Medical instant retail insight system in o2o mode

Abstract

The invention discloses a medical instant retail insight system in an o2o mode, relates to the technical field of intelligent supply chain management, and is used for solving the problem that when an order is generated or the inventory is changed, the system cannot update the inventory information instantly, resulting in information lag and inaccuracy. The updating frequency is dynamically adjusted by combining real-time analysis of order influence measurement, the problem that information of a traditional system is lagged and inaccurate is solved, and it is ensured that inventory information is synchronized with actual requirements; and aiming at the particularity of the medicine storage environment and the medicine type, the medicine complexity is quantified, and an updating method is selected through the TOPSIS algorithm differentiation, so that the medicine failure risk caused by improper storage conditions or untimely updating is reduced, and the medical safety is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of smart supply chain management, and more specifically, to an instant medical retail insight system under an O2O model. Background Art

[0002] The O2O model is a business model that closely integrates online services and offline physical stores. It aims to guide consumers to physical stores through the Internet platform, while converting offline customers into online customers, achieving seamless integration between online and offline.

[0003] Medical instant retail is an emerging business model that combines the characteristics of O2O (online to offline) and instant delivery. It aims to provide consumers with convenient medical products and services through online platforms and achieve fast delivery through efficient logistics systems.

[0004] The existing technology has the following deficiencies:

[0005] Existing medical instant retail systems rely on traditional manual record-keeping or simple management systems, which are unable to achieve real-time inventory monitoring. When orders are placed or inventory changes occur, the system cannot immediately update inventory information, resulting in information lags and inaccuracies. Therefore, this application proposes an O2O medical instant retail system that aims to dynamically adjust the frequency of inventory updates and select appropriate inventory information update technologies to improve service efficiency and cost control.

[0006] In view of the above problems, the present invention proposes a solution. Summary of the Invention

[0007] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a medical instant retail insight system under the O2O model to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A medical instant retail insight system under the O2O model,

[0010] It includes data acquisition module, data classification module, data matching module and feedback adjustment module, and the signal connections between the modules are as follows:

[0011] The data collection module is used to collect inventory information update demand-related data and order impact measurement-related data, and pre-process the data;

[0012] The data classification module is used to classify the inventory information update requirements through clustering algorithms and calculate the comprehensive indicators of order impact measurement;

[0013] The data matching module is used to select the inventory information update method based on the drug inventory information update demand and drug complexity through the TOPSIS method;

[0014] The feedback adjustment module is used to combine the inventory information update demand level and order impact measurement comprehensive indicators to dynamically adjust the inventory information update frequency through fuzzy rules.

[0015] In a preferred embodiment, the inventory information update demand-related data collected by the data acquisition module includes the supply arrival time, replenishment cycle, sales speed, return quantity and storage environment of the drug; the order impact measurement-related data includes order quantity, order processing time and order variability; and the preprocessing includes data standardization processing.

[0016] In a preferred embodiment, the replenishment cycle is the time interval from determining the need for replenishment to the actual completion of replenishment, including order generation time, supplier confirmation time, supplier processing time, transportation time and warehousing time; the storage environment is divided into levels according to temperature parameters, including room temperature storage, cool and dry environment, constant temperature storage, refrigerated storage and strict cold chain storage.

[0017] In a preferred embodiment, the data classification module uses a K-means clustering algorithm to classify the inventory information update demand into three levels: high demand, medium demand, and low demand. The clustering process includes:

[0018] The collected feature data is formed into a feature matrix and the feature values ​​are standardized;

[0019] Set the number of clusters to 3 and iteratively update the cluster centers until convergence;

[0020] The levels are defined based on the average values ​​of the characteristics of each cluster. The cluster with the shortest supply arrival time, the shortest replenishment cycle, the fastest sales speed, the least number of returns, and the most stable storage environment is classified as the high-demand level.

[0021] In a preferred embodiment, the process of calculating the order impact metric comprehensive index by the data classification module includes:

[0022] Calculate the order quantity impact coefficient, order processing time impact coefficient, and order variability impact coefficient expressed as volatility;

[0023] By weighted summation formula ;in 、 、 are the weights of order quantity, order processing time, and order volatility, respectively; Qᵢ, Tᵢ, and Vᵢ are the corresponding impact coefficients.

