Demand degree and inventory optimization-based pharmaceutical data dynamic management method and system

Abstract

The invention provides a demand degree and inventory optimization-based medicine data dynamic management method and system, and relates to the technical field of medicine data management. The method comprises the following steps: firstly, acquiring consumption time series data, inventory time series data and environmental factor time series data of a target medicine set, and fusing the data to generate medicine dynamic collaboration data; secondly, calculating a corresponding real-time demand degree in a target medicine set based on the medicine dynamic collaboration data; according to the real-time demand degree, dynamically generating a dynamic safety inventory benchmark; the real-time demand degree is coupled with the real-time safety inventory benchmark of the corresponding target medicine, and a dynamic inventory control line is generated; and finally, updating and managing the inventory data of the target medicine set according to the dynamic inventory management and control line. According to the technical scheme provided by the invention, closed-loop intelligent inventory management from environment perception to automatic replenishment execution is realized.

Description

Technical Field

[0001] This application relates to the field of pharmaceutical data management technology, and in particular to a method and system for dynamic management of pharmaceutical data based on demand and inventory optimization. Background Technology

[0002] In medical institutions, regional drug distribution centers, and public health emergency supplies reserve systems, the inventory management of pharmaceuticals faces dynamic and complex challenges. Drug consumption is not only affected by routine medical activities, but also closely related to seasonal epidemics, public health emergencies, and regional environmental factors such as temperature, humidity, and air quality, resulting in unstable and sudden fluctuations in demand.

[0003] Currently, a representative approach is a statistical forecasting model based on historical consumption time-series data. This approach analyzes the consumption data of a specific drug over a period of time to establish a time-series forecasting model, such as the ARIMA model, to predict the demand in the future. Based on this forecast, a fixed safety stock level or replenishment point is set. It mainly relies on the historical consumption patterns of the drug itself for extrapolation, aiming to achieve preliminary quantitative management of inventory levels.

[0004] However, this existing approach still has significant shortcomings. The core input data of its predictive model is limited to the historical consumption sequence of the drug itself, and it fails to effectively incorporate dynamic environmental factors closely related to the occurrence and spread of diseases, such as climate and pollutant concentrations. This makes the model unable to perceive and respond to demand surges or declines caused by sudden changes in the external environment. When dealing with seasonal epidemics or public health emergencies, the prediction results will lag far behind actual demand changes. In addition, the model generates a relatively static prediction value and inventory threshold, lacking a mechanism to dynamically and adaptively adjust inventory benchmarks and management strategies based on the urgency and volatility of real-time demand, which can easily lead to shortages of key drugs or stockpiles of non-urgent drugs. Summary of the Invention

[0005] This application provides a dynamic management method and system for pharmaceutical data based on demand and inventory optimization, which solves the problem in the prior art that pharmaceutical inventory management lacks adaptability and accuracy when facing environmentally driven demand fluctuations due to the single data dimension, lagging model response and static and rigid strategies.

[0006] Firstly, this application provides a dynamic management method for pharmaceutical data based on demand and inventory optimization, including:

[0007] Acquire time-series data on consumption and inventory of a target set of pharmaceutical products within a set historical period in the target region, as well as time-series data on environmental factors related to disease occurrence within the target region;

[0008] The consumption time-series data, the inventory time-series data, and the environmental factor time-series data are fused to generate dynamic collaborative data for pharmaceuticals.

[0009] Based on the aforementioned dynamic collaborative data of pharmaceuticals, the real-time demand level corresponding to each target pharmaceutical in the target pharmaceutical set is calculated.

[0010] Based on the real-time demand, a dynamic safety stock baseline for the corresponding target pharmaceutical products is dynamically generated.

[0011] The real-time demand level is coupled with the real-time safety stock benchmark of the corresponding target pharmaceutical product to generate a dynamic inventory control line;

[0012] Based on the aforementioned dynamic inventory control line, the inventory data of the target pharmaceutical product set is updated and managed.

[0013] Optionally, the consumption time-series data, the inventory time-series data, and the environmental factor time-series data are fused to generate dynamic collaborative data for pharmaceuticals, including:

[0014] By analyzing the time-series data of the consumption, the consumption rate variation pattern of the target pharmaceutical product set can be obtained;

[0015] By analyzing the time-series data of the inventory levels, the process of inventory level changes of the target pharmaceutical product set can be obtained;

[0016] Analyze the time-series data of the environmental factors to identify key environmental factors and their fluctuation information;

[0017] Establish the correlation between the fluctuation information of the key environmental factors and the changing pattern of the consumption rate;

[0018] Based on the aforementioned correlation, the consumption rate change pattern, the inventory level change process, and the fluctuation information of the key environmental factors are fused to generate dynamic collaborative data for pharmaceuticals.

[0019] Optionally, based on the dynamic collaborative data of pharmaceuticals, the real-time demand level corresponding to each target pharmaceutical in the target pharmaceutical set is calculated, including:

[0020] From the dynamic collaborative data of pharmaceutical products, extract the historical consumption rate change pattern, historical inventory level change process, and historical fluctuation information of key environmental factors for each target pharmaceutical product in the target pharmaceutical product set, and the historical correlation between these and the historical consumption rate change pattern.

[0021] Obtain the current inventory data and current consumption data for each target medicine in the target medicine set;

[0022] Obtain the current fluctuation information of the key environmental factors at the current moment;

[0023] Based on the historical correlations and the current fluctuation information of the key environmental factors, determine the baseline consumption rate of each target pharmaceutical product at the current moment;

[0024] By combining the current consumption data of each target pharmaceutical product with the baseline consumption rate, demand urgency indication information is calculated;

[0025] By combining the historical consumption rate variation pattern of each target pharmaceutical product with the historical and current fluctuation information of the key environmental factors, demand fluctuation indication information is calculated.

[0026] Based on the urgency of demand indication information, the degree of demand fluctuation indication information, and the current inventory data for each target pharmaceutical product, a real-time demand level is generated for each target pharmaceutical product.

[0027] Optionally, based on the real-time demand, a dynamic safety stock baseline for the corresponding target pharmaceutical product is dynamically generated, including:

[0028] From the dynamic collaborative data of pharmaceutical products, obtain the historical safety stock level of each target pharmaceutical product within the set historical period;

[0029] The real-time demand for each target pharmaceutical product is analyzed to obtain the current demand characteristics information for each target pharmaceutical product;

[0030] The current demand characteristics of each target pharmaceutical product are combined with the historical safety stock level of the same target pharmaceutical product to generate the inventory level adjustment amount for each target pharmaceutical product.

[0031] Based on the inventory level adjustment and the historical safety stock level, a dynamic safety stock baseline is calculated for each target pharmaceutical product.

[0032] Optionally, the real-time demand level is coupled with the corresponding real-time safety stock benchmark for the target pharmaceutical product to generate a dynamic inventory control line, including:

[0033] The real-time demand for each target pharmaceutical product is analyzed to obtain the demand urgency component and the demand volatility component.

[0034] Calculate the first inventory adjustment coefficient based on the demand urgency component;

[0035] Calculate the second inventory adjustment coefficient based on the demand volatility component and the historical inventory level change process of the same target pharmaceutical product in the dynamic collaborative data of pharmaceutical products.

[0036] Based on the first inventory adjustment coefficient and the second inventory adjustment coefficient, the dynamic safety stock benchmark for the same target pharmaceutical product is adjusted to generate a target safety stock benchmark value.

