A catering operation scheduling method and system

Abstract

The application discloses a catering operation scheduling method and system, the method comprises the following steps: collecting real-time catering operation data and obtaining historical operation data; based on the catering operation data and the historical operation data, dynamically predicting the replenishment task; wherein the generation time point of each dish in the replenishment task is configured to make the estimated completion time of the dish earlier than the predicted sell-out time; generating a task sequence according to the replenishment task, and scheduling the corresponding back kitchen resources to perform production. The problem that the production and sales links in the catering operation rely on manual experience judgment, which leads to the fact that the catering system cannot realize accurate regulation and control of supply and demand, and further causes service delay or resource waste is solved. The transformation from experience-driven to data-driven is realized, and a catering operation system with faster response and lower loss is formed.

Description

Technical Field

[0001] This application relates to the field of catering management technology, and in particular to a catering operation scheduling method and system. Background Technology

[0002] In the field of large-scale group catering, the core of its operation lies in responding to peak and off-peak dining demands during concentrated periods. Currently, the production and sales models commonly used in the industry are generally based on standardized process management and human experience-based decision-making.

[0003] The kitchen typically prepares large batches of dishes based on the chefs' experience before serving them and places them in warming equipment for sale. Front-of-house staff are responsible for displaying and selling the dishes and judging which dishes and quantities need to be replenished based on on-site visual observation or sales experience. The timing and quantity of the entire replenishment process are highly dependent on personal experience and subjective judgment.

[0004] The front and back of the restaurant form an open loop that relies on delayed and ambiguous information for decision-making. The lack of real-time and quantitative data links results in the replenishment behavior always being in a passive response state with low accuracy. This leads to problems such as untimely or excessive replenishment, resulting in food waste, which seriously restricts the improvement of the efficiency and service quality of catering operations. Summary of the Invention

[0005] This application provides a catering operation scheduling method and system that solves the problem of untimely replenishment or food waste caused by relying on manual experience in the production and sales stages of catering operations. It achieves dynamic and precise matching and collaborative scheduling of front-of-house sales and back-of-house production resources in catering operations, thereby reducing food waste and operating costs.

[0006] This application provides a catering operation scheduling method and system, wherein the catering operation scheduling method includes: Collect real-time restaurant operation data and obtain historical operation data; Based on the restaurant operation data and the historical operation data, the replenishment task is dynamically predicted; wherein, the generation time of each dish in the replenishment task is configured so that the expected completion time of the dish is earlier than the predicted sell-out time. A task sequence is generated based on the replenishment task, and the corresponding kitchen resources are scheduled to execute production.

[0007] Optionally, the step of dynamically predicting the replenishment task based on the catering operation data and the historical operation data further includes: Periodically retrieve the remaining quantity of all dishes and their sales figures. Traverse the set of remaining quantities, filter out dishes that are currently less than a preset remaining quantity threshold and whose sales ranking is higher than a preset ranking threshold, and form a target dish set; Based on the target menu, the restaurant operation data, and the historical operation data, the replenishment demand is determined and a replenishment task is generated.

[0008] Optionally, the step of determining the replenishment demand and generating a replenishment task based on the target menu, the restaurant operation data, and the historical operation data includes: Based on the real-time sales volume of dishes in the restaurant operation data, calculate the real-time number of people covered by the dishes to be replenished; Based on the historical sales time series data in the historical operation data, the expected number of customers for the dishes to be added is estimated. Based on the real-time number of people covered and the expected number of people to be sold, assess the remaining expected number of people to be sold for the dishes to be replenished; Based on the average sales per person for the dishes to be replenished and the remaining expected number of customers in the catering operation data, calculate the replenishment demand for the dishes to be replenished and generate the replenishment task.

[0009] Optionally, the step of calculating the required quantity of the dish to be replenished and generating the replenishment task includes: Based on the required amount of supplementary vegetables, determine the type of recipe on which the production of the supplementary vegetables is based; If the recipe type is a standard recipe, then query the standard total preparation time corresponding to the standard recipe; If the recipe type is a dynamically generated recipe, then the estimated total preparation time is generated based on the required amount of additional ingredients; Based on the calibrated sales speed and the standard total preparation time or the estimated total preparation time, the future remaining quantity of dishes when the dishes are prepared is estimated; wherein, the calibrated sales speed is calculated from the catering operation data and the historical operation data; If the remaining quantity of the future dishes is lower than the preset risk threshold, a task to replenish the dishes to be replenished will be generated.

[0010] Optionally, the step of generating the replenishment task further includes: Summarize the replenishment needs of the dishes to be replenished in different food lines to generate the total replenishment needs; If the total demand for replenishment exceeds the preset single-time production weight limit, then the production weight in the replenishment task will be set to the single-time production weight limit.

