Canteen food material purchase-sale-stock intelligent management system

Abstract

The invention relates to the technical field of catering management, and discloses a canteen food material purchase-sale-stock intelligent management system, which comprises a food material data acquisition module, a demand prediction module, a purchase plan generation module, a stock monitoring module, a risk assessment module, an intelligent report module, a data synchronization module, a user interaction module and a performance optimization module. The food material data acquisition module acquires inventory data of canteen food materials in real time; analyzing a historical sales mode and external factors by using a demand prediction module; according to the predicted demand data, combining supplier evaluation to generate purchase plan data; the inventory monitoring module dynamically updates the inventory level; the risk assessment module calculates out-of-stock probability and excess inventory risk; the food material state data, the prediction demand data, the purchase plan data, the inventory early warning signal and the risk level index are integrated, and the intelligent report module generates a visual comprehensive management report and pushes the visual comprehensive management report to the user terminal. The economical efficiency and stability of canteen operation are enhanced.

Description

Technical Field

[0001] This invention relates to the field of catering management technology, specifically to an intelligent management system for the purchase, sale, and inventory of canteen ingredients. Background Technology

[0002] Catering management refers to the practice where businesses, hospitals, schools, hotels, and other similar entities contract out catering management services to professional catering companies to manage their businesses, and then choose from a variety of dishes offered by the catering company.

[0003] Currently, due to various dynamic factors in the management of canteen ingredients, the sensor system used to monitor the inventory of ingredients during real-time data collection cannot detect whether the collected data is affected by environmental interference and equipment errors. When data collection is biased, it will lead to inaccurate judgment of inventory status and cannot guarantee the reliability of inventory management.

[0004] Therefore, an intelligent management system for the purchase, sale, and inventory of canteen ingredients is proposed to solve the above problems. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides an intelligent management system for the purchase, sale, and inventory of canteen ingredients, which solves the problems mentioned in the background art, such as the inability to detect in real time whether the collected data is affected by environmental interference and equipment errors, and the inability to guarantee the reliability of the purchase, sale, and inventory management.

[0006] To achieve the above objectives, the present invention provides the following technical solution: an intelligent management system for the purchase, sale, and inventory of canteen ingredients, comprising: The food data acquisition module uses the inventory sensor unit to collect real-time inventory data of canteen food, reduces outliers and noise through the data cleaning unit, and outputs food status data in a uniform format through the data standardization unit. The demand forecasting module receives the food status data, extracts sales patterns and trends using the historical data analysis unit, generates demand forecasts for future periods using the forecasting algorithm unit by applying a time series model, and outputs the forecasted demand data. The procurement plan generation module receives the predicted demand data, calculates the economic order point and order quantity using the inventory optimization unit, evaluates supplier reliability and price through the supplier management unit, and generates procurement plan data. The inventory monitoring module receives the procurement plan data and actual purchase data, dynamically adjusts the inventory level using the inventory update unit, detects whether the inventory is below the safety threshold using the safety stock comparison unit, and outputs an inventory warning signal. The risk assessment module receives the inventory warning signal, uses the risk calculation unit to assess the probability of stockouts and the risk of excess inventory, and outputs risk level indicators through the level classification unit. The intelligent reporting module integrates the food ingredient status data, predicted demand data, procurement plan data, inventory warning signals, and risk level indicators. It uses the report generation unit to synthesize a comprehensive management report and pushes the report to the user terminal through the output interface unit.

[0007] Preferably, the process in the food data acquisition module that uses an inventory sensor unit to collect real-time inventory data of canteen food, reduces outliers and noise through a data cleaning unit, and outputs food status data in a uniform format through a data standardization unit is as follows: Set the data collection parameters for food inventory, including collection frequency, sensor type and calibration value. Based on the characteristics of food, distinguish between perishable food and food that can be stored for a long time, and set high-frequency and low-frequency collection intervals respectively. Start the sensor acquisition cycle, use IoT sensor units to periodically acquire raw inventory readings, and perform initial filtering to reduce instantaneous fluctuations; Perform a data verification step, compare the current reading with the historical normal range, calculate the deviation rate, and mark the data as abnormal when the deviation rate exceeds the preset tolerance threshold, and trigger the re-acquisition mechanism. For abnormal data, an interpolation and removal strategy based on adjacent time points is adopted to ensure data continuity; Data smoothing is performed, and multiple sensor data are integrated using a moving average method to output clean and reliable food condition data.

