Meal delivery control method and system applied to freezing type unmanned restaurant

Abstract

The invention relates to a meal delivery control method and system applied to a freezing type unmanned restaurant, and the method comprises the steps: H1, collecting the data information of historical meal delivery parameters of the unmanned restaurant in the meal delivery process of the freezing type unmanned restaurant, and obtaining the data information of the food type, the data information of the food temperature, and the data information of the food heating duration in real time; and H2, based on the data information of the historical meal delivery parameters of the unmanned restaurant, the data information of the food type, the data information of the food temperature and the data information of the food heating duration, adopting an improved BP neural network prediction algorithm based on a genetic algorithm to predict the meal delivery sequence of the food, and the predicted data information of the food delivery sequence of the food is obtained. According to the invention, the problem of high failure rate of meal delivery under the freezing condition is solved, the food heating energy consumption is further reduced, the meal delivery efficiency of the freezing type unmanned restaurant is improved, and the use experience of a user is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned restaurants, and in particular to a meal delivery control method and system applied to a frozen unmanned restaurant. Background Art

[0002] As a typical representative of the intelligent transformation of the catering industry, the core technologies of unmanned restaurants integrate cutting-edge technologies such as artificial intelligence, the Internet of Things, big data, and automated equipment, aiming to achieve fully unmanned services.

[0003] In vending machines and catering equipment, there are problems of high failure rates in meal delivery under freezing conditions. Especially when it is necessary to maintain the freshness and safety of food, it is difficult to ensure the high-efficiency and low-failure-rate operation of the equipment. In recent years, with the development of emerging technologies such as artificial intelligence, the Internet of Things, and big data, unmanned restaurants, as a new type of catering model, have received wide attention. According to relevant literature, unmanned restaurants can significantly improve service efficiency by realizing automated order taking, meal preparation, and delivery services through intelligent devices. However, in frozen unmanned restaurants, due to the variety of food types and different heating requirements, how to efficiently arrange the meal delivery order has become an urgent problem to be solved.

[0004] In traditional solutions, the simple First-Come-First-Serve (FCFS) strategy is often adopted, but it has the following defects:

[0005] 1. Ignoring the differences in food types may cause the quality of some foods to be affected due to excessive waiting time;

[0006] 2. Lack of dynamic adjustment ability and inability to cope with the situation of a sharp increase in orders during peak periods.

[0007] Existing research has proposed a variety of optimization algorithms to solve similar problems. For example, the research published by Dai Zhikai in the journal "Food Research and Development" uses genetic algorithms to optimize the food processing process; Chinese Patent CN108345958A describes a method for constructing, predicting, and a model and device for predicting the meal delivery time of orders. Although these methods have improved efficiency to a certain extent, they still have the following deficiencies:

[0008] Genetic algorithms are prone to falling into local optimal solutions;

[0009] Deep learning models rely on a large amount of labeled data and are difficult to adapt to small-sample scenarios. Summary of the Invention

[0010] In view of the above problems, the present invention provides a meal delivery control method and system for a frozen unmanned restaurant, which not only solves the problem of high failure rate in meal delivery under frozen conditions, but also further reduces the energy consumption of food heating, improves the meal delivery efficiency of the frozen unmanned restaurant, and enhances the user experience.

[0011] In order to achieve the above object and other related objects, the technical solution provided by the present invention is as follows:

[0012] A meal delivery control method for a frozen unmanned restaurant, the method comprising:

[0013] H1. During the meal delivery process of the frozen unmanned restaurant, collect the data information of the historical meal delivery parameters of the unmanned restaurant, and obtain the data information of the food type, the data information of the food temperature, and the data information of the food heating duration in real time;

[0014] H2. Based on the data information of the historical meal delivery parameters of the unmanned restaurant, the data information of the food type, the data information of the food temperature, and the data information of the food heating duration, use an improved BP neural network prediction algorithm based on the genetic algorithm to predict the meal delivery order of the food, and obtain the data information of the predicted meal delivery order of the food;

[0015] H3. Based on the data information of the predicted meal delivery order of the food, use an improved goshawk optimization algorithm based on crazy self-adaptation to optimize the meal delivery order of the food, and obtain the data information of the optimized meal delivery order of the food;

[0016] H4. Based on the data information of the optimized meal delivery order of the food, construct a user satisfaction evaluation function Q to evaluate the satisfaction of the meal delivery order of the food, and obtain the data information of the satisfaction of the meal delivery order of the food.