[0037] Based on the target safety stock baseline value, determine the inventory replenishment trigger threshold and target inventory maintenance level for each target pharmaceutical product;

[0038] Based on the inventory replenishment trigger threshold and the inventory target maintenance level, a dynamic inventory control line is generated for each target pharmaceutical product.

[0039] Optionally, the real-time demand for each target pharmaceutical product is analyzed to obtain a demand urgency component and a demand volatility component, including:

[0040] From the real-time demand for each of the target pharmaceutical products, obtain a first parameter related to the urgency of demand;

[0041] From the real-time demand for each of the target pharmaceutical products, obtain a second parameter related to demand volatility;

[0042] Calculate the first adjustment factor based on the first parameter and the current inventory data of each target pharmaceutical product;

[0043] Multiply the first parameter by the first adjustment factor to obtain the demand urgency component for each target pharmaceutical product;

[0044] Calculate the second adjustment factor based on the second parameter and the historical inventory level changes of each target pharmaceutical product;

[0045] Multiplying the second parameter by the second adjustment factor yields the demand volatility component for each target pharmaceutical product.

[0046] Optionally, the inventory data of the target pharmaceutical product set is updated and managed according to the dynamic inventory control line, including:

[0047] The current inventory level of each target pharmaceutical product is compared with the inventory replenishment trigger threshold in the dynamic inventory control line of the same target pharmaceutical product.

[0048] When the current inventory level is less than or equal to the inventory replenishment trigger threshold, the quantity of each target pharmaceutical product to be replenished is determined based on the inventory target maintenance level in the dynamic inventory control line and the current inventory level.

[0049] Based on the quantity to be replenished, generate an inventory replenishment instruction for each of the target pharmaceutical products;

[0050] Update the inventory data for each target pharmaceutical product according to the inventory replenishment instruction.

[0051] Secondly, this application provides a dynamic pharmaceutical data management system based on demand and inventory optimization, comprising:

[0052] The acquisition module is used to acquire time-series data on the consumption and inventory of a target set of pharmaceutical products within a set historical period in the target area, as well as time-series data on environmental factors related to the occurrence of diseases within the target area.

[0053] The fusion module is used to fuse the consumption time-series data, the inventory time-series data, and the environmental factor time-series data to generate dynamic collaborative data for pharmaceuticals.

[0054] The calculation module is used to calculate the real-time demand for each target medicine in the target medicine set based on the dynamic collaborative data of the medicines.

[0055] The generation module is used to dynamically generate a dynamic safety stock benchmark for the corresponding target pharmaceutical products based on the real-time demand.

[0056] The coupling module is used to couple the real-time demand level with the real-time safety stock benchmark of the corresponding target pharmaceutical product to generate a dynamic inventory control line.

[0057] The update module is used to update and manage the inventory data of the target pharmaceutical product set according to the dynamic inventory control line.

[0058] Thirdly, this application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement a dynamic management method for pharmaceutical data based on demand and inventory optimization as described in the first aspect above.

[0059] Fourthly, this application provides a computer storage medium storing a computer program, which, when executed by a computer, implements a dynamic management method for pharmaceutical data based on demand and inventory optimization as described in the first aspect.

[0060] This application integrates time-series data of environmental factors related to disease occurrence within the target region with time-series data of pharmaceutical consumption and inventory, generating dynamic collaborative data for pharmaceuticals. This overcomes the limitations of traditional inventory management models that rely solely on internal historical consumption data. Furthermore, this collaborative analysis of multi-source data enables the perception and quantification of the actual impact of external environmental changes on drug demand. Consequently, when calculating the real-time demand for each drug, it can capture demand fluctuation signals caused by specific environmental factors earlier and more accurately, providing forward-looking and high-dimensional data support for subsequent inventory decisions.

[0061] Furthermore, based on real-time demand, a safety stock benchmark and inventory control line are dynamically generated, and the dynamic inventory control line is directly applied to the update management of inventory data. This achieves a fundamental shift in inventory strategy from static preset to dynamic adaptation. Specifically, the dynamic inventory control line can automatically adjust the inventory replenishment trigger threshold and target level according to changes in real-time demand. When the inventory level is detected to have reached the threshold, it automatically triggers a precise replenishment instruction. This effectively solves the problem of slow response of traditional static models when facing sudden changes in demand driven by the environment, and improves the agility and accuracy of the inventory system in dealing with uncertainty. Thus, overall, it achieves a dynamic balance in pharmaceutical inventory that avoids shortages and reduces redundancy in a complex and ever-changing environment.

[0062] These or other aspects of this application will become more apparent in the following description of the embodiments. Attached Figure Description

[0063] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0064] Figure 1 A flowchart of a dynamic pharmaceutical data management method based on demand and inventory optimization provided in this application is shown;

[0065] Figure 2 A schematic diagram of the structure of a dynamic pharmaceutical data management system based on demand and inventory optimization provided in this application is shown.

[0066] Figure 3 A schematic diagram of the structure of a computing device provided in this application is shown. Detailed Implementation

[0067] To enable those skilled in the art to better understand the present application, the technical solution of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0068] In some of the processes described in the specification, claims, and accompanying drawings of this application, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not themselves represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a chronological order, nor do they limit "first" and "second" to different types.

[0069] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0070] Figure 1 This application provides a flowchart of a dynamic pharmaceutical data management method based on demand and inventory optimization, such as... Figure 1 As shown, the method includes:

[0071] Step 101: Obtain time-series data on consumption and inventory of the target pharmaceutical product set within the target region during a set historical period, as well as time-series data on environmental factors related to disease occurrence within the target region.

[0072] In this step, the target pharmaceutical set refers to all pharmaceuticals that require inventory optimization management within a specific geographical area. It is used to define the specific scope of this method and is determined through the management's pharmaceutical catalog.

[0073] Consumption time series data refers to the data sequence formed by recording the quantity of each drug in the target pharmaceutical product set at fixed time intervals over a continuous historical period. It is used to reflect the historical patterns and trends of drug use and is obtained directly by connecting to the drug inventory management system database of medical institutions or pharmacies.

[0074] Inventory time series data and consumption time series data refer to the data sequence formed by recording the real-time inventory quantity of each drug at the same time interval within the same period. It is used to reflect the historical fluctuations in inventory levels and is obtained synchronously through a database connected to the same inventory management system.

[0075] Environmental factor time series data refers to a data sequence formed by the measurement values ​​of environmental indicators that are known or potentially associated with the occurrence and spread of diseases within the same target area over a continuous historical period at fixed time intervals. It is used to provide information on external driving factors affecting drug demand and is obtained by accessing data interfaces of public health, meteorological or environmental monitoring departments.

[0076] In this step, firstly, by executing selection and conditional filtering statements in Structured Query Language (SCL), a list of drug codes and names located within the target region and falling under the management scope is retrieved from a pre-configured drug master database or management list, thus clarifying the specific composition of the target pharmaceutical set. Secondly, for each identified target pharmaceutical, an online connection is established with the medical institution's drug management system through a database connector, and a data extraction job is scheduled. This data extraction job groups the drug transaction record table by drug code and outbound date, and uses aggregate functions such as SUM to sum the outbound quantities, thereby extracting consumption records within a set historical period and at a fixed time granularity, and then organizes and generates structured consumption time-series data. Next, another parallel data extraction job is simultaneously scheduled, accessing the same drug management system database. This other parallel data extraction job extracts the inventory balance records of each drug within the same historical period and at the same time granularity by performing filtering and sorting operations on the drug inventory snapshot table by drug code and record date and time, and then organizes and generates structured inventory time-series data.

