Medicine inventory monitoring method, related device, equipment and storage medium
By using historical drug usage and surgical data to generate predicted drug usage and surgical data and adjusting drug inventory monitoring values, the problem of drug demand fluctuations in static inventory management is solved, and the accuracy and effectiveness of drug inventory monitoring are improved.
Patent Information
- Application Number
- CN202510593728.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-08
- Publication Date
- 2025-10-03
AI Technical Summary
The drug inventory monitoring based on static inventory management methods in existing technologies is less effective and cannot effectively respond to fluctuations in drug demand in medical activities, leading to problems of insufficient or oversupply.
Based on the historical medication data and surgical data of the target drug, predicted medication dosage and predicted surgical data are generated, the predicted medication dosage is adjusted using the adjustment coefficient, and the inventory monitoring value is generated in combination with the surgical scheduling data. The monitoring results are determined by comparing the actual inventory value.
It improves the accuracy and effectiveness of drug inventory monitoring, can better respond to fluctuations in drug demand, reduce supply shortages or surpluses, and improve the operational efficiency of medical institutions and patient medication safety.
Smart Images
Figure CN120748636A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of intelligent drug management, and in particular to a drug inventory monitoring method and related devices, equipment, and storage media. Background Art
[0002] With the development of the medical industry, pharmaceuticals, as important supplies in medical activities, have become increasingly important. Their inventory management is directly related to the operational efficiency of medical institutions and the safety of patients' medication use. Therefore, how to effectively manage pharmaceutical inventory is receiving increasing attention.
[0003] Existing technologies typically implement drug inventory management based on static inventory management methods, specifically monitoring drug inventory levels to ensure they meet demand based on static quantity thresholds. However, due to fluctuations in actual drug demand during medical activities, insufficient drug inventory can lead to delayed medication for patients, while excess inventory increases operating costs for medical institutions. Therefore, drug inventory monitoring based on static quantity thresholds is less effective. Therefore, improving the effectiveness of drug inventory monitoring has become an urgent issue. Summary of the Invention
[0004] The main technical problem solved by this application is to provide a drug inventory monitoring method and related devices, equipment, systems and storage media, which can improve the effectiveness of drug inventory monitoring.
[0005] In order to solve the above technical problems, the first aspect of the present application provides a drug inventory monitoring method, including: obtaining a predicted drug usage in a to-be-predicted period based on historical drug usage data of a target drug in a first historical period, and obtaining predicted surgical data related to the target drug in a to-be-predicted period based on historical surgical data related to the target drug in a second historical period; wherein the second historical period covers the first historical period; generating an adjustment coefficient based on the predicted surgical data and surgical scheduling data about the target drug in the to-be-predicted period; obtaining an inventory monitoring value of the target drug based on the adjustment coefficient and the predicted drug usage; and determining a monitoring result based on a comparison result between the inventory monitoring value and the actual inventory value of the target drug.
[0006] In order to solve the above technical problems, the second aspect of the present application provides a drug inventory monitoring device, including: a prediction module, a generation module, an acquisition module and a monitoring module, the prediction module is used to obtain the predicted medication amount of the period to be predicted based on the historical medication data of the target drug in the first historical period, and to obtain the predicted surgery data related to the target drug in the period to be predicted based on the historical surgery data related to the target drug in the second historical period; wherein the second historical period covers the first historical period; the generation module is used to generate an adjustment coefficient based on the predicted surgery data and the surgery scheduling data about the target drug in the period to be predicted; the acquisition module is used to obtain the inventory monitoring value of the target drug based on the adjustment coefficient and the predicted medication amount; the monitoring module is used to determine the monitoring result based on the comparison result between the inventory monitoring value and the actual inventory value of the target drug.
[0007] In order to solve the above technical problems, the third aspect of this application provides an electronic device, which at least includes a memory and a processor coupled to each other, wherein the memory at least stores program instructions, and the processor is used to execute the program instructions to implement the drug inventory monitoring method in the above first aspect.
[0008] In order to solve the above technical problems, the fourth aspect of the present application provides a computer-readable storage medium storing program instructions that can be executed by a processor, and the program instructions are used to implement the drug inventory monitoring method of the first aspect above.
[0009] The above scheme obtains the predicted medication amount in the period to be predicted based on the historical medication data of the target drug in the first historical period, and obtains the predicted surgery data related to the target drug in the period to be predicted based on the historical surgery data related to the target drug in the second historical period, and the second historical period covers the first historical period. Based on the predicted surgery data and the surgery scheduling data about the target drug in the period to be predicted, an adjustment coefficient is generated, and based on the adjustment coefficient and the predicted medication amount, the inventory monitoring value of the target drug is obtained, and based on the comparison result between the inventory monitoring value and the actual inventory value of the target drug, the monitoring result is determined. On the one hand, the actual consumption of the target drug in the first historical period is used as reference information, and the predicted drug dosage of the period to be predicted is obtained based on the reference information of the drug dimension. The more relevant target drug dosage trend can be used as reference data to improve the effectiveness of generating the predicted drug dosage. On the other hand, the historical surgical data related to the target drug in the second historical period covering the first historical period is used as reference information, and the predicted surgical data of the target drug in the period to be predicted is obtained based on the reference information of the surgical dimension. The predicted drug dosage is adjusted according to the difference between the predicted surgical data and the actual surgical data in the period to be predicted to obtain the inventory monitoring value. Therefore, compared with the first historical period, the second historical period, which is longer than the first historical period, can provide more robust surgical dimension reference data. According to the multi-dimensional information, it is helpful to improve the accuracy of the adjusted predicted drug dosage and further improve the accuracy of generating the target drug inventory monitoring value. Therefore, the effectiveness of drug inventory monitoring can be improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] Figure 1 This is a flow chart of an embodiment of the drug inventory monitoring method of the present application; Figure 2 This is a schematic diagram of the framework of an embodiment of the drug inventory monitoring device of the present application; Figure 3 This is a schematic diagram of the framework of an embodiment of the electronic device of the present application; Figure 4 It is a schematic diagram of a framework of an embodiment of a computer-readable storage medium of the present application. DETAILED DESCRIPTION
[0011] The following describes the embodiments of the present application in detail with reference to the accompanying drawings.
