Meal delivery optimization method and system

Abstract

Embodiments of the present description provide a meal delivery optimization method and system. The method comprises: acquiring an order placing sequence of a meal ordering unit in a dining area, wherein the order placing sequence comprises ordered dishes and order placing times; determining kitchen scheduling parameters on the basis of the order placing sequence of the meal ordering unit, wherein the kitchen scheduling parameters comprise a preferred cooking task sequence of cooking stations in a kitchen; and sending the kitchen scheduling parameters to a kitchen receiving terminal.

Description

A meal delivery optimization method and system Technical Field

[0001] This specification relates to the field of catering management technology, and in particular to a meal delivery optimization method and system. Background Art

[0002] As living standards and consumption levels continue to rise, people's expectations for the service industry are also gradually increasing. This is particularly true for the catering industry, where both service quality and efficiency must be guaranteed at a higher level. While current catering management processes have introduced some intelligent applications for ordering and payment to improve efficiency, there is still a lack of efficient kitchen scheduling methods for food preparation and delivery.

[0003] Therefore, it is hoped to provide a meal serving optimization method and system to improve meal serving efficiency and quality. Summary of the Invention

[0004] One or more embodiments of this specification provide a method for optimizing meal delivery. The method includes: obtaining an order sequence from ordering units within a dining area, the order sequence including ordered dishes and order time; determining kitchen scheduling parameters based on the order sequence from the ordering units, the kitchen scheduling parameters including a preferred cooking task sequence for cooking stations in the kitchen; and transmitting the kitchen scheduling parameters to a kitchen receiving terminal.

[0005] One of the embodiments of the present specification provides a meal delivery optimization system, which includes: an acquisition module, configured to acquire an order sequence of ordering units in a dining area, wherein the order sequence includes ordered dishes and order time; a determination module, configured to determine a back-kitchen scheduling parameter based on the order sequence of the ordering units, wherein the back-kitchen scheduling parameter includes a preferred cooking task sequence for a cooking station in the back-kitchen; and a sending module, configured to send the back-kitchen scheduling parameter to a back-kitchen receiving terminal.

[0006] One or more embodiments of the present specification provide a meal serving optimization device, comprising a processor, wherein the processor is configured to execute the meal serving optimization method.

[0007] One or more embodiments of the present specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the meal delivery optimization method. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein:

[0009] FIG1 is an exemplary schematic diagram of a meal delivery optimization system according to some embodiments of the present specification;

[0010] FIG2 is an exemplary flow chart of a meal delivery optimization method according to some embodiments of this specification;

[0011] FIG3 is an exemplary schematic diagram of determining kitchen scheduling parameters according to some embodiments of this specification;

[0012] FIG4 is an exemplary schematic diagram of determining food preparation parameters according to some embodiments of this specification;

[0013] FIG5 is an exemplary schematic diagram of a distribution prediction model according to some embodiments of this specification. DETAILED DESCRIPTION

[0014] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0015] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0016] As used in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not refer to the singular but also include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0017] Flowcharts are used throughout this specification to illustrate the operations performed by systems according to embodiments of this specification. It should be understood that preceding or following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0018] For the catering management process, reasonable allocation of back-kitchen tasks is particularly important. In some embodiments of this specification, it is hoped to provide a meal delivery optimization method and system that can combine multiple factors such as customer order requirements and order time to intelligently optimize the kitchen's workflow and coordination, automatically allocate cooking tasks and time, and improve the kitchen's meal delivery efficiency and quality.

[0019] FIG1 is an exemplary module diagram of a meal delivery optimization system according to some embodiments of this specification.

[0020] In some embodiments, as shown in FIG1 , the meal delivery optimization system 100 may include an acquisition module 110 , a determination module 120 , and a sending module 130 .

[0021] Acquisition module 110 is a module for acquiring order sequences. In some embodiments, acquisition module 110 may acquire order sequences from ordering units within a dining area. For example, acquisition module 110 may communicate with the ordering units to acquire their current and historical order records and determine the order sequence. For more information about dining areas, ordering units, and order sequences, please refer to the corresponding description of Figure 2.

[0022] The determination module 120 is a module for determining the back-kitchen scheduling parameters. In some embodiments, the determination module 120 can be configured to determine the back-kitchen scheduling parameters according to the order sequence of the ordering unit.

[0023] In some embodiments, the determination module 120 can be further configured to generate one or more sets of candidate back-kitchen scheduling parameters based on the order sequence of the ordering unit; determine the customer's waiting time and the back-kitchen meal delivery efficiency based on the candidate back-kitchen scheduling parameters; determine the first evaluation value corresponding to the candidate back-kitchen scheduling parameters based on the customer's waiting time; determine the second evaluation value corresponding to the candidate back-kitchen scheduling parameters based on the back-kitchen meal delivery efficiency; determine the back-kitchen scheduling parameters based on the first evaluation value and the second evaluation value of the candidate back-kitchen scheduling parameters. For details, please refer to the corresponding description of Figure 3.

[0024] The sending module 130 is a module for transmitting kitchen scheduling parameters. In some embodiments, the sending module 130 can be configured to transmit the kitchen scheduling parameters to a kitchen receiving terminal. For example, the sending module 130 can be communicatively connected to the kitchen receiving terminal or its control center to transmit the kitchen scheduling parameters to the kitchen receiving terminal.

