DETAILED ACTION
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 .
Status of Application
This office action is in response to the most recent filings by applicants on 08/29/25.
Claims 1, 8 and 15 are amended
Claims 2, 9 and 16 are cancelled
No claims are added
Claims 1, 3-8, 10-15, and 17-20 are pending
Note:
In the amended independent claims 1, 8 and 15, the claim limitations discussed are broad and the specification does not provide enough detailed support to show to one of ordinary skill in the art what certain terms in the claim limitations mean.
For instance, in claim 1, regarding the claim limitation “receiving, via a user interface, a first constraint and a second constraint, the first constraint being a total budget for the plurality of geographic regions, the second constraint that one incentive value is determined for each geographic region; determining, by the one or more servers, a plurality of inventive values for the available delivery associates of the on-demand delivery platform for the identified plurality of geographic regions based at least in part on the delivery quality values and using an optimization module, wherein the determining of the plurality of incentive values comprises:”
In light of the specification, [0067]: In some implementations, the constraints are adjusted manually by a system administrator. For example, an administrator manually adjusts the overall budget through a user interface that is configured for maintaining constraints of an optimization module 424. In other implementations, the constraints are adjusted automatically by optimization module 424. For example, after optimization module 424 has been setting incentive values for a period of time, the optimization module can leverage a data set of historical budgets and how they corresponded to selected delivery quality values. With that information, optimization module 424 can use refine the overall budget based on the more accurate information. For example, if the budget was set for $1 million, but optimization module 424 infers that a budget of $1,010,005 would lead to A much higher overall delivery quality, then the overall budget could be adjusted to that $1,010,005 value and optimized accordingly.
[0069]: In some implementations, multiple constraints might be used by the integer programming model to determine incentive values. For example, there may be a constraint for an overall budget and a constraint that there be one incentive per region. In another example, there might be constraints set on a per-region level, e.g., the West Berkeley neighborhood has a local budget of $1,000, and the Elmwood neighborhood has a local budget of $2,000.
In addition, applicants have pointed to [0003]-[0004], [0017], [0064] in the most recently submitted remarks 02/23/26, pages 11-12. None of the cited paragraphs shows the above steps being performed automatically. In fact, even the paragraphs applicants have pointed to describe an administrator performing the above steps.
[0064] Constraints of the integer programming model can be modified as necessary. For example, an administrator may change the overall budget value from $1 million to $1.25 million. This might be done because delivery associate performance for the on- demand delivery platform might be a higher priority and as such supplier quality would increase at the expense of a higher budget. Likewise, the overall budget can be decreased if saving money becomes an increased priority.
In light of these notes, the amended claims, do not overcome previously presented rejections under 101 and 103. As is discussed below. This note is intended as a conversation starter to help applicants understand the examiner’s perspective. Applicants are welcome to call the examiner to discuss this further.
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, 3-8, 10-15, and 17-20 is/are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., an abstract idea) without significantly more.
Step One - First, pursuant to step 1 in the January 2019 Guidance on 84 Fed. Reg. 53, the claims 1, 3-7 is/are directed to a method which is a statutory category.
Step One - First, pursuant to step 1 in the January 2019 Guidance on 84 Fed. Reg. 53, the claims 8, 10-14 is/are directed to a device/apparatus which is a statutory category.
Step One - First, pursuant to step 1 in the January 2019 Guidance on 84 Fed. Reg. 53, the claims 15, 17-20 is/are directed to a computer program product which is a statutory category.
Under the 2019 PEG, Step 2A under which a claim is not “directed to” a judicial exception unless the claim satisfies a two-prong inquiry. Further, particular groupings of abstract ideas are consistent with judicial precedent and are based on an extraction and synthesis of the key concepts identified by the courts as being abstract.
With respect to the Step 2A, Prong One, the claims as drafted, and given their broadest reasonable interpretation, fall within the Abstract idea grouping of “certain methods of organizing human activity” (business relations; relationships or interactions between people). For instance, independent Claim 1 is directed to an abstract idea, as evidenced by claim limitations “identifying, a plurality of geographic regions serviced, the plurality of geographic regions identified according to different levels of granularity based, at least in part, on both density of populations in the plurality of geographic regions and delivery capacity of the on-demand delivery platform across the plurality of geographic regions, the plurality of geographic regions comprises one or more cities, one or more neighborhoods, and one or more subsections of a particular neighborhood; automatically generating, predicted demand based on a set of historical demand data, the predicted demand being generated according to a particular interval and representing customer demand of the on-demand delivery platform for the plurality of geographic regions and for a period of time, the set of historical demand data representing completed deliveries; generating, a predicted supply based on a set of historical supply data, the predicted supply representing available delivery associates of the on-demand delivery platform for the plurality of geographic regions and for the period of time; generating, delivery quality values for the plurality of geographic regions and for the period of time of time based on the predicted demand and the predicted supply; receiving, a first constraint and a second constraint, the first constraint being a total budget for the plurality of geographic regions, the second constraint that one incentive value is determined for each geographic region; determining, a plurality of inventive values for the available delivery associates of the on-demand delivery platform for the identified plurality of geographic regions based at least in part on the delivery quality values and using an optimization module, wherein the determining of the plurality of incentive values comprises: identifying an objective function for maximizing delivery quality values; and selecting the plurality of incentive values based at least in part on the first constraint, the second constraint, and the objective function such that a total cost of the determined plurality of incentive values is less than the total budget, each different one of the determined plurality of incentive values corresponds to a different corresponding one of the plurality of geographic regions, and the determined plurality of incentive values maximizes the delivery quality values; determining, that a delivery associate of the delivery associates has a history of delivery to a particular geographic region of the plurality of geographic regions; and transmitting, a notification of a first one of the determined plurality of incentive values that corresponds to the particular geographic region to a client device of the delivery associate of the on-demand delivery platform, the first one of the determined plurality of incentive values being associated with a particular date for the particular geographic region.”
These claim limitations belong to the grouping of “certain methods of organizing human activity” because the claims are related to balancing demand and supply predictions by determining incentives to better help meet demand needs. Managing the balancing demand and supply predictions by determining incentives to better help meet demand needs for one or more human entities involves organizing human activity based on the description of “certain methods of organizing human activity” provided by the courts. The court have used the phrase “Certain methods of organizing human activity” 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).
Independent Claims 8 and 15 is/are recite substantially similar limitations to independent claim 1 and is/are rejected under 2A for similar reasons to claim 1 above.
With respect to the Step 2A, Prong Two - This judicial exception is not integrated into a practical application. In particular, the claim only recites “A method comprising: by one or more servers, by an on-demand delivery platform, training, by the one or more servers, a machine learning algorithm using historical demand data stored in a database, the machine learning algorithm being a decision-tree based algorithm; by the one or more servers, using the machine learning algorithm, via a user interface, by the one or more servers, by the one or more servers, from a database, by the one or more servers, A computer program product comprising one or more non-transitory computer readable media having instructions stored thereon for performing a method, the method comprising: An on-demand delivery platform including memory and a processor configured to cause:”, such that it amounts to no more than: adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea, as discussed in MPEP 2106.05(f).
Regarding the claim limitations above, the additional elements of a “machine learning model” or “training, by the one or more servers, a machine learning algorithm using historical demand data stored in a database, the machine learning algorithm being a decision-tree based algorithm”, this language merely requires execution of an algorithm that can be performed by a generic computer component and provides no detail regarding the operation of that algorithm. As such, the claim requirement amounts to mere instructions to implement the abstract idea on a computer, and, therefore, is not sufficient to make the claim patent eligible. See Alice, 573 U.S. at 226 (determining that the claim limitations “data processing system”, “communications controller,” and “data storage unit” were generic computer components that amounted to mere instructions to implement the abstract idea on a computer); October 2019 Guidance Update at 11–12 (recitation of generic computer limitations for implementing the abstract idea “would not be sufficient to demonstrate integration of a judicial exception into a practical application”). Such a generic recitation of a “machine learning model” is insufficient to show a practical application of the recited abstract idea.
