Apparatus and method for controlling a food distribution system

Abstract

Aspects relate to a method for controlling a food delivery system, the method comprising: determining, from historical data, information regarding a dependency of a ratio of a food delivery request amount to a food delivery demand on at least one parameter including at least one of a food delivery cost and an estimated food delivery time; determining a serviceable food distribution request quantity; predicting a food distribution demand; determining a target ratio of the food delivery request amount to the food delivery demand, where the target ratio is determined such that a request amount derived from the predicted demand according to the target ratio is serviceable by the determined request amount; one or more values of the at least one parameter are determined, the one or more values generating the target ratio according to the determined dependency, and food delivery information is transmitted to a customer of the food delivery system according to the determined one or more values of the at least one parameter.

Description

Technical Field

[0001] Various aspects of the present disclosure relate to apparatuses and methods for controlling a food delivery system. Background Art

[0002] Due to the development of information technology, users can use computing devices to request on-demand services. On-demand services can allow users to meet their needs by obtaining goods and / or services immediately. Users can use the user interface presented on the computing device to request on-demand services, such as delivery services or transportation services.

[0003] For example, a user can use a computing device to request a search for an on-demand service (e.g., a food delivery order). Then, a server providing the on-demand service can aggregate the locations of available service providers (e.g., restaurants), the types of available services (e.g., food), the estimated cost, and other information, and provide the aggregated information to the computing device, enabling the user to make a selection on the user interface presented on the computing device. Once the user makes a selection on the user interface, the server can assign the service to one of multiple service contractors (e.g., delivery personnel) to deliver the selected food from the selected restaurant to the user.

[0004] Although the demand for on-demand services fluctuates significantly from time to time, the number of multiple service contractors may tend to remain relatively constant. For example, during peak hours (e.g., lunchtime and dinnertime), the demand may far exceed the supply level. Conventionally, as a solution, an on-demand service platform can batch multiple orders to meet the demand as much as possible. As another solution, the on-demand service platform can reduce the delivery radius. The delivery radius can be reduced based on the confirmed assignment rate of multiple orders received in the area where the user is located. If the confirmed assignment rate is low, the on-demand service platform can reduce the delivery radius to control the visibility of service providers, so as to only allow short-distance deliveries.

[0005] However, this may cause merchants (e.g., restaurants) to be unable to serve customers who are within the normal delivery radius but outside the reduced delivery radius. This may be annoying for these customers and lead them to perceive the service as unreliable and may not use the service at all.

[0006] Therefore, a demand regulation method that can maintain merchant availability during periods of supply tension is desirable. Summary of the Invention

[0007] Different embodiments relate to a method for controlling a food delivery system, the method comprising: determining information about a dependency relationship of a ratio of a food delivery request volume to a food delivery demand from historical data based on at least one parameter including at least one of food delivery costs and estimated food delivery time; determining a volume of food delivery requests that can be served; predicting food delivery demand; determining a target ratio of a food delivery request volume to food delivery demand, wherein the target ratio is determined so that, based on the target ratio, a request volume derived from the predicted demand can be served by the determined request volume; determining one or more values ​​of the at least one parameter that generates the target ratio based on the determined dependency relationship, and transmitting food delivery information to customers of the food delivery system based on the one or more values ​​of the determined at least one parameter.

[0008] According to one embodiment, the at least one delivery parameter includes a cost of delivering the food, and transmitting the food delivery information includes transmitting one or more values ​​of the determined cost of delivering the food to a customer of the food delivery system.

[0009] According to one embodiment, the at least one delivery parameter includes the estimated food delivery time, and transmitting the food delivery information includes transmitting one or more values ​​determined of the estimated food delivery time to a customer of the food delivery system.

[0010] According to one embodiment, the at least one delivery parameter includes at least one of a food delivery cost and an estimated food delivery time and includes availability of the food delivery provider.

[0011] According to one embodiment, transmitting the food delivery information includes: transmitting, for each of a plurality of food delivery service providers, information on whether the food delivery service provider is available.

[0012] According to one embodiment, the one or more values ​​of the availability of a food delivery provider include a delivery range of the food delivery provider.

[0013] According to an embodiment, the one or more values ​​indicate a category of the at least one parameter among a plurality of predetermined categories of the at least one parameter.

