Nutritious food order distribution optimization method and system based on data analysis

By analyzing weather and traffic information in real time, dynamically adjusting nutritional meal delivery strategies, predicting order demand and reasonably allocating resources, the existing distribution model is solved in the face of external changes and the problems of resource waste, and the delivery efficiency and customers are improved Satisfaction achieves cost saving and refined management.

CN118966931AInactive Publication Date: 2024-11-15SHENZHEN XIANYU NUTRITIOUS FOOD CO LTD

Patent Information

Application Number
CN202410991307.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-15
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing nutritional meal delivery model lacks flexibility and adaptability in the face of unpredictable external environment changes, resulting in a decrease in distribution efficiency and customer satisfaction, and unreasonable resource allocation leads to an increase in costs.

Method used

By analyzing weather, transportation and resource allocation information in real time, dynamically adjusting distribution strategies, using data analysis to predict order demand, reasonably allocate distribution resources, building an impact model for order delivery capacity and order meal volume, and generating optimization strategies to ensure efficient delivery.

Benefits of technology

It improves the flexibility and adaptability of the distribution system, reduces resource waste caused by demand fluctuations, ensures distribution efficiency and customer satisfaction, and achieves cost savings and refined management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118966931A_ABST
    Figure CN118966931A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of nutritious food delivery, in particular to a nutritious food order delivery optimization method and system based on data analysis, and aims to effectively predict order demands and reasonably distribute delivery resources by analyzing weather, traffic and resource allocation information in real time and dynamically adjusting delivery strategies. The customer satisfaction is improved while high-efficiency distribution is ensured, and cost saving and fine management are realized; the method comprises the following steps: acquiring weather data information, traffic data information and distribution configuration data information in a target time period; carrying out distribution influence feature extraction on the weather data information, the traffic data information and the distribution configuration data information, merging the extracted distribution influence features, and generating an order distribution influence feature set in a target time period; and inputting the order delivery influence feature set into a pre-constructed order delivery capacity prediction model to obtain the order delivery capacity in the target time period.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of nutritious meal delivery, and in particular to a nutritious meal order delivery optimization method and system based on data analysis. Background Art

[0002] In the current rapidly developing catering delivery industry, nutritious meal order delivery services are increasingly favored by consumers due to their health concept and convenience. However, with the continuous growth of order volume, how to complete the delivery task efficiently and accurately, especially in the face of unpredictable changes in the external environment, has become a major challenge facing nutritious meal delivery companies.

[0003] The existing distribution model often relies on manual experience and static distribution resource allocation, which lacks flexibility and adaptability in dealing with emergencies. For example, bad weather may affect delivery efficiency, traffic congestion may increase delivery time, and unreasonable distribution of distribution resources may lead to service delays or reduced customer satisfaction. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a nutritious meal order delivery optimization method and system based on data analysis, which can realize cost savings and refined management by dynamically adjusting delivery strategies, effectively predicting order demand, and reasonably allocating delivery resources to ensure efficient delivery while improving customer satisfaction.

[0005] In a first aspect, the present invention provides a method for optimizing the delivery of nutritious meal orders based on data analysis, the method comprising:

[0006] Obtain weather data information, traffic data information, and delivery configuration data information within the target time period;

[0007] Extract delivery impact features from weather data, traffic data, and delivery configuration data, and merge the extracted delivery impact features to generate a set of order delivery impact features within the target time period;

[0008] Input the order delivery influencing feature set into the pre-built order delivery capacity prediction model to obtain the order delivery capacity within the target time period;

[0009] Based on historical order data, predict the order volume within the target time period;

[0010] Extracting meal ordering influence features from the weather data information, and inputting the extracted meal ordering influence features into a meal ordering influence evaluation model to obtain a meal ordering quantity influence coefficient; the meal ordering quantity influence coefficient is used to characterize the influence of weather factors on the meal ordering quantity;

[0011] Based on the order quantity impact coefficient, the order quantity within the target time period is corrected to obtain the order correction quantity within the target time period;

[0012] The order delivery capacity is compared with the order correction amount: when the order delivery capacity exceeds the order correction amount, delivery is performed according to the normal delivery process; when the order delivery capacity does not exceed the order correction amount, a nutritious meal order delivery optimization strategy is generated and implemented within the target time period.

[0013] Furthermore, the delivery configuration data information includes the number of delivery personnel and delivery vehicles.

[0014] Furthermore, the order delivery influencing feature set within the target time period is as follows:

[0015]

[0016] Among them, T i is the temperature at the ith time point, H i is the humidity at the i-th time point, W i is the wind speed at the ith time point, P i is the precipitation at the i-th time point, V i is the visibility at the i-th time point, C i is the road congestion at the i-th time point, Z i is the impact of the construction area at the i-th time point, L i is the state of the traffic light at the i-th time point, D i is the number of delivery personnel at the i-th time point, VC i is the state of the delivery vehicle at the i-th time point, DP i is the location of the delivery person at the i-th time point.

[0017] Furthermore, the method for constructing the order delivery capacity prediction model includes:

[0018] Extract and merge delivery impact features. The delivery impact feature set includes all relevant variables, and handles missing values, outliers, and duplicate data of delivery impact features.

[0019] Standardize and normalize the distribution impact characteristics;

[0020] Choose the appropriate machine learning model based on the complexity of the problem and the characteristics of the data;

[0021] Use historical data to train the order delivery capacity prediction model;

[0022] The cross-validation technique is used to evaluate the generalization ability of the order delivery capacity prediction model.

[0023] Furthermore, the mathematical formula of the order delivery capacity prediction model is:

[0024] Dc=w 1 A 1 +w 2 A 2 +…+w m A m

[0025] Where Dc represents the distribution capacity, A 1 ,A 2 …,A m represents the independent variables that affect the delivery capacity. The delivery-related independent variables include temperature, humidity, wind speed, precipitation, visibility, road congestion, construction area impact, traffic light status, number of delivery personnel, delivery vehicle status and delivery personnel location. 1 ,w 2 …,w m A is the independent variable that affects the distribution capacity 1 ,A 2 …,A m The weights of the independent variables affecting the distribution capacity reflect the degree of influence of each variable on the distribution capacity.

