Full-automatic medicine sorting and dispatching management system and management method

Abstract

The invention discloses a full-automatic medicine sorting and dispatching management system and method, and relates to the technical field of medicine sorting and dispatching management, and the system comprises an obtaining module which is connected with a production end, an inventory end and a sales end, and obtains the production data, inventory data and sales data of medicines; the library transfer prediction module is connected with the acquisition module and predicts the library transfer quantity according to the production data; the demand prediction module is connected with the acquisition module and predicts demand quantity according to the sales data; and the inventory optimization module is connected with the acquisition module, the transfer prediction module and the demand prediction module, and sets a sorting scheduling management and optimization scheme according to the transfer quantity, the demand quantity and the inventory data of the medicines. According to the invention, efficient and accurate drug sorting scheduling and inventory optimization can be realized based on the data of the production end, the inventory end and the sales end.

Description

Technical Field

[0001] The present invention relates to the technical field of medicine sorting and dispatching management, and in particular to a full-automatic medicine sorting and dispatching management system and a management method. Background Art

[0002] With the rapid development of the pharmaceutical industry and the intensification of market competition, the production and sales of drugs are facing increasingly higher efficiency requirements. In order to ensure that drugs can be transferred from the production end to the sales end in a timely and accurate manner and finally reach the hands of consumers, efficient inventory management and logistics scheduling have become particularly important. Traditional drug sorting and scheduling management relies on manual operation and experience judgment, which is not only inefficient, but also prone to errors, leading to problems such as inventory backlogs or out-of-stock.

[0003] In recent years, the development of information technology has brought new opportunities for pharmaceutical supply chain management. By integrating advanced data collection, processing and analysis technologies, real-time monitoring and intelligent analysis of pharmaceutical production, inventory and sales data can be achieved. However, the existing system still has shortcomings in the following aspects: Data silos: Data from production, inventory, and sales are often scattered across different systems and lack effective integration, leading to information opacity and delayed decision-making.

[0004] Low forecasting accuracy: Many systems rely on simple statistical methods to forecast demand and warehouse transfer volume, and fail to fully consider complex factors such as seasonal changes and market activities, resulting in large deviations in forecast results.

[0005] Insufficient inventory optimization: Traditional methods make it difficult to dynamically adjust inventory levels to respond to changes in market demand, which can easily lead to excess or shortage of inventory.

[0006] Low degree of automation: Although the existing system has achieved partial automation, it still requires a lot of manual intervention in sorting scheduling and inventory optimization, which reduces the overall efficiency.

[0007] In view of this, it is necessary to improve the existing drug sorting and scheduling management system and management method. Summary of the invention

[0008] The present invention aims to solve one of the technical problems in the prior art to at least a certain extent. By proposing a fully automatic drug sorting and scheduling management system and management method, it is possible to achieve efficient and accurate drug sorting and scheduling and inventory optimization based on data from the production end, inventory end and sales end.

[0009] To achieve the above objectives, in the first aspect, the present application provides a fully automatic drug sorting and scheduling management system, based on the production end, the inventory end and the sales end, including: The acquisition module is connected to the production end, the inventory end and the sales end to respectively acquire the production data of the drug, the inventory data of the drug and the sales data of the drug; A warehouse transfer prediction module, connected to the acquisition module, predicts the warehouse transfer amount based on production data; A demand forecasting module, connected to the acquisition module, forecasting demand based on sales data; The inventory optimization module is connected with the acquisition module, the warehouse transfer prediction module and the demand prediction module, and sets the sorting scheduling management and optimization plan according to the warehouse transfer quantity, the demand quantity and the inventory data of the medicine.

[0010] Furthermore, the acquisition module includes: The synchronization unit is used to set a timed task to periodically obtain drug production data, drug inventory data, and drug sales data from the production end, inventory end, and sales end; The preprocessing unit preprocesses the acquired data, including data cleaning and formatting.

[0011] Furthermore, the warehouse transfer prediction module includes: A data extraction unit extracts the production data value of the drug within a period, as well as the actual number of warehouse transfers and the actual warehouse transfer cycle; The first prediction unit uses the ARIMA model to predict the average warehouse transfer volume during the period; The correction unit corrects the average warehouse transfer volume of the period according to the seasonal influence trend parameter to obtain the production data predicted warehouse transfer volume.

[0012] Furthermore, the first prediction unit uses the ARIMA model to predict the average warehouse transfer volume during the period, specifically including: Automatically search for the best p, d, q values ​​using the AIC / BIC criteria, where p is the number of autoregressive terms, d is the number of differences, and q is the number of moving average terms; The ARIMA model is fitted using the selected parameters to predict the value of warehouse transfer quantity.