[0014] According to one embodiment, the method includes receiving a signal predicting a food delivery demand, and predicting a food delivery demand based on the received signal predicting the food delivery demand.

[0015] According to one embodiment, the signal predicting demand is the volume of sessions of the application currently being executed by users making food delivery requests.

[0016] According to one embodiment, the method includes receiving a signal predicting a food delivery offer, and determining a volume of food delivery requests that can be serviced based on the received signal predicting a food delivery offer.

[0017] According to one embodiment, the signal predicting food delivery availability is the number of food couriers available to the food delivery provider.

[0018] According to one embodiment, the at least one delivery parameter includes the food delivery cost and the estimated food delivery time, and the method includes: determining one or more values ​​for each of the food delivery cost and the estimated food delivery time, and the one or more values ​​generate the target ratio according to the determined dependency; and transmitting food delivery information to customers of the food delivery system based on the one or more values ​​determined for each of the food delivery cost and the estimated food delivery time.

[0019] According to one embodiment, the method includes: if the target ratio is higher than the current ratio of the food delivery request volume to the food delivery demand, and the current ratio is the result of one or more current values ​​of the food delivery fee and one or more values ​​of the estimated food delivery time, in order to determine the one or more values ​​of the food delivery fee and the estimated food delivery time, increasing the one or more current values ​​of the estimated food delivery time takes precedence over increasing the one or more current values ​​of the food delivery fee.

[0020] According to one embodiment, the method includes: if the target ratio is lower than the current ratio of the food delivery request volume to the food delivery demand, the current ratio is the result of one or more current values ​​of the food delivery cost and one or more values ​​of the estimated food delivery time, in order to determine the one or more values ​​of the food delivery cost and the estimated food delivery time, reducing the one or more current values ​​of the food delivery cost takes precedence over reducing the one or more current values ​​of the estimated food delivery time.

[0021] According to one embodiment, the at least one parameter includes multiple parameters, and wherein the information from the at least one parameter regarding the dependency of the ratio of the food delivery request amount to the food delivery demand is a table comprising entries of the ratio of the food delivery request amount to the food delivery demand for multiple combinations of values ​​of different parameters among the multiple parameters.

[0022] According to one embodiment, a computer program element is provided, the computer program element comprising program instructions which, when executed by one or more processors, cause the one or more processors to perform the method for controlling a food dispensing system as described above.

[0023] According to one embodiment, a computer readable medium is provided, the computer readable medium comprising program instructions, which when executed by one or more processors causes the one or more processors to perform the method for controlling a food dispensing system as described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The invention will be better understood with reference to the detailed description when considered in conjunction with the non-limiting examples and accompanying drawings, in which:

[0025] - Figure 1 A communication setup including a smartphone and a server is shown.

[0026] - Figure 2 A conversion rate matrix is ​​shown for each of the four geographic regions.

[0027] - Figure 3 A method of demand regulation using ETA (estimated time of arrival) and cost according to an embodiment is shown.

[0028] - Figure 4 A flow chart for demand regulation according to an embodiment is shown.

[0029] - Figure 5 A flow chart of a method for controlling a food dispensing system according to an embodiment is shown.

[0030] - Figure 6 A server computer according to an embodiment is shown. DETAILED DESCRIPTION

[0031] The following detailed description refers to the accompanying drawings, which illustrate the specific details and embodiments in which the present disclosure can be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the present disclosure. Other embodiments may be utilized and structural and logical changes may be made without departing from the scope of the present disclosure. The various embodiments are not necessarily mutually exclusive, as some embodiments may be combined with one or more other embodiments to form new embodiments.

[0032] Embodiments described in the context of one of these devices or methods are analogously valid for the other device or method. Similarly, embodiments described in the context of a device are analogously valid for a vehicle or method, and vice versa.

[0033] Features described in the context of an embodiment may be correspondingly applicable to the same or similar features in other embodiments. Features described in the context of an embodiment may be correspondingly applicable to other embodiments, even if not explicitly described in these other embodiments. Furthermore, additions and / or combinations and / or substitutions as described for features in the context of an embodiment may be correspondingly applicable to the same or similar features in other embodiments.