[0077] Meanwhile, by calling a pre-configured application programming interface (API), an HTTP request containing the geocode of the target area and the required historical time range is sent to the public meteorological data service platform. After receiving the data response from the server, which is usually encapsulated in JSON or XML format, the data packet is parsed using a corresponding parsing library such as a JSON parser to extract daily time-series values ​​such as temperature and humidity. Similarly, by calling the open data interface of the environmental monitoring department, time-series data such as air quality index are obtained and parsed using a similar technical process. Finally, these environmental indicator data related to disease occurrence from different interfaces are aligned and merged according to a unified timestamp to generate a complete environmental factor time-series dataset.

[0078] For example, a regional drug management center needs to perform dynamic inventory management for three commonly used drugs in its jurisdiction, assuming they are drug A, drug B, and drug C, with the period set to the past two years. First, these three drugs are identified as the target pharmaceutical set. Second, the system automatically connects to the drug management systems of major hospitals in the region, collecting the daily outbound quantities of drugs A, B, and C at regular intervals to form a two-year time-series data of daily consumption. Then, the system collects the remaining inventory quantities of these three drugs at the end of each day from the same data source, forming corresponding time-series inventory data. In addition, the system obtains daily average temperature and humidity data from the regional meteorological bureau's data interface and daily average PM2.5 concentration data from the environmental protection department's data interface, and organizes the environmental data for the past two years into a time-series format. Thus, the system has completed the comprehensive acquisition of daily consumption, inventory, temperature, humidity, and PM2.5 concentration data for drugs A, B, and C over the past two years.

[0079] Step 102: The consumption time-series data, the inventory time-series data, and the environmental factor time-series data are fused to generate dynamic collaborative data for pharmaceuticals.

[0080] Optionally, step 102 may specifically include:

[0081] Step 1021: Analyze the consumption time series data to obtain the consumption rate change pattern of the target pharmaceutical product set.

[0082] Step 1022: Analyze the time-series data of the inventory to obtain the inventory level change process of the target pharmaceutical product set.

[0083] Step 1023: Analyze the time series data of the environmental factors to identify key environmental factors and their fluctuation information.

[0084] Step 1024: Establish the correlation between the fluctuation information of the key environmental factors and the change pattern of the consumption rate.

[0085] Step 1025: Based on the correlation, the consumption rate change pattern, the inventory level change process, and the fluctuation information of the key environmental factors are fused to generate dynamic collaborative data for pharmaceuticals.

[0086] In this step, pharmaceutical dynamic collaborative data refers to a comprehensive set of data that integrates drug consumption patterns, changes in inventory status, and key environmental driving factors and their interrelationships. This data is used to comprehensively depict the dynamic evolution of drug supply and demand under the influence of environmental factors.

[0087] Consumption rate variation patterns refer to the patterns of drug usage speed over time extracted from consumption time series data, such as long-term growth or decline trends, recurring seasonal peaks and troughs, etc., which are used to quantitatively describe the historical behavioral characteristics of drug demand.

[0088] The inventory level change process refers to the trajectory and characteristics of inventory quantity fluctuations over time extracted from inventory time series data, such as the speed of inventory turnover and the frequency of inventory hitting low points, which are used to reflect the status and efficiency of historical inventory management.

[0089] Key environmental factors refer to a small number of core environmental indicators selected from a large number of environmental factors’ time-series data that have a strong statistical correlation with changes in the consumption of the target pharmaceutical product set, such as the concentration of specific pollutants or climate variables, and are used to identify external driving factors that have a significant impact on drug demand.

[0090] Fluctuation information refers to the numerical variation characteristics of key environmental factors in their time series data, such as the magnitude, frequency, or periodicity of the changes, which is used to quantitatively describe the dynamic behavior of the environmental factor.

[0091] The correlation refers to the direction and intensity of the influence between the fluctuation information of key environmental factors and the changing patterns of drug consumption rates, which are quantified by mathematical or statistical methods. It is used to establish a specific relationship model between changes in the external environment and changes in drug demand, and is established through statistical modeling techniques such as regression analysis or correlation analysis.

[0092] In this step, firstly, time series decomposition algorithms are applied to the time series consumption data of each target pharmaceutical product. Specifically, the STL seasonal-trend decomposition method can be used to decompose the original series into trend components, seasonal components, and residual components. By analyzing the slope of the trend component and the amplitude and period of the seasonal component, it can be determined whether the consumption rate of the drug shows a long-term upward, downward, or stable trend, and in which specific time periods regular peaks or troughs occur, thereby extracting the consumption rate variation pattern of each drug. Secondly, for the time series inventory data of each target pharmaceutical product, its statistical characteristics are calculated, including the series mean, standard deviation, minimum value, and inventory turnover rate. By analyzing these statistics, especially observing the historical frequency of inventory levels falling below a certain safety threshold, the analysis is conducted. The process of inventory level changes is illustrated by analyzing the time series data of environmental factors, such as daily temperature, humidity, and concentrations of various pollutants. A feature selection algorithm is then used to calculate the correlation coefficient between the time series data of each environmental factor and the consumption time series data of the target pharmaceutical product set or representative pharmaceutical products, such as the Pearson correlation coefficient. Based on the absolute value and statistical significance of the correlation coefficients, several environmental indicators with the highest correlation to pharmaceutical consumption are selected. For example, the daily average PM2.5 concentration and daily average temperature difference are identified as key environmental factors. Furthermore, the fluctuation information is characterized by calculating the moving standard deviation and fluctuation period of the time series data of these factors.

[0093] Then, using the obtained fluctuation information of key environmental factors, such as the fluctuation sequence of PM2.5 concentration, and the trend or seasonally adjusted sequence in the change pattern of drug consumption rate, a correlation model is performed. This model employs multiple linear regression, using the fluctuation value of the key environmental factors as the independent variable and the drug consumption rate as the dependent variable for fitting. Through regression analysis, a regression coefficient describing how many units of change in the drug consumption rate will result from a unit change in the fluctuation of each key environmental factor is obtained. This quantified influence coefficient represents the correlation between them. Finally, a structured data object is created to encapsulate and integrate all the information. The obtained consumption rate change pattern of each drug, the corresponding inventory level change process, the identified key environmental factors and their fluctuation information, and the parameters of the established correlation model are associated and stored according to drug codes. For example, a record is created for drug A, containing its consumption pattern, inventory change process, and associated with the PM2.5 concentration factor, the fluctuation information of this concentration factor, and the correlation that for every unit increase in PM2.5 concentration, the expected increase in the consumption rate of drug A by X units. This data set, integrating internal and external dynamic factors and their quantitative relationships, is the final generated dynamic collaborative data for pharmaceuticals.