[0025] In some embodiments, the meal delivery optimization system 100 may further include an analysis module.

[0026] The analysis module is used to determine meal preparation parameters. In some embodiments, the analysis module can be configured to obtain a customer's user information based on the ordering unit; obtain the customer's first historical order data corresponding to the ordering unit based on the user information; determine a first estimated order distribution based on the first historical order data and the order sequence; and determine meal preparation parameters based on the first estimated order distribution.

[0027] In some embodiments, the analysis module may be further configured to determine a second estimated order distribution based on the order sequence; and determine meal preparation parameters based on the first estimated order distribution and the second estimated order distribution. For details on determining meal preparation parameters, see Figures 4 and 5 and their corresponding descriptions.

[0028] In some embodiments, the meal delivery optimization system 100 may be integrated into a processor. The processor may be configured to execute at least some of the computer instructions to implement the meal delivery optimization system. For example, the acquisition module 110, the determination module 120, and the sending module 130 may be components of the processor.

[0029] By way of example only, the processor may include a central processing unit (CPU), an application specific integrated circuit (ASIC), an application specific instruction processor (ASIP), a graphics processing unit (GPU), a physical processing unit (PPU), a digital signal processor (DSP), a field programmable gate array (FPGA), a programmable logic device (PLD), a controller, a microcontroller unit, a reduced instruction set computer (RISC), a microprocessor, etc., or any combination thereof.

[0030] In some embodiments, the meal delivery optimization system 100 may further include a memory, and the processor may retrieve pre-stored data and / or information related to the meal delivery optimization system 100 from the memory.

[0031] In some embodiments, the meal delivery optimization system 100 may also include the aforementioned kitchen receiving terminal. A kitchen receiving terminal refers to one or more terminal devices or software located in the kitchen. Based on the kitchen scheduling parameters received by the kitchen receiving terminal, a cooking task sequence for each cooking station in the kitchen can be determined, thereby guiding cooking at each cooking station.

[0032] It should be noted that the above description of the meal delivery optimization system and its modules is for convenience of description only and does not limit this specification to the scope of the embodiments cited. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from this principle. In some embodiments, the acquisition module 110, determination module 120 and sending module 130 disclosed in Figure 1 can be different modules in a system, or a module can implement the functions of two or more modules mentioned above. For example, each module can share a storage module, or each module can have its own storage module. Such variations are within the scope of protection of this specification.

[0033] FIG2 is an exemplary flow chart of a method for optimizing meal delivery according to some embodiments of this specification. As shown in FIG2 , process 200 includes the following steps. In some embodiments, process 200 may be performed by a meal delivery optimization system.

[0034] Step 210: Obtain the order sequence of the ordering units in the dining area.

[0035] The dining area refers to the area where customers eat. For example, the dining area can be a restaurant, a dining area, etc.

[0036] An ordering unit is a device used to place orders. For example, an ordering unit can correspond to a table or a customer. For example, an interactive terminal can be installed at each table as the corresponding ordering unit. Based on the ordering unit, customers can select and order their food.

[0037] In some embodiments, the ordering unit and the food preparation station may be equipped with built-in RFID devices. In some embodiments, the RFID device of the ordering unit may be configured to enable customer ordering and personal identification. In some embodiments, the RFID device of the ordering unit and the food preparation station may be configured to complete the collection of dish information data for the dishes being served.

[0038] The food preparation table is a table used to place dishes for serving.

[0039] An RFID (Radio Frequency Identification) device is a data collection device based on radio frequency identification communication technology. It uses radio signals to identify specific targets and read and write related data. For example, an RFID device can obtain the identity information of an object by scanning an RFID tag.

[0040] In some embodiments, customers can place orders through the RFID device of the ordering unit and bind and identify the customer's personal identity. For example, the RFID device of the ordering unit can be used to identify and bind the customer's terminal information such as a mobile phone or watch, so that the customer's personal identity can be bound and identified simultaneously when the customer orders, and the ordering information can be bound to the customer.

[0041] Dish information data refers to data related to dishes. For example, dish information data may include dish name, order time, dish type, and dish quantity.

[0042] In some embodiments, the meal delivery optimization system can collect dish information data for the dishes being served using an RFID device on the meal preparation table and / or an RFID device on the ordering unit. In some embodiments, different dishes may correspond to different tableware, and the RFID device on the meal preparation table and / or the RFID device on the ordering unit can identify the corresponding tableware placed on the meal preparation table and / or dining table to complete the collection of dish information data for the dishes being served.

[0043] In some embodiments, an RFID device may be installed in other devices to collect information about the dishes being served. For example, an RFID device may be installed in a cooking station in a back kitchen.

[0044] In some embodiments of this specification, by building RFID into the ordering unit and the preparation table, functions such as customer ordering, customer personal identity binding and identification, and collection of dish information data can be realized efficiently and quickly, making the ordering process smoother and more conducive to quickly and efficiently collecting relevant identity information, providing supporting data for dining forecasts and production scheduling, so as to improve the efficiency and quality of subsequent services.

