Medical article expiration date management system based on machine learning

Abstract

The invention relates to the technical field of data processing, and provides a medical article expiration date management system based on machine learning, and the system comprises a data obtaining module which is used for obtaining the article information of a to-be-managed medical article and the warehouse information of warehouses of all grades; the first calculation module is used for processing the article information through a machine learning model and predicting the usage amount and the valid period turnover rate of the medical articles; the first strategy module is used for determining a picking strategy for the medical articles according to the usage amount and the effective period turnover rate of the medical articles; the second strategy module is used for determining a deployment strategy for the medical articles according to the stock of the medical articles in the warehouses of all levels and the first expiry date turnover rate; the first management module is used for ordering and getting the medical articles according to the article getting strategy; and the second management module is used for deploying the medical articles according to the deploying strategy. According to the invention, the accuracy of medical article validity period management and medical article receiving and purchasing can be improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a medical product expiration date management system and electronic equipment based on machine learning. Background Art

[0002] In the current medical supplies management, most hospitals use manual records or simple electronic spreadsheets to manage the entry, exit and expiration of items. Usually, warehouse managers or medical staff are responsible for regularly checking the inventory status and expiration dates of items, and judging when to restock or deal with expired items based on experience.

[0003] However, manual inspection and record keeping are not only inefficient, but also prone to omissions or errors, especially when faced with a large number of medical supplies, and cannot achieve accurate expiration date management. Secondly, due to the lack of a systematic inventory forecasting mechanism, hospitals are often unable to reasonably arrange the purchase and allocation of supplies, resulting in over-purchase or shortage of supplies. Summary of the invention

[0004] In view of the technical problems existing in the prior art, the present invention provides a medical product expiration date management system and electronic equipment based on machine learning, which can improve the expiration date management of medical products and the accuracy of medical product collection and procurement.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] The present invention provides a medical product expiration date management system based on machine learning, the system comprising:

[0007] A data acquisition module, used to acquire item information of medical items to be managed, and warehouse information of warehouses at various levels;

[0008] A first computing module, used to process the item information through a machine learning model to predict the usage and expiration turnover rate of the medical item;

[0009] A first strategy module is used to determine a strategy for receiving the medical supplies according to the usage and validity period turnover rate of the medical supplies;

[0010] A second strategy module is used to determine a deployment strategy for the medical supplies according to the inventory of the medical supplies in the warehouses of each level and the first validity period turnover rate;

[0011] A first management module, used for ordering and picking up the medical supplies according to the picking up strategy;

[0012] The second management module is used to allocate the medical supplies according to the allocation strategy.

[0013] Furthermore, the first calculation module is specifically used for:

[0014] Obtaining the current inventory of the medical item;

[0015] Obtain the average monthly usage, average quarterly usage and expiration date of the medical items;

[0016] Performing weighted processing on the current inventory of the medical supplies to obtain a first processing result, and performing weighted sum processing on the monthly average usage, quarterly average usage and validity period of the medical supplies to obtain a second processing result;

[0017] The expiration turnover rate of the medical item is determined according to the first processing result and the second processing result.

[0018] Furthermore, the system also includes an inventory upper and lower limit module, which is used to:

[0019] Get the value of the current month;

[0020] The upper and lower inventory limits of the medical supplies are determined based on the values ​​of the current month, as well as the average monthly usage and the average quarterly usage of the medical supplies.

[0021] Furthermore, the inventory upper and lower limit module is also used for:

[0022] When the inventory of a first medical item is greater than the quarterly average usage of the first medical item, and the number of first medical items with a remaining validity period of less than 6 months accounts for more than 30% of the inventory of the first medical item, an inventory upper limit alarm is issued for the first medical item;

[0023] When the inventory quantity of a second medical item is less than the base number of the second medical item, an inventory lower limit alarm is issued for the second medical item; the base number of the second medical item is determined based on the average monthly usage, average quarterly usage and average annual usage of the second medical item.

[0024] Furthermore, the warehouses at each level include:

[0025] The third-level warehouse is set up in the ward and is used to realize the warehousing and storage of items in the entire ward;

[0026] The secondary warehouse is located in the treatment room of the ward. The items entering the secondary warehouse come from the tertiary warehouse, and the items leaving the warehouse flow to the primary warehouse or are used for consumption.

[0027] The first-level warehouse is set up in the ward treatment vehicle and the nursing vehicle. The incoming items of the first-level warehouse come from the second-level warehouse, and the outgoing items are used for consumption.

[0028] Furthermore, the first strategy module is also specifically used for:

[0029] Obtaining a first difference between an upper inventory limit and a current inventory of the medical item;

[0030] The order quantity of the medical supplies in the delivery strategy is determined based on the values ​​of the current month, the first difference value, the average monthly usage and the expiration date turnover rate of the medical supplies.

[0031] Furthermore, the second strategy module is specifically used for:

[0032] Obtaining a first inventory quantity of the medical supplies in the primary warehouse, a second inventory quantity in the secondary warehouse, and a third inventory quantity in the tertiary warehouse;

[0033] Obtaining a first validity period turnover rate of the medical supplies in the first-level warehouse, a second validity period turnover rate in the second-level warehouse, and a third validity period turnover rate in the third-level warehouse;

[0034] Determine a deployment priority of the medical items in the deployment strategy based on the first expiration turnover rate, the second expiration turnover rate, and the third expiration turnover rate, as well as the first inventory level, the second inventory level, and the third inventory level.

[0035] Furthermore, the system further includes a near expiration warning module, which is used to display warning prompt information of different colors according to the remaining validity period of the medical product, wherein:

[0036] When it is determined that the remaining validity period of the medical item is within one month, a red warning message is displayed;

[0037] When it is determined that the remaining validity period of the medical item is within three months, an orange warning message is displayed;

[0038] When it is determined that the remaining validity period of the medical item is within six months, a yellow warning prompt message is displayed.

[0039] Furthermore, the system also includes an item information updating module, which is used to:

[0040] Obtaining the item consumption record of the medical items by scanning the code on a mobile PDA;

[0041] The inventory information of the medical supplies is automatically updated according to the consumption records of the medical supplies.