[0094] For example, following the specific implementation of the previous step, firstly, based on the obtained time-series data of consumption, inventory, and environmental factors for drugs A, B, and C over the past two years, the daily consumption sequence of drug A over the past two years is analyzed. It is found that its consumption shows a significant upward trend in autumn and winter each year, while it remains relatively stable in spring and summer. This extracts the consumption rate variation pattern of drug A, which is high in autumn and winter and low in spring and summer. Secondly, the inventory data of drug A is analyzed, revealing that its inventory level frequently reaches low levels in autumn and winter, rapidly decreasing after replenishment, indicating rapid turnover. In contrast, the inventory remains relatively abundant and stable in spring and summer, describing the process of inventory level change. Next, the correlation between environmental sequences such as temperature, humidity, and PM2.5 concentration and the consumption sequences of drugs A, B, and C is calculated. The results show that the daily average P... PM2.5 concentration showed the strongest correlation with the consumption of drug A and a moderate correlation with the consumption of drug B. Therefore, PM2.5 concentration was identified as a key environmental factor, and its fluctuation range was calculated. A regression model was then established to quantify the specific relationship that for every 10 micrograms per cubic meter increase in PM2.5 concentration, the daily consumption of drug A is expected to increase by 5 units. Finally, the consumption patterns of drug A (high in autumn and winter, low in spring and summer), its inventory changes (short supply in autumn and winter, ample supply in spring and summer), the key factor of PM2.5 concentration and its fluctuation information, and the aforementioned specific quantitative correlations were packaged and integrated to form a dynamic collaborative data record for drug A. A similar process was performed on drugs B and C, ultimately generating a dynamic collaborative dataset covering all target drugs.

[0095] This step transforms raw data into structured knowledge through in-depth mining and correlation fusion of multi-source time-series data. It also extracts the inherent patterns of drug consumption and inventory from historical data, identifies key environmental factors affecting demand, and establishes a quantitative correlation model between environmental changes and drug consumption. The resulting dynamic collaborative data for pharmaceuticals is a comprehensive data set that integrates internal patterns, external driving factors, and their quantitative relationships, providing a core data foundation for subsequent dynamic demand assessment and inventory decisions.

[0096] Step 103: Based on the dynamic collaborative data of pharmaceutical products, calculate the real-time demand level corresponding to each target pharmaceutical product in the target pharmaceutical product set.

[0097] Optionally, step 103 may specifically include:

[0098] Step 1031: Extract the historical consumption rate change pattern, historical inventory level change process, and historical fluctuation information of key environmental factors for each target pharmaceutical product in the target pharmaceutical product set from the dynamic collaborative data of pharmaceutical products, and the historical correlation between them and the historical consumption rate change pattern.

[0099] Step 1032: Obtain the current inventory data and current consumption data of each target medicine in the target medicine set.

[0100] Step 1033: Obtain the current fluctuation information of the key environmental factors at the current moment.

[0101] Step 1034: Based on the historical correlation and the current fluctuation information of the key environmental factors, determine the baseline consumption rate of each target pharmaceutical product at the current moment.

[0102] Step 1035: Combine the current consumption data of each target pharmaceutical product with the baseline consumption rate to calculate the urgency indication information.

[0103] Step 1036: Calculate the demand fluctuation level indication information by combining the historical consumption rate change pattern of each target pharmaceutical product, the historical fluctuation information of the key environmental factors, and the current fluctuation information.

[0104] Step 1037: Based on the demand urgency indication information, demand fluctuation indication information, and current inventory data for each target pharmaceutical product, generate the real-time demand level corresponding to each target pharmaceutical product.

[0105] In this step, real-time demand refers to a comprehensive quantitative indicator used to dynamically reflect the urgency and expected fluctuation intensity of demand for a certain drug at the current moment and under specific environmental conditions.

[0106] Historical correlation refers to a quantitative impact model that has been pre-established and stored in the dynamic collaborative data of pharmaceuticals, relating the historical fluctuations of key environmental factors to the historical consumption rate of drugs, and is used to predict the expected consumption level of drugs under current environmental conditions.

[0107] Current inventory data refers to the actual inventory quantity of each drug in the target pharmaceutical product set at the most recent point in time. It is used to assess the immediate inventory adequacy and is obtained by querying the drug inventory management system database in real time.

[0108] Current consumption data refers to the actual consumption quantity of each drug in the target pharmaceutical product set within the most recent statistical period. It is used to understand the latest drug usage and is obtained by querying the drug consumption record database in real time.

[0109] Current fluctuation information refers to the changes in the measured values ​​of key environmental factors over a recent period of time. It is used to reflect the real-time impact of the current external environment on drug demand. It is obtained by calling the environmental monitoring data interface to acquire real-time data and calculate its change characteristics.

[0110] The baseline consumption rate refers to the typical or expected consumption rate of a drug at the current moment, predicted based on historical patterns and taking into account the impact of current environmental fluctuations.

[0111] Urgency indicator information refers to a quantitative value that reflects the degree to which the current actual consumption rate of a drug deviates from the expected baseline consumption rate, and is used to indicate the urgency of the demand.

[0112] Demand volatility indicator refers to a quantitative value reflecting the potential instability or magnitude of change in future drug demand under the combined influence of historical patterns and current environmental fluctuations.

[0113] In this step, firstly, by performing a data query operation, the system reads and extracts specific parameters of the historical consumption rate change pattern, key statistical characteristics of the historical inventory level change process, and the historical correlation model and coefficients between key environmental factors and consumption rate from the generated dynamic collaborative database of pharmaceuticals, based on the unique drug code. Secondly, by calling the real-time data interface, a query request is sent to the database of the drug management system to obtain the inventory balance of each target pharmaceutical product at the end of the most recent statistical period, such as the end of yesterday or the end of the current hour, as the current inventory data, and obtains the summary value of the outbound quantity within the same time period as the current consumption data. Then, the system accesses the environmental monitoring data platform... The application programming interface (API) retrieves the latest monitoring sequence of key environmental factors, such as PM2.5 concentration, from the end of the previous statistical period to the present, and calculates its statistical characteristics, such as mean, rate of change, or deviation from the mean of the previous few periods, as the current fluctuation information. Then, using the extracted historical correlation model, the specific values ​​of the current fluctuation information of the key environmental factors, such as the current PM2.5 concentration, are substituted into the mathematical formula of the historical correlation. This formula describes the impact of a unit change in the environmental factor on the consumption rate. By substituting the values ​​into the formula, an expected consumption rate of the drug under the current environmental conditions is output. This value is the determined baseline consumption rate.

[0114] The acquired current consumption data is then compared with the calculated baseline consumption rate. The relative deviation between the current consumption data and the baseline consumption rate is calculated, and this relative difference is standardized or scaled to convert it into a comparable, dimensionless value. This value is the calculated demand urgency indicator; the larger the deviation, the higher the demand urgency indicator value, indicating a more urgent demand. Simultaneously, the volatility characteristics contained in the extracted historical consumption rate variation patterns, such as the amplitude of historical seasonal fluctuations, and the degree of anomalousness of the acquired current volatility information relative to its long-term historical average, are combined using a comprehensive evaluation function, such as a weighted combination of historical volatility amplitude and current environmental volatility anomaly, to obtain... A numerical value reflecting the degree of risk or uncertainty that future demand may deviate from its normal trajectory is the calculated demand volatility indicator. Finally, a demand intensity calculation model is constructed. This model takes the generated demand urgency indicator, demand volatility indicator, and current inventory data as inputs. According to predefined rules or formulas, it performs comprehensive calculations on these three inputs, such as assigning different weights to urgency, volatility, and inventory level and performing weighted summation. Finally, it outputs a single, comprehensive quantitative value, which is the real-time demand intensity for each target pharmaceutical product. The level of this real-time demand intensity directly reflects the urgency and importance of the drug needing to be replenished or monitored at the current moment.

