Unmanned vending machine goods scheduling management system based on cloud computing

Abstract

The invention relates to the technical field of goods management, in particular to an unmanned vending machine goods scheduling management system based on cloud computing, which comprises a goods data integration module, a goods demand prediction and weight determination module, a goods placement task generation module and a goods scheduling execution monitoring module. According to the invention, the accuracy and response speed of management of the unmanned vending machine are effectively improved, the accuracy and efficiency of goods placement are monitored in real time, and the deviation is immediately adjusted by performing quantitative prediction on the goods demand and optimizing the goods weight in combination with the historical data and the sales rate, so that the continuity of goods supply is ensured, and the service life of the unmanned vending machine is prolonged. By optimizing the placing position and sequence of the goods, the unmanned vending machine can more efficiently utilize the space, reduce the time expenditure during goods storage and taking, enhance the immediate response capability of the unmanned vending machine to the requirements of patients, reduce the risk of overdue goods and stock overstock, and improve the safety of the unmanned vending machine. And the effective utilization of goods and the safety of patients are further guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of product management, and in particular to a product dispatching and management system for unmanned vending machines based on cloud computing. Background Art

[0002] The field of product management technology involves a series of methods, systems and tools designed to improve the efficiency and security of the product supply chain. It includes the procurement, storage, distribution and control of products from pharmaceutical factories to end users (such as hospitals, unmanned vending machines and other medical institutions), including product procurement decision support, inventory control, product distribution scheduling, expiration date and quality management, and product usage monitoring. Technical means include the use of database management systems, automated inventory management tools and logistics optimization software, which are key tools to ensure the accuracy, traceability and compliance of product management.

[0003] Among them, the cloud computing-based unmanned vending machine goods dispatching and management system is a computer system specially designed for the internal goods management of unmanned vending machines. Its main purpose is to optimize the storage, distribution and inventory control of goods to reduce costs and improve service efficiency. It ensures that unmanned vending machines can effectively respond to patient needs while maintaining the continuity and compliance of goods supply by automating tasks such as goods receiving, sorting, storage, replenishment, and monitoring of expired goods. It also supports the unmanned vending machines' needs for goods safety and compliance, such as tracking the source of goods and ensuring the correct delivery of goods.

[0004] Although existing technologies support basic product management functions, they generally lack the ability to quickly adapt to changes in product demand. Static inventory management and the lack of efficient forecasting tools often lead to a mismatch between product distribution and actual demand, increasing the operating costs of unmanned vending machines and patient waiting time. In addition, existing systems rarely update product demand in real time, resulting in an inability to effectively respond to rapidly changing market conditions, such as product shortages during medical emergencies. This not only affects the response of unmanned vending machines to emergency needs, but may also cause resource waste and financial burdens when over-purchasing products, reducing the ability of unmanned vending machines to handle public health emergencies. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an unmanned vending machine goods scheduling and management system based on cloud computing.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solution: A cloud computing-based unmanned vending machine goods dispatching and management system comprises:

[0007] The product data integration module receives the sales data of the unmanned vending machines, verifies the accuracy and completeness of the information through data cleaning and format standardization, and generates comprehensive product data;

[0008] The product demand forecasting and weight determination module performs a trend analysis of product demand based on the comprehensive product data, performs a quantitative forecast of future product demand, calculates a weight value for each product based on the quantitative forecast result combined with the sales rate and historical demand data, and generates a product weight list;

[0009] The goods placement task generation module receives the goods weight list, determines whether to perform inventory replenishment according to the set threshold, determines the types and quantities of replenished goods, optimizes the placement position and sequence according to the determination result combined with the unmanned vending machine layout data, updates the task plan, and outputs the goods placement task data;

[0010] The goods scheduling execution monitoring module continuously monitors the goods scheduling process based on the goods placement task data, tracks the accuracy and efficiency of goods placement in real time, identifies execution process deviations according to the real-time tracking results, and dynamically adjusts the deviations immediately to generate a dynamic scheduling management plan for unmanned vending machine goods.

[0011] As a further solution of the present invention, the steps for obtaining the comprehensive product data are:

[0012] Receive sales data from unmanned vending machines, merge the data, and generate a preliminary integrated data set;

[0013] Performing data cleaning on the preliminary integrated data set, deleting duplicate records, standardizing time and value formats, and correcting data errors to obtain a cleaned data set;

[0014] The cleaned data set is subjected to data verification to verify the consistency and completeness of the data and generate comprehensive commodity data.