[0042] In addition, to achieve the above-mentioned purpose, the present invention also proposes an electronic device, comprising: a memory for storing a computer software program; a processor for reading and executing the computer software program, thereby realizing the function of a medical product expiration management system based on machine learning as described above.

[0043] The beneficial effects of the present invention are:

[0044] (1) The present invention can realize automatic management of medical supplies information through data collection and standardized processing, reduce errors and omissions in manual records, and improve management efficiency. At the same time, the mobile PDA terminal is used to perform item entry and exit operations, and inventory information is updated in real time to ensure the accuracy and timeliness of inventory data.

[0045] (2) The present invention uses a machine learning model to predict the usage and turnover of items based on historical data and seasonal demand, and dynamically adjusts the upper and lower limits of inventory. The model can make adaptive adjustments based on the characteristics of different departments, ensure the rational allocation of inventory, reduce over-purchasing and material shortages, and improve the scientific nature of inventory management.

[0046] (3) The present invention can effectively track the expiration date of each item, give priority to consuming items that are about to expire, and reduce waste. The near-expiration warning system can remind management personnel in a graded manner to handle items that are about to expire in a timely manner, further improving the effectiveness of item use.

[0047] (4) The present invention uses an intelligent item collection algorithm and an item allocation optimization mechanism. The system can automatically recommend order quantities and allocation priorities based on expiration dates, inventory status, and usage frequency, thereby ensuring efficient and scientific use of items at all levels of warehouses and minimizing the risk of inventory backlogs and item expiration.

[0048] In summary, the present invention can not only improve the hospital's medical supplies management level, but also effectively reduce the supplies management cost, ensuring the timeliness of supplies supply and the safety of use. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A scenario diagram of a medical product expiration date management system based on machine learning provided by the present invention;

[0050] Figure 2 A schematic diagram of the structure of a medical product expiration date management system based on machine learning provided by the present invention;

[0051] Figure 3 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention. DETAILED DESCRIPTION

[0052] 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0053] See also Figure 1 , Figure 1 This is a scenario diagram of a medical product expiration date management system based on machine learning provided by the present invention. Figure 1 As shown, the terminal and the server are connected via a network, such as a wired or wireless network connection. The terminal may include but is not limited to portable terminals such as mobile phones and tablets installed with various network platform applications, as well as fixed terminals such as computers, query machines, and advertising machines. The server provides users with various business services, including service push servers, user recommendation servers, etc.

[0054] It should be noted that Figure 1 The scenario diagram of a medical item expiration management system based on machine learning is only an example. The terminal, server and application scenario described in the embodiment of the present invention are intended to more clearly illustrate the technical solution of the embodiment of the present invention, and do not generate limitations on the technical solution provided by the embodiment of the present invention. Ordinary technicians in this field can know that with the evolution of the system and the emergence of new business scenarios, the technical solution provided by the embodiment of the present invention is also applicable to similar technical problems.

[0055] Among them, the terminal can be used for:

[0056] Obtain item information of medical items to be managed, and warehouse information of warehouses at all levels;

[0057] Processing the item information through a machine learning model to predict the usage and expiration turnover rate of the medical items;

[0058] Determine the collection strategy for the medical supplies according to the usage and validity period turnover rate of the medical supplies;

[0059] Determine a deployment strategy for the medical supplies according to the inventory and first validity period turnover rate of the medical supplies in the warehouses of each level;

[0060] Ordering and picking up the medical supplies according to the picking up strategy;

[0061] The medical supplies are prepared according to the preparation strategy.

[0062] See also Figure 2 , Figure 2A schematic diagram of the structure of a medical product expiration date management system based on machine learning provided by the present invention.

[0063] like Figure 2 As shown, a medical item expiration date management system based on machine learning proposed in an embodiment of the present invention includes: a data acquisition module 101, a first calculation module 102, a second calculation module 103, a first strategy module 104, a first management module 105 and a second management module 106.

[0064] In some embodiments, the data acquisition module 101 can be used to acquire item information of medical items to be managed, and warehouse information of warehouses at various levels.

[0065] In some embodiments, the item information of medical items may include basic item information, such as item ID: a unique identification code for each medical item, used to distinguish different items. This is the basis for data processing and analysis, ensuring that the system can accurately locate each item. Item name: the name of the medical item, which is convenient for medical staff to identify and query. For example, medicines, consumables, medical equipment, etc. Specification model: detailed specification or model information of the item (such as the dosage of the medicine, packaging specifications, etc.) to ensure that items of different specifications can be properly managed and allocated.

[0066] In some embodiments, the item information of medical items may also include item inventory information, item expiration information, item consumption information, item category and department information, and other auxiliary information.

[0067] In some embodiments, item inventory information may include current inventory: the system needs to record the real-time inventory quantity of each item in each warehouse for inventory management and item allocation. This data is usually dynamic and is constantly updated as items are put in, taken out, and used. Inventory upper limit (UL) and inventory lower limit (LL): the system will set the upper and lower limits of inventory based on historical data and usage to ensure that the inventory does not exceed a reasonable range and avoid inventory backlogs or shortages.

[0068] In some embodiments, item expiration information may include production date: the time when the item was produced, which is very important for expiration management. The remaining validity period of the item can be derived from the production date, thereby ensuring that the item is used reasonably before it expires. Expiration Date (EP): The expiration date of an item is the length of time it can be used. The system uses this data to manage the expiration dates of items, and combines inventory and consumption to ensure that expired items are handled in a timely manner. Expiration Date Turnover Rate (ECR): The expiration date turnover rate is an indicator calculated based on the usage, inventory and expiration date of an item, which is used to measure the turnover efficiency of an item during its validity period. Based on this value, the system will determine whether certain items need to be used first to avoid expiration waste.

[0069] It should be noted that the validity period of the present invention does not refer to the remaining validity period, but to the production validity period of the item itself; the items here include medicines, commonly used medical consumables, etc., but do not include various types of diagnostic and treatment instruments, instruments and items cleaned, disinfected and sterilized by the disinfection supply center. Among them, short-term validity items refer to medical items with a validity period of less than 1 year, medium-term validity items refer to medical items with a validity period of 1-3 years, and long-term validity items refer to medical items with a validity period of more than 3 years.

