US20220198374A1 - Optimizing service requests in transport supply-constrained sub-regions - Google Patents
Optimizing service requests in transport supply-constrained sub-regions Download PDFInfo
- Publication number
- US20220198374A1 US20220198374A1 US17/540,562 US202117540562A US2022198374A1 US 20220198374 A1 US20220198374 A1 US 20220198374A1 US 202117540562 A US202117540562 A US 202117540562A US 2022198374 A1 US2022198374 A1 US 2022198374A1
- Authority
- US
- United States
- Prior art keywords
- menu item
- region
- determining
- fulfillment
- threshold
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012384 transportation and delivery Methods 0.000 claims abstract description 79
- 238000002360 preparation method Methods 0.000 claims abstract description 8
- 238000012544 monitoring process Methods 0.000 claims abstract 2
- 238000000034 method Methods 0.000 claims description 25
- 230000015654 memory Effects 0.000 claims description 19
- 230000004044 response Effects 0.000 claims description 7
- 238000005457 optimization Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000007423 decrease Effects 0.000 description 4
- 230000001960 triggered effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000001413 cellular effect Effects 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003190 augmentative effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
Definitions
- On-demand food delivery requires requesting users to request a menu item from menu listings of individual suppliers.
- the requests are typically processed by the restaurants themselves, which can either deliver the requested item after preparation, or the requesting user can coordinate with a third-party to pick up the requesting item for personalized delivery.
- FIG. 1 is a block diagram illustrating an example network computing system implementing an on-demand coordinated delivery service, in accordance with examples described herein;
- FIG. 2 is a block diagram illustrating an example computing device executing a service application for communicating with a network computing system, according to examples described herein;
- FIGS. 3A and 3B illustrate example user interfaces listing available menu items, according to examples described herein;
- FIG. 4 is a flow chart describing an example method of coordinating menu item delivery, according to various examples
- FIG. 5 is a flow chart describing an example method of implementing dynamic cost optimization for menu item delivery in constrained conditions, according to various examples.
- FIG. 6 is a block diagram that illustrates a computer system upon which examples described herein may be implemented.
- a delivery service (e.g., an on-demand food delivery service) can be managed by a network-based computing system by connecting requesting users, delivery drivers and/or vehicles, and menu item suppliers (e.g., restaurants) via designated applications specific to the delivery service.
- menu item requests are fulfilled by coordinating between available vehicles and the menu item suppliers to ensure the requested item has been prepared or can be prepared quickly, and a selected vehicle can be assigned to pick up the requested item before the request is made (e.g., based on demand forecasting) or to pick up the requested item after the request is made, and deliver the item to the requesting user.
- the computing system receives a request, then transmits the request to the requested menu item supplier for preparation, and finally selects a vehicle from a set of candidate vehicles to deliver the item to the requesting user.
- a high cost result can occur when the request is transmitted to the menu item supplier, the menu item supplier prepares the requested item, but no delivery vehicle is available to fulfill the request (e.g., due to a failure in vehicle supply forecasting for a specified sub-region, a higher than usual volume of received item requests, or lower than usual transport supply conditions).
- the operator of the delivery service may be accountable for the cancellation of the request as well as the loss of the prepared menu item.
- the computing system can monitor current vehicle supply conditions and current request demand for each sub-region of a delivery service region.
- supply-constrained conditions e.g., based on an equilibrium threshold being crossed between received requests versus available vehicles, and/or a divergence threshold between forecasted vehicle supply and current vehicle supply
- the computing system can be triggered to operate under a supply-constrained mode, as opposed to a default mode or standard mode, for the given sub-region, which can result in a set of logistical optimizations for the sub-region that significantly reduces or eliminates the costs and risks associated with request cancellation and/or menu item loss.
- the computing system can initiate the set of logistical optimizations by placing each received menu item request into a request queue, and associating each request in the queue with a timer and dynamic cost optimizer that dynamically (e.g., every five seconds) determines a set of probabilities for one or more of the following: (i) the user self-cancelling the request at any given moment (e.g., due to the delay in confirming the request and/or releasing the request to the menu item supplier), or (ii) matching the requesting user to an available delivery vehicle given the supply-constrained conditions.
- a timer and dynamic cost optimizer that dynamically (e.g., every five seconds) determines a set of probabilities for one or more of the following: (i) the user self-cancelling the request at any given moment (e.g., due to the delay in confirming the request and/or releasing the request to the menu item supplier), or (ii) matching the requesting user to an available delivery vehicle given the supply-constrained conditions.
- the computing system determines an expected cost of continuing to delay the release of the request to the menu item supplier (e.g., lost opportunity of the requesting user self-cancelling) versus an expected cost of releasing the request to the menu item supplier (e.g., including the risk of not securing a delivery vehicle).
- releasing the request to the menu item supplier can correspond to transmitting, over one or more networks, a message or set of data that identifies the item(s) that the menu item that a requesting user has ordered to a computing device associated with the menu item supplier (e.g., a device on premise at a restaurant or kitchen).
- An operator of the menu item supplier can accept or decline the request.
- the computing system can release the request to the menu item supplier.
- the computing system can determine when to either transmit a request cancelation to the requesting user or transmit the request to the menu item supplier for fulfillment.
- the computing system can avoid the highest cost result of both a request cancelation instigated by the computing system and menu item loss. Furthermore, by triggering the supply-constrained queue for supply-constrained sub-regions, the computing system can minimize the costs to the on-demand delivery service (e.g., cost of lost opportunity, reduced goodwill, recompensing menu item suppliers, etc.).
- the on-demand delivery service e.g., cost of lost opportunity, reduced goodwill, recompensing menu item suppliers, etc.
- examples described herein achieve a technical solution to current technical problems experienced in the field of remote, on-demand item delivery services.
- the computing system described herein triggers a request queue and dynamic cost optimization techniques before releasing item requests to item suppliers when the supply of transport providers crosses below a certain threshold.
- Using this probability-based approach to item request fulfillment in transport supply constrained conditions significantly mitigates or eliminates current limitations to provider-supply forecasting models currently implemented in the industry.
- a computing device refers to devices corresponding to desktop computers, cellular devices or smartphones, personal digital assistants (PDAs), laptop computers, virtual reality (VR) or augmented reality (AR) headsets, tablet devices, television (IP Television), etc., that can provide network connectivity and processing resources for communicating with the system over a network.
- PDAs personal digital assistants
- VR virtual reality
- AR augmented reality
- a computing device can also correspond to custom hardware, in-vehicle devices, or on-board computers, etc.
- the computing device can also operate a designated application configured to communicate with the network service.
- One or more examples described herein provide that methods, techniques, and actions performed by a computing device are performed programmatically, or as a computer-implemented method.
- Programmatically means through the use of code or computer-executable instructions. These instructions can be stored in one or more memory resources of the computing device.
- a programmatically performed step may or may not be automatic.
- a programmatic module, engine, or component can include a program, a sub-routine, a portion of a program, or a software component or a hardware component capable of performing one or more stated tasks or functions.
- a module or component can exist on a hardware component independently of other modules or components. Alternatively, a module or component can be a shared element or process of other modules, programs or machines.
- computing devices including processing and memory resources.
- one or more examples described herein may be implemented, in whole or in part, on computing devices such as servers, desktop computers, cellular or smartphones, personal digital assistants (e.g., PDAs), laptop computers, VR or AR devices, printers, digital picture frames, network equipment (e.g., routers) and tablet devices.
- one or more computing device can have direct API integration into another computing device to at least partially perform the operations described herein (e.g., a point-of-sale terminal of a menu item supplier having direct API connectivity with the disclosed computing system).
- Memory, processing, and network resources may all be used in connection with the establishment, use, or performance of any example described herein (including with the performance of any method or with the implementation of any system).
- one or more examples described herein may be implemented through the use of instructions that are executable by one or more processors. These instructions may be carried on a computer-readable medium.
- Machines shown or described with figures below provide examples of processing resources and computer-readable mediums on which instructions for implementing examples disclosed herein can be carried and/or executed.
- the numerous machines shown with examples of the invention include processors and various forms of memory for holding data and instructions.
- Examples of computer-readable mediums include permanent memory storage devices, such as hard drives on personal computers or servers.
- Other examples of computer storage mediums include portable storage units, such as CD or DVD units, flash memory (such as carried on smartphones, multifunctional devices or tablets), and magnetic memory.
- Computers, terminals, network enabled devices are all examples of machines and devices that utilize processors, memory, and instructions stored on computer-readable mediums. Additionally, examples may be implemented in the form of computer-programs, or a computer usable carrier medium capable of carrying such a program.
- FIG. 1 is a block diagram illustrating an example network computing system implementing an on-demand coordinated delivery service, in accordance with examples described herein.
- each participating menu item supplier 193 e.g., a restaurant
- the network computing system 100 can connect with the network computing system 100 over one or more networks 180 via a supplier interface 105 to provide the offered menu items for coordinated on-demand delivery.
- the menu items can comprise images and/or descriptive terms of food and/or drink items to be provided by the supplier 193 for on-demand delivery.
- the network computing system 100 can further include a user device interface 125 that connects with user devices 195 executing an on-demand service application 196 .
- Requesting users 197 can select from a menu of listed menu items for on-demand delivery via a user interface of the delivery service application 196 .
- the computing system 100 can further include a provider device interface 115 and can receive location data, via the provider device interface 115 , from the provider devices 191 of drivers 190 or vehicles 194 operating throughout the delivery service region (e.g., a metropolitan area).
- each transport vehicle 194 may also include an inventory of menu items being offered to the requesting users 197 .
- the network computing system 100 can take into account the inventory of menu items being currently transported in each transport vehicle 194 .
- the computing system 100 can forecast demand for the menu items throughout the delivery service region and coordinate with the menu item suppliers 193 and delivery providers 191 to prepare the items and load them into the delivery vehicles, which the coordination engine 150 can then route to forecasted “hot spots” to anticipate menu items requests and induce faster delivery.
- the on-demand service described herein can provide for more immediate on-demand delivery by forecasting menu item demand (e.g., based on historical data), coordinating the loading of inventory (e.g., comprising menu items from the suppliers 193 ) onto the transport vehicles 194 prior to receiving requests, and in some aspects, routing the transport vehicles 194 around the given service region with inventory on-board based on the demand forecasting while receiving menu item requests from the user devices 195 .
- forecasting menu item demand e.g., based on historical data
- inventory e.g., comprising menu items from the suppliers 193
- examples described herein can coordinate between suppliers 193 , requesting users 197 , and drivers 190 or transport vehicles 194 in a more traditional manner.
- the vehicles 194 may operate without being pre-supplied with menu items from the suppliers 193 .
- the coordination engine 150 can submit the request to a supplier 193 that prepares the requested item coordination engine 150 and matches the request to an optimal driver 190 or vehicle 194 for delivery to the user 197 .
- the coordination engine 150 can determine the current locations, current routes and upcoming deliveries, and/or the current inventory of proximate transport vehicles 194 to the current location of the requesting user 197 (e.g., within four miles).
- the coordination engine 150 can select a most optimal transport vehicle 194 based on distance, time, inventory, and/or additional utility metrics, such as transport vehicle supply, inventory supply, and menu item demand within individual localities or sub-regions of the delivery service region.
- the coordination engine 150 may then transmit a delivery invitation to the driver device 191 of the driver 190 of the optimal transport vehicle 194 .
- the driver 190 can accept or decline the invitation.
- the coordination engine 150 can provide the provider device 191 with a shortest or most optimal route to the rendezvous location with the requesting user 197 , or can add the delivery location to a current route and delivery schedule of the vehicle 194 . If declined, the coordination engine 150 can repeat the optimization process of identifying a next most optimal transport vehicle 194 , and transmit another delivery invitation to the driver 190 of that vehicle 194 —and repeat the sequence, if needed, until a driver 190 or vehicle 194 accepts the delivery invitation.