[0015] As a further solution of the present invention, the quantitative prediction steps of the future demand for goods are:

[0016] Based on the comprehensive product data, time series analysis is performed to determine product sales trends and obtain sales trend analysis results;

[0017] Based on the sales trend analysis results, the formula is adopted:

[0018]

[0019] Calculate the forecast demand for goods in the future period P t , generate quantitative prediction results; where Y t-1 The sales volume in the representative period, ΔY t-1 Represents Y t-1 The first-order difference of t-1 -Y t-2 , Y t-2represents the sales volume in period t-2, and λ is the model sensitivity constant;

[0020] The quantitative prediction results are used to perform validity tests, including residual analysis and prediction accuracy tests, to obtain prediction confirmation results.

[0021] As a further solution of the present invention, the steps for obtaining the commodity weight list are:

[0022] Based on the prediction confirmation results, collect historical sales rate and demand data of the goods, aggregate the data, and output a converged data set;

[0023] Based on the aggregated data set, the formula is adopted:

[0024]

[0025] Calculate the weight value W of each product i , get the product weight value calculation set, where Q i represents the quantitative forecast demand for product i, S i represents the historical sales rate of product i, n represents the total number of product types, and j represents the different product types;

[0026] Based on the product weight value calculation set, priority sorting is performed to generate a product weight list.

[0027] As a further solution of the present invention, the step of determining the quantity of the types of supplementary goods is:

[0028] Import the commodity weight list through the network interface, count the usage frequency and remaining inventory of each commodity, reflect the replenishment demand of the commodity, and generate preliminary analysis results of the commodity demand;

[0029] Compare the preliminary analysis results of the product demand with the set inventory replenishment threshold, determine whether the weight of each product exceeds the threshold, decide whether inventory replenishment needs to be performed, and generate a list of products to be replenished;

[0030] Based on the list of goods to be replenished, determine the types and quantities of goods that actually need to be replenished, simultaneously confirm that the goods inventory can meet future needs, and generate a list of types and quantities of replenished goods.

[0031] As a further solution of the present invention, the steps for acquiring the cargo placement task data are as follows:

[0032] Receive the list of types and quantities of the supplementary goods, determine the placement of each product based on the unmanned vending machine layout data, and generate a preliminary product placement optimization plan;

[0033] Apply the product placement optimization solution to adjust and optimize the unmanned vending machine workflow, automatically update the new product placement sequence and location information, and generate an updated unmanned vending machine task plan;

[0034] Based on the updated unmanned vending machine task plan, formulate medicine placement task instructions, determine the placement location, replenishment quantity and operation sequence of each product, and generate goods placement task data.

[0035] As a further solution of the present invention, the steps for real-time tracking of the accuracy and efficiency of goods placement are:

[0036] Based on the cargo placement task data, real-time cargo scheduling data is generated by monitoring the real-time data stream of the cargo scheduling process, recording the scheduling status and time nodes of the cargo;

[0037] Analyze the real-time cargo scheduling data, evaluate the accuracy and efficiency of cargo placement, record the accuracy and time required for cargo placement, and generate a cargo placement performance evaluation report;

[0038] According to the goods placement performance evaluation report, the monitoring data is continuously updated, the goods scheduling efficiency and accuracy are displayed in real time, and the real-time tracking goods placement data is output.

[0039] As a further solution of the present invention, the steps for obtaining the dynamic scheduling management solution for goods in the unmanned vending machine are:

[0040] According to the real-time tracked goods placement data, count the placement position deviation and time deviation of each goods, and generate deviation statistical records;

[0041] Utilizing the deviation statistical records, optimizing the goods dispatch path and schedule, adjusting the goods circulation efficiency, and generating an adjusted goods dispatch plan;

[0042] The adjusted product dispatching plan is applied to update the unmanned vending machine management in real time, perform product distribution optimization processing, and generate a dynamic dispatching management plan for unmanned vending machine products.

