CN118737496A - An intelligent drug monitoring system - Google Patents

Abstract

The present invention relates to the field of big data processing technology, and in particular to an intelligent drug monitoring system, including: determining the drug label and drug commonality of each drug through a drug data analysis unit, determining the drug usage trend coefficient of each drug through an object database, determining the predicted demand quantity of a single drug within a preset period through a monitoring and analysis unit, and accurately judging whether there is a shortage risk of a single drug based on inventory data and predicted demand quantity. The environmental database adjusts the drug usage trend coefficient of a single drug through the stored historical drug usage peak information, and adjusts the update frequency of the drug usage trend coefficient according to the success rate of judging the historical shortage risk. Finally, the shortage quantity of a single drug is determined through an execution unit and an update request is issued to several data sources according to the update frequency of the drug usage trend coefficient. The accuracy of judging the risk of drug shortage is improved, the stability of the supply of short-supply drugs is improved, and it is conducive to realizing the optimal allocation of drug resources.

Description

An intelligent drug monitoring system

Technical Field

The present invention relates to the technical field of big data processing, and in particular to an intelligent drug monitoring system.

Background Art

In recent years, with the continuous expansion of the pharmaceutical market and the continuous optimization of supply management, the application of big data technology in the pharmaceutical field has become increasingly widespread. Big data technology can help pharmaceutical companies achieve comprehensive monitoring and management of goods supply, sales channels, etc., thereby achieving intelligent prediction and risk control of supply relationships.

Chinese patent publication number CN114664422A discloses a drug shortage risk monitoring and early warning method and system, including: obtaining the circulation data of the drug to be monitored N months before the prediction time point, then calculating the supply average value and demand average value of the drug to be monitored based on the circulation data, and using the supply average value and demand average value as input, respectively, using the Poisson distribution formula to predict the supply forecast value and demand forecast value of the drug to be monitored one month after the prediction time point. Finally, the drug shortage index of the drug to be monitored one month after the prediction time point is calculated based on the supply forecast value and demand forecast value, and the risk is graded according to the drug shortage index to determine the risk level of the drug to be monitored one month after the prediction time point, thereby providing a means for early detection of drug shortage risks and moving the threshold of drug shortage early warning forward.

It can be seen that although the above technical solution obtains the drug shortage index and risk level of the monitored drug one month after the prediction point based on the drug supply forecast value and the demand forecast value, there are still the following problems: it does not judge the drug usage trend in combination with the actual drug usage of users, which may lead to excessive drug inventory after purchasing drugs, and does not judge the shortage risk in combination with the drug usage trend.

Summary of the invention

To this end, the present invention provides an intelligent drug monitoring system to overcome the problem in the prior art that the drug inventory is uncontrollable due to the failure to judge the drug usage trend in combination with the user's actual drug usage situation and the failure to judge the drug shortage risk in combination with the drug usage trend.

To achieve the above object, the present invention provides an intelligent drug monitoring system, comprising:

Basic drug database, which stores drug information from several data sources within a preset time period, including drug name, drug use, outbound data, and inventory data;

a drug data analysis unit connected to the basic drug database, for determining the drug label of the drug according to the drug name, drug use, and inventory data of each drug in a single data source, and determining the drug commonality according to the overlap of drug labels of the same drug in each data source;

An object database storing drug taking cycles of multiple objects of each drug from multiple data sources and states before and after the multiple objects take each drug, for determining a drug use trend coefficient of each drug according to the drug taking cycle and the states before and after taking each drug;

A monitoring and analysis unit, which is connected to the basic drug database, the drug data analysis unit, and the object database, respectively, and is used to determine the predicted demand quantity of a single drug within a preset period according to the outbound data of a single drug and the drug use trend coefficient, and is used to determine whether there is a shortage risk of a single drug according to the inventory data and the predicted demand quantity of a single drug;

An environmental database, which is connected to the object database and the monitoring and analysis unit, respectively, and is used to store peak information of historical medication peaks corresponding to each drug label, including peak time, peak medication amount, and medication range, and to adjust the medication trend of a single drug according to the degree of correlation between the single drug and the peak information, and to adjust the update frequency of the medication trend coefficient according to the success rate of judging the historical shortage risk;

an execution unit, which is connected to the basic drug database, the monitoring and analysis unit and the environment database respectively, and is used to determine the shortage quantity of a single drug according to the inventory data and the predicted demand quantity of the single drug, and to send a data update request to each of the data sources according to the update frequency;

The drug label includes applicable diseases, medication type, inventory type and replacement type.