[0008] Preferably, the process by which the demand forecasting module receives the food ingredient status data, extracts sales patterns and trends using the historical data analysis unit, generates demand forecasts for future periods using a time series model through the forecasting algorithm unit, and outputs the forecasted demand data is as follows: Collect historical sales data, including daily sales volume, ingredient type and external factor records, and clean and normalize the data through the data preprocessing unit to reduce outliers and missing values; Using time series analysis, the moving average method is used to calculate the trend line of basic demand. The calculation formula is as follows: ; in, Let t be the predicted demand value for period t. This represents the actual demand value for period t-1. This is a smoothing coefficient, ranging from 0 to 1, used to adjust the weight of historical data; Identify seasonal fluctuation patterns and adjust forecasts using seasonal indices to reflect cyclical changes; By integrating external influencing factors, including holidays, weather conditions, and canteen activity plans, and using multiple regression analysis units to quantify the impact weights of these factors on demand, the forecast results are revised. Output daily demand forecasts for specific future periods, including point forecasts and confidence intervals, to support decision-making uncertainty management.

[0009] Preferably, the process by which the procurement plan generation module receives the predicted demand data, calculates the economic order point and order quantity using the inventory optimization unit, evaluates supplier reliability and price through the supplier management unit, and generates procurement plan data is as follows: Based on demand forecast data and current inventory levels, holding costs, stockout costs, and ordering costs are calculated using an inventory cost model unit. An optimization algorithm is then used to determine the economic order quantity. The calculation formula is as follows: ; in, To achieve the optimal economic order quantity, This represents the projected total annual demand. Cost per order, Annual holding cost per unit of food ingredients; Set a reorder point and calculate the safety stock level based on demand volatility and supplier delivery time to ensure that the inventory is greater than the critical value. The supplier evaluation unit analyzes the supplier's historical performance, including on-time delivery rate, quality pass rate, and price stability, to generate a supplier score. By combining market data, the purchase volume is dynamically adjusted, and the optimal purchase plan data is output, including order quantity, delivery time and priority allocation.

[0010] Preferably, the process by which the inventory monitoring module receives the procurement plan data and actual purchase data, dynamically adjusts the inventory level using the inventory update unit, detects whether the inventory is below the safety threshold using the safety stock comparison unit, and outputs an inventory warning signal is as follows: It receives procurement plan data and actual warehousing information in real time, and uses the inventory update unit to synchronously update the inventory database, recording each purchase, outbound and loss event. The safety stock comparison unit periodically checks the current inventory level against the safety threshold. When the inventory level falls below the safety threshold, an early warning signal is generated, triggering an automatic replenishment suggestion. Implement inventory turnover rate monitoring, calculate the average inventory days of food ingredients, and identify slow-moving and overstocked items; Integrate environmental sensor data, including temperature and humidity, to assess the impact of storage conditions on inventory quality and adjust safety stock parameters to adapt to environmental changes; Outputs real-time inventory status reports and early warning information, supporting timely intervention.

[0011] Preferably, the process by which the risk assessment module receives the inventory warning signal, assesses the probability of stockouts and the risk of excess inventory using the risk calculation unit, and outputs risk level indicators through the level classification unit is as follows: The risk indicator calculation unit analyzes inventory warning signals and, combined with the uncertainty of demand forecasting, calculates the probability of stockouts based on historical stockout events and current inventory trends. Assess the risk of excess inventory by comparing actual inventory with ideal levels using the inventory backlog rate calculation unit to identify potential waste issues; By applying probabilistic analysis models, including Monte Carlo simulations, risk distribution maps are generated to quantify the risk levels under different scenarios. Risk indicators are classified into three levels—low, medium, and high—through a grading system, and corresponding countermeasures are associated with them. It outputs risk level data, including risk description, probability of occurrence, and degree of impact, providing visual support for decision-making.

[0012] Preferably, the intelligent reporting module integrates the ingredient status data, predicted demand data, procurement plan data, inventory early warning signals, and risk level indicators, synthesizes a comprehensive management report using the report generation unit, and pushes the report to the user terminal through the output interface unit as follows: Integrate multi-source data, including food status data, forecasted demand data, procurement plan data, inventory warning signals, and risk level indicators, and use data fusion units for alignment and aggregation to reduce data conflicts; The report generation unit uses a template engine to synthesize standardized report content, covering inventory summary, demand analysis, procurement execution, risk assessment, and recommended actions; Utilize visualization units to create charts and dashboards, including inventory trend graphs, demand forecast curves, and risk heatmaps, to enhance report readability; The report can be pushed to the user terminal in multiple formats through the output interface unit, and supports real-time updates and custom queries.