[0043] Compared with the prior art, the advantages and positive effects of the present invention are:

[0044] In the present invention, by quantitatively predicting the demand for goods and combining historical data and sales rate to optimize the strategy of goods weight, the accuracy and response speed of unmanned vending machine management are effectively improved, the accuracy and efficiency of goods placement are monitored in real time, and deviations are adjusted immediately, which not only ensures the continuity of goods supply, but also improves the compliance of unmanned vending machine operations. By optimizing the placement and sequence of goods, unmanned vending machines can use space more efficiently, reduce the time cost of storing and retrieving goods, and enhance the unmanned vending machine's ability to respond immediately to patient needs. At the same time, it reduces the risk of expired goods and inventory backlogs, further ensuring the effective use of goods and patient safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 is a system flow chart of the present invention;

[0046] Figure 2 This is a flowchart of obtaining comprehensive product data of the present invention;

[0047] Figure 3 A quantitative forecasting flow chart of future demand for the goods of the present invention;

[0048] Figure 4 This is a flow chart for obtaining a product weight list of the present invention;

[0049] Figure 5 A flow chart for determining the quantity of replenished goods types in the present invention;

[0050] Figure 6 This is a flow chart for obtaining the cargo placement task data of the present invention;

[0051] Figure 7 A real-time tracking flow chart for the accuracy and efficiency of goods placement of the present invention;

[0052] Figure 8 This is a flowchart of obtaining the dynamic dispatch management solution for goods of the unmanned vending machine of the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0054] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0055] See also Figure 1 , a cloud computing-based unmanned vending machine goods dispatching and management system includes:

[0056] The product data integration module receives the sales data of the unmanned vending machines, verifies the accuracy and completeness of the information through data cleaning and format standardization, and generates comprehensive product data;

[0057] The commodity demand forecasting and weight determination module performs a trend analysis of commodity demand based on comprehensive commodity data, makes quantitative forecasts of future commodity demand, calculates the weight value of each commodity based on the quantitative forecast results combined with sales rate and historical demand data, and generates a commodity weight list;

[0058] The goods placement task generation module receives the goods weight list, compares it with the set threshold to determine whether to perform inventory replenishment, determines the types and quantities of replenished goods, optimizes the placement position and sequence based on the determination results combined with the unmanned vending machine layout data, updates the task plan, and outputs the goods placement task data;

[0059] The goods scheduling execution monitoring module continuously monitors the goods scheduling process based on the goods placement task data, tracks the accuracy and efficiency of goods placement in real time, identifies execution process deviations based on real-time tracking results, and immediately makes dynamic adjustments to the deviations to generate a dynamic scheduling management plan for unmanned vending machine goods.

[0060] Comprehensive product data includes data integrity indicators, data format standard processing records and data accuracy verification results; the product weight list includes predicted demand, historical demand comparison results and product weight determination results; the product placement task data includes product category index, replenishment quantity calculation results and placement optimization sequence; the dynamic scheduling management plan for unmanned vending machine products includes execution monitoring records, deviation adjustment measures and efficiency optimization measures.

[0061] See also Figure 2 , the steps to obtain comprehensive product data are:

[0062] Receive sales data from unmanned vending machines, merge the data, and generate a preliminary integrated data set;

[0063] Receive sales data from unmanned vending machines in medical institutions. The data sources include but are not limited to patients' diagnostic information, prescription drug records, sales time and quantity. First, unify the format of the received data, such as unifying the date format to YYYY-MM-DD and the drug names to generic names. Then clean the data and remove null values ​​and outliers in the data. For example, records with abnormally high or low sales quantities are treated as input errors and removed. Use the data timestamp to exclude data records with illogical time sequence. After completing a series of processing, a preliminary, cleaned data set is obtained, which provides basic data for subsequent analysis.

[0064] Perform data cleaning on the preliminary integrated data set, delete duplicate records, standardize time and value formats, correct data errors, and obtain the cleaned data set;

[0065] Perform detailed data cleaning operations on the preliminary integrated data set, including deleting duplicate data entries and standardizing the format of each data item, such as converting all time data into a unified format and standardizing the range of all values ​​to meet subsequent processing requirements. In addition, check each item in the data set to ensure data consistency. For example, the name of the product must be consistent in multiple records of the same patient. After completing the steps, a cleaned, more accurate and standardized data set is generated, which will be directly used for the next step of integrity verification and data analysis.