[0012] In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures, interfaces, and technologies are provided to facilitate a thorough understanding of the present application.
[0013] The terms "system" and "network" are often used interchangeably in this document. The term "and / or" is simply a description of an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the fragment " / " generally indicates that the related objects are in an "or" relationship. Furthermore, "multiple" in this document refers to two or more than two.
[0014] See also Figure 1 , Figure 1 This is a flow chart of an embodiment of the drug inventory monitoring method of the present application. Specifically, it may include the following steps: Step S11: Based on the historical medication data of the target drug in the first historical period, the predicted medication amount of the predicted period is obtained, and based on the historical surgery data related to the target drug in the second historical period, the predicted surgery data related to the target drug in the predicted period is obtained.
[0015] In the embodiment of the present disclosure, the period to be predicted represents a specific time unit. Specifically, the period to be predicted can be a preset number of hours, minutes, etc. in the time granularity dimension. As an example, the start time and the end time of the period to be predicted are based on the natural day. For example, one period represents one natural day, and the period to be predicted is specifically from 0:00 on the current day to 0:00 on the next day.
[0016] In one implementation scenario, the second historical period covers the first historical period. Specifically, as a time interval with a wider range and richer data volume, the second historical period completely includes the first historical period. When the coverage relationship is reflected on the time axis, the start time of the second historical period is earlier than the start time of the first historical period, and the end time of the second historical period is not earlier than the end time of the first historical period. For example, taking a single cycle as a natural day as an example, if the first historical period selects data from one week before the period to be predicted, the second historical period may be a period of one month before the period to be predicted, or a period of one year before the period to be predicted.
[0017] It should be noted that the above embodiments are only possible implementation methods, and the specific durations of the period to be predicted, the first historical period, and the second historical period are not limited in this application.
[0018] In a specific implementation scenario, the first historical period includes a first number of time periods, the second historical period includes a second number of time periods, and the end time of the first historical period and the second historical period is consistent with the start time of the period to be predicted. A single time period represents a continuous time unit with a fixed time scale as the starting boundary. The duration of any time period is consistent with the period to be predicted. For example, taking a natural day as an example, the period to be predicted is half a day, that is, drug inventory monitoring is performed once every half a day. Specifically, it can be set at zero o'clock on the day to predict the inventory monitoring value from zero o'clock to twelve o'clock on the day. The first historical period is the period one week before midnight of the day, and the second historical period is the period one year before midnight of the day. At twelve o'clock on the day, the inventory monitoring value from twelve o'clock on the day to the next day is predicted. The first historical period is the period one week before twelve o'clock on the day, and the second historical period is the period one year before twelve o'clock on the day. For another example, the prediction cycle is one day, that is, the drug inventory monitoring is performed once a day. Specifically, it can be set to predict the inventory monitoring value from eight o'clock on the day to eight o'clock the next day at eight o'clock on the day. The first historical period is the period one week before eight o'clock on the day, and the second historical period is the period one year before eight o'clock on the day.
[0019] In one implementation scenario, based on the historical medication data of the target drug in the first historical period, the predicted medication amount for the period to be predicted is obtained. Therefore, the actual consumption of the target drug in the first historical period is used as reference information, and the predicted medication amount for the period to be predicted is obtained based on the reference information of the drug dimension. The more relevant target drug usage trend can be used as reference data to improve the effectiveness of generating the predicted medication amount.
[0020] In a specific implementation scenario, before obtaining the predicted drug usage of the period to be predicted based on the historical drug usage data of the target drug in the first historical period, the target weight corresponding to each historical period is determined based on the time series of each historical period in the first historical period, and the target weight represents the importance of the historical drug usage data of the historical period in the stage of predicting drug usage. The predicted drug usage of the period to be predicted is determined based on the historical drug usage data of the target drug in each historical period and the target weight corresponding to each historical period. The above scheme determines the target weight corresponding to each historical period based on the importance of the historical drug usage data of the historical period in the stage of predicting drug usage, which can obtain a more relevant target drug usage trend and further improve the accuracy of inventory monitoring value generation.
[0021] In a specific implementation scenario, taking the prediction period as one day and the first historical period as one week as an example, the historical periods in the first historical period are from the day before today to the seven days before today, and the time sequence of the historical periods in the first historical period is the time sequence from the day before today to the seven days before today.
[0022] In a specific implementation scenario, the starting moment of the period to be predicted is used as the base moment, and the time difference between the starting moment of each historical period and the base moment is obtained. Based on each time difference, the target weight corresponding to each historical period is determined, and the target weight is inversely proportional to the time difference. It can be understood that, still taking the above embodiment as an example, the time difference between the seventh day before today in the first historical period and the base moment is greater than the time difference between the sixth day before today in the first historical period and the base moment, then the target weight corresponding to the seventh day before today in the first historical period is less than the target weight corresponding to the sixth day before today in the first historical period. The above scheme assigns different weights to data from different periods, and the weight of recent data is higher, thereby improving the accuracy of the predicted medication amount for the period to be predicted.
