74- 75- data science module 321 may retrieve order information from FO system 311 and glance view (i.e., number of webpage views for the product) from external front end system 313 to train the forecast model and anticipate a level of future demand. The order information may include sales statistics such as a number of items sold over time, a number of items sold during promotion periods, and a number of items sold during regular periods); Par. 114)
and automatically generate an electronic order placement instruction of the target product based on a demand predicted by the active prediction model, the electronic order placement instruction configured to control an automated order placement system to maintain a stock level of the target product (Wang Par. 79-“ PO generator 326, in some embodiments, may include one or more computing devices configured to generate POs to one or more suppliers based on the recommended order quantities or results of the distribution by IPS 324. SCM 320, by this point, would have determined a recommended order quantity for each product that requires additional inventory and for each FC 200, where each product has one or more suppliers that procure or manufacture the particular product and ship it to one or more FCs. A particular supplier may supply one or more products, and a particular product may be supplied by one or more suppliers. When generating POs, PO generator 326 may issue a paper PO to be mailed or faxed to the supplier or an electronic PO to be transmitted to the same.; Claim 1);
Wang teaches product demand forecasting and the feature is expounded upon by Wagenblatt:
… acquired from a point of sale (POS) server (Wagenblatt Par. 51- In FIG. 5, the first representative process may be data acquisition as illustrated by block 500 of FIG. 5. Data can include both data from traditional sources, such as sales history, scan-data, direct POS data, syndicated data, loyalty data, customer demographic data, and consumer panel data, as well as data having a qualitative aspect, such as weather, social media data, etc. Data can be acquired from a variety of services and through a variety of mechanisms. The rise of web services on the internet makes data that was formerly difficult and/or expensive to obtain readily accessible, much of the time for free or low cost. However, the challenge today is not availability of the data, but in understanding and interpreting and transforming the data into actionable intelligence.; Par. 40-43”)
determine, based on comparing historical sales data stored in the POS server with a first demand prediction of the target product by the single article prediction model, a first accuracy of the single article prediction model, the first accuracy representing accuracy of the first demand prediction of the target product by the single article prediction model; (Wagenblatt Par. 27- Par. 37- An important part of demand science is the analysis of the model quality and forecast accuracy to determine the quality and health of the source demand data, models, and forecasts. Model quality can be assessed using model metrics or model time series analysis to validate the quality of the input demand data, configuration settings, and resulting model fits. Any data or configuration issues may be identified and fixed early leading to more accurate models and forecasts. Forecast accuracy can be assessed using hold-out analysis as well as forecast vs. actual comparisons.; Par. 34; Par 51”)
determine, based on comparing the historical sales data stored in the POS server with a second demand prediction of the target product by the category prediction model, a second accuracy of the category prediction model, the second accuracy representing accuracy of the second demand prediction of the target product by the category prediction model; (Wagenblatt Par. 27- Par. 37- An important part of demand science is the analysis of the model quality and forecast accuracy to determine the quality and health of the source demand data, models, and forecasts. Model quality can be assessed using model metrics or model time series analysis to validate the quality of the input demand data, configuration settings, and resulting model fits. Any data or configuration issues may be identified and fixed early leading to more accurate models and forecasts. Forecast accuracy can be assessed using hold-out analysis as well as forecast vs. actual comparisons.; Par. 34; Par 51”)
adopt, based on determining the first one of the single article prediction model and the category prediction model as having the higher accuracy, the first one of the single article prediction model and the category prediction model as an active prediction model of the target product; (Wagenblatt Par. 34-37-“ In a nutshell, demand science transforms historical demand data into demand models for demand forecasting or optimization. Accurate and sufficient demand data should be obtained in order to ensure the best demand modeling and forecasting results. “Accurate” means minimal inherent errors (e.g. incorrect dates, accidental double aggregation). “Sufficient” means enough to obtain adequate results.”);
Wang and Wagenblatt are directed to product forecasting. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have improve upon data analysis of Wang as taught by Wagenblatt, by utilizing additional forecasting analysis with a reasonable expectation of success of arriving at the claimed invention. One of ordinary skill in the art would have been motivated to make the modification to the teachings of Wang with the motivation of improving model accuracy (Wagenblatt Par. 36).