[0066] Perform data validation on the cleaned data set to verify the consistency and completeness of the data and generate comprehensive product data;

[0067] When verifying the consistency and completeness of data, the formula is used:

[0068]

[0069] Verify the consistency and integrity of the data. The cleaned data set contains 10,000 data items, of which 9,950 items have passed the verification and there are no empty data items. The calculation process of the consistency index is as follows:

[0070]

[0071] Similarly, the calculation process of the integrity index is:

[0072]

[0073] It shows that the vast majority of data are consistent and the integrity of the data set is very high, which is crucial for confirming data quality. The consistency index shows that the standardization of the data has achieved the expected results, and the integrity index reflects that no important information has been lost in the data set during the cleaning process.

[0074] See also Figure 3 , the quantitative forecasting steps for future demand for goods are:

[0075] Based on comprehensive product data, conduct time series analysis to determine product sales trends and obtain sales trend analysis results;

[0076] Applying time series analysis to comprehensive product data aims to capture the sales trends and seasonal patterns of products through detailed historical sales data. First, collect and organize the historical sales records of the products, including information such as daily sales volume, sales date, and sales location. Subsequently, preprocess the data to remove outliers and missing data to ensure the accuracy of the analysis. Next, use the autoregressive moving average model (ARMA) or seasonal autoregressive moving average model (SARIMA) to fit the product sales data. The model can predict future sales trends through historical data points. By calculating the goodness of fit and prediction error of the model, the best model is selected for sales forecasting. Generate accurate sales trend analysis results to provide support for product inventory management and market strategies, and achieve effective prediction of product demand.

[0077] Based on the sales trend analysis results, the formula is used:

[0078]

[0079] Calculate the forecast demand for goods in the future period P t , generate quantitative prediction results; where Y t-1 represents the sales volume in period t-1, ΔY t-1 Represents Y t-1 The first-order difference of t-1 -Y t-2 , Y t-2 represents the sales volume in period t-2, and λ is the model sensitivity constant;

[0080] Y t-1 Represents the sales volume of the previous period. The sales volume of the previous period is 2000 units; ΔY t-1 Represents Y t-1 The first-order difference of t-1 -Y t-2 , if Y t-2 is 1800 units, then ΔY t-1 =2000-1800=200 units; λ is a constant used to adjust the sensitivity of the model, which is determined by comparative analysis and has a value of 50.

[0081] Calculation derivation process:

[0082]

[0083] P t =12.6492

[0084] This result shows that the predicted future demand is 12.65 (the unit depends on Y t-1 units), which can be further used for inventory management and demand forecast adjustment.

[0085] Use the quantitative forecast results to conduct validity tests, including residual analysis and forecast accuracy tests, to obtain forecast confirmation results;

[0086] In the step of testing the effectiveness of the forecast results, the key is to ensure that the forecast model used can not only generate accurate forecast values, but also that the values ​​can truly reflect changes in market demand. First, residual analysis is used to evaluate the forecasting performance of the model to check whether the residuals are white noise, that is, there is no autocorrelation between the residuals, indicating that the model has successfully captured all the information in the data and no structural information is missed. Further, a forecast accuracy test is performed, such as calculating the mean absolute error (MAE) and mean square error (MSE) between the forecast value and the actual sales data. The indicators can quantify the accuracy of the model's forecast. According to the test results, adjust the model parameters or switch to different models to improve the forecast accuracy. The final test results will determine the reliability of the quantitative forecast of the future demand for goods and ensure that the forecast data can effectively guide production and inventory decisions.

[0087] See also Figure 4 , the steps to obtain the product weight list are:

[0088] Based on the prediction confirmation results, collect the historical sales rate and demand data of the goods, summarize the data, and output the aggregated data set;

[0089] In the process of collecting and analyzing the quantitative forecast results, historical sales rates and demand data of goods, the quality and integrity of the data set are crucial. The data usually comes from the sales records of unmanned vending machines, including the sales volume, sales revenue and market feedback of each product in the past few years. The cyclical fluctuations and trend changes in product sales can be observed. The data is preprocessed, including cleaning outliers and filling missing values ​​in the data to ensure the accuracy of data analysis. After that, statistical methods are used to conduct in-depth analysis of the data to identify key factors affecting product sales, such as seasonal changes, market activities and competitors' actions. The analysis results can provide more accurate basic data for quantitative forecasting, thereby more effectively planning production and adjusting market strategies, which not only enhances the efficiency of data utilization, but also improves the scientific nature and real-time nature of decision-making.