[0070] In some embodiments, item consumption information may include monthly average usage (MU): the average usage of an item each month over a period of time. This data is used to predict future usage needs and help the system dynamically adjust the upper and lower limits of inventory. Quarterly average usage (SU): average usage calculated on a quarterly basis, used for longer-term inventory demand analysis. Yearly average usage (YU): average usage of an item calculated on a yearly basis, to help analyze the long-term consumption trend of an item.

[0071] In some embodiments, the item category and department information may include item category: the system may classify items according to their nature, such as medicines, consumables, equipment, etc. Items of different categories may have different management requirements. Use department: the system will record the use department of each item, such as internal medicine, surgery, emergency, etc. This helps to manage items in combination with the needs and characteristics of the department, especially when formulating the collection strategy and inventory allocation.

[0072] In some embodiments, other auxiliary information may include price: unit price information of the item, which helps the system to make cost management and item purchasing decisions. Storage conditions: Some medical items require special storage conditions (such as temperature, humidity, etc.), and the system will record this information so that the items can be stored under the required conditions.

[0073] In some embodiments, the above item information can be acquired and entered into the system by manual entry, barcode scanning or automatic docking. For small-scale medical institutions, initial data may be imported through manual entry or Excel spreadsheets. Barcode or QR code technology can be used to collect item information in real time and synchronize it to the system when items are put in, out of the warehouse and counted through PDA or mobile terminal devices. For large hospitals, item information may be directly docked and automatically imported into the inventory management system through the hospital information management system (HIS) or the drug supply chain system (such as ERP).

[0074] It is understandable that obtaining detailed information on medical supplies is crucial for subsequent expiration date management, inventory forecasting, allocation optimization, and smart ordering. Accurate and comprehensive information can: Realize refined management of supplies to avoid expiration, backlogs, or shortages. Provide data support to help the system perform intelligent forecasting and inventory optimization through machine learning models. Through expiration date management, dynamic inventory adjustment, and item allocation, ensure the efficient operation of the hospital's item supply chain to meet clinical needs.

[0075] In summary, obtaining medical product information is the first step in building an intelligent medical product expiration management system, which provides a data foundation for subsequent intelligent management.

[0076] In some embodiments, each level of warehouse may include:

[0077] The third-level warehouse is set up in the ward and is used to realize the warehousing and storage of items in the entire ward;

[0078] The secondary warehouse is located in the treatment room of the ward. The items entering the secondary warehouse come from the tertiary warehouse, and the items leaving the warehouse flow to the primary warehouse or are used for consumption.

[0079] The first-level warehouse is set up in the ward treatment vehicle and the nursing vehicle. The incoming items of the first-level warehouse come from the second-level warehouse, and the outgoing items are used for consumption.

[0080] In some embodiments, the first computing module 102 can be used to process the item information through a machine learning model to predict the usage and expiration turnover rate of the medical items.

[0081] In some embodiments, the model can be fed with data related to medical products. Such data will serve as the basis for predicting the usage of the products, including:

[0082] Historical usage data: including the monthly average usage (MU), quarterly average usage (SU), and annual average usage (YU) of items. These data reflect the historical consumption trend of items.

[0083] Inventory information: current inventory quantity (I), upper inventory limit (UL) and lower inventory limit (LL), etc., used to guide forecasted inventory management.

[0084] Expiration date information: The item’s expiration date (EP), production date, and expiration date turnover rate (ECR) help the system dynamically adjust the predicted usage based on the item’s expiration date.

[0085] Seasonality and department demand data: The demand for medical supplies may vary in different seasons and departments, such as the increased demand for antiviral drugs during the flu season. These specific seasonal factors are also important inputs to the forecasting model.

[0086] In some embodiments, historical data can be used to train a machine learning model to improve the accuracy of predicting item usage. By analyzing historical data, the machine learning model can identify usage patterns and trends hidden in the data and make adaptive adjustments.

[0087] In some embodiments, after the machine learning model is trained, the system can predict future usage based on current item information. This step generates future item demand by processing existing data through the model, usually based on a certain time period in the future (such as the next month, quarter, or year). The model can adjust the prediction of future item usage based on seasonal fluctuations in historical data. For example, in winter, the demand for antibiotics and antiviral drugs may increase, and the model will recognize this pattern and increase the predicted usage. Different departments have different needs for items, and the model can predict the future usage of a specific item in a department based on the historical usage of the department. For example, the emergency department may need more disposable medical consumables, and the prediction model will make accurate estimates based on historical data. By combining the expiration information of the item, the model can avoid predicting usage that exceeds the expiration range of the item. For example, some items that are about to expire may need to be consumed in advance, and the model will adjust the short-term usage prediction based on the expiration information to avoid waste. The system can dynamically adjust the prediction results based on changes in current inventory. For example, if the current inventory of an item is close to the lower limit, the model will predict an increase in future usage demand accordingly and trigger an automatic replenishment or allocation process.

[0088] In some embodiments, the prediction results can help the system dynamically adjust the upper and lower limits of inventory to ensure that the inventory level remains within a reasonable range. For items with high frequency of use, the system will increase the upper limit of inventory based on the prediction; for items with low frequency of use or reduced demand, the system will reduce the purchase volume or lower the upper limit of inventory. The system can automatically generate ordering suggestions based on future item demand and trigger replenishment based on real-time inventory status. For example, if the predicted usage of an item is high and the inventory is close to the lower limit, the system will automatically recommend purchases and issue replenishment requests. By predicting the demand for items in different departments or warehouses, the system can optimize the cross-warehouse allocation of items to ensure that items at all levels of warehouses are reasonably allocated and avoid inventory shortages or backlogs in some warehouses. By predicting the demand for items in different departments or warehouses, the system can optimize the cross-warehouse allocation of items to ensure that items at all levels of warehouses are reasonably allocated and avoid inventory shortages or backlogs in some warehouses. For the hospital's long-term material procurement and budget planning, the results of the prediction model can provide important data support for management to help them formulate item procurement plans for the next few months or years and optimize costs.