[0013] Furthermore, the correction unit corrects the period average warehouse transfer quantity according to the seasonal influence trend parameter to obtain the production data predicted warehouse transfer quantity, specifically including: Introducing the seasonal impact trend parameter S(t), where the seasonal impact trend parameter S(t) is expressed as a multiplication correction coefficient, the production data forecast transfer quantity is expressed as: In the formula, is the corrected transfer quantity; It is the predicted value of warehouse transfer output by ARIMA model; Correction coefficient of seasonal influence on trend parameter; T1 is the average sales data of all years in the corresponding month in monthly units, T: the average daily sales value of the corresponding month; float(T): the total average of all monthly averages.

[0014] Furthermore, the demand forecasting module includes: A data determination unit, which determines the factors affecting the sales data; A framework unit is used to construct a prediction model of the relationship between the influencing factors and the sales data, and the prediction model described by the ARMA algorithm is used for correction; The second prediction unit obtains sales data prediction demand based on the prediction model.

[0015] Furthermore, the data determination unit determines the influencing factors of the sales data, including: Use Pearson's correlation coefficient to determine the correlation parameter with sales volume in the sales data of drugs; The correlation parameter with the greatest impact on sales volume is selected as the influencing factor.

[0016] Furthermore, the framework unit constructs a prediction model of the relationship between the influencing factors and the sales data, and uses the ARMA algorithm to modify the prediction model, including: Construct a predictive model of the relationship between influencing factors and sales data: ; Where, X 1 ,X 2 ,...,X n is the impact factor, is the regression coefficient; The ARMA model is used to correct the residuals of the forecast model: ; In the formula, is the basic prediction function of the prediction model, is the error correction term generated by the ARMA model.

[0017] Furthermore, a sorting scheduling management and optimization plan is set according to the transfer quantity, the demand quantity and the inventory data of the medicine, including: The dynamic inventory adjustment model is: ; In the formula, is the new inventory level, is the current inventory level, V is the predicted transfer volume, is the predicted demand; Use heuristic algorithms or optimization algorithms to determine the optimal sorting order and generate priority sorting rules.

[0018] In a second aspect, the present application also provides a fully automatic drug sorting and scheduling management method, comprising: S100: Obtaining drug production data, drug inventory data, and drug sales data respectively; S200: Predict the amount of warehouse transfer based on production data; S300: forecast demand based on sales data; S400: Setting a sorting scheduling management and optimization plan according to the warehouse transfer quantity, the demand quantity and the inventory data of the medicines.

[0019] Beneficial effects of the invention: Compared with the prior art, the present invention provides a fully automatic drug sorting and scheduling management system and management method, which can realize efficient and accurate drug sorting and scheduling and inventory optimization based on the data of the production end, the inventory end and the sales end. The specific beneficial effects are: (1) The present invention can automatically collect the latest data from each endpoint at a regular interval to ensure the real-time and consistency of information, clean and format the data, improve data quality, and reduce the impact of errors and outliers; (2) The present invention predicts the average warehouse transfer volume based on the ARIMA model and further improves the prediction accuracy through seasonal correction; (3) The present invention uses the Pearson correlation coefficient to identify key influencing factors, constructs a multivariate linear regression model, and uses the ARMA model to correct the residuals to improve the accuracy of demand forecasting; (4) The present invention formulates a reasonable sorting and scheduling plan based on the predicted transfer volume and demand volume, combined with the current inventory data, to achieve dynamic adjustment of inventory levels, and provide a scientific basis to support managers in making more intelligent decisions. Highly automated data processing and predictive analysis reduce the need for manual operations, improve overall operational efficiency, reduce dependence on human resources, reduce labor costs, and reduce the occurrence of human errors.

[0020] (5) The present invention ensures timely supply of drugs, meets customer needs, improves customer satisfaction, monitors drug production and inventory, ensures drug quality and safety, and enhances customer trust through accurate demand forecasting and efficient inventory management.