Wang in view of Wagenblatt teach product demand forecasting and the feature is expounded upon by Harma:
determine, based on comparing the first accuracy of the single article prediction model with the second accuracy of the category prediction model, a first one of the single article prediction model and the category prediction model as having a higher accuracy than a second one of the single article prediction model and the category prediction model; (Harma Par. 84-87-“ Step 14 may determine, for example, that the prediction model is sufficiently accurate (e.g. an inaccuracy measure is below a predetermined value). Step 14 may thereby classify the prediction model as “accurate”. In this case, step 15 may comprise not modifying the prediction model. In another example, step 14 may determine that the prediction model is completely inaccurate, for example, that an inaccuracy measure is above a second predetermined value. Step 14 may thereby classify the prediction model as “very inaccurate”. In this case, step 15 may comprise rebuilding the prediction model from new training data (i.e. different to the existing training data used to produce the existing prediction model 2.);
Wang and Wagenblatt and Harma are directed to product forecasting. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have improve upon data analysis of Wang in view of Wagenblatt as taught by Harma, by utilizing additional forecasting analysis with a reasonable expectation of success of arriving at the claimed invention. One of ordinary skill in the art would have been motivated to make the modification to the teachings of Wang in view of Wagenblatt with the motivation of improving performance of the prediction model (Harma Par. 4).
Regarding Claim 2,
The demand prediction device according to claim 1, wherein the at least one processor is further configured to execute the instructions to: output information of the active prediction model. (Wang Par. 75-“ Demand forecast generator 322, in some embodiments, may include one or more computing devices configured to forecast a level of demand for a particular product using the forecast model developed by data science module 321. More specifically, the forecast model may output a demand forecast quantity for each product, where the demand forecast quantity is a specific quantity of the product expected to be sold to one or more customers in a given period (e.g., a day). In some embodiments, demand forecast generator 322 may output demand forecast quantities for each given period over a predetermined period (e.g., a demand forecast quantity for each day over a 5-week period). Each demand forecast quantity may also comprise a standard deviation quantity (e.g., ±5) or a range (e.g., maximum of 30 and minimum of 25) to provide more flexibility in optimizing product inventory levels).”)
Regarding Claim 3,
The demand prediction device according to claim 1, wherein the at least one processor is further configured to execute the instructions to: based on the target product being determined to be a new product, acquire the single article prediction model and the category prediction model as models of a product similar to a target product. (Wang Par. 96; Fig. 5; Par. 122-“ in some embodiments, IPS 324 may prioritize the recommended order quantities for different products based on a set of urgency scores assigned to each product instead of the rules described above with respect to FIGS. 7A and 7B. For example, IPS 324 may sort the recommended order quantities by product based on the urgency scores, make further adjustments to the quantities based on corresponding current inventory levels, and order the products in sequence from top-priority products to low-priority products. In some embodiments, the urgency scores may be determined through a machine learning model, where the machine learning model is trained with data from data science module 321 and the urgency scores are logit values of the machine learning model. Logit values refer to unnormalized or raw predictions or probability values of a model as known in the art)
Regarding Claim 4,
based on a prediction result of a demand for each of a plurality of products, including the target product, being displayed in a list, display which prediction model predicted the prediction result, the prediction model being one of the single article prediction model and the category prediction model. (Wang Fig. 7B; Par. 105-“ Referring back to graph 600A, the total quantity comprising of total ROQ (D-1) 611A, total ROQ (D) 612A, and total open PO 613 is adjusted to be a fulfillment ratio applied (FRA) quantity comprising total FRA ROQ (D-1) 621A, total FRA ROQ (D) 622A, and total FRA open PO 623. The quantity (i.e., reduction target 630) over total inbound processing capacity 604 may be the amount of quantity that IPS 324 must reduce by prioritizing certain products over others using a set of rules explained below with respect to 7A and 7B.”)
