Medicine supply chain data management system and method based on data analysis

Abstract

The invention discloses a medicine supply chain data management system and method based on data analysis, and relates to the technical field of data analysis. The system comprises a demand urgency evaluation module, an inventory authenticity verification module, a transportation path reliability evaluation module and an optimal allocation scheme screening module. According to the method, the demand urgency score is calculated by collecting the medical resource and material consumption data of the demand point; screening adaptive warehouses and verifying the authenticity of the inventory; evaluating the reliability of the transportation path; and a three-dimensional matrix is constructed, a comprehensive score is calculated through dynamic weighting, and an optimal'demand point-warehouse-path 'combination is screened. According to the invention, quantitative decision and global cooperation of emergency material allocation are realized, the response efficiency and accuracy are improved, and the method is suitable for material guarantee in public health emergencies.

Description

Technical Field

[0001] This invention relates to the field of data analysis technology, specifically to a pharmaceutical supply chain data management system and method based on data analysis. Background Technology

[0002] In pharmaceutical supply chain management, the efficient allocation of emergency supplies is a core element in ensuring public health security. Especially in various public health emergencies, the ability to quickly and accurately deliver medicines and medical supplies to the points of need directly affects the efficiency of emergency response and the level of public health protection.

[0003] Traditional emergency supplies allocation methods typically follow a fixed, forward-looking allocation logic: starting from the point of need, supplies are allocated from the nearest warehouse. While this method can meet the need for rapid response in some situations, it has significant limitations in complex and sudden public health events: First, the assessment of urgency lacks quantitative logic, relying heavily on subjective reports from the point of need or simple time-based sorting, failing to combine objective data such as medical resource saturation rates and supply consumption rates to differentiate the true level of urgency, easily leading to resource misallocation; Second, the lack of an inventory authenticity verification mechanism, relying solely on static warehouse reporting data, makes it difficult to identify issues such as outdated reserves or data entry delays, often resulting in allocation failures where "goods are on paper but not in reality"; Third, transportation feasibility assessments are detached from reality, often selecting warehouses based on the "nearest" principle without dynamically linking real-time traffic conditions and transportation resource availability, easily leading to supply delays due to route congestion and vehicle dispatch delays. Summary of the Invention

[0004] The purpose of this invention is to provide a pharmaceutical supply chain data management system and method based on data analysis to solve the problems mentioned in the background art.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: A data analysis-based approach to pharmaceutical supply chain data management includes the following: Step S100. Collect medical resource data and material consumption data for each demand point. The medical resource data includes the occupancy rate of key resources of medical institutions in the area where the demand point is located, and the material consumption data includes the consumption rate of emergency medical supplies within a specified time period. Based on the medical resource data and material consumption data of each demand point, obtain the corresponding demand urgency score. Step S200. Based on the material consumption data of each demand point, obtain the types of materials required by the demand point, and then select warehouses with corresponding material storage capacity; for each warehouse, retrieve the corresponding inventory data, analyze the inventory data to determine the authenticity of the warehouse inventory data, and generate an inventory authenticity assessment result. Step S300. Based on the inventory authenticity assessment results, candidate warehouses are selected and transportation routes from the candidate warehouses to the corresponding demand points are extracted; real-time traffic data and real-time trajectory data of transportation vehicles for each transportation route are obtained, a transportation time prediction model is constructed, and the reliability of each transportation route is evaluated based on the transportation time prediction model. Step S400. Construct a three-dimensional matrix based on the urgency score, inventory authenticity assessment results, and transportation route reliability assessment results; analyze the dynamic weights of each dimension of the three-dimensional matrix according to the characteristics of the emergency scenario and the attributes of the materials, and comprehensively score all combinations of demand points, candidate warehouses, and transportation routes through matrix weighted operations, and select the combination with the highest score as the optimal allocation plan.