[0023] In a specific embodiment, after obtaining the target weights of each historical period, the historical medication data of each historical period are weighted based on the target weights corresponding to each historical period to obtain the weighted historical medication amounts. Based on the weighted historical medication amounts, the average medication amount of each historical period is obtained as the predicted medication amount for the period to be predicted.
[0024] In a specific implementation scenario, the weight distribution ratio is determined based on the time series of each historical period, and normalization is performed based on the weight distribution ratio to obtain the target weight corresponding to each historical period. The weighted historical drug dosages are summed to obtain the predicted drug dosage for the period to be predicted. For details, please refer to the following formula:
[0025] In formula (1), n represents the historical period n periods before the period to be predicted. Represents the historical medication data corresponding to the historical period, Characterize the target weight corresponding to the historical period. For example, the first historical period includes three historical periods with time intervals from near to far compared with the period to be predicted, and the weight distribution ratio is 3:2:1. The historical consumption of the target drug is 40, 45, and 50 respectively. The calculated predicted drug usage in the period to be predicted is approximately 43.3.
[0026] In a specific implementation scenario, the predicted medication dosage for the forecast period can be implemented based on a weighted moving average algorithm. The weighted moving average method is a forecasting method based on time series data. It predicts future data trends by assigning different weights to historical data and calculating the average value. Compared with the simple moving average method, it can more flexibly reflect the characteristics of data changes. The core principle of this method is that the data closer to the forecast period has a greater impact on future trends, so it is given a higher weight; the data farther away from the forecast period has a relatively smaller influence, and the weight is correspondingly reduced. In the calculation process, the time window is first determined, that is, the number of historical periods involved in the average calculation in the first historical period. Then, weights are assigned according to the importance of each data, and the sum of the weights is 1. Specifically, the target weights are set based on the time series to decrease in equal proportion or increase in non-equal proportion. Each historical data is multiplied by its corresponding weight, and the sum is divided by the total weight to obtain the weighted moving average.
[0027] In an implementation scenario, based on the historical surgical data related to the target drug in the second historical period, the predicted surgical data related to the target drug in the period to be predicted is obtained. The historical surgical data related to the target drug in the second historical period covering the first historical period is used as reference information. Based on the reference information of the surgical dimension, the predicted surgical data about the target drug in the period to be predicted is obtained, which can provide reference data of the surgical dimension for the adjustment of the predicted medication dosage, and is conducive to improving the effectiveness of the adjusted predicted medication dosage.
[0028] In a specific implementation scenario, the correlation between the historical surgical data related to the target drug in the second historical period and the reference features is analyzed to construct a feature matrix. The reference features include at least time series features, surgical type features, and medication preference features. Based on the feature matrix, the predicted surgical data of the period to be predicted is predicted. Specifically, historical surgical data related to the target drug in the second historical period is obtained from the medical database, and the historical surgical data includes but is not limited to information such as operation time, operation type, and drug usage record. At the same time, reference features are extracted, wherein the time series features cover time-related attributes such as the specific time point, time interval, and season of the operation; the operation type features include different operation classification codes, the complexity of the operation, etc.; the medication preference features involve the frequency of use of the target drug, the combination of drugs, the use of alternative drugs, etc., and the correlation between the historical surgical data and the reference features is analyzed. Taking the time series features as an example, the correlation between different seasons and time periods and the number of operations and the usage of the target drug is analyzed. Through the correlation analysis, the influence weight of each reference feature on the historical surgical data is clarified, and then a feature matrix is constructed. Specifically, each historical surgical data record is used as a row, and the corresponding time series features, operation type features, medication preference features, and surgical data indicators are used as columns to form a multi-dimensional feature matrix. Prediction is performed based on the feature matrix to obtain predicted surgical data for the period to be predicted.
[0029] In a specific implementation scenario, a feature matrix is used as input to train a prediction model using historical data. Based on the correlations and weights between historical surgical data and reference features, a weighted calculation is performed on the data in the feature matrix to predict surgical data for the predicted period. For example, the model can predict the number of related surgeries performed within the predicted period. It should be noted that the training steps of the prediction model can be found in technical details such as those of neural network models, and for the sake of brevity, they are not detailed here.
[0030] In a specific implementation scenario, the prediction model is specifically a random forest model, and the generation of predicted surgical data is performed based on the trained and optimized random forest model. The relevant feature data of the period to be predicted, such as the season and holiday information within the prediction time period, are processed in the same preprocessing method as the historical data, and then input into the trained random forest model. Each decision tree in the model makes predictions based on the input feature data and generates its own prediction results. The prediction results of all decision trees are integrated through the averaging method, and finally the predicted surgical data of the period to be predicted is obtained. For more technical details about the random forest model, please refer to the relevant technical content of the random forest algorithm. For the sake of brevity, we will not go into details here.
[0031] In a specific implementation scenario, after obtaining the historical usage data of the target drug in the first historical period and before obtaining the predicted usage for the predicted period, the historical usage data for the first historical period is preprocessed, such as by removing outliers. Data normalization is performed, specifically, by detecting and removing outliers in daily usage through boxplots.