[0090] According to the aggregated data set, the formula is used:

[0091]

[0092] Calculate the weight value W of each product i , get the product weight value calculation set, where Q i represents the quantitative forecast demand for product i, S i represents the historical sales rate of product i, n represents the total number of product types, and j represents the different product types;

[0093] Q i is the quantitative forecast demand for product i, and the forecast demand for product A is 1500 units; S i is the historical sales rate of product i, the sales rate of product A is 300 units / month; n is the total number of product types, assuming there are 10 different products; assuming the total Q j ·S j The value is 600000 units.

[0094] Calculation derivation process:

[0095]

[0096] W A =0.75

[0097] The results show that product A has a weight of 75% in the total sales volume, which is calculated by combining the predicted demand and historical sales data, reflecting the market importance and priority of product A.

[0098] Based on the calculation set of product weight values, priority sorting is performed to generate a product weight list;

[0099] The calculated weight values ​​of each commodity are organized into a list, which is crucial for the hospital's inventory management and procurement decisions. The list lists the weight values ​​of each commodity in detail, and the priority can be sorted according to the weight value. Hospitals or enterprises can optimize their inventory levels to ensure that high-demand commodities have sufficient inventory and low-demand commodities are not overstocked. In addition, the weight list can also help the marketing team determine promotion priorities and allocate more market resources to high-weight commodities, thereby maximizing sales efficiency and market response. The entire list generation process is based on detailed data analysis, ensuring data support for each decision, thereby making the enterprise resource allocation more reasonable and effectively supporting the overall business strategy of the enterprise.

[0100] See also Figure 5 , the steps to determine the quantity of replenished goods are:

[0101] Import the product weight list through the network interface, count the usage frequency and remaining inventory of each product, reflect the replenishment demand of the product, and generate the preliminary analysis results of the product demand;

[0102] Through the network interface, the system automatically imports a list of product weights from the product management database. Each item in the list records in detail the name, frequency of use and inventory status of the product. The automated data import method not only improves the efficiency of data processing, but also reduces the possibility of human errors, ensuring the accuracy and real-time updating of the data. Relevant data can be used to make more scientific inventory management decisions and effectively balance the supply and demand relationship of unmanned vending machines.

[0103] Compare the preliminary analysis results of product demand with the set inventory replenishment threshold, determine whether the weight of each product exceeds the threshold, decide whether inventory replenishment is needed, and generate a list of products to be replenished;

[0104] The preliminary analysis results of the received product demand will be compared with the preset inventory replenishment threshold. The system will decide whether inventory replenishment is needed by analyzing whether the weight of each product exceeds this threshold. This judgment process is fully automated, ensuring fast and accurate operation. For products that exceed the threshold, the system will mark them as requiring replenishment for further processing, making full use of existing data resources and improving the response speed and accuracy of product management, so as to better meet the needs of patients and ensure the stability of product supply.

[0105] According to the list of goods to be replenished, determine the types and quantities of goods that actually need to be replenished, and simultaneously confirm that the inventory of goods can meet future needs, and generate a list of types and quantities of replenished goods;

[0106] Based on the aforementioned list of goods that need to be replenished, the system automatically counts and determines the types and quantities of each item to be replenished, covering everything from the analysis of the goods list to the formulation of a specific replenishment plan, ensuring that each high-demand item can be replenished to the appropriate inventory level in a timely manner. This process not only optimizes the inventory structure of the unmanned vending machine, but also improves the ability to respond quickly to emergency needs. The final list of types and quantities of replenished goods will provide scientific guidance for the daily operation and management of the unmanned vending machine, ensuring the timeliness and accuracy of product replenishment.

[0107] See also Figure 6 ,The steps to obtain the data of the goods placement task are:

[0108] Receive a list of replenished goods and quantities, combine it with the unmanned vending machine layout data, determine the placement of each item, and generate a preliminary optimization plan for item placement;

[0109] The system receives a list of goods to be replenished from the goods inventory management process. The list details the type of each product and the quantity to be replenished. Based on the layout data of the unmanned vending machine, the system determines the best placement and replenishment order of each product, and adopts path optimization logic. The goal is to reduce the movement distance of unmanned vending machine employees when placing and taking goods. In this way, the system not only optimizes work efficiency, but also improves the operating speed of the unmanned vending machine. The generated preliminary product placement optimization plan provides the unmanned vending machine with a dynamic placement guide adjusted according to the actual layout and frequency of product use.