[0045] The order sequence refers to a sequence generated based on the customer's current order information. In some embodiments, the order sequence may include the ordered dishes and the order time.

[0046] The delivery optimization system (e.g., the acquisition module) can obtain the order sequence of the ordering unit in various ways. For example, the acquisition module can obtain the order sequence of the ordering unit from the RFID device of the ordering unit, the storage module of the ordering unit, or the control center.

[0047] Step 220: Determine the kitchen scheduling parameters based on the order sequence of the ordering unit.

[0048] The back kitchen scheduling parameters refer to the relevant parameters for scheduling the back kitchen cooking tasks. In some embodiments, the back kitchen scheduling parameters may include the preferred cooking task sequence corresponding to each cooking station in the back kitchen.

[0049] A cooking station is a station used for cooking dishes.

[0050] A cooking task sequence for a cooking station is a sequence that reflects the order of cooking tasks for that cooking station. A preferred cooking task sequence is a cooking task sequence that satisfies a preset condition. For example, the preset condition may be to minimize customer wait time or minimize the total cooking time for the cooking station. In some embodiments, each cooking station may correspond to a preferred cooking task sequence.

[0051] In some embodiments, the food delivery optimization system (e.g., the determination module) can determine kitchen scheduling parameters in various ways based on the order sequence of the ordering units. For example, the determination module can prioritize the order sequence of dishes ordered earlier in the cooking task sequence to the cooking station with the fewest cooking tasks, thereby determining the kitchen scheduling parameters.

[0052] By way of example only, the determination module may:

[0053] (1) Determine the first cooking task to be scheduled from the unscheduled cooking tasks in the order sequence of each ordering unit. The first cooking task to be scheduled is the cooking task with the earliest order time in the current order sequence of each ordering unit. The unscheduled cooking task refers to the cooking task generated based on the ordered dishes in the order sequence that has not been assigned to the cooking station;

[0054] (2) Determine the first idle cooking station according to the current cooking task sequence of each cooking station in the kitchen. The first idle cooking station refers to the cooking station with the least current cooking task among all cooking stations. The current cooking task sequence refers to the sequence of cooking tasks that have not yet been completed at each cooking station.

[0055] (3) adding the first cooking task to be scheduled to the cooking task sequence of the first idle cooking station;

[0056] (4) Marking the first cooking task to be scheduled as a scheduled cooking task; for example, removing the cooking task corresponding to the first cooking task to be scheduled from the unscheduled cooking tasks in the order sequence of the corresponding ordering unit and adding it to the scheduled cooking task, where the scheduled cooking task refers to the cooking task that has been assigned to the cooking station.

[0057] (5) Jump to execute (1) until there are no unscheduled cooking tasks in the cooking tasks corresponding to the order sequence of each ordering unit.

[0058] After the above operations, the optimal cooking task sequence for each cooking station can be determined, and the corresponding kitchen scheduling parameters can be generated. For more information on determining the kitchen scheduling parameters, please refer to Figure 3 and its related description.

[0059] Step 230: Send the kitchen scheduling parameters to the kitchen receiving terminal.

[0060] The kitchen receiving terminal refers to a terminal for receiving data in the kitchen. For relevant descriptions of the kitchen receiving terminal, please refer to the corresponding description of Figure 1.

[0061] In some embodiments, the meal delivery optimization system (e.g., the sending module) can send the kitchen scheduling parameters to the kitchen receiving terminal in various ways. For example, the sending module can send the kitchen scheduling parameters to the kitchen receiving terminal via a network, an RFID device, or the like.

[0062] In some embodiments of the present specification, by obtaining the order sequence of the ordering units in the dining area, determining the back kitchen scheduling parameters based on the order sequence, and sending them to the back kitchen receiving terminal, the back kitchen can be reasonably scheduled, cooking tasks can be automatically assigned, the food delivery process can be optimized, and the kitchen food delivery efficiency can be improved.

[0063] It should be noted that the above description of process 200 is for illustration and purpose only and does not limit the scope of application of this specification. Those skilled in the art may make various modifications and variations to process 200 under the guidance of this specification. However, such modifications and variations are still within the scope of this specification.

[0064] FIG3 is an exemplary schematic diagram of determining kitchen scheduling parameters according to some embodiments of this specification.

[0065] In some embodiments, as shown in Figure 3, the determination module can be further configured to: generate one or more groups of candidate back-kitchen scheduling parameters 320 based on the order sequence 310 of the ordering unit; determine the customer's waiting time 330 and the back-kitchen meal delivery efficiency 340 based on the candidate back-kitchen scheduling parameters 320; determine the first evaluation value 350 corresponding to the candidate back-kitchen scheduling parameter 320 based on the customer's waiting time 330; determine the second evaluation value 360 ​​corresponding to the candidate back-kitchen scheduling parameter 320 based on the back-kitchen meal delivery efficiency 340; determine the back-kitchen scheduling parameter 370 based on the first evaluation value 350 and the second evaluation value 360 ​​of the candidate back-kitchen scheduling parameter 320.

[0066] For relevant information about ordering units, ordering sequences and kitchen scheduling parameters, please refer to the corresponding description of Figure 2.