[0032] In a specific implementation scenario, after obtaining the historical surgical data related to the target drug during the second historical period, and before obtaining the predicted surgical data related to the target drug during the predicted period, the historical surgical data related to the target drug during the second historical period is preprocessed, for example, by removing outliers. Data normalization, specifically, Min-Max normalization is performed on multi-source data to eliminate dimensional differences.
[0033] Step S12: Generate an adjustment coefficient based on the predicted surgery data and the surgery schedule data for the target drug in the period to be predicted.
[0034] In one implementation scenario, an adjustment coefficient for adjusting the predicted medication dosage is generated based on the difference between the predicted surgical data and the actual surgical data within the predicted period, which is beneficial to improving the accuracy of the adjusted predicted medication dosage based on multi-dimensional information.
[0035] In a specific implementation scenario, the first and second surgical volumes with the same surgical type are obtained from the predicted surgical data and the surgical scheduling data, and the adjustment coefficient is determined based on the ratio of the second surgical volume to the first surgical volume. For example, based on the predicted surgical data and the surgical data with the same surgical type in the surgical scheduling data, it is found that 3 heart bypass surgeries are added to the cardiac surgery department on that day, and the corresponding predicted surgical volume is 10, that is, the heart bypass surgery volume increases by 30%, and the adjustment coefficient is determined to be 1.3.
[0036] In a specific implementation scenario, the type of surgery can be classified based on the department to which the surgery belongs, the surgical organ, or the technical surgeon. The specific classification is not limited in this application.
[0037] In a specific implementation scenario, the correlation between the surgical type and the target drug is used as reference data, and the adjustment coefficient is determined in combination with the ratio between the second surgical volume and the first surgical volume. For example, large-scale surgery requires a higher amount of target drugs, while small-scale surgery requires a lower amount of target drugs, or certain organ surgeries require a higher amount of certain specific target drugs. The predicted surgical data includes a mapping relationship between the predicted surgical type, the predicted surgical volume, and the correlation between the target drugs. After obtaining the ratio between the second surgical volume and the first surgical volume of each surgical type, the adjustment parameter is dynamically corrected based on the difference between the mapping relationship between the predicted surgical type, the predicted surgical volume, and the correlation between the target drugs and the mapping relationship between the actual surgical type, the actual surgical volume, and the correlation between the target drugs in the surgical scheduling data to generate the final adjustment parameter.
[0038] Step S13: Based on the adjustment coefficient and the predicted medication amount, the inventory monitoring value of the target drug is obtained.
[0039] In one implementation scenario, based on the adjustment coefficient and the predicted medication amount, on the one hand, the actual consumption of the target drug in the first historical period is used as reference information, and the predicted medication amount of the period to be predicted is obtained based on the reference information of the drug dimension. The more relevant target drug dosage trend can be used as reference data to improve the effectiveness of generating the predicted medication amount. On the other hand, the historical surgical data related to the target drug in the second historical period covering the first historical period is used as reference information, and the predicted surgical data of the target drug in the period to be predicted is obtained based on the reference information of the surgical dimension. The predicted medication amount is adjusted according to the difference between the predicted surgical data and the actual surgical data in the period to be predicted to obtain the inventory monitoring value. Therefore, compared with the first historical period, the second historical period, which is longer than the first historical period, can provide more robust surgical dimension reference data. According to the multi-dimensional information, it is beneficial to improve the accuracy of the adjusted predicted medication amount and further improve the accuracy of generating the target drug inventory monitoring value. Therefore, the effectiveness of drug inventory monitoring can be improved.
[0040] In one implementation scenario, the target medication amount is obtained based on the product of the adjustment coefficient and the predicted medication amount. Taking the aforementioned embodiment as an example, the predicted medication amount for the predicted period is approximately 43.3 units, and the adjustment coefficient is 1.3. Based on the rounded result of the product of the adjustment coefficient and the predicted medication amount, the target medication amount is 50 units, and the inventory control parameters for the target drug are obtained. Based on the target medication amount and the inventory control parameters, the inventory monitoring value is generated.
[0041] In a specific implementation scenario, inventory control parameters include procurement cycle, safety factor, and emergency buffer volume. The safety factor is dynamically adjusted according to the historical out-of-stock rate. For example, for every 1% increase in the out-of-stock rate, the safety factor increases by 0.2. The emergency buffer volume is determined based on the target medication amount. For example, the emergency buffer volume is fixed at 20% of the target medication amount. The cumulative value of the target medication amount, procurement cycle, and safety factor is obtained, and the cumulative value is summed with the emergency buffer volume to obtain the inventory monitoring value of the target drug. Specifically, the inventory monitoring value = predicted consumption × procurement cycle × (1 + safety factor) + emergency buffer volume. For example, taking the aforementioned target medication amount of 50 units as an example, if the procurement cycle is 2 days, the safety factor is 0.2, and the emergency buffer volume is 10 units, the calculated inventory monitoring value of the target drug is 130 units.
[0042] In a specific implementation scenario, inventory control parameters are predicted based on the random forest model. For example, the procurement cycle is determined based on the supplier delivery time in the second historical period, and the safety factor is determined based on the target drug expiration date in the second historical period. For details, please refer to the relevant technical features of the random forest model. For the sake of brevity, they will not be repeated here.
[0043] Step S14: Determine the monitoring result based on the comparison result between the inventory monitoring value and the actual inventory value of the target drug.