- a coordination engine 150 of the network computing system can communicate with drivers 190 of transport vehicles 194 via an executing driver application 192 and a driver device interface 115 to coordinate the on-demand delivery of the selected menu item.
- the requesting user 197 may make a selection on a menu item and confirm purchase via the on-demand service application 196 executing on the user's computing device 195 .
- Request data indicating the selected menu item can be transmitted to the network computing system 100 over the one or more networks 180 , and can be processed by the coordination engine 150 .
- the menu item request can include location information indicating the current location of the user 197 , or the user 197 can input a rendezvous location to meet with a delivery driver 190 .
- the computing system 100 can further include a provider monitor 140 and transport supply forecasting engine 160 .
- the provider monitor 140 can receive the location data from the transport vehicles 194 , and can further receive status information of the transport providers 190 , which can indicate availability, whether the vehicle 194 is currently matched to a request, the current inventory of the vehicle 194 , and the like. Based on the location data, the provider monitor 140 can monitor current transport provider supply conditions in each sub-region of the delivery service region. For example, the provider monitor 140 can parse the delivery service region into sub-regions and monitor the supply conditions of the transport providers 190 at any given time.
- the computing system 160 can further include a transport supply forecasting engine 160 —distinct from forecasting menu item demand from requesting users 197 , or forecasting menu item supply from the suppliers 193 .
- the transport supply forecasting engine 160 can forecast the supply of available transport providers 190 and/or transport vehicles 194 in each sub-region or select sub-regions (e.g., low demand or more rural sub-regions) of the delivery service area.
- the forecasting engine 160 can generate these supply forecasts based historical data, time of day, day of the week, current weather conditions, and the like.
- the forecasting engine 160 can generate a supply forecast for transport providers 190 and/or vehicles 194 , which can be utilized by the coordination engine 150 and the provider monitor 140 to anticipate transport supply shortages and/or compel the movement of transport providers 190 and/or vehicles 194 to supply constrained sub-regions (e.g., via a financial incentive, surge pricing tools, through expedition routing, and the like).
- the provider monitor 140 can receive demand data from the coordination engine 150 , which can indicate the current demand from requesting users 197 for each menu item in each sub-region. Additionally or alternatively, the provider monitor 140 can receive item supply data from the coordination engine 150 , indicating the current availability of menu items and/or current capacity to make menu items by the item suppliers 193 . Based on one or more of a transport supply forecast for a given sub-region, the item supply data, the demand data, and/or the current transport supply conditions, the provider monitor 140 can trigger a supply constrained mode for the given sub-region. This supply constraint trigger can indicate to the coordination engine 150 that the supply conditions of transport providers 190 and/or available vehicles 194 for the sub-region is constrained in comparison to current item demand and/or item availability.
- the provider monitor 140 triggers the supply constrained mode when the number of available transport providers in a target sub-region is less than a current demand for menu items. For example, the provider monitor 140 can dynamically determine a ratio between current item requests received from the sub-region and the current number of available transport providers. When that ratio drops below a certain equilibrium threshold (e.g., 75%), the provider monitor 140 can trigger the supply-constrained mode. In alternative examples, the provider monitor 140 can perform an optimization based on the current demand for menu items, current available transport providers 190 , and/or available menu items to determine an acceptable or optimal range of transport providers in the sub-region to maintain equilibrium in the target sub-region. When the number of available transport providers 190 drops below that acceptable range, the provider monitor 140 can trigger the supply-constrained mode.
- a certain equilibrium threshold e.g. 75%)
- the provider monitor 140 can execute a statistical model, using the demand data, item supply data, and/or location and status data of transport providers 190 to predict the likelihood that a received item request will go unfulfilled.
- the coordination engine 150 can determine whether to reject or cancel the item request based on the predicted likelihood. For example, if the predicted likelihood is above a predetermined threshold (e.g., 75%), then the coordination engine 150 can transmit a cancelation notification to the computing device 195 of the user 197 that transmitted the item request. In further examples, if the predicted likelihood is above the predetermined threshold, the coordination engine 150 can input the item request into a queue 155 and associate the request with a dynamic cost optimizer 156 , as described herein.
- a predetermined threshold e.g. 75%)
- a sub-region can comprise a physical area of the delivery service region encompassed by a geo-fence (e.g., based on population, like area, or a combination of the two).
- a sub-region can comprise an area in which the menu items of suppliers 193 can practically be delivered (e.g., the historical extent in each direction of a supplier 193 in which requests area made for menu items from that supplier 193 ).
- a sub-region can comprise an area in which menu items from a particular supplier 193 or group of suppliers 193 are offered to requesting users 197 by the computing system 100 (e.g., through the service app 196 ). It is further contemplated that the sub-regions can be supplier-specific, in which each supplier 193 is attributed with its own sub-region. Alternatively, the sub-regions can be fixed via geo-fences, and can be associated with any number of menu item suppliers 193 that supply menu items to requesting users 197 .
- the coordination engine 150 can generally delay releasing menu item requests from requesting users 197 to the item suppliers 193 until the coordination engine 150 has a high certainty of a transport provider 190 being available to deliver the requested item.
- the supply-constrained conditions may be quite brief, so the coordination engine 150 can take a “wait-and-see” approach for the next few minutes before either canceling the request (e.g., transmitting an unavailability message to the requesting user 197 with a coupon for a future menu item) or releasing the request to the menu item supplier 193 .
- the coordination engine 150 does not require certainty that a vehicle 194 or provider 190 is currently available to make the delivery. Rather, the coordination engine 150 can associate each received request with a probability of fulfillment at any given time given a set of fulfillment probability metrics.
- the supply constrained mode executed by the coordination engine 150 can cause the coordination engine 150 to implement a queue 155 for the sub-region.
- the coordination engine 150 can input each received item request from each requesting user 197 within the triggered sub-region into the queue 155 and a dynamic cost optimizer 156 can be triggered to dynamically determine a probability that the item request will be fulfilled within a set of limitations (e.g., a time limitation from when the request was received) and/or fulfillment probability metrics.
- the dynamic cost optimizer 156 continuously determines the fulfillment probability for any given item request.
- the dynamic cost optimizer 156 periodically (e.g., once every twenty seconds) determines the fulfillment probability for any given item request.
- the dynamic cost optimizer 156 can receive as input the location data of the current transport providers 190 in the target sub-region, the current status of each provider 190 , the locations of requesting users 197 who have submitted the requests, and the location of the supplier(s) 193 of the requested menu item(s).
- the cost optimizer 156 can further receive as input general or average cancelation times for users 197 and/or increasing cancelation rates of users 197 given increasing delay times.
- the dynamic cost optimizer 156 can further receive as input user-specific information about the requesting user 197 , such as cancelation history, utilization history (e.g., indicating frequency of engagement with the on-demand delivery service), and the like. These inputs can comprise the fulfillment probability metrics, with certain inputs changing continuously and others remaining static.
- details of each menu item request can be included as input for the dynamic cost optimizer 156 .
- the specified item requested, the size of the item request (e.g., twenty menu items versus a single menu item), or the price associated with the item request (e.g., a five dollar item request versus a fifty dollar item request) can be factored into the calculated fulfillment probability.
- the dynamic cost optimizer 156 can attribute a priority weighting to any one of the inputs (e.g., higher valued requests), which can cause the coordination engine 150 to increase or decrease priority in matching the request to a particular transport provider 190 .
- any one or more of the above-discussed inputs can enable the dynamic cost optimizer 156 to calculate a probability that the item request will be fulfilled prior to a time expiration (e.g., two minutes) or an estimated time that the requesting user 197 will cancel the request.
- a time expiration e.g., two minutes
- an estimated time that the requesting user 197 will cancel the request e.g., 95% probability of fulfillment
- the coordination engine 150 can release the request from the queue 155 and transmit the request to the relevant supplier 193 .
- the coordination engine 150 with high confidence of successful fulfillment—can monitor the transport providers 190 and vehicles 194 in the supply constrained sub-region and match the request to a transport provider 190 and/or vehicle 194 for item delivery to the requesting user 197 .
- the coordination engine 150 can mitigate the potential costs resulting from an unfulfilled request by canceling the request and providing a mitigative gratuity or token to the requesting user 197 (e.g., a coupon for a future requested item).
- a lower threshold e.g., 65%
- the coordination engine 150 is prevented from releasing the item request to the supplier 193 until a minimum fulfillment probability is met for the item request in the queue 155 —as determined by the dynamic cost optimizer 156 . It is contemplated that this minimum fulfillment probability will increase as the relative costs of delay increase.
- the dynamic cost optimizer 156 prevents the item request from being released to the relevant menu item supplier 193 as long as the expected cost incurred from releasing the item request is greater than the expected cost incurred from delaying further (e.g., until a next probability determination).
- the dynamic cost optimizer 156 can dynamically determine each of these expected costs (e.g., continuously or based on a scan interval) based on the inputs described herein.
- the coordination engine 150 can release the item request from the queue 155 and transmit the request to the relevant supplier 193 .
- the dynamic cost optimizer 156 can factor in the fulfillment probability or cancelation of one menu item request in the queue 155 into other items in the queue 155 .
- the cancelation of one item request can cause an increase in the fulfillment probability of the other request.
- the dynamic cost optimizer 156 can take into account cancelations, fulfillments, and/or fulfillment probabilities of other item requests within the supply-constrained sub-region and/or neighboring sub-regions.
- a primary goal of the dynamic cost optimizer 156 is to significantly reduce or minimize the costs of an unfulfilled item request. This includes the assumed reduction in goodwill from a user 197 when that user's 197 request is canceled—either by the user 197 due to delay, or by the computing system 100 due to low probability of fulfillment. These costs can further include the costs associated with a wasted menu item prepared by a supplier 193 and requested by a user 197 , but not delivered due to the transport supply-constrained conditions. In such a scenario, the delivery service typically reimburses the menu item supplier 193 for the wasted menu item and provides the requesting user 197 with a mitigative token for the cancelation.
- the supply conditions for transport providers 190 in the target sub-region can normalize given current demand from requesting users 197 and availability of menu items from the suppliers 193 .
- the provider monitor 140 can trigger the coordination engine 150 to initiate a standard coordination mode in which menu item requests are automatically released to the suppliers 193 when received, with a relative certainty that transport supply conditions are currently robust.
- FIG. 2 is a block diagram illustrating an example computing device executing and operating a delivery service application 232 for communicating with a network computing system, according to examples described herein.
- the computing device 200 can comprise a mobile computing device, such as a smartphone, tablet computer, laptop computer, VR or AR headset device, and the like.
- the computing device 200 can include telephony features such as a microphone 245 , a camera 250 , and a communication interface 210 to communicate with external entities using any number of wireless communication protocols.
- the computing device 200 can further include a positioning module 260 and an inertial measurement unit 264 that includes one or more accelerometers, gyroscopes, or magnetometers.
- the computing device 200 can store a designated delivery service application 232 in a local memory 230 .
- the memory 230 can store additional applications executable by one or more processors 240 of the computing device 200 , enabling access and interaction with one or more host servers over one or more networks 280 .
- the computing device 200 can be operated by a requesting user 197 through execution of the on-demand service application 232 .
- the computing device 200 can further be operated by a transport provider 190 through execution of a provider application 234 .
- the computing device 200 can be operated by a supplier 193 through execution of a supplier application 236 .
- the user can select the service application 232 via a user input on the display screen 220 , which can cause the service application 232 to be executed by the processor 240 .
- a user application interface 222 can be generated on the display screen 220 , which can display available menu items and enable the user to submit an item request for any displayed item.
- the provider can select the provider application 234 via a user input 218 on the display screen 220 , which can cause the provider application 234 to be executed by the processor 240 .
- a provider application interface 222 can be generated on the display screen 220 , which can enable the provider to receive delivery invitations, and accept or decline these invitations.
- the provider app interface 222 can further enable the transport provider to select a current status (e.g., available, on-duty, on-break, on-trip, busy, unavailable, and the like).