[0011] Optionally, the step of dynamically predicting the replenishment task based on the catering operation data and the historical operation data includes: A sales forecasting model is established based on the historical sales time-series data in the aforementioned historical operational data; The output of the sales forecasting model is dynamically adjusted based on the real-time sales volume of dishes and real-time customer traffic in the restaurant operation data. Based on the model output and the standard preparation time of the dishes, the timing of replenishing each dish is predicted, and the replenishment task is generated.

[0012] Optionally, the step of generating a task sequence based on the replenishment task and scheduling corresponding kitchen resources to perform production includes: When there are multiple replenishment tasks, a priority index is calculated for each replenishment task. Based on the priority index, the execution order of the multiple replenishment tasks is determined, and the task sequence is generated; According to the order in the task sequence, kitchen resources are scheduled to perform production in sequence.

[0013] Optionally, the step of sequentially scheduling kitchen resources to perform production according to the order in the task sequence includes: The replenishment task in the task sequence is parsed into multiple ordered production instructions, which include at least ingredient preparation instructions, cooking and processing instructions, and finished product delivery instructions. The production instructions are assigned to the corresponding kitchen resource units, wherein the kitchen resource units include a material preparation area, cooking equipment, and conveying equipment. Monitor the execution status of the production instructions and dynamically adjust the execution order of the instructions according to the priority of the task sequence.

[0014] Furthermore, to achieve the above objectives, embodiments of the present invention also provide a catering operation scheduling system, the system comprising: The data acquisition module is used to collect restaurant operation data in real time. The data storage module is used to store historical operational data; The task prediction module is used to dynamically predict replenishment tasks based on the catering operation data and the historical operation data; wherein, the generation time of each dish in the replenishment task is configured so that the expected completion time of the dish is earlier than the predicted sell-out time. The task scheduling and execution module is used to generate a task sequence based on the replenishment task and schedule the corresponding kitchen resources to perform production.

[0015] Optionally, the task prediction module includes: The data filtering unit is used to periodically obtain the remaining quantity set and sales ranking of all dishes, and filter out the dishes to be added that have a current remaining quantity less than a preset remaining quantity threshold and a sales ranking higher than a preset ranking threshold, so as to form a target dish set. The demand calculation unit is used to calculate the replenishment demand of each dish to be replenished in the target dish set based on the output catering operation data and the historical operation data. The task decision unit is used to determine whether to generate the final replenishment task based on the required amount of replenishment vegetables and the estimated future surplus when the preparation of vegetables is completed.

[0016] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: By integrating real-time data with historical patterns, we can accurately predict when dishes will sell out and when replenishment will be needed, thus avoiding decision-making errors caused by a lack of transparency and human experience.

[0017] By configuring the generation time of replenishment tasks to match the predicted sell-out time, a shift has been achieved from a passive "replenish when out of stock" mode to a proactive early warning mode of "replenishing before stockouts occur," thereby ensuring the continuity of supply and reducing the risk of service interruptions.

[0018] By automatically generating sequences for predicted tasks and scheduling kitchen resources, the entire chain from sales to production is streamlined, eliminating delays and errors caused by manual communication. This allows the entire system to operate as a highly efficient whole, significantly reducing human coordination costs while improving response speed. Attached Figure Description

[0019] Figure 1 This is a schematic diagram illustrating the framework of the catering operation scheduling method in this application; Figure 2 This is a flowchart illustrating the catering operation scheduling method of this application; Figure 3 This is a system composition and data flow diagram of an embodiment of the catering operation scheduling method of this application; Figure 4 This is a system architecture diagram of the catering operation scheduling system in this application; Figure 5 This is an architecture diagram of the task prediction module in the catering operation scheduling system of this application; Figure 6 This is an architecture diagram of the task scheduling and execution module in the catering operation scheduling system of this application; Figure 7 This is a schematic diagram of the terminal structure of the hardware operating environment involved in one embodiment of this application. Detailed Implementation

[0020] To address the technical challenges of information disconnect between front-of-house sales and back-of-house production in restaurant operations, and the coexistence of untimely replenishment and food waste due to reliance on manual experience, this application proposes a restaurant operation scheduling method. By collecting multi-source data such as sales volume and customer traffic in real time, and combining this with historical sales patterns, the method dynamically predicts the latest time and quantity of each dish that needs replenishment, and automatically generates task sequences to schedule kitchen resources for execution. This transforms the passive and vague response relying on manual experience into proactive and precise control based on data prediction, thereby achieving precise matching of supply and demand. Ultimately, while ensuring a continuous supply of dishes, it significantly reduces food waste and operating costs.

[0021] To better understand the above technical solutions, exemplary embodiments of this application will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of this application are shown in the drawings, it should be understood that this application can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of this application and to fully convey the scope of this application to those skilled in the art.