[0067] The candidate kitchen scheduling parameters 320 are alternative kitchen scheduling parameters. In some embodiments, the candidate kitchen scheduling parameters may include candidate cooking task sequences for each cooking station in the kitchen. The candidate cooking task sequences are alternative cooking task sequences.

[0068] In some embodiments, the determination module may generate candidate kitchen scheduling parameters in various ways based on the order sequence of the ordering units. For example, the determination module may randomly assign different dishes ordered by different customers to different cooking stations based on the order sequence of each ordering unit, and generate different candidate kitchen scheduling parameters based on different assignment results.

[0069] Customer wait time 330 refers to the estimated wait time for a customer's meal when cooking is scheduled based on the corresponding candidate kitchen scheduling parameters. In some embodiments, the customer wait time can be the estimated time from when the customer places their order to when the meal is served. In some embodiments, when there is more than one customer in the dining area, the customer wait time can be the sum of the wait times for each customer.

[0070] The back kitchen meal delivery efficiency 340 refers to the efficiency of the estimated back kitchen meal delivery. In some embodiments, the back kitchen meal delivery efficiency can be represented by the ratio of the number of cooked dishes to the cooking time.

[0071] In some embodiments, the determination module can determine the customer's waiting time and the kitchen's food delivery efficiency through various methods based on the candidate kitchen scheduling parameters. For example, when determining each customer's waiting time, the determination module can determine the estimated delivery time of the dish based on the current ranking of the dish ordered by the customer in the candidate cooking task sequence for the corresponding cooking station, the estimated cooking time of the preceding dish, and the estimated cooking time of the dish. The time interval between the customer's order placement and the estimated delivery time is the customer's waiting time.

[0072] Similarly, the determination module can determine the number of cooked dishes that can be served within a unit time based on the corresponding candidate cooking task sequences of each cooking station, and use the number of cooked dishes as the kitchen serving efficiency.

[0073] First evaluation value 350 refers to an evaluation value of a candidate kitchen scheduling parameter determined based on customer wait times. In some embodiments, the determination module may calculate the total wait time based on the customer wait time for each cooking task in each ordering unit, and determine the first evaluation value based on the total wait time. For example, the first evaluation value may be negatively correlated with the total wait time.

[0074] The second evaluation value 360 ​​refers to the evaluation value of the candidate kitchen scheduling parameter determined based on the kitchen's food delivery efficiency. In some embodiments, the determination module may calculate an average value based on the kitchen's food delivery efficiency obtained in multiple future time periods, and determine the second evaluation value based on this average value. For example, the determination module may divide the future operating time into multiple future time periods, for example, each 20-minute time period corresponds to a future time period. The determination module may calculate the average value of the kitchen's food delivery efficiency for these multiple future time periods, and the second evaluation value is positively correlated with this average value.

[0075] In some embodiments, the determination module may also determine a first evaluation value corresponding to the candidate kitchen scheduling parameter based on the customer's waiting time, and a second evaluation value corresponding to the candidate kitchen scheduling parameter based on the kitchen's food delivery efficiency, using various other methods. The first evaluation value is negatively correlated with the customer's waiting time, and the second evaluation value is positively correlated with the kitchen's food delivery efficiency.

[0076] For example, the determination module can determine the first evaluation value and the second evaluation value by looking up the evaluation value comparison table, which stores the first evaluation value corresponding to each waiting time determined based on historical experience and the second evaluation value corresponding to each back-kitchen meal delivery efficiency.

[0077] In some embodiments, the determination module may also determine the first evaluation value and the second evaluation value of the candidate kitchen scheduling parameter in other ways.

[0078] For example, the determination module can match the feature vectors in the vector database based on the feature vectors generated by the candidate scheduling parameters, determine one or more reference vectors whose similarity is greater than a preset similarity threshold as the target vector, and obtain the first evaluation value and the second evaluation value corresponding to each group of candidate back-kitchen scheduling parameters based on the historical first evaluation value and the historical second evaluation value corresponding to the matched one or more target vectors.

[0079] Among them, the feature vector is composed of candidate back-kitchen scheduling parameters, the vector database includes a reference vector and its corresponding historical first evaluation value and historical second evaluation value, the reference vector is composed of actual back-kitchen scheduling parameters in historical records, and its corresponding historical first evaluation value and historical second evaluation value can be determined based on the actual historical customer waiting time and back-kitchen meal delivery efficiency.

[0080] In some embodiments, if there are multiple target vectors, the historical first evaluation values ​​of the multiple target vectors can be weighted and summed to determine the first evaluation value corresponding to the candidate back-kitchen scheduling parameter. Similarly, the historical second evaluation values ​​of the multiple target vectors can be weighted and summed to determine the second evaluation value corresponding to the candidate back-kitchen scheduling parameter.

[0081] The weighting can be determined based on the similarity between each set of candidate kitchen scheduling parameters and the target vector. The higher the similarity, the greater the corresponding weight. The similarity can be negatively correlated with the cosine distance, Euclidean distance, etc. between vectors.

[0082] In some embodiments, the determination module can also: determine the estimated delivery time of the cooking task included in the candidate back-kitchen scheduling parameters based on the candidate back-kitchen scheduling parameters and the chef information of the cooking station through the delivery time prediction model; and determine the customer's waiting time and the back-kitchen delivery efficiency based on the estimated delivery time.