[0026] Furthermore, the method for obtaining the order quantity influence coefficient includes:

[0027] Process the collected weather data information, clean the collected weather data, and handle missing values, outliers and duplicate records;

[0028] Standardize or normalize the cleaned weather data;

[0029] Use statistical methods to examine the relationship between weather characteristics and meal ordering;

[0030] Use the feature importance evaluation of the machine learning model to select features that have an impact on the number of orders;

[0031] Choose the right machine learning model;

[0032] Use historical data to train the ordering impact evaluation model, divide the data set into a training set and a test set, use the training set data to adjust the ordering impact evaluation model parameters, and use the test set to test the ordering impact evaluation model;

[0033] Select evaluation metrics to assess the predictive power of the ordering impact evaluation model;

[0034] Use the ordering impact evaluation model, input the ordering impact characteristics, and output the order quantity impact coefficient.

[0035] Furthermore, the mathematical formula used in the meal ordering impact evaluation model is expressed as:

[0036] O=Oq 1 W 1 +Oq 2 W 2 +…+Oq n W n

[0037] Among them, O represents the order quantity, Wc 1 , Wc 2 , …, Wc n Indicates different weather characteristics, Oq 1 ,Oq 2 , ..., Oq n Represents the order quantity impact coefficient.

[0038] On the other hand, the present application also provides a nutritious meal order delivery optimization system based on data analysis, the system comprising:

[0039] The data collection module is used to collect weather data information, traffic data information and delivery configuration data information within the target time period, including the number of delivery personnel and the status of delivery vehicles;

[0040] The feature integration module is used to analyze the collected weather data, traffic data and delivery configuration data, extract and integrate the delivery impact features to form an order delivery impact feature set;

[0041] The delivery capacity prediction module is used to input the order delivery influencing feature set into the order delivery capacity prediction model, and the output order delivery capacity is used to predict the upper limit of the delivery capacity within the target time period;

[0042] The order volume forecasting module is used to forecast the expected order volume within the target time period based on historical order data using time series analysis;

[0043] The ordering impact assessment module is used to analyze the impact of weather data information on ordering behavior and extract ordering impact features; the ordering impact assessment model is used to calculate the ordering volume impact coefficient to reflect the specific impact of weather factors on ordering volume;

[0044] An order correction module is used to adjust the predicted order quantity based on the order quantity influence coefficient to obtain the order correction quantity within the target time period;

[0045] The delivery decision module is used to compare the order delivery capacity with the order correction amount and adjust the delivery strategy according to the comparison results;

[0046] The delivery implementation module is used to formulate the optimization strategy for the delivery of nutritious meal orders when the delivery capacity is lower than the order correction amount.

[0047] In a third aspect, the present application provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above methods.

[0048] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in any one of the above-mentioned methods when executed by a processor.

[0049] Compared with the prior art, the invention has the following beneficial effects: by collecting and analyzing weather, traffic and distribution resource configuration data in real time, the distribution strategy can be adjusted in time to facilitate response to emergencies and improve the flexibility and adaptability of the distribution system; by using historical order data to predict future order volumes and combining weather data to evaluate the impact on meal orders, it is convenient to accurately predict actual order demand and reduce the waste of distribution resources caused by demand fluctuations; by comprehensively evaluating the distribution impact characteristics, it is convenient to allocate delivery personnel and transportation tools, avoid excessive concentration or dispersion of resources, and ensure maximum distribution efficiency under limited distribution resources; by predicting and optimizing the distribution process in advance, it can reduce customer dissatisfaction caused by distribution delays , while ensuring that the quality of nutritious meals is not affected, improving customer satisfaction and loyalty; reducing unnecessary distribution costs through effective resource allocation and order forecasting, reducing cost expenditures, and realizing refined cost management; by providing distribution managers with data-driven decision-making basis, making the decision-making process more objective and scientific, and reducing the uncertainty caused by relying on personal experience and intuition; in summary, through the nutritious meal order distribution optimization method based on data analysis, through real-time analysis of weather, traffic and resource allocation information, dynamically adjusting the distribution strategy, effectively predicting order demand, and reasonably allocating distribution resources, ensuring efficient distribution while improving customer satisfaction, achieving cost savings and refined management. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 is a flow chart of the present invention;

[0051] Figure 2 is a flow chart of a method for obtaining a meal order quantity influence coefficient according to the present invention;

[0052] Figure 3 This is the structural diagram of the nutritious meal order delivery optimization system based on data analysis. DETAILED DESCRIPTION

[0053] In the description of the present application, those skilled in the art should know that the present application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, the present application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, the present application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0054] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0055] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.

[0056] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0057] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0058] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0059] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0060] The present application is described below in conjunction with the drawings in the present application.

[0061] Embodiment 1: Figure 1 to Figure 2 As shown, the method for optimizing the delivery of nutritious meal orders based on data analysis of the present invention specifically comprises the following steps:

[0062] S1. Obtain weather data information, traffic data information, and delivery configuration data information within a target time period;

[0063] Step S1 is to obtain weather data information, traffic data information and delivery configuration data information within the target time period, specifically including:

[0064] Weather data information acquisition:

[0065] Data source: Integrate APIs of multiple authoritative meteorological data providers, such as the National Meteorological Information Center, Yunyao Aerospace, Mojichibi and AccuWeather, to ensure the accuracy and comprehensiveness of data;

[0066] Key indicators: temperature, humidity, wind speed, wind direction, precipitation, snowfall, visibility and UV index, etc.; also pay attention to weather conditions that affect delivery speed and safety;

[0067] Update frequency: Due to the uncertainty of weather changes, data needs to be updated in real time or at a higher frequency to reflect the latest weather conditions;

[0068] Traffic data information acquisition:

[0069] Source channels: intelligent transportation systems, GPS tracking services, map service providers, etc.