[0044] In one implementation scenario, the maximum and minimum thresholds for inventory monitoring are determined based on the inventory monitoring value and the preset detection ratio. The preset detection ratios used to calculate the maximum and minimum thresholds for inventory monitoring can be consistent or inconsistent. For example, the preset detection ratio is set to 10%. Taking the inventory monitoring value of the aforementioned target drug as 130 units as an example, the maximum threshold for inventory monitoring is determined to be 143 units and the minimum threshold is determined to be 117 units. For another example, the preset detection ratio for the maximum threshold for inventory monitoring is determined to be 20%, and the preset detection ratio for the maximum threshold for inventory monitoring is determined to be 10%. When the actual inventory value is greater than the maximum threshold or less than the minimum threshold, it is determined that the monitoring result indicates an inventory abnormality. The above scheme uses the actual consumption of the target drug in the first historical period as reference information, and obtains the predicted drug dosage for the period to be predicted based on the reference information of the drug dimension. It can use the more relevant target drug dosage trend as reference data to improve the effectiveness of generating the predicted drug dosage, and uses the historical surgical data related to the target drug in the second historical period covering the first historical period as reference information, and obtains the predicted surgical data on the target drug for the period to be predicted based on the reference information of the surgical dimension. The predicted drug dosage is adjusted according to the difference between the predicted surgical data and the actual surgical data in the period to be predicted to obtain the inventory monitoring value. Therefore, compared with the first historical period, the second historical period, which is longer than the first historical period, can provide more robust surgical dimension reference data. The multi-dimensional information is conducive to improving the accuracy of the adjusted predicted drug dosage, and further improving the accuracy of generating the target drug inventory monitoring value. Therefore, the effectiveness of drug inventory monitoring can be improved.
[0045] In one implementation scenario, surgical scheduling data is collected through the hospital's internal information system to improve the accuracy and real-time nature of the data. The actual inventory value of target drugs can be tracked in real time based on the existing weighing technology and inventory management logic of the medicine box.
[0046] In a specific implementation scenario, when the test results indicate an inventory anomaly, an early warning message is generated and sent. For example, when the inventory anomaly judgment criteria are met, the early warning message generation process is triggered. The early warning message contains multi-dimensional key content. The first is the abnormality type identification, which clearly marks the specific abnormality categories such as inventory shortage, approaching expiration date, or loss abnormality. The second is the abnormality details description, which details the name of the target drug involved, specifications and models, current inventory quantity, predicted demand quantity, degree of abnormality, etc. The third is the impact prompt, which explains the potential impact of the abnormality on surgical arrangements, patient treatment, etc. The fourth is the recommended measures, which provide targeted solutions based on the abnormality type. For example, for inventory shortage abnormalities, it is recommended to immediately start the emergency procurement process and coordinate the allocation of materials from other hospital areas.
[0047] In a specific implementation scenario, differentiated delivery methods are used for different personnel roles and urgency levels: For inventory management personnel, early warning information is sent synchronously through pop-up windows, text messages, emails, and other methods within the hospital's internal information management system to ensure that they can obtain anomaly details in a timely manner. For hospital management, concise and intuitive inventory anomaly summary information is provided in the form of email reports and visual large-screen early warning displays to assist them in making resource scheduling decisions. For material suppliers, early warning information is pushed through the supply chain collaboration platform to enable them to respond to material supply needs in a timely manner. For another example, the priority of early warning information delivery is set. For highly urgent anomalies, phone notifications and expedited text messages are used to ensure that the information reaches the relevant personnel as soon as possible.
[0048] The above scheme obtains the predicted medication amount in the period to be predicted based on the historical medication data of the target drug in the first historical period, and obtains the predicted surgery data related to the target drug in the period to be predicted based on the historical surgery data related to the target drug in the second historical period, and the second historical period covers the first historical period. Based on the predicted surgery data and the surgery scheduling data about the target drug in the period to be predicted, an adjustment coefficient is generated, and based on the adjustment coefficient and the predicted medication amount, the inventory monitoring value of the target drug is obtained, and based on the comparison result between the inventory monitoring value and the actual inventory value of the target drug, the monitoring result is determined. On the one hand, the actual consumption of the target drug in the first historical period is used as reference information, and the predicted drug dosage of the period to be predicted is obtained based on the reference information of the drug dimension. The more relevant target drug dosage trend can be used as reference data to improve the effectiveness of generating the predicted drug dosage. On the other hand, the historical surgical data related to the target drug in the second historical period covering the first historical period is used as reference information, and the predicted surgical data of the target drug in the period to be predicted is obtained based on the reference information of the surgical dimension. The predicted drug dosage is adjusted according to the difference between the predicted surgical data and the actual surgical data in the period to be predicted to obtain the inventory monitoring value. Therefore, compared with the first historical period, the second historical period, which is longer than the first historical period, can provide more robust surgical dimension reference data. According to the multi-dimensional information, it is helpful to improve the accuracy of the adjusted predicted drug dosage and further improve the accuracy of generating the target drug inventory monitoring value. Therefore, the effectiveness of drug inventory monitoring can be improved.