- the supplier can select the supplier application 236 via a user input 218 on the display screen 220 , which can cause the supplier application 236 to be executed by the processor 240 .
- a supplier application interface 222 can be generated on the display screen 220 , which can enable the supplier to provide menu items for on-demand delivery, receive item requests, and accept or reject these requests.
- the supplier may then prepare the requested menu item, and provide the prepare menu item to a transport provider for delivery to the requesting user.
- a menu item supplier 193 can be provided with an option to automatically accept all received item requests. Accordingly, once a menu item request is released by the coordination engine 150 to this supplier 193 , the coordination engine 150 can operate under the assumption that the requested item will be prepared by the supplier 193 .
- the applications 232 , 234 , 236 can enable a communication link with a network computing system 290 over one or more networks 280 , such as the network computing system 100 as shown and described with respect to FIG. 1 .
- the processor 240 can generate user interface features using content data received from the network computing system 290 over network 280 .
- the applications 232 , 234 , 236 can enable the network computing system 290 to cause the generated interface 222 to be displayed on the display screen 220 .
- the positioning module 260 can provide location data indicating the current location of the user, transport provider, and supplier to the network system 290 to, for example, enable the network computing system 290 to coordinate on-demand delivery of selected items.
- the network computing system 290 can transmit content data to the communication interface 210 of the computing device 200 over the network(s) 280 .
- the content data can cause the executing service application 232 to display the respective interface 222 for each executing application 232 , 234 , 236 .
- the service application 232 can cause the processor 240 to transmit an item request to the network computing system 290 to enable the computer system 290 to coordinate with a supplier to prepare the item, and a transport provider to rendezvous with the user at either the user's current location, or a selected rendezvous location.
- FIGS. 3A and 3B are example user interfaces showing menu items on a computing device 200 , according to examples described herein.
- the user interface 300 can be generated on the display screen 220 of the user computing device 200 .
- the network computing system 100 provides available menu items from suppliers 193 as a scrollable list of menu items 305 .
- the scrollable list 305 may be based on an initial filter inputted by the user, such as a text search or voice input for “Pad Thai.” Accordingly, the initial filter can cause the network computing system 100 to filter out any available menu items that do not match the user's search (or similar spellings of the search), and the resultant list can be provided based on each of the recommendation metrics described herein.
- the user interface 310 displayed on the user computing device 200 can also provide a general recommendation based on the preferences of other users (e.g., when historical data is lacking for the user, or upon an input by the user to provide a popular recommendation).
- the network computing system 100 can determine a menu item supplier 193 and/or menu item from that supplier 193 that is widely popular (e.g., based on number of orders and/or rating), and cause the menu item to be displayed prominently on the user interface 310 .
- the user can select a menu item to configure an item request, which can be transmitted to the computing system 100 as described herein.
- FIGS. 4 and 5 are flow charts describing an example method of coordinating menu item delivery and implementing dynamic cost optimization for menu item delivery in supply-constrained conditions, according to various examples.
- FIGS. 4 and 5 reference may be made to reference characters representing various features of FIGS. 1 and 2 .
- the processes described with respect to FIGS. 4 and 5 may be performed by an example network computing system 100 as shown and described with respect to FIG. 1 .
- the computing system 100 can coordinate an on-demand delivery service for a service region in a standard mode ( 400 ).
- the computing system 100 receives item requests from requesting users 197 , submits the requests to relevant suppliers 193 , and coordinates with transport providers 190 or vehicles 194 to pick-up the items from the suppliers 193 and rendezvous with the requesting users 197 for delivery.
- the computing system 100 can further monitor transport supply conditions for each sub-region of the delivery service region ( 405 ).
- the sub-region can comprise a physical area of the delivery service region encompassed by a geo-fence (e.g., based on population, like area, or a combination of the two).
- the sub-region can comprise an area in which menu items from one or more suppliers 193 are offered to requesting users 197 by the computing system 100 (e.g., in which the menu items show up as offers on user devices).
- the computing system 100 can determine whether the transport supply within a particular sub-region is below a predetermined equilibrium threshold ( 410 ). If not ( 412 ), then the computing system 100 can continue to coordinate on-demand delivery in the standard mode ( 400 ). However, if so ( 414 ), then the computing system 100 can initiate a supply-constrained mode for the sub-region ( 415 ), which is described in detailed with respect to FIG. 5 .
- the computing system 100 can receive items requests from requesting users 197 in the sub-region ( 510 ).
- the computing system 100 can queue each received item request and dynamically determine a probability of fulfillment of each item request ( 515 ). In doing so, the computing system 100 can execute a dynamic cost optimizer 156 for each request which determines the probability of fulfillment given a set of fulfillment probability metrics specific to each request, as described above with respect to FIG. 1 .
- the computing system 100 can determine whether the minimum threshold for fulfillment has been exceeded ( 520 ). If not ( 522 ), then the computing system 100 can continue delaying the release of the request and recalculating the fulfillment probability in a subsequent iteration ( 515 ). However, if the minimum threshold is exceeded ( 524 ), then the computing system 100 can release the request to the relevant supplier 193 and coordinate delivery ( 525 ).
- the dynamic cost optimizer 156 can generally determine whether to cancel the item request from the user ( 530 ). In certain implementations, this determination can flow from the same fulfillment probability calculation described herein. In such examples, if the fulfillment probability remains above a certain cancelation threshold (e.g., 65% fulfillment probability) ( 532 ), then the computing system 100 can keep the request in the queue 155 and continue with the dynamic cost optimization calculation. However, when the fulfillment probability drops below the cancelation threshold ( 534 ), the computing system 100 can cancel the request by transmitting a cancelation notice to the requesting user 197 ( 535 ).
- a certain cancelation threshold e.g., 65% fulfillment probability
- the dynamic cost optimizer 156 prevents the item request from being released to the relevant menu item supplier 193 as long as the expected cost incurred from releasing the item request to the supplier 193 is greater than the expected cost incurred from delaying further (e.g., until a next probability determination).
- FIG. 6 is a block diagram that illustrates a computer system upon which examples described herein may be implemented.
- a computer system 600 can be implemented on, for example, a server or combination of servers.
- the computer system 600 may be implemented as part of a network service, such as described in FIGS. 1 through 5 .
- the computer system 100 may be implemented using a computer system 600 such as described by FIG. 6 .
- the computer system 100 may also be implemented using a combination of multiple computer systems as described in connection with FIG. 6 .
- the computer system 600 includes processing resources 610 , a main memory 620 , a read-only memory (ROM) 630 , a storage device 640 , and a communication interface 650 .
- the computer system 600 includes at least one processor 610 for processing information stored in the main memory 620 , such as provided by a random access memory (RAM) or other dynamic storage device, for storing information and instructions which are executable by the processor 610 .
- the main memory 620 also may be used for storing temporary variables or other intermediate information during execution of instructions to be executed by the processor 610 .
- the computer system 600 may also include the ROM 630 or other static storage device for storing static information and instructions for the processor 610 .
- a storage device 640 such as a magnetic disk or optical disk, is provided for storing information and instructions.
- the communication interface 650 enables the computer system 600 to communicate with one or more networks 680 (e.g., cellular network) through use of the network link (wireless or wired). Using the network link, the computer system 600 can communicate with one or more computing devices, one or more servers, one or more databases, and/or one or more self-driving vehicles. In accordance with examples, the computer system 600 receives requests from mobile computing devices of individual users.
- the executable instructions stored in the memory 630 can include coordination instructions 628 and cost optimization instructions 632 .
- the instructions and data stored in the memory 620 can be executed by the processor 610 to implement the functions of an example computer system 100 of FIG. 1 .
- the processor 610 can execute the coordination instructions 628 to receive menu item requests and coordinate delivery of menu items from suppliers to requesting users.
- the processor 910 executes the cost optimization instructions 632 for a particular sub-region when that sub-region is in a supply-constrained transport environment. The cost optimization instructions 632 cause the processor 610 to queue received request from a particular sub-region, and dynamically determine a fulfillment probability that ultimately results in the item request either being canceled or released to the supplier for preparation and delivery.
- Examples described herein are related to the use of the computer system 600 for implementing the techniques described herein. According to one example, those techniques are performed by the computer system 600 in response to the processor 610 executing one or more sequences of one or more instructions contained in the main memory 620 . Such instructions may be read into the main memory 620 from another machine-readable medium, such as the storage device 640 . Execution of the sequences of instructions contained in the main memory 620 causes the processor 610 to perform the process steps described herein. In alternative implementations, hard-wired circuitry may be used in place of or in combination with software instructions to implement examples described herein. Thus, the examples described are not limited to any specific combination of hardware circuitry and software.
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
A system can implement a delivery service for a service region by monitoring, for each respective sub-region of the service region, supply conditions corresponding to transport providers available to deliver menu items from menu item suppliers to requesting users. When the supply conditions have dropped below the equilibrium threshold for a respective sub-region, the system can initiate a supply-constrained mode for the respective sub-region in which the system inputs each respective menu item request received, corresponding to a delivery location within the respective sub-region, into a queue, and dynamically determines a fulfillment probability for the respective menu item request. When the fulfillment probability of the respective menu item request exceeds a fulfillment threshold, the system can transmit the respective menu item request to a corresponding menu item supplier for preparation of a corresponding menu item and coordinate delivery of the corresponding menu item to the requesting user.
Description
- This application is a continuation application of U.S. patent application Ser. No. 16/570,631, filed Sep. 13, 2019, the entire disclosure of which is hereby incorporated herein by reference.
- On-demand food delivery requires requesting users to request a menu item from menu listings of individual suppliers. The requests are typically processed by the restaurants themselves, which can either deliver the requested item after preparation, or the requesting user can coordinate with a third-party to pick up the requesting item for personalized delivery.
- The disclosure herein is illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings in which like reference numerals refer to similar elements, and in which:
-
FIG. 1 is a block diagram illustrating an example network computing system implementing an on-demand coordinated delivery service, in accordance with examples described herein; -
FIG. 2 is a block diagram illustrating an example computing device executing a service application for communicating with a network computing system, according to examples described herein; -
FIGS. 3A and 3B illustrate example user interfaces listing available menu items, according to examples described herein; -
FIG. 4 is a flow chart describing an example method of coordinating menu item delivery, according to various examples; -
FIG. 5 is a flow chart describing an example method of implementing dynamic cost optimization for menu item delivery in constrained conditions, according to various examples; and -
FIG. 6 is a block diagram that illustrates a computer system upon which examples described herein may be implemented. - A delivery service (e.g., an on-demand food delivery service) can be managed by a network-based computing system by connecting requesting users, delivery drivers and/or vehicles, and menu item suppliers (e.g., restaurants) via designated applications specific to the delivery service. Typically, menu item requests are fulfilled by coordinating between available vehicles and the menu item suppliers to ensure the requested item has been prepared or can be prepared quickly, and a selected vehicle can be assigned to pick up the requested item before the request is made (e.g., based on demand forecasting) or to pick up the requested item after the request is made, and deliver the item to the requesting user. In this typical request and delivery process, the computing system receives a request, then transmits the request to the requested menu item supplier for preparation, and finally selects a vehicle from a set of candidate vehicles to deliver the item to the requesting user.
- However, certain inefficiencies exist in these typical request and delivery processes that can result in high costs for operating the delivery service. For example, when the computing system confirms a delivery request for a specific menu item for a requesting user, but the supplier of the requested menu item is unable to prepare it (e.g., the supplier has run out of ingredients), the goodwill of the service can suffer when the confirmed request is subsequently canceled. In another scenario, the supply of available delivery drivers or vehicles for a particular area can be constrained in relation to menu item request demand from requesting users. In the typical request and delivery process, a high cost result can occur when the request is transmitted to the menu item supplier, the menu item supplier prepares the requested item, but no delivery vehicle is available to fulfill the request (e.g., due to a failure in vehicle supply forecasting for a specified sub-region, a higher than usual volume of received item requests, or lower than usual transport supply conditions). In such a scenario, the operator of the delivery service may be accountable for the cancellation of the request as well as the loss of the prepared menu item.