[0070] Data types: including road congestion, accident reports, construction zones, traffic light status, and public transportation schedules;

[0071] Update frequency: real-time or near real-time data flow is required to quickly respond to changes in traffic conditions;

[0072] Delivery configuration data information acquisition:

[0073] Information on the number of couriers: By integrating the enterprise resource planning system or dedicated logistics management software, the number of couriers currently on duty, their work status, work ability and historical performance data can be extracted; the personal information of couriers, including work schedules, skill certifications, health status assessments and acceptable working environment conditions, can be obtained from the human resources management system; GPS positioning technology can be used to collect real-time location information from the couriers’ mobile devices to understand the current location of each couriers, so as to facilitate dynamic adjustment of the delivery plan;

[0074] Acquisition of delivery vehicle information: Integrate fleet management software to obtain the real-time status of the delivery personnel's vehicles, including the type of vehicle or bicycle, license plate number, current load, fuel or power status, maintenance records and insurance validity; analyze historical performance data of each vehicle, such as average speed, load capacity, failure rate and repair cost, to ensure the selection of the most appropriate vehicle for delivery; confirm the compatibility of the vehicle with the delivery task, such as refrigerated trucks for cold meal delivery, electric vehicles or bicycles for short-distance urban delivery, to reduce energy consumption and carbon emissions; ensure that all vehicles comply with local traffic regulations and food safety standards, and regularly check the cleanliness and sanitary conditions of the vehicles;

[0075] By integrating APIs from multiple authoritative meteorological data providers, it is possible to cross-verify information and improve data accuracy and coverage. High-frequency data updates ensure the real-time nature of information, enabling decision makers to respond to sudden weather changes and adjust delivery strategies in a timely manner. Paying attention to weather indicators that have a direct impact on delivery, such as precipitation and wind speed, helps prevent risks brought by bad weather in advance. Through intelligent transportation systems and map service providers, real-time traffic conditions, including congestion, accidents and construction information, are obtained to facilitate flexible adjustment of delivery routes. Combined with the status of traffic lights and public transportation timetables, delivery plans can be arranged more accurately to avoid delivery waiting and delays. The real-time data streams obtained facilitate the system to quickly respond to changes in traffic conditions and reduce delivery delays caused by unknown traffic events. Through human resource management systems and logistics management software, it is easy to allocate delivery personnel resources to ensure sufficient manpower and reasonable allocation. By obtaining the personal information of delivery personnel and the performance and applicability of transportation tools, it is easy to achieve personalized and efficient delivery services. By obtaining real-time, accurate and comprehensive information, it helps delivery companies make more accurate decisions, improve delivery efficiency, reduce delivery costs, and ensure service quality and delivery safety. Through intelligent and automated means, human errors can be reduced and the overall operation level can be improved.

[0076] S2, extracting delivery impact features from weather data information, traffic data information, and delivery configuration data information, and merging the extracted delivery impact features to generate a set of order delivery impact features within a target time period;

[0077] In step S2, in order to generate a set of order delivery impact features within the target time period, it is first necessary to prepare weather data information, traffic data information, and delivery configuration data information within the target time period, and extract and merge the above delivery impact features, including:

[0078] Delivery impact feature extraction:

[0079] a. Weather data feature extraction:

[0080] Temperature and humidity: Extreme temperatures or high humidity can affect the efficiency of delivery personnel. For example, high temperatures can reduce the efficiency of physical labor.

[0081] Wind speed: Strong winds affect the stability of vehicles. For example, it is not easy to ride a bicycle or motorcycle for delivery in strong winds.

[0082] Precipitation: Precipitation will slow down delivery and increase delivery difficulty. For example, in the case of heavy precipitation and heavy snowfall, the roads are slippery and transportation is inconvenient, which increases delivery difficulty.

[0083] Visibility: Low visibility increases the risk of traffic accidents and affects delivery safety;

[0084] b. Traffic data information characteristics

[0085] Road congestion: Identify frequently congested roads and predict delivery delays;

[0086] Construction Zones: Construction zones require detours and allow extra time;

[0087] Traffic light status: Frequent red and green traffic lights will interrupt the delivery person’s schedule and increase delivery time;

[0088] c. Distribution configuration data information characteristics:

[0089] The number of delivery personnel and their working status: including working hours, fatigue level and health status;

[0090] Delivery vehicle status: maintenance status of the vehicle or bicycle, endurance level, suitability for current weather conditions;

[0091] Delivery personnel location: Real-time location information facilitates dynamic adjustment of delivery routes;

[0092] After the above delivery impact features are extracted, the original data is preprocessed. The preprocessing method is as follows:

[0093] First, load the extracted delivery impact feature data, which comes from different data sources, such as historical order data, weather forecasts, holiday information, and traffic flow data. To ensure the integrity and consistency of the data, check whether there are missing values ​​or outliers.

[0094] Preprocess the distribution impact feature data. For missing data, use interpolation strategies or machine learning models to predict missing values. Use statistical methods to identify and process outliers that affect distribution. Convert data types to ensure that all features are of the correct data type.

[0095] For non-numeric features, convert them into numeric types to facilitate subsequent algorithm processing; for example, convert them into numeric types through one-hot encoding, label encoding, or embedded encoding;

[0096] Scaling the numerical delivery impact features, so that features of different scales have the same weight in the order delivery capacity prediction model; Commonly used scaling techniques include minimum and maximum scaling and standard scaling;

[0097] Use statistical tests or machine learning algorithms to select the most predictive features. Methods such as correlation coefficient, mutual information, recursive feature elimination, and feature importance based on tree models can be used.