[0022] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0023] Example 1 This embodiment provides a method for scheduling restaurant operations.

[0024] Reference Figure 1-2 The catering operation scheduling method in this embodiment includes the following steps: Step S100: Collect real-time restaurant operation data and obtain historical operation data; In this embodiment, restaurant operation data includes at least multi-source data such as real-time sales volume of dishes, real-time customer traffic, and real-time inventory data; historical operation data includes at least historical sales time-series data and standard preparation time for dishes. Historical sales time-series data refers to data such as dish sales volume, sales revenue, and customer traffic recorded in chronological order, used to analyze sales trends, peak period patterns, and dish lifecycles.

[0025] As an optional implementation method, refer to Figure 3 By deploying various sensors and system interfaces, dynamic catering operation data is collected in real time. Relevant historical operation data is then retrieved from a stored historical database.

[0026] For example, the remaining weight of dishes can be obtained in real time via a smart scale, such as 2.1kg of braised pork. Real-time transaction data can be captured through the payment interruption interface at the checkout counter, such as 12 servings sold in the past 5 minutes. Customer flow can be counted using a people flow monitoring device, such as 25 new customers added in 5 minutes. At the same time, the current inventory status can be read from the inventory management system. Meanwhile, historical sales time-series data can be queried, such as sales records from Tuesday lunchtimes over the past four weeks, and the standard preparation time for dishes can be obtained from a recipe database, such as the standard preparation, cooking, and serving time for braised pork.

[0027] Optionally, when acquiring historical operational data, contextual dimensions such as weather conditions and weekday type can be incorporated. For example, when predicting the demand for dishes on a rainy Wednesday, historical sales records of "Wednesday + Rainy Day" can be prioritized as the analysis benchmark. Contextualized data matching mechanisms can effectively identify customer consumption preferences under specific circumstances, thereby making the predicted replenishment tasks more accurate.

[0028] Step S200: Based on the catering operation data and the historical operation data, dynamically predict the replenishment task; wherein, the generation time of each dish in the replenishment task is configured so that the expected completion time of the dish is earlier than the predicted sell-out time. In this embodiment, by integrating real-time catering operation data and historical operation data, replenishment tasks are dynamically predicted and generated. The generation time of the replenishment tasks is configured so that the expected completion time of the dishes is earlier than the predicted sell-out time. This transforms the original passive, response-based replenishment mode that relies on human experience into a proactive, early warning-based supply guarantee, avoiding sales interruptions caused by untimely replenishment, and also avoiding the problems of reduced dish quality or waste caused by replenishing too early.

[0029] As an optional implementation, replenishment tasks can be predicted based on the remaining quantity of dishes. Specifically, the remaining quantity set of all dishes can be obtained periodically, along with the sales volume of each dish. The remaining quantity set is then traversed, and dishes whose current remaining quantity is less than a preset remaining quantity threshold and whose sales volume ranking is higher than a preset ranking threshold are selected to form a target dish set. The target dish set typically contains multiple dishes that need replenishment. By performing subsequent replenishment demand calculations on each dish in the target dish set in parallel, and then prioritizing these generated replenishment tasks according to the urgency of each dish, such as the expected sell-out time and sales speed, an ordered replenishment task sequence is formed.

[0030] For example, taking Kung Pao Chicken during the lunch peak as an example, a timed scan found that its current remaining quantity is 25% of the full plate, which is lower than the preset remaining quantity threshold of 30%, and its real-time sales ranking is the 2nd in the entire menu, which is higher than the ranking threshold of the top 10. Therefore, it is included in the target dish set.

[0031] As another optional implementation, after determining the target menu, the replenishment demand is determined based on the target menu, the restaurant operation data, and the historical operation data, and a replenishment task is generated. Specifically, based on the real-time sales volume of the dishes in the restaurant operation data, the real-time reach of the dishes to be replenished is calculated; then, based on the historical sales time series data in the historical operation data, the expected number of customers for the dishes to be replenished is estimated; based on the real-time reach and the expected number of customers, the remaining expected number of customers for the dishes to be replenished is assessed; finally, based on the average sales per customer for the dishes to be replenished in the restaurant operation data and the remaining expected number of customers, the replenishment demand of the dishes to be replenished is calculated, and the replenishment task is generated.

[0032] For example, taking dish A as an example, based on the data that 18 servings were sold in the past 15 minutes and corresponded to 60 customers, the real-time average sales per person are calculated to be 0.3 servings / person; based on historical sales time series data, the total customer flow for the day is predicted to be 150 people, and after deducting the 60 people already served, the remaining expected sales number is 90 people; multiplying the real-time average sales per person by the remaining expected sales number, the precise demand of replenishing 27 servings, about 8.1 kilograms, is obtained, and the replenishment task is automatically generated and sent to the kitchen scheduling system.