[0049] See also Figure 2 , Figure 2: This is a schematic diagram of the framework of an embodiment of the drug inventory monitoring device 20 of the present application. Specifically, the drug inventory monitoring device 20 includes: a prediction module 21, a generation module 22, an acquisition module 23 and a monitoring module 24. The prediction module 21 is used to obtain the predicted drug usage of the to-be-predicted period based on the historical drug usage data of the target drug in the first historical period, and to obtain the predicted surgical data related to the target drug in the to-be-predicted period based on the historical surgical data related to the target drug in the second historical period; wherein the second historical period covers the first historical period; the generation module 22 is used to generate an adjustment coefficient based on the predicted surgical data and the surgical scheduling data about the target drug in the to-be-predicted period; the acquisition module 23 is used to obtain the inventory monitoring value of the target drug based on the adjustment coefficient and the predicted drug usage; and the monitoring module 24 is used to determine the monitoring result based on the comparison result between the inventory monitoring value and the actual inventory value of the target drug.
[0050] Therefore, the drug inventory monitoring device 20 obtains the predicted drug usage in the period to be predicted based on the historical drug usage data of the target drug in the first historical period, and obtains the predicted surgical data related to the target drug in the period to be predicted based on the historical surgical data related to the target drug in the second historical period, and the second historical period covers the first historical period. Based on the predicted surgical data and the surgical scheduling data about the target drug in the period to be predicted, an adjustment coefficient is generated, and based on the adjustment coefficient and the predicted drug usage, the inventory monitoring value of the target drug is obtained, and based on the comparison result between the inventory monitoring value and the actual inventory value of the target drug, the monitoring result is determined. On the one hand, the actual consumption of the target drug in the first historical period is used as reference information, and the predicted drug dosage of the period to be predicted is obtained based on the reference information of the drug dimension. The more relevant target drug dosage trend can be used as reference data to improve the effectiveness of generating the predicted drug dosage. On the other hand, the historical surgical data related to the target drug in the second historical period covering the first historical period is used as reference information, and the predicted surgical data of the target drug in the period to be predicted is obtained based on the reference information of the surgical dimension. The predicted drug dosage is adjusted according to the difference between the predicted surgical data and the actual surgical data in the period to be predicted to obtain the inventory monitoring value. Therefore, compared with the first historical period, the second historical period, which is longer than the first historical period, can provide more robust surgical dimension reference data. According to the multi-dimensional information, it is helpful to improve the accuracy of the adjusted predicted drug dosage and further improve the accuracy of generating the target drug inventory monitoring value. Therefore, the effectiveness of drug inventory monitoring can be improved.
[0051] In some disclosed embodiments, the drug inventory monitoring device 20 also includes a weight determination module (not shown) for determining a target weight corresponding to each historical period based on the time sequence of each historical period in the first historical period; wherein the target weight represents the importance of the historical medication data of the historical period in the medication dosage prediction stage; the prediction module 21 also includes a medication dosage prediction module (not shown) for determining the predicted medication dosage of the period to be predicted based on the historical medication data of the target drug in each historical period and the target weight corresponding to each historical period.
[0052] In some disclosed embodiments, the medication dosage prediction module (not shown) further includes a weighting module (not shown) for weighting the historical medication data of each historical period based on the target weight corresponding to each historical period to obtain weighted historical medication dosages; the medication dosage prediction module (not shown) further includes a processing module (not shown) for processing the weighted historical medication dosages to obtain the average medication dosage of each historical period as the predicted medication dosage for the period to be predicted.
[0053] In some disclosed embodiments, the weight determination module (not shown) further includes a difference acquisition module (not shown) for taking the start moment of the period to be predicted as the base moment and obtaining the difference in duration between the start moment of each historical period and the base moment; the weight determination module (not shown) further includes a weight matching module (not shown) for determining the target weight corresponding to each historical period based on the differences in duration; wherein the target weight is inversely proportional to the difference in duration.
[0054] In some disclosed embodiments, the prediction module 21 also includes a data analysis module (not shown) for analyzing the correlation between historical surgical data related to the target drug in the second historical period and reference features, and constructing a feature matrix; wherein the reference features include at least time series features, surgical type features, and medication preference features; the prediction module 21 also includes a surgical prediction module (not shown) for predicting the predicted surgical data of the period to be predicted based on the feature matrix.
[0055] In some disclosed embodiments, the generation module 22 also includes a surgical volume acquisition module (not shown), which is used to respectively obtain a first surgical volume and a second surgical volume of the same surgical type in the predicted surgical data and the surgical scheduling data; the generation module 22 also includes a coefficient generation module (not shown), which is used to determine an adjustment coefficient based on the ratio between the second surgical volume and the first surgical volume.
[0056] In some disclosed embodiments, the acquisition module 23 also includes a target medication dosage calculation module (not shown), which is used to obtain the target medication dosage based on the product of the adjustment coefficient and the predicted medication dosage; the acquisition module 23 also includes a control parameter acquisition module (not shown), which is used to obtain inventory control parameters for the target drug; the acquisition module 23 also includes a target medication monitoring value generation module (not shown), which is used to generate inventory monitoring values based on the target medication dosage and the inventory control parameters.
[0057] In some disclosed embodiments, inventory control parameters include a procurement cycle, a safety factor, and an emergency buffer, and the emergency buffer is determined based on the target medication amount. The monitoring value generation module (not shown) also includes a multiplication module (not shown) for obtaining the cumulative value of the target medication amount, the procurement cycle, and the safety factor; the monitoring value generation module (not shown) also includes a summation module (not shown) for summing the cumulative value and the emergency buffer to obtain the inventory monitoring value of the target drug.