[0110] Apply the product placement optimization plan to adjust and optimize the unmanned vending machine workflow, automatically update the new placement order and location information, and generate an updated unmanned vending machine task plan;

[0111] The product placement optimization plan is integrated into the task plan of the unmanned vending machine. The process includes re-evaluation and adjustment of the unmanned vending machine's workflow. The system automatically updates the product placement and replenishment sequence information in the unmanned vending machine management system. The synchronous update of information ensures that all operators can access the latest operating guidelines. In addition, the system also conducts process update training for unmanned vending machine employees to ensure that each employee can place goods according to the new operating procedures, thereby ensuring that the operation of the entire unmanned vending machine meets the latest optimization standards.

[0112] Based on the updated unmanned vending machine task plan, formulate the task instructions for placing medicines, determine the placement location, replenishment quantity and operation sequence of each product, and generate the task data for placing goods;

[0113] After the unmanned vending machine task plan is updated, the system automatically converts the new product placement and replenishment tasks into specific execution instructions. The instructions specify in detail the placement and quantity of each product and the specific execution order of the operator. The conversion process ensures the clarity and executability of the instructions. The user interface of the unmanned vending machine management system clearly displays these instructions to the unmanned vending machine staff, allowing daily product replenishment and placement work to be completed efficiently according to the latest guidelines. In this way, the system supports the unmanned vending machines to maintain efficient operation while also improving the response speed to emergency and routine needs.

[0114] See also Figure 7 , the real-time tracking steps for goods placement accuracy and efficiency are:

[0115] Based on the data of the goods placement task, the real-time data stream of the goods scheduling process is monitored and called, the scheduling status and time nodes of the goods are recorded, and real-time goods scheduling data is generated;

[0116] Based on the data of the goods placement tasks, the monitoring software interface is activated, and the real-time data stream is called to integrate the dispatch status and time nodes of the goods. The technologies involved in the data collection process need to explain in detail the accuracy of goods identification and time recording. The identification and location information of each product are accurately tracked to ensure the integrity and reliability of the data. The dispatch efficiency of the goods is analyzed in real time. After being screened and optimized, the data is used to update the monitoring dashboard. The monitoring dashboard displays the real-time flow of goods and the time delays that may occur during the dispatch process to ensure the efficiency and accuracy of medical management. The data processing involved in this process includes but is not limited to time series analysis, data screening, and the realization of real-time update mechanisms to optimize the circulation and storage management of goods in a data-driven manner.

[0117] Analyze real-time cargo dispatch data, evaluate the accuracy and efficiency of cargo placement, record the accuracy and time required for cargo placement, and generate cargo placement performance evaluation reports;

[0118] The accuracy and efficiency of product placement is evaluated through location data using the formula:

[0119]

[0120] Among them, x and y represent the current coordinates of the goods, which are taken from the real-time goods dispatch data. 0 and 0 Represents the preset placement coordinates of the goods. The coordinates are specified in the goods placement plan. The placement deviation is calculated by comparing the difference between the actual position and the preset position. The deviation value Δ is calculated by interpolating the actual coordinate data: x=5, y=5 and the preset coordinate data: x 0 =3,y 0 =4, we can calculate:

[0121]

[0122] The results show that the placement of the goods deviates from the preset position by 2.236 units. This value is used to evaluate the accuracy of goods placement. A higher deviation value may indicate the need to optimize the placement strategy or adjust the accuracy of the placement machine. This is a specific value obtained through real-time data monitoring and analysis. It not only reflects the accuracy of goods placement, but also serves as the basis for future adjustment strategies.