Furthermore, the drug data analysis unit determines the applicable disease and medication type of each drug according to the drug name and drug use of each drug in the single data source, and determines the replacement type of each drug according to the applicable disease of each drug, including:

If the number of types of drugs with the same applicable symptoms is greater than or equal to the preset substitution threshold, the substitution type of the drug is a replaceable drug;

If the number of types of drugs with the same applicable symptoms is less than a preset substitution threshold, the substitution type of the drug is an irreplaceable drug.

Furthermore, the drug data analysis unit determines the inventory type according to the inventory data of each drug and the replacement type, and the inventory type includes a high inventory type and a low inventory type, wherein different inventory types correspond to different stock warning thresholds.

Furthermore, the drug data analysis unit determines the drug label overlap of the same drug according to the applicable indications, medication types, inventory types, and replacement types of the same drug in each data source, and determines the drug commonality according to the drug label overlap.

Furthermore, the object database determines the medication trend coefficient of a single drug according to a preset medication cycle of the single drug and the states of several subjects before and after medication and the medication taking cycle.

Furthermore, the monitoring and analysis unit determines the predicted demand quantity of a single drug in a single data source within a preset period based on the delivery data of the single drug in a single data source at historical time points and the medication trend coefficient, and determines the predicted total demand quantity of a single drug in several data sources within a preset period based on the delivery data of the single drug in several data sources at historical time points, the medication trend coefficient, and the degree of commonality of the drug.

Furthermore, the monitoring and analysis unit determines whether there is a risk of shortage of a single drug based on the inventory data and predicted total demand quantity of the single drug in several data sources.

Furthermore, the environmental database determines an adjustment factor according to the degree of correlation between the single drug and the peak information, and adjusts the medication trend coefficient of the single drug based on the adjustment factor.

Furthermore, the environmental database adjusts the updating frequency of the medication trend coefficient according to the success rate of judging the historical shortage risk, including:

If the success rate of judging the historical shortage risk is less than a preset success rate threshold, it is determined to increase the update frequency;

If the success rate of judging the historical shortage risk is greater than or equal to a preset success rate threshold, it is determined to reduce the updating frequency.

Furthermore, the execution unit determines the shortage quantity of a single drug in a single data source based on the inventory data of the single drug in a single data source and the predicted demand quantity, and determines the total shortage quantity of a single drug in several data sources based on the inventory data of the single drug in several data sources and the predicted total demand quantity.

Compared with the prior art, the beneficial effect of the present invention is to establish a comprehensive intelligent drug monitoring system, determine the drug label and drug commonality of each drug through the drug data analysis unit, determine the drug usage trend coefficient of each drug through the object database, determine the predicted demand quantity of a single drug within a preset period through the monitoring and analysis unit, and accurately judge whether there is a shortage risk of a single drug based on inventory data and predicted demand quantity. The environmental database adjusts the drug usage trend coefficient of a single drug through the stored historical drug usage peak information, and adjusts the update frequency of the drug usage trend coefficient according to the success rate of judging the historical shortage risk. Finally, the shortage quantity of a single drug is determined through the execution unit and an update request is issued to several data sources according to the update frequency of the drug usage trend coefficient. The accuracy of judging the risk of drug shortage is further improved, the timeliness of the management of shortage drugs and the stability and reliability of drug supply are improved, which is conducive to the optimal allocation and efficient utilization of drug resources.

Furthermore, the drug data analysis unit of the present invention analyzes the drug name and drug use of each drug in the single data source to effectively determine the applicable symptoms and medication type of each drug, and determines whether the drug is a replaceable drug or an irreplaceable drug based on the same number of applicable symptoms, and determines the drug inventory type based on the replacement type of the drug and the corresponding drug inventory warning threshold. The present invention classifies and marks each drug by setting a drug label, thereby further improving the accuracy of drug shortage risk judgment, improving the timeliness of drug shortage management and the stability and reliability of drug supply, and facilitating the optimal allocation and efficient use of drug resources.

Furthermore, the drug data analysis unit in the present invention accurately calculates the drug label overlap of the same drugs according to the overlap of medication types, inventory types and replacement types of the same drugs in each data source, thereby improving the information integration of the same drugs in each data source, and determining the commonality of drugs through the overlap of drug labels, further improving the accuracy of drug shortage risk judgment, improving the timeliness of shortage drug management and the stability and reliability of drug supply, and facilitating the optimal allocation and efficient utilization of drug resources.

Furthermore, the object database of the present invention accurately determines the medication trend coefficient of a single drug based on the preset medication cycle of the single drug and the states of several subjects before and after medication, and the medication cycle. This is further conducive to predicting the drug demand trend of each data source, improving the accuracy of drug shortage risk judgment, improving the timeliness of drug shortage management and the stability and reliability of drug supply, and facilitating the optimal allocation and efficient use of drug resources.