[0083] Chef information refers to information related to the chef. For example, the chef information may include the chef's length of service, hours worked that day, etc. In some embodiments, each cooking station may correspond to one or more chef information.

[0084] Estimated cooking time refers to the estimated time to complete the cooking task.

[0085] The meal delivery time prediction model is a model used to predict meal delivery time. In some embodiments, the meal delivery time prediction model may be a machine learning model. For example, the meal delivery time prediction model may be a neural network (NN) model, a deep neural network (DNN) model, or the like.

[0086] In some embodiments, the input of the meal delivery time prediction model may include candidate kitchen scheduling parameters and chef information of the cooking station, and the output may be the estimated meal delivery time of each cooking task in the candidate kitchen scheduling parameters.

[0087] In some embodiments, the meal delivery time prediction model can be trained based on a large number of first training samples with a first label. The first training sample can be sample kitchen scheduling parameters and corresponding chef information from historical records. The first label can be the actual historical meal delivery time of the cooking task corresponding to the sample kitchen scheduling parameters. The first label can be automatically annotated by the system based on the historical records.

[0088] In some embodiments, the determination module 120 may input a large number of first training samples into an initial meal delivery time prediction model, construct a loss function based on the output of the initial meal delivery time prediction model and labels representing actual meal delivery times corresponding to sample kitchen scheduling parameters, and iteratively update the initial meal delivery time prediction model based on the loss function. When the value of the loss function meets an iteration completion condition, training is completed, resulting in a trained meal delivery time prediction model. The iteration completion condition may include convergence of the loss function, a number of iterations reaching a threshold, etc.

[0089] In some embodiments, the determination module may determine the customer's waiting time based on the estimated serving time and order time of each cooking task. For example, for each order unit, the determination module may subtract the corresponding order time from the estimated serving time of each cooking task in the order unit to calculate the customer's waiting time for each cooking task in each order unit.

[0090] In some embodiments, the determination module may calculate the average of the waiting times of customers corresponding to all cooking tasks to obtain an average of the waiting times, and use the average of the waiting times as the waiting time of customers for determining the first evaluation value.

[0091] In some embodiments, the determination module can determine the kitchen's food delivery efficiency by calculating the amount of food delivered in a future time period based on the estimated delivery time of each cooking task. For example, if the determination module calculates that the amount of food delivered in the next 10 minutes is 15 based on the estimated delivery time of each cooking task, the kitchen's food delivery efficiency in the next 10 minutes can be: 15 / 10 = 1.5. The length of the future time period can be manually preset.

[0092] In some embodiments, the determination module may use the average of the back-kitchen meal serving efficiency in the future time periods included in the future time range for which the meal serving efficiency needs to be evaluated as the back-kitchen meal serving efficiency for determining the second evaluation value.

[0093] In some embodiments of the present specification, by utilizing a meal delivery time prediction model, a more accurate prediction of the estimated meal delivery time can be made to determine a more reasonable first evaluation value and second evaluation value for the candidate back-kitchen scheduling parameters, making it more reliable to determine the back-kitchen scheduling parameters.

[0094] In some embodiments, the determination module may perform a weighted summation of the first evaluation value and the second evaluation value, and select the candidate back-kitchen scheduling parameter with the highest weighted value as the back-kitchen scheduling parameter, wherein the first evaluation value and the second evaluation value may be preset. For example, the more importance is attached to the waiting time of the customer, the greater the weight of the first evaluation value.

[0095] In some embodiments of the present specification, by generating candidate back-kitchen scheduling parameters, determining the customer's waiting time and the back-kitchen meal delivery efficiency based on the candidate back-kitchen scheduling parameters, and then determining a first evaluation value and a second evaluation value respectively, and then determining the back-kitchen scheduling parameters based on the first evaluation value and the second evaluation value, different candidate back-kitchen scheduling parameters can be evaluated, and the back-kitchen scheduling parameters can be determined while taking into account the customer's waiting time and meal delivery efficiency, which can ensure the customer's dining experience while improving the meal delivery efficiency.

[0096] FIG4 is an exemplary schematic diagram of determining food preparation parameters according to some embodiments of the present specification.

[0097] In some embodiments, as shown in Figure 4, the meal delivery optimization system (such as an analysis module) can also obtain the customer's user information 410 based on the ordering unit; obtain the first historical order data 420 corresponding to the customer in the ordering unit based on the user information 410; determine the first estimated order distribution 430 based on the first historical order data 420 and the order sequence 310; and determine the food preparation parameters 440 based on the first estimated order distribution 430.

[0098] For relevant instructions on ordering units and ordering sequences, please refer to the corresponding description in Figure 2.

[0099] User information 410 refers to customer-related information, such as the customer's name, gender, age, customer code, etc. In some embodiments, the analysis module can obtain the current user information based on the ordering unit through a storage module, a built-in RFID device, etc.

[0100] The first historical order data 420 refers to the historical order data of the current customer. In some embodiments, the first historical order data may include the customer's multiple historical ordering situations, for example, the time of historical ordering and the sequence of dishes ordered each time.