[0089] It is understandable that as the system continues to run, new item usage data will continue to be input into the machine learning model. The system will continue to train and optimize the model based on the new data to improve the prediction accuracy. For some items with obvious seasonal changes or special departmental needs, the model can make adaptive adjustments to dynamically track changes in item demand to make the prediction more accurate.

[0090] The present invention uses a machine learning model to process medical supplies information and predict usage, so that item management is transformed from traditional empirical judgment to data-driven intelligent prediction. This process integrates multi-dimensional data such as historical usage data, inventory status, expiration date management, and seasonal demand, providing an efficient and accurate decision-making basis for the procurement, inventory management, and item allocation of medical supplies. This can not only greatly reduce item waste and avoid inventory shortages, but also significantly improve the overall efficiency of hospital supply chain management.

[0091] In some embodiments, the first calculation module 102 may be specifically configured to:

[0092] Obtaining the current inventory of the medical item;

[0093] Obtain the average monthly usage, average quarterly usage and expiration date of the medical items;

[0094] Performing weighted processing on the current inventory of the medical supplies to obtain a first processing result, and performing weighted sum processing on the monthly average usage, quarterly average usage and validity period of the medical supplies to obtain a second processing result;

[0095] The expiration turnover rate of the medical item is determined according to the first processing result and the second processing result.

[0096] In some practical examples, the expiration turnover rate of medical items can be expressed as:

[0097]

[0098] Among them, ECR is the validity period turnover rate, I is the current inventory, MU is the average monthly usage, SU is the average quarterly usage, YU is the average annual usage, EP is the value of the validity period, α, β, γ, δ are the first weight, second weight, third weight and fourth weight respectively.

[0099] In specific implementation, ECR is the validity period turnover rate, which reflects whether the items can be consumed in time before the expiration date. Through the calculation of ECR, the turnover speed of inventory items can be evaluated to help determine whether it is necessary to speed up consumption or adjust inventory strategies to avoid expiration.

[0100] I is the current inventory, which refers to the actual inventory quantity of the item in the system at the current moment. The larger the inventory, theoretically, the higher the turnover efficiency required to consume it in time within the validity period. Therefore, I as the numerator represents its positive impact on ECR.

[0101] MU is the average monthly usage, which indicates the average monthly consumption of the item in the past period of time. The amount of usage directly affects the speed of inventory consumption. The larger the average monthly usage, the higher the turnover rate, so this item is part of the denominator, reflecting the impact of usage frequency on expiration management.

[0102] SU is the quarterly average usage, which is the average usage calculated on a quarterly basis over the past few months. Quarterly average usage reflects the usage trend of items over a longer period of time, and it is multiplied by the square root of the expiration date to smooth out short-term fluctuations.

[0103] YU is the average annual usage, which is the average usage of the item in the past year, and can comprehensively reflect the fluctuation of the usage frequency throughout the year. Using ln(YU×EP) means that the value is logarithmically smoothed to make its impact more stable, so as to avoid excessive influence of short-term abnormal data.

[0104] EP is the value of the validity period, which is the length of time from the entry of an item into the warehouse to its expiration, usually in months. The validity period directly affects the urgency of the item's consumption. The shorter the validity period, the higher the turnover rate needs to be to ensure that the item is used up before it expires.

[0105] α, β, γ, δ are the first weight, the second weight, the third weight, and the fourth weight, respectively.

[0106] Specifically, the numerator of α×I is composed of the current inventory I and the weight α, which represents the impact of inventory on turnover rate. The larger the inventory, the higher the turnover efficiency is required to ensure that the items are consumed within the validity period.

[0107] In β×MU×EP+γ×SU×EP+δ×ln(YU×EP), β×MU×EP represents the product of the average monthly usage and the validity period, reflecting the consumption rate of inventory by monthly usage, and the weight β makes it adjustable.

[0108] The product of the quarterly average usage and the square root of the validity period is used to smooth short-term fluctuations, and the weight γ makes this part more flexible to the consumption patterns of different items.

[0109] δ×ln(YU×EP) is the logarithmic function of the average annual usage and the validity period. The weight δ adjusts its impact on the long-term consumption trend, ensuring that the system can optimize inventory management based on usage data at different time scales.

[0110] It can be understood that the larger the ECR value, the higher the turnover rate of inventory items and the greater the probability that the items will be consumed in time within the validity period; the smaller the ECR value, the greater the risk of expiration or backlog of the item, and the management personnel need to take corresponding measures.

[0111] The present invention can help hospitals and medical institutions accurately evaluate the effectiveness of item expiration management, dynamically adjust inventory strategies based on different usage frequencies, expiration dates and historical data, and ensure reasonable turnover and inventory optimization of items. By reasonably adjusting the weight coefficient, the system can adapt to the specific needs of different departments and items, reducing the risk of expiration or shortage of medical items.

[0112] In some embodiments, the system of the present invention further includes an inventory upper and lower limit module for:

[0113] Get the value of the current month;

[0114] The upper and lower inventory limits of the medical supplies are determined based on the values ​​of the current month, as well as the average monthly usage and the average quarterly usage of the medical supplies.

[0115] In some embodiments, the upper and lower inventory limits may be expressed as:

[0116]

[0117] Among them, UL is the upper limit of inventory, LL is the lower limit of inventory, MU is the average monthly usage, SU is the average quarterly usage, YU is the average annual usage, t is the value of the current month, μ, σ, λ, ρ are the first adjustment coefficient, the second adjustment coefficient, the third adjustment coefficient, and the fourth adjustment coefficient, respectively.

[0118] In the specific implementation, μ is the key coefficient used to adjust the entire inventory limit. Through this parameter, the inventory limit can be adjusted according to different item characteristics (such as importance, shelf life, etc.), so that the system can adapt to different demand situations.

[0119] MU×3 represents the high-frequency demand for items in the short term (monthly). Usually, the demand for items is relatively stable within a month. Multiplying by 3 means that the system tends to prepare three months of inventory reserves to cope with possible short-term fluctuations.

[0120] It is used to assess the demand for items in the long term (annual). Adding the average annual usage can ensure that the system has sufficient long-term inventory support. Taking a quarter is to balance short-term demand with long-term demand and avoid excessive long-term reserves.