[0013] Preferably, it also includes a data synchronization module to ensure data consistency between various modules of the system: The data synchronization unit periodically verifies the data flow of the food data acquisition module, demand forecasting module, procurement plan generation module, inventory monitoring module, risk assessment module, and intelligent reporting module to detect data delays and loss. Data inconsistency issues are addressed through conflict resolution mechanisms, including timestamp priority and version control strategies. Integrated cloud storage units back up critical data, ensuring system robustness and disaster recovery capabilities; Output a synchronization status report to inform the user of the data health status.

[0014] Preferably, the system enhances the user experience through a user interaction module: The graphical user interface unit provides an intuitive operation panel that allows users to manually input and adjust parameters, including modifying safety stock thresholds and forecasting model settings. The alarm configuration unit allows users to customize alarm rules and notification methods, including SMS, email, and mobile application push notifications. An integrated feedback collection unit is used to gather user satisfaction with system suggestions, enabling subsequent optimizations. Output interaction logs to record user actions and system responses, supporting auditing and performance analysis.

[0015] Preferably, the system implementation process also includes a performance optimization module: Use the performance monitoring unit to track system response time, data accuracy, and resource utilization, and generate performance reports regularly. By analyzing the effects of historical decisions through adaptive learning units, the parameters of the prediction model and inventory strategies are adjusted to improve the system's accuracy. Integrating energy-saving algorithms optimizes data acquisition frequency and computing resource allocation, thereby reducing energy consumption; Provide optimization suggestions, including module upgrades and process improvements, to ensure long-term system operation.

[0016] Compared with the prior art, the present invention provides an intelligent management system for the purchase, sale, and inventory of canteen ingredients, which has the following beneficial effects: 1. In this invention, when collecting canteen food inventory data in real time, standardized collection parameters and data cleaning processes are set through the food data collection module. The collection frequency is differentiated for different types of food, and environmental interference and equipment errors are detected in real time using a data verification mechanism. This can reduce the impact of abnormal data, ensure the accuracy and consistency of inventory status data, thereby reducing decision-making bias in inventory management and improving system reliability.

[0017] 2. In this invention, when conducting demand forecasting analysis for canteen ingredients, the demand forecasting module integrates historical sales data and external unforeseen factors, including holidays and weather changes. It applies time series models and multiple regression analysis to adjust forecasting parameters in real time, enabling the system to adapt to fluctuations in external events, correct forecast deviations in a timely manner, improve the accuracy of demand forecasting and real-time response capabilities, and avoid supply shortages and surpluses.

[0018] 3. In this invention, when generating a canteen food procurement plan, the procurement plan generation module, combined with the supplier evaluation and risk assessment modules, performs multi-dimensional analysis to calculate the economic order point and risk level in real time. This enables dynamic hedging against market supply fluctuations and potential risks, allowing the system to optimize procurement batches and timing, reduce inventory backlog and stockout risks, and enhance the economy and stability of canteen operations. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of the architecture of an intelligent management system for the purchase, sale, and inventory of canteen ingredients according to the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] Please see Figure 1 The specific implementation of a smart management system for the purchase, sale, and inventory of canteen ingredients is as follows: The food data acquisition module uses the inventory sensor unit to collect real-time inventory data of canteen food, reduces outliers and noise through the data cleaning unit, and outputs food status data in a uniform format through the data standardization unit. The demand forecasting module receives food status data, extracts sales patterns and trends using the historical data analysis unit, applies a time series model through the forecasting algorithm unit to generate demand forecasts for future periods, and outputs the forecasted demand data. The procurement plan generation module receives forecasted demand data, uses the inventory optimization unit to calculate the economic order point and order quantity, evaluates supplier reliability and price through the supplier management unit, and generates procurement plan data. The inventory monitoring module receives procurement plan data and actual purchase data, dynamically adjusts inventory levels using the inventory update unit, detects whether the inventory is below the safety threshold using the safety stock comparison unit, and outputs an inventory warning signal. The risk assessment module receives inventory warning signals, uses the risk calculation unit to assess the probability of stockouts and the risk of excess inventory, and outputs risk level indicators through the level classification unit. The intelligent reporting module integrates food status data, forecasted demand data, procurement plan data, inventory warning signals, and risk level indicators. It uses the report generation unit to synthesize a comprehensive management report and pushes the report to the user terminal through the output interface unit.