[0021] In summary, the present invention significantly improves the overall performance of the pharmaceutical supply chain through efficient data integration, accurate forecasting analysis and intelligent inventory optimization, which is conducive to bringing higher economic benefits and market competitiveness to enterprises. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1A principle block diagram of a fully automatic medicine sorting and scheduling management system provided by the present invention; Figure 2 A flowchart of the steps of a fully automatic drug sorting and scheduling management method provided by the present invention; DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] Example 1, please refer to Figure 1 As shown, the present application provides a fully automatic drug sorting and scheduling management system, based on the production end, inventory end and sales end, including: The acquisition module is connected to the production end, the inventory end and the sales end to respectively acquire the production data of the drug, the inventory data of the drug and the sales data of the drug; A warehouse transfer prediction module, connected to the acquisition module, predicts the warehouse transfer amount based on production data; A demand forecasting module, connected to the acquisition module, forecasting demand based on sales data; The inventory optimization module is connected with the acquisition module, the warehouse transfer prediction module and the demand prediction module, and sets the sorting scheduling management and optimization plan according to the warehouse transfer quantity, the demand quantity and the inventory data of the medicine.

[0025] In the specific implementation process, the acquisition module includes: The synchronization unit is used to set a timed task to periodically obtain drug production data, drug inventory data, and drug sales data from the production end, inventory end, and sales end; The preprocessing unit preprocesses the acquired data, including data cleaning and formatting.

[0026] Specifically, the synchronization unit must also ensure that the data interfaces with the production, inventory, and sales ends are standardized and support real-time or periodic data exchange.

[0027] Specifically, the preprocessing unit preprocesses the acquired data, including data cleaning and formatting such as removing invalid data and filling missing values, to ensure data quality.

[0028] Specifically, through the acquisition module, the system can automatically collect the latest data from the production, inventory and sales ends at regular intervals to ensure the timeliness and consistency of the information.

[0029] In the specific implementation process, the warehouse transfer prediction module includes: A data extraction unit extracts the production data value of the drug within a period, as well as the actual number of warehouse transfers and the actual warehouse transfer cycle; The first prediction unit uses the ARIMA model to predict the average warehouse transfer volume during the period; The correction unit corrects the average warehouse transfer volume of the period according to the seasonal influence trend parameter to obtain the production data predicted warehouse transfer volume.

[0030] Specifically, the warehouse transfer prediction module continuously adjusts the parameters (p, d, q) of the ARIMA model through historical data to achieve the best prediction effect, while considering obvious seasonal changes and incorporating seasonal components into the prediction model.

[0031] Specifically, the first prediction unit uses the ARIMA model to predict the average warehouse transfer volume during the period, including: Automatically search for the best p, d, q values ​​using the AIC / BIC criteria, where p is the number of autoregressive terms, d is the number of differences, and q is the number of moving average terms; The ARIMA model is fitted using the selected parameters to predict the value of warehouse transfer quantity.

[0032] Specifically, the correction unit corrects the cycle average warehouse transfer quantity prediction value according to the seasonal influence trend parameter to obtain the production data predicted warehouse transfer quantity, specifically including: Introducing the seasonal impact trend parameter S(t), where the seasonal impact trend parameter S(t) is expressed as a multiplication correction coefficient, the production data forecast transfer quantity is expressed as: In the formula, is the corrected transfer quantity; It is the predicted value of warehouse transfer output by ARIMA model; Correction coefficient of seasonal influence on trend parameter; T1 is the average sales data of all years in the corresponding month in monthly units, T: the average daily sales value of the corresponding month; float(T): the total average of all monthly averages.

[0033] Specifically, the first prediction unit uses the ARIMA model to predict the average inventory transfer volume during the period, and automatically searches for the optimal parameters through the AIC / BIC criterion, thereby improving the accuracy and reliability of the prediction.

[0034] Specifically, the correction unit introduces the seasonal influence trend parameter S(t) to adjust the prediction results, which further improves the prediction accuracy and makes the warehouse transfer volume prediction more in line with the actual situation.

[0035] In the specific implementation process, the demand forecasting module includes: A data determination unit, which determines the factors affecting the sales data; A framework unit is used to construct a prediction model of the relationship between the influencing factors and the sales data, and the prediction model described by the ARMA algorithm is used for correction; The second prediction unit obtains sales data prediction demand based on the prediction model.

[0036] Specifically, the data determination unit determines the influencing factors of the sales data, including: Use Pearson's correlation coefficient to determine the correlation parameter with sales volume in the sales data of drugs; The correlation parameter with the greatest impact on sales volume is selected as the influencing factor.

[0037] Specifically, in addition to conventional time series and seasonal factor analysis, other factors that may affect sales should also be considered, such as market trends, competitor behavior, etc.

[0038] Specifically, determine the drug's sales data, prices, promotion records, holiday information, etc.

[0039] Use the Pearson correlation coefficient (a statistical method) to determine which factors are significantly correlated with sales. For example, you can calculate the correlation coefficient between price changes, promotions, holidays, etc. and sales.

[0040] According to the results of correlation analysis, several factors that have the greatest impact on sales volume are selected as input variables of the model.