[0017] Further, the method further comprises:

[0018] H5. Based on the data information of the satisfaction of the meal delivery order of the food, set a preset score. If the satisfaction of the meal delivery order of the food is less than the preset score, the meal delivery order does not meet the requirements, and return to step H2. If the satisfaction of the meal delivery order of the food is greater than the preset score, the meal delivery order meets the requirements and runs normally.

[0019] Further, the user satisfaction evaluation function Q is

[0020]

[0021] where x is the data information of the optimized meal delivery order of the food, f(x) is the characterization value function of the meal delivery order of the food, and α1, α2, and α3 are weight coefficients.

[0022] Furthermore, the constraint conditions for the weight coefficients α1, α2, and α3 are that

[0023]

[0024] The characterization value function f(x) of the serving order of the food is

[0025]

[0026] where x is the data information of the optimized serving order of the food.

[0027] Furthermore, in step H2, the prediction of the serving order of the food by using the improved BP neural network prediction algorithm based on the genetic algorithm includes:

[0028] H21. Input the data information of the historical serving parameters of the unmanned restaurant, the data information of the food type, the data information of the food temperature, and the data information of the food heating duration into the BP neural network model for training and learning, initialize the weights and biases of the model, and obtain the data information of the weights and biases of the initialized model;

[0029] H22. Based on the data information of the weights and biases of the initialized model, initialize the population, determine the population parameters and the maximum number of iterations L, and obtain the data information of the initialized population;

[0030] H23. Based on the data information of the initialized population, establish the fitness function W of the population individuals,

[0031]

[0032] where y i is the parameter value of the i-th population individual of the initialized population, N is the total number of population individuals, N is a positive integer, calculate the fitness values of the population individuals, and obtain the data information of the fitness values of the population individuals;

[0033] H24. Based on the data information of the fitness values of the population individuals, establish the objective optimization function R,

[0034]

[0035] where z is the data information of the fitness values of the population individuals, β1, β2, and β3 are any constant parameters between 0 and 1, optimize the weights and biases of the model, and obtain the data information of the optimized weights and biases of the model.

[0036] Further, the prediction of the food serving order using the improved BP neural network prediction algorithm based on the genetic algorithm further includes:

[0037] H25. Based on the data information of the weights and biases of the optimized model, an optimized BP neural network prediction model is obtained. Inputting the data information of the historical food serving parameters, the data information of the food types, the data information of the food temperatures, and the data information of the food heating durations of the unmanned restaurant, the food serving order is predicted to obtain the data information of the predicted food serving order.

[0038] Further, the constraint function g of the constant parameters β1, β2, and β3 is

[0039]

[0040] where the value range of the constraint function g is (1, 2).

[0041] Further, in step H3, the optimization of the food serving order using the improved goshawk optimization algorithm based on crazy self - adaptation includes:

[0042] H31. Based on the data information of the predicted food serving order, the goshawk population is initialized, the population parameters are determined, and the data information of the initialized goshawk population is obtained;

[0043] H32. Based on the data information of the initialized goshawk population, a fitness function G of the goshawk population individuals is established.

[0044]

[0045] where r is the data information of the initialized goshawk population, and λ1, λ2, and λ3 are penalty factors, and the fitness values of the goshawk population individuals are deduced to obtain the data information of the fitness values of the goshawk population individuals;

[0046] H33. Based on the data information of the fitness values of the goshawk population individuals, an optimization function H of the goshawk population is established.