[0006] Furthermore, step S100 includes: Collect medical resource data and material consumption data for each demand point. Based on the medical resource data, obtain the key resource occupancy rate Rm of medical institutions in the corresponding demand point area, and Rm=Us_m / Um, where Us_m represents the actual usage of the m-th key resource, Um represents the total allocation of the m-th key resource, and m represents the number of key resource types in medical institutions in the corresponding demand point area. Based on the material consumption data, calculate the consumption rate Cn of each type of emergency medical supply, and Cn=An / T, where An represents the total consumption of the n-th emergency medical supply in the selected time period, T represents the selected time period, and n represents the type of emergency medical supply. For each demand point, the critical resource occupancy rate and emergency medical supply consumption rate are standardized to obtain a set of standardized medical resource values ​​SR and a set of standardized supply consumption values ​​SC; where SR = {R1, R2, ..., Rm}, R1 represents the occupancy rate of the first type of critical resource, R2 represents the occupancy rate of the second type of critical resource, and so on, with Rm representing the occupancy rate of the m-th type of critical resource; SC = {C1, C2, ..., Cn}, similarly, C1 represents the consumption rate of the first type of emergency medical supply, C2 represents the consumption rate of the second type of emergency medical supply, and Cn represents the consumption rate of the n-th type of emergency medical supply; Based on the standardized value set SR for medical resources and the standardized value set SC for material consumption, the urgency score (Surgency) for each demand point is calculated, and Surgency = ∑ i∈[1,m] αi×Ri+∑ j∈[1,n] βj×Cj, where αi represents the weight of the i-th key resource, and ∑ i∈[1,m] αi=1; βj represents the weight of the j-th type of emergency medical supplies, and ∑ j∈[1,n] βj=1.

[0007] Furthermore, step S200 includes: For each demand point, the consumption rate Cn of the corresponding emergency medical supplies is obtained and compared with the preset consumption threshold C. When the consumption rate Cn of a certain emergency medical supply is ≥ C, this emergency medical supply is marked as a required supply. All required supplies are summarized to obtain the set Mt of required supply types for the corresponding demand point, and Mt = {mt1, mt2, ..., mtp}, where mt1 represents the first type of required supply, mt2 represents the second type of required supply, and so on, and mtp represents the p-th type of required supply. Based on the required material type set Mt, select warehouses with corresponding material storage capacity. Warehouses with corresponding material storage capacity must meet the following conditions: the warehouse inventory records contain all material types in the required material type set Mt; the inventory of all material types in the required material type set Mt declared by the warehouse is greater than the material application quantity of the corresponding demand point. For each warehouse with the corresponding material storage capacity, retrieve the relevant inventory data to extract the last update time T_update of the inventory data for each required material in the required material type set Mt, and then calculate the corresponding timeliness score S_timeliness, where S_timeliness=e -λΔT , where λ represents the time decay coefficient, ΔT represents the standardized value of the time interval, and (T_current-T_update) / Tmax, where T_current represents the current time, and Tmax represents the preset maximum effective time interval; obtain the most recent selected time period of the inbound and outbound records of each required material in the required material type set Mt, and calculate the theoretical inventory Qt based on the inbound and outbound records, and Qt=Q0+Q_in+Q_out; Obtain the required material inventory quantity Q1, calculate the inventory change consistency score S_consistency, and S_consistency=1-|(Q1-Qt) / Q1|; summarize the timeliness score S_timeliness and inventory change consistency score S_consistency for each required material in the required material type set Mt, calculate the overall warehouse inventory authenticity score S_inventory, and S_inventory=γ1·(1 / p)∑ k∈[1,p] Sk_timeliness+γ2·(1 / p)∑ k∈[1,p]Sk_consistency, where γ1 and γ2 represent the weight coefficients of the timeliness score S_timeliness and the inventory change consistency score S_consistency, respectively, and γ1+γ2=1; The inventory change consistency score S_consistency is compared with the authenticity threshold Tu. If S_consistency≥Tu, the inventory data of this warehouse is determined to be true and reliable, and an evaluation result of "verified" is generated; otherwise, an evaluation result of "to be verified" is generated.