[0022] The food ingredient data acquisition module utilizes inventory sensor units to collect real-time inventory data of canteen ingredients. The data cleaning unit reduces outliers and noise, and the data standardization unit outputs uniformly formatted food ingredient status data. Set the data collection parameters for food inventory, including collection frequency, sensor type and calibration value. Based on the characteristics of food, distinguish between perishable food and food that can be stored for a long time, and set high-frequency and low-frequency collection intervals respectively. Start the sensor acquisition cycle, use IoT sensor units to periodically acquire raw inventory readings, and perform initial filtering to reduce instantaneous fluctuations; Perform the data verification step, compare the current reading with the historical normal range, and calculate the deviation rate using the following formula: ; in, For data deviation rate, This is the current inventory reading collected by the sensor. This represents the average inventory level within the historical normal range. Specific procedures: The historical normal range is calculated by statistically analyzing inventory data from the past 30 days, resulting in the average inventory level. The daily moving average of inventory is used, and the preset tolerance threshold is dynamically set according to the type of food, including a 5% threshold for perishable foods and a 10% threshold for foods that can be stored for a long time. When the deviation rate exceeds the preset tolerance threshold, it is marked as abnormal data and a re-acquisition mechanism is triggered; For abnormal data, an interpolation and removal strategy based on adjacent time points is adopted to ensure data continuity; Data smoothing is performed, and multiple sensor data are integrated using a moving average method to output clean and reliable food condition data.

[0023] The demand forecasting module receives food ingredient status data, extracts sales patterns and trends using the historical data analysis unit, and generates demand forecasts for future periods using a time series model through the forecasting algorithm unit, outputting the forecasted demand data as follows: Collect historical sales data, including daily sales volume, ingredient type and external factor records, and clean and normalize the data through the data preprocessing unit to reduce outliers and missing values; Using time series analysis, the moving average method is used to calculate the trend line of basic demand. The calculation formula is as follows: ; in, Let t be the predicted demand value for period t. This represents the actual demand value for period t-1. This is a smoothing coefficient, ranging from 0 to 1, used to adjust the weight of historical data; Identify seasonal fluctuation patterns and adjust forecasts using seasonal indices to reflect cyclical changes; By integrating external influencing factors, including holidays, weather conditions, and canteen activity plans, and using multiple regression analysis units to quantify the impact weights of these factors on demand, the forecast results are revised. Output daily demand forecasts for specific future periods, including point forecasts and confidence intervals, to support decision-making uncertainty management.

[0024] The procurement planning generation module receives forecasted demand data, calculates the economic order point and order quantity using the inventory optimization unit, evaluates supplier reliability and pricing through the supplier management unit, and generates procurement plan data as follows: Based on demand forecast data and current inventory levels, holding costs, stockout costs, and ordering costs are calculated using an inventory cost model unit. An optimization algorithm is then used to determine the economic order quantity. The calculation formula is as follows: ; in, To achieve the optimal economic order quantity, This represents the projected total annual demand. Cost per order, Annual holding cost per unit of food ingredients; Set a reorder point and calculate the safety stock level based on demand volatility and supplier delivery time to ensure that the inventory is greater than the critical value. The supplier evaluation unit analyzes the supplier's historical performance, including on-time delivery rate, quality pass rate, and price stability, to generate a supplier score. By combining market data, the purchase volume is dynamically adjusted, and the optimal purchase plan data is output, including order quantity, delivery time and priority allocation.

[0025] The inventory monitoring module receives procurement plan data and actual purchase data, dynamically adjusts inventory levels using the inventory update unit, and detects whether the inventory is below the safety stock threshold using the safety stock comparison unit, then outputs an inventory warning signal. It receives procurement plan data and actual warehousing information in real time, and uses the inventory update unit to synchronously update the inventory database, recording each purchase, outbound and loss event. The current inventory level is periodically checked against the safety stock threshold using a safety stock comparison unit. The safety stock level is dynamically calculated based on demand fluctuations and supply cycles, using the following formula: ; in, To maintain a safe inventory level, For the service level factor, The standard deviation of daily demand. The average delivery time for suppliers is in days; Specific procedures: Service Level Factor The standard deviation of daily demand is obtained from a standard normal distribution table based on the target service level. The average delivery cycle of suppliers was calculated by analyzing daily sales data from the past 90 days. Updated based on historical delivery records, reassessed monthly; When the current inventory level is lower than the safety stock This will generate an early warning signal and trigger an automatic replenishment suggestion; Implement inventory turnover rate monitoring, calculate the average inventory days of food ingredients, and identify slow-moving and overstocked items; Integrate environmental sensor data, including temperature and humidity, to assess the impact of storage conditions on inventory quality and adjust safety stock parameters to adapt to environmental changes; Outputs real-time inventory status reports and early warning information, supporting timely intervention.