[0047]

[0048] where q is the data information of the fitness values of the goshawk population individuals, and ω1, ω2, and ω3 are crazy self - adaptation adjustment factors, and the food serving order is optimized to obtain the data information of the optimized food serving order.

[0049] Further, the crazy self - adaptation adjustment factors ω1, ω2, and ω3 are

[0050]

[0051] Among them, q is the data information of the fitness value of the individuals in the goshawk population.

[0052] To achieve the above object and other related objects, the present invention also provides a system for implementing the meal delivery control method applied to a frozen unmanned restaurant described in any one of the above, the system includes:

[0053] A data acquisition module, configured to acquire the data information of the historical meal delivery parameters of the unmanned restaurant, and obtain the data information of the food type, the data information of the food temperature, and the data information of the food heating duration in real time;

[0054] A food meal delivery sequence module, connected to the data acquisition module, configured to predict the meal delivery order of the food by using an improved BP neural network prediction algorithm based on the genetic algorithm, and obtain the data information of the predicted meal delivery order of the food;

[0055] A food meal delivery sequence optimization module, connected to the food meal delivery sequence module, configured to optimize the meal delivery order of the food by using an improved goshawk optimization algorithm based on crazy self - adaptation, and obtain the data information of the optimized meal delivery order of the food;

[0056] A customer satisfaction evaluation module, connected to the food meal delivery sequence optimization module, configured to construct a user satisfaction evaluation function Q to evaluate the satisfaction of the meal delivery order, and obtain the data information of the satisfaction of the meal delivery order.

[0057] The present invention has the following positive effects:

[0058] 1. By using an improved BP neural network prediction algorithm based on the genetic algorithm to predict the meal delivery order of the food, the present invention obtains the data information of the predicted meal delivery order of the food, and combines with an improved goshawk optimization algorithm based on crazy self - adaptation to optimize the meal delivery order of the food, obtaining the data information of the optimized meal delivery order of the food. It can not only analyze the historical data of meal delivery, optimize the meal delivery strategy, improve efficiency and food quality, but also solve the problem of high failure rate in meal delivery under frozen conditions.

[0059] 2. By constructing a user satisfaction evaluation function Q to evaluate the satisfaction of the meal delivery order, the present invention can not only dynamically adjust the meal delivery order in real time according to the customer's reaction state, further improve the meal delivery efficiency of the frozen unmanned restaurant, enhance the user experience, but also adapt to different operation modes. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a schematic flowchart of the method of the present invention;

[0061] Figure 2 It is a schematic flowchart of an improved BP neural network prediction algorithm based on genetic algorithm of the present invention;

[0062] Figure 3 It is a schematic flowchart of an improved goshawk optimization algorithm based on crazy self - adaptation of the present invention;

[0063] Figure 4 It is a schematic diagram of the system framework of the present invention. Specific embodiments

[0064] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to assist in understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, descriptions of well - known functions and structures are omitted below for clarity and conciseness.

[0065] Embodiment 1: As Figure 1 shown, a food delivery control method applied to a frozen unmanned restaurant, the method includes:

[0066] H1. During the food delivery process of the frozen unmanned restaurant, collect data information of the historical food delivery parameters of the unmanned restaurant, and real - time obtain data information of food types, data information of food temperatures, and data information of food heating durations;

[0067] H2. Based on the data information of the historical food delivery parameters of the unmanned restaurant, the data information of food types, the data information of food temperatures, and the data information of food heating durations, use an improved BP neural network prediction algorithm based on genetic algorithm to predict the food delivery order, and obtain data information of the predicted food delivery order;

[0068] H3. Based on the data information of the predicted food delivery order, use an improved goshawk optimization algorithm based on crazy self - adaptation to optimize the food delivery order, and obtain data information of the optimized food delivery order;

[0069] H4. Based on the data information of the optimized food delivery order, construct a user satisfaction evaluation function Q to evaluate the satisfaction of the food delivery order, and obtain data information of the satisfaction of the food delivery order.