Furthermore, the monitoring and analysis unit in the present invention determines the predicted demand quantity of a single drug in a single data source within a preset period based on the outbound data of the single drug in a single data source at a historical time point and the medication trend coefficient, and determines the predicted total demand quantity of a single drug from several data sources within the preset period, thereby further improving the accuracy of drug shortage risk judgment, improving the timeliness of shortage drug management and the stability and reliability of drug supply, and facilitating the optimal allocation and efficient utilization of drug resources.

Furthermore, the monitoring and analysis unit in the present invention integrates the inventory data and predicted total demand quantity of a single drug from several data sources to accurately assess whether there is a risk of shortage of a single drug, which helps several data sources to discover drug shortage problems, thereby further improving the timeliness of the management of shortage drugs and the stability and reliability of drug supply, and is conducive to the optimal allocation and efficient utilization of drug resources.

Furthermore, the environmental database in the present invention determines an adjustment factor according to the degree of correlation between a single drug and the peak information, and adjusts the medication trend coefficient of the single drug based on the adjustment factor, thereby more accurately reflecting the real-time changes in drug demand, improving the timeliness of shortage drug management and the stability and reliability of drug supply, and facilitating the optimal allocation and efficient utilization of drug resources.

Furthermore, the environmental database in the present invention dynamically adjusts the updating frequency of the medication trend coefficient according to the success rate of judging the historical shortage risk, and continuously optimizes and calibrates the medication trend coefficient, thereby making the prediction of drug demand more flexible and efficient, further improving the timeliness of the management of shortage drugs and the stability and reliability of drug supply, and facilitating the optimal allocation and efficient utilization of drug resources.

Furthermore, the execution unit in the present invention determines the shortage quantity of a single drug in a single data source based on the inventory data of a single drug in a single data source and the predicted demand, and determines the total shortage quantity of a single drug based on the inventory data of a single drug in several data sources and the predicted total demand. This further improves the accuracy of drug shortage risk judgment, improves the timeliness of drug shortage management, and improves the stability and reliability of drug supply, which is conducive to the optimal allocation and efficient use of drug resources.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a connection block diagram of the intelligent drug monitoring system of the present invention;

FIG2 is a determination diagram of the drug data analysis unit of the present invention for determining the replacement type of each drug according to the applicable symptoms of each drug;

3 is a decision diagram of the drug data analysis unit of the present invention for determining the inventory type according to the inventory data and the replacement type of each drug;

4 is a determination diagram of the environmental database of the present invention for adjusting the updating frequency of the medication trend coefficient according to the success rate of judging the historical shortage risk.

DETAILED DESCRIPTION

In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

Please refer to FIG. 1 , which is a connection block diagram of an intelligent drug monitoring system of the present invention. The present invention provides an intelligent drug monitoring system, including:

Basic drug database, which stores drug information from several data sources within a preset time period, including drug name, drug use, outbound data, and inventory data;

a drug data analysis unit connected to the basic drug database, for determining the drug label of the drug according to the drug name, drug use, and inventory data of each drug in a single data source, and determining the drug commonality according to the overlap of drug labels of the same drug in each data source;

An object database storing drug taking cycles of multiple objects of each drug from multiple data sources and states before and after the multiple objects take each drug, for determining a drug use trend coefficient of each drug according to the drug taking cycle and the states before and after taking each drug;

A monitoring and analysis unit, which is connected to the basic drug database, the drug data analysis unit, and the object database, respectively, and is used to determine the predicted demand quantity of a single drug within a preset period according to the outbound data of a single drug and the drug use trend coefficient, and is used to determine whether there is a shortage risk of a single drug according to the inventory data and the predicted demand quantity of a single drug;

An environmental database, which is connected to the object database and the monitoring and analysis unit, respectively, and is used to store peak information of historical medication peaks corresponding to each drug label, including peak time, peak medication amount, and medication range, and to adjust the medication trend of a single drug according to the degree of correlation between the single drug and the peak information, and to adjust the update frequency of the medication trend coefficient according to the success rate of judging the historical shortage risk;

an execution unit, which is connected to the basic drug database, the monitoring and analysis unit and the environment database respectively, and is used to determine the shortage quantity of a single drug according to the inventory data and the predicted demand quantity of the single drug, and to send a data update request to each of the data sources according to the update frequency;

The drug label includes applicable diseases, medication type, inventory type and replacement type.