[0041] If there is a linear relationship between the influencing factors and sales volume, a multiple linear regression model can be used.

[0042] Specifically, a prediction model for the relationship between influencing factors and sales data is constructed: ; Where, X 1 ,X 2 ,...,X n is the impact factor, is the regression coefficient; The ARMA(p, q) model is established based on the residuals of the basic forecasting model. The ARMA model can help capture the time series characteristics that are not explained by the basic model. AR part (autoregression): captures the autocorrelation in the time series. MA part (moving average): captures the random shocks in the time series.

[0043] The ARMA model is used to correct the residuals of the forecast model: ; In the formula, is the basic prediction function of the prediction model, It is the error correction term generated by the ARMA model.

[0044] Specifically, the data determination unit uses the Pearson correlation coefficient to identify key influencing factors, and the construction unit establishes a multiple linear regression model based on these factors, comprehensively considering the influence of various factors on sales data.

[0045] Specifically, the second prediction unit uses the ARMA model to correct the residuals of the basic prediction model, further improving the accuracy of demand prediction and reducing the prediction error.

[0046] Specifically, it also includes: using a part of historical data as a test set, comparing the predicted values with the actual values, and evaluating the accuracy of the model. Commonly used evaluation indicators include mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), etc. Finally, as new data accumulates, the model parameters are updated regularly to maintain the accuracy and adaptability of the model.

[0047] Specifically, based on the above technical solution, this embodiment constructs a demand prediction model that comprehensively considers various influencing factors, and further improves the prediction accuracy through the ARMA model. This can help the fully automatic drug sorting and scheduling management system more accurately predict future demand, thereby optimizing inventory management and scheduling decisions.

[0048] In the specific implementation process, the inventory optimization module sets the sorting, scheduling management and optimization plan according to the transfer volume, the demand volume and the inventory data of drugs, including: The dynamic inventory adjustment model is: ; In the formula, is the new inventory level, is the current inventory level, V is the predicted transfer volume, is the predicted demand volume; Specifically, the dynamic adjustment strategy includes: When the demand volume increases, accelerate the transfer speed and increase the transfer volume to ensure that the inventory can meet the market demand.

[0049] When the demand volume decreases, appropriately slow down the transfer speed and reduce the transfer volume to save logistics costs and storage costs.

[0050] Ensure that the inventory level is not lower than the safety inventory level to avoid losses caused by out-of-stock.

[0051] Specifically, if <Ss, it is necessary to increase the transfer volume to ensure that the inventory reaches the safety level (Ss is the safety inventory level).

[0052] Specifically, if >Ss, the transfer volume can be appropriately reduced to avoid excessive inventory (Ss is the safety stock level).

[0053] Specifically, it also includes cost-benefit analysis: Define the total cost function, including logistics cost, storage cost, and out-of-stock cost.

[0054] ; In the formula, is the unit transfer cost, is the unit storage cost, is the unit stock-out cost, is the current inventory level, is the predicted demand, V is the predicted transfer volume, is to minimize the total cost.

[0055] In the specific implementation process, priority rules: set sorting priorities based on factors such as the shelf life of the drug and the urgency of demand. Prioritize drugs with a shorter shelf life and drugs with higher demand.

[0056] Specifically, a heuristic algorithm (such as a greedy algorithm) or an optimization algorithm (such as linear programming) can be used to determine the optimal sorting order.

[0057] Specifically, a path optimization algorithm (such as Dijkstra algorithm, A* algorithm) is used to determine the shortest or most efficient sorting path to reduce sorting time and cost.

[0058] Specifically, sorting tasks can be reasonably allocated according to the capabilities of the sorting equipment and the complexity of the tasks to improve overall efficiency.

[0059] Example 2, please refer to Figure 2 As shown, the present application also provides a fully automatic drug sorting and scheduling management method, including S100: Obtaining drug production data, drug inventory data, and drug sales data respectively; S200: Predict the amount of warehouse transfer based on production data; S300: forecast demand based on sales data; S400: Setting a sorting scheduling management and optimization plan according to the warehouse transfer quantity, the demand quantity and the inventory data of the medicines.

[0060] Specifically, the present application provides a fully automatic drug sorting and scheduling management system and management method, which can efficiently manage the sorting and scheduling of drugs, optimize inventory levels, reduce costs, and improve the overall performance of the supply chain.