[0034] In the context of various embodiments, the articles “a,” “an,” and “the” as used with respect to features or elements include reference to one or more of these features or elements.

[0035] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0036] Hereinafter, embodiments will be described in detail.

[0037] Figure 1 A communication setup including a smartphone 100 and a server (computer) 106 is shown.

[0038] The smartphone 100 has a screen showing a graphical user interface (GUI) of applications for one or more of different services that a user using the smartphone has previously installed on his smartphone and has turned on (i.e., turned on), for example, ordering food or calling a taxi online.

[0039] GUI 101 includes graphical user interface elements 102, 103 that help the user use the service, such as a map near the user's location, food available near the user (e.g., the application can determine based on location services (such as GPS-based location services)), buttons for placing orders, etc.

[0040] When the user has made a selection for a service (e.g., selected a restaurant and / or selected to order food), the application communicates with the server 106 of the corresponding service via a radio connection. The server 106 (via the processor 107 executing the corresponding server program) may consult a memory 109 or a data storage device 108 with information about the service (e.g., price (including food price and delivery fee), availability (including the availability of the delivery person for delivery), estimated delivery time (ETA), etc.). The server transmits any data related to the user or requested by the user (e.g., price (including explicit or implicit delivery fee) and estimated delivery time) back to the smartphone 100, and the smartphone 100 displays the information on the GUI 101. Finally, the user may accept the service, for example, order food. In this case, the server 106 notifies the service provider 104 accordingly, for example, a restaurant or an online supermarket. The server 106 may also communicate with the service provider 104 earlier, for example, to determine the estimated delivery time.

[0041] It should be noted that although server 106 is described as a single server, its functions (e.g., providing certain services and advertising data) are usually provided by a configuration of multiple server computers (e.g., implementing cloud services) in actual applications. Therefore, the functions provided by a server (e.g., server 106) described below can be understood as being provided by a configuration of multiple servers or multiple server computers.

[0042] Typically, there are periods of time when service demand is higher (e.g., lunch time when food delivery services are needed) and periods of time when service demand is lower (e.g., late at night when food delivery services are needed). Thus, during peak hours, demand may be higher than supply, i.e., there may be a supply crunch. This may result in a service provider (e.g., a restaurant) becoming severely overloaded and lacking delivery personnel.

[0043] One way to avoid this situation is to reduce the delivery radius of a certain service provider (e.g., restaurant 104). However, this may result in the merchant (e.g., restaurant) being unable to provide services to customers (who are located within the normal delivery radius but outside the reduced delivery radius). For example, the merchant may be indicated as unavailable on GUI 101, or not displayed at all when the user searches for a restaurant to order. This loss of unavailability of a service provider (a service provider familiar to the customer or a service provider that the customer frequently uses) may be very annoying to the customer and cause the customer to think that the service (e.g., food delivery service) is unreliable and may quit using the service. Even if only some service providers are listed as unavailable when the customer searches, this may also reduce the customer's confidence in the service and may reduce the customer's willingness to use the service. In fact, real-life data shows that, for example, when about 30% of unavailable results are displayed to customers, the conversion rate (i.e., the ratio of order volume to service demand (e.g., represented by the number of sessions of the application for ordering food)) will drop sharply.

[0044] Since customers are more likely to place an order when they see a familiar merchant in the search results, the merchant may not be able to provide service due to being out of delivery range, or the familiar merchant may not be able to meet customer needs due to temporary closure (which is also one of the reasons for not being able to provide service). Therefore, for customers who are less willing to place orders at unfamiliar merchants, one approach is to relax the delivery range or reduce the temporary closure time of familiar merchants. When a familiar merchant is unavailable due to no service time, it is also possible to recommend merchants similar to the familiar merchant to the customer when the customer exits the search session without placing an order. However, these two methods may not be sufficient to avoid customer dissatisfaction (and not using the service at all) or may not be easy to apply or have other disadvantages, especially when there is supply shortage that needs to be dealt with.

[0045] In view of the above, according to various embodiments, methods for regulating demand are provided to allow merchant availability to be maintained during periods of tight supply, i.e., avoiding (or at least not solely relying on) reducing the delivery radius of the service provider.