[0033] As another optional implementation method, after determining the replenishment demand, it is determined whether to use a standard recipe or a dynamically generated recipe based on the replenishment demand. If based on a standard recipe, the standard total preparation time is queried; if based on a dynamically generated recipe, an estimated total preparation time is generated based on the replenishment demand. Then, based on the current sales trend generated from the restaurant operation data, and combined with the historical patterns of the same period in historical operation data, a calibrated sales speed is obtained. Based on the calibrated sales speed and the standard total preparation time or the estimated total preparation time, the future remaining quantity of dishes when the dishes are prepared is estimated; if the future remaining quantity of dishes is lower than a preset risk threshold, a replenishment task for the dishes to be replenished is confirmed.

[0034] For example, after determining that dish A needs to be replenished by 8.1 kg, and judging that this category meets the standard recipe's 10 kg specification, the standard recipe is adopted, and its standard total preparation time is retrieved, i.e., standard cooking time + standard preparation time + standard serving time = 25 minutes. Based on the calibrated sales speed prediction, after 25 minutes, the remaining quantity of this dish is only 1.2 kg, which is lower than the preset risk threshold. A replenishment task for this dish will be generated. The replenishment task includes key information such as the dish label, the recipe used, the estimated sell-out time of the dish, and the estimated generation time. If the replenishment quantity is only 3 kg, far below the standard portion, the dynamic recipe generation process is initiated. Based on the characteristics of small-batch cooking, an estimated total preparation time of 15 minutes is generated. When the remaining quantity is predicted to be lower than the preset risk threshold after 15 minutes, a replenishment task is also triggered.

[0035] It's important to note that after generating the target menu, the corresponding replenishment task isn't generated immediately. Instead, a secondary decision is made based on the future remaining stock of the menu items. This filtering mechanism accurately distinguishes between temporary stock fluctuations and substantial stockout risks. When forecasts indicate that future stock levels remain above the risk threshold, production is not triggered, effectively preventing over-replenishment due to short-term sales fluctuations.

[0036] As another alternative implementation, when generating a food replenishment task, for scenarios with multiple food lines simultaneously, such as... Figure 3 It has two food service lines, summarizing the replenishment needs of the dishes to be replenished in different food service lines to generate the total replenishment needs. If the total replenishment needs exceed the preset single-time production weight limit, the production weight in the replenishment task will be set to the single-time production weight limit.

[0037] For example, to manage customer flow during peak dining hours, the restaurant operates two parallel food lines. Monitoring showed that dish A required 2.5 kg to replenish on food line one and 3.0 kg on food line two, totaling 5.5 kg. Since the maximum single-batch production weight for this dish is set at 5 kg, the production weight was automatically set to 5 kg when generating the total replenishment task. This 5 kg of food, once completed, was proportionally distributed to the different food lines for replenishment. This ensured continuous supply to all parallel food lines while preventing the kitchen from being affected by excessive single-batch cooking, thus maintaining production efficiency and quality.

[0038] As an optional implementation, in addition to predicting replenishment tasks based on surplus stock, a sales forecasting model can also be used to predict and generate replenishment tasks. A sales forecasting model is established based on historical sales time-series data from historical operational data. The output of the sales forecasting model is dynamically adjusted according to the real-time sales volume of dishes and real-time customer traffic in the restaurant operational data. Based on the model output and the standard preparation time of the dishes, the replenishment time point for each dish is predicted, and the replenishment task is generated.

[0039] Optionally, an initial sales forecasting model can be established based on historical operational data before or at the beginning of the meal period. At this stage, the model outputs a preliminary, rough prediction of the sell-out time for each dish based on historical patterns, and a preliminary plan for replenishment tasks. This initial forecast provides the kitchen with a general reference for the production rhythm, helping them prepare materials in advance. Real-time catering operation data is continuously collected, and the sales forecasting model is continuously updated and corrected based on this data. When it is determined that the remaining sellable time is less than or equal to the required preparation time, a replenishment task is triggered. The remaining sellable time includes buffer time; that is, the remaining sellable time is the sum of the preparation time and the buffer time.

[0040] Step S300: Generate a task sequence based on the replenishment task, and schedule the corresponding kitchen resources to perform production.

[0041] In this embodiment, after generating the task sequence, scheduling is as follows: Figure 3 The food preparation area handles ingredient cutting and preparation, schedules multi-material loading robots to transport necessary materials, and schedules the cooking area to execute cooking tasks. Once cooking is complete, delivery robots transport the finished dishes. Furthermore, each scheduled task can be displayed on a corresponding Kanban board. For example, the food preparation Kanban board displays the raw materials needed for the dishes, allowing operators to notify for replenishment or reject tasks when materials are insufficient. The robot operation Kanban board displays the work tasks of each robot, and the scheduling Kanban board displays the tasks of each module. Operators can adjust tasks on the scheduling Kanban board, such as canceling, adding / modifying, or merging tasks.