- To address the technical problems arising from inaccurate vehicle supply forecasting, the computing system can monitor current vehicle supply conditions and current request demand for each sub-region of a delivery service region. When supply-constrained conditions exist (e.g., based on an equilibrium threshold being crossed between received requests versus available vehicles, and/or a divergence threshold between forecasted vehicle supply and current vehicle supply), the computing system can be triggered to operate under a supply-constrained mode, as opposed to a default mode or standard mode, for the given sub-region, which can result in a set of logistical optimizations for the sub-region that significantly reduces or eliminates the costs and risks associated with request cancellation and/or menu item loss.
- In various examples, when the supply-constrained mode is triggered for a given sub-region, the computing system can initiate the set of logistical optimizations by placing each received menu item request into a request queue, and associating each request in the queue with a timer and dynamic cost optimizer that dynamically (e.g., every five seconds) determines a set of probabilities for one or more of the following: (i) the user self-cancelling the request at any given moment (e.g., due to the delay in confirming the request and/or releasing the request to the menu item supplier), or (ii) matching the requesting user to an available delivery vehicle given the supply-constrained conditions.
- The computing system determines an expected cost of continuing to delay the release of the request to the menu item supplier (e.g., lost opportunity of the requesting user self-cancelling) versus an expected cost of releasing the request to the menu item supplier (e.g., including the risk of not securing a delivery vehicle). As described herein, releasing the request to the menu item supplier can correspond to transmitting, over one or more networks, a message or set of data that identifies the item(s) that the menu item that a requesting user has ordered to a computing device associated with the menu item supplier (e.g., a device on premise at a restaurant or kitchen). An operator of the menu item supplier can accept or decline the request.
- When the probability of finding a matching delivery driver or vehicle exceeds a certain threshold—or when the probability that the request will go unfulfilled drops below a certain threshold—the computing system can release the request to the menu item supplier. In other words, given the dynamic probabilities of self-cancellation by the user and of finding a matching driver or vehicle for delivery, the computing system can determine when to either transmit a request cancelation to the requesting user or transmit the request to the menu item supplier for fulfillment.
- Accordingly, by associating each request in the supply-constraint queue with a dynamic cost optimizer, the computing system can avoid the highest cost result of both a request cancelation instigated by the computing system and menu item loss. Furthermore, by triggering the supply-constrained queue for supply-constrained sub-regions, the computing system can minimize the costs to the on-demand delivery service (e.g., cost of lost opportunity, reduced goodwill, recompensing menu item suppliers, etc.).
- Among other benefits, examples described herein achieve a technical solution to current technical problems experienced in the field of remote, on-demand item delivery services. In particular, the computing system described herein triggers a request queue and dynamic cost optimization techniques before releasing item requests to item suppliers when the supply of transport providers crosses below a certain threshold. Using this probability-based approach to item request fulfillment in transport supply constrained conditions significantly mitigates or eliminates current limitations to provider-supply forecasting models currently implemented in the industry.
- As used herein, a computing device refers to devices corresponding to desktop computers, cellular devices or smartphones, personal digital assistants (PDAs), laptop computers, virtual reality (VR) or augmented reality (AR) headsets, tablet devices, television (IP Television), etc., that can provide network connectivity and processing resources for communicating with the system over a network. A computing device can also correspond to custom hardware, in-vehicle devices, or on-board computers, etc. The computing device can also operate a designated application configured to communicate with the network service.
- One or more examples described herein provide that methods, techniques, and actions performed by a computing device are performed programmatically, or as a computer-implemented method. Programmatically, as used herein, means through the use of code or computer-executable instructions. These instructions can be stored in one or more memory resources of the computing device. A programmatically performed step may or may not be automatic.
- One or more examples described herein can be implemented using programmatic modules, engines, or components. A programmatic module, engine, or component can include a program, a sub-routine, a portion of a program, or a software component or a hardware component capable of performing one or more stated tasks or functions. As used herein, a module or component can exist on a hardware component independently of other modules or components. Alternatively, a module or component can be a shared element or process of other modules, programs or machines.
- Some examples described herein can generally require the use of computing devices, including processing and memory resources. For example, one or more examples described herein may be implemented, in whole or in part, on computing devices such as servers, desktop computers, cellular or smartphones, personal digital assistants (e.g., PDAs), laptop computers, VR or AR devices, printers, digital picture frames, network equipment (e.g., routers) and tablet devices. In certain examples, one or more computing device can have direct API integration into another computing device to at least partially perform the operations described herein (e.g., a point-of-sale terminal of a menu item supplier having direct API connectivity with the disclosed computing system). Memory, processing, and network resources may all be used in connection with the establishment, use, or performance of any example described herein (including with the performance of any method or with the implementation of any system).
- Furthermore, one or more examples described herein may be implemented through the use of instructions that are executable by one or more processors. These instructions may be carried on a computer-readable medium. Machines shown or described with figures below provide examples of processing resources and computer-readable mediums on which instructions for implementing examples disclosed herein can be carried and/or executed. In particular, the numerous machines shown with examples of the invention include processors and various forms of memory for holding data and instructions. Examples of computer-readable mediums include permanent memory storage devices, such as hard drives on personal computers or servers. Other examples of computer storage mediums include portable storage units, such as CD or DVD units, flash memory (such as carried on smartphones, multifunctional devices or tablets), and magnetic memory. Computers, terminals, network enabled devices (e.g., mobile devices, such as cell phones) are all examples of machines and devices that utilize processors, memory, and instructions stored on computer-readable mediums. Additionally, examples may be implemented in the form of computer-programs, or a computer usable carrier medium capable of carrying such a program.
-
FIG. 1 is a block diagram illustrating an example network computing system implementing an on-demand coordinated delivery service, in accordance with examples described herein. At any given time or in accordance with a set schedule, each participating menu item supplier 193 (e.g., a restaurant) can connect with thenetwork computing system 100 over one ormore networks 180 via asupplier interface 105 to provide the offered menu items for coordinated on-demand delivery. As described herein, the menu items can comprise images and/or descriptive terms of food and/or drink items to be provided by thesupplier 193 for on-demand delivery. - The
network computing system 100 can further include auser device interface 125 that connects with user devices 195 executing an on-demand service application 196. Requesting users 197 can select from a menu of listed menu items for on-demand delivery via a user interface of thedelivery service application 196. Thecomputing system 100 can further include aprovider device interface 115 and can receive location data, via theprovider device interface 115, from theprovider devices 191 ofdrivers 190 orvehicles 194 operating throughout the delivery service region (e.g., a metropolitan area). In certain examples, eachtransport vehicle 194 may also include an inventory of menu items being offered to the requesting users 197. - Thus, according to certain implementations, in coordinating the on-demand delivery service, the
network computing system 100 can take into account the inventory of menu items being currently transported in eachtransport vehicle 194. For example, in certain examples, thecomputing system 100 can forecast demand for the menu items throughout the delivery service region and coordinate with themenu item suppliers 193 anddelivery providers 191 to prepare the items and load them into the delivery vehicles, which thecoordination engine 150 can then route to forecasted “hot spots” to anticipate menu items requests and induce faster delivery. - This is distinct from traditional delivery services, in which an item is requested by a person, and then prepared and packaged by the item supplier and finally delivered by a vehicle. The on-demand service described herein, can provide for more immediate on-demand delivery by forecasting menu item demand (e.g., based on historical data), coordinating the loading of inventory (e.g., comprising menu items from the suppliers 193) onto the
transport vehicles 194 prior to receiving requests, and in some aspects, routing thetransport vehicles 194 around the given service region with inventory on-board based on the demand forecasting while receiving menu item requests from the user devices 195. - In variations, examples described herein can coordinate between
suppliers 193, requesting users 197, anddrivers 190 ortransport vehicles 194 in a more traditional manner. For example, thevehicles 194 may operate without being pre-supplied with menu items from thesuppliers 193. When a item request is received from a requesting user 197, thecoordination engine 150 can submit the request to asupplier 193 that prepares the requesteditem coordination engine 150 and matches the request to anoptimal driver 190 orvehicle 194 for delivery to the user 197. - For each item request received from a requesting user 197, the
coordination engine 150 can determine the current locations, current routes and upcoming deliveries, and/or the current inventory ofproximate transport vehicles 194 to the current location of the requesting user 197 (e.g., within four miles). Thecoordination engine 150 can select a mostoptimal transport vehicle 194 based on distance, time, inventory, and/or additional utility metrics, such as transport vehicle supply, inventory supply, and menu item demand within individual localities or sub-regions of the delivery service region. Thecoordination engine 150 may then transmit a delivery invitation to thedriver device 191 of thedriver 190 of theoptimal transport vehicle 194. Thedriver 190 can accept or decline the invitation. - If accepted, the
coordination engine 150 can provide theprovider device 191 with a shortest or most optimal route to the rendezvous location with the requesting user 197, or can add the delivery location to a current route and delivery schedule of thevehicle 194. If declined, thecoordination engine 150 can repeat the optimization process of identifying a next mostoptimal transport vehicle 194, and transmit another delivery invitation to thedriver 190 of thatvehicle 194—and repeat the sequence, if needed, until adriver 190 orvehicle 194 accepts the delivery invitation. - Upon selection of a menu item by the user 197 (whether recommended or not), a
coordination engine 150 of the network computing system can communicate withdrivers 190 oftransport vehicles 194 via an executingdriver application 192 and adriver device interface 115 to coordinate the on-demand delivery of the selected menu item. For example, the requesting user 197 may make a selection on a menu item and confirm purchase via the on-demand service application 196 executing on the user's computing device 195. Request data indicating the selected menu item can be transmitted to thenetwork computing system 100 over the one ormore networks 180, and can be processed by thecoordination engine 150. In various examples, the menu item request can include location information indicating the current location of the user 197, or the user 197 can input a rendezvous location to meet with adelivery driver 190. - According to examples described herein, the
computing system 100 can further include aprovider monitor 140 and transportsupply forecasting engine 160. The provider monitor 140 can receive the location data from thetransport vehicles 194, and can further receive status information of thetransport providers 190, which can indicate availability, whether thevehicle 194 is currently matched to a request, the current inventory of thevehicle 194, and the like. Based on the location data, the provider monitor 140 can monitor current transport provider supply conditions in each sub-region of the delivery service region. For example, the provider monitor 140 can parse the delivery service region into sub-regions and monitor the supply conditions of thetransport providers 190 at any given time. - In certain examples, the
computing system 160 can further include a transportsupply forecasting engine 160—distinct from forecasting menu item demand from requesting users 197, or forecasting menu item supply from thesuppliers 193. The transportsupply forecasting engine 160 can forecast the supply ofavailable transport providers 190 and/ortransport vehicles 194 in each sub-region or select sub-regions (e.g., low demand or more rural sub-regions) of the delivery service area. In certain implementations, theforecasting engine 160 can generate these supply forecasts based historical data, time of day, day of the week, current weather conditions, and the like. Thus, for any given sub-region at any future given time, theforecasting engine 160 can generate a supply forecast fortransport providers 190 and/orvehicles 194, which can be utilized by thecoordination engine 150 and the provider monitor 140 to anticipate transport supply shortages and/or compel the movement oftransport providers 190 and/orvehicles 194 to supply constrained sub-regions (e.g., via a financial incentive, surge pricing tools, through expedition routing, and the like). - In various implementations, the provider monitor 140 can receive demand data from the