[0008] Furthermore, step S300 includes: Based on the inventory authenticity assessment results, warehouses that have passed verification are selected as candidate warehouses, and a candidate warehouse set W is obtained for each demand point, where W = {w1, w2, ..., wh}, where w1 represents the first candidate warehouse, w2 represents the second candidate warehouse, and so on, with wh representing the h-th candidate warehouse. For each candidate warehouse we, all transportation routes from the candidate warehouse to the corresponding demand point are obtained, forming a route set Pe. Each route includes several road segments, and the travel distance of each road segment is equal. Real-time traffic data for each transportation route in the route set Pe is obtained, and the real-time traffic data is then analyzed. Extract the number of congested road segments N1 and the number of temporary traffic control signs N2 for each transportation route; collect the average driving speed Vavg of transportation vehicles on similar historical routes; for each road segment of each route, calculate the corresponding predicted travel time tf, and tf=L / {Vavg·[1+(g1·N1+g2·N2) / N]}, where L represents the travel distance of the road segment, g1 and g2 represent the influence coefficients of congested road segments and temporary traffic control signs, respectively, and g1+g2=1; N represents the number of road segments; for each route, summarize the predicted travel time of all road segments and sum them to obtain the predicted travel time T_total for the corresponding route; For each transport route in the route set Pe, a time fluctuation coefficient B is calculated based on the historical trajectory data of the transport vehicles, and B = T_σ / T_μ, where T_σ represents the standard deviation of the historical transport time of the transport vehicles on the corresponding transport route, and T_μ represents the average historical transport time of the transport vehicles on the corresponding transport route. Combining the predicted travel time T_total and the time fluctuation coefficient B for each transport route, a transport route reliability score S_reliability is calculated, and S_reliability = d1·(1-T_total / T1) + d2·(1-B), where d1 and d2 represent weighting coefficients, and d1+d2=1; T1 represents the maximum travel time in the historical records of the corresponding transport route.

[0009] Furthermore, step S400 includes: For each demand point, associate it with the corresponding candidate warehouse set W; for each candidate warehouse we in the candidate warehouse set W, associate it with the corresponding transportation route set Pe; thus obtaining the combination set G of all "demand point-candidate warehouse-transportation route"; based on each element in the combination set G, obtain the corresponding demand urgency score Surgency, warehouse overall inventory authenticity score S_inventory and transportation route reliability score S_reliabilit, thus constructing a three-dimensional matrix M; For a three-dimensional matrix M, dynamic weights w_U, w_I, and w_R are obtained for each dimension based on the characteristics of the emergency scenario and the attributes of the materials, and w_U+w_I+w_R=1. For each three-dimensional matrix M, the corresponding comprehensive score S_total is calculated, and S_total=w_U·Surgency+w_I·S_inventory+w_R·S_reliabilit. For each demand point, all combinations are summarized, and the combination with the largest comprehensive score S_total is selected as the optimal candidate solution for this demand point. If multiple combinations have the same comprehensive score S_total, they are further filtered according to the following priority: the combination with the shortest predicted travel time T_total is selected first; if the predicted travel time is still the same, the combination with the highest inventory authenticity score is selected. The optimal candidate solutions for all demand points are summarized, and it is verified whether the inventory of the candidate warehouses meets the total application amount of all demand points. If there is an inventory conflict, for the demand points involved in the conflict, the second highest-scoring optimal candidate solution in the corresponding combination is selected for re-verification until the inventory of all warehouses meets the demand. The set of solutions without conflict after verification is the final optimal allocation solution.

[0010] A data analysis-based pharmaceutical supply chain data management system includes: a demand urgency assessment module, an inventory authenticity verification module, a transportation route reliability assessment module, and an optimal allocation scheme screening module. The urgency assessment module collects medical resource data and material consumption data for each demand point. The medical resource data includes the occupancy rate of key resources of medical institutions in the area where the demand point is located, and the material consumption data includes the consumption rate of emergency medical supplies within a specified time period. Based on the medical resource data and material consumption data of each demand point, a corresponding demand urgency score is obtained. The inventory authenticity verification module uses material consumption data from each demand point to determine the types of materials required by the demand point, thereby filtering out warehouses with the corresponding material storage capacity; for each warehouse, it retrieves the corresponding inventory data, analyzes the inventory data to determine the authenticity of the warehouse inventory data, and generates an inventory authenticity assessment result. The transportation route reliability assessment module selects candidate warehouses based on the inventory authenticity assessment results and extracts the transportation routes from the candidate warehouses to the corresponding demand points; it acquires real-time traffic data and real-time trajectory data of transportation vehicles for each transportation route, constructs a transportation time prediction model, and evaluates the reliability of each transportation route based on the transportation time prediction model. The optimal allocation scheme selection module constructs a three-dimensional matrix based on the urgency score of demand, the inventory authenticity assessment results, and the reliability assessment results of transportation routes. According to the characteristics of the emergency scenario and the attributes of materials, it analyzes the dynamic weights of each dimension of the three-dimensional matrix, and performs a comprehensive score on all combinations of demand points, candidate warehouses, and transportation routes through matrix weighted operations, and selects the combination with the highest score as the optimal allocation scheme.