As demonstrated by use of language “machine learning model”, “training, by the one or more servers, a machine learning algorithm using historical demand data stored in a database, the machine learning algorithm being a decision-tree based algorithm”, “using an optimization module” and other similar limitations, without much technological details following the limitation are simply the preparation steps and subsequent use of machine to represent mere invocation of machinery per MPEP 2106.05(f)(2) possibly an example of a mathematical algorithm [here machine learning preparation] being applied on a general-purpose computer per MPEP 2106.05(f)(2)(i).
Here, the claims are pre-processing data for use by the machine learning model to balancing demand and supply predictions by determining incentives to better help meet demand needs. The training step is math. To overcome the 101 the output of the model would have to be used in a meaningful way.
Further, calculation steps, such as determining a plurality of incentive values also constitutes a mental process, such as an observation, evaluation, judgment, or opinion that can be performed in the human mind. The 2019 Guidance expressly recognizes such mental processes as constituting patent-ineligible abstract ideas. MPEP § 2106.04(a).
Further still, training a learning model constitutes a mathematical concept, such as the concept of using known data to set and adjust coefficients and mathematical relationships of variables that represent some modeled characteristic or phenomenon. The 2019 Guidance expressly recognizes mathematical concepts including mathematical relationships as constituting an abstract idea. MPEP § 2106.04(a).
As a result, claims 1, 8 and 15 do not provide any specifics regarding the integration into a practical application when recited in a claim with a judicial exception.
Similarly, dependent claims 3-7, 10-14, and 17-20 are also directed to an abstract idea under 2A, first and second prong. In the present application, all of the dependent claims have been evaluated and it was found that they all inherit the deficiencies set forth with respect to the independent claims. For instance, dependent claims 4 recite “wherein the predicted demand is categorized according to a geographical region and a period of time”. Here, these claims offer further descriptive limitations of elements found in the independent claims which are similar to the abstract idea noted in the independent claim above.
Dependent claims 3 recites “using a machine learning algorithm configured” in the claim limitations “wherein generating the predicted supply includes using a machine learning algorithm configured to determine a first amount of delivery associates in relation to a first incentive value and determine a second amount of delivery associates in relation to a second incentive value.” In this claim, “using a machine learning algorithm configured” is an additional element, but it is still being recited such that it amounts to no more than: adding the words “apply it” (or an equivalent) with the judicial exception, or mere instructions to implement an abstract idea on a computer, or merely uses a computer as a tool to perform an abstract idea, as discussed in MPEP 2106.05(f). As a result, Examiner asserts that dependent claims, such as dependent claims 3-7, 10-14, and 17-20 are also directed to the abstract idea identified above.
With respect to Step 2B, the claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. First, the invention lacks improvements to another technology or technical field [see Alice at 2351; 2019 IEG at 55], and lacks meaningful limitations beyond generally linking the use of an abstract idea to a particular technological environment [Alice at 2360, 2019 IEG at 55], and fails to effect a transformation or reduction of a particular article to a different state or thing [2019 IEG, 55]. For the reasons articulated above, the claims recite an abstract idea that is limited to a particular field of endeavor (MPEP § 2106.05(h)) and recites insignificant extra-solution activity (MPEP § 2106.05(g)). By the factors and rationale provided above with respect to these MPEP sections, the additional elements of the claims that fail to integrate the abstract idea into a practical application also fail to 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 element(s) of “A method comprising: by one or more servers, by an on-demand delivery platform, training, by the one or more servers, a machine learning algorithm using historical demand data stored in a database, the machine learning algorithm being a decision-tree based algorithm; by the one or more servers, using the machine learning algorithm, via a user interface, by the one or more servers, by the one or more servers, from a database, by the one or more servers, A computer program product comprising one or more non-transitory computer readable media having instructions stored thereon for performing a method, the method comprising: An on-demand delivery platform including memory and a processor configured to cause:” are insufficient to amount to significantly more. Applicants originally submitted specification describes the computer components above at least in page/ paragraph 16, 24, 74, 76-77. In light of the specification, it should be noted that the components discussed above did not meaningfully limit the abstract idea because they merely linked the use of the abstract idea to a particular technological environment (i.e., "implementation via computers"). In light of the specification, it should be noted that the claim limitations discussed above are merely instructions to implement the abstract idea on a computer. See MPEP 2106.05(f). (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 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.
Independent Claims 8 and 15 is/are recite substantially similar limitations to independent claim 1 and is/are rejected under 2B for similar reasons to claim 1 above.
Further, it should be noted that additional elements of the claimed invention such as claim limitations when considered individually or as an ordered combination along with the other limitations discussed above in method claim 1 also do not meaningfully limit the abstract idea because they merely linked the use of the abstract idea to a particular technological environment (i.e., "implementation via computers"). In light of the specification, it should be noted that the claim limitations discussed above are merely instructions to implement the abstract idea on a computer. See MPEP 2106.
Similarly, dependent claims 3-7, 10-14, and 17-20 also do not include limitations amounting to significantly more than the abstract idea under the second prong or 2B of the Alice framework. In the present application, all of the dependent claims have been evaluated and it was found that they all inherit the deficiencies set forth with respect to the independent claims. Further, it should be noted that the dependent claims do not include limitations that overcome the stated assertions. Here, the dependent claims recite features/limitations that include computer components identified above in part 2B of analysis of independent claims 1, 8 and 15. As a result, Examiner asserts that dependent claims, such as dependent claims 3-7, 10-14, and 17-20 are also directed to the abstract idea identified above.
For more information on 101 rejections, see MPEP 2106, January 2019 Guidance at https://www.govinfo.gov/content/pkg/FR-2019-01 -07/pdf/2018-28282.pdf
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, 3-8, 10-15, and 17-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over (US 2019/0266557) Berk; Jonathan et al., further in view of (US 2006/0136237) Spiegel; Joel R. et al. and Zhou et. al (2017/0221086).
As per claims 1, 8 and 15:
Regarding the claim limitations below, Berk shows:
A method comprising (Berk: [0064]: method):
Regarding the claim limitations below, Berk shows:
An on-demand delivery platform including memory and a processor configured to cause (Berk: [0033]-[0034]: delivery platform):
Regarding the claim limitations below, Berk shows:
A computer program product comprising one or more non-transitory computer readable media having instructions stored thereon for performing a method, the method comprising (Berk: [0064], [0097]):
Regarding the claim limitations below, Berk in view of Spiegel shows:
identifying, by one or more servers, a plurality of geographic regions serviced by an on-demand delivery platform, the plurality of geographic regions identified according to different levels of granularity based, at least in part, on both density of populations in the plurality of geographic regions and delivery capacity of the on-demand delivery platform across the plurality of geographic regions, wherein the identified the plurality of geographic regions comprises one or more cities, one or more neighborhoods, and one or more subsections of a particular neighborhood
Berk shows “identifying, by one or more servers, a plurality of geographic regions serviced by an on-demand delivery platform, the plurality of geographic regions identified according to different levels of granularity based, at least in part, on both density of populations in the plurality of geographic regions” in [0034] taking into consideration the challenges with delivery for carriers or service providers and creating incentives to help more carriers want to deliver in certain areas. This reads on the limitation above, since the granularity of the location of delivery and the difficulty of the delivery both address most of the limitation above. Similarly, in [0039] In some embodiments, the delivery routing system tracks the courier acceptance rate of the system for a given location and time. Various metrics may be used to determine the courier acceptance rate. For example, the courier acceptance rate may correspond to the average number of delivery opportunities that are declined for a given location and time. In other embodiments, the courier acceptance rate may correspond to the average amount of time between the creation of an order and acceptance of the delivery opportunity for such order. In yet other embodiments, the courier acceptance rate may correspond to the average amount of time between the transmittal of the delivery opportunity to the courier device and the acceptance of the delivery opportunity for such order. The routing system then determines whether the current courier acceptance rate is at a desired threshold rate. Also, see [0123]-[0124]. The location information reads on “geographic region” in the claim. This reads on “wherein the identified the plurality of geographic regions comprises one or more cities, one or more neighborhoods, and one or more subsections of a particular neighborhood.”