[0101] The first historical order data can be represented by various forms such as a vector group or a matrix. As an example, the first historical order data of customer Wang (customer code 001) can be represented as [(time 1, dish A, dish B), (time 2, dish A, dish C), …].

[0102] In some embodiments, the ordering unit may store first historical order data corresponding to each customer code based on a customer code, etc. The analysis module may retrieve the corresponding first historical order data from the ordering unit based on the acquired user information.

[0103] The first estimated order distribution 430 refers to the estimated order status corresponding to the current customers in the store. In some embodiments, the first estimated order distribution may include the future order status of each customer who has already arrived at the store. The customer's future order status may include the customer's estimated order items and corresponding quantities.

[0104] In some embodiments, the analysis module may determine the first estimated order distribution in a variety of ways based on the first historical order data and the current order sequence.

[0105] For example, the analysis module may determine the ordered dish sequence based on the current order sequence of the customer corresponding to the current order unit, and then match the ordered dish sequence with the dish sequences of each historical order in the first historical order data, selecting the historical orders with a matching degree greater than a preset matching degree threshold as the historical matching orders. The matching degree may be determined based on the degree of overlap between the dish information included in the ordered dish sequence and the dish information included in the historical order sequence, such that the greater the overlap, the greater the matching degree. The preset matching degree threshold may be an empirical value, such as 0.5.

[0106] Based on historical matching orders, the analysis module can determine the dishes that appeared in each historical matching order, as well as the number of times each dish appeared in all historical matching orders. If the number of times a dish appears is not less than a threshold number of orders, and the corresponding dish is not in the ordered sequence, the analysis module can add the corresponding dish to the first estimated order distribution as the customer's estimated order. The threshold number of orders can be set based on historical experience, such as three times.

[0107] Based on the above method, the analysis module can determine the estimated dishes ordered by each customer who has arrived at the store, and then the analysis module can generate a corresponding first estimated order distribution.

[0108] In some embodiments, different ordering units have different order number thresholds, and the order number thresholds of the ordering units are related to the dining time of the customers of the ordering units and the second evaluation value corresponding to the current kitchen scheduling parameters.

[0109] In some embodiments, the order threshold corresponding to an ordering unit may be positively correlated with the dining time of the customer corresponding to the ordering unit and negatively correlated with a second evaluation value corresponding to the current kitchen scheduling parameter. For example, the longer the customer's dining time, the less likely they are to order, and the order threshold may be increased. The second evaluation value reflects the restaurant's expected food delivery efficiency. A lower second evaluation value indicates a lower expected food delivery efficiency, which may reduce customers' desire to order, and the order threshold may be increased.

[0110] For an explanation of the second evaluation value, please refer to FIG. 3 and its corresponding description.

[0111] In some embodiments of the present specification, by introducing a threshold for the number of orders, the first estimated order distribution can be appropriately restricted and adjusted in combination with the customer's dining time and the second evaluation value corresponding to the current kitchen scheduling parameters, so that the determined first estimated order distribution is more in line with the actual situation.

[0112] The food preparation parameters refer to parameters related to food preparation. In some embodiments, the food preparation parameters may include the food preparation type and the food preparation amount. For example, for a serving of Mapo Tofu, the corresponding food preparation type and food preparation amount may be: 400 grams of tofu and 50 grams of ground beef.

[0113] In some embodiments, the analysis module may determine the dish preparation parameters based on the first estimated order distribution in a variety of ways. For example, the analysis module may determine the corresponding dish preparation type and quantity based on the dishes and quantities included in the first estimated order distribution, thereby obtaining the dish preparation parameters.

[0114] In some embodiments of the present specification, by obtaining the customer's first historical order data and combining it with the current order sequence, a first estimated order distribution is determined to determine the food preparation parameters. Based on the predicted order situation, reasonable food preparation can be carried out, which can achieve advance preparation and improve the accuracy of the prepared dishes, thereby improving the food delivery efficiency and further enhancing the customer's dining experience.

[0115] In some embodiments, the analysis module may further determine a second estimated order distribution 450 based on the order sequence 310 ; and determine a food preparation parameter 440 based on the first estimated order distribution 430 and the second estimated order distribution 450 .

[0116] The second estimated order distribution refers to the estimated order situation of customers who have not yet arrived at the store. For example, the second estimated order distribution may include the dishes and quantities that customers who may arrive at the store in a preset future time period may order.

[0117] In some embodiments, the analysis module may determine the second estimated order distribution in a variety of ways.

[0118] For example, the analysis module can count the corresponding dishes in the order sequence of each current ordering unit, count the number of dishes ordered in a preset historical period (such as the current day, etc.) and rank them in descending order, and determine the corresponding dishes and quantity ratios in the second estimated order distribution based on the top N dishes and the ratio of their ordered quantities.

[0119] For example, if the dishes ordered by users of each current ordering unit are ranked in descending order based on the number of dishes ordered, the resulting sequence is: [(dish 1, number of dishes ordered: 10), (dish 2, number of dishes ordered: 6), (dish 3, number of dishes ordered: 5), (dish 4, number of dishes ordered: 4), (dish 5, number of dishes ordered: 2)]. Let N = 3. The top three dishes are used as the dishes in the second estimated order distribution. The number of dishes in the second estimated order distribution is calculated by dividing the number of dishes ordered by 2 and rounding down. The second estimated order distribution can then be: (dish 1: 5, dish 2: 3, dish 3: 2). This means that it is estimated that customers who will visit the restaurant in the future are likely to order a total of 5 dishes 1, 3 dishes 2, and 2 dishes 3.