[0046] According to various embodiments, demand is regulated using fee (i.e., delivery price), ETA (estimated time of arrival), and availability. In this context, it should be noted that between ETA and fee, real-life data shows that customers are less sensitive to ETA than fee, i.e., given availability, customers would rather pay a lower fee and wait a little longer than pay a higher fee. Higher fees have a large adverse impact on conversion rates compared to longer ETAs.

[0047] The biggest factor affecting conversion rate (i.e., the ratio between the volume of food delivery requests issued and the "general" delivery demand, e.g. represented by the number of users using the food delivery app at a certain point in time) is availability. With high unavailability (e.g., when less than 50% of the available merchants are available), conversion rate is low. Short ETAs and low fees do not seem to compensate for availability and therefore fail to increase demand. Real-life data shows that customers can tolerate moderate unavailability (below 30%) as long as they do not have to pay more.

[0048] Customer sensitivity may be different in different markets (e.g., regions or countries). Therefore, according to various embodiments, the conversion rate depends on the above three demand adjustment parameters, namely, cost, ETA and availability. These can be represented, for example, as a CVR (conversion rate) matrix, such as Figure 2 as shown.

[0049] Figure 2 Shown are a CVR matrix for a first (geographical) region 201, a CVR matrix for a second region 202, a CVR matrix for a third region 203 and a CVR matrix for a fourth region 204. The geographical regions may be countries, but may also be smaller areas (such as cities, regions etc.).

[0050] Each CVR matrix (also referred to as a table) has entries for the conversion rate (determined from historical data) for a combination of specified cost, ETA, and availability.

[0051] exist Figure 2 In the example of , there are three categories of cost (low, medium, high), three categories of availability (low, medium, high), and two categories of ETA (low and high). The range of these categories (i.e., what values ​​qualify as "low", etc.) can be defined based on historical values ​​(e.g., the lower third of historical cost values ​​(e.g., for a range of delivery distances) are considered "low" costs). Finer granularity (i.e., more than two or three categories per parameter) can also be used, or even the correlation of conversion rate with the parameters can be modeled.

[0052] Although availability can effectively regulate demand, as described above, it may be desirable to maintain a certain level of service provider availability (e.g., with a goal of service reliability). Therefore, in order to maintain a certain level of service provider availability, in at least some scenarios, demand is regulated using ETA and fees (e.g., when the mismatch between supply and demand is not too high and thus ETA and fees are sufficient to regulate demand). Since customers are more sensitive to high fees than long ETAs, according to various embodiments, the service provider may be provided as follows: Figure 3 The method shown shapes the requirements.

[0053] Figure 3 A method of demand regulation using ETA (estimated time of arrival) and cost according to an embodiment is shown.

[0054] As shown, when distribution health begins to deteriorate (i.e., demand begins to exceed supply), ETA adjustments (i.e., increases in ETAs) are first used, and then if distribution health continues to be poor, fees are increased to minimize demand losses.

[0055] Once allocation health begins to recover, first reduce fees and then remove ETA adjustments as this allows CVR to recover faster.

[0056] Figure 4 A flow chart 400 of demand regulation is shown according to an embodiment.

[0057] First, a signal predicting supply 401 and a signal predicting demand 402 are obtained. For example, the server 106 may receive in real time a supply signal indicating the amount of delivery personnel within a predetermined distance of a merchant location as a signal predicting supply 401 and a signal indicating the amount of application sessions (i.e., the amount of users currently using a smartphone application to search for a service provider) as a signal predicting demand 402. It should be noted that the signal predicting demand is a "general" demand for food delivery, while the adjusted demand is the actual amount of requests generated by this general demand and conversion rate.

[0058] It should also be noted that according to various embodiments, signals 401, 402 are selected to be independent in the sense that they are not affected by demand regulation. For example, the real-time CAR (Confirmed Allocation Rate) signal (i.e., a real-time signal reflecting the allocation status of incoming orders in the past 10 minutes, for example, which helps to identify the balance between demand and supply in a timely manner) and the signal indicating incoming orders are affected by demand regulation actions. In contrast, the amount of nearby couriers and the amount of app sessions are independent of demand regulation actions (e.g., the customer does not know the app content before deciding to launch the app).