Further, Berk shows “a plurality of geographic regions serviced by an on-demand delivery platform” in (Abstract): described are systems and processes for generating dynamic effort-based delivery value predictions for real-time delivery of perishable goods. In one aspect, a system is configured for generating dynamic delivery value predictions for delivery opportunities provided to couriers. For each order, delivery events and corresponding timestamps are received from devices operated by customers, restaurants, and couriers. Based on the timestamps, the system generates a predicted delivery duration with trained predictive models that use weighted factors such as order data and historical restaurant data. A service value for the delivery of the order is determined based the predicted delivery duration and a predetermined active time value. The service value is then transmitted along with the corresponding delivery opportunity to a user device of a courier. The determined service values may be adjusted based on courier acceptance rates of delivery opportunities and other factors such as customer experience. [0001] The present disclosure relates to a system for facilitating a real-time, on-demand delivery platform for perishable goods. In one example, the present disclosure relates to mechanisms and processes for dynamic valuations of deliveries. [0011] Other implementations of this disclosure include corresponding devices, systems, and computer programs, as well as and associated methods for dynamically predicting delivery service values. These other implementations may each optionally include one or more of the following features. For instance, provided is a programmable device configured for generating dynamic delivery value predictions for real-time delivery of perishable goods using a predictive machine learning model. The programmable device is configured to operate in a training mode and an inference mode.
The only thing that is not addressed in the paragraphs above by Berk is the “density of population” consideration. Spiegel shows collecting and analyzing customer demographic information in [0069], [0071]-[0074] and order volume in [0075]-[0081], [0091]. This reads on “density of population” in the claim. Spiegel also in shows [0058]-[0059]: A destination may be a completely specified delivery address, but in some embodiments a predictive shipping model may support latency predictions for multiple degrees of granularity of destinations (e.g., broad geographical regions, specific geographical areas, delivery zones/routes within geographical areas, street addresses, etc.). Additionally, in some embodiments a predictive shipping model may predict shipping outcomes in addition to or other than latency. For example, a shipping model may be configured to predict a route (such as a sequence of hubs 120) that will be traversed by a given package 260. [0059]: For example, latencies for shipping from a particular geographical area may vary depending on the point within the region a package 260 is tendered (e.g., at a hub 120, from a fulfillment center 110, or from another location). [0027] FIGS. 9A-9C illustrate an example method for generating dynamic delivery value predictive updates using a predictive machine learning model, in accordance with one or more embodiments. [0036] Accordingly, the present disclosure describes various examples of delivery tracking and pairing systems and processes that provide ways of more accurately determining the value of a delivery by associating the value with delivery effort. In some examples, a delivery tracking system generates ETA predictions using a predictive event model that implements machine learning to evaluate weighted factors. In some embodiments, the predictive event model may implement a neural network. In other embodiments, the predictive event model may be a gradient boosted machine or gradient boosted decision tree. [0160] With reference to FIGS. 9A-9C, shown an example method 900 for generating dynamic delivery value predictive updates using a predictive machine learning model, in accordance with one or more embodiments. In certain embodiments, the predictive machine learning model may be a predictive event model and/or a service valuation model, and comprise one or more computational layers or chained decision trees. FIG. 9B illustrates an example of operations of the predictive model in the training mode 910 and inference mode 960, in accordance with one or more embodiments.
Reference Berk and Reference Spiegel are analogous prior art to the claimed invention because the references generally relate to field of dynamic or on demand delivery. Lastly, said references are filed before the effective filing date of the instant application; hence, said references are analogous prior-art references.
It would have been obvious to one of ordinary skill in the art at the time the invention was made for Pre-AIA to provide the teachings of Reference Spiegel, particularly [0077]: speculative shipment decision analysis by forecasting model, in the disclosure of Reference Berk, particularly in the ways for overcoming the inflexibility related to structure which allows testing to optimize delivery valuation around a supply and demand equilibrium, or implementation of adjustments to the model (Berk: [0034]) in order to provide for a system that monitors the data relationships among elements of system… physical shipment paths exist between supplier(s) 1020 and fulfillment center(s) 110 as well as between fulfillment center(s) 110 and customers 1010. These shipper transit paths are shown as distinct from the data relationships within system 1000 as taught by Reference Spiegel (see at least in [0093]) so that the process of dynamic or on demand delivery services can be made more efficient and effective.
Further, the claimed invention is merely a combination of old elements in a similar dynamic or on demand delivery field of endeavor, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that, given the existing technical ability to combine the elements as evidenced by Reference Berk in view of Reference Spiegel, the results of the combination were predictable (MPEP 2143 A).
Regarding the claim limitations below, Berk in view of Spiegel shows:
training, by the one or more servers, a machine learning algorithm using historical demand data stored in a database, the machine learning algorithm being a decision-tree based algorithm (Berk: [0092]: delivery parameters may include time, date, traffic, weather, historical courier performance, and size of markets, [0140]: dates may fall on holidays that are historically known to be busy days. Further, Berk shows [0036]: a delivery tracking system generates ETA predictions using a predictive event model that implements machine learning to evaluate weighted factors. In some embodiments, the predictive event model may implement a neural network. In other embodiments, the predictive event model may be a gradient boosted machine or gradient boosted decision tree. [0037]: the predictive event model may iteratively update various decision trees and corresponding error measurements. [0088]: a gradient boosted machine implemented in various example embodiments may comprise a plurality of iteratively trained chained decision trees. A single decision tree may be trained at a time with each subsequent decision tree trained based on the measured error from the previously trained decision tree. [0158]: the service valuation model may be a gradient boosted machine based off of iteratively trained decisions trees);
Regarding the claim limitations below, Berk in view of Spiegel and Zhou shows:
automatically generating, by the one or more servers, predicted demand using the machine learning algorithm based on a set of historical demand data, the predicted demand being generated according to a particular interval and representing customer demand of the on-demand delivery platform for the plurality of geographic regions and for a period of time, the set of historical demand data representing completed deliveries
Berk: [0092]: delivery parameters may include time, date, traffic, weather, historical courier performance, and size of markets, [0140]: dates may fall on holidays that are historically known to be busy days. Further, Berk shows [0036]: a delivery tracking system generates ETA predictions using a predictive event model that implements machine learning to evaluate weighted factors. In some embodiments, the predictive event model may implement a neural network. In other embodiments, the predictive event model may be a gradient boosted machine or gradient boosted decision tree. [0037]: the predictive event model may iteratively update various decision trees and corresponding error measurements. [0088]: a gradient boosted machine implemented in various example embodiments may comprise a plurality of iteratively trained chained decision trees. A single decision tree may be trained at a time with each subsequent decision tree trained based on the measured error from the previously trained decision tree. [0158]: the service valuation model may be a gradient boosted machine based off of iteratively trained decisions trees), the predicted demand being generated according to a particular interval and representing customer demand of the on-demand delivery platform for the plurality of geographic regions and for a period of time (regarding this claim limitation, applicants’ specification in [58] As mentioned above, predicted demand values can be categorized in a variety of ways. In some implementations, predicted demand might be generated according to 30- minute intervals. As such the predicted demand value for a 30-minute interval can be distributed smoothly by the minute across the 30-minute interval. Similarly, for that same 30-minute interval, the total predicted supply can be spread smoothly by the minute across a 30-minute interval in a similar manner. Delivery quality module 420 can use the minute-by-minute distribution in order to come up with an accurate quality value for all times of the day. Besides a minute-by-minute basis, different periods of time may be used for a 30-minute interval. For example, a two-minute smoothing sample, five-minute smoothing sample, ten-minute smoothing sample, etc.