[0026] The risk assessment module receives inventory warning signals, uses the risk calculation unit to assess the probability of stockouts and the risk of excess inventory, and outputs risk level indicators through the level classification unit. By analyzing inventory warning signals using risk indicator calculation units and combining this with the uncertainty of demand forecasting, the probability of stockouts can be calculated. The formula is: ; in, This represents the probability of being out of stock. For the actual inventory level to be lower than the safety threshold during the statistical period Number of times, Total number of monitoring sessions; Specific procedures: The statistical period is set to weekly and monthly, adjusted according to the canteen's operational cycle. The determination that actual inventory is below the safety threshold is based on daily inventory snapshot data, and the total number of monitoring sessions... Total number of inspections within the corresponding period; Assess the risk of excess inventory by comparing actual inventory with ideal levels using the inventory backlog rate calculation unit to identify potential waste issues; By applying probabilistic analysis models, including Monte Carlo simulations, risk distribution maps are generated to quantify the risk levels under different scenarios. Risk indicators are classified into three levels—low, medium, and high—through a grading system, and corresponding countermeasures are associated with them. It outputs risk level data, including risk description, probability of occurrence, and degree of impact, providing visual support for decision-making.

[0027] The intelligent reporting module integrates food ingredient status data, forecasted demand data, procurement plan data, inventory warning signals, and risk level indicators. It then uses a report generation unit to synthesize a comprehensive management report, which is pushed to the user terminal via an output interface unit. Integrate multi-source data, including food status data, forecasted demand data, procurement plan data, inventory warning signals, and risk level indicators, and use data fusion units for alignment and aggregation to reduce data conflicts; The report generation unit uses a template engine to synthesize standardized report content, covering inventory summary, demand analysis, procurement execution, risk assessment, and recommended actions, and calculates a comprehensive management performance score. The formula is: ; in, For comprehensive management performance scoring, To improve data collection accuracy, This represents the probability of being out of stock. For inventory turnover rate, , , These are the weighting coefficients for each indicator, and ; The specific operation is as follows: weighting coefficients are set using expert scoring and AHP (Analytic Hierarchy Process), including... Emphasizing data accuracy, Emphasizing supply stability Emphasis is placed on inventory efficiency and data collection accuracy. The results were calculated by comparing sensor data with manual inventory results. Utilize visualization units to create charts and dashboards, including inventory trend graphs, demand forecast curves, and risk heatmaps, to enhance report readability; The report can be pushed to the user terminal in multiple formats through the output interface unit, and supports real-time updates and custom queries.

[0028] It also includes a data synchronization module to ensure data consistency between different modules in the system. The data synchronization unit periodically verifies the data flow of the food data acquisition module, demand forecasting module, procurement plan generation module, inventory monitoring module, risk assessment module, and intelligent reporting module to detect data delays and loss. Data inconsistency issues are addressed through conflict resolution mechanisms, including timestamp-first and version control strategies, and data consistency rates are calculated. The formula is:

[0029] in, For data consistency rate, This refers to the number of records for data matching between modules during the synchronization period. This represents the total number of data records. Specific operations: The synchronization cycle is set to hourly or daily, adjusted according to the data update frequency. Data matching is based on the consistency of key fields including ingredient ID and timestamp, and the total number of data records. It covers all interactive data points from all modules and uses timestamp priority and version control strategies to resolve data conflicts; Integrated cloud storage units back up critical data, ensuring system robustness and disaster recovery capabilities; Output a synchronization status report to inform the user of the data health status.

[0030] The system enhances the user experience through a user interaction module: The graphical user interface unit provides an intuitive operation panel that allows users to manually input and adjust parameters, including modifying safety stock thresholds and forecasting model settings. The alarm configuration unit allows users to customize alarm rules and notification methods, including SMS, email, and mobile application push notifications. An integrated feedback collection unit is used to gather user satisfaction with system suggestions, enabling subsequent optimizations. Output interaction logs to record user actions and system responses, supporting auditing and performance analysis.