[0042] As an optional implementation, when there are multiple replenishment tasks, a priority index is calculated for each replenishment task. Based on the priority index, the execution order of the multiple replenishment tasks is determined, a task sequence is generated, and kitchen resources are scheduled to perform production in sequence according to the order in the task sequence.

[0043] Optionally, when determining the execution order of multiple replenishment tasks, at least one of the following factors can be used: future remaining quantity of dishes, real-time sales speed of dishes, standard total preparation time of dishes, or estimated total preparation time of dishes. The calculation logic is that the lower the future remaining quantity of dishes, the faster the real-time sales speed, and the longer the total preparation time, the higher the priority.

[0044] As another optional implementation, when scheduling kitchen resources to perform production in sequence according to the order in the task sequence, the replenishment tasks in the task sequence are parsed into multiple ordered production instructions, which include at least ingredient preparation instructions, cooking and processing instructions, and finished product delivery instructions; the production instructions are assigned to the corresponding kitchen resource units, which include a preparation area, cooking equipment, and delivery equipment; the execution status of the production instructions is monitored, and the execution order of the instructions is dynamically adjusted according to the priority of the task sequence.

[0045] For example, a high-priority task to replenish dish A is parsed into ingredient preparation instructions, cooking and processing instructions, and finished product delivery instructions. (Refer to...) Figure 3 The system sends ingredient preparation instructions to the food preparation room, instructing the preparation of raw materials and seasonings, and instructing the compound loading robot to transport the prepared materials to the designated location in the cooking room; then it sends cooking instructions to the designated cooking equipment in the cooking room, along with the corresponding recipe, and starts the cooking process; after cooking is completed, it sends instructions to the robot scheduling system, instructing the delivery robot to load the cooked dishes and transport them to the designated serving line.

[0046] Optionally, the status of each instruction is monitored in real time during the above operation process. When it is found that a higher-priority B dish replenishment task is blocked due to congestion in the preparation room, the instruction sequence is immediately dynamically adjusted, and the ingredient preparation instruction of the B dish replenishment task is temporarily moved before the cooking instruction of the A dish replenishment task to ensure that the urgent task gets priority access to resources. After the ingredients are ready, the original sequence is restored.

[0047] The technical solutions described in the embodiments of this application above have at least the following technical effects or advantages: By continuously monitoring remaining food inventory and combining this with sales rankings for filtering, we can quickly and directly identify popular dishes that are at risk of running out of stock, forming a target dish set. For the selected dishes, we calculate the replenishment quantity based on real-time average sales per person and the predicted number of remaining customers, and incorporate preparation time to estimate future inventory levels for the final decision, ensuring a high degree of match between replenishment quantity and actual demand. The replenishment tasks are automatically parsed into ordered production instructions, and kitchen resources such as the preparation room, cooking equipment, and conveyor robots are coordinated to work together. By monitoring the status of instructions and dynamically adjusting the execution order, we ensure that high-priority tasks are completed first, thereby maximizing the continuous supply of key dishes during peak periods when resources are scarce.

[0048] Based on the same inventive concept, this application also provides a system corresponding to the method in Embodiment 1, as shown in Embodiment 2.

[0049] Example 2 This embodiment provides a catering operation scheduling system. (Refer to...) Figure 4 The catering operation scheduling system in this embodiment includes: The data acquisition module is used to collect restaurant operation data in real time. In this embodiment, the data acquisition module is used to collect system time, real-time sales and trends of dishes based on smart scales, and real-time pedestrian flow obtained through passenger flow monitoring equipment.

[0050] The data storage module is used to store historical operational data; In this embodiment, the data storage module is used to store historical operational data such as historical sales time-series data, historical customer flow data, standard menu preparation time, and historical scheduling records.

[0051] The task prediction module is used to dynamically predict replenishment tasks based on the catering operation data and the historical operation data; wherein, the generation time of each dish in the replenishment task is configured so that the expected completion time of the dish is earlier than the predicted sell-out time. In this embodiment, refer to Figure 5 The task prediction module includes a data filtering unit, a demand calculation unit, and a task decision unit.

[0052] The data filtering unit performs initial screening of dishes through the following process: The input interface continuously receives real-time catering operation data from the data acquisition module, including the remaining quantity data and sales ranking data of each dish; the real-time remaining quantity is compared with the preset remaining quantity threshold, and the real-time sales ranking is compared with the preset ranking threshold. When any dish meets the conditions of having a remaining quantity lower than the preset remaining quantity threshold and a sales ranking higher than the preset ranking threshold, it is included in the target dish set, and the output interface transmits the target dish set to the demand calculation unit.