[0070] In this embodiment, the method further includes:

[0071] H5. Based on the data information of the satisfaction degree of the food serving order, set a preset score. If the satisfaction degree of the food serving order is less than the preset score, the food serving order does not meet the requirements, and return to step H2. If the satisfaction degree of the food serving order is greater than the preset score, the food serving order meets the requirements and runs normally.

[0072] In this embodiment, in step H2, the prediction of the food serving order by using the improved BP neural network prediction algorithm based on the genetic algorithm includes:

[0073] H21. Input the data information of the historical serving parameters of the unmanned restaurant, the data information of the food type, the data information of the food temperature, and the data information of the food heating duration into the BP neural network model for training and learning, initialize the weights and biases of the model, and obtain the data information of the weights and biases of the initialized model.

[0074] H22. Based on the data information of the weights and biases of the initialized model, initialize the population, determine the population parameters and the maximum number of iterations L, and obtain the data information of the initialized population.

[0075] H23. Based on the data information of the initialized population, establish the fitness function W of the population individuals,

[0076]

[0077] where, y i is the parameter value of the i-th population individual of the initialized population, N is the total number of population individuals, N is a positive integer, calculate the fitness values of the population individuals, and obtain the data information of the fitness values of the population individuals.

[0078] H24. Based on the data information of the fitness values of the population individuals, establish the target optimization function R,

[0079]

[0080] where, z is the data information of the fitness values of the population individuals, β1, β2, and β3 are any constant parameters between 0 and 1, optimize the weights and biases of the model, and obtain the data information of the weights and biases of the optimized model.

[0081] In this embodiment, the main idea of the genetic algorithm is borrowed from the evolutionary theory model under Darwin's natural selection. By drawing on biological evolution, the genetic algorithm simulates the problem to be solved as a biological evolution process. Through operations such as replication, crossover, and mutation, it generates the solutions of the next generation and gradually eliminates the solutions with low fitness function values while increasing the solutions with high fitness function values. After evolving for N generations, it is very likely to evolve an individual with a very high fitness function value, that is, the optimal solution of your objective function value.

[0082] In this embodiment, the step of predicting the food serving order by using the improved BP neural network prediction algorithm based on the genetic algorithm further includes:

[0083] H25. Based on the data information of the weights and biases of the optimized model, an optimized BP neural network prediction model is obtained. By inputting the data information of the historical food serving parameters, the data information of the food types, the data information of the food temperatures, and the data information of the food heating durations of the unmanned restaurant, the food serving order is predicted, and the data information of the predicted food serving order is obtained.

[0084] In this embodiment, the accuracy of the BP neural network prediction model is reflected in the errors of the weights and biases of the model. Therefore, the weights and biases of the model are optimized to improve the prediction accuracy of the model.

[0085] In this embodiment, the constraint function g for the constant parameters β1, β2, and β3 is

[0086]

[0087] where the value range of the constraint function g is (1, 2).

[0088] In this embodiment, further constraints on the constant parameters β1, β2, and β3 ensure that the weights and biases of the model do not deviate from the actual application range, thus ensuring that the serving sequence conforms to the normal serving process.

[0089] In this embodiment, in step H3, the step of optimizing the food serving order by using the improved goshawk optimization algorithm based on crazy self - adaptation includes:

[0090] H31. Based on the data information of the predicted food serving order, the goshawk population is initialized, the population parameters are determined, and the data information of the initialized goshawk population is obtained;

[0091] H32. Based on the data information of the initialized goshawk population, a fitness function G for the individuals of the goshawk population is established.

[0092]

[0093] Among them, r is the data information of the initialized goshawk population, λ1, λ2 and λ3 are penalty factors, and the fitness values ​​of the individuals in the goshawk population are calculated to obtain the data information of the fitness values ​​of the individuals in the goshawk population;

[0094] H33. Based on the data information of the fitness values ​​of the individual goshawk population, an optimization function H of the goshawk population is established.