Regarding Claim 5,
Wang in view of Wagenblatt teach product demand forecasting and the feature is expounded upon by Harma:
display an error rate between a prediction result by the active prediction model and an actual value. (Harma Par. 98- “The difference determination process 20 comprises a step 21 of obtaining an entry 25′ of the training data 25, which entry 25′ is formed of sample input data 25 a and actual sample answer data 25 b. In step 22, the prediction model 2′ is applied to the sample input data 25 a to generate predicted sample answer data 27. In step 23, a difference 28 between the predicted sample answer data 27 and the actual sample answer data 25 b is calculated (e.g. an error value is determined). In step 24, this difference is stored to thereby contribute to a plurality of differences 28′ associated with the prediction model and the training data. The difference determination process 20 is repeated on each data entry of the training data, to thereby form the plurality of differences 28′.”);
Wang and Wagenblatt and Harma are directed to product forecasting. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have improve upon data analysis of Wang in view of Wagenblatt as taught by Harma, by utilizing additional forecasting analysis with a reasonable expectation of success of arriving at the claimed invention. One of ordinary skill in the art would have been motivated to make the modification to the teachings of Wang in view of Wagenblatt with the motivation of improving performance of the prediction model (Harma Par. 4).
Regarding Claim 6, Wang in view of Wagenblatt in further view of Harma teach The demand prediction device according to claim 5, wherein the at least one processor is further configured to execute the instructions to:…
Wang teaches product demand forecasting and the feature is expounded upon by Wagenblatt:
… being determined to be equal to or greater than a predetermined value, output an alert. (Wagenblatt Par. 51- In FIG. 5, the first representative process may be data acquisition as illustrated by block 500 of FIG. 5. Data can include both data from traditional sources, such as sales history, scan-data, direct POS data, syndicated data, loyalty data, customer demographic data, and consumer panel data, as well as data having a qualitative aspect, such as weather, social media data, etc. Data can be acquired from a variety of services and through a variety of mechanisms. The rise of web services on the internet makes data that was formerly difficult and/or expensive to obtain readily accessible, much of the time for free or low cost. However, the challenge today is not availability of the data, but in understanding and interpreting and transforming the data into actionable intelligence.; Par. 40-43”)
Wang and Wagenblatt are directed to product forecasting. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have improve upon data analysis of Wang as taught by Wagenblatt, by utilizing additional forecasting analysis with a reasonable expectation of success of arriving at the claimed invention. One of ordinary skill in the art would have been motivated to make the modification to the teachings of Wang with the motivation of improving model accuracy (Wagenblatt Par. 36).
Wang in view of Wagenblatt teach product demand forecasting and the feature is expounded upon by Harma:
based on the error rate ... (Harma Par. 98- “The difference determination process 20 comprises a step 21 of obtaining an entry 25′ of the training data 25, which entry 25′ is formed of sample input data 25 a and actual sample answer data 25 b. In step 22, the prediction model 2′ is applied to the sample input data 25 a to generate predicted sample answer data 27. In step 23, a difference 28 between the predicted sample answer data 27 and the actual sample answer data 25 b is calculated (e.g. an error value is determined). In step 24, this difference is stored to thereby contribute to a plurality of differences 28′ associated with the prediction model and the training data. The difference determination process 20 is repeated on each data entry of the training data, to thereby form the plurality of differences 28′.”);
Wang and Wagenblatt and Harma are directed to product forecasting. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have improve upon data analysis of Wang in view of Wagenblatt as taught by Harma, by utilizing additional forecasting analysis with a reasonable expectation of success of arriving at the claimed invention. One of ordinary skill in the art would have been motivated to make the modification to the teachings of Wang in view of Wagenblatt with the motivation of improving performance of the prediction model (Harma Par. 4).