[0059] At 403, the server 106 determines a maximum capacity 405, i.e., the maximum amount of orders that can be allocated based on a real-time supply signal (i.e., a signal predicting supply) 401 within a certain time window (e.g., the next few minutes). Additionally, the server determines the dependence of CVR on availability, ETA, and cost from historical data 404, e.g., in the form of a CVR matrix as described with reference to Figure 2 or in a form determined (e.g., trained) on historical data or another model. As explained, when using a matrix, different demand suppression (or regulation) tools (i.e., parameters) correspond to dimensions, and the matrix can be different in the market. It can be determined from historical data (historical patterns) over a certain time period.

[0060] Based on the maximum capacity 405, the server further determines a target CVR: Given the maximum amount of allocable (i.e., served) orders and the predicted demand (i.e., the amount of sessions from the predicted demand signal 402), since the incoming orders = the amount of sessions * CVR, the server 106 determines at a certain level the target CVR (to be maintained) to meet the maximum capacity 405 (i.e., incoming orders = maximum capacity) to avoid demand loss or low allocation rate.

[0061] At 407, given the target CVR 406 and the correlation (i.e., dependence) of CVR on demand suppression tools, the server 106 then determines demand regulation measurement measures. This means that using the information about CVR with respect to availability, ETA, and cost (e.g., given by a CVR matrix), the server 106 determines a value 408 based on the information to be provided to the customer (i.e., displayed on the GUI101) for availability, ETA, and cost (e.g., determining these values according to percentages, etc.).

[0062] According to one embodiment, a method is provided as Figure 5 shown.

[0063] Figure 5 A flowchart of a method for controlling a food delivery system according to an embodiment is shown.

[0064] At 501, information on the dependence of the ratio of the food delivery request volume to the food delivery demand on at least one parameter including at least one of the food delivery cost and the estimated food delivery time is determined from historical data.

[0065] At 502, for example, based on (further) historical data, such as historical supply and demand balance, the amount of food delivery requests that can be served is determined.

[0066] At 503, the food delivery demand is predicted.

[0067] At 504 , a target ratio of the food delivery request volume to the food delivery demand is determined, wherein the target ratio is determined such that a request volume derived from the predicted demand according to the target ratio can be served by the determined request volume.

[0068] At 505, one or more values ​​of the at least one parameter are determined, the one or more values ​​generating the target ratio according to the determined dependency.

[0069] At 506 , food delivery information according to the determined one or more values ​​of the at least one parameter is transmitted to a customer of the food delivery system (ie, a terminal device, such as a computer or a mobile device of the customer).

[0070] According to various embodiments, in other words, at least one of the delivery fee and the delivery time (i.e., how long it takes to deliver the requested food, for example in the form of an ETA) is set to achieve a specific target conversion rate (i.e., a target ratio), which is determined to enable the service to be provided for the volume of requests generated.

[0071] Figure 5 For example, by Figure 6 The server computer shown is used to execute.

[0072] Figure 6 A server computer 600 is shown according to an embodiment.

[0073] The server computer 600 includes a communication interface 601 (e.g., configured to receive data about demand and supply). The server computer 600 also includes a processing unit 602 and a memory 603. The memory 603 can be used by the processing unit 602 to store, for example, data to be processed, such as information about demand and supply. The server computer is configured to execute Figure 5 method.

[0074] The methods described herein may be performed and the different processing or computing units and devices and computing entities described herein may be implemented by one or more circuits. In an embodiment, a "circuit" may be understood as any kind of logic implementation entity, which may be hardware, software, firmware, or any combination thereof. Therefore, in an embodiment, a "circuit" may be a hardwired logic circuit or a programmable logic circuit such as a programmable processor, for example, a microprocessor. A "circuit" may also be software implemented or executed by, for example, a processor, such as any kind of computer program, for example, a computer program using a virtual machine code. According to alternative embodiments, any other kind of implementation of the various functions described herein may also be understood as a "circuit".

[0075] Although the present disclosure has been specifically shown and described with reference to specific embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present invention as defined in the appended claims. Therefore, the scope of the present invention is indicated by the appended claims, and it is therefore intended to cover all changes within the meaning and range of equivalents of the claims.