[0120] For more information on how to determine the second estimated order distribution, please refer to the corresponding content of Figure 5.

[0121] In some embodiments, the analysis module may determine the meal preparation parameters in various ways based on the first estimated order distribution and the second estimated order distribution. For example, the analysis module may determine the corresponding meal preparation type and amount based on the dishes and quantities included in the first estimated order distribution and the second estimated order distribution, thereby obtaining the final meal preparation parameters.

[0122] In some embodiments of the present specification, by determining a second estimated order distribution based on the current order sequence, and determining food preparation parameters in combination with the second estimated order distribution, more reasonable food preparation parameters can be determined in combination with the existing order situation, which helps to improve the efficiency of food preparation and serving, make the serving process more reasonable, and enhance the customer's dining experience.

[0123] FIG5 is an exemplary schematic diagram of a distribution prediction model according to some embodiments of this specification.

[0124] In some embodiments, as shown in FIG. 5 , the analysis module may further determine a second estimated order distribution 450 based on the first historical order data 420 and the order sequence 310 through a distribution prediction model 510 .

[0125] For an explanation of the first historical order data and the second estimated order distribution, please refer to FIG4 and its corresponding description. For an explanation of the order sequence, please refer to the corresponding description of FIG2.

[0126] Distribution prediction model 510 is a model used to predict the second estimated order distribution. In some embodiments, the distribution prediction model can be a machine learning model, such as a neural network model or a deep neural network model. In some embodiments, the input of the distribution prediction model can include the first historical order data and order sequence corresponding to each order unit, and the output can be the second estimated order distribution.

[0127] In some embodiments, the distribution prediction model can be trained based on a large number of second training samples with second labels. The second training samples can be sample first historical order data and sample order sequences for each ordering unit at a certain first historical moment. The second training samples can be obtained based on historical business data in historical records. The second labels can be constructed based on actual order data from customers visiting the store at a second historical moment corresponding to the second training samples. The second labels can be automatically annotated by the system based on historical records. The first historical moment is before the second historical moment.

[0128] The specific training method of the distribution prediction model is similar to the training method of the meal delivery time prediction model. For details, please refer to the corresponding description in Figure 3.

[0129] In some embodiments of the present specification, by using a distribution prediction model to predict the second estimated order distribution, the accuracy of the predicted second estimated order distribution can be improved, making the subsequently determined food preparation parameters more reasonable, which helps to improve food delivery efficiency.

[0130] In some embodiments, as shown in FIG. 5 , the input of the distribution prediction model 510 may further include current time period features 520 .

[0131] The current time period feature 520 refers to the relevant features of the current time period. In some embodiments, the current time period feature may include the current time period, the current weather (sunny, rainy), etc.

[0132] In some embodiments, when the input of the distribution prediction model includes the current time period feature, the time period feature of the first historical moment in the historical record can be added to the second training sample for training during model training.

[0133] In some embodiments of the present specification, by also taking the current time period characteristics as the input of the distribution prediction model, the impact of external factors such as time period and weather on the restaurant's customer flow can be taken into account. For example, when the weather is too hot, customers who come to the store all order cold drinks. The distribution prediction model can learn this pattern and thus predict the estimated ordering situation of future customers who come to the store under similar circumstances, and make a more accurate prediction of the second estimated order distribution, so as to determine better preparation parameters and ensure food delivery efficiency.

[0134] In some embodiments, as shown in FIG5 , the input of the distribution prediction model 510 may also include the number of customers 530 currently in the restaurant and the second evaluation value 360 ​​corresponding to the current kitchen scheduling parameter.

[0135] For the description of the kitchen scheduling parameters, please refer to the corresponding description of Figure 2, and for the relevant description of the second evaluation value, please refer to Figure 3 and its corresponding description.

[0136] In some embodiments, when the input of the distribution prediction model includes the current number of customers in the restaurant and a second evaluation value, the second evaluation value corresponding to the number of customers in the restaurant at the first historical moment in the historical records and the back-kitchen scheduling parameters at the first historical moment can be added to the second training sample for training during model training.

[0137] In some embodiments of the present specification, the number of customers in the current restaurant and the second evaluation value will affect the customer flow. For example, customers are more willing to go to popular restaurants. Therefore, the more people dine in the restaurant, the more customers it will attract in the future. The second evaluation value reflects the expected waiting time after the customer orders, and the customer's dining time will also affect the number of people in the restaurant. By using the current number of customers in the restaurant and the second evaluation value as inputs to the distribution prediction model, the impact of various factors on customer flow can be comprehensively evaluated, and a more accurate second estimated order distribution can be determined, so that the subsequent preparation parameters are more reasonable and the kitchen's food delivery efficiency is improved.

[0138] Some embodiments of the present specification provide a meal delivery optimization device, comprising at least one processor and at least one memory; the at least one memory is used to store computer instructions; and the at least one processor is used to execute at least part of the computer instructions to implement the above-mentioned meal delivery optimization method.