[0031] The system implementation process also includes a performance optimization module: Use the performance monitoring unit to track system response time, data accuracy, and resource utilization, and generate performance reports regularly. By analyzing the effects of historical decisions through adaptive learning units, the parameters of the prediction model and inventory strategies are adjusted to improve the system's accuracy. Integrating energy-saving algorithms optimizes data acquisition frequency and computing resource allocation, thereby reducing energy consumption; Provide optimization suggestions, including module upgrades and process improvements, to ensure long-term system operation.

[0032] The operation steps of an intelligent management system for the purchase, sale, and inventory of canteen ingredients are as follows: Step 1: Ingredient Data Collection and Status Recognition The system first starts working through the food data acquisition module, which uses various sensor units deployed in the warehouse to collect raw data on the inventory of canteen food in real time. Next, the data cleaning unit processes the raw data to remove outliers and noise caused by sensor interference and communication errors. Then, the data standardization unit formats the cleaned data and outputs food status data in a uniform format that can be directly used by subsequent modules. This step is the cornerstone of the system's operation, ensuring that analysis and decision-making are based on an accurate and consistent data foundation.

[0033] Step Two: Demand Forecasting and Trend Analysis The demand forecasting module receives food status data from upstream suppliers and calls the historical data analysis unit to extract historical sales patterns, seasonal trends, and other data related to the current food from the database. Then, the forecasting algorithm unit applies algorithms such as time series models to analyze and calculate the historical and real-time data to generate forecast demand data for a specific future period. This data includes not only point forecast values ​​but also confidence intervals to quantify the uncertainty of the forecast and provide a basis for procurement.

[0034] Step 3: Intelligent generation of procurement plan: After receiving the forecasted demand data, the procurement plan generation module's inventory optimization unit will use an inventory cost model to comprehensively consider the holding costs, stockout costs, and ordering costs of ingredients. Through optimization algorithms, it will calculate the economic order point and the optimal order quantity, aiming to minimize total costs. At the same time, the supplier management unit will evaluate the performance indicators of each supplier and combine them with real-time market data to dynamically adjust the procurement plan. Finally, it will generate a detailed procurement plan that includes order quantity, delivery time, and priority recommendations.

[0035] Step 4: Inventory Dynamic Monitoring and Early Warning The core task of the inventory monitoring module is to maintain inventory levels within a safe range. This module receives procurement plan data and actual inbound and outbound information in real time, and dynamically updates the inventory database using the inventory update unit. The safety stock comparison unit periodically compares the current inventory level with the pre-calculated safety stock threshold. Once the inventory level is detected to be lower than the safety threshold, an inventory warning signal is immediately generated, triggering the system's automatic replenishment suggestion mechanism, thereby realizing the transformation from passive response to proactive warning.

[0036] Step 5: Operational Risk Assessment and Classification The risk assessment module receives early warning signals from the inventory monitoring module. Its risk calculation unit combines the uncertainties in demand forecasting to comprehensively calculate the probability of stockouts and the risk of excess inventory. The calculation process references the historical failure database. Then, the level classification unit quantifies the risk indicators into different levels such as low, medium, and high according to the preset risk matrix, and outputs risk level indicators that include risk description, probability of occurrence, and degree of impact, providing decision support for whether intervention is needed.

[0037] Step Six: Intervention Needs Analysis and Decision Making The intervention demand analysis module conducts a comprehensive assessment based on the received fault risk level and expected occurrence time, combined with the current production plan information and equipment health tolerance obtained from external systems. This module uses methods such as correlation analysis to evaluate the impact of maintenance intervention on the production plan and ultimately determines whether early intervention measures need to be implemented in the current cycle, thereby making a balanced decision between ensuring equipment safety and maintaining production continuity.

[0038] Step 7: Intelligent Report Generation and Output: The intelligent reporting module, as the system's output terminal, is responsible for integrating data from the entire process, including ingredient status data, forecasted demand data, procurement plan data, inventory warning signals, and risk level indicators. The report generation unit uses a preset template engine to merge this multi-source data into a standardized comprehensive management report. The report content covers inventory summary, demand analysis, procurement execution, risk assessment, and recommended measures, and is presented in the form of charts and graphs through the visualization unit. Finally, it is pushed to the user terminal through the output interface unit, providing managers with comprehensive decision support.