[0061] In the embodiments provided in the present application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of systems, modules and units can be electrical, mechanical or other forms.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A fully automatic drug sorting and scheduling management system based on the production end, inventory end and sales end, characterized in that: include: The acquisition module is connected to the production end, the inventory end and the sales end to respectively acquire the production data of the drug, the inventory data of the drug and the sales data of the drug; A warehouse transfer prediction module, connected to the acquisition module, predicts the warehouse transfer amount based on production data; A demand forecasting module, connected to the acquisition module, forecasting demand based on sales data; The inventory optimization module is connected with the acquisition module, the warehouse transfer prediction module and the demand prediction module, and sets the sorting scheduling management and optimization plan according to the warehouse transfer quantity, the demand quantity and the inventory data of the medicine.

2. A fully automatic medicine sorting and dispatching management system according to claim 1, characterized in that: The acquisition module comprises: The synchronization unit is used to set a timed task to periodically obtain drug production data, drug inventory data, and drug sales data from the production end, inventory end, and sales end; The preprocessing unit preprocesses the acquired data, including data cleaning and formatting.

3. The fully automatic drug sorting and dispatching management system according to claim 1 is characterized in that: The warehouse transfer prediction module includes: A data extraction unit extracts the production data value of the drug within a period, as well as the actual number of warehouse transfers and the actual warehouse transfer cycle; The first prediction unit uses the ARIMA model to predict the average warehouse transfer volume during the period; The correction unit corrects the average warehouse transfer volume of the period according to the seasonal influence trend parameter to obtain the production data predicted warehouse transfer volume.

4. A fully automatic medicine sorting and dispatching management system according to claim 3, characterized in that: The first prediction unit uses the ARIMA model to predict the average warehouse transfer volume during the period, specifically including: Automatically search for the best p, d, q values ​​using the AIC / BIC criteria, where p is the number of autoregressive terms, d is the number of differences, and q is the number of moving average terms; The ARIMA model is fitted using the selected parameters to predict the value of warehouse transfer quantity.

5. The fully automatic medicine sorting and dispatching management system according to claim 3 is characterized in that: The correction unit corrects the average warehouse transfer volume of the period according to the seasonal influence trend parameter to obtain the production data predicted warehouse transfer volume, specifically including: Introducing the seasonal impact trend parameter S(t), where the seasonal impact trend parameter S(t) is expressed as a multiplication correction coefficient, the production data forecast transfer quantity is expressed as: In the formula, is the corrected transfer quantity; It is the predicted value of warehouse transfer output by ARIMA model; Correction coefficient of seasonal influence on trend parameter; T1 is the average sales data of all years in the corresponding month in monthly units, T: the average daily sales value of the corresponding month; float(T): the total average of all monthly averages.

6. The fully automatic medicine sorting and dispatching management system according to claim 1 is characterized in that: The demand forecasting module comprises: A data determination unit, which determines the factors affecting the sales data; A framework unit is used to construct a prediction model of the relationship between the influencing factors and the sales data, and the prediction model described by the ARMA algorithm is used for correction; The second prediction unit obtains sales data prediction demand based on the prediction model.

7. A fully automatic medicine sorting and dispatching management system according to claim 6, characterized in that: The data determination unit determines the factors affecting the sales data, including: Use Pearson's correlation coefficient to determine the correlation parameter with sales volume in the sales data of drugs; The correlation parameter with the greatest impact on sales volume is selected as the influencing factor.

8. The fully automatic medicine sorting and dispatching management system according to claim 6 is characterized in that: The framework unit constructs a prediction model of the relationship between the influencing factors and the sales data, and uses the ARMA algorithm to modify the prediction model, including: Construct a predictive model of the relationship between influencing factors and sales data: ； Where X1, X2, ..., X n is the impact factor, is the regression coefficient; The ARMA model is used to correct the residuals of the forecast model: ； In the formula, is the basic prediction function of the prediction model, is the error correction term generated by the ARMA model.

9. The fully automatic medicine sorting and dispatching management system according to claim 1 is characterized in that: The sorting scheduling management and optimization plan is set according to the transfer quantity, the demand quantity and the inventory data of the medicine, including: The dynamic inventory adjustment model is: ； In the formula, is the new inventory level, is the current inventory level, V is the predicted transfer volume, is the predicted demand; Use heuristic algorithms or optimization algorithms to determine the optimal sorting order and generate priority sorting rules.

10. A fully automatic drug sorting and scheduling management method using the fully automatic drug sorting and scheduling management system according to any one of claims 1 to 9, characterized in that: include S100: Obtaining drug production data, drug inventory data, and drug sales data respectively; S200: Predict the amount of warehouse transfer based on production data; S300: forecast demand based on sales data; S400: Setting a sorting scheduling management and optimization plan according to the transfer quantity, the demand quantity and the inventory data of the medicines.

Images