[0024] In a preferred embodiment, the fuzzy rules of the feedback adjustment module include:

[0025] The input variables are inventory information update desirability, which is divided into High, Medium, and Low, and order impact measure, which is divided into Big, Medium, and Small;

[0026] The output variable is the inventory information update frequency, which is specifically divided into Increase, Unchanged, and Decrease;

[0027] The rules include: if the inventory information update demand is High and the order impact measure is Big, then the inventory information update frequency is Increase; if the inventory information update demand is Low and the order impact measure is Small, then the inventory information update frequency is Decrease.

[0028] In a preferred embodiment, the drug complexity is calculated by weighted summation of the storage environment level and the drug type level, using the formula: Where For the storage environment of drugs, For drug type, and They are weight coefficients of storage environment and drug type respectively, and the sum of the weight coefficients is 1; the drug type level is divided into 1-5 points according to medical use.

[0029] In a preferred embodiment, the TOPSIS method adopted by the data matching module includes:

[0030] Determine the decision criteria as inventory information update necessity and drug complexity, and convert the inventory information update necessity level into a numerical value of 1-3;

[0031] Normalize the decision criteria data, set the ideal solution as the maximum demand for inventory information update and the minimum drug complexity, and the negative ideal solution as the minimum demand for inventory information update and the maximum drug complexity;

[0032] Calculate the Euclidean distance between each drug and the ideal solution and the negative ideal solution, and use the comprehensive index Where and are the distances between the i-th drug and the ideal solution and the negative ideal solution, respectively.

[0033] In a preferred embodiment, the data matching module selects an inventory information update method based on the comprehensive index: automatic update is selected when the comprehensive index is ≥ the 66th percentile; semi-automatic update is selected when the comprehensive index is ≥ the 33rd percentile and < the 66th percentile; manual update is selected when the comprehensive index is ≤ the 33rd percentile.

[0034] In a preferred embodiment, the order volatility is calculated by volatility, including:

[0035] Calculate the logarithmic rate of return of the number of orders in adjacent time periods ; Where yi is the number of orders in the i-th time period, and ln is the natural logarithm;

[0036] ; where N is the total number of time periods, is the logarithmic rate of return, is the average of the logarithmic returns.

[0037] The technical effects and advantages of the instant medical retail insight system under the O2O model of the present invention are as follows:

[0038] The present invention divides the inventory update demand level through a clustering algorithm, combines it with real-time analysis of order impact metrics, and dynamically adjusts the update frequency, solving the problems of information lag and inaccuracy in traditional systems, ensuring that inventory information is synchronized with actual demand. In view of the particularity of drug storage environment and drug type, the complexity of drugs is quantified, and the update method is differentiated and selected through the TOPSIS algorithm to reduce the risk of drug failure due to improper storage conditions or untimely updates, thereby ensuring medical safety. Fuzzy rules are used to respond to order variability, and the update frequency is increased for drugs with high demand and large order impact, so as to respond quickly to urgent orders; optimized update methods are used for low-demand, simple drugs to reduce unnecessary system computing power and manpower investment, and balance service efficiency and cost. Finally, supply chain data such as supply arrival time and replenishment cycle are integrated, and inventory update priorities are clarified through cluster analysis to help medical retail companies accurately control the replenishment rhythm, reduce out-of-stock or backlog problems, and improve supply chain stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a structural diagram of a medical instant retail insight system under the O2O model of the present invention. DETAILED DESCRIPTION

[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0041] This invention combines real-time analysis of order impact metrics and dynamically adjusts the update frequency, solving the problems of information lag and inaccuracy in traditional systems and ensuring that inventory information is synchronized with actual demand. It also quantifies the complexity of drugs based on the particularity of drug storage environments and drug types, and uses the TOPSIS algorithm to differentiate and select update methods, reducing the risk of drug failure caused by improper storage conditions or untimely updates, thereby ensuring medical safety.

[0042] Example 1

[0043] Figure 1 This paper proposes an O2O-based medical instant retail insight system, which aims to dynamically adjust the frequency of updating inventory information and select appropriate inventory information updating technologies. The system includes the following steps:

[0044] Step 1: Collect relevant data needed to analyze the frequency of dynamically adjusting and updating inventory information, including inventory information update demand and order impact measurement, ensure data accuracy and consistency, pre-process the data, and store it in the database.

[0045] Step 2: Retrieve data from the database, use a clustering algorithm to calculate the inventory information update demand, and divide it into three levels.