In light of this specification, Reference Berk does not show “predicted demand” in the claim limitation “the predicted demand being generated according to a particular interval and representing customer demand of the on-demand delivery platform for the plurality of geographic regions and for a period of time”. However, Reference Zhou shows the above limitation at least in Fig. 3 and Fig. 4 as well as [0028]-[0034]: FIG. 3 shows an exemplary graph 300 that summarizes historical sales orders associated with a customer. More particularly, the graph 300 depicts the original price 302 and coupon discount 304 redeemed by the customer at different time stamps. The time interval #304 in Fig. 3 and #404 – 406 in Fig. 4 read on the claim limitations above).
Reference Berk and Reference Zhou are analogous prior art to the claimed invention because the references generally relate to field of analyzing demand. Lastly, said references are filed before the effective filing date of the instant application; hence, said references are analogous prior-art references.
It would have been obvious to one of ordinary skill in the art at the time the invention was made for Pre-AIA to provide the teachings of Reference Zhou, particularly [0028]-[0034]: exemplary graph 300 that summarizes historical sales orders associated with a customer, in the disclosure of Reference Berk, particularly in the ways for overcoming the inflexibility related to structure which allows testing to optimize delivery valuation around a supply and demand equilibrium, or implementation of adjustments to the model (Berk: [0034]) in order to provide for a system where the objective function maximizes return-on- investment while fulfilling one or more predefined constraints as taught by Reference Zhou (see at least in [0033]) so that the process of dynamic or on demand delivery services can be made more efficient and effective.
Further, the claimed invention is merely a combination of old elements in a similar dynamic or on demand delivery field of endeavor, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that, given the existing technical ability to combine the elements as evidenced by Reference Berk in view of Reference Zhou, the results of the combination were predictable (MPEP 2143 A).
Regarding the claim limitations below, Berk in view of Spiegel and Zhou shows:
Regarding the claim limitations below:
“generating, by the one or more servers, a predicted supply based on a set of historical supply data, the predicted supply representing available delivery associates of the on-demand delivery platform for the plurality of geographic regions and for the period of time;”
Berk in view of Zhou shows “the predicted supply representing a quantity of available delivery associates of the on-demand delivery platform for the geographic region and period of time” as is shown above and the rejection and motivation are incorporated herein.
Berk shows ways for overcoming the inflexibility related to structure which allows testing to optimize delivery valuation around a supply and demand equilibrium, or implementation of adjustments to the model (Berk: [0034]). However, Berk does not show “predicted supply” in the claim above.
Spiegel shows the above claim limitations at least in [0077]: speculative shipment decision analysis by forecasting model 420… Similarly, risk tolerance for speculative shipment of packages 260 including various items may vary dependent upon volume and availability of those items. For example, forecasting model 420 may generally indicate against speculative shipment of low-volume items or items for which availability from suppliers is scarce. [0094]: inventory data supply chain data relevant to managing items in transit between supplier(s) 1020 and fulfillment center(s) 110.
Reference Berk and Reference Spiegel are analogous prior art to the claimed invention because the references generally relate to field of dynamic or on demand delivery. Lastly, said references are filed before the effective filing date of the instant application; hence, said references are analogous prior-art references.
It would have been obvious to one of ordinary skill in the art at the time the invention was made for Pre-AIA to provide the teachings of Reference Spiegel, particularly [0077]: speculative shipment decision analysis by forecasting model, in the disclosure of Reference Berk, particularly in the ways for overcoming the inflexibility related to structure which allows testing to optimize delivery valuation around a supply and demand equilibrium, or implementation of adjustments to the model (Berk: [0034]) in order to provide for a system that monitors the data relationships among elements of system… physical shipment paths exist between supplier(s) 1020 and fulfillment center(s) 110 as well as between fulfillment center(s) 110 and customers 1010. These shipper transit paths are shown as distinct from the data relationships within system 1000 as taught by Reference Spiegel (see at least in [0093]) so that the process of dynamic or on demand delivery services can be made more efficient and effective.
Further, the claimed invention is merely a combination of old elements in a similar dynamic or on demand delivery field of endeavor, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that, given the existing technical ability to combine the elements as evidenced by Reference Berk in view of Reference Spiegel, the results of the combination were predictable (MPEP 2143 A).
Regarding the claim limitations below, Berk in view of Spiegel and Zhou shows:
“generating, by the one or more servers, delivery quality values for the plurality of geographic regions and for the period of time of time based on the predicted demand and the predicted supply;”
Berk in view of Zhou shows “delivery quality values for the plurality of geographic regions and for the period of time of time based on the predicted demand and the predicted supply” as is shown above and the rejection and motivation are incorporated herein. Here, Reference Zhou shows the above limitation at least in Fig. 3 and Fig. 4 as well as [0028]-[0034]: FIG. 3 shows an exemplary graph 300 that summarizes historical sales orders associated with a customer. More particularly, the graph 300 depicts the original price 302 and coupon discount 304 redeemed by the customer at different time stamps. The time interval #304 in Fig. 3 and #404 – 406 in Fig. 4 read on the claim limitations above.
Berk does not show “predicted supply”. However, Spiegel shows the claim limitations above in [0057]: predictive modeling of a common carrier's shipping network behavior and forecasting of customer demand for various products.
Berk in view of Zhou shows “delivery quality values for the geographic region and period of time based on the predicted demand and the predicted supply” as is shown above and the rejection and motivation are incorporated herein. Here, Reference Zhou shows the above limitation at least in Fig. 3 and Fig. 4 as well as [0028]-[0034]: FIG. 3 shows an exemplary graph 300 that summarizes historical sales orders associated with a customer. More particularly, the graph 300 depicts the original price 302 and coupon discount 304 redeemed by the customer at different time stamps. The time interval #304 in Fig. 3 and #404 – 406 in Fig. 4 read on the claim limitations above.
Berk does not show “predicted supply”. However, Spiegel shows the claim limitations above in [0057]: predictive modeling of a common carrier's shipping network behavior and forecasting of customer demand for various products. [0077]: Similarly, risk tolerance for speculative shipment of packages 260 including various items may vary dependent upon volume and availability of those items. For example, forecasting model 420 may generally indicate against speculative shipment of low-volume items or items for which availability from suppliers is scarce.
It would have been obvious to one of ordinary skill in the art at the time the invention was made for Pre-AIA to provide the teachings of Reference Spiegel, particularly [0077]: speculative shipment decision analysis by forecasting model, in the disclosure of Reference Berk, particularly in the ways for overcoming the inflexibility related to structure which allows testing to optimize delivery valuation around a supply and demand equilibrium, or implementation of adjustments to the model (Berk: [0034]) in order to provide for a system that monitors the data relationships among elements of system… physical shipment paths exist between supplier(s) 1020 and fulfillment center(s) 110 as well as between fulfillment center(s) 110 and customers 1010. These shipper transit paths are shown as distinct from the data relationships within system 1000 as taught by Reference Spiegel (see at least in [0093]) so that the process of dynamic or on demand delivery services can be made more efficient and effective.