The present invention establishes a comprehensive intelligent drug monitoring system, determines the drug label and drug commonality of each drug based on the drug data analysis unit, determines the drug usage trend coefficient of each drug through the object database, determines the predicted demand quantity of a single drug within a preset period through the monitoring and analysis unit, and accurately judges whether a single drug has a shortage risk based on inventory data and predicted demand quantity. The environmental database adjusts the drug usage trend coefficient of a single drug through the stored historical drug usage peak information, and adjusts the update frequency of the drug usage trend coefficient according to the success rate of judging the historical shortage risk. Finally, the shortage quantity of a single drug is determined through the execution unit and an update request is issued to several data sources according to the update frequency of the drug usage trend coefficient. The accuracy of judging the risk of drug shortage is further improved, the timeliness of the management of shortage drugs and the stability and reliability of drug supply are improved, which is conducive to the optimal allocation and efficient utilization of drug resources.

Please refer to FIG. 2 , which is a determination diagram of the drug data analysis unit of the present invention determining the replacement type of each drug according to the applicable symptoms of each drug. Specifically, the drug data analysis unit determines the applicable symptoms and medication types of each drug according to the key features extracted from the drug name and drug use of each drug in the single data source, and determines the replacement type of each drug according to the applicable symptoms of each drug, including:

If the number of types of drugs with the same applicable symptoms is greater than or equal to the preset substitution threshold, the substitution type of the drug is a replaceable drug;

If the number of types of drugs with the same applicable symptoms is less than a preset substitution threshold, the substitution type of the drug is an irreplaceable drug.

It is understandable that key features can be extracted from the drug name and drug use of each drug in a single data source. The key features can reflect which diseases a number of drugs treat, thereby determining the applicable diseases and medication types of the corresponding drugs. When the number of types of drugs with the same applicable diseases is greater than or equal to the preset substitution threshold, it means that when needed, any one of these drugs can be replaced by another drug with the same applicable disease, and the corresponding substitution type is a replaceable drug; when the number of types of drugs with the same applicable disease is less than the preset substitution threshold, it means that these drugs have certain special features and importance when needed and cannot be easily replaced by other drugs, so the corresponding substitution type is an irreplaceable drug.

In implementation, the value range of the preset replacement threshold is 2 to 5. Preferably, the preset replacement threshold is 3. The value range and preferred value of the preset replacement threshold need to be adjusted according to actual conditions and will not be elaborated here.

Please refer to FIG. 3 , which is a determination diagram of the drug data analysis unit of the present invention determining the inventory type according to the inventory data and the replacement type of each drug. Specifically, the drug data analysis unit determines the inventory type according to the inventory data of each drug and the replacement type. The inventory type includes a high inventory type and a low inventory type. Different inventory types have different corresponding stock alert thresholds, including:

If the replacement type of the drug is a replaceable drug, and the inventory data of the drug is greater than or equal to a first inventory warning threshold, it is determined that the inventory type of the drug is a high inventory type;

If the replacement type of the drug is a replaceable drug, and the inventory data of the drug is less than a first inventory warning threshold, it is determined that the inventory type of the drug is a low inventory type;

If the replacement type of the drug is an irreplaceable drug, and the inventory data of the drug is greater than or equal to a second inventory warning threshold, it is determined that the inventory type of the drug is a high inventory type;

If the replacement type of the drug is an irreplaceable drug, and the inventory data of the drug is less than a second inventory warning threshold, it is determined that the inventory type of the drug is a low inventory type.

It is understandable that, in a single data source, if the drug is a replaceable drug, the total inventory data of the drugs of the same medication type can be comprehensively viewed, and the inventory type of the drug can be determined based on the total inventory data and the first inventory warning threshold. If the drug is an irreplaceable drug, the inventory data of a single drug is viewed separately, and the inventory type of the drug can be determined based on the inventory data of the single drug and the second inventory warning threshold. In implementation, the first inventory warning threshold is greater than the second inventory warning threshold.

In implementation, it is assumed that the single data source is a provincial medical institution, wherein the value range of the first stock alert threshold is 10,000 boxes to 30,000 boxes, and preferably, the first stock alert threshold is 15,000 boxes. The value range of the second stock alert threshold is 5,000 boxes to 8,000 boxes, and preferably, the second stock alert threshold is 6,000 boxes. The value range and preferred value of the first stock alert threshold and the second stock alert threshold need to be adjusted according to the actual situation of the single data source, which will not be repeated here.