coordination engine 150, which can indicate the current demand from requesting users 197 for each menu item in each sub-region. Additionally or alternatively, the provider monitor 140 can receive item supply data from thecoordination engine 150, indicating the current availability of menu items and/or current capacity to make menu items by theitem suppliers 193. Based on one or more of a transport supply forecast for a given sub-region, the item supply data, the demand data, and/or the current transport supply conditions, the provider monitor 140 can trigger a supply constrained mode for the given sub-region. This supply constraint trigger can indicate to thecoordination engine 150 that the supply conditions oftransport providers 190 and/oravailable vehicles 194 for the sub-region is constrained in comparison to current item demand and/or item availability. - In one example, the provider monitor 140 triggers the supply constrained mode when the number of available transport providers in a target sub-region is less than a current demand for menu items. For example, the provider monitor 140 can dynamically determine a ratio between current item requests received from the sub-region and the current number of available transport providers. When that ratio drops below a certain equilibrium threshold (e.g., 75%), the provider monitor 140 can trigger the supply-constrained mode. In alternative examples, the provider monitor 140 can perform an optimization based on the current demand for menu items, current
available transport providers 190, and/or available menu items to determine an acceptable or optimal range of transport providers in the sub-region to maintain equilibrium in the target sub-region. When the number ofavailable transport providers 190 drops below that acceptable range, the provider monitor 140 can trigger the supply-constrained mode. - In various implementations, the provider monitor 140 can execute a statistical model, using the demand data, item supply data, and/or location and status data of
transport providers 190 to predict the likelihood that a received item request will go unfulfilled. In such implementations, thecoordination engine 150 can determine whether to reject or cancel the item request based on the predicted likelihood. For example, if the predicted likelihood is above a predetermined threshold (e.g., 75%), then thecoordination engine 150 can transmit a cancelation notification to the computing device 195 of the user 197 that transmitted the item request. In further examples, if the predicted likelihood is above the predetermined threshold, thecoordination engine 150 can input the item request into aqueue 155 and associate the request with adynamic cost optimizer 156, as described herein. - In various examples, upon receiving the supply constraint trigger for a given sub-region, the
coordination engine 150 can initiate a supply-constrained mode for that sub-region. As provided herein, a sub-region can comprise a physical area of the delivery service region encompassed by a geo-fence (e.g., based on population, like area, or a combination of the two). In variations, a sub-region can comprise an area in which the menu items ofsuppliers 193 can practically be delivered (e.g., the historical extent in each direction of asupplier 193 in which requests area made for menu items from that supplier 193). In further variations, a sub-region can comprise an area in which menu items from aparticular supplier 193 or group ofsuppliers 193 are offered to requesting users 197 by the computing system 100 (e.g., through the service app 196). It is further contemplated that the sub-regions can be supplier-specific, in which eachsupplier 193 is attributed with its own sub-region. Alternatively, the sub-regions can be fixed via geo-fences, and can be associated with any number ofmenu item suppliers 193 that supply menu items to requesting users 197. - In the supply constrained mode, the
coordination engine 150 can generally delay releasing menu item requests from requesting users 197 to theitem suppliers 193 until thecoordination engine 150 has a high certainty of atransport provider 190 being available to deliver the requested item. For example, the supply-constrained conditions may be quite brief, so thecoordination engine 150 can take a “wait-and-see” approach for the next few minutes before either canceling the request (e.g., transmitting an unavailability message to the requesting user 197 with a coupon for a future menu item) or releasing the request to themenu item supplier 193. By releasing the request to theitem supplier 193, thecoordination engine 150 does not require certainty that avehicle 194 orprovider 190 is currently available to make the delivery. Rather, thecoordination engine 150 can associate each received request with a probability of fulfillment at any given time given a set of fulfillment probability metrics. - In certain examples, once a supply-constraint trigger is received for a particular sub-region, the supply constrained mode executed by the
coordination engine 150 can cause thecoordination engine 150 to implement aqueue 155 for the sub-region. As such, thecoordination engine 150 can input each received item request from each requesting user 197 within the triggered sub-region into thequeue 155 and adynamic cost optimizer 156 can be triggered to dynamically determine a probability that the item request will be fulfilled within a set of limitations (e.g., a time limitation from when the request was received) and/or fulfillment probability metrics. In one example, thedynamic cost optimizer 156 continuously determines the fulfillment probability for any given item request. In variations, thedynamic cost optimizer 156 periodically (e.g., once every twenty seconds) determines the fulfillment probability for any given item request. - In various examples, given the supply-constrained conditions of
transport providers 190, thedynamic cost optimizer 156 can receive as input the location data of thecurrent transport providers 190 in the target sub-region, the current status of eachprovider 190, the locations of requesting users 197 who have submitted the requests, and the location of the supplier(s) 193 of the requested menu item(s). In further examples, thecost optimizer 156 can further receive as input general or average cancelation times for users 197 and/or increasing cancelation rates of users 197 given increasing delay times. In still further examples, thedynamic cost optimizer 156 can further receive as input user-specific information about the requesting user 197, such as cancelation history, utilization history (e.g., indicating frequency of engagement with the on-demand delivery service), and the like. These inputs can comprise the fulfillment probability metrics, with certain inputs changing continuously and others remaining static. - In some aspects, details of each menu item request can be included as input for the
dynamic cost optimizer 156. For example, the specified item requested, the size of the item request (e.g., twenty menu items versus a single menu item), or the price associated with the item request (e.g., a five dollar item request versus a fifty dollar item request) can be factored into the calculated fulfillment probability. In certain examples, thedynamic cost optimizer 156 can attribute a priority weighting to any one of the inputs (e.g., higher valued requests), which can cause thecoordination engine 150 to increase or decrease priority in matching the request to aparticular transport provider 190. - Any one or more of the above-discussed inputs can enable the
dynamic cost optimizer 156 to calculate a probability that the item request will be fulfilled prior to a time expiration (e.g., two minutes) or an estimated time that the requesting user 197 will cancel the request. When this probability crosses an upper threshold (e.g., 95% probability of fulfillment), then thecoordination engine 150 can release the request from thequeue 155 and transmit the request to therelevant supplier 193. Thereafter, thecoordination engine 150—with high confidence of successful fulfillment—can monitor thetransport providers 190 andvehicles 194 in the supply constrained sub-region and match the request to atransport provider 190 and/orvehicle 194 for item delivery to the requesting user 197. Conversely, when the probability crosses a lower threshold (e.g., 65%), thecoordination engine 150 can mitigate the potential costs resulting from an unfulfilled request by canceling the request and providing a mitigative gratuity or token to the requesting user 197 (e.g., a coupon for a future requested item). - Specifically, the
coordination engine 150 is prevented from releasing the item request to thesupplier 193 until a minimum fulfillment probability is met for the item request in thequeue 155—as determined by thedynamic cost optimizer 156. It is contemplated that this minimum fulfillment probability will increase as the relative costs of delay increase. - In other words, the
dynamic cost optimizer 156 prevents the item request from being released to the relevantmenu item supplier 193 as long as the expected cost incurred from releasing the item request is greater than the expected cost incurred from delaying further (e.g., until a next probability determination). In such examples, thedynamic cost optimizer 156 can dynamically determine each of these expected costs (e.g., continuously or based on a scan interval) based on the inputs described herein. When the expected cost from releasing the item request drops below the expected cost from delaying further, thecoordination engine 150 can release the item request from thequeue 155 and transmit the request to therelevant supplier 193. - In further implementations, the
dynamic cost optimizer 156 can factor in the fulfillment probability or cancelation of one menu item request in thequeue 155 into other items in thequeue 155. For example, when two item requests originate within a certain proximity of each other, the cancelation of one item request can cause an increase in the fulfillment probability of the other request. Accordingly, in the calculation of a fulfillment probability of one menu item request in thequeue 155, thedynamic cost optimizer 156 can take into account cancelations, fulfillments, and/or fulfillment probabilities of other item requests within the supply-constrained sub-region and/or neighboring sub-regions. - It is contemplated that a primary goal of the
dynamic cost optimizer 156 is to significantly reduce or minimize the costs of an unfulfilled item request. This includes the assumed reduction in goodwill from a user 197 when that user's 197 request is canceled—either by the user 197 due to delay, or by thecomputing system 100 due to low probability of fulfillment. These costs can further include the costs associated with a wasted menu item prepared by asupplier 193 and requested by a user 197, but not delivered due to the transport supply-constrained conditions. In such a scenario, the delivery service typically reimburses themenu item supplier 193 for the wasted menu item and provides the requesting user 197 with a mitigative token for the cancelation. - At any given time, the supply conditions for
transport providers 190 in the target sub-region can normalize given current demand from requesting users 197 and availability of menu items from thesuppliers 193. When conditions are normalized, the provider monitor 140 can trigger thecoordination engine 150 to initiate a standard coordination mode in which menu item requests are automatically released to thesuppliers 193 when received, with a relative certainty that transport supply conditions are currently robust. -
FIG. 2 is a block diagram illustrating an example computing device executing and operating adelivery service application 232 for communicating with a network computing system, according to examples described herein. In many implementations, thecomputing device 200 can comprise a mobile computing device, such as a smartphone, tablet computer, laptop computer, VR or AR headset device, and the like. As such, thecomputing device 200 can include telephony features such as amicrophone 245, acamera 250, and acommunication interface 210 to communicate with external entities using any number of wireless communication protocols. Thecomputing device 200 can further include apositioning module 260 and aninertial measurement unit 264 that includes one or more accelerometers, gyroscopes, or magnetometers. In certain aspects, thecomputing device 200 can store a designateddelivery service application 232 in alocal memory 230. In variations, thememory 230 can store additional applications executable by one ormore processors 240 of thecomputing device 200, enabling access and interaction with one or more host servers over one ormore networks 280. - The
computing device 200 can be operated by a requesting user 197 through execution of the on-demand service application 232. Thecomputing device 200 can further be operated by atransport provider 190 through execution of aprovider application 234. Alternatively, thecomputing device 200 can be operated by asupplier 193 through execution of asupplier application 236. For requesting user 197 implementations, the user can select theservice application 232 via a user input on thedisplay screen 220, which can cause theservice application 232 to be executed by theprocessor 240. In response, auser application interface 222 can be generated on thedisplay screen 220, which can display available menu items and enable the user to submit an item request for any displayed item. - For
transport provider 190 implementations, the provider can select theprovider application 234 via auser input 218 on thedisplay screen 220, which can cause theprovider application 234 to be executed by theprocessor 240. In response, aprovider application interface 222 can be generated on thedisplay screen 220, which can enable the provider to receive delivery invitations, and accept or decline these invitations. Theprovider app interface 222 can further enable the transport provider to select a current status (e.g., available, on-duty, on-break, on-trip, busy, unavailable, and the like). - For
supplier 193 implementations, the supplier can select thesupplier application 236 via auser input 218 on thedisplay screen 220, which can cause thesupplier application 236 to be executed by theprocessor 240. In response, asupplier application interface 222 can be generated on thedisplay screen 220, which can enable the supplier to provide menu items for on-demand delivery, receive item requests, and accept or reject these requests. In accepting a request, the supplier may then prepare the requested menu item, and provide the prepare menu item to a transport provider for delivery to the requesting user. - In some examples, a
menu item supplier 193 can be provided with an option to automatically accept all received item requests. Accordingly, once a menu item request is released by thecoordination engine 150 to thissupplier 193, thecoordination engine 150 can operate under the assumption that the requested item will be prepared by thesupplier 193. - As provided herein, the
applications network computing system 290 over one ormore networks 280, such as thenetwork computing system 100 as shown and described with respect toFIG. 1 . Theprocessor 240 can generate user interface features using content data received from thenetwork computing system 290 overnetwork 280. Furthermore, as discussed herein, theapplications network computing system 290 to cause the generatedinterface 222 to be displayed on thedisplay screen 220. - In various examples, the
positioning module 260 can provide location data indicating the current location of the user, transport provider, and supplier to thenetwork system 290 to, for example, enable thenetwork computing system 290 to coordinate on-demand delivery of selected items. In examples described herein, thenetwork computing system 290 can transmit content data to thecommunication interface 210 of thecomputing device 200 over the network(s) 280. The content data can cause the executingservice application 232 to display therespective interface 222 for each executingapplication service application 232 can cause theprocessor 240 to transmit an item request to thenetwork computing system 290 to enable thecomputer system 290 to coordinate with a supplier to prepare the item, and a transport provider to rendezvous with the user at either the user's current location, or a selected rendezvous location. -