Regarding Claim 7,
Wang teaches
A demand prediction method causing a computer to execute: acquiring, from a storage device, a single article prediction model, that predicts a first sales quantity of a target product, and a category prediction model, that predicts a second sales quantity of a category including the target product, wherein the single article prediction model and the category prediction model are generated using learning data … ; (Wang Par. 6; (par 74- 75- data science module 321 may retrieve order information from FO system 311 and glance view (i.e., number of webpage views for the product) from external front end system 313 to train the forecast model and anticipate a level of future demand. The order information may include sales statistics such as a number of items sold over time, a number of items sold during promotion periods, and a number of items sold during regular periods); Par. 114)
and automatically generating an electronic order placement instruction of the target product based on a demand predicted by the active prediction model, the electronic order placement instruction configured to control an automated order placement system to maintain a stock level of the target product (Wang Par. 79-“ PO generator 326, in some embodiments, may include one or more computing devices configured to generate POs to one or more suppliers based on the recommended order quantities or results of the distribution by IPS 324. SCM 320, by this point, would have determined a recommended order quantity for each product that requires additional inventory and for each FC 200, where each product has one or more suppliers that procure or manufacture the particular product and ship it to one or more FCs. A particular supplier may supply one or more products, and a particular product may be supplied by one or more suppliers. When generating POs, PO generator 326 may issue a paper PO to be mailed or faxed to the supplier or an electronic PO to be transmitted to the same.; Claim 1);
Wang teaches product demand forecasting and the feature is expounded upon by Wagenblatt:
… acquired from a point of sale (POS) server (Wagenblatt Par. 51- In FIG. 5, the first representative process may be data acquisition as illustrated by block 500 of FIG. 5. Data can include both data from traditional sources, such as sales history, scan-data, direct POS data, syndicated data, loyalty data, customer demographic data, and consumer panel data, as well as data having a qualitative aspect, such as weather, social media data, etc. Data can be acquired from a variety of services and through a variety of mechanisms. The rise of web services on the internet makes data that was formerly difficult and/or expensive to obtain readily accessible, much of the time for free or low cost. However, the challenge today is not availability of the data, but in understanding and interpreting and transforming the data into actionable intelligence.; Par. 40-43”)
determining, based on comparing historical sales data stored in the POS server with a first demand prediction of the target product by the single article prediction model, a first accuracy of the single article prediction model, the first accuracy representing accuracy of the first demand prediction of the target product by the single article prediction model; (Wagenblatt Par. 27- Par. 37- An important part of demand science is the analysis of the model quality and forecast accuracy to determine the quality and health of the source demand data, models, and forecasts. Model quality can be assessed using model metrics or model time series analysis to validate the quality of the input demand data, configuration settings, and resulting model fits. Any data or configuration issues may be identified and fixed early leading to more accurate models and forecasts. Forecast accuracy can be assessed using hold-out analysis as well as forecast vs. actual comparisons.; Par. 34; Par 51”)
determining, based on comparing the historical sales data stored in the POS server with a second demand prediction of the target product by the category prediction model, a second accuracy of the category prediction model, the second accuracy representing accuracy of the second demand prediction of the target product by the category prediction model; (Wagenblatt Par. 27- Par. 37- An important part of demand science is the analysis of the model quality and forecast accuracy to determine the quality and health of the source demand data, models, and forecasts. Model quality can be assessed using model metrics or model time series analysis to validate the quality of the input demand data, configuration settings, and resulting model fits. Any data or configuration issues may be identified and fixed early leading to more accurate models and forecasts. Forecast accuracy can be assessed using hold-out analysis as well as forecast vs. actual comparisons.; Par. 34; Par 51”)
adopting, based on determining the first one of the single article prediction model and the category prediction model as having the higher accuracy, the first one of the single article prediction model and the category prediction model as an active prediction model of the target product; (Wagenblatt Par. 34-37-“ In a nutshell, demand science transforms historical demand data into demand models for demand forecasting or optimization. Accurate and sufficient demand data should be obtained in order to ensure the best demand modeling and forecasting results. “Accurate” means minimal inherent errors (e.g. incorrect dates, accidental double aggregation). “Sufficient” means enough to obtain adequate results.”);
Wang and Wagenblatt are directed to product forecasting. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have improve upon data analysis of Wang as taught by Wagenblatt, by utilizing additional forecasting analysis with a reasonable expectation of success of arriving at the claimed invention. One of ordinary skill in the art would have been motivated to make the modification to the teachings of Wang with the motivation of improving model accuracy (Wagenblatt Par. 36).