Regarding the claim limitations below, Berk in view of Spiegel and Zhou shows:
receiving, via a user interface, a first constraint and a second constraint, the first constraint being a total budget for the plurality of geographic regions, the second constraint that one incentive value is determined for each geographic region
(Berk shows “the second constraint being a quantity of incentive values per geographic region”: [0033]: couriers are incentivized to maximize compensation for a delivery for the least amount of time or effort involved. [0041]: the incentives of the couriers are more aligned with those of the merchants and customers by preventing couriers from selectively choosing larger orders over smaller orders, which would reduce volatility in compensation for deliveries across all couriers. [0152] This aligns the incentives of the couriers with the merchants and customers by preventing couriers from selectively choosing large orders over smaller orders. Thus, smaller orders and orders with inaccessible merchant locations will experience improved service quality. Berk: [0034]: Current systems for determining delivery values do not sufficiently align incentives of the couriers with those of the merchants and customers, as well as those of the delivery platform. For example, many delivery opportunities may be declined by a courier where the base pay for a delivery is the same for all deliveries in a given market location causing compensation for more difficult deliveries to be undervalued. In some cases, couriers would selectively choose to accept only delivery opportunities with larger orders due to a higher likelihood of substantial gratuity. This also caused many smaller order delivery opportunities to be declined. This may also result in high volatility and inconsistency in courier compensation. Existing systems are also inflexible and may not provide a structure which allows testing to optimize delivery valuation around a supply and demand equilibrium, or implementation of adjustments to the model. [0041] This approach more closely links the delivery value with the effort required to complete the delivery and results in compensation that is more aligned with the work associated with each delivery. Linking delivery value with effort results in one or more improvements over existing systems and mechanisms. First, the incentives of the couriers are more aligned with those of the merchants and customers by preventing couriers from selectively choosing larger orders over smaller orders, which would reduce volatility in compensation for deliveries across all couriers. Also see, [0079].
Even though, Berk shows [0099] In some embodiments, the item types in an order may be input as parameters. For example, certain dishes may be correlated with particular preparation times. In some embodiments, the size of an order may be input as predictive parameters. In some embodiments, more items within an order may correlate to longer preparation times. In some embodiments, the sub-total price of an order may also correspond to order size or order preparation time. For example, a larger sub-total may correlate to a larger amount of items within the order. Additionally, more expensive items may take longer to make, due to more ingredients, more difficulty, or more specialization in preparation. [0147] As another example, increased delivery distances may require additional effort by the courier or fuel expense. Therefore, an additional supplemental value may be added based on additional travel distance above a predetermined threshold distance, such as $0.75 per additional mile beyond 5 miles.
Berk does not explicitly show a budget and as such does not show: “a first constraint and a second constraint, the first constraint being a total budget for the plurality of geographic regions”.
However, Zhou shows the above limitation at least in [0018]: the present framework may automatically optimize various coupon parameters (e.g., redemption value, distribution date, expiration date, target customer type) so as to maximize return-on-investment while observing certain constraints (e.g., budget, time). [0024]: Coupon distribution optimizer 125 may include, for example, a return-on-investment (ROI) ratio calculator, a customer selector and a budget updater. [0030]: Each marketing campaign data record may be represented by a database table (or other data structure) that stores, for example, campaign identifier, campaign name, campaign budget, start and end timestamps of the campaign, [0031]: The user interface screen 500 may display various user-editable fields 502-510 for customizing campaign property values. The fields may include, but are not limited to, campaign name 502, campaign budget 504, target customer type 506 (e.g., new user, very important person, all, etc.), start date (or timestamp) 508 and end date (or timestamp) 510 of the marketing campaign. The budget 504 is the estimated expenditure intended for marketing purposes (e.g., coupon redemption values). The total redemption value of distributed coupons should not exceed the budget 504. [0034] Based on the historical data of sales orders and coupon distribution, the framework may seek to optimize parameters (e.g., value, distribution date, expiration date) of time-sensitive electronic coupons to offer to various customers in order to maximize the return-on-investment, given the budget constraint B and the time period constraint with start time S and end time E of the marketing campaign. [0035] Suppose there are H customized time-sensitive coupons Cn.sub.h, h=1, 2, . . . , H to be offered while maximizing the return-on-investment within the budget constraint B and the time period constraint. The objective function may then be expressed as follows: [0037], [0039]: At 208, coupon distribution optimizer 125 updates the remaining budget Br for the marketing campaign. The budget may be updated by subtracting the redemption values of distributed coupons from the currently available budget Br.
It would have been obvious to one of ordinary skill in the art at the time the invention was made for Pre-AIA to provide the teachings of Reference Zhou, particularly [0028]-[0034]: exemplary graph 300 that summarizes historical sales orders associated with a customer, in the disclosure of Reference Berk, particularly in the ways for overcoming the inflexibility related to structure which allows testing to optimize delivery valuation around a supply and demand equilibrium, or implementation of adjustments to the model (Berk: [0034]) in order to provide for a system where the objective function maximizes return-on- investment while fulfilling one or more predefined constraints as taught by Reference Zhou (see at least in [0033]) so that the process of dynamic or on demand delivery services can be made more efficient and effective.
Further, the claimed invention is merely a combination of old elements in a similar dynamic or on demand delivery field of endeavor, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that, given the existing technical ability to combine the elements as evidenced by Reference Berk in view of Reference Zhou, the results of the combination were predictable (MPEP 2143 A)); and
Regarding the claim limitations below, Berk in view of Spiegel and Zhou shows:
determining, by the one or more servers, a plurality of inventive values for the available delivery associates of the on-demand delivery platform for the identified plurality of geographic regions based at least in part on the delivery quality values and using an optimization module, wherein the determining of the plurality of incentive values comprises: (Berk: [0033]: couriers are incentivized to maximize compensation for a delivery for the least amount of time or effort involved. [0041]: the incentives of the couriers are more aligned with those of the merchants and customers by preventing couriers from selectively choosing larger orders over smaller orders, which would reduce volatility in compensation for deliveries across all couriers. [0152] This aligns the incentives of the couriers with the merchants and customers by preventing couriers from selectively choosing large orders over smaller orders. Thus, smaller orders and orders with inaccessible merchant locations will experience improved service quality. [0153] This approach would also increase courier acceptance rates, which results in improved overall efficiency, and less down time between orders. It also provides a dynamic means of adjusting courier acceptance rates by automatically determining an improved active time value. Increasing courier acceptance rates, or the likelihood of courier acceptance, of first-time delivery opportunities also ensures that more deliveries completed by more optimally available couriers.); and
Regarding the claim limitations below, Berk in view of Spiegel and Zhou shows:
identifying an objective function for maximizing delivery quality values (Berk: [0034], [0041]. [0091]: a predictive event model implementing a neural network may comprise a plurality of subnetworks, each of which function as a predictive event model to generate an estimated length of time for a particular interval of time between subsequent delivery events. Berk: [0033]: couriers are incentivized to maximize compensation for a delivery for the least amount of time or effort involved. [0041]: the incentives of the couriers are more aligned with those of the merchants and customers by preventing couriers from selectively choosing larger orders over smaller orders, which would reduce volatility in compensation for deliveries across all couriers. [0152] This aligns the incentives of the couriers with the merchants and customers by preventing couriers from selectively choosing large orders over smaller orders. Thus, smaller orders and orders with inaccessible merchant locations will experience improved service quality. [0153] This approach would also increase courier acceptance rates, which results in improved overall efficiency, and less down time between orders. It also provides a dynamic means of adjusting courier acceptance rates by automatically determining an improved active time value. Increasing courier acceptance rates, or the likelihood of courier acceptance, of first-time delivery opportunities also ensures that more deliveries completed by more optimally available couriers.); and
Regarding the claim limitations below, Berk in view of Spiegel and Zhou shows:
selecting the plurality of incentive values based at least in part on the first constraint, the second constraint, and the objective function such that a total cost of the determined plurality of incentive values is less than the total budget, each different one of the determined plurality of incentive values corresponds to a different corresponding one of the plurality of geographic regions, and the determined plurality of incentive values maximizes the delivery quality values (Berk shows “selecting the plurality of incentive values based at least in part on the first constraint, the second constraint, and the objective function such that a … of the determined plurality of incentive values is less than the total budget, each different one of the determined plurality of incentive values corresponds to a different corresponding one of the plurality of geographic regions, and the determined plurality of incentive values maximizes the delivery quality values”: [0138]: a service valuation model implementing a neural network may comprise a plurality of various computational layers, which function to generate a predicted active time value that more closely corresponds to the effort required to complete the delivery. In some embodiments, such computational layers may include, but are not limited to, linear layers, convolution layers, deconvolution layers, residual layers, quadratic layers, etc. [0033]: couriers are incentivized to maximize compensation for a delivery for the least amount of time or effort involved. [0041]: the incentives of the couriers are more aligned with those of the merchants and customers by preventing couriers from selectively choosing larger orders over smaller orders, which would reduce volatility in compensation for deliveries across all couriers. [0152] This aligns the incentives of the couriers with the merchants and customers by preventing couriers from selectively choosing large orders over smaller orders. Thus, smaller orders and orders with inaccessible merchant locations will experience improved service quality. Berk: [0034]: Current systems for determining delivery values do not sufficiently align incentives of the couriers with those of the merchants and customers, as well as those of the delivery platform. For example, many delivery opportunities may be declined by a courier where the base pay for a delivery is the same for all deliveries in a given market location causing compensation for more difficult deliveries to be undervalued. In some cases, couriers would selectively choose to accept only delivery opportunities with larger orders due to a higher likelihood of substantial gratuity. This also caused many smaller order delivery opportunities to be declined. This may also result in high volatility and inconsistency in courier compensation. Existing systems are also inflexible and may not provide a structure which allows testing to optimize delivery valuation around a supply and demand equilibrium, or implementation of adjustments to the model. [0041] This approach more closely links the delivery value with the effort required to complete the delivery and results in compensation that is more aligned with the work associated with each delivery. Linking delivery value with effort results in one or more improvements over existing systems and mechanisms. First, the incentives of the couriers are more aligned with those of the merchants and customers by preventing couriers from selectively choosing larger orders over smaller orders, which would reduce volatility in compensation for deliveries across all couriers. Also see, [0079].