[0039] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0040] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A smart management system for the purchase, sale, and inventory of canteen ingredients, characterized in that, include: The food data acquisition module uses the inventory sensor unit to collect real-time inventory data of canteen food, reduces outliers and noise through the data cleaning unit, and outputs food status data in a uniform format through the data standardization unit. The demand forecasting module receives the food status data, extracts sales patterns and trends using the historical data analysis unit, generates demand forecasts for future periods using the forecasting algorithm unit by applying a time series model, and outputs the forecasted demand data. The procurement plan generation module receives the predicted demand data, uses the inventory optimization unit to calculate the economic order point and order quantity, evaluates supplier reliability and price through the supplier management unit, and generates procurement plan data. The inventory monitoring module receives the procurement plan data and actual purchase data, dynamically adjusts the inventory level using the inventory update unit, detects whether the inventory is below the safety threshold using the safety stock comparison unit, and outputs an inventory warning signal. The risk assessment module receives the inventory warning signal, uses the risk calculation unit to assess the probability of stockouts and the risk of excess inventory, and outputs risk level indicators through the level classification unit. The intelligent reporting module integrates the food ingredient status data, predicted demand data, procurement plan data, inventory warning signals, and risk level indicators. It uses the report generation unit to synthesize a comprehensive management report and pushes the report to the user terminal through the output interface unit.

2. The intelligent management system for the purchase, sale, and inventory of canteen ingredients according to claim 1, characterized in that, The process of the food data acquisition module using an inventory sensor unit to collect real-time inventory data of canteen food, reducing outliers and noise through a data cleaning unit, and outputting food status data in a uniform format through a data standardization unit is as follows: Set the data collection parameters for food inventory, including collection frequency, sensor type and calibration value. Based on the characteristics of food, distinguish between perishable food and food that can be stored for a long time, and set high-frequency and low-frequency collection intervals respectively. Start the sensor acquisition cycle, use IoT sensor units to periodically acquire raw inventory readings, and perform initial filtering to reduce instantaneous fluctuations; Perform a data verification step, compare the current reading with the historical normal range, calculate the deviation rate, and mark the data as abnormal when the deviation rate exceeds the preset tolerance threshold, and trigger the re-acquisition mechanism. For abnormal data, an interpolation and removal strategy based on adjacent time points is adopted to ensure data continuity; Data smoothing is performed, and multiple sensor data are integrated using a moving average method to output clean and reliable food condition data.

3. The intelligent management system for the purchase, sale, and inventory of canteen ingredients according to claim 1, characterized in that, The process by which the demand forecasting module receives the food ingredient status data, extracts sales patterns and trends using the historical data analysis unit, generates demand forecasts for future periods using a time series model through the forecasting algorithm unit, and outputs the forecasted demand data is as follows: Collect historical sales data, including daily sales volume, ingredient type and external factor records, and clean and normalize the data through the data preprocessing unit to reduce outliers and missing values; Using time series analysis, the moving average method is used to calculate the trend line of basic demand. The calculation formula is as follows: ； in, Let t be the predicted demand value for period t. This represents the actual demand value for period t-1. This is a smoothing coefficient, ranging from 0 to 1, used to adjust the weight of historical data; Identify seasonal fluctuation patterns and adjust forecasts using seasonal indices to reflect cyclical changes; By integrating external influencing factors, including holidays, weather conditions, and canteen activity plans, and using multiple regression analysis units to quantify the impact weights of these factors on demand, the forecast results are revised. Output daily demand forecasts for specific future periods, including point forecasts and confidence intervals, to support decision-making uncertainty management.

4. The intelligent management system for the purchase, sale, and inventory of canteen ingredients according to claim 1, characterized in that, The process by which the procurement plan generation module receives the predicted demand data, calculates the economic order point and order quantity using the inventory optimization unit, evaluates supplier reliability and price through the supplier management unit, and generates procurement plan data is as follows: Based on demand forecast data and current inventory levels, holding costs, stockout costs, and ordering costs are calculated using an inventory cost model unit. An optimization algorithm is then used to determine the economic order quantity. The calculation formula is as follows: ； in, To achieve the optimal economic order quantity, This represents the projected total annual demand. Cost per order, Annual holding cost per unit of food ingredients; Set a reorder point and calculate the safety stock level based on demand volatility and supplier delivery time to ensure that the inventory is greater than the critical value. The supplier evaluation unit analyzes the supplier's historical performance, including on-time delivery rate, quality pass rate, and price stability, to generate a supplier score. By combining market data, the purchase volume is dynamically adjusted, and the optimal purchase plan data is output, including order quantity, delivery time and priority allocation.