[0115] For example, following the specific implementation of the previous step, firstly, dynamic collaborative data on drug A is already available, including its consumption rate variation pattern, inventory level variation process, and a historical correlation established that for every 10 units increase in PM2.5 concentration, daily consumption of drug A increases by 5 units. Secondly, from this dynamic collaborative data, the consumption pattern of drug A (high in autumn and winter, low in spring and summer), its rapid inventory turnover characteristics, and a specific concentration-consumption correlation model are extracted. Next, a real-time query reveals that drug A consumed 120 units yesterday, and the current inventory is 300 units. Then, from the environmental platform, it is obtained that the average PM2.5 concentration in the area from yesterday to the present is 25 units higher than its historical average for the same period; this abnormal increase is the current fluctuation information. Subsequently, this current fluctuation information of PM2.5 concentration exceeding 25 units is substituted into the historical correlation model to calculate that the baseline consumption rate should increase by an additional 12.5 units on top of the normal rate, and combined with... Based on historical benchmarks, the baseline consumption rate of drug A at the current moment is determined to be 132.5 units per day. Then, comparing the current consumption data of 120 units with the baseline consumption rate of 132.5 units, the calculation shows that the current consumption is slightly lower than expected, but the deviation is not significant, generating a moderate level of demand urgency indication. Simultaneously, considering the historically large fluctuations in drug A's consumption during autumn and winter, and the strong fluctuation signal of the current significantly abnormally high PM2.5 concentration, a higher level of demand volatility indication is calculated. Finally, the moderate demand urgency indication, the high demand volatility indication, and the current inventory data of 300 units (the inventory level itself is still acceptable) are input into the calculation model. Due to the high demand volatility indication, future demand may rise sharply and is highly uncertain. The model ultimately outputs a high real-time demand level, suggesting that close attention should be paid to the inventory status of drug A and that preparations may need to be made in advance.

[0116] This step combines historical pattern models from dynamic collaborative data with real-time data to achieve dynamic, multi-dimensional assessment of drug demand. By quantifying the urgency of current demand and the risk of future fluctuations, and by comprehensively considering real-time inventory status, a unified real-time demand index is generated. This index provides a precise and forward-looking quantitative decision-making basis for the immediate adjustment of subsequent inventory strategies.

[0117] Step 104: Based on the real-time demand, dynamically generate a dynamic safety stock benchmark for the corresponding target pharmaceutical products.

[0118] Optionally, step 104 may specifically include:

[0119] Step 1041: Obtain the historical safety stock level of each target pharmaceutical product within the set historical period from the dynamic collaborative data of pharmaceutical products.

[0120] Step 1042: Analyze the real-time demand for each target pharmaceutical product to obtain the current demand characteristic information for each target pharmaceutical product.

[0121] Step 1043: Combine the current demand characteristics of each target pharmaceutical product with the historical safety stock level of the same target pharmaceutical product to generate the inventory level adjustment amount for each target pharmaceutical product.

[0122] Step 1044: Calculate the dynamic safety stock baseline for each target pharmaceutical product based on the inventory level adjustment amount and the historical safety stock level.

[0123] In this step, the dynamic safety stock baseline refers to a standard value of inventory quantity that is dynamically adjusted according to changes in real-time demand. It is used to define the minimum inventory level that should be held to prevent stockouts under current and foreseeable demand conditions. It is calculated by adjusting historical safety stock levels in conjunction with real-time demand characteristics.

[0124] Historical safety stock level refers to the quantity of safety stock that can meet the demand fluctuations during a set historical period, obtained through statistical analysis or actually used. It serves as an initial reference benchmark for dynamic adjustment.

[0125] Current demand characteristic information refers to the key attributes extracted from real-time demand that can specifically guide inventory adjustments, such as whether demand tends to be highly urgent or highly volatile. It is used to quantitatively describe the core impact of current demand on inventory strategy.

[0126] Inventory level adjustment refers to a specific value that indicates the amount of inventory to be increased or decreased based on historical safety stock levels, according to current demand characteristics. It is used to translate dynamic demand signals into specific instructions for changing inventory quantities.

[0127] In this step, firstly, a database storing dynamic collaborative data for pharmaceuticals is accessed using a database query language. Based on the drug's unique identifier, the corresponding data record is retrieved, and the historical safety stock level value, calculated and saved during the collaborative data construction phase, is read. Secondly, the calculated real-time demand level is analyzed by calling a parsing function. This function decomposes the comprehensive value of the real-time demand level into components on several preset dimensions. For example, the function can extract the strength of the component reflecting demand urgency and the strength of the component reflecting demand volatility. The specific numerical combination of these two components constitutes the current demand characteristic information. Next, a predefined adjustment calculation rule is applied. This adjustment calculation rule takes the parsed current demand characteristic information as input, such as the demand urgency component and the demand volatility component. The numerical value of each component is compared with a preset threshold or substituted into an adjustment coefficient mapping table. Simultaneously, the historical safety stock level is referenced, as the adjustment amount is usually proportional to the base level. This adjustment is calculated according to rules and outputs a specific value, which is the generated inventory level adjustment amount for each target pharmaceutical product. A positive value indicates that inventory needs to be increased, while a negative value indicates that it can be reduced. Finally, an arithmetic calculation is performed, adding the historical safety stock level as the base to the inventory level adjustment amount. The result of this addition operation is a new safety stock value that reflects the current real-time demand characteristics—the calculated dynamic safety stock benchmark for each target pharmaceutical product. This dynamic safety stock benchmark will replace the original static historical value and serve as the core basis for subsequently generating inventory control lines.

[0128] For example, following the specific implementation of the previous step, firstly, it has been calculated that the real-time demand for drug A is relatively high, mainly driven by its demand fluctuation indication information characteristics; secondly, from the pharmaceutical dynamic collaborative data records of drug A, it is found that its historical safety stock level, calculated based on data from the past two years, is 200 units; then, the high real-time demand for drug A is analyzed, specifically decomposed into a medium demand urgency indication information component and a high demand fluctuation indication information component, and this set of medium urgency and high fluctuation information is the current demand characteristic information; then, it is processed according to preset business rules, which stipulate that when demand fluctuation... When the volatility characteristic is high, regardless of urgency, a certain percentage of inventory should be added to the historical safety stock to cope with uncertainty. Assuming that the business rules calculate that for drug A, its historical safety stock level of 200 units needs to be increased by 30%, an inventory level adjustment of 60 units is generated accordingly. Finally, the historical safety stock level of 200 units and the inventory level adjustment of 60 units are added together to calculate that the current dynamic safety stock benchmark for drug A is 260 units. This means that, considering the high volatility risk in the future caused by the current environment, it is believed that the safety stock standard for drug A should be dynamically increased from the past 200 units to 260 units.

[0129] This step transforms the comprehensive signal of real-time demand into specific inventory management parameters. By analyzing the real-time demand, identifying current demand characteristics, and combining historical safety stock levels, a dynamically calculated and generated adaptive safety stock benchmark is generated. This allows the safety stock level to accurately respond to real-time demand changes, providing a dynamic and accurate benchmark value for setting subsequent inventory control lines.

[0130] Step 105: Couple the real-time demand level with the real-time safety stock benchmark of the corresponding target pharmaceutical product to generate a dynamic inventory control line.

[0131] Optionally, step 105 may specifically include:

[0132] Step 1051: Analyze the real-time demand for each target pharmaceutical product to obtain the demand urgency component and the demand volatility component.