Even though, Berk shows [0099] In some embodiments, the item types in an order may be input as parameters. For example, certain dishes may be correlated with particular preparation times. In some embodiments, the size of an order may be input as predictive parameters. In some embodiments, more items within an order may correlate to longer preparation times. In some embodiments, the sub-total price of an order may also correspond to order size or order preparation time. For example, a larger sub-total may correlate to a larger amount of items within the order. Additionally, more expensive items may take longer to make, due to more ingredients, more difficulty, or more specialization in preparation. [0147] As another example, increased delivery distances may require additional effort by the courier or fuel expense. Therefore, an additional supplemental value may be added based on additional travel distance above a predetermined threshold distance, such as $0.75 per additional mile beyond 5 miles.
Berk does not explicitly show a budget and as such that does not show: “a total cost of the determined plurality of incentive values is less than the total budget”
However, Zhou shows the above limitation at least in [0018]: the present framework may automatically optimize various coupon parameters (e.g., redemption value, distribution date, expiration date, target customer type) so as to maximize return-on-investment while observing certain constraints (e.g., budget, time). [0024]: Coupon distribution optimizer 125 may include, for example, a return-on-investment (ROI) ratio calculator, a customer selector and a budget updater. [0030]: Each marketing campaign data record may be represented by a database table (or other data structure) that stores, for example, campaign identifier, campaign name, campaign budget, start and end timestamps of the campaign, [0031]: The user interface screen 500 may display various user-editable fields 502-510 for customizing campaign property values. The fields may include, but are not limited to, campaign name 502, campaign budget 504, target customer type 506 (e.g., new user, very important person, all, etc.), start date (or timestamp) 508 and end date (or timestamp) 510 of the marketing campaign. The budget 504 is the estimated expenditure intended for marketing purposes (e.g., coupon redemption values). The total redemption value of distributed coupons should not exceed the budget 504. [0034] Based on the historical data of sales orders and coupon distribution, the framework may seek to optimize parameters (e.g., value, distribution date, expiration date) of time-sensitive electronic coupons to offer to various customers in order to maximize the return-on-investment, given the budget constraint B and the time period constraint with start time S and end time E of the marketing campaign. [0035] Suppose there are H customized time-sensitive coupons Cn.sub.h, h=1, 2, . . . , H to be offered while maximizing the return-on-investment within the budget constraint B and the time period constraint. The objective function may then be expressed as follows: [0037], [0039]: At 208, coupon distribution optimizer 125 updates the remaining budget Br for the marketing campaign. The budget may be updated by subtracting the redemption values of distributed coupons from the currently available budget Br. [0024] Problem formatter 122 may serve to read data from the database 127 and format the data to be readable by the other components. Consumer behavior predictor 124 may serve to predict consumer behavior during the marketing campaign period. Consumer behavior predictor 124 may include a sales timestamp predictor, a consumption value predictor and a coupon redemption value predictor. Coupon distribution optimizer 125 may serve to calculate coupon parameters based on the predicted consumer behavior to optimize coupon distribution. Coupon distribution optimizer 125 may include, for example, a return-on-investment (ROI) ratio calculator, a customer selector and a budget updater. [0030] Each coupon redemption historical record may be represented by a database table (or other data structure) that stores, for example, a coupon identifier, redemption timestamp and identifier of customer who redeemed the coupon. Each marketing campaign data record may be represented by a database table (or other data structure) that stores, for example, campaign identifier, campaign name, campaign budget, start and end timestamps of the campaign. [0031] The generation or modification of a current marketing campaign may be initiated by a user via user interface 168 at the client device 166. FIG. 5 shows an exemplary user interface screen 500 arranged to enable a user to create or edit a marketing campaign. The user interface screen 500 may be generated by, for example, a mobile application or other type of software application on the client device 166. The user interface screen 500 may display various user-editable fields 502-510 for customizing campaign property values. The fields may include, but are not limited to, campaign name 502, campaign budget 504, target customer type 506 (e.g., new user, very important person, all, etc.), start date (or timestamp) 508 and end date (or timestamp) 510 of the marketing campaign. The budget 504 is the estimated expenditure intended for marketing purposes (e.g., coupon redemption values). The total redemption value of distributed coupons should not exceed the budget 504. The target customer type 506 enables the filtering of customer types to limit the distribution of coupons to the selected customer types. The user interface screen 500 may further include an “Optimize” button 512 (or other user interface element) that the user can activate to invoke the optimization process (e.g., steps 204-220) to optimize the coupons offered during the marketing campaign. The client device 166 may also transmit the campaign property values to the problem formatter 122 in response to the activation of the “Optimize” button. [0037] In some implementations, problem formatter 122 initializes the following input parameters of the objective function (1) and constraints (2)-(5) based on the historical data and current campaign property values: (1) total budget of the campaign (B); (2) start time of campaign (S); end time of campaign (H); (3) time unit in the period of campaign (U); (4) number of time units, (5) index of time unit (I) set to 0; (6) remaining budget Br=B; (7) predicted sales order Sp.sub.ip from customer U.sub.i during the period of campaign with the predicted timestamp Tp.sub.ip, consumption value Op.sub.ip and redeemed coupon value Dp.sub.ip; (8) new customized time-sensitive electronic coupon Cd.sub.i distributed to customer U.sub.i; and (9) status flag F.sub.i of Cd.sub.i set to 1 if Cd.sub.i is redeemed, otherwise set to 0. [0039] At 208, coupon distribution optimizer 125 updates the remaining budget Br for the marketing campaign. The budget may be updated by subtracting the redemption values of distributed coupons from the currently available budget Br. More particularly, the budget may be updated by determining the following: wherein Br denotes the remaining budget, Cd.sub.i denotes the distributed coupon redemption value, i is the index of the customer, N is the total number of customers, and F.sub.i denotes the status flag of Cd.sub.i. F.sub.i is set to 1 if coupon Cd.sub.i is redeemed, otherwise set to 0. After the budget is updated, coupon distribution optimizer 125 invokes consumer behavior predictor 124 to predict consumer behavior parameters. [0043] At 214, coupon distribution optimizer 125 selects top predicted sales orders that optimizes an objective function within one or more constraints. In some implementations, the predicted sales orders that maximize return-on-investment within one or more constraints are selected. Coupon distribution optimizer 125 may select the predicted sales orders with the highest ROI ratios from the sorted list. For example, coupon distribution optimizer 125 may select a predetermined number of predicted sales orders with highest ROI ratios, wherein the total sum of redemption values of the selected orders is less than or equal to the remaining budget Br of the campaign. More particularly, coupon distribution optimizer 125 may select H Dp.sub.ip from the beginning of the sorted list with the constraint ΣDp.sub.ip≦Br, wherein Dp.sub.ip is the coupon redemption value associated with the predicted sales order Sp.sub.ipfrom customer U.sub.i in the campaign period.