5. The intelligent management system for the purchase, sale, and inventory of canteen ingredients according to claim 1, characterized in that, The inventory monitoring module receives the procurement plan data and actual purchase data, dynamically adjusts the inventory level using the inventory update unit, and detects whether the inventory is below the safety threshold using the safety stock comparison unit, and outputs an inventory warning signal as follows: It receives procurement plan data and actual warehousing information in real time, and uses the inventory update unit to synchronously update the inventory database, recording each receipt, outbound and loss event; The safety stock comparison unit periodically checks the current inventory level against the safety threshold. When the inventory level falls below the safety threshold, an early warning signal is generated, triggering an automatic replenishment suggestion. Implement inventory turnover rate monitoring, calculate the average inventory days of food ingredients, and identify slow-moving and over-stocked items; Integrate environmental sensor data, including temperature and humidity, to assess the impact of storage conditions on inventory quality and adjust safety stock parameters to adapt to environmental changes; Outputs real-time inventory status reports and early warning information, supporting timely intervention.

6. The intelligent management system for the purchase, sale, and inventory of canteen ingredients according to claim 1, characterized in that, The process by which the risk assessment module receives the inventory warning signal, uses the risk calculation unit to assess the probability of stockouts and the risk of excess inventory, and outputs risk level indicators through the level classification unit is as follows: The risk indicator calculation unit analyzes inventory warning signals and, combined with the uncertainty of demand forecasting, calculates the probability of stockouts based on historical stockout events and current inventory trends. Assess the risk of excess inventory by comparing actual inventory with ideal levels using the inventory backlog rate calculation unit to identify potential waste issues; By applying probabilistic analysis models, including Monte Carlo simulations, risk distribution maps are generated to quantify the risk levels under different scenarios. Risk indicators are classified into three levels—low, medium, and high—through a grading system, and corresponding countermeasures are associated with them. It outputs risk level data, including risk description, probability of occurrence, and degree of impact, providing visual support for decision-making.

7. The intelligent management system for the purchase, sale, and inventory of canteen ingredients according to claim 1, characterized in that, The intelligent reporting module integrates the ingredient status data, predicted demand data, procurement plan data, inventory warning signals, and risk level indicators. It then uses a report generation unit to synthesize a comprehensive management report, which is then pushed to the user terminal via an output interface unit. Integrate multi-source data, including food status data, forecasted demand data, procurement plan data, inventory warning signals, and risk level indicators, and use data fusion units for alignment and aggregation to reduce data conflicts; The report generation unit uses a template engine to synthesize standardized report content, covering inventory summary, demand analysis, procurement execution, risk assessment, and recommended actions; Utilize visualization units to create charts and dashboards, including inventory trend graphs, demand forecast curves, and risk heatmaps, to enhance report readability; The report can be pushed to the user terminal in multiple formats through the output interface unit, and supports real-time updates and custom queries.

8. The intelligent management system for the purchase, sale, and inventory of canteen ingredients according to claim 1, characterized in that, It also includes a data synchronization module to ensure data consistency between different modules in the system. The data synchronization unit periodically verifies the data flow of the food data acquisition module, demand forecasting module, procurement plan generation module, inventory monitoring module, risk assessment module, and intelligent reporting module to detect data delays and loss. Data inconsistency issues are addressed through conflict resolution mechanisms, including timestamp priority and version control strategies. Integrated cloud storage units back up critical data, ensuring system robustness and disaster recovery capabilities; Output a synchronization status report to inform the user of the data health status.

9. The intelligent management system for the purchase, sale, and inventory of canteen ingredients according to claim 1, characterized in that, The system enhances the user experience through a user interaction module: The graphical user interface unit provides an intuitive operation panel that allows users to manually input and adjust parameters, including modifying safety stock thresholds and forecasting model settings. The alarm configuration unit allows users to customize alarm rules and notification methods, including SMS, email, and mobile application push notifications. An integrated feedback collection unit is used to gather user satisfaction with system suggestions, enabling subsequent optimizations. Output interaction logs to record user actions and system responses, supporting auditing and performance analysis.

10. The intelligent management system for the purchase, sale, and inventory of canteen ingredients according to claim 1, characterized in that, The system implementation process also includes a performance optimization module: Use the performance monitoring unit to track system response time, data accuracy, and resource utilization, and generate performance reports regularly. By analyzing the effects of historical decisions through adaptive learning units, the parameters of the prediction model and inventory strategies are adjusted to improve the system's accuracy. Integrating energy-saving algorithms optimizes data acquisition frequency and computing resource allocation, thereby reducing energy consumption; Provide optimization suggestions, including module upgrades and process improvements, to ensure long-term system operation.

Images