FIGS. 3A and 3B are example user interfaces showing menu items on acomputing device 200, according to examples described herein. Referring toFIG. 3A , theuser interface 300 can be generated on thedisplay screen 220 of theuser computing device 200. In the example shown, thenetwork computing system 100 provides available menu items fromsuppliers 193 as a scrollable list ofmenu items 305. Furthermore, thescrollable list 305 may be based on an initial filter inputted by the user, such as a text search or voice input for “Pad Thai.” Accordingly, the initial filter can cause thenetwork computing system 100 to filter out any available menu items that do not match the user's search (or similar spellings of the search), and the resultant list can be provided based on each of the recommendation metrics described herein. - Referring to
FIG. 3B , theuser interface 310 displayed on theuser computing device 200 can also provide a general recommendation based on the preferences of other users (e.g., when historical data is lacking for the user, or upon an input by the user to provide a popular recommendation). Thenetwork computing system 100 can determine amenu item supplier 193 and/or menu item from thatsupplier 193 that is widely popular (e.g., based on number of orders and/or rating), and cause the menu item to be displayed prominently on theuser interface 310. In eitheruser interface FIG. 3A orFIG. 3B , the user can select a menu item to configure an item request, which can be transmitted to thecomputing system 100 as described herein. -
FIGS. 4 and 5 are flow charts describing an example method of coordinating menu item delivery and implementing dynamic cost optimization for menu item delivery in supply-constrained conditions, according to various examples. In the below description ofFIGS. 4 and 5 , reference may be made to reference characters representing various features ofFIGS. 1 and 2 . Furthermore, the processes described with respect toFIGS. 4 and 5 may be performed by an examplenetwork computing system 100 as shown and described with respect toFIG. 1 . - Referring to
FIG. 4 , thecomputing system 100 can coordinate an on-demand delivery service for a service region in a standard mode (400). In this standard mode, thecomputing system 100 receives item requests from requesting users 197, submits the requests torelevant suppliers 193, and coordinates withtransport providers 190 orvehicles 194 to pick-up the items from thesuppliers 193 and rendezvous with the requesting users 197 for delivery. Thecomputing system 100 can further monitor transport supply conditions for each sub-region of the delivery service region (405). As described herein, the sub-region can comprise a physical area of the delivery service region encompassed by a geo-fence (e.g., based on population, like area, or a combination of the two). In variations, the sub-region can comprise an area in which menu items from one ormore suppliers 193 are offered to requesting users 197 by the computing system 100 (e.g., in which the menu items show up as offers on user devices). - According to various examples, the
computing system 100 can determine whether the transport supply within a particular sub-region is below a predetermined equilibrium threshold (410). If not (412), then thecomputing system 100 can continue to coordinate on-demand delivery in the standard mode (400). However, if so (414), then thecomputing system 100 can initiate a supply-constrained mode for the sub-region (415), which is described in detailed with respect toFIG. 5 . - Referring to
FIG. 5 , in the supply-constrained mode, thecomputing system 100 can receive items requests from requesting users 197 in the sub-region (510). Thecomputing system 100 can queue each received item request and dynamically determine a probability of fulfillment of each item request (515). In doing so, thecomputing system 100 can execute adynamic cost optimizer 156 for each request which determines the probability of fulfillment given a set of fulfillment probability metrics specific to each request, as described above with respect toFIG. 1 . At any given time, thecomputing system 100 can determine whether the minimum threshold for fulfillment has been exceeded (520). If not (522), then thecomputing system 100 can continue delaying the release of the request and recalculating the fulfillment probability in a subsequent iteration (515). However, if the minimum threshold is exceeded (524), then thecomputing system 100 can release the request to therelevant supplier 193 and coordinate delivery (525). - In conjunction with determining the fulfillment probability, the
dynamic cost optimizer 156 can generally determine whether to cancel the item request from the user (530). In certain implementations, this determination can flow from the same fulfillment probability calculation described herein. In such examples, if the fulfillment probability remains above a certain cancelation threshold (e.g., 65% fulfillment probability) (532), then thecomputing system 100 can keep the request in thequeue 155 and continue with the dynamic cost optimization calculation. However, when the fulfillment probability drops below the cancelation threshold (534), thecomputing system 100 can cancel the request by transmitting a cancelation notice to the requesting user 197 (535). As such, thedynamic cost optimizer 156 prevents the item request from being released to the relevantmenu item supplier 193 as long as the expected cost incurred from releasing the item request to thesupplier 193 is greater than the expected cost incurred from delaying further (e.g., until a next probability determination). -
FIG. 6 is a block diagram that illustrates a computer system upon which examples described herein may be implemented. Acomputer system 600 can be implemented on, for example, a server or combination of servers. For example, thecomputer system 600 may be implemented as part of a network service, such as described inFIGS. 1 through 5 . In the context ofFIG. 1 , thecomputer system 100 may be implemented using acomputer system 600 such as described byFIG. 6 . Thecomputer system 100 may also be implemented using a combination of multiple computer systems as described in connection withFIG. 6 . - In one implementation, the
computer system 600 includes processingresources 610, amain memory 620, a read-only memory (ROM) 630, astorage device 640, and acommunication interface 650. Thecomputer system 600 includes at least oneprocessor 610 for processing information stored in themain memory 620, such as provided by a random access memory (RAM) or other dynamic storage device, for storing information and instructions which are executable by theprocessor 610. Themain memory 620 also may be used for storing temporary variables or other intermediate information during execution of instructions to be executed by theprocessor 610. Thecomputer system 600 may also include theROM 630 or other static storage device for storing static information and instructions for theprocessor 610. Astorage device 640, such as a magnetic disk or optical disk, is provided for storing information and instructions. - The
communication interface 650 enables thecomputer system 600 to communicate with one or more networks 680 (e.g., cellular network) through use of the network link (wireless or wired). Using the network link, thecomputer system 600 can communicate with one or more computing devices, one or more servers, one or more databases, and/or one or more self-driving vehicles. In accordance with examples, thecomputer system 600 receives requests from mobile computing devices of individual users. The executable instructions stored in thememory 630 can includecoordination instructions 628 andcost optimization instructions 632. - By way of example, the instructions and data stored in the
memory 620 can be executed by theprocessor 610 to implement the functions of anexample computer system 100 ofFIG. 1 . In various examples, theprocessor 610 can execute thecoordination instructions 628 to receive menu item requests and coordinate delivery of menu items from suppliers to requesting users. In certain implementations, the processor 910 executes thecost optimization instructions 632 for a particular sub-region when that sub-region is in a supply-constrained transport environment. Thecost optimization instructions 632 cause theprocessor 610 to queue received request from a particular sub-region, and dynamically determine a fulfillment probability that ultimately results in the item request either being canceled or released to the supplier for preparation and delivery. - Examples described herein are related to the use of the
computer system 600 for implementing the techniques described herein. According to one example, those techniques are performed by thecomputer system 600 in response to theprocessor 610 executing one or more sequences of one or more instructions contained in themain memory 620. Such instructions may be read into themain memory 620 from another machine-readable medium, such as thestorage device 640. Execution of the sequences of instructions contained in themain memory 620 causes theprocessor 610 to perform the process steps described herein. In alternative implementations, hard-wired circuitry may be used in place of or in combination with software instructions to implement examples described herein. Thus, the examples described are not limited to any specific combination of hardware circuitry and software. - It is contemplated for examples described herein to extend to individual elements and concepts described herein, independently of other concepts, ideas or systems, as well as for examples to include combinations of elements recited anywhere in this application. Although examples are described in detail herein with reference to the accompanying drawings, it is to be understood that the concepts are not limited to those precise examples. As such, many modifications and variations will be apparent to practitioners skilled in this art. Accordingly, it is intended that the scope of the concepts be defined by the following claims and their equivalents. Furthermore, it is contemplated that a particular feature described either individually or as part of an example can be combined with other individually described features, or parts of other examples, even if the other features and examples make no mentioned of the particular feature. Thus, the absence of describing combinations should not preclude claiming rights to such combinations.
Claims (21)
1.-20. (canceled)
21. A computing system comprising:
one or more processors; and
one or more memories storing instructions that are executable by the one or more processors to cause the computing system to perform operations comprising:
accessing, for at least one respective sub-region of a service region, supply conditions corresponding to one or more transport providers available to deliver one or more menu items from one or more menu item suppliers to one or more users;
determining that the supply conditions for the respective sub-region have dropped below an equilibrium threshold;
in response to determining that the supply conditions have dropped below the equilibrium threshold for the respective sub-region, determining a fulfillment probability value for a respective menu item associated with a respective user;
based on the fulfillment probability value exceeding a fulfillment threshold, transmitting a respective menu item request to a respective menu item supplier for preparation of the respective menu item; and
coordinating delivery of the respective menu item to the respective user.
22. The computing system of claim 21 , wherein determining the fulfillment probability value comprises determining a probability that the respective user will cancel the respective menu item request.
23. The computing system of claim 21 , wherein determining the fulfillment probability value comprises determining a probability that a transport provider will become available to deliver the respective menu item to the respective user prior to the respective user canceling the respective menu item request.
24. The computing system of claim 21 , wherein determining that the supply conditions for the respective sub-region have dropped below the equilibrium threshold comprises determining a transport supply forecast for the respective sub-region based on historical data.
25. The computing system of claim 21 , wherein determining the fulfillment probability value for the respective menu item associated with the respective user comprises:
obtaining at least one of: location data associated with the one or more transport providers within the respective sub-region, status data associated with the one or more transport providers, location data associated with the one or more respective users, or location data associated with the one or more menu item suppliers;
accessing a predictive model; and
determining the fulfillment probability value based on the predictive model and at least one of: the location data associated with the one or more transport providers within the respective sub-region, the status data associated with the one or more transport providers, the location data associated with the one or more respective users, or the location data associated with the one or more menu item suppliers.
26. The computing system of claim 21 , wherein determining the fulfillment probability value for the respective menu item associated with the respective user comprises:
associating each respective menu item request in a queue with a timer; and
monitoring the timer to determine whether the timer exceeds an expiration time threshold.
27. The computing system of claim 21 , wherein determining the fulfillment probability value for the respective menu item associated with the respective user comprises:
accessing data associated with the respective user, wherein the data associated with the respective user comprises at least one of: a cancelation history of the respective user and a service utilization history of the respective user.
28. The computing system of claim 21 , wherein coordinating the delivery of the respective menu item to the respective user comprises transmitting a delivery invitation to a computing device associated with a respective transport provider.
29. A computer-implemented method comprising:
accessing, for a respective sub-region of a service region, a supply condition corresponding to one or more transport providers available to deliver one or more menu items from one or more menu item suppliers;
determining that the supply condition for the respective sub-region have dropped below an equilibrium threshold;
in response to determining that the supply condition has dropped below the equilibrium threshold for the respective sub-region, determining a fulfillment probability value for a respective menu item associated with a respective user;
determining a comparison between the fulfillment probability value and a threshold;
based on the comparison of the fulfillment probability value and the threshold, determining an action associated with the respective menu item; and
transmitting, over a network, data indicative of the action associated with the respective menu item.
30. The computer-implemented method of claim 29 , wherein the threshold is a fulfillment threshold, and wherein the comparison between the fulfillment probability value and the threshold indicates the fulfillment probability value exceeds the fulfillment threshold, and
wherein the action associated with the respective menu item comprises generating a respective menu item request for preparation of the respective menu item, and
wherein transmitting the data indicative of the action associated with the respective menu item comprises transmitting the respective menu item request to a respective menu item supplier for preparation of the respective menu item.