[0133] Optionally, step 1051 may include the following steps: obtaining a first parameter related to demand urgency from the real-time demand of each target pharmaceutical product; obtaining a second parameter related to demand volatility from the real-time demand of each target pharmaceutical product; calculating a first adjustment factor based on the first parameter and the current inventory data of each target pharmaceutical product; multiplying the first parameter by the first adjustment factor to obtain the demand urgency component of each target pharmaceutical product; calculating a second adjustment factor based on the second parameter and the historical inventory level change process of each target pharmaceutical product; and multiplying the second parameter by the second adjustment factor to obtain the demand volatility component of each target pharmaceutical product.

[0134] Step 1052: Calculate the first inventory adjustment coefficient based on the demand urgency component.

[0135] Step 1053: Calculate the second inventory adjustment coefficient based on the demand volatility component and the historical inventory level change process of the same target pharmaceutical product in the dynamic collaborative data of pharmaceutical products.

[0136] Step 1054: Based on the first inventory adjustment coefficient and the second inventory adjustment coefficient, the dynamic safety stock benchmark for the same target pharmaceutical product is adjusted to generate a target safety stock benchmark value.

[0137] Step 1055: Based on the target safety stock baseline value, determine the inventory replenishment trigger threshold and target inventory maintenance level for each target pharmaceutical product.

[0138] Step 1056: Generate a dynamic inventory control line for each target pharmaceutical product based on the inventory replenishment trigger threshold and the inventory target maintenance level.

[0139] In this step, the dynamic inventory control line refers to a set of inventory management boundaries that dynamically change with demand and benchmarks, consisting of two key values: the inventory replenishment trigger threshold and the inventory target maintenance level. It is used to directly guide when to initiate replenishment and at what level replenishment should be achieved.

[0140] The demand urgency component refers to a value separated from the real-time demand level, specifically used to quantify the urgency of current demand, and is used to fine-tune inventory strategies to cope with immediate consumption pressure.

[0141] The demand volatility component refers to a value separated from the real-time demand level, specifically used to quantify the uncertainty and volatility risk of future demand, and is used to fine-tune inventory strategies to cope with potential demand changes.

[0142] The first parameter refers to the original numerical value or vector related to the urgency of the demand that is directly extracted during the process of parsing the real-time demand degree. It is used to initially represent the intensity of urgency and is obtained by calling the data structure of the real-time demand degree and reading its corresponding attributes.

[0143] The second parameter refers to the original numerical value or vector related to demand volatility that is directly extracted during the parsing of real-time demand. It is used to initially represent the intensity of volatility and is obtained by calling the data structure of real-time demand and reading its corresponding attributes.

[0144] The first adjustment factor refers to a coefficient that calibrates the first parameter based on the current inventory data. It is used to transform the original urgency parameter into an urgency component that better reflects the actual inventory situation. It is calculated by comparing and mapping the current inventory data with preset rules.

[0145] The second adjustment factor is a coefficient that calibrates the second parameter based on the historical inventory level change process. It is used to transform the original volatility parameter into a volatility component that better reflects the historical inventory behavior pattern of the drug. It is calculated by analyzing the characteristics of the historical inventory level change process and matching it with preset rules.

[0146] The first inventory adjustment factor refers to a specific magnification or reduction factor used to quantify the adjustment range of the demand urgency component to the dynamic safety stock benchmark. It is obtained by inputting the demand urgency component into a preset conversion function or by looking up a table.

[0147] The second inventory adjustment factor refers to a specific magnification or reduction factor used to quantify the adjustment magnitude of the demand volatility component to the dynamic safety stock benchmark. It is calculated by inputting the demand volatility component into a preset conversion function along with the historical inventory level change process.

[0148] The target safety stock benchmark refers to the final safety stock level determined after adjustments based on both demand urgency and volatility, and is used to guide inventory management at the current stage.

[0149] The inventory replenishment trigger threshold refers to a specific inventory quantity value. When the actual inventory level is lower than or equal to this value, a replenishment operation is automatically triggered. It is usually set as a fixed percentage of the target safety stock benchmark value, which is calculated by multiplying the target safety stock benchmark value by a preset percentage coefficient.

[0150] The target inventory maintenance level refers to a specific inventory quantity value, which is the expected inventory level to be achieved during replenishment operations. It is usually set above the inventory replenishment trigger threshold and is calculated by adding a preset fixed buffer amount to the target safety stock baseline value or multiplying it by another percentage coefficient.

[0151] In this step, a deep analysis of real-time demand is first performed. A parsing function is called to directly read the first parameter representing the intensity of demand urgency and the second parameter representing the intensity of demand volatility from the real-time demand data structure. Next, current inventory data is queried, and based on the sufficiency of the current inventory relative to a certain reference level, a first adjustment factor is calculated using a preset mapping rule. The first parameter and the first adjustment factor are multiplied to obtain a more accurate demand urgency component. Simultaneously, the historical inventory level changes of the drug are obtained from the dynamic collaborative data of pharmaceutical products, and its historical volatility characteristics are analyzed. Based on these characteristics, a second adjustment factor is calculated using another preset rule. The second parameter and the second adjustment factor are multiplied to obtain a more accurate... The system first takes the demand volatility component as input and then uses the demand urgency component as input. A pre-defined conversion function maps the urgency component to a specific value, which is the first inventory adjustment coefficient. The higher the urgency component, the larger the calculated first inventory adjustment coefficient. Next, the system takes the demand volatility component and the historical inventory level change characteristics of the same drug obtained from pharmaceutical dynamic collaborative data as input. A more complex comprehensive conversion function is used, which considers both the intensity of the volatility component and the inertia or sensitivity of the drug's historical inventory fluctuations, to calculate a specific value, which is the second inventory adjustment coefficient.

[0152] Then, a correction calculation is applied to obtain the generated dynamic safety stock baseline. The first and second inventory adjustment coefficients are combined, usually by adding them together or by merging them into a total adjustment coefficient using a comprehensive formula. This total adjustment coefficient is used to calculate the dynamic safety stock baseline, such as by multiplying it, thereby adjusting its value upwards or downwards to generate the final target safety stock baseline value. Subsequently, based on the determined target safety stock baseline value, two key control parameters are calculated. The target safety stock baseline value is multiplied by a predefined percentage coefficient less than 1, such as 70%, to obtain the inventory replenishment trigger threshold. At the same time, the target safety stock baseline value is multiplied by a percentage coefficient greater than 1, such as 120%, or a fixed amount is added directly to the target value to obtain the target inventory maintenance level. Finally, the calculated inventory replenishment trigger threshold and target inventory maintenance level are paired and bound to the corresponding drug identifier to form a complete management instruction pair. This management instruction pair is the generated dynamic inventory control line for the target pharmaceutical product, directly specifying the specific inventory control range for the drug in the following time period.