[0098] Use Pandas dataframe to merge all preprocessed features into one dataset, so that all delivery impact features correspond to the same time point or time period;

[0099] The pre-processed weather data information, traffic data information and delivery configuration data information are subjected to delivery impact feature extraction and merged to generate an order delivery impact feature set within the target time period. The order delivery impact feature set within the target time period is as follows:

[0100]

[0101] Among them, T i is the temperature at the ith time point, H i is the humidity at the i-th time point, W i is the wind speed at the ith time point, P i is the precipitation at the i-th time point, V i is the visibility at the i-th time point, C i is the road congestion at the i-th time point, Z i is the impact of the construction area at the i-th time point, L i is the state of the traffic light at the i-th time point, D i is the number of delivery personnel at the i-th time point, VC iis the state of the delivery vehicle at the i-th time point, DP i is the location of the delivery person at the i-th time point;

[0102] By comprehensively considering weather data, traffic data, and delivery configuration data, it is easy to extract a variety of features that comprehensively affect order delivery; delivery influencing features cover multiple aspects from external environment to internal configuration, which makes it easy to comprehensively consider various influencing factors when building a prediction model; through feature extraction and preprocessing, the accuracy and consistency of the data are ensured; the processing of missing values ​​and outliers can reduce data noise and improve the prediction accuracy of the prediction model; converting non-numeric features to numerical types and scaling numerical features ensures that the prediction model has the same weight when processing features of different scales, thereby improving the accuracy of the prediction; using data processing tools such as Pandas, data can be loaded, processed, and merged efficiently; through statistical tests or machine The learning algorithm selects the most predictive features, which makes it easy to flexibly adjust the feature set according to actual conditions; it is easy to remove redundant features, reduce the amount of calculation, and improve the prediction performance; the extracted features have clear physical meanings, such as temperature, humidity and wind speed, making the results of the order delivery capacity prediction model easier to understand and explain; by obtaining weather, traffic and delivery configuration data in real time, it is easy to dynamically update the order delivery impact feature set; at the same time, it can also promptly reflect changes in actual conditions, improving the real-time and accuracy of the prediction model; the order delivery impact feature set generated by the above method within the target time period has the advantages of comprehensiveness, accuracy, efficiency, flexibility, interpretability and dynamism, which is convenient for providing data support for subsequent order delivery capacity prediction.

[0103] S3, inputting the order delivery influencing feature set into a pre-built order delivery capacity prediction model to obtain the order delivery capacity within the target time period;

[0104] In step S3, the nutritious meal order delivery optimization method based on data analysis inputs the previously generated order delivery influencing feature set within the target time period into the pre-built order delivery capacity prediction model; specifically, the order delivery capacity prediction model used is intended to estimate the maximum carrying capacity of the delivery system under specific conditions; the order delivery capacity prediction model is based on machine learning or deep learning technology, and its core lies in considering various influencing factors to quantify delivery efficiency and capacity;

[0105] The construction process of the order delivery capacity prediction model is as follows:

[0106] Data preparation: In step S2, the delivery-influencing features have been extracted and merged. The delivery-influencing feature set includes all relevant variables, such as weather conditions, traffic conditions, and delivery resources. Missing values, outliers, and duplicate data are processed to ensure data quality.

[0107] Feature engineering: normalize and standardize delivery-influencing features to ensure they can be effectively used in the order delivery capacity prediction model;

[0108] Model selection: Choose an appropriate machine learning model based on the complexity of the problem and the characteristics of the data; choices include but are not limited to linear regression, decision tree, random forest, support vector machine, or neural network; in the delivery capacity forecasting scenario, prefer models that can handle multivariate inputs and complex relationships;

[0109] Training model: Use historical data to train the order delivery capacity prediction model, where the historical data contains past delivery impact characteristics and actual delivery capacity; the purpose is to find the best combination of order delivery capacity prediction model parameters to minimize the prediction error;

[0110] Model evaluation and tuning: Use cross-validation technology to evaluate the generalization ability of the order delivery capacity prediction model; adjust the hyperparameters of the order delivery capacity prediction model through grid search or random search to find the optimal configuration;

[0111] Prediction execution: The order delivery influencing feature set generated in step S2 within the target time period is used as the input of the order delivery capacity prediction model; the order delivery capacity prediction model will output the predicted delivery capacity, that is, the number of orders that the delivery system can effectively handle within the target time period taking into account all influencing factors;

[0112] Result interpretation and feedback: Analyze the gap between the forecast results and the actual delivery capacity, and understand which factors lead to forecast deviations; regularly update and optimize the order delivery capacity forecast model based on actual performance and business needs to improve forecast accuracy and practicality;

[0113] The mathematical formula of the order delivery capacity prediction model is:

[0114] Dc=w 1 A 1 +w 2 A 2 +…+w m A m

[0115] Where Dc represents the distribution capacity, A 1 ,A 2 …,A m represents the independent variables that affect the delivery capacity. The delivery-related independent variables include temperature, humidity, wind speed, precipitation, visibility, road congestion, construction area impact, traffic light status, number of delivery personnel, delivery vehicle status and delivery personnel location. 1 ,w 2 …,w mA is the independent variable that affects the distribution capacity 1 ,A 2 …,A m The weights of the independent variables affecting the distribution capacity reflect the degree of influence of each variable on the distribution capacity;

[0116] The order delivery capacity prediction model can simultaneously consider multiple delivery influencing characteristics, such as weather conditions, traffic conditions and delivery resources, so as to capture the complex interactions between the above variables and improve the accuracy of delivery capacity prediction; the deep learning model is used to identify and model the potential nonlinear relationship between variables; through continuous data collection and model order delivery capacity prediction model retraining, the prediction accuracy can be continuously improved over time and with changes in market conditions; the delivery system can respond flexibly to environmental changes; the order delivery capacity prediction model learns to identify abnormal patterns during the training process, so as to plan and adjust delivery strategies in advance and reduce the negative impact of uncertainty; delivery capacity prediction helps to reasonably allocate delivery resources, reduce over-allocation or under-allocation of resources, and improve overall operational efficiency and cost-effectiveness; the order delivery capacity prediction model is trained and deployed, the prediction process is automated, reducing the need for manual intervention and improving the efficiency and controllability of large-scale delivery operations; through the application of the order delivery capacity prediction model, the accuracy of delivery prediction is improved, and the flexibility and efficiency of delivery operations are enhanced.