It would have been obvious to one of ordinary skill in the art at the time the invention was made for Pre-AIA to provide the teachings of Reference Zhou, particularly [0028]-[0034]: exemplary graph 300 that summarizes historical sales orders associated with a customer, in the disclosure of Reference Berk, particularly in the ways for overcoming the inflexibility related to structure which allows testing to optimize delivery valuation around a supply and demand equilibrium, or implementation of adjustments to the model (Berk: [0034]) in order to provide for a system where the objective function maximizes return-on- investment while fulfilling one or more predefined constraints as taught by Reference Zhou (see at least in [0033]) so that the process of dynamic or on demand delivery services can be made more efficient and effective.
Further, the claimed invention is merely a combination of old elements in a similar dynamic or on demand delivery field of endeavor, and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that, given the existing technical ability to combine the elements as evidenced by Reference Berk in view of Reference Zhou, the results of the combination were predictable (MPEP 2143 A)));
Regarding the claim limitations below, Berk in view of Spiegel and Zhou shows:
determining by the one or more servers, from a database, that a delivery associate of the delivery associates has a history of delivery to a particular geographic region of the plurality of geographic regions (Berk: [0033]: couriers are incentivized to maximize compensation for a delivery for the least amount of time or effort involved. [0041]: the incentives of the couriers are more aligned with those of the merchants and customers by preventing couriers from selectively choosing larger orders over smaller orders, which would reduce volatility in compensation for deliveries across all couriers. [0091]-[0103]: [0101] The historical performance of a courier may be a record of the previous time durations between one or more events on courier timeline 211 for a particular courier. [0102] The historical performance of a particular merchant may also be input. This may include the average time duration between events on merchant timeline 210 for that particular merchant. The predictive event model may use this factor to assign a particular state variable to a given merchant to adjust predictions accordingly. For example, the average time for a particular merchant to prepare a particular item may be tracked and determined. [0103] In some embodiments, historical performance parameters may be organized into aggregate units for a predetermined amount of time. For example, the historical performance of a courier or merchant for the previous thirty (30) day increment is given higher weighted values. In some embodiments, the historical performance parameters for days occurring before the previous thirty (30) days are also input with lower weighted values. In some embodiments, the historical performance parameters for days occurring before the previous thirty (30) days may be discarded. [0152] This aligns the incentives of the couriers with the merchants and customers by preventing couriers from selectively choosing large orders over smaller orders. Thus, smaller orders and orders with inaccessible merchant locations will experience improved service quality. [0034]: determining delivery values do not sufficiently align incentives of the couriers with those of the merchants and customers, as well as those of the delivery platform. For example, many delivery opportunities may be declined by a courier where the base pay for a delivery is the same for all deliveries in a given market location causing compensation for more difficult deliveries to be undervalued. In some cases, couriers would selectively choose to accept only delivery opportunities with larger orders due to a higher likelihood of substantial gratuity. This also caused many smaller order delivery opportunities to be declined. This may also result in high volatility and inconsistency in courier compensation. Existing systems are also inflexible and may not provide a structure which allows testing to optimize delivery valuation around a supply and demand equilibrium, or implementation of adjustments to the model.); and
Regarding the claim limitations below, Berk in view of Spiegel and Zhou shows:
transmitting, by the one or more servers, a notification of a first one of the determined plurality of incentive values that corresponds to the particular geographic region to a client device of the delivery associate of the on-demand delivery platform, the first one of the determined plurality of incentive values being associated with a particular date for the particular geographic region (Berk: [0033]: couriers are incentivized to maximize compensation for a delivery for the least amount of time or effort involved. [0041]: the incentives of the couriers are more aligned with those of the merchants and customers by preventing couriers from selectively choosing larger orders over smaller orders, which would reduce volatility in compensation for deliveries across all couriers. [0152]: This aligns the incentives of the couriers with the merchants and customers by preventing couriers from selectively choosing large orders over smaller orders. Thus, smaller orders and orders with inaccessible merchant locations will experience improved service quality. [0034]: determining delivery values do not sufficiently align incentives of the couriers with those of the merchants and customers, as well as those of the delivery platform. For example, many delivery opportunities may be declined by a courier where the base pay for a delivery is the same for all deliveries in a given market location causing compensation for more difficult deliveries to be undervalued. In some cases, couriers would selectively choose to accept only delivery opportunities with larger orders due to a higher likelihood of substantial gratuity. This also caused many smaller order delivery opportunities to be declined. This may also result in high volatility and inconsistency in courier compensation. Existing systems are also inflexible and may not provide a structure which allows testing to optimize delivery valuation around a supply and demand equilibrium, or implementation of adjustments to the model. [0079] It is contemplated that forecasting model 420 may take into account numerous other types of dynamic variables. For example, forecasting model 420 may be more or less continuously gathering logistical, financial and other information and responsively updating indications of what packages 260 should be speculatively shipped to specific geographical areas. Additionally, it is contemplated that in some embodiments, forecasting model 420 may take similar variables into account for packages 260 that have already been speculatively shipped and are current in transit. For example, forecasting model 420 may be configured to monitor previously speculatively shipped packages 260 to determine whether those packages should be redirected to different geographical areas, based on any of the factors described above as well as time in transit, distance to the originally-specified destination geographical area, etc. As an alternative to redirection, forecasting model 420 may be configured to determine whether to offer cost incentives to potential customers, such as discounts or promotions, to increase the likelihood of a sale. Such a determination may take into account cost and product variables similar to those described previously. [0086] Dependent upon the business variable analysis, a disposition of the given speculatively shipped package 260 is determined (block 904). In various embodiments, a package disposition may include allowing the given package 260 to continue along its current path towards its current destination geographical area. Alternatively, a package disposition may include returning the given package 260 to a fulfillment center, redirecting it to another destination geographical area, or determining to offer a purchase incentive to a potential customer, for example to encourage a sale rather than an alternative disposition. This reads on “the first one of the determined incentive values being associated with a particular date for the particular geographic region”. [0077]: shows notification, also see the following paragraphs for notification: [0079], [0113], [0116]).
As per claims 3, 10 and 17: Regarding the claim limitations below, Berk in view of Spiegel and Zhou shows:
wherein generating the predicted supply includes using a machine learning algorithm configured to determine a first amount of delivery associates in relation to a first incentive value and determine a second amount of delivery associates in relation to a second incentive value (Berk: [0138]: a service valuation model implementing a neural network may comprise a plurality of various computational layers, which function to generate a predicted active time value that more closely corresponds to the effort required to complete the delivery. In some embodiments, such computational layers may include, but are not limited to, linear layers, convolution layers, deconvolution layers, residual layers, quadratic layers, etc.).
As per claims 4, 11 and 18: Regarding the claim limitations below, Berk in view of Spiegel and Zhou shows:
wherein the predicted demand is categorized according to a geographical region and a period of time ([0038]: The delivery service value may also take into account a predetermined active time value for a given location and time.).