[0153] For example, following the specific implementation of the previous step, firstly, the dynamic safety stock baseline for drug A has been set to 260 units; secondly, the real-time demand for drug A is analyzed, extracting a first parameter value of 0.7 and a second parameter value of 0.9; then, it is found that the current inventory of drug A is 300 units, and based on the sufficiency of inventory, a first adjustment factor of 0.8 is calculated, and from the dynamic collaborative data, it is learned that the historical inventory of drug A has fluctuated drastically, so a second adjustment factor of 1.2 is calculated; thus, the urgency component of demand is 0.7 multiplied by 0.8 equals 0.56, and the volatility component of demand is 0.9 multiplied by 1.2 equals 1.08; then, the urgency component of 0.56 is input into the conversion function, outputting a first inventory adjustment coefficient of 1.1, and the volatility component... The input conversion function for 1.08 and historical inventory drastic changes outputs a second inventory adjustment coefficient of 1.3. The two adjustment coefficients are then combined, assuming a multiplicative logic, the total adjustment impact is 1.1 multiplied by 1.3 equals 1.43. This coefficient is used to correct the dynamic safety stock benchmark, i.e., 260 units multiplied by 1.43, resulting in a target safety stock benchmark value of approximately 372 units. A preset percentage is then used: multiplying the target value of 372 units by 70% yields an inventory replenishment trigger threshold of approximately 260 units; multiplying this by 120% yields a target inventory maintenance level of approximately 446 units. Finally, the dynamic inventory control line for drug A is generated as follows: replenishment is triggered when the inventory is below or equal to 260 units, with the replenishment target being to increase the inventory to 446 units.

[0154] This step completes the precise transformation from real-time demand assessment to specific inventory control rules. By analyzing the urgency and volatility components of demand, the corresponding inventory adjustment coefficient is calculated, and the dynamic safety stock benchmark is corrected accordingly to generate the target safety stock benchmark value. Based on this value, the inventory replenishment trigger threshold and the target inventory maintenance level are determined, forming an automatically executable dynamic inventory control line. This achieves deep coupling and adaptive matching between the inventory control strategy and the real-time, volatile demand environment.

[0155] 106. Based on the aforementioned dynamic inventory control line, update and manage the inventory data of the target pharmaceutical product set.

[0156] Optionally, step 106 may specifically include:

[0157] Step 1061: Compare the current inventory level of each target pharmaceutical product with the inventory replenishment trigger threshold in the dynamic inventory control line of the same target pharmaceutical product.

[0158] Step 1062: When the current inventory level is less than or equal to the inventory replenishment trigger threshold, determine the quantity of each target pharmaceutical product to be replenished based on the inventory target maintenance level in the dynamic inventory control line and the current inventory level.

[0159] Step 1063: Based on the quantity to be replenished, generate an inventory replenishment instruction for each target pharmaceutical product.

[0160] Step 1064: Update the inventory data of each target pharmaceutical product according to the inventory replenishment instruction.

[0161] In this step, the quantity of the target pharmaceutical product to be replenished refers to the specific number of drugs for which a replenishment request needs to be made to the supply chain in order to restore the inventory level from the current value to the preset target maintenance level. This is used to precisely guide procurement or distribution operations.

[0162] An inventory replenishment instruction is a structured command that contains key information such as the target drug identifier, the quantity to be replenished, and the suggested replenishment time. It is used to drive downstream procurement systems, warehouse management systems, or supplier interfaces to execute the actual replenishment process. It is obtained by formatting the quantity to be replenished and related context information into a standard data message.

[0163] In this step, firstly, the latest inventory snapshot of each target pharmaceutical product is retrieved from the pharmaceutical inventory management database via a real-time query interface, i.e., the current inventory level. Simultaneously, the dynamic inventory control line generated for that pharmaceutical product is read, and the inventory replenishment trigger threshold is extracted. A comparison operation is then executed, using conditional statements in the programming to compare the current inventory level with the inventory replenishment trigger threshold. Secondly, when the comparison results indicate that the current inventory level is less than or equal to the inventory replenishment trigger threshold, the replenishment calculation logic is triggered. Another parameter, the target inventory maintenance level, is read from the same dynamic inventory control line, and an arithmetic operation is performed, subtracting the current inventory level from the target inventory maintenance level. The difference is the determined quantity of the target pharmaceutical product to be replenished. Then... Based on the calculated replenishment quantity, a structured data object is created. This object encapsulates information such as the drug's unique code, the replenishment quantity, the timestamp of the generated instruction, and the associated inventory control line identifier, according to a predefined data format. For example, it can be organized into a JSON or XML message conforming to a specific interface specification. This complete message is the generated inventory replenishment instruction for that target pharmaceutical product. Finally, by calling an application programming interface or message queue, the generated inventory replenishment instruction is sent to the downstream procurement execution system. Simultaneously, the system's own inventory management records are pre-positioned or marked to reflect that a replenishment instruction is in transit. This logically updates the inventory data for each target pharmaceutical product, ensuring that the data status within the system remains consistent with the upcoming logistics operations.

[0164] For example, following the specific implementation of the previous step, firstly, the dynamic inventory control line for drug A is set to an inventory replenishment trigger threshold of 260 units and an inventory target maintenance level of 446 units. Real-time query reveals that the current inventory level of drug A is 250 units. Secondly, comparing 250 units with 260 units, it is determined that the current inventory is below the trigger threshold. Then, since the replenishment condition has been triggered, the target maintenance level of 446 units is read, and the current inventory of 250 units is subtracted from it to calculate the quantity to be replenished as 196 units. This information is then encapsulated to generate a standardized inventory replenishment instruction for drug A, requiring an immediate replenishment of 196 units. Finally, this standardized inventory replenishment instruction is automatically pushed to the order system of the regional distribution center, and replenishment is marked as "in progress" in the drug A inventory record, thereby completing the inventory data update and management response.

[0165] This step transforms the intelligently generated dynamic inventory control line into actual inventory management operations. By automatically monitoring inventory levels and precisely triggering replenishment, it achieves immediate response and automated processing of inventory shortage risks, completing a closed loop from dynamic decision-making to precise execution, and effectively improving the timeliness and accuracy of inventory management.

[0166] Figure 2 This application provides a schematic diagram of the structure of a dynamic pharmaceutical data management system based on demand and inventory optimization, as shown below. Figure 2 As shown, the system includes:

[0167] The acquisition module 21 is used to acquire time-series data on the consumption and inventory of the target pharmaceutical products set within a set historical period in the target area, as well as time-series data on environmental factors related to the occurrence of diseases within the target area.

[0168] The fusion module 22 is used to fuse the consumption time-series data, the inventory time-series data, and the environmental factor time-series data to generate dynamic collaborative data for pharmaceuticals.

[0169] Calculation module 23 is used to calculate the real-time demand degree corresponding to each target medicine in the target medicine set based on the dynamic collaborative data of the medicines.

[0170] The generation module 24 is used to dynamically generate a dynamic safety stock benchmark for the corresponding target pharmaceutical products based on the real-time demand.

[0171] The coupling module 25 is used to couple the real-time demand level with the real-time safety stock benchmark of the corresponding target pharmaceutical product to generate a dynamic inventory control line.

[0172] The update module 26 is used to update and manage the inventory data of the target pharmaceutical product set according to the dynamic inventory control line.

[0173] Figure 2 The aforementioned dynamic pharmaceutical data management system based on demand and inventory optimization can execute... Figure 1 The implementation principle and technical effects of the dynamic pharmaceutical data management method based on demand and inventory optimization described in the illustrated embodiment will not be repeated here. The specific methods by which each module and unit performs operations in the dynamic pharmaceutical data management system based on demand and inventory optimization in the above embodiments have been described in detail in the embodiments related to this method, and will not be elaborated upon here.

[0174] In one possible design, Figure 2 The illustrated embodiment of a dynamic pharmaceutical data management system based on demand and inventory optimization can be implemented as a computing device, such as... Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0175] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are invoked and executed by the processing component 32.