31. The computer-implemented method of claim 30 , further comprising coordinating delivery of the respective menu item to the respective user.
32. The computer-implemented method of claim 29 , wherein the threshold is a cancelation threshold, and wherein the comparison between the fulfillment probability value and the threshold indicates the fulfillment probability value is below the cancelation threshold, and wherein the action associated with the respective menu item comprises canceling the respective menu item request for the respective menu item.
33. The computer-implemented method of claim 32 , wherein transmitting the data indicative of the action associated with the respective menu item comprises transmitting a cancelation notification to a computing device of the respective user.
34. The computer-implemented method of claim 33 , further comprising transmitting a mitigative token to the computing device of the respective user.
35. The computer-implemented method of claim 29 , wherein the respective menu item comprises food.
36. The computer-implemented method of claim 29 , wherein the one or more menu item suppliers comprise one or more restaurants.
37. One or more non-transitory computer-readable medium storing instructions that are executable by one or more processors to perform operations comprises:
accessing, for a respective sub-region of a service region, a supply condition corresponding to one or more transport providers available to deliver one or more menu items from one or more menu item suppliers;
determining that the supply condition for the respective sub-region has dropped below an equilibrium threshold;
in response to determining that the supply conditions have dropped below the equilibrium threshold for the respective sub-region, determining a fulfillment probability value for a respective menu item associated with a respective user; and
based on the fulfillment probability value exceeding a fulfillment threshold, transmitting a respective menu item request to a respective menu item supplier for preparation of the respective menu item.
38. The one or more non-transitory computer-readable medium of claim 37 , wherein determining the fulfillment probability value comprises determining a probability that the respective user will cancel the respective menu item request.
39. The one or more non-transitory computer-readable medium of claim 37 , wherein determining the fulfillment probability value comprises determining a probability that a transport provider will become available to deliver the respective menu item to the respective user prior to the respective user canceling the respective menu item request.
40. The one or more non-transitory computer-readable medium of claim 37 , wherein the operations further comprise coordinating delivery of the respective menu item to the respective user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US17/540,562 US20220198374A1 (en) | 2019-09-13 | 2021-12-02 | Optimizing service requests in transport supply-constrained sub-regions |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US16/570,631 US11216770B2 (en) | 2019-09-13 | 2019-09-13 | Optimizing service requests in transport supply-constrained sub-regions |
US17/540,562 US20220198374A1 (en) | 2019-09-13 | 2021-12-02 | Optimizing service requests in transport supply-constrained sub-regions |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/570,631 Continuation US11216770B2 (en) | 2019-09-13 | 2019-09-13 | Optimizing service requests in transport supply-constrained sub-regions |
Publications (1)
Publication Number | Publication Date |
---|---|
US20220198374A1 true US20220198374A1 (en) | 2022-06-23 |
Family
ID=74868625
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/570,631 Active US11216770B2 (en) | 2019-09-13 | 2019-09-13 | Optimizing service requests in transport supply-constrained sub-regions |
US17/540,562 Pending US20220198374A1 (en) | 2019-09-13 | 2021-12-02 | Optimizing service requests in transport supply-constrained sub-regions |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/570,631 Active US11216770B2 (en) | 2019-09-13 | 2019-09-13 | Optimizing service requests in transport supply-constrained sub-regions |
Country Status (1)
Country | Link |
---|---|
US (2) | US11216770B2 (en) |
Families Citing this family (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10190886B2 (en) | 2017-01-04 | 2019-01-29 | Uber Technologies, Inc. | Network system to determine a route based on timing data |
US11416792B2 (en) | 2017-04-19 | 2022-08-16 | Uber Technologies, Inc. | Network system capable of grouping multiple service requests |
US11436554B2 (en) | 2017-11-02 | 2022-09-06 | Uber Technologies, Inc. | Network computer system to implement predictive time-based determinations for fulfilling delivery orders |
US11449917B2 (en) | 2018-09-05 | 2022-09-20 | Uber Technologies, Inc. | Network computing system for providing interactive menus and group recommendations |
US11397911B2 (en) | 2018-11-15 | 2022-07-26 | Uber Technologies, Inc. | Network computer system to make effort-based determinations for delivery orders |
US20200410624A1 (en) * | 2019-06-26 | 2020-12-31 | Lyft, Inc. | Dynamically adjusting transportation provider pool size |
US20210082075A1 (en) * | 2019-09-14 | 2021-03-18 | Lyft, Inc. | Systems and methods for matching transportation devices based on conversion probability |
US20210142243A1 (en) * | 2019-11-12 | 2021-05-13 | Lyft, Inc. | Intelligently customizing a cancellation notice for cancellation of a transportation request based on transportation features |
US11989669B2 (en) | 2019-11-12 | 2024-05-21 | Lyft, Inc. | Intelligently customizing a cancellation notice for cancellation of a transportation request based on transportation features |
US20210192420A1 (en) * | 2019-12-19 | 2021-06-24 | Lyft, Inc. | Systems and methods for wedging transportation options for a transportation requestor device |
WO2021162630A1 (en) * | 2020-02-11 | 2021-08-19 | Grabtaxi Holdings Pte. Ltd. | Service pricing devices and service pricing method |
JP7354913B2 (en) * | 2020-04-16 | 2023-10-03 | トヨタ自動車株式会社 | Traffic management device, traffic management system, and traffic management method |
US11553618B2 (en) | 2020-08-26 | 2023-01-10 | PassiveLogic, Inc. | Methods and systems of building automation state load and user preference via network systems activity |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190130354A1 (en) * | 2017-10-30 | 2019-05-02 | DoorDash, Inc. | Depot dispatch protocol for aggregating on-demand deliveries |
Family Cites Families (108)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AU3274201A (en) | 2000-01-07 | 2001-07-24 | Ez2Get, Inc. | Method and system for automatic dispatching of delivery service |
US20050209913A1 (en) | 2000-04-05 | 2005-09-22 | Wied William J | Computer based system and method for facilitating commerce between shippers and carriers |
US6862572B1 (en) | 2000-04-21 | 2005-03-01 | De Sylva Robert F. | System and method for facilitating interaction between businesses, delivery agents, and customers |
US7139721B2 (en) | 2000-05-10 | 2006-11-21 | Borders Louis H | Scheduling delivery of products via the internet |
US7912744B2 (en) | 2001-01-12 | 2011-03-22 | Energy Control Technologies | Automated service broker |
US20020152128A1 (en) | 2001-04-13 | 2002-10-17 | Charles Walch | System and method for delivery of remotely ordered items |
US20020188492A1 (en) | 2001-06-11 | 2002-12-12 | Borton Robert L. | Food-making, -delivery, and -carry-out system and method |
US20040030572A1 (en) | 2002-05-03 | 2004-02-12 | Helen Campbell | Same day product and document delivery management system and process |
US20040210621A1 (en) | 2003-04-18 | 2004-10-21 | Antonellis Robert J. | Method and system for order optimization |
US7119716B2 (en) | 2003-05-28 | 2006-10-10 | Legalview Assets, Limited | Response systems and methods for notification systems for modifying future notifications |
US20040260470A1 (en) | 2003-06-14 | 2004-12-23 | Rast Rodger H. | Conveyance scheduling and logistics system |
US10687166B2 (en) | 2004-09-30 | 2020-06-16 | Uber Technologies, Inc. | Obtaining user assistance |
US9805395B2 (en) | 2012-01-19 | 2017-10-31 | Dizpersion Corporation | Online marketing system and method |
EP2135200A4 (en) | 2007-02-12 | 2011-12-28 | Sean O'sullivan | Shared transport system and service network |
US20090048890A1 (en) | 2007-08-16 | 2009-02-19 | Burgh Stuart G | Delivery Management System for Quick Service Restaurants |
US20100153279A1 (en) | 2008-09-30 | 2010-06-17 | Walter Zahn | Systems and methods for global transportation,vetting, and payment |
US8315802B2 (en) | 2009-02-11 | 2012-11-20 | Telogis, Inc. | Systems and methods for analyzing the use of mobile resources |
EP2507753A4 (en) * | 2009-12-04 | 2013-10-30 | Uber Technologies Inc | System and method for arranging transport amongst parties through use of mobile devices |
US20110258134A1 (en) | 2010-04-16 | 2011-10-20 | Klassic Corporation | Method and system for providing adaptive processing and delivery of food catering orders |
US10032210B2 (en) | 2011-02-08 | 2018-07-24 | Cfph, Llc | Apparatus, article of manufacture and methods for purchasing arbitrage |
US20120203619A1 (en) | 2011-02-09 | 2012-08-09 | Lutnick Howard W | Multi-system distributed processing of group goals |
US20120253878A1 (en) | 2011-03-29 | 2012-10-04 | Trapeze Software Inc. | Method and system for scheduling paratransit service |
US20130031001A1 (en) | 2011-07-26 | 2013-01-31 | Stephen Patrick Frechette | Method and System for the Location-Based Discovery and Validated Payment of a Service Provider |
US20140214465A1 (en) | 2012-05-26 | 2014-07-31 | Israel L'Heureux | Processing restaurant orders within computing systems |
US9066206B2 (en) | 2012-07-03 | 2015-06-23 | Uber Technologies, Inc. | System and method for providing dynamic supply positioning for on-demand services |
US9569100B2 (en) | 2012-07-22 | 2017-02-14 | Magisto Ltd. | Method and system for scribble based editing |
CN104885485A (en) | 2012-08-07 | 2015-09-02 | 投石通信有限公司 | System for automatically matching a service requestor with a service provider based on their proximity and establishing a voice call between them |
US20140058902A1 (en) | 2012-08-21 | 2014-02-27 | Ovni, Inc. | Distributed system for remote ordering |
GB201215193D0 (en) | 2012-08-25 | 2012-10-10 | Dalp Daniel | Order delivery system |
WO2014052732A1 (en) | 2012-09-28 | 2014-04-03 | Intercontinental Great Brands Llc | System and method for suggesting commestibles |
WO2014099680A2 (en) | 2012-12-17 | 2014-06-26 | United States Postal Service | System and method of coordinating distribution of an item |
US20140188750A1 (en) | 2012-12-26 | 2014-07-03 | Alternative Courier, Inc. | Method For Shipping |
KR20140101501A (en) | 2013-02-08 | 2014-08-20 | 에스케이플래닛 주식회사 | Method for goods purchase of location information, system and apparatus thereof |
US20140229099A1 (en) | 2013-02-12 | 2014-08-14 | Broadcom Corporation | Location aware appointment management application |
US20160035248A1 (en) | 2013-03-14 | 2016-02-04 | Sciencestyle Capital Partners, Llc | Providing Food-Portion Recommendations to Facilitate Dieting |
US9159994B2 (en) | 2013-03-15 | 2015-10-13 | Wildcat Discovery Technologies, Inc. | High energy materials for a battery and methods for making and use |
US20140278635A1 (en) | 2013-03-15 | 2014-09-18 | Bringaroo, LLC | Delivery methods and systems utilizing a stand-by delivery driver |