Wang in view of Wagenblatt teach product demand forecasting and the feature is expounded upon by Harma:
determine, based on comparing the first accuracy of the single article prediction model with the second accuracy of the category prediction model, a first one of the single article prediction model and the category prediction model as having a higher accuracy than a second one of the single article prediction model and the category prediction model; (Harma Par. 84-87-“ Step 14 may determine, for example, that the prediction model is sufficiently accurate (e.g. an inaccuracy measure is below a predetermined value). Step 14 may thereby classify the prediction model as “accurate”. In this case, step 15 may comprise not modifying the prediction model. In another example, step 14 may determine that the prediction model is completely inaccurate, for example, that an inaccuracy measure is above a second predetermined value. Step 14 may thereby classify the prediction model as “very inaccurate”. In this case, step 15 may comprise rebuilding the prediction model from new training data (i.e. different to the existing training data used to produce the existing prediction model 2.);
Wang and Wagenblatt and Harma are directed to product forecasting. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have improve upon data analysis of Wang in view of Wagenblatt as taught by Harma, by utilizing additional forecasting analysis with a reasonable expectation of success of arriving at the claimed invention. One of ordinary skill in the art would have been motivated to make the modification to the teachings of Wang in view of Wagenblatt with the motivation of improving performance of the prediction model (Harma Par. 4).
Regarding Claim 8,
Wang teaches
A non-transitory computer-readable recording medium that records a program for causing a computer to execute: acquiring, from a storage device, a single article prediction model, that predicts a first sales quantity of a target product, and a category prediction model, that predicts a second sales quantity of a category including the target product, wherein the single article prediction model and the category prediction model are generated using learning data … ; (Wang Par. 6; Par. 9; (par 74- 75- data science module 321 may retrieve order information from FO system 311 and glance view (i.e., number of webpage views for the product) from external front end system 313 to train the forecast model and anticipate a level of future demand. The order information may include sales statistics such as a number of items sold over time, a number of items sold during promotion periods, and a number of items sold during regular periods); Par. 114)
and automatically generating an electronic order placement instruction of the target product based on a demand predicted by the active prediction model, the electronic order placement instruction configured to control an automated order placement system to maintain a stock level of the target product (Wang Par. 79-“ PO generator 326, in some embodiments, may include one or more computing devices configured to generate POs to one or more suppliers based on the recommended order quantities or results of the distribution by IPS 324. SCM 320, by this point, would have determined a recommended order quantity for each product that requires additional inventory and for each FC 200, where each product has one or more suppliers that procure or manufacture the particular product and ship it to one or more FCs. A particular supplier may supply one or more products, and a particular product may be supplied by one or more suppliers. When generating POs, PO generator 326 may issue a paper PO to be mailed or faxed to the supplier or an electronic PO to be transmitted to the same.; Claim 1);
Wang teaches product demand forecasting and the feature is expounded upon by Wagenblatt:
… acquired from a point of sale (POS) server (Wagenblatt Par. 51- In FIG. 5, the first representative process may be data acquisition as illustrated by block 500 of FIG. 5. Data can include both data from traditional sources, such as sales history, scan-data, direct POS data, syndicated data, loyalty data, customer demographic data, and consumer panel data, as well as data having a qualitative aspect, such as weather, social media data, etc. Data can be acquired from a variety of services and through a variety of mechanisms. The rise of web services on the internet makes data that was formerly difficult and/or expensive to obtain readily accessible, much of the time for free or low cost. However, the challenge today is not availability of the data, but in understanding and interpreting and transforming the data into actionable intelligence.; Par. 40-43”)