[0121] Reflects the seasonal fluctuations in inventory demand. t is the input parameter for seasonal adjustment based on monthly changes. The value of t ranges from 1 to 12, corresponding to the 12 months of the year. Used to reflect seasonal cyclic fluctuations in demand for items, with a period of 12 months. The value of the sine function changes periodically throughout the year, simulating seasonal fluctuations in demand. For example, demand for medicines surges in certain months (such as winter flu season), and the peaks of the sine function reflect this fluctuation. σ controls the magnitude of seasonal fluctuations. Different items have different sensitivities to seasonal fluctuations, and the size determines the extent to which the sine wave affects the inventory ceiling.

[0122] λ is similar to μ in that it is a coefficient that adjusts the entire inventory floor. It controls the overall size of the inventory floor to ensure that the minimum inventory of different items meets actual demand and management requirements. Reflects medium-term demand. Taking into account quarterly fluctuations, one-third of quarterly demand should be retained in the inventory floor to ensure that inventory will not be depleted due to fluctuations in a short period of time.

[0123] It is used to reflect long-term demand and smooth the demand throughout the year to ensure the rationality of long-term inventory reserves. Taking one-twelfth of the average annual demand is to prevent the inventory of items that have not been used for a long time from taking up too many resources.

[0124] Used to reflect seasonal changes in demand.

[0125] The present invention dynamically adjusts the inventory limit by combining the short-term (monthly), medium-term (quarterly) and long-term (annual) demand for items to cope with changes in usage frequency, and captures seasonal fluctuations through a sinusoidal function, making the inventory limit more flexible and in line with actual needs.

[0126] It is the opposite of the sine function in a one-year cycle and is used to represent the impact of seasonal changes on the inventory floor. Its function is to simulate the decrease in certain seasonal demand and reduce the inventory floor to avoid over-replenishment.

[0127] ρ is used to control the impact of seasonal demand changes on the inventory lower limit. Different items have different sensitivities to seasonal changes, and the size of ρ determines the adjustment range of the cosine wave on the inventory lower limit.

[0128] The present invention dynamically adjusts the upper and lower limits of inventory by combining the short-term (monthly), medium-term (quarterly) and long-term (annual) demands for items to cope with changes in usage frequency, and captures seasonal fluctuations through a sinusoidal function, making the upper limit of inventory more flexible and in line with actual needs.

[0129] In some embodiments, the inventory limit module is further configured to:

[0130] When the inventory of a first medical item is greater than the quarterly average usage of the first medical item, and the number of first medical items with a remaining validity period of less than 6 months accounts for more than 30% of the inventory of the first medical item, an inventory upper limit alarm is issued for the first medical item;

[0131] When the inventory quantity of a second medical item is less than the base number of the second medical item, an inventory lower limit alarm is issued for the second medical item; the base number of the second medical item is determined based on the average monthly usage, average quarterly usage and average annual usage of the second medical item.

[0132] In some embodiments, the first strategy module 103 may be used to determine a collection strategy for the medical supplies based on the usage and expiration turnover rate of the medical supplies.

[0133] In some embodiments, the first policy module 103 is specifically used to:

[0134] Obtaining a first difference between an upper inventory limit and a current inventory of the medical item;

[0135] The order quantity of the medical supplies in the delivery strategy is determined based on the values ​​of the current month, the first difference value, the average monthly usage and the expiration date turnover rate of the medical supplies.

[0136] In some embodiments, the order quantity is expressed as:

[0137]

[0138] Among them, OQ is the order quantity, MU is the average monthly usage, UL is the inventory upper limit, I is the current inventory, ECR is the validity period turnover rate, ∈, ∈, φ are the fifth, sixth, and seventh weights, respectively.

[0139] In the specific implementation, is a seasonal fluctuation correction term, which is used to adjust the order quantity to reflect the seasonal changes in demand for items and is corrected based on a sine function.

[0140] t is the numeric value of the current month (1-12) and is used to determine the current time's position in the year. The sine function has a period of 12 months and simulates seasonal demand fluctuations. For example, the demand for certain medical items may increase significantly in certain seasons (such as winter), and the sine function fluctuations can accurately reflect these changes. ∈ is the adjustment coefficient, which is used to control the amplitude of seasonal fluctuations. Different items have different sensitivities to seasonal fluctuations, and the size of ∈ determines the impact of seasonal fluctuations on the order quantity. Through the sine function correction, the order quantity can be adjusted dynamically to ensure that the order quantity is increased during the peak demand season and reduced during the off-season, thereby optimizing the inventory level.

[0141] ω is the fifth weight, which is used to adjust the first part of the formula, which is the impact of average monthly usage on order quantity. It determines the impact of historical usage data on ordering decisions. By adjusting ω, the system can determine the weight of this part based on the importance of the item or other factors.

[0142] In the middle, φ is the seventh weight, which is used to adjust the second part of the formula, that is, the impact of the difference between the inventory upper limit and the current inventory on the order quantity. It determines the degree of impact of the inventory difference on the order quantity. By adjusting φ, the system can decide whether to quickly reduce the order quantity when the inventory is close to the upper limit.

[0143] This part represents the basic order quantity based on the average monthly usage and seasonal fluctuations. By adjusting ω and ∈, the system can dynamically adjust the order quantity according to the historical usage frequency of the item and seasonal demand changes, ensuring timely replenishment during the peak season and reducing purchases during the off-season.

[0144] This part further modifies the order quantity based on the current inventory status and expiration turnover rate. By adjusting φ and ECR, the system can dynamically balance the order quantity with the inventory limit to avoid overstocking or shortage of items.

[0145] In the present invention, the larger the OQ value, the more the item needs to be ordered; the smaller the OQ value, the more sufficient the current inventory of the item is and no large-scale replenishment is required. This combines multiple factors such as historical usage data, current inventory, inventory limit, and expiration date turnover rate to ensure that ordering decisions are both reasonable and flexible, thereby maximizing the efficiency of inventory management.

[0146] In some embodiments, the second strategy module 104 may be used to determine a deployment strategy for the medical supplies based on the inventory levels of the medical supplies in the warehouses at each level and the first validity period turnover rates.