[0139] Some embodiments of the present specification provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the above-mentioned meal delivery optimization method.

[0140] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit this specification. Although not explicitly stated herein, various modifications, improvements, and revisions to this specification may be made by those skilled in the art. Such modifications, improvements, and revisions are suggested in this specification and remain within the spirit and scope of the exemplary embodiments of this specification.

[0141] This specification also uses specific terms to describe the embodiments of this specification. Terms such as "one embodiment," "an embodiment," and / or "some embodiments" refer to a feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "one embodiment," "an embodiment," or "an alternative embodiment" two or more times in different locations in this specification do not necessarily refer to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of this specification may be appropriately combined.

[0142] In addition, unless expressly stated in the claims, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the spirit and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0143] Similarly, it should be noted that, in order to simplify the presentation of this specification and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this specification sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of this specification requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single disclosed embodiment.

[0144] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the description and claims are approximate values, which may vary according to the required features of the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0145] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, and documents, cited in this specification is hereby incorporated by reference in its entirety. This excludes any application history documents that are inconsistent with or conflicting with the content of this specification, as well as any documents (currently or subsequently appended to this specification) that limit the broadest scope of the claims of this specification. It should be noted that if the descriptions, definitions, and / or terminology used in the accompanying materials are inconsistent or conflicting with the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0146] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly described and illustrated in this specification.

Claims

1. A method for optimizing meal delivery, characterized in that, Including: Obtain the order sequence of the order-taking unit in the dining area, where the order sequence includes the ordered dishes and the order time; Determine the kitchen scheduling parameters according to the order sequence of the order-taking unit, where the kitchen scheduling parameters include the preferred cooking task sequence of the cooking stations in the kitchen; Send the kitchen scheduling parameters to the kitchen receiving terminal.

2. The method according to claim 1, wherein The determining the kitchen scheduling parameters according to the order sequence of the order-taking unit includes: Generate one or more groups of candidate kitchen scheduling parameters according to the order sequence of the order-taking unit; Based on the candidate kitchen scheduling parameters, determine the waiting time of the customer and the meal preparation efficiency of the kitchen; Based on the waiting time of the customer, determine the first evaluation value corresponding to the candidate kitchen scheduling parameters; Based on the meal preparation efficiency of the kitchen, determine the second evaluation value corresponding to the candidate kitchen scheduling parameters; Based on the first evaluation value and the second evaluation value of the candidate kitchen scheduling parameters, determine the kitchen scheduling parameters.

3. The method according to claim 1, characterized in that The method further includes: Obtain the user information of the customer based on the order-taking unit; According to the user information, obtain the first historical order data corresponding to the customer in the order-taking unit; Determine the first estimated order distribution according to the first historical order data and the order sequence, where the first estimated order distribution includes the future order situation of the customer; Determine the ingredient preparation parameters according to the first estimated order distribution.

4. The method according to claim 3, characterized in that, The determining the ingredient preparation parameters according to the first estimated order distribution includes: Determine the second estimated order distribution according to the order sequence, where the second estimated order distribution includes the estimated order situation of customers who have not arrived at the store; Determine the ingredient preparation parameters according to the first estimated order distribution and the second estimated order distribution.

5. A meal delivery optimization system, characterized in that, Including: An obtaining module, configured to obtain the order sequence of the order-taking unit in the dining area, where the order sequence includes the ordered dishes and the order time; A determining module, configured to determine the kitchen scheduling parameters according to the order sequence of the order-taking unit, where the kitchen scheduling parameters include the preferred cooking task sequence of the cooking stations in the kitchen; A sending module, configured to send the kitchen scheduling parameters to the kitchen receiving terminal.

6. The system according to claim 5, characterized in that The determining module is further configured to: Generate one or more groups of candidate kitchen scheduling parameters according to the order sequence of the order-taking unit; Based on the candidate kitchen scheduling parameters, determine the waiting time of the customer and the meal preparation efficiency of the kitchen; Based on the waiting time of the customer, determine the first evaluation value corresponding to the candidate kitchen scheduling parameters; Based on the meal preparation efficiency of the kitchen, determine the second evaluation value corresponding to the candidate kitchen scheduling parameters; Based on the first evaluation value and the second evaluation value of the candidate kitchen scheduling parameters, determine the kitchen scheduling parameters.

7. The system according to claim 5, wherein The system further includes an analysis module; The analysis module is configured to: Obtain the user information of the customer based on the order-taking unit; According to the user information, obtain the first historical order data corresponding to the customer in the order-taking unit; Determine the first estimated order distribution according to the first historical order data and the order sequence, where the first estimated order distribution includes the future order situation of the customer; Determine the ingredient preparation parameters according to the first estimated order distribution.

8. The system according to claim 7, wherein The analysis module is further configured to: Determine a second estimated order distribution according to the order placing sequence, where the second estimated order distribution includes the estimated order placing situations of customers who have not arrived at the store; Determine the ingredient preparation parameters according to the first estimated order distribution and the second estimated order distribution.

9. A meal delivery optimization device, characterized in that, The device includes at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is used to execute at least some of the computer instructions to implement the method according to any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method according to any one of claims 1 to 4.

Images