[0011] The urgency assessment module includes a data collection unit and an urgency scoring unit; The data acquisition unit collects medical resource data and material consumption data from each demand point. The medical resource data includes the occupancy rate of key resources of medical institutions in the area where the demand point is located, and the material consumption data includes the consumption rate of emergency medical supplies within a specified time period. The urgency scoring unit obtains the corresponding urgency score based on the medical resource data and material consumption data of each demand point.

[0012] The inventory authenticity verification module includes a required material identification unit, a warehouse screening unit, and an inventory verification unit; The required materials identification unit compares the material consumption rate at the demand point with a preset threshold to identify the urgently needed material types, forming a set of required material types. The warehouse screening unit, based on the required material types set, selects warehouses whose inventory records contain all required materials and whose inventory levels meet the demand point's application quantity as candidate warehouses. The inventory verification unit evaluates the candidate warehouses' inventory data from two dimensions: the timeliness of inventory data updates and the consistency of inventory changes, generating an inventory authenticity score and evaluation result.

[0013] The transportation route reliability assessment module includes a route and traffic data acquisition unit, a travel time prediction unit, and a route reliability scoring unit. The route and traffic data acquisition unit extracts all transportation routes from candidate warehouses to demand points, and collects real-time traffic data and historical trajectory data of transportation vehicles for each route; the travel time prediction unit combines real-time traffic conditions and historical speed characteristics to predict the segment travel time and total travel time for each route; the route reliability scoring unit calculates the reliability score of the transportation route based on the fluctuation of predicted travel time and historical transportation time.

[0014] The optimal allocation scheme selection module includes a three-dimensional matrix construction unit, a comprehensive scoring calculation unit, and a scheme selection and verification unit. The three-dimensional matrix construction unit associates the urgency score of demand, the inventory authenticity assessment result, and the transportation route reliability score to construct a three-dimensional matrix of "demand-inventory-transportation" and integrates all allocation combinations. The comprehensive score calculation unit determines the dynamic weight of each dimension of the three-dimensional matrix based on the characteristics of the emergency scenario and the attributes of the materials, and calculates the comprehensive score of each allocation combination through weighted calculation. The scheme screening and verification unit selects the combination with the highest comprehensive score as the optimal candidate scheme for each demand point. After summarizing all candidate schemes, it verifies whether the warehouse inventory meets the total demand. If there is a conflict, it is dynamically adjusted, and finally outputs the optimal allocation scheme.

[0015] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention quantifies the urgency of each demand point by combining the occupancy rate of medical resources and the consumption rate of supplies, based on data standardization. This method abandons the traditional reliance on subjective reporting and time-based sorting, and can scientifically assess the urgency based on actual medical resource saturation rates, supply consumption rates, and other data, thereby reducing the risk of resource misallocation. This invention constructs a strict inventory authenticity assessment mechanism by collecting inventory data in real time and combining it with assessment dimensions such as inventory change consistency and timeliness. This mechanism can not only identify problems of false or delayed inventory, but also reflect the dynamic changes in inventory in real time, greatly improving the accuracy and reliability of inventory allocation. This invention establishes a transportation time prediction model by acquiring traffic data and transport vehicle trajectories in real time, dynamically assessing the reliability of each transportation route, and adjusting transportation routes in real time, avoiding material delays caused by traffic congestion or vehicle dispatch delays, and improving emergency response efficiency. By establishing a three-dimensional matrix, multiple dimensions such as demand urgency, inventory authenticity, and transportation route reliability are comprehensively evaluated with weighted calculations. This ensures multi-dimensional optimized allocation decisions in complex emergency scenarios. Compared with the traditional single-factor consideration model, this invention can more comprehensively balance various factors to obtain the optimal allocation plan, improving the accuracy and efficiency of allocation. Attached Figure Description

[0016] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a schematic diagram of a pharmaceutical supply chain data management method based on data analysis according to the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Please see Figure 1 The present invention provides the following technical solution: A data analysis-based approach to pharmaceutical supply chain data management includes the following: Step S100. Collect medical resource data and material consumption data for each demand point. The medical resource data includes the occupancy rate of key resources of medical institutions in the area where the demand point is located, and the material consumption data includes the consumption rate of emergency medical supplies within a specified time period. Based on the medical resource data and material consumption data of each demand point, obtain the corresponding demand urgency score. Step S200. Based on the material consumption data of each demand point, obtain the types of materials required by the demand point, and then select warehouses with corresponding material storage capacity; for each warehouse, retrieve the corresponding inventory data, analyze the inventory data to determine the authenticity of the warehouse inventory data, and generate an inventory authenticity assessment result. Step S300. Based on the inventory authenticity assessment results, candidate warehouses are selected and transportation routes from the candidate warehouses to the corresponding demand points are extracted; real-time traffic data and real-time trajectory data of transportation vehicles for each transportation route are obtained, a transportation time prediction model is constructed, and the reliability of each transportation route is evaluated based on the transportation time prediction model. Step S400. Construct a three-dimensional matrix based on the urgency score, inventory authenticity assessment results, and transportation route reliability assessment results; analyze the dynamic weights of each dimension of the three-dimensional matrix according to the characteristics of the emergency scenario and the attributes of the materials, and comprehensively score all combinations of demand points, candidate warehouses, and transportation routes through matrix weighted operations, and select the combination with the highest score as the optimal allocation plan.

[0019] Step S100 includes: Collect medical resource data and material consumption data for each demand point. Based on the medical resource data, obtain the key resource occupancy rate Rm of medical institutions in the corresponding demand point area, and Rm=Us_m / Um, where Us_m represents the actual usage of the m-th key resource, Um represents the total allocation of the m-th key resource, and m represents the number of key resource types in medical institutions in the corresponding demand point area. Based on the material consumption data, calculate the consumption rate Cn of each type of emergency medical supply, and Cn=An / T, where An represents the total consumption of the n-th emergency medical supply in the selected time period, T represents the selected time period, and n represents the type of emergency medical supply. For each demand point, the critical resource occupancy rate and emergency medical supply consumption rate are standardized to obtain a set of standardized medical resource values ​​SR and a set of standardized supply consumption values ​​SC; where SR = {R1, R2, ..., Rm}, R1 represents the occupancy rate of the first type of critical resource, R2 represents the occupancy rate of the second type of critical resource, and so on, with Rm representing the occupancy rate of the m-th type of critical resource; SC = {C1, C2, ..., Cn}, similarly, C1 represents the consumption rate of the first type of emergency medical supply, C2 represents the consumption rate of the second type of emergency medical supply, and Cn represents the consumption rate of the n-th type of emergency medical supply; Based on the standardized value set SR for medical resources and the standardized value set SC for material consumption, the urgency score (Surgency) for each demand point is calculated, and Surgency = ∑ i∈[1,m] αi×Ri+∑ j∈[1,n] βj×Cj, where αi represents the weight of the i-th key resource, and ∑ i∈[1,m] αi=1; βj represents the weight of the j-th type of emergency medical supplies, and ∑ j∈[1,n] βj=1.

[0020] In this embodiment, it is assumed that the key resource occupancy rate of medical institutions in the area where the data collection demand point is located includes, but is not limited to: Intensive Care Unit (ICU) bed occupancy rate R1 = Number of ICU beds in use / Total number of ICU beds; Ventilator utilization rate R2 = Number of ventilators in use / Total number of ventilators; Medical staff workload coefficient R3 = Current number of on-duty medical staff / Standard number of medical staff; Similarly, assuming the consumption rate of emergency medical supplies in the areas where each demand point is located is collected, including but not limited to: Drug consumption rate C1: The ratio of the total amount of a drug consumed (in doses) within a selected time period to the duration of that time period (in hours); for example: C1 = total consumption (in doses) / time period (in hours). Consumption rate of ventilator-related consumables C2: The ratio of the total consumption (in units: number) of ventilator-related consumables (such as breathing tubes, filters, etc.) within a selected time period to the duration of that time period (in units: hours); For example: C2 = total consumption (in units: number) / time period (in units: hours); For each demand point, the key resource utilization rates (e.g., R1, R2, R3) and material consumption rates (e.g., C1, C2) are standardized. Common standardization methods include min-max standardization or z-score standardization, aiming to give all data the same dimensions. The resulting standardized datasets are SR and SC. A weighted summation method is used to calculate the demand urgency score for each demand point.