[0058] In some disclosed embodiments, the monitoring module 24 further includes a threshold determination module (not shown) for determining a maximum threshold and a minimum threshold for inventory monitoring based on the inventory monitoring value and a preset detection ratio; the monitoring module 24 further includes a result determination module (not shown) for determining that the monitoring result indicates an inventory abnormality in response to the actual inventory value being greater than the maximum threshold or less than the minimum threshold; and / or, in the event that the detection result indicates an inventory abnormality, the drug inventory monitoring device 20 further includes an early warning module (not shown) for generating and sending early warning information.
[0059] See also Figure 3 , Figure 3 : This is a schematic diagram of the framework of an embodiment of an electronic device of the present application. The electronic device 30 includes at least a memory 31 and a processor 32 coupled to each other. The memory 31 stores at least program instructions, and the processor 32 is used to execute the program instructions to implement the steps in any of the above-mentioned drug inventory monitoring method embodiments. For details, please refer to the aforementioned disclosed embodiments, which will not be repeated here. It should be noted that the electronic device 30 may include but is not limited to office notebooks, smart large screens, monitoring hosts and other devices, and the specific type of the electronic device 30 is not limited here.
[0060] Specifically, processor 32 is used to control itself and memory 31 to implement the steps of any of the above-mentioned drug inventory monitoring method embodiments. Processor 32 may also be referred to as a CPU (Central Processing Unit). Processor 32 may be an integrated circuit chip with signal processing capabilities. Processor 32 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component. A general-purpose processor may be a microprocessor or any conventional processor. In addition, processor 32 may be implemented by an integrated circuit chip.
[0061] In the above scheme, the electronic device 30 obtains the predicted medication amount in the period to be predicted based on the historical medication data of the target drug in the first historical period, and obtains the predicted surgery data related to the target drug in the period to be predicted based on the historical surgery data related to the target drug in the second historical period, and the second historical period covers the first historical period. Based on the predicted surgery data and the surgery scheduling data about the target drug in the period to be predicted, an adjustment coefficient is generated, based on the adjustment coefficient and the predicted medication amount, the inventory monitoring value of the target drug is obtained, and based on the comparison result between the inventory monitoring value and the actual inventory value of the target drug, the monitoring result is determined. On the one hand, the actual consumption of the target drug in the first historical period is used as reference information, and the predicted drug dosage of the period to be predicted is obtained based on the reference information of the drug dimension. The more relevant target drug dosage trend can be used as reference data to improve the effectiveness of generating the predicted drug dosage. On the other hand, the historical surgical data related to the target drug in the second historical period covering the first historical period is used as reference information, and the predicted surgical data of the target drug in the period to be predicted is obtained based on the reference information of the surgical dimension. The predicted drug dosage is adjusted according to the difference between the predicted surgical data and the actual surgical data in the period to be predicted to obtain the inventory monitoring value. Therefore, compared with the first historical period, the second historical period, which is longer than the first historical period, can provide more robust surgical dimension reference data. According to the multi-dimensional information, it is helpful to improve the accuracy of the adjusted predicted drug dosage and further improve the accuracy of generating the target drug inventory monitoring value. Therefore, the effectiveness of drug inventory monitoring can be improved.
[0062] See also Figure 4 , Figure 4The computer-readable storage medium 40 stores program instructions 41 that can be executed by a processor, and the program instructions 41 are used to implement the steps of any of the above-mentioned drug inventory monitoring method embodiments.
[0063] In the above scheme, the computer-readable storage medium 40 obtains the predicted medication amount in the period to be predicted based on the historical medication data of the target drug in the first historical period, and obtains the predicted surgery data related to the target drug in the period to be predicted based on the historical surgery data related to the target drug in the second historical period, and the second historical period covers the first historical period, and generates an adjustment coefficient based on the predicted surgery data and the surgery scheduling data about the target drug in the period to be predicted, obtains the inventory monitoring value of the target drug based on the adjustment coefficient and the predicted medication amount, and determines the monitoring result based on the comparison result between the inventory monitoring value and the actual inventory value of the target drug. On the one hand, the actual consumption of the target drug in the first historical period is used as reference information, and the predicted drug dosage of the period to be predicted is obtained based on the reference information of the drug dimension. The more relevant target drug dosage trend can be used as reference data to improve the effectiveness of generating the predicted drug dosage. On the other hand, the historical surgical data related to the target drug in the second historical period covering the first historical period is used as reference information, and the predicted surgical data of the target drug in the period to be predicted is obtained based on the reference information of the surgical dimension. The predicted drug dosage is adjusted according to the difference between the predicted surgical data and the actual surgical data in the period to be predicted to obtain the inventory monitoring value. Therefore, compared with the first historical period, the second historical period, which is longer than the first historical period, can provide more robust surgical dimension reference data. According to the multi-dimensional information, it is helpful to improve the accuracy of the adjusted predicted drug dosage and further improve the accuracy of generating the target drug inventory monitoring value. Therefore, the effectiveness of drug inventory monitoring can be improved.
[0064] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.
[0065] The above description of the various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced with each other and will not be repeated herein for the sake of brevity.
[0066] In the several embodiments provided in this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation methods described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.
[0067] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.
[0068] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.
[0069] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the various implementation methods of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.
[0070] If the technical solution of this application involves personal information, the product that applies the technical solution of this application has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing personal information. If the technical solution of this application involves sensitive personal information, the product that applies the technical solution of this application has obtained the individual's separate consent before processing sensitive personal information, and at the same time meets the "explicit consent" requirement. For example, on personal information collection devices such as cameras, a clear and prominent sign is set to inform that the personal information collection scope has been entered and personal information will be collected. If the individual voluntarily enters the collection scope, it is deemed that they agree to the collection of their personal information; or on the personal information processing device, when the personal information processing rules are notified by obvious signs / information, the individual's authorization is obtained through pop-up information or by asking the individual to upload their personal information; among which, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the type of personal information processed.