[0117] S4. Based on historical order data, predict the order volume within the target time period;

[0118] In step S4, the order volume within the target time period is predicted based on historical order data, which is a key link in the entire nutritious meal order delivery optimization method; and the past data is used to predict the number of orders in a specific time period in the future; the steps are as follows:

[0119] S41. Collect historical order data, including daily order volume, order time distribution, and order patterns on special dates. The above data needs to be obtained from the company's internal database, third-party delivery platform or other data sources;

[0120] S42. Clean the collected historical order data to remove duplicate, erroneous and abnormal data; and pre-process the data, such as data standardization and normalization, to facilitate subsequent analysis and modeling;

[0121] S43. Extract features related to order volume, such as date, time, and promotions; and consider external data, such as competitor activities, social media trends, and other factors that affect order volume;

[0122] S44. Select an appropriate forecasting model, such as time series analysis, regression analysis, machine learning model, or deep learning model; train the model to predict future orders based on historical order data and extracted features;

[0123] S45. Evaluate the constructed prediction model. Common evaluation indicators include accuracy, recall rate, and F1 value. If the prediction model performance is poor, improve the prediction accuracy by adjusting the prediction model parameters, optimizing feature selection, or trying other models.

[0124] S46, using the evaluated and optimized forecasting model, inputting relevant features of the target time period, and obtaining the order volume forecast result within the time period;

[0125] S47, outputting the prediction results and combining them with other steps to formulate and optimize the nutritious meal order delivery strategy;

[0126] Relying on big data analysis and machine learning technology, order forecasting can be made more accurate and scientific, reducing the uncertainty of human decision-making and ensuring the rational allocation of resources. Secondly, by mining historical data, the law of how order volume is affected by various internal and external factors such as time and date can be identified, and refined forecasting of order volume can be achieved, providing a basis for the dynamic adjustment of distribution resources. The implementation of data cleaning and feature engineering eliminates the interference of outliers and improves the accuracy of the prediction model. Through the evaluation and optimization mechanism, the prediction model is ensured to be continuously iterated and upgraded with the development of the business to adapt to the ever-changing market environment. The prediction method in step S4 brings more scientific and efficient order management and distribution optimization to nutrition meal distribution companies, reduces the operating costs of distribution companies, and improves operational efficiency and customer service levels.

[0127] S5, extracting meal ordering influence features from the weather data information, and inputting the extracted meal ordering influence features into a meal ordering influence evaluation model to obtain a meal ordering quantity influence coefficient; the meal ordering quantity influence coefficient is used to characterize the influence of weather factors on meal ordering quantity;

[0128] Step S5 is described in detail as follows:

[0129] First, extract the features that affect meal ordering from weather data, including:

[0130] Temperature and humidity: Extreme temperatures or high humidity can affect people’s appetite and thus affect meal orders; for example, hot weather can increase demand for cool drinks and light meals, while cold weather can boost orders for hot and high-calorie foods.

[0131] Wind speed: Strong winds reduce outdoor activities, prompting people to stay indoors and increase food orders;

[0132] Precipitation: Precipitation can limit people’s mobility, making takeout orders a more popular option, especially in heavy precipitation or snowfall;

[0133] Visibility: Low visibility reduces people’s willingness to travel and also increases the demand for ordering food;

[0134] Then, the ordering impact features are input into the ordering impact evaluation model to obtain the ordering quantity impact coefficient as follows:

[0135] First, the collected weather data information is processed, the collected weather data is cleaned, and missing values, outliers and duplicate records are processed; and the collected weather data is standardized or normalized so that the collected weather data can be compared on the same scale;

[0136] Use statistical methods, such as Pearson’s correlation coefficient or Spearman’s rank correlation coefficient, to examine the relationship between weather features and order volume; and use feature importance assessment of machine learning models to select features that have an impact on order volume;

[0137] Choose the appropriate model type based on the characteristics of the problem; for example, linear regression, decision tree, random forest, support vector machine, neural network, etc.

[0138] Use historical data to train the ordering impact evaluation model, divide the data set into a training set and a test set, use the training set data to adjust the ordering impact evaluation model parameters, and use cross-validation and other techniques to prevent overfitting; use the test set to test the ordering impact evaluation model to improve the performance of the ordering impact evaluation model;

[0139] Select appropriate evaluation indicators, such as mean square error, root mean square error, and mean absolute error, to evaluate the predictive ability of the ordering influence evaluation model;

[0140] Use the trained ordering impact evaluation model, input the ordering impact features, and output the order quantity impact coefficient;

[0141] The mathematical formula used in the meal ordering impact evaluation model is expressed as:

[0142] O=Oq 1 W 1 +Oq 2 W 2 +…+Oq n W n

[0143] Among them, O represents the order quantity, Wc 1 , Wc 2 , …, Wc n Indicates different weather characteristics, Oq 1 ,Oq 2, ..., Oq n Indicates the order quantity impact coefficient;

[0144] Through comprehensive analysis, the impact of multiple weather parameters on ordering behavior is considered, which is more comprehensive and accurate than considering only a single factor. By cleaning data, processing missing values, outliers and duplicate records, the quality of data is ensured, and the stability and reliability of the ordering impact evaluation model are improved. Statistical methods and feature importance evaluation in machine learning are used to effectively identify weather characteristics that have a significant impact on the order volume, reduce the complexity of the ordering impact evaluation model, and improve the computational efficiency of the ordering impact evaluation model. Historical data is used for training and verification, which facilitates the ordering impact evaluation model to capture temporal trends and patterns and improve prediction accuracy. Cross-validation technology is used to reduce the fitting of the ordering impact evaluation model and improve the generalization ability of the ordering impact evaluation model on unknown data. Multiple evaluation indicators are used to measure the prediction performance of the model, providing multi-angle effect feedback, which is convenient for the continuous optimization of the ordering impact evaluation model. Through sophisticated weather data analysis and the construction of the ordering impact evaluation model, a precise, flexible and adaptable solution is provided for the optimization of nutritious meal delivery, which can cope with the impact of external environmental changes on the order volume and improve the stability and efficiency of delivery services.