Claims

1. A method for controlling a food delivery system, include: determining, from the historical data, information regarding a dependency of a ratio of food delivery request volume to food delivery demand on at least one parameter including at least one of food delivery cost and estimated food delivery time; Determine the volume of food delivery requests that can be served; forecasting food delivery demand; determining a target ratio of the food delivery request volume to the food delivery demand, wherein the target ratio is determined so that the request volume derived from the predicted demand according to the target ratio can be served by the determined request volume; determining one or more values ​​for the at least one parameter, the one or more values ​​producing the target ratio based on the determined dependency; and Food delivery information is transmitted to a customer of the food delivery system based on the determined one or more values ​​of the at least one parameter.

2. The method according to claim 1, in, At least one delivery parameter includes the food delivery cost, and transmitting the food delivery information includes transmitting one or more values ​​of the determined food delivery cost to the customer of the food delivery system.

3. The method according to claim 1 or 2, in, At least one delivery parameter includes the estimated food delivery time, and transmitting the food delivery information includes transmitting one or more values ​​of the determined estimated food delivery time to the customer of the food delivery system.

4. The method according to any one of claims 1 to 3, in, At least one delivery parameter includes at least one of the food delivery cost and the estimated food delivery time and includes availability of a food delivery provider.

5. The method according to claim 4, in, Transmitting the food delivery information includes transmitting, for each of a plurality of food delivery service providers, information on whether the food delivery service provider is available.

6. The method according to claims 4 and 5, in, The one or more values ​​of the availability of the food delivery provider include a delivery range of the food delivery provider.

7. The method according to any one of claims 1 to 6, in, The one or more values ​​indicate a category of the at least one parameter among a plurality of predetermined categories of the at least one parameter.

8. The method according to any one of claims 1 to 7, include: A signal predicting a food delivery demand is received, and based on the received signal predicting a food delivery demand, the food delivery demand is predicted.

9. The method according to claim 8, in, The signal predicting demand is the volume of sessions of the application currently being executed by users making food delivery requests.

10. The method according to any one of claims 1 to 9, include: A signal predicting food delivery offers is received, and a quantity of food delivery requests that can be serviced is determined based on the received signal predicting food delivery offers.

11. The method according to claim 10, in, The signal for predicting food delivery supply is the number of food couriers available to the food delivery provider.

12. The method according to any one of claims 1 to 11, in, At least one delivery parameter includes the food delivery cost and the estimated food delivery time, and the method includes: determining one or more values ​​for each of the food delivery cost and the estimated food delivery time, the one or more values ​​generating the target ratio according to the determined dependency, and transmitting food delivery information to customers of the food delivery system according to the determined one or more values ​​for each of the food delivery cost and the estimated food delivery time.

13. The method according to claim 12, include: If the target ratio is higher than the current ratio of the food delivery request volume to the food delivery demand, the current ratio being the result of one or more current values ​​of the food delivery cost and one or more values ​​of the estimated food delivery time, increasing one or more current values ​​of the estimated food delivery time takes precedence over increasing one or more current values ​​of the food delivery cost for determining the one or more values ​​of the food delivery cost and the estimated food delivery time.

14. The method according to claim 12 or 13, include: If the target ratio is lower than the current ratio of the food delivery request volume to the food delivery demand, the current ratio being the result of one or more current values ​​of the food delivery cost and one or more values ​​of the estimated food delivery time, reducing the one or more current values ​​of the food delivery cost takes precedence over reducing the one or more current values ​​of the estimated food delivery time for determining the one or more values ​​of the food delivery cost and the estimated food delivery time.

15. The method according to any one of claims 1 to 14, in, The at least one parameter includes multiple parameters, and wherein the information about the dependence of the ratio of the food delivery request amount to the food delivery demand on the at least one parameter is a table comprising entries of the ratio of the food delivery request amount to the food delivery demand for multiple combinations of values ​​of different parameters among the multiple parameters.

16. A server computer comprising a radio interface, a memory interface and a processing unit, the processing unit being configured to perform the method according to any one of claims 1 to 15.

17. A computer program element comprising program instructions which, when executed by one or more processors, cause the one or more processors to perform the method according to any one of claims 1 to 15.

18. A computer readable medium comprising program instructions which, when executed by one or more processors, cause the one or more processors to perform the method according to any one of claims 1 to 15.

Images