[0046] Step 3: Collect order-related data, calculate order volatility, impact coefficient, and comprehensive indicators through standardization.

[0047] Step 4: Use fuzzy rule definition to comprehensively analyze the inventory information update demand and order impact measurement to dynamically adjust the inventory information update frequency.

[0048] Step 5: Calculate the complexity of the drug based on its storage environment and drug type.

[0049] Step 6: Analyze the methods for drug inventory updates. Use TOPSIS to comprehensively analyze the drug inventory information update needs and drug complexity to select the most appropriate inventory update method.

[0050] Specifically, in step 1, dynamically adjusting and updating inventory information refers to the process of flexibly adjusting and updating inventory information based on real-time or near-real-time data. The need for inventory information updates refers to assessing the urgency or frequency of inventory information updates based on characteristic data. Characteristic data used for this assessment includes, but is not limited to, drug supply arrival time, replenishment cycle, sales velocity, number of returns, and storage environment. The supply arrival time refers to the time interval from the actual shipment of a drug in the supply chain to its arrival at the warehouse or distribution center; each shipment and arrival time can be recorded in the supply chain management system with a timestamp.

[0051] The replenishment cycle refers to the time interval from the time replenishment is determined to the time it actually occurs during the sales process. This includes order generation time, supplier confirmation time, supplier processing time, transportation time, and warehousing time. This can be calculated by recording the start and end times of each process, subtracting them to get the time for that process, and then adding up all the processes to get the replenishment cycle. For example, by recording the shipping and arrival times of pharmaceutical products, we can determine the transportation time.

[0052] Sales velocity refers to the number of drugs sold per unit time, usually on a daily, weekly, or monthly basis. Sales data (such as sales volume) can be recorded and collected in real time through a POS system or sales spreadsheet.

[0053] The number of returns refers to the number of drugs returned from customers due to various reasons; the number of returns can be recorded through return records and customer service feedback.

[0054] The storage environment refers to the environmental conditions, such as temperature and humidity, experienced during drug storage and transportation. Environmental monitoring equipment (such as temperature sensors and hygrometers) can be used to monitor drug storage conditions in real time. For example, the storage environment temperature can be collected in real time. Excessively high or low temperatures can affect drug storage. The storage environment can be categorized as ambient temperature storage (25°C to 30°C) and labeled 1, cool and dry environment (15°C to 25°C) as 2, constant temperature storage (8°C to 15°C) as 3, refrigerated storage (2°C to 8°C) as 4, and strict cold chain storage (-20°C and below) as 5, and so on. It should be noted that using temperature to assess the storage environment is merely an example in this embodiment; humidity, light, and other factors can also be used for assessment, which will not be detailed here.

[0055] Order impact measurement measures the degree to which orders affect the frequency of inventory updates. This includes factors such as order quantity, order processing time, and order variability. Order processing time refers to the length of time from order generation to order completion or delivery. Order generation and completion timestamps can also be recorded to calculate order processing time. Order variability refers to the fluctuation and change in order quantity and type over a given period of time. This can be calculated using factors such as the number of orders in each time period.

[0056] Specifically, in step 2, a clustering algorithm is used to calculate the demand for inventory information updates and classify them into three levels (clusters): high demand, medium demand, and low demand. A clustering algorithm is an unsupervised learning method used to divide a dataset into multiple groups so that data points in the same group are more similar in some sense, and data points in different groups are more different in some sense. The specific calculation process is as follows:

[0057] S1: Collect feature data, i.e., feature data that evaluates the need for inventory information updates, including but not limited to drug supply arrival time, replenishment cycle, sales speed, return quantity, storage environment, etc. The collected feature data is formed into a feature matrix. Assume that a medical instant retail enterprise has n drug products, each drug product has m features, then the feature matrix X is: represents the jth eigenvalue of the i-th drug product. A sample is a vector containing all eigenvalues. Each sample represents a drug product and contains a vector of all the features of the drug product. That is, each sample is an m-dimensional feature vector, where m is the number of features.

[0058] S2: Data preprocessing. Standardize the eigenvalues ​​to ensure they have the same scale and dimension. A common method is to subtract the mean from each eigenvalue and then divide it by its standard deviation so that its mean is 0 and its standard deviation is 1. The specific formula is Where is the standardized eigenvalue, x is the original eigenvalue, α is the mean of the feature, is the standard deviation of the feature.

[0059] S3: Select an appropriate number of clusters. The number of clusters indicates how many clusters or groups the data will be divided into when using a clustering algorithm. Selecting an appropriate number of clusters is a very important step in cluster analysis, which directly affects the quality and interpretability of the final clustering results. According to this implementation case, the demand for inventory information updates can be divided into three levels, namely, high, medium and low corresponding to high demand, medium demand and low demand, so the number of clusters can be determined as 3. By selecting the number of clusters as 3, the desired three clusters can be obtained, each cluster representing a level of inventory information update demand. At the same time, further adjustments can be made through the elbow rule or silhouette coefficient, which will not be described in detail here.

[0060] S4: Select and apply a clustering algorithm. Common clustering algorithms include K-means clustering, hierarchical clustering, and density-based clustering. Based on drug feature data, this solution uses K-means clustering as an example. This algorithm is simple, easy to understand, and implement, making it particularly well-suited for processing large datasets.

[0061] Randomly select k initial cluster centers and assign each sample to the cluster with the closest cluster center. Then, calculate the new center of each cluster (i.e., the mean of the samples within the cluster) and use it as the new cluster center. Repeat the two steps of assigning samples and updating centers until the cluster centers no longer change or the maximum number of iterations is reached. Assigning samples means assigning each sample to the cluster with the closest cluster center, and updating centers means calculating the new center of each cluster (i.e., the mean of the samples within the cluster) and using it as the new cluster center.

[0062] Mark the randomly selected k initial cluster centers as μ1, μ2..., μk. For each sample, calculate its distance to each cluster center. The specific formula is ;In the formula Represents the distance between sample xi and cluster center μj. Assign it to the nearest cluster Cu (u=1, 2, 3), specifically For each cluster Cu, calculate its new cluster center μj, that is, the sample mean within the cluster, , where xi represents the i-th drug product and contains the feature vector of all the features of the drug product.

[0063] S5: Explain the clustering results. A short supply arrival time indicates that the inventory needs to be updated frequently to ensure the smooth flow of the supply chain; a short replenishment cycle indicates that the sales speed of these drugs is fast, and they need to be replenished quickly and the frequency of inventory information updates is increased; a fast sales speed indicates that these drugs are in high demand in the market, and inventory information needs to be updated frequently to maintain sufficient supply; a small number of returns indicates that the quality of these drugs is good and customer satisfaction is high, and inventory information needs to be updated frequently at this time; a small (stable) storage environment means that the storage conditions of these drugs are relatively easy to control, and the frequency of updating inventory information is high. Therefore, the average value of each feature of each cluster can be calculated to further define high-demand clusters, etc. For each cluster, the average value of each feature is calculated and expressed as ; where u represents the index of the cluster and j represents the index of the feature. The specific formula is Where is the number of drugs in cluster Cu, is the jth characteristic value of the qth drug in cluster Cu. By comparing the average values ​​of each characteristic within the cluster, three clusters can be defined. For example, a cluster with the fastest supply arrival time, shortest replenishment cycle, fastest sales speed, fewest returns, and a moderate and stable storage environment can be defined as a high-demand cluster.

[0064] Specifically, in step 3, order-related data mainly includes order quantity, order processing time, and order volatility. Order quantity and order processing time can be obtained by collecting data or directly calculating. The calculation method of order volatility is as follows:

[0065] First, we collect data, including the total number of orders for each time period (daily, weekly, and monthly) and the timestamp of each order. Then, we calculate the standard deviation of the number of orders. The standard deviation is a common measure of variability that reflects the average deviation of the data set. The calculation formula is: ;In the formula is the standard deviation, N is the number of orders, yi is the number of orders in each time period, μ is the average number of orders, and Finally, volatility is calculated to assess order volatility. Volatility is a commonly used volatility measurement method in the financial field and can also be used to calculate order volatility. It is usually measured using time series data by calculating the standard deviation of the logarithmic return rate (a commonly used return rate calculation method in the financial field to measure the relative change in asset prices between two time points) of the number of orders in adjacent time periods. The logarithmic return rate of the number of orders in adjacent time periods is calculated as follows: ; where yi is the number of orders in the i-th time period, and ln is the natural logarithm. The average value of the logarithmic rate of return is calculated as ; Finally, the calculation formula is ; where N is the total number of time periods, is the logarithmic rate of return, is the average of the logarithmic returns.

[0066] The order impact metric oll is calculated by order quantity, order processing time, and order volatility, as follows:

[0067] Calculate the order quantity impact coefficient. The specific formula is: ; where Q is the number of orders in the current time period, is the average order quantity, is the standard deviation of the order quantity. Similarly, we obtain the order processing time impact coefficient Ti. The order variability impact coefficient is replaced by volatility and labeled Vi.

[0068] The influence coefficients of order quantity, order processing time, and order volatility are combined into an indicator oll, and the formula is: ;in 、 、 These are the weights of order quantity, order processing time, and order variability, which need to be determined based on relevant field expertise and specific needs and will not be elaborated here.

[0069] When Oll is high, it means that the order impact measure is large, the demand for inventory information update is high, and the update frequency of inventory information should be increased; when Oll is low, it means that the order impact measure is small, the demand for inventory information update is low, and the update frequency of inventory information can be reduced.

[0070] Specifically, in step 4, fuzzy rules are used to define a comprehensive analysis of inventory information update demand and order impact measurement, thereby dynamically adjusting the inventory information update frequency.

[0071] The inventory information update desirability and order impact measure are defined as input variables, which are divided into different fuzzy sets, such as "Low", "Medium", and "High" for inventory information update desirability and "Small", "Medium", and "Big" for order impact measure.

[0072] The inventory information update frequency is defined as the output variable and is also divided into different fuzzy sets, such as "Decrease", "Unchanged", and "Increase". For the inventory information update frequency, "Decrease" means reducing the inventory information update frequency, "Unchanged" means that the inventory information update frequency remains unchanged, and "Increase" means increasing the inventory information update frequency.

[0073] Develop fuzzy rules to describe the impact of inventory update demand and order impact metrics on inventory update frequency. Rules can be defined based on industry expertise or obtained through data analysis and experimentation. For example, label inventory update demand as A, order impact metrics as oll, and inventory update frequency as R. Then, we can define:

[0074] Rule1:IF(AisHigh)AND(ollisBig)THEN(RisIncrease)

[0075] Rule2:IF(AisLow)AND(ollisSmall)THEN(RisDecrease) ......

[0077] Perform fuzzy reasoning based on fuzzy rules and dynamically adjust the frequency of inventory information updates.

[0078] It should be noted that the division of fuzzy sets can be adjusted according to actual conditions. For example, this embodiment takes three fuzzy sets as an example. In fact, the inventory information update demand, order impact measurement and inventory information update frequency can be divided into more than three sets, so as to more conveniently dynamically adjust the inventory information update frequency.

[0079] Further judgment on whether the inventory information update demand is low, medium or high can be made directly based on the clustering results of the inventory information update demand, which will not be repeated here; for the judgment on whether the order impact measure is small, medium or large, an order impact measure threshold can be set for comparison. For example, when OLL is greater than the first order impact measure threshold, it is marked as "Big", etc., which will not be elaborated on here.

[0080] Specifically, in step 5, drug complexity refers to the strictness and difficulty of managing the conditions required for storage, transportation, and inventory updates. Drug complexity can be calculated based on two primary factors: storage environment and drug type. Storage environment can be assessed solely by temperature, while drug type can be converted into numerical data (data with specific values) based on its medical use or importance. The calculation is as follows:

[0081] Data on drug chemical composition, biological product characteristics, primary effects, and side effects is collected from drug inserts and supplier information. Safety records and efficacy evaluations are also obtained from medical institutions, drug manufacturers, and drug regulatory agencies. Based on this data, drugs are categorized and assigned a score. For example, drugs for common ailments (such as cold and painkillers) are assigned a score of 1; drugs for chronic disease management (such as hypertension and diabetes) are assigned a score of 2; drugs for serious but treatable conditions (such as antibiotics and antivirals) are assigned a score of 3; drugs for life-saving conditions (such as emergency heart disease medications and certain cancer drugs) are assigned a score of 4; and critical emergency drugs (such as rescue drugs and organ transplant rejection medications) are assigned a score of 5.

[0082] The storage environment of the drug is the same as the collection method in step 1 and will not be repeated here.

[0083] Finally, a weighted sum is used to calculate the comprehensive score of the two factors of storage environment and drug type to evaluate the complexity of the drug. The calculation formula is Where For the storage environment of drugs, For drug type, and The weighting factors for storage environment and drug type are respectively, and the sum of these weighting factors is 1. These weighting factors can be set based on relevant field expertise and specific needs. For example, if a drug is very sensitive to temperature, the weighting factor for the storage environment should be increased, etc., but this is not limited here. The resulting comprehensive score ranges from 1 to 5. A higher comprehensive score indicates a more complex drug; conversely, a lower score indicates a less complex drug.

[0084] Specifically, in step 6, the inventory information update methods can be divided into three types: automatic update, manual update, and semi-automatic update (a combination of manual and automatic). The decision to use automatic update, manual update, or semi-automatic update to update the drug inventory information is mainly based on the drug inventory information update demand and drug complexity. TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) is a multi-criteria decision analysis method used to evaluate the pros and cons of candidate solutions relative to a set of specific attributes. This embodiment uses TOPSIS to conduct a comprehensive analysis of the two, and the specific process is as follows:

[0085] P1: Determine the decision criteria. Determine the decision criteria for analyzing and selecting the appropriate inventory update method, including the need for updating drug inventory information and the complexity of the drug. The sample data is ; That is, the inventory information update demand and drug complexity of each drug, and the sample size is the number of drugs that need to be updated.

[0086] P2: Normalized data. A represents the inventory information update demand of the drug. The cluster with low update demand can be marked as 1, and the inventory information update demand value of all drugs in the cluster is 1. Similarly, the cluster with medium update demand is marked as 2, and the cluster with high update demand is marked as 3. The formula is used to normalize the inventory information update demand and drug complexity of the sample drug. The formula is Where, is the normalized value.

[0087] P3: Determine the ideal solution and the negative ideal solution. The ideal solution is the solution that achieves the best value on each decision criterion, and the negative ideal solution is the solution that achieves the worst value on each decision criterion. Generally speaking, the higher the demand for inventory information update, the more likely it is to consider using the automatic update method in order to quickly respond to demand changes and maintain a stable inventory level; the lower the complexity (simple) of the drug, the more flexible the automatic update method can be in meeting its needs, and the more likely it is to choose the automatic update method. Therefore, the ideal solution is the maximum value of the demand for inventory information update and the minimum value of the drug complexity, that is, Similarly, the negative ideal solution is the minimum value of inventory information update demand and the maximum value of drug complexity, that is, .

[0088] P4: Calculate the similarity metric. Use the Euclidean distance formula to calculate the distance between each drug and the ideal solution. Where is the distance between the ith drug and the ideal solution, is the actual value of the i-th drug on the j-th decision criterion, The ideal solution is , γ is the number of decision criteria, which is 2, namely the drug inventory information update demand and drug complexity. Similarly, by calculating the distance between each drug and the negative ideal solution, we can get .

[0089] P5: Calculate the comprehensive index of the drug. Use the comprehensive index formula to calculate the comprehensive index of each drug, specifically: Where and are the distances between the i-th drug and the ideal solution and the negative ideal solution, respectively.

[0090] P6: Interpret the results. Sort the drugs by their composite index from largest to smallest. For drugs with a composite index greater than or equal to the 66th percentile (the 66th percentile value in a data set), select the manual update method. For drugs with a composite index greater than or equal to the 33rd percentile and less than the 66th percentile, select the semi-automatic update method. For drugs with a composite index less than or equal to the 33rd percentile, select the manual update method.

[0091] It's important to note that the ideal and negative ideal solutions are analyzed using the automatic update method as the benchmark. Therefore, the larger the resulting comprehensive index, the more suitable the automatic update method is. If the ideal and negative ideal solutions are analyzed using the manual update method as the benchmark, the larger the resulting comprehensive index, the more suitable the manual update method is. This is not explained in detail here.

[0092] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0093] The above embodiments may be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0094] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application of the technical solution and the invention constraints. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0095] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0096] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0097] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A medical instant retail insight system under the O2O model, characterized by ； It includes data acquisition module, data classification module, data matching module and feedback adjustment module, and the signal connections between the modules are as follows: The data collection module is used to collect inventory information update demand-related data and order impact measurement-related data, and pre-process the data; The data classification module is used to classify the inventory information update requirements through clustering algorithms and calculate the comprehensive indicators of order impact measurement; The data matching module is used to select the inventory information update method based on the drug inventory information update demand and drug complexity through the TOPSIS method; The feedback adjustment module is used to combine the inventory information update demand level and order impact measurement comprehensive indicators to dynamically adjust the inventory information update frequency through fuzzy rules.