US10223719B2 (en) | 2013-03-25 | 2019-03-05 | Steven B. Schoeffler | Identity authentication and verification |
US20150073925A1 (en) * | 2013-05-23 | 2015-03-12 | Gavon Augustus Renfroe | System and Method for Integrating Business Operations |
US9292889B2 (en) | 2013-06-18 | 2016-03-22 | Zume Pizza, Inc. | Systems and methods of preparing food products |
US9569766B2 (en) | 2013-11-18 | 2017-02-14 | Paypal, Inc. | Auto-detection of merchant payment preferences |
US9234757B2 (en) | 2013-11-29 | 2016-01-12 | Fedex Corporate Services, Inc. | Determining node location using a variable power characteristic of a node in a wireless node network |
US20150204684A1 (en) | 2014-01-21 | 2015-07-23 | Abtin Rostamian | Methods and systems of multi-dimensional automated ride-sharing optimization |
US9754331B1 (en) | 2014-01-30 | 2017-09-05 | Grubhub Holdings Inc. | System and method for managing group orders |
US20150248689A1 (en) | 2014-03-03 | 2015-09-03 | Sunil Paul | Systems and methods for providing transportation discounts |
US20150363843A1 (en) | 2014-04-23 | 2015-12-17 | United Parcel Service Of America, Inc. | Dynamic provisioning of pick-up, delivery, transportation, and/or sortation options |
US20150310379A1 (en) | 2014-04-28 | 2015-10-29 | Ford Global Technologies, Llc | Shared vehicle systems and methods |
US20150347964A1 (en) | 2014-06-03 | 2015-12-03 | Hti, Ip, L.L.C. | Method and system for distributing delivery of items |
US20160012391A1 (en) | 2014-07-08 | 2016-01-14 | Rick Burnett | Shipper and Carrier Interaction Optimization Platform |
SG11201700669RA (en) | 2014-07-30 | 2017-02-27 | Uber Technologies Inc | Arranging a transport service for multiple users |
US20160042303A1 (en) | 2014-08-05 | 2016-02-11 | Qtech Partners LLC | Dispatch system and method of dispatching vehicles |
US20160078516A1 (en) | 2014-09-17 | 2016-03-17 | Umm Al-Qura University | Wasul transport application |
US20160104112A1 (en) | 2014-10-13 | 2016-04-14 | Marc Gorlin | Peer to Peer Delivery System |
US20160104113A1 (en) | 2014-10-13 | 2016-04-14 | Marc Gorlin | Peer to Peer Delivery System |
US10366434B1 (en) | 2014-10-22 | 2019-07-30 | Grubhub Holdings Inc. | System and method for providing food taxonomy based food search and recommendation |
US20160132792A1 (en) | 2014-11-10 | 2016-05-12 | Carzac, Inc. | Systems and methods for facilitating transportation transactions |
US20160140589A1 (en) | 2014-11-14 | 2016-05-19 | International Business Machines Corporation | Retail customer engagement zones |
US20160148287A1 (en) | 2014-11-21 | 2016-05-26 | Peach Labs, Inc. | Lunch order communication |
US10929804B2 (en) | 2014-11-21 | 2021-02-23 | Deliveright Logistics, Inc. | Delivery management systems and methods for zero-inventory distribution |
US20160171113A1 (en) | 2014-12-11 | 2016-06-16 | Connectivity, Inc. | Systems and Methods for Controlling Crawling Operations to Aggregate Information Sets With Respect to Named Entities |
US9384505B1 (en) | 2014-12-12 | 2016-07-05 | Laura Cao | System and method for image based viewing and ordering |
CA2973904A1 (en) | 2015-01-19 | 2016-07-28 | Developpement Pi Inc. | System and method for managing and optimizing delivery networks |
US10133995B1 (en) | 2015-02-19 | 2018-11-20 | Square, Inc. | Courier network management |
CN104751272A (en) | 2015-03-04 | 2015-07-01 | 径圆(上海)信息技术有限公司 | Intelligent order scheduling method and server, electric vehicle, mobile terminal and system |
US10360616B2 (en) | 2015-03-23 | 2019-07-23 | Amazon Technologies, Inc. | System and methods for prioritization of items for delivery |
US10839438B2 (en) | 2015-03-27 | 2020-11-17 | Creator, Inc. | Method for queuing orders at a food assembly apparatus |
US20160353235A1 (en) | 2015-06-01 | 2016-12-01 | Accenture Global Services Limited | Location-based order recommendations |
US20160328669A1 (en) | 2015-05-04 | 2016-11-10 | Uber Technologies, Inc. | On-demand delivery system |
US9733096B2 (en) | 2015-06-22 | 2017-08-15 | Waymo Llc | Determining pickup and destination locations for autonomous vehicles |
US10586273B1 (en) | 2015-07-30 | 2020-03-10 | DoorDash, Inc. | Managing couriers for fast deliveries |
US10148624B2 (en) | 2015-09-25 | 2018-12-04 | Mcafee, Llc | Secure service matching |
US10127519B2 (en) * | 2015-10-23 | 2018-11-13 | Prahfit, Inc. | Apparatus and method for predictive dispatch for geographically distributed, on-demand services |
KR101821752B1 (en) | 2015-11-10 | 2018-01-24 | 중소기업은행 | Order systems for delivery food |
AU2017209368B2 (en) | 2016-01-21 | 2022-10-27 | Chr. Hansen A/S | A system and a method for collecting batches of food |
CN107153882B (en) | 2016-03-03 | 2021-10-15 | 北京嘀嘀无限科技发展有限公司 | Method and system for predicting passenger taxi taking time distribution interval |
US9993735B2 (en) | 2016-03-08 | 2018-06-12 | Electronic Arts Inc. | Multiplayer video game matchmaking optimization |
US10242574B2 (en) | 2016-03-21 | 2019-03-26 | Uber Technologies, Inc. | Network computer system to address service providers to contacts |
BR112018070731A2 (en) | 2016-04-08 | 2019-02-12 | Zume, Inc. | robotic assembly of food on demand and related systems, devices and methods |
CN107424022B (en) | 2016-05-23 | 2022-02-11 | 北京嘀嘀无限科技发展有限公司 | Order pushing method and system |
US10029787B1 (en) | 2016-06-30 | 2018-07-24 | X Development Llc | Interactive transport services provided by unmanned aerial vehicles |
WO2018017903A1 (en) | 2016-07-20 | 2018-01-25 | ClusterTruck Holdings, LLC | System and method for communication routing, transportation coordination and product creation |
US11087252B2 (en) | 2016-08-16 | 2021-08-10 | Teleport Mobility, Inc. | Interactive real time system and real time method of use thereof in conveyance industry segments |
US10296200B2 (en) | 2016-09-08 | 2019-05-21 | Gt Gettaxi Limited | Drag and drop map for marking pickup and drop off locations on a predetermined line |
US20180089621A1 (en) | 2016-09-29 | 2018-03-29 | Ford Global Technologies, Llc | Method and apparatus for coordinated food delivery |
US10304147B2 (en) | 2016-10-31 | 2019-05-28 | Kevin Kelly | Drive-thru / point-of-sale automated transaction technologies and apparatus |
US10308430B1 (en) | 2016-12-23 | 2019-06-04 | Amazon Technologies, Inc. | Distribution and retrieval of inventory and materials using autonomous vehicles |
US10190886B2 (en) | 2017-01-04 | 2019-01-29 | Uber Technologies, Inc. | Network system to determine a route based on timing data |
US11614751B2 (en) | 2017-01-23 | 2023-03-28 | Massachusetts Institute Of Technology | System for on-demand high-capacity ride-sharing via dynamic trip-vehicle assignment and related techniques |
US20180225796A1 (en) | 2017-02-08 | 2018-08-09 | Uber Technologies, Inc. | Resource Allocation in a Network System |
US20180300660A1 (en) | 2017-04-18 | 2018-10-18 | Lyft, Inc. | Systems and methods for provider claiming and matching of scheduled requests |
US10839695B2 (en) | 2017-05-11 | 2020-11-17 | Uber Technologies, Inc. | Network computer system to position service providers using provisioning level determinations |
JP7202353B2 (en) | 2017-07-25 | 2023-01-11 | チェイス,アーノルド | virtual restaurant system |
US11112793B2 (en) | 2017-08-28 | 2021-09-07 | Motional Ad Llc | Mixed-mode driving of a vehicle having autonomous driving capabilities |
US10818186B2 (en) | 2017-10-18 | 2020-10-27 | Maplebear, Inc. | Optimizing task assignments in a delivery system |
US11436554B2 (en) | 2017-11-02 | 2022-09-06 | Uber Technologies, Inc. | Network computer system to implement predictive time-based determinations for fulfilling delivery orders |
US20190130320A1 (en) | 2017-11-02 | 2019-05-02 | Uber Technologies, Inc. | Network computer system to implement dynamic provisioning for fulfilling delivery orders |
US20190132699A1 (en) * | 2017-11-02 | 2019-05-02 | Uber Technologies, Inc. | Computing system to implement network delivery service |
US20190132702A1 (en) | 2017-11-02 | 2019-05-02 | Uber Technologies, Inc. | Network computer system to selectively batch delivery orders |
US11481457B2 (en) | 2017-11-28 | 2022-10-25 | Uber Technologies, Inc. | Menu personalization |
US20190295440A1 (en) | 2018-03-23 | 2019-09-26 | Nutrino Health Ltd. | Systems and methods for food analysis, personalized recommendations and health management |
US20200065734A1 (en) | 2018-08-23 | 2020-02-27 | Uber Technologies, Inc. | Network computing system to coordinate timing of delivery services |
US11449917B2 (en) | 2018-09-05 | 2022-09-20 | Uber Technologies, Inc. | Network computing system for providing interactive menus and group recommendations |
US20200090248A1 (en) | 2018-09-13 | 2020-03-19 | Uber Technologies, Inc. | Network computing system for determining interest levels for consumable items |
US20200151660A1 (en) | 2018-11-14 | 2020-05-14 | Uber Technologies, Inc. | Network computing system for detecting auditory indicators of activity |
US11397911B2 (en) | 2018-11-15 | 2022-07-26 | Uber Technologies, Inc. | Network computer system to make effort-based determinations for delivery orders |
US10467563B1 (en) | 2019-02-18 | 2019-11-05 | Coupang, Corp. | Systems and methods for computerized balanced delivery route pre-assignment |
US10467562B1 (en) * | 2019-02-18 | 2019-11-05 | Coupang, Corp. | Systems and methods for computerized balanced delivery route assignment |
US20200311618A1 (en) | 2019-03-26 | 2020-10-01 | Uber Technologies, Inc. | Multimodal network-based service |
-
2019
- 2019-09-13 US US16/570,631 patent/US11216770B2/en active Active
-
2021
- 2021-12-02 US US17/540,562 patent/US20220198374A1/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190130354A1 (en) * | 2017-10-30 | 2019-05-02 | DoorDash, Inc. | Depot dispatch protocol for aggregating on-demand deliveries |
Non-Patent Citations (2)
Title |
---|
Kawa, Arkadiusz. Fulfillment service in e-commerce logistics. LogForum; Poznan Vol. 13, Iss. 4, (2017). (Year: 2017) * |
Kawa, Arkadiusz. Fulfillment service in e-commerce logistics. LogForum; Poznan Vol. 13, Iss. 4, 2017. (Year: 2017) * |
Also Published As
Publication number | Publication date |
---|---|
US11216770B2 (en) | 2022-01-04 |
US20210081880A1 (en) | 2021-03-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20220198374A1 (en) | Optimizing service requests in transport supply-constrained sub-regions | |
US12044542B2 (en) | Optimization of network service based on an existing service | |
US11888948B2 (en) | Optimizing multi-user requests for a network-based service | |
US20190392357A1 (en) | Request optimization for a network-based service | |
CA2965397A1 (en) | Arranging on-demand services based on one or more predefined rules | |
US20190132702A1 (en) | Network computer system to selectively batch delivery orders | |
US20220156338A1 (en) | Pre-computed service metric lookup for a network-based service | |
US11416792B2 (en) | Network system capable of grouping multiple service requests | |
US20200311618A1 (en) | Multimodal network-based service | |
US20200267497A1 (en) | Contextual notifications for a network-based service | |
JP2023162429A (en) | Computing system for implementing network delivery service | |
US20220357965A1 (en) | Pre-generating data for user interface latency improvement | |
WO2022069847A1 (en) | Apparatus and methods for controlling the arrival of consumers and/or parcels |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: UBER TECHNOLOGIES, INC., CALIFORNIA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:BIVINS, DAVID;WIEN, JASON;WANG, DANIEL;AND OTHERS;SIGNING DATES FROM 20190916 TO 20190917;REEL/FRAME:058269/0105 |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |