Medical data processing method, device and equipment

Abstract

The invention provides a medical data processing method, device and equipment. The method comprises the following steps: acquiring medicine purchasing data in a preset area; determining medicine purchasing combination data and medicine purchasing frequency data according to the medicine purchasing data in the preset area; according to the drug purchase combination data, the drug purchase frequency data and the disease occurrence probability data, determining the number of drugs to be prepared by a drug institution; determining a target type of drugs according to the number of drugs to be prepared by the drug institution; and according to the stock quantity of the target type of drugs in the database and the health monitoring data of the target object in the preset area, determining the supply demand quantity of the target type of drugs in the preset area. According to the scheme of the invention, the medicine data is deeply mined and analyzed, so that the real-time scheduling of the number of medicines is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of computer information processing, and particularly to a method, device and equipment for processing medical data. Background Art

[0002] In the context of the current digital wave, the data in the medical field shows an explosive growth trend. However, since most pharmaceutical sales enterprises may reach customers in a single scenario and cannot conduct full-scenario early warning analysis of drug data, the supply and demand of drugs cannot be balanced, which may lead to the inability to conduct real-time scheduling of drug quantities in areas with relatively high health risks. Summary of the Invention

[0003] The present invention provides a method, device and equipment for processing medical data, which realizes real-time scheduling of drug quantities by deeply mining and analyzing medical data.

[0004] To solve the above technical problems, the technical solution of the present invention is as follows:

[0005] A method for processing medical data includes:

[0006] Obtaining drug procurement data within a preset area;

[0007] Determining drug procurement combination data and drug purchase frequency data according to the drug procurement data within the preset area;

[0008] Determining the quantity of drugs to be stocked by a drug institution according to the drug procurement combination data, drug purchase frequency data and disease occurrence probability data;

[0009] Determining target type drugs according to the quantity of drugs to be stocked by the drug institution;

[0010] Determining the supply demand quantity of target type drugs within the preset area according to the inventory quantity of target type drugs in the database and the health monitoring data of target objects within the preset area.

[0011] Optionally, determining drug procurement combination data according to the drug procurement data within the preset area includes:

[0012] Determining various collocation combination relationships among multiple different drugs according to the drug procurement data within the preset area and a procurement combination data analysis model;

[0013] Determining the optimal drug procurement combination data according to the various collocation combination relationships.

[0014] Optionally, determining drug purchase frequency data within the preset area according to the drug procurement data within the preset area includes:

[0015] Determine the drug purchase frequency data within the preset area based on the number of drug purchases and the quantity of drugs purchased each time within a preset time period in the drug purchase data within the preset area.

[0016] Optionally, determine the quantity of drugs to be stocked by the drug institution according to the drug purchase combination data, the drug purchase frequency data, and the disease occurrence probability data, including:

[0017] Obtain the quantity of drugs to be stocked according to Q = α1(S1(1 + r)P(D)+α2S2fP(D)) - I + γL + δ*W;

[0018] Where Q is the quantity of drugs to be stocked by the drug institution, α1 is the weight coefficient of commonly used drugs in hospitals, α2 is the weight coefficient of commonly used over-the-counter drugs, S1 is the historical sales volume from enterprise to enterprise, S2 is the historical sales volume from enterprise to individual, r is the enterprise-side sales growth rate, P(D) is the disease occurrence probability data, f is the individual-side purchase frequency, I is the inventory quantity, γ is the adjustment coefficient related to the expiration date, L is the drug expiration date, δ is the weight coefficient of the historical weather affecting the disease incidence rate, and W is the disease incidence rate affected by the historical weather.

[0019] Optionally, the disease occurrence probability data is determined through the following process:

[0020] Obtain multiple infection index data within a preset time period in the preset area;

[0021] Obtain the disease occurrence probability data according to the multiple infection index data and the disease probability prediction model; among them, the disease probability prediction model is determined according to the comprehensive weather, humidity, air quality, population age distribution, and population density in the preset area.

[0022] Optionally, determine the target type of drugs according to the quantity of drugs to be stocked by the drug institution, including:

[0023] Identify the types of drugs in the quantity of drugs to be stocked by the drug institution to obtain multiple types of drugs;

[0024] Determine at least one type of drug with a drug quantity greater than a preset value as the target type of drug.

[0025] Optionally, determine the supply demand quantity of the target type of drug in the preset area according to the inventory quantity of the target type of drug in the database and the health monitoring and evaluation data of the target objects in the preset area, including:

[0026] Query the inventory quantity of the target type of drug in the database;

[0027] Dynamically evaluate the health risk of the target object according to the historical health data of the target object in the preset area and the health monitoring data model, and obtain the health monitoring evaluation data of the target object;

[0028] Determine the supply demand quantity of the target type of medicine in the preset area according to the inventory quantity of the target type of medicine and the health monitoring evaluation data of the target object.

[0029] An embodiment of the present invention further provides a processing device for medical data, including:

[0030] An acquisition module, configured to acquire medicine procurement data in a preset area;

[0031] A processing module, configured to determine medicine procurement combination data and medicine purchase frequency data according to the medicine procurement data in the preset area; determine the quantity of medicine to be stocked by the medicine institution according to the medicine procurement combination data, the medicine purchase frequency data, and the disease occurrence probability data; determine the target type of medicine according to the quantity of medicine to be stocked by the medicine institution; and determine the supply demand quantity of the target type of medicine in the preset area according to the inventory quantity of the target type of medicine in the database and the health monitoring data of the target object in the preset area.

[0032] An embodiment of the present invention further provides a computing device, including: a processor and a memory storing a computer program, and when the computer program is run by the processor, the above-mentioned method is executed.

[0033] An embodiment of the present invention further provides a computer-readable storage medium, storing instructions, and when the instructions are run on a computer, the computer is made to execute the above-mentioned method.

[0034] The above solution of the present invention has at least the following beneficial effects:

[0035] The above solution of the present invention realizes real-time scheduling of the quantity of medicine by acquiring medicine procurement data in a preset area; determining medicine procurement combination data and medicine purchase frequency data according to the medicine procurement data in the preset area; determining the quantity of medicine to be stocked by the medicine institution according to the medicine procurement combination data, the medicine purchase frequency data, and the disease occurrence probability data; determining the target type of medicine according to the quantity of medicine to be stocked by the medicine institution; and determining the supply demand quantity of the target type of medicine in the preset area according to the inventory quantity of the target type of medicine in the database and the health monitoring data of the target object in the preset area. Description of the Drawings

[0036] Figure 1It is a schematic flowchart of a method for processing medical data provided by an embodiment of the present invention;

[0037] Figure 2 It is a schematic diagram of modules of a device for processing medical data provided by an embodiment of the present invention. Detailed implementation manners

[0038] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present invention can be more thoroughly understood and the scope of the present invention can be fully conveyed to those skilled in the art.

[0039] As Figure 1 shown, an embodiment of the present invention provides a method for processing medical data, including:

[0040] Step 11, obtaining drug procurement data within a preset area; here, the drug procurement data may include various drug procurement data recorded in a drug institution system; including information such as drug name, procurement time, procurement quantity, procurement amount, and supplier.

[0041] Step 12, determining drug procurement combination data and drug purchase frequency data according to the drug procurement data within the preset area;

[0042] Step 13, determining the quantity of drugs to be stocked by a drug institution according to the drug procurement combination data, the drug purchase frequency data, and the disease occurrence probability data;

[0043] Step 14, determining target type drugs according to the quantity of drugs to be stocked by the drug institution;

[0044] Step 15, determining the supply demand quantity of target type drugs within the preset area according to the inventory quantity of the target type drugs in the database and the health monitoring data of the target objects within the preset area.

[0045] This embodiment of the present invention obtains drug procurement data in a preset area; determines drug procurement combination data and drug purchase frequency data based on the drug procurement data in the preset area; determines the number of drugs that a drug agency needs to prepare for distribution based on the drug procurement combination data, drug purchase frequency data and disease occurrence probability data; determines target type drugs based on the number of drugs that the drug agency needs to prepare for distribution; determines the supply demand quantity of target type drugs in the preset area based on the inventory quantity of the target type drugs in the database and the health monitoring data of the target objects in the preset area; thereby achieving real-time scheduling of drug quantities based on the supply demand quantity of target type drugs.

[0046] In an optional embodiment of the present invention, in step 12, determining the drug purchasing combination data according to the drug purchasing data in the preset area includes:

[0047] Step 121, determining a plurality of collocation and combination relationships between a plurality of different drugs according to the drug procurement data in the preset area and the procurement combination data analysis model;

[0048] Step 122, determining the optimal drug purchasing combination data based on the multiple matching combination relationships.

[0049] In this embodiment, the purchase combination data analysis model can rely on massive user purchase data to analyze the frequency of use and matching rules of conventional drug combinations and explore potential association patterns. For example, analyze the purchase of cold medicines and antipyretics during the peak cold season to determine the best matching plan. Refined analysis of special drug categories can be achieved: for chronic disease drugs, combined with long-term treatment data of patients, analyze the differences in the efficacy of drug combinations at different stages of the disease and their association with weather factors (seasonal changes, temperature changes, etc.). Such as the optimized combination of hypertension drugs and other cardiovascular drugs in the cold winter to cope with blood pressure fluctuations. For children's drugs, combined with their special physiological characteristics and medication needs, analyze the common drug combination patterns of children of different ages in different seasons (affected by weather), such as the combination of related drugs during the peak period of intestinal diseases in children in summer.

[0050] Specifically, the procurement combination data analysis model can be used to analyze the various combination relationships between different drugs through the following steps:

[0051] Enter drug purchase data, including drug name, purchase time, purchase quantity, purchase amount, supplier and other information.

[0052] Organize drug purchase data into a structured table format for subsequent analysis. For example, each row represents a purchase record, and each column corresponds to a different drug attribute.

[0053] According to the analysis purpose and the characteristics of the drugs, relevant features are selected for clustering. For example, the purchase frequency of drugs, the purchase amount, the co-occurrence times with other drugs (i.e., the times of being purchased simultaneously), the drug categories (such as cardiovascular drugs, antibiotics, etc.), suppliers, etc.

[0054] Feature quantization: For some non-numerical features, such as drug categories and suppliers, quantization processing is required. Methods such as one-hot encoding can be used to convert them into numerical data for the model to calculate.

[0055] Data standardization: All selected features are standardized and transformed into standard normal distribution data with a mean of 0 and a standard deviation of 1. For example, each drug is converted into a boolean feature, where existence is 1 and otherwise 0. To eliminate the influence of the dimension and numerical range between different features and ensure that each feature has the same weight and influence in the clustering process. The drug combinations are regarded as "sentences" to generate low-dimensional vectors.

[0056] Determine the number of clusters: The optimal number of clusters can be determined by methods such as the elbow method and the silhouette coefficient. The elbow method is to draw the sum of squared errors (SSE) curve under different numbers of clusters, find the point with the largest slope change in the curve, calculate the SSE (Sum of Squared Errors) for different K values, and select the inflection point as a reference for the number of clusters. The silhouette coefficient is an index to measure the clustering quality, with a value range between [-1, 1]. The larger the value, the better the clustering effect. The optimal value can be selected by calculating the silhouette coefficient under different numbers of clusters.

[0057] SSE represents the sum of the squares of the distances from all sample points to their respective cluster centers and is used to measure the tightness of the clustering. Specifically: where K is the number of clusters, C i is the sample set of the i-th cluster, and μ i is the centroid (mean point) of the i-th cluster. x is the sample point.

[0058] Model training: The processed data is input into the selected clustering algorithm model for training to obtain different drug clustering results. Each cluster can be regarded as a combination of drugs with similar features.

[0059] Result analysis and mining of potential association patterns. Analyze each cluster and describe its features. For example, calculate the average purchase frequency, average purchase amount, and main drug categories of the drugs in each cluster. It can be found that the drugs in some clusters are mainly for treating specific diseases or are from the same supplier, which may imply some potential associations between these drugs.

[0060] Cluster result analysis, statistical features of each cluster: high-frequency drug combinations within the cluster.

[0061] Comparison of drug distributions between clusters (e.g., cluster 0 is mainly composed of cardiovascular drugs, and cluster 1 is mainly composed of hypoglycemic drugs).

[0062] Visualization: Use t-SNE or UMAP to reduce high-dimensional data to 2D and label cluster tags.

[0063] Mining collocation rules: Observe the co-occurrence of drugs in clustering, analyze which drugs often appear in the same cluster, which means they have a high correlation in procurement and may be used in combination. For example, in a drug cluster for treating colds, it may contain antipyretics, cough suppressants, and cold medicines at the same time, indicating that these drugs are often purchased together in actual procurement, reflecting their collocation rules in treating colds.

[0064] Discovering potential associations: By comparing the differences and similarities between different clusters, mining potential association patterns. For example, finding that the drugs in a certain cluster are supplementary or alternative drugs to the drugs in another cluster, or there is a sequential relationship between the drugs in two clusters during the treatment process. For instance, the drugs in one cluster are first-line drugs for treating a certain disease, while the drugs in another cluster are second-line drugs used when the first-line drugs are ineffective, which reveals the potential treatment associations and procurement sequences between drugs. High-frequency drug combination patterns, example output: Cluster 0: {aspirin, amlodipine} (support 15%), often used in combination with metformin (confidence 80%). Cluster 1: {insulin, metformin} (support 10%), reflecting the combined use of drugs for diabetes. Cluster 2: {omeprazole, amoxicillin} (support 8%), suggesting a treatment plan for Helicobacter pylori;

[0065] Verification combined with business knowledge: Combine the results obtained from cluster analysis with professional knowledge in the medical field and actual business experience for verification. Ensure that the mined potential association patterns have clinical rationality and practical application value. For example, judge whether the combination of certain drugs conforms to the treatment specifications based on medical knowledge, or communicate with professionals such as doctors and pharmacists to understand the usage of these drug combinations in clinical practice.

[0066] Through the above steps, the cluster analysis model can help drug purchasers discover potential association patterns between drugs, providing valuable reference for optimizing drug procurement strategies, reasonably arranging inventory, and improving drug supply efficiency.

[0067] In an optional embodiment of the present invention, in step 12, according to the drug procurement data within the preset area, determining the drug purchase frequency data within the preset area includes:

[0068] Step 123: Determine the drug purchase frequency data within the preset area based on the number of drug purchases and the quantity of drugs purchased each time within the preset time period in the drug purchase data within the preset area.

[0069] In this embodiment, by the number of purchases within the preset time period and the quantity of drugs purchased each time, the change in the purchase frequency of various drugs by users is monitored in real time. Once an abnormal fluctuation is found (such as a sharp increase in the purchase frequency in the short term or a sudden decrease after a long-term stability), a deep health risk assessment is immediately triggered. Combining the user's historical purchase data and the drug knowledge base, the change in the user's health condition is accurately inferred, and a corresponding early intervention plan is provided.

[0070] In an alternative embodiment of the present invention, in step 13, determine the quantity of drugs to be stocked by the drug institution according to the drug procurement combination data, the drug purchase frequency data, and the disease occurrence probability data, including:

[0071] Obtain the quantity of drugs to be stocked according to Q = α1(S1(1 + r)P(D) + α2S2fP(D)) - I + γL + δ*W;

[0072] Where Q is the quantity of drugs to be stocked by the drug institution, that is, the quantity of drugs to be prepared;

[0073] α1 is the weight coefficient of commonly used drugs in hospitals, and α2 is the weight coefficient of commonly used over-the-counter drugs, which are adjusted according to the drugs and market conditions. For example, for commonly used drugs in hospitals, the weight of α1 is high; for commonly used over-the-counter drugs, the weight of α2 is high;

[0074] S1 is the historical sales volume from enterprise to enterprise, the historical sales volume at the B end (enterprise to enterprise), reflecting the purchase volume of large customers such as medical institutions;

[0075] S2 is the historical sales volume from enterprise to individual, the historical sales volume at the C end (enterprise to consumer), showing the purchase situation of consumers;

[0076] r is the sales growth rate at the enterprise end, the sales growth rate at the B end, reflecting the growth or decline trend of market demand at the B end;

[0077] P(D) is the disease occurrence probability data;

[0078] f is the purchase frequency at the individual end, the purchase frequency at the C end. For example, the purchase frequency of cold medicine is high during the flu season;

[0079] I is the inventory quantity. When calculating the stocking quantity, the existing inventory should be considered to avoid overstocking or out-of-stock;

[0080] γ is the adjustment coefficient related to the expiration date. For drugs with a short expiration date, the value of γ affects the adjustment of the stocking quantity. For example, for drugs approaching the expiration date, γ can reduce the stocking quantity;

[0081] Let \(L\) be the expiration date of the drug. For drugs with a short expiration date, the stocking should be cautious to prevent losses caused by expiration;

[0082] Let \(\delta\) be the weight coefficient of the historical weather affecting the disease incidence rate. The weight coefficient of the historical weather affecting the disease incidence rate is determined based on historical data and drug characteristics, and reflects the influence degree of the disease incidence rate affected by historical weather on the stocking quantity;

[0083] Let \(W\) be the disease incidence rate affected by historical weather, which is obtained by analyzing historical weather data (such as temperature, precipitation, humidity, etc.) and the disease occurrence situation in the corresponding period, and reflects the influence degree of weather factors on the occurrence of diseases. For example, during continuous high-temperature weather, the incidence rate of intestinal diseases increases.

[0084] In an optional embodiment of the present invention, the disease occurrence probability data is determined through the following process:

[0085] Step 1211: Obtain multiple infection index data within a preset time period in the preset area;

[0086] Step 1212: Obtain the disease occurrence probability data according to the multiple infection index data and the disease probability prediction model;

[0087] Among them, the disease probability prediction model is:

[0088] \(P(D)=\frac{1}{1 + e^{-(\beta_0+\beta_1T+\beta_2H+\beta_3AQ+\beta_4A+\beta_5D+\cdots)}}\),

[0089] Among them, \(P(D)\) is the disease probability prediction value, which is calculated based on comprehensive weather (temperature \(T\), humidity \(H\), air quality (\(AQ\))), population (age distribution (\(A\)), population density (\(D\))) and other factors. The closer the value is to 1, the greater the possibility of disease outbreak, and the demand for related drugs may increase.

[0090] Of course, the disease probability prediction model can also be the following model, and the training process of this model includes:

[0091] Step 12121, obtain the first dataset, the second dataset, and the third dataset, where the first dataset represents the number of susceptible individuals within a preset time period in a preset area, the second dataset represents the number of infected individuals within a preset time period in a preset area, and the third dataset represents the number of recovered individuals within a preset time period in a preset area; the number of susceptible individuals is determined based on the drug purchase data of the first type, the number of infected individuals is determined based on the drug data of the second type, and the types of the first type of drug and the second type of drug may be the same, different, or partially different;

[0092] Step 12122, determine a first parameter according to the first dataset and the second dataset;

[0093] Step 12123, determine a second parameter according to the second dataset and the third dataset;

[0094] Step 12124, obtain a regional epidemic prediction model according to the first parameter, the second parameter, and a preset equation.

[0095] Furthermore, use the trained regional epidemic prediction model to extract features from the input population data to obtain feature data;

[0096] Extract a first sub-feature data and a second sub-feature data from the feature data, where the first sub-feature data represents the eigenvalue of the number of susceptible individuals, and the second sub-feature data represents the eigenvalue of the number of infected individuals;

[0097] Input the first sub-feature data and the second sub-feature data into the regional epidemic prediction model for risk prediction to obtain a disease probability prediction value.

[0098] Specifically, let A(t), B(t), and C(t) represent the number of susceptible individuals, infected individuals, and recovered individuals at time t, respectively, and A(t)+B(t)+C(t)=N.

[0099] In the SIR model, there are two conversions among the three types of populations of susceptible individuals, infected individuals, and recovered individuals: the infection rate β from susceptible individuals to infected individuals and the recovery rate γ from infected individuals to recovered individuals.

[0100] Assume that after a susceptible individual comes into contact with an infected individual, the probability that a susceptible individual is infected within a unit time is b. Since the proportion of susceptible individuals is A / N and there are B(t) infected individuals in the model at time t, the number of susceptible individuals decreases with the following rate of change:

[0101]

[0102] Accordingly, the number of infected individuals increases at the following rate of change and simultaneously transitions to the removed state with a probability γ per unit time:

[0103]

[0104] The number of removed individuals transitions from the infected population to the removed state with a probability γ:

[0105]

[0106] The behaviors of disease transmission and disease cure are represented using the infection rate β and the recovery rate γ.

[0107] In the early stage of disease transmission, A≈N. Substituting A≈N into equation (2) gives:

[0108]

[0109] It is easy to know that the general solution of this differential equation is: B(t) = Ce (β―γ)t

[0110] Substituting the initial condition B(t = 0) = 1 into the above equation gives C = 1. Therefore:

[0111] B(t) = e (β―γ)t = e (rb―γ)t ;

[0112] Data fitting gives β = 0.1827 (95% confidence interval: (0.176, 0.1895))

[0113] When C = 1, it is the threshold for whether the infectious disease dies out. When C < 1, during the infection process, the maximum number of infections that each infected individual can transmit per unit time is less than 1. In this case, even without any prevention and control measures, the infectious disease will gradually die out naturally; when C > 1, the infectious disease will always persist and form an endemic epidemic. In this case, only by implementing certain measures can C be reduced and made less than 1, and the infectious disease epidemic can be effectively controlled, thereby gradually disappearing.

[0114] In an alternative embodiment of the present invention, in step 14, determining the target type of drug according to the quantity of drugs to be stocked prepared by the drug institution includes:

[0115] Step 141, identifying the types of drugs in the quantity of drugs to be stocked prepared by the drug institution to obtain various types of drugs;

[0116] Step 142, determining at least one type of drug with a quantity greater than a preset value as the target type of drug.

[0117] In this embodiment, by identifying drugs with a sharp increase in sales in a specific region or nationwide (i.e., hot-selling drugs), the drug knowledge base and clinical research data are combined to conduct in-depth analysis of the efficacy, applicable population, and therapeutic effects of hot-selling drugs, and determine the reasons why they become hot-selling drugs (such as demand growth caused by public health emergencies, and increased demand for drugs caused by the promotion of new treatment plans, etc.).

[0118] Establish a rapid response cooperation mechanism with pharmaceutical companies. Once a hot-selling drug is detected, immediately contact the relevant pharmaceutical company to obtain more detailed drug information (such as drug ingredients, production processes, quality control standards, etc.) and supply conditions (such as inventory quantity, production capacity, distribution plan, etc.). At the same time, the hot-selling drug information is promptly pushed to the company's internal procurement department, sales department and medical institutions through the push system to ensure that the company can adjust the procurement strategy in time, reserve sufficient inventory, optimize sales channels, meet market demand and ensure the timeliness and stability of drug supply.

[0119] In an optional embodiment of the present invention, in step 15, the supply demand quantity of the target type of medicine in the preset area is determined according to the inventory quantity of the target type of medicine in the database and the health monitoring assessment data of the target object in the preset area, including:

[0120] Step 151, querying the inventory quantity of the target type of medicine in the database;

[0121] Step 152, dynamically assessing the health risk of the target object according to the historical health data of the target object in the preset area and the health monitoring data model, and obtaining health monitoring assessment data of the target object;

[0122] Step 153, determining the supply demand quantity of the target type of medicine in the preset area according to the inventory quantity of the target type of medicine and the health monitoring assessment data of the target object.

[0123] In this embodiment, the specific implementation of the health monitoring data model is as follows:

[0124] Acquire physiological health data and equipment health data, including physiological health: wearable devices: heart rate, blood oxygen, body temperature (sampling frequency 1Hz~100Hz). Medical instruments: ECG, EEG, respiratory waveform (high-precision time series). Equipment health: sensor data: temperature, vibration, pressure, current (industrial equipment).

[0125] Preprocess and clean the data: remove signal loss segments.

[0126] Health status monitoring through memory network models, such as:

[0127] pass Perform health status monitoring, where L is the lag operator, d is the order of differencing, and ε t is white noise, φ i is physiological health data, θ i is equipment health data, X t is the initial noise.

[0128] In this embodiment, by monitoring the health data, the health risks are evaluated, so as to determine the supply demand quantity of the target type of drugs within the preset area, providing a decision-making basis for drug supply.

[0129] For the method described in the above embodiment of the present invention, by mining and analyzing the drug data, the supply demand quantity of the target type of drugs within the preset area can be determined, and thus better subsequent inventory optimization suggestions can be given. The first one: Q1 and Q4: The demand for cardiovascular and cerebrovascular drugs is relatively high, and stockpiling should be carried out in advance to cope with the winter peak. It is recommended to gradually increase the inventory of cardiovascular and cerebrovascular drugs at the end of Q3. The second one: Q2: The demand is relatively stable, and the regular purchase quantity can be maintained to avoid inventory backlog. Appropriately reduce the purchase quantity of other seasonal drugs. The third one: Q3: The high temperature in summer leads to a sharp increase in the demand for gastrointestinal drugs, children's drugs and anti-allergy drugs. It is recommended to purchase a large amount. The demand for anti-inflammatory drugs is moderate, and the purchase quantity can be flexibly adjusted according to historical sales data.

[0130] Inventory management: Use a dynamic inventory model (such as the γ coefficient) to adjust the purchase quantity: Recommended purchase quantity = S B ×(1 + λ × r B ); where γ is the demand fluctuation coefficient (it is recommended to take 1.2 - 1.5). Considering the sales frequency (f_C), reduce the inventory backlog of low-frequency drugs.

[0131] As Figure 2 shown, the embodiment of the present invention also provides a processing device 20 for medical data, including:

[0132] An acquisition module 21, configured to acquire drug purchase data within a preset area;

[0133] A processing module 22, configured to determine drug purchase combination data and drug purchase frequency data according to the drug purchase data within the preset area; determine the drug stocking quantity that the drug institution needs to prepare according to the drug purchase combination data, drug purchase frequency data, and disease occurrence probability data; determine the target type of drugs according to the drug stocking quantity that the drug institution needs to prepare; and determine the supply demand quantity of the target type of drugs within the preset area according to the inventory quantity of the target type of drugs in the database and the health monitoring data of the target objects within the preset area.

[0134] Optionally, determining the drug purchase combination data according to the drug purchase data within the preset area includes:

[0135] Determine various collocation combination relationships among various different drugs according to the drug procurement data and procurement portfolio data analysis model within the preset area;

[0136] Determine the optimal drug procurement portfolio data according to the various collocation combination relationships.

[0137] Optionally, determine the drug purchase frequency data within the preset area according to the drug procurement data within the preset area, including:

[0138] Determine the drug purchase frequency data within the preset area according to the number of drug purchases and the quantity of drugs purchased each time within a preset time period in the drug procurement data within the preset area.

[0139] Optionally, determine the quantity of drugs to be stocked by the drug institution according to the drug procurement portfolio data, drug purchase frequency data, and disease occurrence probability data, including:

[0140] Obtain the quantity of drugs to be stocked according to Q = α1(S1(1 + r)P(D)+α2S2fP(D)) - I + γL + δ*W;

[0141] where Q is the quantity of drugs to be stocked by the drug institution, α1 is the weight coefficient of commonly used drugs in hospitals, α2 is the weight coefficient of commonly used over-the-counter drugs, S1 is the historical sales volume from enterprise to enterprise, S2 is the historical sales volume from enterprise to individual, r is the sales growth rate at the enterprise end, P(D) is the disease occurrence probability data, f is the purchase frequency at the individual end, I is the inventory quantity, γ is the adjustment coefficient related to the expiration date, L is the drug expiration date, δ is the weight coefficient of the influence of historical weather on the disease incidence rate, and W is the disease incidence rate affected by historical weather.

[0142] Optionally, the disease occurrence probability data is determined through the following process:

[0143] Obtain multiple infection index data within a preset time period in the preset area;

[0144] Obtain the disease occurrence probability data according to the multiple infection index data and the disease probability prediction model; among them, the disease probability prediction model is determined according to the comprehensive weather, humidity, air quality, population age distribution, and population density within the preset area.

[0145] Optionally, determine the target type of drugs according to the quantity of drugs to be stocked by the drug institution, including:

[0146] Identify the types of drugs in the quantity of drugs to be stocked by the drug institution to obtain various types of drugs;

[0147] Determine at least one type of drug with the quantity of drugs greater than a preset value as the target type of drug.

[0148] Optionally, determine the supply demand quantity of the target type of drug in the preset area according to the inventory quantity of the target type of drug in the database and the health monitoring and evaluation data of the target objects in the preset area, including:

[0149] Query the inventory quantity of the target type of drug in the database;

[0150] Dynamically evaluate the health risks of the target objects according to the historical health data and the health monitoring data model of the target objects in the preset area to obtain the health monitoring and evaluation data of the target objects;

[0151] Determine the supply demand quantity of the target type of drug in the preset area according to the inventory quantity of the target type of drug and the health monitoring and evaluation data of the target objects.

[0152] It should be noted that the device corresponding to the above method, all implementation manners in the embodiments of the above method are applicable to the embodiments of this device and can also achieve the same technical effects.

[0153] An embodiment of the present invention further provides a computing device, including: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, enabling the one or more processors to implement the method as described in the above embodiments. All implementation manners in the above method embodiments are applicable to this embodiment and can also achieve the same technical effects.

[0154] An embodiment of the present invention further provides a computer-readable storage medium for a computing device, in which a program is stored, and when the program is executed by a processor, it implements the method as described in the above embodiments. All implementation manners in the above method embodiments are applicable to this embodiment and can also achieve the same technical effects.

[0155] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in the present invention can be implemented by electronic hardware, or a combination of computing device software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraint conditions of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0156] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0157] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and 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 displayed or discussed couplings or direct couplings or communication connections between each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0158] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0159] In addition, in each embodiment of the present invention, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0160] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a storage medium readable by a computing device. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computing device software product is stored in a storage medium and includes several instructions for causing a computing device (which can be a personal computing device, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0161] In addition, it should be noted that in the device and method of the present invention, obviously, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations shall be regarded as equivalent solutions of the present invention. Moreover, the steps of performing the above series of processes can naturally be executed chronologically in the order described, but it is not necessary to be executed necessarily in chronological order. Some steps can be executed in parallel or independently of each other. For those of ordinary skill in the art, it is possible to understand that all or any steps or components of the method and device of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in the form of hardware, firmware, software, or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0162] Therefore, the object of the present invention can also be achieved by running a program or a set of programs on any computing device. The computing device can be a well-known general-purpose device. Therefore, the object of the present invention can also be achieved only by providing a program product containing program code for implementing the method or device. That is to say, such a program product also constitutes the present invention, and a storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be noted that in the device and method of the present invention, obviously, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations shall be regarded as equivalent solutions of the present invention. Moreover, the steps of performing the above series of processes can naturally be executed chronologically in the order described, but it is not necessary to be executed necessarily in chronological order. Some steps can be executed in parallel or independently of each other.

[0163] The above is the preferred embodiment of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for processing medical data, characterized in that, Including: Obtain drug procurement data within a preset area; Determine drug procurement combination data and drug purchase frequency data according to the drug procurement data within the preset area; Determine the quantity of drug stockpiling that the drug institution needs to prepare according to the drug procurement combination data, drug purchase frequency data, and disease occurrence probability data; Determine the target type of drugs according to the quantity of drug stockpiling that the drug institution needs to prepare; Determine the supply demand quantity of the target type of drugs within the preset area according to the inventory quantity of the target type of drugs in the database and the health monitoring data of the target objects within the preset area.

2. The processing method of medical data according to claim 1, wherein, Determine drug procurement combination data according to the drug procurement data within the preset area, including: Determine various collocation combination relationships among multiple different drugs according to the drug procurement data within the preset area and the procurement combination data analysis model; Determine the optimal drug procurement combination data according to the various collocation combination relationships.

3. The processing method of medical data according to claim 1, characterized in that, Determine the drug purchase frequency data within the preset area according to the drug procurement data within the preset area, including: Determine the drug purchase frequency data within the preset area according to the number of drug purchases within a preset time period in the drug procurement data within the preset area and the quantity of drugs purchased each time.

4. The method for processing medical data according to claim 1, characterized in that Determine the quantity of drug stockpiling that the drug institution needs to prepare according to the drug procurement combination data, drug purchase frequency data, and disease occurrence probability data, including: Obtain the quantity of drug stockpiling according to Q = α1(S1(1 + r)P(D)+α2S2fP(D)) - I + γL + δ*W; Wherein, Q is the quantity of drug stockpiling that the drug institution needs to prepare, α1 is the weight coefficient of commonly used drugs in the hospital, α2 is the weight coefficient of commonly used over-the-counter drugs, S1 is the historical sales volume from enterprise to enterprise, S2 is the historical sales volume from enterprise to individual, r is the enterprise-side sales growth rate, P(D) is the disease occurrence probability data, f is the individual-side purchase frequency, I is the inventory quantity, γ is the adjustment coefficient related to the expiration date, L is the drug expiration date, δ is the weight coefficient of the historical weather affecting the disease incidence rate, and W is the disease incidence rate affected by the historical weather.

5. The method for processing medical data according to claim 1, wherein The disease occurrence probability data is determined through the following process: Obtain multiple infection index data within a preset time period within the preset area; Obtain the disease occurrence probability data according to the multiple infection index data and the disease probability prediction model; wherein, the disease probability prediction model is determined according to the comprehensive weather, humidity, air quality, population age distribution, and population density within the preset area.

6. The processing method of medical data according to claim 1, wherein, Determine the target type of drugs according to the quantity of drug stockpiling that the drug institution needs to prepare, including: Identify the drug types in the quantity of drug stockpiling that the drug institution needs to prepare to obtain multiple types of drugs; Determine at least one type of drug with a drug quantity greater than a preset value as the target type of drugs.

7. The method for processing medical data according to claim 1, characterized in that Determine the supply demand quantity of the target type of drugs within the preset area according to the inventory quantity of the target type of drugs in the database and the health monitoring and evaluation data of the target objects within the preset area, including: Query the inventory quantity of the target type of drugs in the database; Dynamically evaluate the health risk of the target object according to the historical health data of the target object in the preset area and the health monitoring data model to obtain the health monitoring evaluation data of the target object; Determine the supply demand quantity of the target type of drug in the preset area according to the inventory quantity of the target type of drug and the health monitoring evaluation data of the target object.

8. A processing device for medical data, characterized in that, Including: An acquisition module, configured to acquire drug procurement data in a preset area; A processing module, configured to determine drug procurement combination data and drug purchase frequency data according to the drug procurement data in the preset area; determine the quantity of drugs to be stocked that the drug institution needs to prepare according to the drug procurement combination data, the drug purchase frequency data, and the disease occurrence probability data; determine the target type of drug according to the quantity of drugs to be stocked that the drug institution needs to prepare. Determine the supply demand quantity of the target type of drug in the preset area according to the inventory quantity of the target type of drug in the database and the health monitoring data of the target object in the preset area.

9. A computing device, characterized in that, Including: A processor and a memory storing a computer program, where when the computer program is run by the processor, it executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Stored with instructions, when the instructions are run on a computer, the computer is made to execute the method according to any one of claims 1 to 7.

Images