[0147] In some embodiments, the second policy module 104 is specifically configured to:

[0148] Obtaining a first inventory quantity of the medical supplies in the primary warehouse, a second inventory quantity in the secondary warehouse, and a third inventory quantity in the tertiary warehouse;

[0149] Obtaining a first validity period turnover rate of the medical supplies in the first-level warehouse, a second validity period turnover rate in the second-level warehouse, and a third validity period turnover rate in the third-level warehouse;

[0150] Determine a deployment priority of the medical items in the deployment strategy based on the first expiration turnover rate, the second expiration turnover rate, and the third expiration turnover rate, as well as the first inventory level, the second inventory level, and the third inventory level.

[0151] In some embodiments, the deployment priority can be expressed as:

[0152]

[0153] Among them, TP is the deployment priority, I 1 ,I 2 ,I 3 They are the first inventory, the second inventory and the third inventory, ECR 1 、ECR 2 、ECR 3 They are the first-period turnover rate, the second-period turnover rate, and the third-period turnover rate respectively, and ψ is the fifth adjustment coefficient.

[0154] In specific implementation, TP is the allocation priority determined by the system for a certain item in different warehouses. The larger the value, the more likely the item should be allocated and used from the warehouse first. By calculating the allocation priority, the system can effectively manage the cross-warehouse allocation of items, give priority to the use of items with high turnover and those that are about to expire, and avoid inventory backlogs and item expiration.

[0155] I 1 ×ECR 1 +I 2 ×ECR 2 +I 3 ×ECR 3 The inventory of three different warehouses I 1 ,I 2 ,I 3 Multiply each by its corresponding validity period turnover rate ECR 1 、ECR 2 、ECR 3 , and sum them up. It represents the contribution of inventory items in each warehouse to the overall turnover efficiency.

[0156] In some embodiments, I 1 It is the inventory of the first-level warehouse, usually the inventory of items in the ward treatment cart or nursing cart, which is directly used in the ward or clinical use. 2 It is the inventory in the secondary warehouse, usually the inventory in the ward treatment room, used as ward reserve.3 It is the inventory of the third-level warehouse, usually the inventory of the ward warehouse, which is the long-term reserve of the entire ward. The inventory is an important factor affecting the allocation priority. Usually, items in small inventory warehouses (such as first-level or second-level warehouses) are allocated first to maximize their use efficiency and reduce the risk of expiration.

[0157] The higher the expiration turnover rate, the faster the items in the warehouse are consumed, the faster the inventory turnover, and the higher the priority. By multiplying the inventory volume with the expiration turnover rate, the system can reasonably balance the efficiency of item use and inventory level, and avoid long-term storage of low-turnover items.

[0158] I 1 +I 2 +I 3 is the total inventory of the item in the primary, secondary, and tertiary warehouses. The total inventory is used as the denominator to normalize the inventory contribution of each warehouse. This allows the system to evaluate the allocation priority of the entire inventory of the item, rather than considering only one warehouse in isolation. This normalization allows the system to ensure that the item is evenly allocated between warehouses, avoiding overstocking or depletion of inventory in one warehouse.

[0159] μ is the fifth adjustment coefficient, which is used to adjust the weight of the allocation priority as a whole. The overall output scale of the control formula is adjusted to adapt the allocation priority value to the specific management needs. By adjusting the value of μ, the system can adjust the allocation strategy according to actual needs. For example, for highly consumable or expiration-sensitive items, the allocation priority may need to be increased, so the value of ψ can be appropriately increased.

[0160] In some embodiments, the system of the present invention may further include a near expiration warning module, which is used to display warning prompt information of different colors according to the remaining validity period of the medical product, wherein:

[0161] When it is determined that the remaining validity period of the medical item is within one month, a red warning message is displayed;

[0162] When it is determined that the remaining validity period of the medical item is within three months, an orange warning message is displayed;

[0163] When it is determined that the remaining validity period of the medical item is within six months, a yellow warning prompt message is displayed.

[0164] It can be understood that the red, orange and yellow colors, which are arranged in descending order according to their degree of eye-catchingness, can represent the severity of the remaining validity period in turn, and the shorter the remaining validity period, the higher and more serious the corresponding warning level.

[0165] In some embodiments, the system of the present invention may further include an item information updating module, which is used to:

[0166] Obtaining the item consumption record of the medical items by scanning the code on the mobile PDA terminal;

[0167] The inventory information of the medical supplies is automatically updated according to the consumption records of the medical supplies.

[0168] Among them, mobile PDA (Personal Digital Assistant) devices are usually equipped with a barcode scanning function. Each medical item has a unique barcode or QR code. By scanning the barcode through the PDA end, relevant information of the item, such as the item name, specification, batch number, expiration date, etc., can be quickly and accurately obtained.

[0169] When medical staff use medical supplies in clinical scenarios, they first scan the barcode of the item through the PDA. The system will automatically identify the information of the item and record the consumption behavior. After scanning the code, the information of the item will be immediately transmitted to the management system, including the name of the item, inventory number, production batch, expiration date, etc. At the same time, information such as the consumption time of the item, the department using it, and the operator will also be synchronously recorded in the system. Based on the scanning results, the system will generate a consumption record of the item in real time, recording its usage quantity, delivery time, use location, etc. These data will be used for subsequent inventory updates and analysis.

[0170] By scanning the barcode on the PDA, the item consumption record can reflect the usage of inventory items in real time, avoiding delays or omissions caused by traditional manual records. The barcode of each item is unique, ensuring the accurate transmission of item information, eliminating the possibility of errors in manual records, and improving the accuracy of inventory management. The system records the consumption information of each item, including the operator, place of use and time, to facilitate future traceability and statistical analysis of item usage.