[0145] S6. Based on the order quantity influence coefficient, the order quantity within the target time period is corrected to obtain the order correction quantity within the target time period;

[0146] By extracting the ordering influence features from weather data information and inputting the ordering influence features into the ordering influence evaluation model, the ordering volume influence coefficient is obtained; the ordering volume influence coefficient reflects the direct impact of weather conditions on consumers' willingness to order.

[0147] Analyze historical order data to understand the order volume trends under similar weather conditions; and facilitate the prediction of order volume under current weather conditions;

[0148] Based on the historical order data and the order volume impact coefficient, the original order volume within the target time period is corrected; the specific correction methods include:

[0149] Direct correction method: directly apply the order quantity impact factor to the original order quantity to get the corrected order quantity; for example, if the order quantity impact factor is 1.2, the original order quantity will be multiplied by 1.2 to get the corrected order quantity;

[0150] Regression model correction method: Use statistical methods such as regression analysis to establish a mathematical relationship model between weather factors and order volume, predict the order volume within the target time period through the mathematical relationship model, and make corrections based on the order volume influence coefficient;

[0151] Machine learning model correction method: Use machine learning algorithms to train a model to predict order volume, take order-influencing features as input, and output the corrected order volume;

[0152] The calculation formula for order correction is:

[0153] Ocq′=Ocq×Qn

[0154] Among them, Ocq′ represents the order correction quantity in the target time period, Ocq represents the original order quantity in the target time period predicted based on historical order data, and Qn represents the order quantity impact coefficient;

[0155] When Qn>1, it is expected to increase due to weather factors, so Ocq′ will be greater than the original predicted order volume Ocq. When Ocq=1, weather factors have no effect on the order volume, so Ocq′ will be equal to Ocq. When Qn<1, it means that weather factors will cause the order volume to decrease, so Ocq′ will be less than Ocq.

[0156] In the process of correcting the order volume, other factors that affect the order volume are taken into account. The above factors are quantified through similar data analysis methods and integrated into the process of correcting the order volume;

[0157] Finally, verify and adjust the revised order quantity; check whether the revised order quantity is reasonable by comparing it with the actual order quantity or simulating the delivery process; if it is found that there is a large deviation between the revised order quantity and the actual situation, it is necessary to readjust the order quantity influence coefficient or other related parameters until a satisfactory correction result is obtained;

[0158] Through real-time analysis and processing of weather data, the order volume impact coefficient is calculated, and the order volume is corrected in real time accordingly; ensure that the prediction and correction of order volume are consistent with the current weather conditions to improve the accuracy of the prediction; flexibly adapt to the changes in order volume under different weather conditions; whether it is high temperature, rainfall or other extreme weather, the order volume impact coefficient is calculated through the order volume impact evaluation model to provide a data basis for the correction of order volume; provide a variety of correction methods, including direct correction method, regression model correction method and machine learning model correction method. The above methods are selected according to actual conditions and needs to improve the flexibility and accuracy of correction; in the process of correcting the order volume, consider the impact of weather factors and other factors affecting the order volume; quantify through data analysis methods , integrate weather factors into the order quantity correction process to make the correction result more comprehensive and accurate; verify and adjust the corrected order quantity to ensure the rationality and reliability of the correction result; check whether the corrected order quantity is reasonable by comparing it with the actual order quantity or simulating the delivery process, and readjust the relevant parameters when deviations are found until the correct correction result is obtained; based on the corrected order quantity, the company reasonably allocates distribution resources and personnel to avoid resource waste and delivery delays; improves delivery efficiency and service quality, and enhances customer satisfaction; based on the order correction method of the order quantity influence coefficient, through data-driven prediction and dynamic adjustment, realizes the optimal allocation of distribution resources, improves the efficiency of distribution services and customer satisfaction, and provides data support for nutrition order delivery.

[0159] S7, comparing the order delivery capacity with the order correction amount: when the order delivery capacity exceeds the order correction amount, delivering according to the normal delivery process; when the order delivery capacity does not exceed the order correction amount, generating a nutritious meal order delivery optimization strategy and implementing it within the target time period;

[0160] Step S7 is specifically implemented as follows:

[0161] Compare the order delivery capacity obtained through the order delivery capacity prediction model with the order correction amount corrected by weather factors;

[0162] When the order delivery capacity exceeds the order correction amount, it means that the current delivery resources are sufficient to meet the order demand. At this time, delivery is carried out according to the established normal delivery process, and no additional optimization strategy adjustment is required.

[0163] When the order delivery capacity does not exceed the order correction amount, it indicates that the current delivery resources are insufficient to meet the needs of all orders. At this time, it is necessary to generate a nutritious meal order delivery optimization strategy to maximize the use of existing resources while ensuring that the orders can be delivered on time and efficiently. The delivery optimization strategy includes:

[0164] Increase delivery resources: Increase delivery personnel and transportation tools, temporarily hire additional delivery personnel or add delivery vehicles to improve delivery capacity; adjust the work shifts of delivery personnel, extend working hours or add shifts to ensure that there are enough people to deliver orders during peak hours;

[0165] Optimize delivery route planning: Use route optimization algorithms and real-time traffic conditions to plan the shortest or fastest delivery routes to reduce unnecessary driving distance and time; analyze order distribution, prioritize delivery to high-density areas, and reduce empty mileage;

[0166] Dynamically adjust the delivery area: Dynamically adjust the delivery area according to the geographical distribution of order volume, concentrate resources in the order-intensive areas, and improve delivery efficiency; implement a zoned delivery strategy, divide the city into multiple delivery areas, each area is managed by a group of delivery personnel, and reduce the inefficiency of cross-regional delivery;

[0167] Prepare and pre-process orders in advance: For known large orders, start preparing meals in advance to ensure that they can be quickly packaged and shipped within the delivery time window; sort and package orders in advance, such as packaging orders on the same route together to reduce on-site sorting time;

[0168] Customer communication and expectation management: Notify customers of delivery delays and provide updated estimated delivery times through mobile apps or text messages to manage customer expectations; provide self-service options such as contactless delivery or self-collection to reduce delivery personnel’s waiting time;