As per claims 5, 12 and 19: Regarding the claim limitations below, Berk in view of Spiegel and Zhou shows:
wherein the predicted supply includes a first incentive value for a geographical region and a second incentive value for the geographical region (Berk: [0039]: the delivery routing system tracks the courier acceptance rate of the system for a given location and time. Various metrics may be used to determine the courier acceptance rate. For example, the courier acceptance rate may correspond to the average number of delivery opportunities that are declined for a given location and time. [0123]: the delivery service value of a given delivery opportunity is determined by multiplying the PDD by a predetermined active time value... he predetermined active time value may vary based on various factors, including location, time of day, traffic conditions, etc. This may provide a mechanism to easily evaluate and determine what constitutes fair and competitive compensation for a delivery and how it varies by geography and time of day. [0124]: the location of a merchant, customer, or courier corresponds to a defined geographic area in which such merchant, customer, or courier is located. In some embodiments, the active time value may be adjusted in various increments, such as in 30-minute increments. For example, for a given area corresponding to the location of the merchant, an active time value of $15.00 may be set for between the hours of 11:30 am and 1:00 pm.).
As per claims 6, 13 and 20: Regarding the claim limitations below, Berk in view of Spiegel and Zhou shows:
wherein generating delivery quality values includes generating a first delivery quality value based on the first incentive value for the geographical region and generating a second delivery quality value based on the second incentive value for the geographical region (Berk: [0039]: the delivery routing system tracks the courier acceptance rate of the system for a given location and time. Various metrics may be used to determine the courier acceptance rate. For example, the courier acceptance rate may correspond to the average number of delivery opportunities that are declined for a given location and time. [0123]: the delivery service value of a given delivery opportunity is determined by multiplying the PDD by a predetermined active time value... he predetermined active time value may vary based on various factors, including location, time of day, traffic conditions, etc. This may provide a mechanism to easily evaluate and determine what constitutes fair and competitive compensation for a delivery and how it varies by geography and time of day. [0124]: the location of a merchant, customer, or courier corresponds to a defined geographic area in which such merchant, customer, or courier is located. In some embodiments, the active time value may be adjusted in various increments, such as in 30-minute increments. For example, for a given area corresponding to the location of the merchant, an active time value of $15.00 may be set for between the hours of 11:30 am and 1:00 pm.).
As per claims 7 and 14: Regarding the claim limitations below, Berk in view of Spiegel and Zhou shows:
wherein determining the incentive values based at least on the delivery quality values includes selecting the second incentive value as the first incentive value provided to the delivery associate (Berk: [0039]: the delivery routing system tracks the courier acceptance rate of the system for a given location and time. Various metrics may be used to determine the courier acceptance rate. For example, the courier acceptance rate may correspond to the average number of delivery opportunities that are declined for a given location and time. [0123]: the delivery service value of a given delivery opportunity is determined by multiplying the PDD by a predetermined active time value... he predetermined active time value may vary based on various factors, including location, time of day, traffic conditions, etc. This may provide a mechanism to easily evaluate and determine what constitutes fair and competitive compensation for a delivery and how it varies by geography and time of day. [0124]: the location of a merchant, customer, or courier corresponds to a defined geographic area in which such merchant, customer, or courier is located. In some embodiments, the active time value may be adjusted in various increments, such as in 30-minute increments. For example, for a given area corresponding to the location of the merchant, an active time value of $15.00 may be set for between the hours of 11:30 am and 1:00 pm. [0141]: an updated active time value may be generated for each particular location or geographic area. The adjusted active time value may then be used to determine delivery service values for subsequent orders at operation 704. [0159] The adjusted active time value may then be used to determine service value amounts for subsequent delivery opportunities at 801. In some embodiments, an updated active time value may be generated for each predefined location or geographic area. In some embodiments the active time value may be adjusted at equal time intervals, such as at 30-minute intervals. In other embodiments, an updated active time value may be generated for each rejected order before the delivery opportunity for such order is transmitted to a subsequent courier.).
Response to Arguments
Applicants’ arguments are moot in view of the new grounds of rejection necessitated by the amendments made to previously presented claims.
Applicant’s Argument #1
Applicants argue on page(s) 8-14 of applicants remarks that the amended claims overcome previously presented rejection under 35 U.S.C. 101 (see applicants remarks for more details).
Response to Argument #1
Applicants' arguments have been fully considered; however, the examiner respectfully disagrees.
Please see the 101 rejection above and also the Note above.
The claims are directed to balancing demand and supply predictions by determining incentives to better help meet demand needs and merely use a computer to improve the performance of that determination—not the performance of a computer. (See MPEP 2106.05(a)(II)(i); A commonplace business method or mathematical algorithm being applied on a general-purpose computer, Versata Dev. Group, Inc. v. SAP Am., Inc., 793 F.3d 1306, 1334, 115 USPQ2d 1681, 1701 (Fed. Cir. 2015)).
MPEP 2106.05f - Similarly, "claiming the improved speed or efficiency inherent with applying the abstract idea on a computer" does not integrate a judicial exception into a practical application or provide an inventive concept. Intellectual Ventures I LLC v. Capital One Bank (USA), 792 F.3d 1363
MPEP 2106.05(f) iii. A process for monitoring audit log data that is executed on a general-purpose computer where the increased speed in the process comes solely from the capabilities of the general-purpose computer, FairWarning IP, LLC v. Iatric Sys., 839 F.3d 1089, 1095, 120 USPQ2d 1293, 1296 (Fed. Cir. 2016);
As discussed above in step 2A prong 2 the additional elements are recited without much technological details following the limitation are simply the preparation steps and subsequent use of machine to represent mere invocation of machinery per MPEP 2106.05(f)(2) possibly an example of a mathematical algorithm [here machine learning preparation] being applied on a general-purpose computer per MPEP 2106.05(f)(2)(i).
Here, the claims are pre-processing data for use by the machine learning model to balancing demand and supply predictions by determining incentives to better help meet demand needs. The training step is math. To overcome the 101 the output of the model would have to be used in a meaningful way.
Further, determining steps also constitute a mental process, such as an observation, evaluation, judgment, or opinion that can be performed in the human mind. The 2019 Guidance expressly recognizes such mental processes as constituting patent-ineligible abstract ideas. MPEP § 2106.04(a).
Further still, training a learning model constitutes a mathematical concept, such as the concept of using known data to set and adjust coefficients and mathematical relationships of variables that represent some modeled characteristic or phenomenon. The 2019 Guidance expressly recognizes mathematical concepts including mathematical relationships as constituting an abstract idea. MPEP § 2106.04(a).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
NPL Reference:
Kaiser, Tom. Experts predict huge growth for on-demand delivery services. Food on demand: The intersection of Food, Technology, & Mobility. https://foodondemandnews.com/10312016/experts-predict-huge-growth-for-on-demand-delivery-services/
Holger Luedorf, senior vice president of business development at Postmates, predicts substantial growth ahead for the industry, especially in retail- and convenience-oriented deliveries. Since joining the company in mid-2014, he’s seen the company grow from fewer than 10,000 deliveries a month to approximately 1.5 million deliveries by late 2016.
Foreign Reference:
(KR 102041971 B1) OH YOUNG. The reference discloses cloud delivery service system comprises: a smart delivery management system ordering delivery by issuing a label to be attached to a logistics box, constituting routing setting modeling of the least expense delivery path for delivery, calculating and providing a delivery path and costs using the constituted routing setting modeling of the least expense delivery path, and calculating costs generated by the delivery; a shipper company terminal receiving the issued label in remote from the smart delivery management system and scanning a label of a logistics box corresponding to an order history for delivery to connect the order history with the logistics box; and a delivery company terminal registering a main driving path in the smart delivery management system and receiving the calculated information of the delivery path and costs.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NANCY PRASAD whose telephone number is (571)270-3265. The examiner can normally be reached M-F: 8:00 AM - 4:30 PM EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Patricia Munson can be reached on (571)270-5396. 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.
/N.N.P/Examiner, Art Unit 3624
/PATRICIA H MUNSON/Supervisory Patent Examiner, Art Unit 3624