[0176] The processing component 32 is used for the above Figure 1 The above embodiment describes a dynamic management method for pharmaceutical data based on demand and inventory optimization.

[0177] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A dynamic management method for pharmaceutical product data based on demand and inventory optimization, characterized in that, include: Acquire time-series data on consumption and inventory of a target set of pharmaceutical products within a set historical period in the target region, as well as time-series data on environmental factors related to disease occurrence within the target region; The consumption time-series data, the inventory time-series data, and the environmental factor time-series data are fused to generate dynamic collaborative data for pharmaceuticals. Based on the aforementioned dynamic collaborative data of pharmaceuticals, the real-time demand level corresponding to each target pharmaceutical in the target pharmaceutical set is calculated. Based on the real-time demand, a dynamic safety stock baseline for the corresponding target pharmaceutical products is dynamically generated. The real-time demand level is coupled with the real-time safety stock benchmark of the corresponding target pharmaceutical product to generate a dynamic inventory control line; Based on the aforementioned dynamic inventory control line, the inventory data of the target pharmaceutical product set is updated and managed.

2. The method according to claim 1, characterized in that, The consumption time-series data, the inventory time-series data, and the environmental factor time-series data are fused to generate dynamic collaborative data for pharmaceuticals, including: By analyzing the time-series data of the consumption, the consumption rate variation pattern of the target pharmaceutical product set can be obtained; By analyzing the time-series data of the inventory levels, the process of inventory level changes of the target pharmaceutical product set can be obtained; Analyze the time-series data of the environmental factors to identify key environmental factors and their fluctuation information; Establish the correlation between the fluctuation information of the key environmental factors and the changing pattern of the consumption rate; Based on the aforementioned correlation, the consumption rate change pattern, the inventory level change process, and the fluctuation information of the key environmental factors are fused to generate dynamic collaborative data for pharmaceuticals.

3. The method according to claim 1, characterized in that, Based on the aforementioned dynamic collaborative data for pharmaceuticals, the real-time demand level corresponding to each target pharmaceutical in the target pharmaceutical set is calculated, including: From the dynamic collaborative data of pharmaceutical products, extract the historical consumption rate change pattern, historical inventory level change process, and historical fluctuation information of key environmental factors for each target pharmaceutical product in the target pharmaceutical product set, and the historical correlation between these and the historical consumption rate change pattern. Obtain the current inventory data and current consumption data for each target medicine in the target medicine set; Obtain the current fluctuation information of the key environmental factors at the current moment; Based on the historical correlations and the current fluctuation information of the key environmental factors, determine the baseline consumption rate of each target pharmaceutical product at the current moment; By combining the current consumption data of each target pharmaceutical product with the baseline consumption rate, demand urgency indication information is calculated; By combining the historical consumption rate variation pattern of each target pharmaceutical product with the historical and current fluctuation information of the key environmental factors, demand fluctuation indication information is calculated. Based on the urgency of demand indication information, the degree of demand fluctuation indication information, and the current inventory data for each target pharmaceutical product, a real-time demand level is generated for each target pharmaceutical product.

4. The method according to claim 1, characterized in that, Based on the real-time demand, a dynamic safety stock baseline for the corresponding target pharmaceutical products is dynamically generated, including: From the dynamic collaborative data of pharmaceutical products, obtain the historical safety stock level of each target pharmaceutical product within the set historical period; The real-time demand for each target pharmaceutical product is analyzed to obtain the current demand characteristics information for each target pharmaceutical product; The current demand characteristics of each target pharmaceutical product are combined with the historical safety stock level of the same target pharmaceutical product to generate the inventory level adjustment amount for each target pharmaceutical product. Based on the inventory level adjustment and the historical safety stock level, a dynamic safety stock baseline is calculated for each target pharmaceutical product.

5. The method according to claim 1, characterized in that, The real-time demand level is coupled with the corresponding real-time safety stock benchmark for the target pharmaceutical product to generate a dynamic inventory control line, including: The real-time demand for each target pharmaceutical product is analyzed to obtain the demand urgency component and the demand volatility component. Calculate the first inventory adjustment coefficient based on the demand urgency component; Calculate the second inventory adjustment coefficient based on the demand volatility component and the historical inventory level change process of the same target pharmaceutical product in the dynamic collaborative data of pharmaceutical products. Based on the first inventory adjustment coefficient and the second inventory adjustment coefficient, the dynamic safety stock benchmark for the same target pharmaceutical product is adjusted to generate a target safety stock benchmark value. Based on the target safety stock baseline value, determine the inventory replenishment trigger threshold and target inventory maintenance level for each target pharmaceutical product; Based on the inventory replenishment trigger threshold and the inventory target maintenance level, a dynamic inventory control line is generated for each target pharmaceutical product.

6. The method according to claim 5, characterized in that, The real-time demand for each target pharmaceutical product is analyzed to obtain the demand urgency component and the demand volatility component, including: From the real-time demand for each of the target pharmaceutical products, obtain a first parameter related to the urgency of demand; From the real-time demand for each of the target pharmaceutical products, obtain a second parameter related to demand volatility; Calculate the first adjustment factor based on the first parameter and the current inventory data of each target pharmaceutical product; Multiply the first parameter by the first adjustment factor to obtain the demand urgency component for each target pharmaceutical product; Calculate the second adjustment factor based on the second parameter and the historical inventory level changes of each target pharmaceutical product; Multiplying the second parameter by the second adjustment factor yields the demand volatility component for each target pharmaceutical product.

7. The method according to claim 1, characterized in that, Based on the aforementioned dynamic inventory control line, the inventory data of the target pharmaceutical product set is updated and managed, including: The current inventory level of each target pharmaceutical product is compared with the inventory replenishment trigger threshold in the dynamic inventory control line of the same target pharmaceutical product. When the current inventory level is less than or equal to the inventory replenishment trigger threshold, the quantity of each target pharmaceutical product to be replenished is determined based on the inventory target maintenance level in the dynamic inventory control line and the current inventory level. Based on the quantity to be replenished, generate an inventory replenishment instruction for each of the target pharmaceutical products; Update the inventory data for each target pharmaceutical product according to the inventory replenishment instruction.

8. A dynamic management system for pharmaceutical product data based on demand and inventory optimization, characterized in that, include: The acquisition module is used to acquire time-series data on the consumption and inventory of a target set of pharmaceutical products within a set historical period in the target area, as well as time-series data on environmental factors related to the occurrence of diseases within the target area. The fusion module is used to fuse the consumption time-series data, the inventory time-series data, and the environmental factor time-series data to generate dynamic collaborative data for pharmaceuticals. The calculation module is used to calculate the real-time demand for each target medicine in the target medicine set based on the dynamic collaborative data of the medicines. The generation module is used to dynamically generate a dynamic safety stock benchmark for the corresponding target pharmaceutical products based on the real-time demand. The coupling module is used to couple the real-time demand level with the real-time safety stock benchmark of the corresponding target pharmaceutical product to generate a dynamic inventory control line. The update module is used to update and manage the inventory data of the target pharmaceutical product set according to the dynamic inventory control line.

9. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement a dynamic pharmaceutical data management method based on demand and inventory optimization as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The device contains a computer program that, when executed by a computer, implements a dynamic pharmaceutical data management method based on demand and inventory optimization as described in any one of claims 1 to 7.

Images