[0123] Based on the product placement performance evaluation report, the monitoring data is continuously updated to display the efficiency and accuracy of product scheduling in real time, and output real-time tracking product placement data;

[0124] According to the product placement performance evaluation report, the process of updating the monitoring dashboard requires a detailed analysis of the correlation between product scheduling data and product placement efficiency. The design of the monitoring dashboard needs to include indicators of time efficiency and placement accuracy of product scheduling. The indicators are obtained from the product placement performance evaluation report. The data points provided by the report include the deviation value between the real-time location of the product and the preset location, as well as the circulation speed of the product. The data update mechanism needs to be able to process a large amount of data entering in real time and convert this data into charts and indicators so that medical staff can intuitively understand the real-time status and historical performance of the product. The update strategy includes but is not limited to selecting appropriate data visualization tools and techniques to ensure accurate data transmission and visualization. In addition, the monitoring dashboard must be able to reflect any abnormalities in the scheduling process in real time for rapid response and adjustment, so as to provide a scientific basis for the management of unmanned vending machines with a data-driven decision support system.

[0125] See also Figure 8 ,The steps to obtain the dynamic scheduling management plan for unmanned vending machine goods are:

[0126] According to the real-time tracking of goods placement data, the placement position deviation and time deviation of each product are counted, and deviation statistical records are generated;

[0127] Based on the real-time tracking of the goods placement data, the placement position deviation and time deviation of each goods are identified and recorded. The process includes obtaining a continuous position data stream from the goods management system. The data stream contains the specific coordinates of each goods at each time point. Whenever the deviation between the actual position of the goods and the preset position exceeds the set threshold, the system automatically marks it as an abnormality and records it in the deviation report. This report lists the specific placement deviation data of all goods in detail. These data are the difference values ​​between the goods location coordinates and the preset location coordinates.

[0128] Utilize deviation statistics to optimize the goods dispatch path and schedule, adjust the goods circulation efficiency, and generate an adjusted goods dispatch plan;

[0129] Use deviation statistical records to re-optimize the dispatch path and schedule of goods based on the data in the report. The process includes optimizing the circulation path of each product, determining the new shortest or optimal path, and adjusting the schedule to reduce overall delivery delays and increase efficiency. Consider the real-time nature of the circulation of goods and the predetermined time frame to minimize deviations in time and space, generate an adjusted goods dispatch plan, ensure that the goods dispatch logic is updated synchronously with the actual situation, and use it to guide subsequent goods distribution activities.

[0130] Apply the adjusted product dispatch plan, update the unmanned vending machine management in real time, perform product distribution optimization, and generate a dynamic dispatch management plan for unmanned vending machine products;

[0131] Apply the adjusted product scheduling plan, upload the new scheduling plan to the unmanned vending machine management system, and update the product circulation path and delivery schedule in the system. This operation ensures that the delivery of each product is carried out according to the latest scheduling plan, thereby optimizing the efficiency and accuracy of product delivery. After the management plan is updated, the system automatically notifies relevant personnel to review and implement it, ensuring that the execution of the scheduling plan is closely linked to the demand and supply of goods. Through this dynamic update mechanism, the unmanned vending machine can quickly respond to any changes in the product supply chain and maintain the continuity and effectiveness of the product supply. The final unmanned vending machine product dynamic scheduling management plan realizes efficient product distribution and precise inventory control, providing strong support for the daily operation of the unmanned vending machine.

[0132] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A cloud computing-based unmanned vending machine product dispatching and management system, characterized in that: The system comprises: The product data integration module receives the sales data of the unmanned vending machines, verifies the accuracy and completeness of the information through data cleaning and format standardization, and generates comprehensive product data; The product demand forecasting and weight determination module performs a trend analysis of product demand based on the comprehensive product data, performs a quantitative forecast of future product demand, calculates a weight value for each product based on the quantitative forecast result combined with the sales rate and historical demand data, and generates a product weight list; The goods placement task generation module receives the goods weight list, determines whether to perform inventory replenishment according to the set threshold, determines the types and quantities of replenished goods, optimizes the placement position and sequence according to the determination result combined with the unmanned vending machine layout data, updates the task plan, and outputs the goods placement task data; The goods scheduling execution monitoring module continuously monitors the goods scheduling process based on the goods placement task data, tracks the accuracy and efficiency of goods placement in real time, identifies execution process deviations according to the real-time tracking results, and dynamically adjusts the deviations immediately to generate a dynamic scheduling management plan for unmanned vending machine goods.