2. The instant medical retail insight system under the O2O model according to claim 1 is characterized by: The inventory information update demand-related data collected by the data acquisition module include the supply arrival time, replenishment cycle, sales speed, return quantity and storage environment of the drug; the order impact measurement-related data include order quantity, order processing time and order variability; the preprocessing includes data standardization processing.

3. The instant medical retail insight system under the O2O model according to claim 2 is characterized by: The replenishment cycle is the time interval from the determination of the need for replenishment to the actual completion of replenishment, including order generation time, supplier confirmation time, supplier processing time, transportation time and warehousing time; the storage environment is divided into levels according to temperature parameters, including normal temperature storage, cool and dry environment, constant temperature storage, refrigerated storage and strict cold chain storage.

4. The instant medical retail insight system under the O2O model according to claim 1 is characterized in that ； The data classification module uses the K-means clustering algorithm to classify the inventory information update demand into three levels: high demand, medium demand, and low demand. The clustering process includes: The collected feature data is formed into a feature matrix and the feature values ​​are standardized; Set the number of clusters to 3 and iteratively update the cluster centers until convergence; The levels are defined based on the average values ​​of the characteristics of each cluster. The cluster with the shortest supply arrival time, the shortest replenishment cycle, the fastest sales speed, the least number of returns, and the most stable storage environment is classified as the high-demand level.

5. The instant medical retail insight system in an O2O mode according to claim 1 is characterized by: The process of calculating the comprehensive order impact metric by the data classification module includes: Calculate the order quantity impact coefficient, order processing time impact coefficient, and order variability impact coefficient expressed as volatility; By weighted summation formula ;in 、 、 are the weights of order quantity, order processing time, and order volatility, respectively; Qᵢ, Tᵢ, and Vᵢ are the corresponding impact coefficients.

6. The instant medical retail insight system in an O2O mode according to claim 1 is characterized by: The fuzzy rules of the feedback regulation module include: The input variables are inventory information update desirability, which is divided into High, Medium, and Low, and order impact measure, which is divided into Big, Medium, and Small; The output variable is the inventory information update frequency, which is specifically divided into Increase, Unchanged, and Decrease; The rules include: if the inventory information update demand is High and the order impact measure is Big, then the inventory information update frequency is Increase; if the inventory information update demand is Low and the order impact measure is Small, then the inventory information update frequency is Decrease.

7. The instant medical retail insight system in an O2O mode according to claim 1 is characterized by: The drug complexity is calculated by weighted summation of the storage environment level and the drug type level, using the formula: Where For the storage environment of drugs, For drug type, and They are weight coefficients of storage environment and drug type respectively, and the sum of the weight coefficients is 1; the drug type level is divided into 1-5 points according to medical use.

8. The instant medical retail insight system in an O2O mode according to claim 1 is characterized by: The TOPSIS method adopted by the data matching module includes: Determine the decision criteria as inventory information update necessity and drug complexity, and convert the inventory information update necessity level into a numerical value of 1-3; Normalize the decision criteria data, set the ideal solution as the maximum demand for inventory information update and the minimum drug complexity, and the negative ideal solution as the minimum demand for inventory information update and the maximum drug complexity; Calculate the Euclidean distance between each drug and the ideal solution and the negative ideal solution, and use the comprehensive index Where and are the distances between the i-th drug and the ideal solution and the negative ideal solution, respectively.

9. The instant medical retail insight system under the O2O model according to claim 8 is characterized by: The data matching module selects an inventory information update method based on the comprehensive index: automatic update is selected when the comprehensive index is ≥ the 66th percentile; semi-automatic update is selected when the comprehensive index is ≥ the 33rd percentile and < the 66th percentile; manual update is selected when the comprehensive index is ≤ the 33rd percentile.

10. The instant medical retail insight system in an O2O mode according to claim 1 is characterized by: The stated order volatility is calculated using volatility, including: Calculate the logarithmic rate of return of the number of orders in adjacent time periods ; Where yi is the number of orders in the i-th time period, and ln is the natural logarithm; ; where N is the total number of time periods, is the logarithmic rate of return, is the average of the logarithmic returns.

Images