[0171] In some embodiments, when an item has recorded its consumption behavior by scanning a code, the system will immediately adjust the inventory quantity of the corresponding item according to the consumption record. For example, if the original inventory of an item is 100 pieces and 5 pieces are used, the system will automatically update the inventory quantity of the item to 95 pieces. Medical supplies are usually distributed in different inventory levels (such as primary, secondary, and tertiary warehouses). Each item consumption record will accurately reflect the inventory changes of the item at the corresponding level. For example, if an item is consumed in a primary warehouse (treatment vehicle), the system will automatically update the inventory of the primary warehouse. If an item is shipped out of a warehouse (for example, transferred from a third-level warehouse to a first-level warehouse), after scanning the code to record the outbound information, the system will synchronously update the inventory data of the two warehouses to ensure that the circulation of the item is tracked globally.

[0172] After an item is shipped out or consumed, the system obtains the consumption record of the item, including the shipment quantity, shipping warehouse, using department and other information. The system automatically calculates the remaining inventory: Based on the quantity of the item consumed in the warehouse, the system automatically reduces the inventory of the corresponding warehouse. Expiration date management: When the system updates the inventory, it will also track the expiration date of the item. If a batch of items is about to expire, the system will trigger an expiration date warning to remind relevant personnel to give priority to the use of the item and reduce expiration waste. Adjustment of upper and lower limits of inventory: Based on the real-time changes in inventory, the system dynamically monitors whether the inventory of the item is lower than the lower limit or higher than the upper limit of inventory. If it is lower than the lower limit, a replenishment reminder will be issued. If it is higher than the upper limit, a prompt will be issued to reduce purchases.

[0173] Through automated inventory updates, the tedious steps of manually adjusting inventory are eliminated, the real-time and accuracy of inventory information is guaranteed, and the efficiency of material management is significantly improved. The system's real-time updated inventory information can provide a complete inventory visualization status, allowing managers to keep track of the inventory status of each warehouse at any time to avoid excessive or insufficient inventory. Based on real-time inventory data, the system can further generate replenishment suggestions, item allocation suggestions, and inventory reports to help managers make more scientific material procurement and scheduling decisions.

[0174] The present invention obtains the item consumption record of medical items by scanning the code on the mobile PDA terminal, and automatically updates the inventory information according to the record, so as to realize the real-time update and automatic management of the inventory information. This method not only improves the efficiency and accuracy of item use and inventory update, but also provides a data basis for intelligent management functions such as dynamic inventory adjustment, expiration date management, and item allocation, ensuring that the use and management of medical items are more efficient and reliable, and avoiding waste and shortage problems.

[0175] In some embodiments, the first management module 105 can be used to order and collect the medical supplies according to the collection strategy.

[0176] In some embodiments, when the inventory is lower than the lower limit (LL) set by the system, the system will automatically issue a replenishment reminder and calculate a reasonable order quantity based on the order quantity formula. If the inventory is close to the upper limit (UL), the system will reduce or suspend ordering to avoid backlogs. Once the system determines that an order is needed, the relevant department can directly issue a purchase order to the supplier based on the ordering plan generated by the system to ensure that the items can arrive on time and the inventory can be replenished in time.

[0177] In some embodiments, when medical staff pick up items, they can scan the code through the PDA device to pick up the items from the warehouse, record them in real time in the system, and automatically update the inventory information. The system will automatically adjust the inventory and allocate it according to the actual usage of the items.

[0178] Through the collection strategy of the present invention, the system can automatically evaluate the usage, inventory status and expiration date of the items, dynamically adjust the ordering and collection process, ensure the reasonable flow of items, inventory safety and expiration date management, and ultimately achieve efficient supply chain management of medical supplies.

[0179] In some embodiments, the second management module 106 can be used to allocate the medical supplies according to the allocation strategy.

[0180] In some embodiments, the allocation operation may mainly include the following scenarios: allocation from the third-level warehouse to the first-level warehouse and the second-level warehouse, allocation based on validity period priority, and allocation based on usage needs. In the specific implementation, the items in the first-level warehouse (such as the ward treatment vehicle) are directly used for clinical use, so they are consumed quickly and have a high turnover rate. If the system detects that the inventory in the first-level warehouse is lower than the lower limit (LL), automatic allocation is triggered. The system calculates the priority of the item in the third-level warehouse according to the inventory situation in the third-level warehouse (long-term reserve) through the allocation priority formula. If the priority is high, a certain number of items will be allocated from the third-level warehouse to the first-level or second-level warehouse. After allocation, the system will update the inventory information of each warehouse, and adjust the inventory upper limit (UL) and lower limit (LL) values ​​to ensure the inventory balance of each warehouse.

[0181] The system can sort the items in different warehouses according to the expiration turnover rate (ECR), giving priority to those items that are about to expire or have a higher turnover rate. For example, if the expiration date of an item in a third-level warehouse is about to expire, the system will prioritize its allocation to the first-level or second-level warehouse to ensure that the item is used first in clinical practice and avoids expiration. In this case, the expiration turnover rate ECR in the allocation priority formula has a greater impact on the allocation decision. For warehouses with lower turnover rates or larger inventory volumes, the system will prioritize the items to be transferred out to reduce inventory backlogs.

[0182] The system can predict the demand for certain items in different departments. For example, the emergency department may have a greater demand for emergency medicines. Based on the prediction results, the system will prioritize the allocation of these items from the third-level warehouse to the second-level or first-level warehouse of the emergency department. The calculation of the allocation priority combines the warehouse's inventory and expiration date management to ensure that the items with high demand are used first and that clinical needs can be met.

[0183] Through the above methods, the system can monitor the inventory changes of each warehouse in real time and adjust the allocation strategy according to the inventory status of the warehouse. For example, if the inventory of a warehouse is about to fall below the lower limit, the system will allocate items from the superior warehouse in advance to replenish the inventory. When the expiration date of a batch of items is approaching, the system will prioritize the allocation of these items to warehouses with higher frequency of use to ensure that they are used first and reduce the risk of expiration. The adjustment coefficient in the ψ allocation priority formula can be adjusted according to the actual needs of the hospital. For example, for some items of high importance and urgent need, the system can appropriately increase the value of ψ to increase the allocation priority of these items.