[0169] Utilize technology assistance: Introduce automated technologies, such as drones or automatic delivery vehicles, to assist in delivery in suitable areas and scenarios; use big data and artificial intelligence to predict future demand patterns and plan resources in advance;

[0170] Continuous monitoring and adjustment: During the entire delivery process, we continuously monitor the delivery progress and resource utilization, and dynamically adjust the strategy according to the actual situation to deal with emergencies;

[0171] Implement the generated distribution optimization strategy within the target time period; ensure the effectiveness and feasibility of the strategy through real-time monitoring and adjustment;

[0172] After the delivery optimization strategy is implemented, the delivery effect is evaluated; by comparing the actual delivery data with the expected target, the effectiveness of the delivery optimization strategy is analyzed, and customer feedback and opinions are collected; based on the evaluation results, the delivery optimization strategy is iterated and optimized to improve delivery efficiency and service quality;

[0173] When the order delivery capacity exceeds the correction amount, it can quickly identify and continue to deliver according to the normal process, reducing unnecessary resource adjustments; when the delivery resources are insufficient, it can automatically generate optimization strategies and flexibly adjust the delivery plan according to real-time data to adapt to changes in the external environment; through dynamic allocation of delivery resources and optimization of delivery routes, resource utilization can be maximized and delivery costs can be reduced; preparing and pre-processing orders in advance can reduce on-site sorting time and improve delivery efficiency; by optimizing delivery routes and dynamically adjusting delivery areas, delivery time can be reduced and customer satisfaction can be improved; customer communication and expectation management can reduce dissatisfaction caused by delivery delays and provide a better customer experience; using automation technology and big data prediction to The company can further improve the efficiency and accuracy of delivery; introduce advanced technologies such as drones or automatic delivery vehicles to solve problems in traditional delivery; continuous monitoring and evaluation of delivery results can detect problems in a timely manner, and iterate and optimize delivery optimization strategies to ensure continuous improvement in delivery efficiency and service quality; customer feedback and opinions can provide important reference for delivery optimization, helping companies to continuously improve and perfect delivery services; through real-time monitoring and dynamic adjustment, it can detect and respond to emergencies in a timely manner and reduce the impact of risks on delivery; through the comprehensive application of data analysis, optimization algorithms and real-time adjustment, it provides a flexible, efficient and sustainable solution for the delivery of nutritious meal orders, improves delivery efficiency, reduces costs and enhances customer experience.

[0174] Embodiment 2: Figure 3 As shown, the nutritious meal order delivery optimization system based on data analysis of the present invention specifically includes the following modules:

[0175] The data collection module is used to collect weather data information, traffic data information and delivery configuration data information within the target time period, including the number of delivery personnel and the status of delivery vehicles;

[0176] The feature integration module is used to analyze the collected weather data, traffic data and delivery configuration data to extract delivery impact features; integrate the delivery impact features to form an order delivery impact feature set;

[0177] The delivery capacity prediction module is used to input the order delivery influencing feature set into the pre-trained order delivery capacity prediction model to predict the upper limit of the delivery capacity within the target time period;

[0178] An order volume forecasting module is used to forecast the expected order volume within a target time period based on historical order data using time series analysis or other forecasting techniques;

[0179] The ordering impact assessment module is used to analyze the impact of weather data information on ordering behavior and extract ordering impact features; the ordering impact assessment model is used to calculate the ordering volume impact coefficient to reflect the specific impact of weather factors on ordering volume;

[0180] The order correction module is used to adjust the predicted order quantity based on the order quantity impact coefficient to obtain a more accurate order correction quantity within the target time period;

[0181] The delivery decision module is used to compare the order delivery capacity with the order correction amount to determine whether the delivery strategy needs to be adjusted;

[0182] The delivery implementation module is used when the delivery capacity is lower than the order correction amount. The delivery implementation module is responsible for formulating optimization strategies for the delivery of nutritious meal orders, such as increasing delivery personnel, adjusting route planning, etc., to ensure that the above strategies are implemented within the target time period.

[0183] By collecting and analyzing weather, traffic and distribution resource allocation data in real time, it is possible to make predictions and decisions based on objective data, reduce reliance on manual experience, and improve the accuracy and reliability of decisions; the distribution capacity prediction module and the order quantity prediction module can predict distribution capacity and order demand in advance, allowing distribution companies to plan resources in advance and reduce inefficient distribution or customer dissatisfaction caused by excessive or insufficient resources; the order impact assessment module focuses on the impact of weather on ordering behavior, facilitating a more accurate prediction of order volume, so that when weather conditions change significantly, strategies can be adjusted in time to cope with order fluctuations; the distribution decision module and the distribution implementation module trigger distribution strategy adjustments when potential distribution bottlenecks are predicted; reduce customer dissatisfaction caused by delivery delays through more accurate order predictions and resource allocation; in summary, the system can improve delivery punctuality and customer experience; reasonable distribution strategies and resource allocation reduce unnecessary expenses, achieve effective cost control, and bring competitive advantages to distribution companies.

[0184] The various variations and specific embodiments of the nutritious meal order delivery optimization method based on data analysis in the aforementioned embodiment 1 are also applicable to the nutritious meal order delivery optimization system based on data analysis in the present embodiment. Through the aforementioned detailed description of the nutritious meal order delivery optimization method based on data analysis, those skilled in the art can clearly understand the implementation method of the nutritious meal order delivery optimization system based on data analysis in the present embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0185] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0186] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for optimizing the delivery of nutritious meal orders based on data analysis, characterized in that: The method comprises: Obtain weather data information, traffic data information, and delivery configuration data information within the target time period; Extract delivery impact features from weather data, traffic data, and delivery configuration data, and merge the extracted delivery impact features to generate a set of order delivery impact features within the target time period; Input the order delivery influencing feature set into the pre-built order delivery capacity prediction model to obtain the order delivery capacity within the target time period; Based on historical order data, predict the order volume within the target time period; Extracting meal ordering influence features from the weather data information, and inputting the extracted meal ordering influence features into a meal ordering influence evaluation model to obtain a meal ordering quantity influence coefficient; the meal ordering quantity influence coefficient is used to characterize the influence of weather factors on the meal ordering quantity; Based on the order quantity impact coefficient, the order quantity within the target time period is corrected to obtain the order correction quantity within the target time period; Compare the order delivery capacity with the order correction amount: when the order delivery capacity exceeds the order correction amount, delivery is carried out according to the normal delivery process; when the order delivery capacity does not exceed the order correction amount, generate a nutritious meal order delivery optimization strategy and implement it within the target time period.