[0095]

[0096] Among them, q is the data information of the fitness value of the individuals in the goshawk population, ω1, ω2 and ω3 are crazy adaptive adjustment factors, which optimize the order in which the food is served to obtain the data information of the optimized order in which the food is served.

[0097] In this embodiment, the initialized goshawk population is X,

[0098]

[0099] Among them, u j,j is the data information of the characteristic value of the predicted food serving order, and n is the sample size.

[0100] In this embodiment, the crazy adaptive adjustment factors ω1, ω2 and ω3 are,

[0101]

[0102] Among them, q is the data information of the fitness value of the individuals in the goshawk population.

[0103] In this embodiment, in order to verify the effectiveness of Example 1 of the present invention, we conducted a comparative experiment, and the experimental conditions are as follows:

[0104] Control group: In the process of serving food in a traditional frozen food restaurant, 3 different customers ordered food, and the time taken to serve the food was T1.

[0105] Experimental group: In the process of serving food in the method for serving food in a frozen unmanned restaurant proposed in Example 1 of the present application, three different customers ordered the same food as the control group, and the time taken to serve the food was T2. The experimental results show that the time taken by the control group was 10.6 minutes, and the time taken by the experimental group was 6.5 minutes. In addition, the energy consumption of the experimental group was 10% lower than that of the control group.

[0106] The following is a chart showing the experimental data analysis: Table 1: Comparison of the time spent on serving meals

[0107] Group Number of customers ordering meals and food items Food preparation time (min) Control group 3 people, 2 boxes per person 10.6 Experimental group 3 people, 2 boxes per person 6.5

[0108] Table 2: Comparison of energy consumption after a meal

[0109] Group Number of customers ordering meals and food items Energy consumption (kWh) Control group 3 people, 2 boxes per person 0.426 Experimental group 3 people, 2 boxes per person 0.383

[0110] A certain frozen unmanned restaurant processes about 200 orders per day, and the main food types include vegetables, meat, soup, etc. Experiments show that compared with the traditional FCFS strategy, the method of the present invention shortens the average meal delivery time by 30% and improves the user satisfaction by 46%.

[0111] In this embodiment, by adopting an improved BP neural network prediction algorithm based on the genetic algorithm to predict the meal delivery order of food, data information of the predicted meal delivery order of food is obtained, and in combination with an improved goshawk optimization algorithm based on crazy self - adaptation to optimize the meal delivery order of food, data information of the optimized meal delivery order of food is obtained. It can not only analyze the historical data of meal delivery, optimize the meal delivery strategy, improve efficiency and food quality, but also solve the problem of high failure rate in meal delivery under freezing conditions.

[0112] Embodiment 2: On the basis of a meal delivery control method applied to a frozen unmanned restaurant in Embodiment 1, the present invention will be further described and illustrated below.

[0113] As Figure 1 shown, a meal delivery control method applied to a frozen unmanned restaurant, the method includes:

[0114] H1. During the meal delivery process of the frozen unmanned restaurant, collect data information of the historical meal delivery parameters of the unmanned restaurant, and obtain in real - time data information of food types, data information of food temperatures, and data information of food heating durations;

[0115] H2. Based on the data information of the historical meal delivery parameters of the unmanned restaurant, the data information of food types, the data information of food temperatures, and the data information of food heating durations, adopt an improved BP neural network prediction algorithm based on the genetic algorithm to predict the meal delivery order of food, and obtain data information of the predicted meal delivery order of food;

[0116] H3. Based on the data information of the predicted meal delivery order of food, adopt an improved goshawk optimization algorithm based on crazy self - adaptation to optimize the meal delivery order of food, and obtain data information of the optimized meal delivery order of food;

[0117] H4. Based on the data information of the optimized meal delivery order of food, construct a user satisfaction evaluation function Q to evaluate the satisfaction of the meal delivery order of food, and obtain data information of the satisfaction of the meal delivery order of food.

[0118] In this embodiment, the user satisfaction evaluation function Q is

[0119]

[0120] Among them, x is the data information of the serving order of the optimized food, f(x) is the representation value function of the serving order of the food, and α1, α2, and α3 are weight coefficients.

[0121] In this embodiment, the constraint conditions for the weight coefficients α1, α2, and α3 are

[0122]

[0123] The representation value function f(x) of the serving order of the food is

[0124]

[0125] Among them, x is the data information of the serving order of the optimized food.

[0126] In this embodiment, the preset score is set to 9, and the value obtained through the user satisfaction function Q is 8.6. Then, the food serving sequence does not meet the public demand. Therefore, the serving sequence is adjusted in real time to reduce the customer waiting time and improve the customer's dining mood.

[0127] In this embodiment, to verify the effectiveness of Embodiment 1 of the present invention, we set up a refrigerated unmanned restaurant vehicle in an enterprise. 35 employees of the enterprise ordered food, consumed, and evaluated at noon. After implementing this method, the effect is remarkable:

[0128] Table 3 Data comparison table before and after implementation

[0129]

[0130] In this embodiment, as Figure 4 shown, the present invention provides a system for implementing the food serving control method applied to a refrigerated unmanned restaurant according to any one of the above, and the system includes:

[0131] A data acquisition module, configured to collect the data information of the historical food serving parameters of the unmanned restaurant, and to obtain in real time the data information of the food type, the data information of the food temperature, and the data information of the food heating duration;

[0132] A food serving sequence module, connected to the data acquisition module, configured to predict the serving order of the food by using an improved BP neural network prediction algorithm based on a genetic algorithm, and to obtain the data information of the predicted serving order of the food;

[0133] The food serving sequence optimization module, connected to the food serving sequence module, is used to optimize the food serving order by adopting an improved goshawk optimization algorithm based on crazy self - adaptation, and obtain the data information of the optimized food serving order.

[0134] The customer satisfaction evaluation module, connected to the food serving sequence optimization module, is used to construct a user satisfaction evaluation function Q to evaluate the satisfaction of the food serving order and obtain the data information of the satisfaction of the food serving order.

[0135] In this embodiment, the intelligent hardware system

[0136] Sensor integration: Integrate temperature, humidity, and door status sensors in the freezer to monitor the environmental conditions in real - time. The sensor data is used to adjust the serving strategy to ensure that the food is stored and output under optimal conditions.

[0137] Low - temperature cables and low - temperature motors: Use cables and motors made of low - temperature resistant materials to ensure normal operation at low temperatures and prevent hardware failures caused by low temperatures.

[0138] Heating element integration: Integrate micro - heating elements near key hardware components (such as motors, sensors, and circuit boards). Through the heating control program designed on the main board, these heating elements can be automatically activated when the detected temperature is too low to prevent the components from freezing.

[0139] Automatic defrosting function: The program designed on the main board realizes the regular start of the automatic defrosting function. Combined with the internal cold air circulation in the freezer, it clears the frost inside the equipment to prevent the impact of frost on the hardware. Automatic calibration: The system conducts self - checks regularly. After the self - check is completed, it automatically resets and calibrates the sensors to ensure the accuracy of the data and triggers an alarm when an abnormality is detected.

[0140] Dynamic serving algorithm: Temperature and food type adjustment: According to the real - time temperature data and food type, dynamically adjust the serving order and time. For example, give priority to serving products with a long heating time to ensure that the serving time can be shortened when two heating channels are heating simultaneously.

[0141] Machine learning optimization: Use machine learning algorithms to analyze historical data, optimize the serving strategy, and improve efficiency and food quality.

[0142] User - defined options: Allow operators to customize serving parameters according to their needs to adapt to different operation modes

[0143] In this embodiment, it is equipped with a remote management function:

[0144] Real - time monitoring network interface: Through a secure network interface, operators can view the device status in real - time anywhere, including temperature, inventory, and fault information.