[0053] The demand calculation unit employs a multi-source data fusion algorithm to calculate the precise replenishment quantity: it acquires historical operational data from the data storage module, including historical sales time-series data and historical customer flow data. Based on the real-time sales volume and real-time customer flow of each dish in the target menu, it calculates the dynamic average sales volume per person and predicts customer flow for subsequent periods based on historical customer flow patterns. The unit outputs a quantitative demand using the calculation model: Replenishment Demand = Dynamic Average Sales Volume per Person × Predicted Customer Flow. An upper limit constraint is applied to the calculation results: when the demand value exceeds the single-time production limit, the replenishment demand is automatically adjusted to the set upper limit value.

[0054] The task decision unit calls up standard recipes or dynamically generates recipes according to the type of dish, obtains the corresponding standard total preparation time or estimated total preparation time, estimates the future surplus when the dish preparation is completed based on the current sales trend and preparation time, compares the estimated surplus with the preset risk threshold, and only generates a structured replenishment task containing dish identification, production quantity and expected completion time when the future surplus is lower than the risk threshold.

[0055] Through the cascading collaboration of the three units, a complete closed loop is achieved, enabling precise identification of key dishes from massive amounts of data, calculation of demand, and intelligent decision-making based on risk prediction. This ensures the system's high responsiveness to real-time operational status, while multi-level verification mechanisms prevent overproduction, ultimately reducing food waste while ensuring supply.

[0056] The task scheduling and execution module is used to generate a task sequence based on the replenishment task and schedule the corresponding kitchen resources to perform production.

[0057] In this embodiment, refer to Figure 6 The task scheduling and execution module includes a task receiving and priority sorting unit, a task parsing and instruction generation unit, a resource scheduling and allocation unit, an execution monitoring and dynamic adjustment unit, and an exception handling and recovery unit.

[0058] The task receiving and priority sorting unit establishes a task receiving queue and ensures task order traceability through timestamps. A dynamic priority algorithm is employed, comprehensively considering the predicted sell-out time of dishes, real-time sales speed, and total preparation time to calculate an urgency index and sort tasks. Manual intervention is supported to meet special needs.

[0059] The task parsing and instruction generation unit adopts a layered parsing architecture, decomposing the food replenishment task into three categories of standardized instructions: ingredient preparation, cooking and processing, and finished product delivery. Instructions are identified through a unified coding standard, establishing logical dependencies and ensuring accurate execution timing.

[0060] The resource scheduling and allocation unit collects resource status in real time based on IoT technology to construct a dynamic resource map. Using load balancing algorithms, it allocates tasks to the most suitable resource units by considering factors such as device location, load rate, and idle time.

[0061] The execution monitoring and dynamic adjustment unit monitors process progress and equipment status in real time through a sensor network. A rule-driven adjustment mechanism is established, automatically generating adjustment plans when execution deviations are detected, ensuring that high-priority tasks are executed first.

[0062] The anomaly handling and recovery unit has pre-set contingency plans for equipment failures, raw material shortages, and other anomalies. When the system detects an anomaly, it automatically activates backup resources and reallocates tasks. The entire anomaly handling process is recorded, providing data support for system optimization.

[0063] The catering operation scheduling system in this embodiment achieves precision and automation in replenishment decisions during catering operations through a data-driven intelligent prediction and dynamic scheduling mechanism, which significantly reduces food waste and operating costs while ensuring a continuous supply of dishes.

[0064] Since the system described in Embodiment 2 of this application is a system used to implement the method of Embodiment 1 of this application, those skilled in the art can understand the specific structure and variations of the system based on the method described in Embodiment 1 of this application, and therefore will not be described again here. All systems used in the method of Embodiment 1 of this application fall within the scope of protection of this application.

[0065] Example 3 In this application embodiment, a catering operation scheduling device is proposed.

[0066] Reference Figure 7 , Figure 7 This is a schematic diagram of the terminal structure of the hardware operating environment involved in one embodiment of this application.

[0067] like Figure 7As shown, the control terminal may include: a processor 1001, such as a CPU, a network interface 1003, a memory 1004, and a communication bus 1002. The communication bus 1002 is used to enable communication between these components. The network interface 1003 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1004 may be high-speed RAM or stable non-volatile memory, such as disk storage. Alternatively, the memory 1004 may be a storage device independent of the aforementioned processor 1001.

[0068] Those skilled in the art will understand that Figure 7 The terminal structure shown does not constitute a limitation on the terminal and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0069] like Figure 7 As shown, the memory 1004, which serves as a computer storage medium, may include an operating system, a network communication module, and a catering operation scheduling program.