[0184] By allocating items according to the inventory and expiration dates of each warehouse, the system can give priority to items that are about to expire or have a high turnover rate, reduce waste, and ensure that items are fully utilized. The allocation strategy can reasonably balance the inventory of warehouses at all levels to avoid backlogs or shortages of items in certain warehouses. At the same time, by dynamically adjusting the upper and lower limits of inventory, the system can optimize the procurement and allocation of items and reduce unnecessary inventory occupation. The allocation strategy runs automatically without manual intervention, which greatly improves the efficiency and accuracy of item allocation and reduces the burden of manual management. By predicting changes in demand in each department, the system can flexibly adjust the allocation strategy of items to ensure that clinical needs are met in a timely manner.

[0185] The present invention intelligently controls the flow of items between different warehouses through multiple factors such as allocation priority formula, inventory monitoring and expiration date management. This strategy can optimize inventory management, ensure that items are reasonably allocated and used, reduce expiration and inventory backlogs, and improve the efficiency of item use and the ability to respond to clinical needs.

[0186] In summary, the present invention can not only improve the hospital's medical supplies management level, but also effectively reduce the supplies management cost, ensuring the timeliness of supplies supply and the safety of use.

[0187] See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 400, including a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor 420. When the processor 420 executes the computer program 411, the following steps are implemented:

[0188] Obtain item information of medical items to be managed, and warehouse information of warehouses at all levels;

[0189] Processing the item information through a machine learning model to predict the usage and expiration turnover rate of the medical items;

[0190] Determine the collection strategy for the medical supplies according to the usage and validity period turnover rate of the medical supplies;

[0191] Determine a deployment strategy for the medical supplies according to the inventory and first validity period turnover rate of the medical supplies in the warehouses of each level;

[0192] Ordering and picking up the medical supplies according to the picking up strategy;

[0193] The medical supplies are prepared according to the preparation strategy.

[0194] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0195] Those skilled in the art will appreciate that embodiments of the present invention may provide a system or computer program product. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects.

Claims

1. A medical product expiration date management system based on machine learning, characterized in that: The system comprises: A data acquisition module, used to acquire item information of medical items to be managed, and warehouse information of warehouses at various levels; A first computing module, configured to process the item information through a machine learning model to predict the usage and expiration turnover rate of the medical item; A first strategy module is used to determine a strategy for receiving the medical supplies according to the usage and validity period turnover rate of the medical supplies; A second strategy module is used to determine a deployment strategy for the medical supplies according to the inventory of the medical supplies in the warehouses of each level and the first validity period turnover rate; A first management module, used for ordering and picking up the medical supplies according to the picking up strategy; The second management module is used to allocate the medical supplies according to the allocation strategy.

2. The medical product expiration date management system based on machine learning according to claim 1, characterized in that: The first calculation module is specifically used for: Obtaining the current inventory of the medical item; Obtain the average monthly usage, average quarterly usage and expiration date of the medical items; Performing weighted processing on the current inventory of the medical supplies to obtain a first processing result, and performing weighted sum processing on the monthly average usage, quarterly average usage and validity period of the medical supplies to obtain a second processing result; The expiration turnover rate of the medical item is determined according to the first processing result and the second processing result.

3. The medical product expiration date management system based on machine learning according to claim 2, characterized in that: The system also includes an inventory upper and lower limit module for: Get the value of the current month; The upper and lower inventory limits of the medical supplies are determined based on the values ​​of the current month, as well as the average monthly usage and the average quarterly usage of the medical supplies.

4. The medical product expiration date management system based on machine learning according to claim 3 is characterized in that: The inventory upper and lower limit module is also used for: When the inventory of a first medical item is greater than the quarterly average usage of the first medical item, and the number of first medical items with a remaining validity period of less than 6 months accounts for more than 30% of the inventory of the first medical item, an inventory upper limit alarm is issued for the first medical item; When the inventory quantity of a second medical item is less than the base number of the second medical item, an inventory lower limit alarm is issued for the second medical item; the base number of the second medical item is determined based on the average monthly usage, average quarterly usage and average annual usage of the second medical item.

5. The medical product expiration date management system based on machine learning according to claim 4, characterized in that: The warehouses at each level include: The third-level warehouse is set up in the ward and is used to realize the warehousing and storage of items in the entire ward; The secondary warehouse is located in the treatment room of the ward. The items entering the secondary warehouse come from the tertiary warehouse, and the items leaving the warehouse flow to the primary warehouse or are used for consumption. The first-level warehouse is set up in the ward treatment vehicle and the nursing vehicle. The incoming items of the first-level warehouse come from the second-level warehouse, and the outgoing items are used for consumption.

6. The medical product expiration date management system based on machine learning according to claim 5, characterized in that: The first strategy module is further specifically configured to: Obtaining a first difference between an upper inventory limit and a current inventory of the medical item; The order quantity of the medical supplies in the delivery strategy is determined based on the values ​​of the current month, the first difference value, the average monthly usage and the expiration date turnover rate of the medical supplies.

7. The medical product expiration date management system based on machine learning according to claim 6, characterized in that: The second strategy module is specifically used for: Obtaining a first inventory quantity of the medical supplies in the primary warehouse, a second inventory quantity in the secondary warehouse, and a third inventory quantity in the tertiary warehouse; Obtaining a first validity period turnover rate of the medical supplies in the first-level warehouse, a second validity period turnover rate in the second-level warehouse, and a third validity period turnover rate in the third-level warehouse; Determine a deployment priority of the medical items in the deployment strategy based on the first expiration turnover rate, the second expiration turnover rate, and the third expiration turnover rate, as well as the first inventory level, the second inventory level, and the third inventory level.

8. The medical product expiration date management system based on machine learning according to claim 7, characterized in that: The system also includes a near expiration warning module, which is used to display warning prompt information of different colors according to the remaining validity period of the medical product, wherein: When it is determined that the remaining validity period of the medical item is within one month, a red warning message is displayed; When it is determined that the remaining validity period of the medical item is within three months, an orange warning message is displayed; When it is determined that the remaining validity period of the medical item is within six months, a yellow warning prompt message is displayed.

9. The medical product expiration date management system based on machine learning according to any one of claims 1 to 8, characterized in that: The system further comprises an item information updating module, which is used to: Obtaining the item consumption record of the medical items by scanning the code on the mobile PDA terminal; The inventory information of the medical supplies is automatically updated according to the consumption records of the medical supplies.

Images