[0145] Mobile application support: Provide a device control mini-program to facilitate operators to monitor and manage through mobile phones or tablet devices.

[0146] Remote control device operation: Support remote start, stop, and restart of the device to facilitate quick response to operational requirements. Parameter adjustment: Allow remote adjustment of meal delivery parameters and temperature settings to cope with different operational conditions and user needs.

[0147] Data analysis - Data collection: Automatically collect device operation data, including meal delivery times, fault records, and energy consumption data.

[0148] Report generation: Generate detailed sales reports and performance analysis to help operators optimize inventory and operational strategies.

[0149] Predictive analysis: Use data analysis to predict device maintenance needs and reduce fault downtime.

[0150] In this embodiment, the present invention also provides a computer-readable storage medium, on which a computer program is stored that is programmed or configured to execute the meal delivery control method applied to a frozen unmanned restaurant described in any one of the above.

[0151] Any reference to a memory, storage, database, or other medium used in the embodiments provided by this application may include non-volatile and / or volatile memories. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0152] In summary, the present invention not only solves the problem of high failure rate in meal delivery under frozen conditions, but also further reduces food heating energy consumption, improves the meal delivery efficiency of the frozen unmanned restaurant, and enhances the user experience.

[0153] The above specific embodiments do not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present disclosure shall be included within the protection scope of the present disclosure.

Claims

1. A meal delivery control method applied to a frozen unmanned restaurant, characterized in that, The method includes: H1. During the meal delivery process of the frozen unmanned restaurant, collect the data information of the historical meal delivery parameters of the unmanned restaurant, and obtain the data information of the food type, the data information of the food temperature, and the data information of the food heating duration in real time; H2. Based on the data information of the historical meal delivery parameters of the unmanned restaurant, the data information of the food type, the data information of the food temperature, and the data information of the food heating duration, use an improved BP neural network prediction algorithm based on the genetic algorithm to predict the meal delivery order of the food, and obtain the data information of the predicted meal delivery order of the food; H3. Based on the data information of the predicted meal delivery order of the food, use an improved goshawk optimization algorithm based on crazy self-adaptation to optimize the meal delivery order of the food, and obtain the data information of the optimized meal delivery order of the food; H4. Based on the data information of the optimized meal delivery order of the food, construct a user satisfaction evaluation function Q to evaluate the satisfaction of the meal delivery order of the food, obtain the data information of the satisfaction of the meal delivery order of the food, and set a preset score. If the satisfaction of the meal delivery order of the food is less than the preset score, the meal delivery order does not meet the requirements, and return to step H2. If the satisfaction of the meal delivery order of the food is greater than the preset score, the meal delivery order meets the requirements and runs normally.

2. The meal delivery control method applied to a refrigerated unmanned restaurant according to claim 1, wherein: The user satisfaction evaluation function Q is where x is the data information of the optimized meal delivery order of the food, f(x) is the characterization value function of the meal delivery order of the food, and α1, α2, and α3 are weight coefficients.

3. The meal delivery control method applied to a refrigerated unmanned restaurant according to claim 2, characterized in that: The constraint conditions of the weight coefficients α1, α2, and α3 are 4. The meal delivery control method applied to a frozen unmanned restaurant according to claim 2, wherein: The characterization value function f(x) of the meal delivery order of the food is where x is the data information of the optimized meal delivery order of the food.