[0070] exist Figure 7 In the hardware structure of the catering operation scheduling equipment shown, the processor 1001 can call the catering operation scheduling program stored in the memory 1004 and perform the following operations: Collect real-time restaurant operation data and obtain historical operation data; Based on the restaurant operation data and the historical operation data, the replenishment task is dynamically predicted; wherein, the generation time of each dish in the replenishment task is configured so that the expected completion time of the dish is earlier than the predicted sell-out time. A task sequence is generated based on the replenishment task, and the corresponding kitchen resources are scheduled to execute production.

[0071] Optionally, the processor 1001 may call the catering operation scheduling program stored in the memory 1004 and also perform the following operations: Periodically retrieve the remaining quantity of all dishes and their sales figures. Traverse the set of remaining quantities, filter out dishes that are currently less than a preset remaining quantity threshold and whose sales ranking is higher than a preset ranking threshold, and form a target dish set; Based on the target menu, the restaurant operation data, and the historical operation data, the replenishment demand is determined and a replenishment task is generated.

[0072] Optionally, the processor 1001 may call the catering operation scheduling program stored in the memory 1004 and also perform the following operations: Based on the real-time sales volume of dishes in the restaurant operation data, calculate the real-time number of people covered by the dishes to be replenished; Based on the historical sales time series data in the historical operation data, the expected number of customers for the dishes to be added is estimated. Based on the real-time number of people covered and the expected number of people to be sold, assess the remaining expected number of people to be sold for the dishes to be replenished; Based on the average sales per person for the dishes to be replenished and the remaining expected number of customers in the catering operation data, calculate the replenishment demand for the dishes to be replenished and generate the replenishment task.

[0073] Optionally, the processor 1001 may call the catering operation scheduling program stored in the memory 1004 and also perform the following operations: Based on the required amount of supplementary vegetables, determine the type of recipe on which the production of the supplementary vegetables is based; If the recipe type is a standard recipe, then query the standard total preparation time corresponding to the standard recipe; If the recipe type is a dynamically generated recipe, then the estimated total preparation time is generated based on the required amount of additional ingredients; Based on the calibrated sales speed and the standard total preparation time or the estimated total preparation time, the future remaining quantity of dishes when the dishes are prepared is estimated; wherein, the calibrated sales speed is calculated from the catering operation data and the historical operation data; If the remaining quantity of the future dishes is lower than the preset risk threshold, a task to replenish the dishes to be replenished will be generated.

[0074] Optionally, the processor 1001 may call the catering operation scheduling program stored in the memory 1004 and also perform the following operations: Summarize the replenishment needs of the dishes to be replenished in different food lines to generate the total replenishment needs; If the total demand for replenishment exceeds the preset single-time production weight limit, then the production weight in the replenishment task will be set to the single-time production weight limit.

[0075] Optionally, the processor 1001 may call the catering operation scheduling program stored in the memory 1004 and also perform the following operations: A sales forecasting model is established based on the historical sales time-series data in the aforementioned historical operational data; The output of the sales forecasting model is dynamically adjusted based on the real-time sales volume of dishes and real-time customer traffic in the restaurant operation data. Based on the model output and the standard preparation time of the dishes, the timing of replenishing each dish is predicted, and the replenishment task is generated.

[0076] Optionally, the processor 1001 may call the catering operation scheduling program stored in the memory 1004 and also perform the following operations: When there are multiple replenishment tasks, a priority index is calculated for each replenishment task. Based on the priority index, the execution order of the multiple replenishment tasks is determined, and the task sequence is generated; According to the order in the task sequence, kitchen resources are scheduled to perform production in sequence.

[0077] Optionally, the processor 1001 may call the catering operation scheduling program stored in the memory 1004 and also perform the following operations: The replenishment task in the task sequence is parsed into multiple ordered production instructions, which include at least ingredient preparation instructions, cooking and processing instructions, and finished product delivery instructions. The production instructions are assigned to the corresponding kitchen resource units, wherein the kitchen resource units include a material preparation area, cooking equipment, and conveying equipment. Monitor the execution status of the production instructions and dynamically adjust the execution order of the instructions according to the priority of the task sequence.

[0078] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0079] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0080] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0081] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0082] It should be noted that any reference signs placed between parentheses in the claims should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. This application can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, third, etc., does not indicate any order. These words can be interpreted as names.

[0083] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0084] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of the invention. Therefore, if these modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include these modifications and variations.

Claims

1. A catering operation scheduling method, characterized in that, The method includes: Collect real-time restaurant operation data and obtain historical operation data; Based on the restaurant operation data and the historical operation data, the replenishment task is dynamically predicted; wherein, the generation time of each dish in the replenishment task is configured so that the expected completion time of the dish is earlier than the predicted sell-out time. A task sequence is generated based on the replenishment task, and the corresponding kitchen resources are scheduled to execute production.