2. The method for optimizing nutritious meal order delivery based on data analysis according to claim 1, characterized in that: The delivery configuration data information includes the number of delivery personnel and delivery vehicles.

3. The method for optimizing nutritious meal order delivery based on data analysis as claimed in claim 2, characterized in that: The order delivery influencing feature set within the target time period is as follows: Among them, T i is the temperature at the ith time point, H i is the humidity at the i-th time point, W i is the wind speed at the ith time point, P i is the precipitation at the i-th time point, V i is the visibility at the i-th time point, C i is the road congestion at the i-th time point, Z i is the impact of the construction area at the i-th time point, L i is the state of the traffic light at the i-th time point, D i is the number of delivery personnel at the i-th time point, VC i is the state of the delivery vehicle at the i-th time point, DP i is the location of the delivery person at the i-th time point.

4. The method for optimizing nutritious meal order delivery based on data analysis according to claim 1, characterized in that: The method for constructing an order delivery capacity prediction model includes: Extract and merge delivery impact features. The delivery impact feature set includes all relevant variables, and handles missing values, outliers, and duplicate data of delivery impact features. Standardize and normalize the distribution impact characteristics; Choose a machine learning model based on the complexity of the problem and the characteristics of the data; Use historical data to train the order delivery capacity prediction model; The cross-validation technique is used to evaluate the generalization ability of the order delivery capacity prediction model.

5. The method for optimizing nutritious meal order delivery based on data analysis according to claim 1, characterized in that: The mathematical formula of the order delivery capacity prediction model is: Dc=w1A1+w2A2+…+w m A m Among them, Dc represents the distribution capacity, A1, A2…, A m represents the independent variables that affect the delivery capacity. The delivery-related independent variables include temperature, humidity, wind speed, precipitation, visibility, road congestion, construction area impact, traffic light status, number of delivery personnel, delivery vehicle status and delivery personnel location, w1, w2…, w m It is the independent variable A1, A2…, A that affects the distribution capacity m The weights of the independent variables affecting the distribution capacity reflect the degree of influence of each variable on the distribution capacity.

6. The method for optimizing nutritious meal order delivery based on data analysis according to claim 1, characterized in that: The method for obtaining the order quantity influence coefficient includes: Process the collected weather data information, clean the collected weather data, and handle missing values, outliers and duplicate records; Standardize or normalize the cleaned weather data; Use statistical methods to examine the relationship between weather characteristics and meal ordering; Use the feature importance evaluation of the machine learning model to select features that have an impact on the number of orders; Choose the right machine learning model; Use historical data to train the ordering impact evaluation model, divide the data set into a training set and a test set, use the training set data to adjust the ordering impact evaluation model parameters, and use the test set to test the ordering impact evaluation model; Select evaluation metrics to assess the predictive power of the ordering impact evaluation model; Use the ordering impact evaluation model, input the ordering impact characteristics, and output the order quantity impact coefficient.

7. The method for optimizing nutritious meal order delivery based on data analysis according to claim 1, characterized in that: The mathematical formula used in the meal ordering impact evaluation model is expressed as: O=Oq1Wc1+Oq2Wc2+…+Oq n Toilets n Where O represents the order quantity, Wc1, Wc2, ..., Wc n Indicates different weather characteristics, Oq1, Oq2, ..., Oq n Represents the order quantity impact coefficient.

8. A nutritious meal order delivery optimization system based on data analysis, characterized in that: The system comprises: The data collection module is used to collect weather data information, traffic data information and delivery configuration data information within the target time period, including the number of delivery personnel and the status of delivery vehicles; The feature integration module is used to analyze the collected weather data, traffic data and delivery configuration data, extract and integrate the delivery impact features to form an order delivery impact feature set; The delivery capacity prediction module is used to input the order delivery influencing feature set into the order delivery capacity prediction model, and the output order delivery capacity is used to predict the upper limit of the delivery capacity within the target time period; The order volume forecasting module is used to forecast the expected order volume within the target time period based on historical order data using time series analysis; The ordering impact assessment module is used to analyze the impact of weather data information on ordering behavior and extract ordering impact features; the ordering impact assessment model is used to calculate the ordering volume impact coefficient to reflect the specific impact of weather factors on ordering volume; An order correction module is used to adjust the predicted order quantity based on the order quantity influence coefficient to obtain the order correction quantity within the target time period; The delivery decision module is used to compare the order delivery capacity with the order correction amount and adjust the delivery strategy according to the comparison results; The delivery implementation module is used to formulate the optimization strategy for the delivery of nutritious meal orders when the delivery capacity is lower than the order correction amount.

9. An electronic device for optimizing the delivery of nutritious meal orders based on data analysis, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and characterized in that: When the computer program is executed by the processor, the steps in the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method according to any one of claims 1 to 7 are implemented.

Citation Information

Patent Citations

  • Full automation intelligent meal ordering and delivering system and method

    CN106910113A

  • Take-out delivery time prediction method and device

    CN108364085A

  • Flow direction completion method, device and system, model training method and electronic equipment

    CN115409446A

  • Intelligent logistics distribution data management platform

    CN118134358A

  • Engineering quality checking method and system based on BIM (Building Information Modeling) and live-action measurement technology

    CN118195375A

Cited By

  • Production control method based on food demand prediction

    CN119740821A

  • Automobile market logistics distribution scheduling system based on AI optimization

    CN119831238A

  • Ship date data processing method and device, computer program product and storage medium

    CN120634398A

  • Sales plan creation device, sales plan creation method, and program

    WO2026211098A1