determining, based on comparing historical sales data stored in the POS server with a first demand prediction of the target product by the single article prediction model, a first accuracy of the single article prediction model, the first accuracy representing accuracy of the first demand prediction of the target product by the single article prediction model; (Wagenblatt Par. 27- Par. 37- An important part of demand science is the analysis of the model quality and forecast accuracy to determine the quality and health of the source demand data, models, and forecasts. Model quality can be assessed using model metrics or model time series analysis to validate the quality of the input demand data, configuration settings, and resulting model fits. Any data or configuration issues may be identified and fixed early leading to more accurate models and forecasts. Forecast accuracy can be assessed using hold-out analysis as well as forecast vs. actual comparisons.; Par. 34; Par 51”)
determining, based on comparing the historical sales data stored in the POS server with a second demand prediction of the target product by the category prediction model, a second accuracy of the category prediction model, the second accuracy representing accuracy of the second demand prediction of the target product by the category prediction model; (Wagenblatt Par. 27- Par. 37- An important part of demand science is the analysis of the model quality and forecast accuracy to determine the quality and health of the source demand data, models, and forecasts. Model quality can be assessed using model metrics or model time series analysis to validate the quality of the input demand data, configuration settings, and resulting model fits. Any data or configuration issues may be identified and fixed early leading to more accurate models and forecasts. Forecast accuracy can be assessed using hold-out analysis as well as forecast vs. actual comparisons.; Par. 34; Par 51”)
adopting, based on determining the first one of the single article prediction model and the category prediction model as having the higher accuracy, the first one of the single article prediction model and the category prediction model as an active prediction model of the target product; (Wagenblatt Par. 34-37-“ In a nutshell, demand science transforms historical demand data into demand models for demand forecasting or optimization. Accurate and sufficient demand data should be obtained in order to ensure the best demand modeling and forecasting results. “Accurate” means minimal inherent errors (e.g. incorrect dates, accidental double aggregation). “Sufficient” means enough to obtain adequate results.”);
Wang and Wagenblatt are directed to product forecasting. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have improve upon data analysis of Wang as taught by Wagenblatt, by utilizing additional forecasting analysis with a reasonable expectation of success of arriving at the claimed invention. One of ordinary skill in the art would have been motivated to make the modification to the teachings of Wang with the motivation of improving model accuracy (Wagenblatt Par. 36).
Wang in view of Wagenblatt teach product demand forecasting and the feature is expounded upon by Harma:
determine, based on comparing the first accuracy of the single article prediction model with the second accuracy of the category prediction model, a first one of the single article prediction model and the category prediction model as having a higher accuracy than a second one of the single article prediction model and the category prediction model; (Harma Par. 84-87-“ Step 14 may determine, for example, that the prediction model is sufficiently accurate (e.g. an inaccuracy measure is below a predetermined value). Step 14 may thereby classify the prediction model as “accurate”. In this case, step 15 may comprise not modifying the prediction model. In another example, step 14 may determine that the prediction model is completely inaccurate, for example, that an inaccuracy measure is above a second predetermined value. Step 14 may thereby classify the prediction model as “very inaccurate”. In this case, step 15 may comprise rebuilding the prediction model from new training data (i.e. different to the existing training data used to produce the existing prediction model 2.);
Wang and Wagenblatt and Harma are directed to product forecasting. It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have improve upon data analysis of Wang in view of Wagenblatt as taught by Harma, by utilizing additional forecasting analysis with a reasonable expectation of success of arriving at the claimed invention. One of ordinary skill in the art would have been motivated to make the modification to the teachings of Wang in view of Wagenblatt with the motivation of improving performance of the prediction model (Harma Par. 4).
Regarding Claim 9,
periodically retrain the single article prediction model and the category prediction model using machine learning with updated historical sales data from the POS server, wherein periodically retraining the single article prediction model and the category prediction model refines the automated order placement system by improving an accuracy in adopting the first one of the single article prediction model and the category prediction model as the active prediction model of the target product by refining the first accuracy of the single article prediction model and the second accuracy of the category prediction model (Wang Par. 104- In some embodiments