The drug data analysis unit of the present invention analyzes the drug name and drug use of each drug in the single data source to effectively determine the medication type of each drug, and determines whether the drug is a replaceable drug or an irreplaceable drug based on the same number of applicable symptoms, and determines the drug inventory type based on the replacement type of the drug and the corresponding drug inventory warning threshold. The present invention classifies and marks each drug by setting a drug label, thereby further improving the accuracy of drug shortage risk judgment, improving the timeliness of drug shortage management and the stability and reliability of drug supply, and facilitating the optimal allocation and efficient use of drug resources.

Specifically, the drug data analysis unit determines the drug label overlap of the same drug according to the applicable symptoms, medication type, inventory type, and replacement type of the same drug in each data source, and determines the drug commonality according to the drug label overlap.

In implementation, the overlap of drug labels of a single drug in the several data sources is used as the common degree of the drug. Assuming there are two data sources, the drug label of a single drug in the first data source is [cold, oral, high inventory, replaceable], and the drug label of a single drug in the second data source is [cold, granules, low inventory, replaceable]. The same drug label of a single drug in the first data source and the second group of data elements can be represented by 1, and the different drug labels of a single drug in the first data source and the second data source are represented by 0 (different drug labels in the first data source) and 1 (different drug labels in the second data source), respectively. The drug label of a single drug in the first data source is represented by a vector A ₁ = [1, 0, 0, 1], and the drug label of a single drug in the first data source is represented by a vector A ₂ = [1, 1, 1, 1]. The overlap of drug labels of single drugs in the two data sources can be obtained by calculating the cosine similarity between the two. The value range of the drug label overlap R is [0, 1]. The calculation formula of the overlap of drug labels of single drugs in the two data sources is as follows:

Wherein, A ₁ ·A ₂ is the dot product of two vectors A ₁ and A ₂ , ||A ₁ || is the modulus of vector A ₁ , and ||A ₂ || is the modulus of vector A ₂ .

The calculation formula of drug label overlap _Rx of a single drug in the several data sources is as follows:

Among them, R is the average value calculated based on the number E of drug label overlaps of several single drugs after summing up the drug label overlaps of a single drug in any two data sources. The number E of drug label overlaps of several single drugs is the number of combinations that can be made between the several data sources, which will not be repeated here.

The drug data analysis unit in the present invention accurately calculates the drug label overlap of the same drug according to the drug usage type overlap, inventory type overlap, and replacement type overlap of the same drug in each data source, thereby improving the information integration of the same drug in each data source, and determining the commonality of the drug through the drug label overlap, further improving the accuracy of drug shortage risk judgment, improving the timeliness of shortage drug management and the stability and reliability of drug supply, and facilitating the optimal allocation and efficient utilization of drug resources.

Specifically, the object database determines the medication trend coefficient of a single drug according to the preset medication cycle of the single drug and the states of several subjects before and after medication and the medication taking cycle.

It can be understood that the drug taking cycle is the duration that several subjects actually take a single drug.

In implementation, the physical conditions of the subjects are represented by 1 to 10, where 1 is an extremely poor condition of the subject, and 10 is an extremely good condition of the subject. Assuming that the pre-medication conditions of p subjects using a single drug are set to n ₁ , n ₂ , n ₃ ...., n _p , and the post-medication conditions of the subjects using a single drug are set to m ₁ , m ₂ , m ₃ ...., m _p , then the preset medication cycle of the single drug is T ₀ , and the medication cycle of each subject using a single drug is T _j , j = 1, 2, 3, ..., p, then the calculation formula for the medication trend coefficient of the single drug is as follows:

The object database of the present invention accurately determines the medication trend coefficient of a single drug according to the preset medication cycle of the single drug and the states before and after medication of several objects and the medication cycle. This is further conducive to predicting the drug demand trend of each data source, improving the accuracy of drug shortage risk judgment, improving the timeliness of drug shortage management and the stability and reliability of drug supply, and is conducive to achieving optimal allocation and efficient utilization of drug resources.

Specifically, the monitoring and analysis unit determines the predicted demand quantity of a single drug in a single data source within a preset period based on the delivery data of the single drug in a single data source at a historical time point and the medication trend coefficient, and determines the predicted total demand quantity of a single drug in several data sources within a preset period based on the delivery data of the single drug in several data sources at a historical time point, the medication trend coefficient, and the commonality of the drug.

In implementation, the outbound data of a single drug in a single data source at a historical time point is S ₁ , S ₂ , ..., _Sk , ..., _St , where t is the number of several historical time points, and the several time points can be 12 months of a year, with a total of 12 historical time points. The preset period value range is 3 months to 6 months, preferably, the preset period value range is 5 months. The number of historical time points, the value range of the preset period and the preferred value can be determined according to actual conditions, and will not be repeated here.