Claims
1. A drug inventory monitoring method, characterized in that: include: Based on the historical medication data of the target drug in the first historical period, a predicted medication amount for the period to be predicted is obtained; and based on the historical surgery data related to the target drug in the second historical period, predicted surgery data related to the target drug in the period to be predicted is obtained; wherein the second historical period covers the first historical period; generating an adjustment coefficient based on the predicted surgery data and surgery schedule data regarding the target drug in the period to be predicted; Obtaining an inventory monitoring value of the target drug based on the adjustment coefficient and the predicted drug dosage; A monitoring result is determined based on a comparison result between the inventory monitoring value and the actual inventory value of the target drug.
2. The method according to claim 1, characterized in that Before obtaining the predicted medication amount for the period to be predicted based on the historical medication data of the target drug in the first historical period, the method further includes: Determining target weights corresponding to the respective historical periods based on the time sequence of the respective historical periods in the first historical period; wherein the target weights represent the importance of the historical medication data of the respective historical periods in the predicted medication dosage prediction stage; The step of obtaining the predicted dosage of the target drug in the first historical period based on the historical dosage data of the target drug includes: Based on the historical medication data of the target drug in each historical period and the target weight corresponding to each historical period, the predicted medication amount for the period to be predicted is determined.
3. The method according to claim 2, characterized in that The step of determining the predicted medication amount for the period to be predicted based on the historical medication data of the target drug in each historical period and the target weight corresponding to each historical period includes: weighting the historical medication data of each historical period based on the target weight corresponding to each historical period to obtain weighted historical medication amounts; Based on the weighted historical medication amounts, the average medication amount of each historical period is obtained as the predicted medication amount of the period to be predicted.
4. The method according to claim 2, characterized in that The determining, based on the time sequence of each historical period in the first historical period, a target weight corresponding to each historical period includes: Taking the start time of the period to be predicted as the base time, obtaining the time difference between the start time of each historical period and the base time; Based on each of the duration differences, the target weight corresponding to each of the historical periods is determined; wherein the target weight is in inverse proportion to the duration difference.
5. The method according to claim 1, wherein The step of obtaining the predicted surgical data for the period to be predicted based on the historical surgical data related to the target drug during the second historical period includes: Analyzing the correlation between the historical surgical data related to the target drug in the second historical period and reference features to construct a feature matrix; wherein the reference features include at least time series features, surgical type features, and drug preference features; The predicted surgical data of the period to be predicted is predicted based on the feature matrix.
6. The method according to claim 1, characterized in that The step of generating an adjustment coefficient based on the predicted surgery data and the surgery schedule data regarding the target drug within the period to be predicted includes: Respectively obtaining a first operation volume and a second operation volume of the same operation type in the predicted operation data and the operation scheduling data; The adjustment coefficient is determined based on a ratio between the second surgical volume and the first surgical volume.
7. The method according to claim 1, characterized in that The step of obtaining the inventory monitoring value of the target drug based on the adjustment coefficient and the predicted drug dosage includes: Based on the product of the adjustment coefficient and the predicted medication amount, a target medication amount is obtained, and inventory control parameters for the target drug are obtained; The inventory monitoring value is generated based on the target medication amount and the inventory control parameter.
8. The method according to claim 7, characterized in that The inventory control parameters include a procurement cycle, a safety factor, and an emergency buffer, and the emergency buffer is determined based on the target medication amount. Generating the inventory monitoring value based on the target medication amount and the inventory control parameters includes: Obtaining a cumulative multiplication value of the target medication dosage, the procurement cycle, and the safety factor; The inventory monitoring value of the target drug is obtained by summing the cumulative value and the emergency buffer amount.
9. The method according to claim 1, characterized in that The determining of the monitoring result based on the comparison result between the inventory monitoring value and the actual inventory value of the target drug includes: Determining a maximum threshold and a minimum threshold for inventory monitoring based on the inventory monitoring value and a preset monitoring ratio; In response to the actual inventory value being greater than the maximum threshold or less than the minimum threshold, determining that the monitoring result indicates an inventory abnormality; And / or, when the detection result indicates an inventory abnormality, the method further includes: Generate and send early warning information.
10. A drug inventory monitoring device, characterized in that: include: a prediction module, configured to obtain a predicted medication amount for a period to be predicted based on historical medication data of a target drug during a first historical period, and to obtain predicted surgical data related to the target drug during the period to be predicted based on historical surgical data related to the target drug during a second historical period; wherein the second historical period overlaps the first historical period; a generating module, configured to generate an adjustment coefficient based on the predicted surgery data and surgery schedule data regarding the target drug in the period to be predicted; an acquisition module, configured to obtain an inventory monitoring value of the target drug based on the adjustment coefficient and the predicted drug dosage; The monitoring module is used to determine a monitoring result based on a comparison result between the inventory monitoring value and the actual inventory value of the target drug.
11. An electronic device, characterized in that: The invention comprises a memory and a processor coupled to each other, wherein the memory stores program instructions, and the processor is used to execute the program instructions to implement the drug inventory monitoring method according to any one of claims 1 to 9.
12. A computer-readable storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the drug inventory monitoring method according to any one of claims 1 to 9 is implemented.