2. The cloud computing-based unmanned vending machine product dispatching and management system according to claim 1, characterized in that: The steps for obtaining the comprehensive product data are as follows: Receive sales data from unmanned vending machines, merge the data, and generate a preliminary integrated data set; Performing data cleaning on the preliminary integrated data set, deleting duplicate records, standardizing time and value formats, and correcting data errors to obtain a cleaned data set; The cleaned data set is subjected to data verification to verify the consistency and completeness of the data and generate comprehensive commodity data.

3. The cloud computing-based unmanned vending machine product dispatching and management system according to claim 2, characterized in that: The steps for quantitatively predicting the future demand for the goods are: Based on the comprehensive product data, time series analysis is performed to determine product sales trends and obtain sales trend analysis results; Based on the sales trend analysis results, the formula is adopted: Calculate the forecast demand for goods in the future period P t , generate quantitative prediction results; where Y t-1 represents the sales volume in period t-1, ΔY t-1 Represents Y t-1 The first-order difference of t-2 represents the sales volume in period t-2, and λ is the model sensitivity constant; The quantitative prediction results are used to perform validity tests, including residual analysis and prediction accuracy tests, to obtain prediction confirmation results.

4. The cloud computing-based unmanned vending machine product dispatching and management system according to claim 3, characterized in that: The steps for obtaining the commodity weight list are as follows: Based on the prediction confirmation results, collect historical sales rate and demand data of the goods, aggregate the data, and output a converged data set; Based on the aggregated data set, the formula is adopted: Calculate the weight value W of each product i , get the product weight value calculation set, where Q i represents the quantitative forecast demand for product i, S i represents the historical sales rate of product i, n represents the total number of product types, and j represents the different product types; Based on the product weight value calculation set, priority sorting is performed to generate a product weight list.

5. The cloud computing-based unmanned vending machine product dispatching and management system according to claim 4, characterized in that: The steps for determining the quantity of the replenishment product types are as follows: Import the commodity weight list through the network interface, count the usage frequency and remaining inventory of each commodity, reflect the replenishment demand of the commodity, and generate preliminary analysis results of the commodity demand; Compare the preliminary analysis results of the product demand with the set inventory replenishment threshold, determine whether the weight of each product exceeds the threshold, decide whether inventory replenishment needs to be performed, and generate a list of products to be replenished; Based on the list of goods to be replenished, determine the types and quantities of goods that actually need to be replenished, simultaneously confirm that the goods inventory can meet future needs, and generate a list of types and quantities of replenished goods.

6. The cloud computing-based unmanned vending machine product dispatching and management system according to claim 5, characterized in that: The steps for obtaining the cargo placement task data are as follows: Receive the list of types and quantities of the supplementary goods, determine the placement of each product based on the unmanned vending machine layout data, and generate a preliminary product placement optimization plan; Apply the product placement optimization solution to adjust and optimize the unmanned vending machine workflow, automatically update the new product placement sequence and location information, and generate an updated unmanned vending machine task plan; Based on the updated unmanned vending machine task plan, formulate medicine placement task instructions, determine the placement location, replenishment quantity and operation sequence of each product, and generate goods placement task data.

7. The cloud computing-based unmanned vending machine product dispatching and management system according to claim 6, characterized in that: The steps for real-time tracking of the accuracy and efficiency of goods placement are: Based on the cargo placement task data, real-time cargo scheduling data is generated by monitoring the real-time data stream of the cargo scheduling process, recording the scheduling status and time nodes of the cargo; Analyze the real-time cargo scheduling data, evaluate the accuracy and efficiency of cargo placement, record the accuracy and time required for cargo placement, and generate a cargo placement performance evaluation report; According to the goods placement performance evaluation report, the monitoring data is continuously updated, the goods scheduling efficiency and accuracy are displayed in real time, and the real-time tracking goods placement data is output.

8. The cloud computing-based unmanned vending machine product dispatching and management system according to claim 7, characterized in that: The steps for obtaining the dynamic dispatch management plan for goods in the unmanned vending machine are as follows: According to the real-time tracked goods placement data, count the placement position deviation and time deviation of each goods, and generate deviation statistical records; Utilizing the deviation statistical records, optimizing the goods dispatch path and schedule, adjusting the goods circulation efficiency, and generating an adjusted goods dispatch plan; The adjusted product dispatching plan is applied to update the unmanned vending machine management in real time, perform product distribution optimization processing, and generate a dynamic dispatching management plan for unmanned vending machine products.

Images