In implementation, the calculation formula for the predicted demand quantity _H1 of a single drug in a single data source within a preset period is as follows:

H ₁ =S ₀ ×t ₀ ×ΔP (4)

Wherein, s ₀ is the average of the outbound data S ₁ , S ₂ , ..., _Sk , ..., _St of the single drug in a single data source at a historical time point, t ₀ is a preset period, and ΔP is a drug use trend coefficient.

In practice, the calculation formula for the predicted total demand quantity H of a single drug in a preset period from several data sources is as follows:

Wherein, _Mz is the average number of outbound shipments of a single drug in the zth data source at a historical time point, _z1 is the number of data sources, _t0 is the preset period, ΔP is the drug use trend coefficient, and _Rx is the drug universality.

The monitoring and analysis unit described in the present invention determines the predicted demand quantity of a single drug in a single data source within a preset period based on the outbound data of a single drug in a single data source at a historical time point and the drug usage trend coefficient, and determines the predicted total demand quantity of a single drug from several data sources within the preset period, thereby further improving the accuracy of drug shortage risk judgment, improving the timeliness of shortage drug management and the stability and reliability of drug supply, and facilitating the optimal allocation and efficient utilization of drug resources.

Specifically, the monitoring and analysis unit determines whether there is a shortage risk of a single drug based on the inventory data and the predicted total demand quantity of the single drug in several data sources, including:

If the inventory data of the single drug in several data sources is less than the predicted total demand quantity, it is determined that the single drug is at risk of shortage;

If the inventory data of the single drug in several data sources is greater than or equal to the predicted total demand quantity, it is determined that there is no shortage risk for the single drug.

It is understandable that the several data sources are medical institutions, pharmacies, etc. of different sizes. When the inventory data of the single drug in the several data sources is less than the predicted total demand, it means that the current inventory of the single drug in the several data sources can no longer meet the demand of the several objects for the single drug, and there is a shortage of the single drug. When the inventory data of the single drug in the several data sources is greater than or equal to the predicted total demand, it means that the current inventory of the single drug in the several data sources can meet the demand of the several objects for the single drug, the inventory of the single drug is sufficient, there is no risk of shortage, and it will not affect the status of several objects.

The monitoring and analysis unit described in the present invention integrates the inventory data and predicted total demand quantity of a single drug from several data sources to accurately evaluate whether there is a shortage risk of a single drug, which helps several data sources to discover drug shortage problems, thereby further improving the timeliness of the management of shortage drugs and the stability and reliability of drug supply, and is conducive to the optimal allocation and efficient utilization of drug resources.

Specifically, the environmental database determines an adjustment factor according to the degree of correlation between a single drug and the peak information, and adjusts the medication trend coefficient of the single drug based on the adjustment factor.

In implementation, it is assumed that the single drug is a cold medicine, the peak time is winter, the peak dosage is 120,000 boxes, and the demand range is mainly children and the elderly. Assuming that the use of the single drug increases from December to February, and the average monthly usage is 100,000 boxes (close to the peak dosage), if the actual dosage increases significantly in winter and reaches more than 80% of the peak dosage, a time correlation _β1 ( _β1 is 0.8) can be set between the single drug and the peak time; if the actual dosage is close to the peak dosage and reaches more than 90% of the peak dosage, a dosage correlation _β2 ( _β2 is set to 0.9) can be set between the single drug and the peak dosage; if the actual dosage and the number of drug-needing subjects increase to a certain extent and reach more than 70% of the minimum increase in the number of drug-needing subjects, a range matching degree _β3 can be set between the single drug and the drug-needing range (although it is mainly for children and the elderly, middle-aged people and young people also have certain needs, and _β3 is set to 0.7), and the time correlation _β1 , dosage correlation _β2 , and range matching degree β3 are respectively _3. Set different weights (because the main adjustment is the medication trend coefficient, the dosage correlation weight _β2 accounts for a relatively high proportion and can be set to 0.5, the time correlation _β1 accounts for a medium proportion and is set to 0.3, and the range matching _β3 accounts for a relatively small proportion and is set to 0.2) to obtain the adjustment factor. The calculation formula of the adjustment factor is as follows:

δ＝γ ₁ ×β ₁ +γ ₂ ×β ₂ +γ ₃ ×β ₃ (7)

Among them, γ ₁ is the time correlation weight, γ ₂ is the usage correlation weight, γ ₃ is the range matching weight, and the sum of γ ₁ , γ ₂ , and γ ₃ is 1.

In implementation, the time correlation, the usage correlation, the range matching, and the weight may be adjusted according to actual conditions, which will not be described in detail here.

In implementation, the medication trend coefficient of the single drug is adjusted based on the adjustment factor, and the calculation formula of the adjusted medication trend coefficient is as follows:

ΔP ^' ＝ΔP×δ (8)

Wherein, the ΔP ^' is the medication trend coefficient after adjustment, ΔP is the medication trend coefficient before adjustment, and δ is the adjustment factor.

The environmental database in the present invention determines the adjustment factor according to the correlation between a single drug and the peak information, and adjusts the medication trend coefficient of the single drug based on the adjustment factor, thereby more accurately reflecting the real-time changes in drug demand, improving the timeliness of shortage drug management and the stability and reliability of drug supply, and facilitating the optimal allocation and efficient utilization of drug resources.

Please refer to FIG4, which is a determination diagram of the environment database of the present invention adjusting the updating frequency of the medication trend coefficient according to the success rate of judging the historical shortage risk. Specifically, the environment database adjusts the updating frequency of the medication trend coefficient according to the success rate of judging the historical shortage risk, including:

If the success rate of judging the historical shortage risk is less than a preset success rate threshold, it is determined to increase the update frequency;

If the success rate of judging the historical shortage risk is greater than or equal to a preset success rate threshold, it is determined to reduce the updating frequency.

It is understandable that if the success rate of judging the historical shortage risk is less than the preset success rate threshold, it means that the intelligent monitoring system has made an incorrect judgment on the historical shortage risk, and it is necessary to increase the update frequency of the medication trend coefficient, so as to adjust the predicted demand quantity of the single drug within the preset period, and re-determine whether there is a shortage risk of the single drug based on the inventory data and predicted demand quantity of the single drug. If the success rate of judging the historical shortage risk is greater than or equal to the preset success rate threshold, it means that the medication trend coefficient of the single drug does not need to be adjusted and updated at this stage, so the update frequency of the medication trend coefficient of the single drug can be reduced to reduce the complexity of the computer.

In implementation, the shortage risk can be judged at several time points. Assuming that at the several time points, the total number of shortage risk judgments is N ₁ , the number of shortage risk judgment errors is N ₂ , and the number of shortage risk judgment successes is N ₁ -N ₂ , the judgment success rate α is calculated as follows:

In implementation, the several time points may be 12 months in a year, and the shortage risk of the single drug is judged every month respectively. The preset success rate threshold value ranges from 85% to 95%. Preferably, the preset success rate is 90%. The value ranges and preferred values of the several time points and the preset success rate need to be determined based on actual conditions and will not be elaborated here.

The environmental database in the present invention dynamically adjusts the updating frequency of the medication trend coefficient according to the success rate of judging the historical shortage risk, and continuously optimizes and calibrates the medication trend coefficient, thereby making the prediction of drug demand more flexible and efficient, further improving the timeliness of the management of shortage drugs and the stability and reliability of drug supply, and facilitating the optimal allocation and efficient utilization of drug resources.

Specifically, the execution unit determines the shortage quantity of a single drug in a single data source based on the inventory data of the single drug in a single data source and the predicted demand quantity, and determines the total shortage quantity of a single drug in several data sources based on the inventory data of the single drug in several data sources and the predicted total demand quantity.

It can be understood that the shortage situation of the single drug can be determined by the shortage quantity of the single drug in the single data source and the total shortage quantity of the single drug in several data sources, and the scheduling of drugs between the single data source and other data sources can be realized through the execution unit, thereby realizing timely management and supply of the short-supply drugs.

In implementation, the calculation formula for the shortage quantity P _i of a single drug in the i-th data source is as follows:

P _i =Q _i -M _i (10)

Among them, _Qi is the predicted demand quantity of a single drug in the i-th data source, and _Mi is the inventory quantity of a single drug in the i-th data source.

The total number of shortages of a single drug in the above data sources is calculated as follows:

Wherein, Q is the predicted total demand quantity of a single drug in the L data sources, _Mi is the inventory quantity of a single drug in the i-th data source, is the total inventory quantity in L data sources.

The execution unit will subsequently send a data update request to each of the data sources according to the update frequency of the medication trend coefficient.

The execution unit of the present invention determines the shortage quantity of a single drug in a single data source based on the inventory data of a single drug in a single data source and the predicted demand, and determines the total shortage quantity of a single drug based on the inventory data of a single drug in several data sources and the predicted total demand. This further improves the accuracy of drug shortage risk judgment, improves the timeliness of drug shortage management, and improves the stability and reliability of drug supply, which is conducive to the optimal allocation and efficient use of drug resources.

So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims (10)

1. An intelligent drug monitoring system, characterized in that it includes: Basic drug database, which stores drug information from several data sources within a preset time period, including drug name, drug use, outbound data, and inventory data; a drug data analysis unit connected to the basic drug database, for determining the drug label of the drug according to the drug name, drug use, and inventory data of each drug in a single data source, and determining the drug commonality according to the overlap of drug labels of the same drug in each data source; An object database storing drug taking cycles of multiple objects of each drug from multiple data sources and states before and after the multiple objects take each drug, for determining a drug use trend coefficient of each drug according to the drug taking cycle and the states before and after taking each drug; A monitoring and analysis unit, which is connected to the basic drug database, the drug data analysis unit, and the object database, respectively, and is used to determine the predicted demand quantity of a single drug within a preset period according to the outbound data of a single drug and the drug use trend coefficient, and is used to determine whether there is a shortage risk of a single drug according to the inventory data and the predicted demand quantity of a single drug; An environmental database, which is connected to the object database and the monitoring and analysis unit, respectively, and is used to store peak information of historical medication peaks corresponding to each drug label, including peak time, peak medication amount, and medication range, and to adjust the medication trend coefficient of a single drug according to the degree of correlation between the single drug and the peak information, and to adjust the update frequency of the medication trend coefficient according to the success rate of judging the historical shortage risk; an execution unit, which is connected to the basic drug database, the monitoring and analysis unit and the environment database respectively, and is used to determine the shortage quantity of a single drug according to the inventory data and the predicted demand quantity of the single drug, and to send a data update request to each of the data sources according to the update frequency; The drug label includes applicable diseases, medication type, inventory type and replacement type. 2. The intelligent drug monitoring system according to claim 1 is characterized in that the drug data analysis unit determines the applicable disease and medication type of each drug according to the drug name and drug use of each drug in the single data source, and determines the replacement type of each drug according to the applicable disease of each drug, including: If the number of types of drugs with the same applicable symptoms is greater than or equal to the preset substitution threshold, the substitution type of the drug is a replaceable drug; If the number of types of drugs with the same applicable symptoms is less than a preset substitution threshold, the substitution type of the drug is an irreplaceable drug. 3. The intelligent drug monitoring system according to claim 1 is characterized in that the drug data analysis unit determines the inventory type based on the inventory data of each drug and the replacement type, and the inventory type includes a high inventory type and a low inventory type, wherein different inventory types correspond to different inventory warning thresholds. 4. The intelligent drug monitoring system according to claim 3 is characterized in that the drug data analysis unit determines the drug label overlap of the same drugs according to the applicable symptoms, medication types, inventory types, and replacement types of the same drugs in each data source, and determines the degree of drug commonality based on the drug label overlap. 5. The intelligent drug monitoring system according to claim 1 is characterized in that the object database determines the medication trend coefficient of a single drug based on the preset medication cycle of the single drug and the pre- and post-medication states and drug taking cycles of several objects. 6. The intelligent drug monitoring system according to claim 1 is characterized in that the monitoring and analysis unit determines the predicted demand quantity of a single drug in a single data source within a preset period based on the outbound data of the single drug in a single data source at a historical time point and the medication trend coefficient, and determines the predicted total demand quantity of a single drug in several data sources within a preset period based on the outbound data of the single drug in several data sources at a historical time point, the medication trend coefficient, and the commonality of the drug. 7. The intelligent drug monitoring system according to claim 6 is characterized in that the monitoring and analysis unit determines whether there is a shortage risk of a single drug based on the inventory data and predicted total demand quantity of the single drug in several data sources. 8. The intelligent drug monitoring system according to claim 5 is characterized in that the environmental database determines an adjustment factor according to the degree of correlation between a single drug and the peak information, and adjusts the medication trend coefficient of the single drug based on the adjustment factor. 9. The intelligent drug monitoring system according to claim 8, characterized in that the environmental database adjusts the update frequency of the drug use trend coefficient according to the success rate of judging the historical shortage risk, including: If the success rate of judging the historical shortage risk is less than a preset success rate threshold, it is determined to increase the update frequency; If the success rate of judging the historical shortage risk is greater than or equal to a preset success rate threshold, it is determined to reduce the updating frequency. 10. The intelligent drug monitoring system according to claim 7 is characterized in that the execution unit determines the shortage quantity of a single drug in a single data source based on the inventory data of a single drug in a single data source and the predicted demand quantity, and determines the total shortage quantity of a single drug in several data sources based on the inventory data of a single drug in several data sources and the predicted total demand quantity.