2. The method as described in claim 1, characterized in that, The step of dynamically predicting the replenishment task based on the catering operation data and the historical operation data further includes: Periodically retrieve the remaining quantity of all dishes and their sales figures. Traverse the set of remaining quantities, filter out dishes that are currently less than a preset remaining quantity threshold and whose sales ranking is higher than a preset ranking threshold, and form a target dish set; Based on the target menu, the restaurant operation data, and the historical operation data, the replenishment demand is determined and a replenishment task is generated.

3. The method as described in claim 2, characterized in that, The steps of determining the replenishment demand and generating a replenishment task based on the target menu, the restaurant operation data, and the historical operation data include: Based on the real-time sales volume of dishes in the restaurant operation data, calculate the real-time number of people covered by the dishes to be replenished; Based on the historical sales time series data in the historical operation data, the expected number of customers for the dishes to be added is estimated. Based on the real-time number of people covered and the expected number of people to be sold, assess the remaining expected number of people to be sold for the dishes to be replenished; Based on the average sales per person for the dishes to be replenished and the remaining expected number of customers in the catering operation data, calculate the replenishment demand for the dishes to be replenished and generate the replenishment task.

4. The method as described in claim 3, characterized in that, The steps of calculating the required quantity of the dish to be replenished and generating the replenishment task include: Based on the required amount of supplementary vegetables, determine the type of recipe on which the production of the supplementary vegetables is based; If the recipe type is a standard recipe, then query the standard total preparation time corresponding to the standard recipe; If the recipe type is a dynamically generated recipe, then the estimated total preparation time is generated based on the required amount of additional ingredients; Based on the calibrated sales speed and the standard total preparation time or the estimated total preparation time, the future remaining quantity of dishes when the dishes are prepared is estimated; wherein, the calibrated sales speed is calculated from the catering operation data and the historical operation data; If the remaining quantity of the future dishes is lower than the preset risk threshold, a task to replenish the dishes to be replenished will be generated.

5. The method according to any one of claims 2-4, characterized in that, The steps for generating the replenishment task also include: Summarize the replenishment needs of the dishes to be replenished in different food lines to generate the total replenishment needs; If the total demand for replenishment exceeds the preset single-time production weight limit, then the production weight in the replenishment task will be set to the single-time production weight limit.

6. The method as described in claim 1, characterized in that, The step of dynamically predicting the replenishment task based on the catering operation data and the historical operation data includes: A sales forecasting model is established based on the historical sales time-series data in the aforementioned historical operational data; The output of the sales forecasting model is dynamically adjusted based on the real-time sales volume of dishes and real-time customer traffic in the restaurant operation data. Based on the model output and the standard preparation time of the dishes, the timing of replenishing each dish is predicted, and the replenishment task is generated.

7. The method as described in claim 1, characterized in that, The step of generating a task sequence based on the replenishment task and scheduling the corresponding kitchen resources to execute production includes: When there are multiple replenishment tasks, a priority index is calculated for each replenishment task. Based on the priority index, the execution order of the multiple replenishment tasks is determined, and the task sequence is generated; According to the order in the task sequence, kitchen resources are scheduled to perform production in sequence.

8. The method as described in claim 7, characterized in that, The step of sequentially scheduling kitchen resources to perform production according to the order in the task sequence includes: The replenishment task in the task sequence is parsed into multiple ordered production instructions, which include at least ingredient preparation instructions, cooking and processing instructions, and finished product delivery instructions. The production instructions are assigned to the corresponding kitchen resource units, wherein the kitchen resource units include a material preparation area, cooking equipment, and conveying equipment. Monitor the execution status of the production instructions and dynamically adjust the execution order of the instructions according to the priority of the task sequence.

9. A catering operation scheduling system, characterized in that, The system includes: The data acquisition module is used to collect restaurant operation data in real time. The data storage module is used to store historical operational data; The task prediction module is used to dynamically predict replenishment tasks based on the catering operation data and the historical operation data; wherein, the generation time of each dish in the replenishment task is configured so that the expected completion time of the dish is earlier than the predicted sell-out time. The task scheduling and execution module is used to generate a task sequence based on the replenishment task and schedule the corresponding kitchen resources to perform production.

10. The system as described in claim 9, characterized in that, The task prediction module includes: The data filtering unit is used to periodically obtain the remaining quantity set and sales ranking of all dishes, and filter out the dishes to be added that have a current remaining quantity less than a preset remaining quantity threshold and a sales ranking higher than a preset ranking threshold, so as to form a target dish set. The demand calculation unit is used to calculate the replenishment demand of each dish to be replenished in the target dish set based on the output catering operation data and the historical operation data. The task decision unit is used to determine whether to generate the final replenishment task based on the required amount of replenishment vegetables and the estimated future surplus when the preparation of vegetables is completed.

Images