5. The meal delivery control method applied to a refrigerated unmanned restaurant according to claim 1, wherein In step H2, the using an improved BP neural network prediction algorithm based on the genetic algorithm to predict the meal delivery order of the food includes: H21. Input the data information of the historical meal delivery parameters of the unmanned restaurant, the data information of the food type, the data information of the food temperature, and the data information of the food heating duration into the BP neural network model for training and learning, initialize the weights and biases of the model, and obtain the data information of the initialized weights and biases of the model; H22. Based on the data information of the initialized weights and biases of the model, initialize the population, determine the population parameters and the maximum number of iterations L, and obtain the data information of the initialized population; H23. Based on the data information of the initialized population, establish a fitness function W for the population individuals where y i is the parameter value of the i-th population individual of the initialized population, N is the total number of population individuals, N is a positive integer, and the fitness value of the population individuals is deduced to obtain the data information of the fitness value of the population individuals; H24. Based on the data information of the fitness values of the population individuals, establish an objective optimization function R where z is the data information of the fitness values of the population individuals, and β1, β2, and β3 are any constant parameters between 0 and 1, optimize the weights and biases of the model, and obtain the data information of the optimized weights and biases of the model.

6. The meal delivery control method applied to a frozen unmanned restaurant according to claim 5, characterized in that, The using an improved BP neural network prediction algorithm based on the genetic algorithm to predict the meal delivery order of the food further includes: Based on the data information of the weights and biases of the optimized model, an optimized BP neural network prediction model is obtained. By inputting the data information of the historical meal delivery parameters of the unmanned restaurant, the data information of the food type, the data information of the food temperature, and the data information of the food heating duration, the meal delivery order of the food is predicted, and the data information of the predicted meal delivery order of the food is obtained.

7. The meal delivery control method applied to a frozen unmanned restaurant according to claim 5, wherein: The constraint function g of the constant parameters β1, β2, and β3 is where the value range of the constraint function g is (1, 2).

8. The meal delivery control method applied to a refrigerated unmanned restaurant according to claim 1, wherein, In step H3, the optimization of the meal delivery order of the food by using the improved goshawk optimization algorithm based on crazy self-adaptation includes: H31. Based on the data information of the predicted meal delivery order of the food, the goshawk population is initialized, the population parameters are determined, and the data information of the initialized goshawk population is obtained; H32. Based on the data information of the initialized goshawk population, a fitness function G of the goshawk population individuals is established. where r is the data information of the initialized goshawk population, and λ1, λ2, and λ3 are penalty factors, and the fitness values of the goshawk population individuals are deduced to obtain the data information of the fitness values of the goshawk population individuals; H33. Based on the data information of the fitness values of the goshawk population individuals, an optimization function H of the goshawk population is established. where q is the data information of the fitness values of the goshawk population individuals, and ω1, ω2, and ω3 are crazy self-adaptation adjustment factors, and the meal delivery order of the food is optimized to obtain the data information of the optimized meal delivery order of the food.

9. The meal delivery control method applied to a refrigerated unmanned restaurant according to claim 8, wherein: The crazy self-adaptation adjustment factors ω1, ω2, and ω3 are where q is the data information of the fitness values of the goshawk population individuals.

10. A system for implementing the meal delivery control method applied to a frozen unmanned restaurant according to any one of claims 1-9, characterized in that, The system includes: A data acquisition module, which is used to collect the data information of the historical meal delivery parameters of the unmanned restaurant, and to obtain the data information of the food type, the data information of the food temperature, and the data information of the food heating duration in real time; A food meal delivery sequence module, which is connected to the data acquisition module, and is used to predict the meal delivery order of the food by using an improved BP neural network prediction algorithm based on the genetic algorithm, and to obtain the data information of the predicted meal delivery order of the food; A food meal delivery sequence optimization module, which is connected to the food meal delivery sequence module, and is used to optimize the meal delivery order of the food by using an improved goshawk optimization algorithm based on crazy self-adaptation, and to obtain the data information of the optimized meal delivery order of the food; A customer satisfaction evaluation module, which is connected to the food meal delivery sequence optimization module, and is used to construct a user satisfaction evaluation function Q, evaluate the satisfaction of the food meal delivery order, obtain the data information of the satisfaction of the food meal delivery order, and set a preset score. If the satisfaction of the food meal delivery order is less than the preset score, the food meal delivery order does not meet the requirements, and return to step H2. If the satisfaction of the food meal delivery order is greater than the preset score, the food meal delivery order meets the requirements and runs normally.

Images