[0021] Step S200 includes: For each demand point, the consumption rate Cn of the corresponding emergency medical supplies is obtained and compared with the preset consumption threshold C. When the consumption rate Cn of a certain emergency medical supply is ≥ C, this emergency medical supply is marked as a required supply. All required supplies are summarized to obtain the set Mt of required supply types for the corresponding demand point, and Mt = {mt1, mt2, ..., mtp}, where mt1 represents the first type of required supply, mt2 represents the second type of required supply, and so on, and mtp represents the p-th type of required supply. Based on the required material type set Mt, select warehouses with corresponding material storage capacity. Warehouses with corresponding material storage capacity must meet the following conditions: the warehouse inventory records contain all material types in the required material type set Mt; the inventory of all material types in the required material type set Mt declared by the warehouse is greater than the material application quantity of the corresponding demand point. For each warehouse with the corresponding material storage capacity, retrieve the relevant inventory data to extract the last update time T_update of the inventory data for each required material in the required material type set Mt, and then calculate the corresponding timeliness score S_timeliness, where S_timeliness=e -λΔT , where λ represents the time decay coefficient, ΔT represents the standardized value of the time interval, and (T_current-T_update) / Tmax, where T_current represents the current time, and Tmax represents the preset maximum effective time interval; obtain the most recent selected time period of the inbound and outbound records of each required material in the required material type set Mt, and calculate the theoretical inventory Qt based on the inbound and outbound records, and Qt=Q0+Q_in+Q_out; Obtain the required material inventory quantity Q1, calculate the inventory change consistency score S_consistency, and S_consistency=1-|(Q1-Qt) / Q1|; summarize the timeliness score S_timeliness and inventory change consistency score S_consistency for each required material in the required material type set Mt, calculate the overall warehouse inventory authenticity score S_inventory, and S_inventory=γ1·(1 / p)∑ k∈[1,p] Sk_timeliness+γ2·(1 / p)∑ k∈[1,p] Sk_consistency, where γ1 and γ2 represent the weight coefficients of the timeliness score S_timeliness and the inventory change consistency score S_consistency, respectively, and γ1+γ2=1; The inventory change consistency score S_consistency is compared with the authenticity threshold Tu. If S_consistency≥Tu, the inventory data of this warehouse is determined to be true and reliable, and an evaluation result of "verified" is generated; otherwise, an evaluation result of "to be verified" is generated.

[0022] Step S300 includes: Based on the inventory authenticity assessment results, warehouses that have passed verification are selected as candidate warehouses, and a candidate warehouse set W is obtained for each demand point, where W = {w1, w2, ..., wh}, where w1 represents the first candidate warehouse, w2 represents the second candidate warehouse, and so on, with wh representing the h-th candidate warehouse. For each candidate warehouse we, all transportation routes from the candidate warehouse to the corresponding demand point are obtained, forming a route set Pe. Each route includes several road segments, and the travel distance of each road segment is equal. Real-time traffic data for each transportation route in the route set Pe is obtained, and the real-time traffic data is then analyzed. Extract the number of congested road segments N1 and the number of temporary traffic control signs N2 for each transportation route; collect the average driving speed Vavg of transportation vehicles on similar historical routes; for each road segment of each route, calculate the corresponding predicted travel time tf, and tf=L / {Vavg·[1+(g1·N1+g2·N2) / N]}, where L represents the travel distance of the road segment, g1 and g2 represent the influence coefficients of congested road segments and temporary traffic control signs, respectively, and g1+g2=1; N represents the number of road segments; for each route, summarize the predicted travel time of all road segments and sum them to obtain the predicted travel time T_total for the corresponding route; For each transport route in the route set Pe, a time fluctuation coefficient B is calculated based on the historical trajectory data of the transport vehicles, and B = T_σ / T_μ, where T_σ represents the standard deviation of the historical transport time of the transport vehicles on the corresponding transport route, and T_μ represents the average historical transport time of the transport vehicles on the corresponding transport route. Combining the predicted travel time T_total and the time fluctuation coefficient B for each transport route, a transport route reliability score S_reliability is calculated, and S_reliability = d1·(1-T_total / T1) + d2·(1-B), where d1 and d2 represent weighting coefficients, and d1+d2=1; T1 represents the maximum travel time in the historical records of the corresponding transport route.

[0023] Step S400 includes: For each demand point, associate it with the corresponding candidate warehouse set W; for each candidate warehouse we in the candidate warehouse set W, associate it with the corresponding transportation route set Pe; thus obtaining the combination set G of all "demand point-candidate warehouse-transportation route"; based on each element in the combination set G, obtain the corresponding demand urgency score Surgency, warehouse overall inventory authenticity score S_inventory and transportation route reliability score S_reliabilit, thus constructing a three-dimensional matrix M; For a three-dimensional matrix M, dynamic weights w_U, w_I, and w_R are obtained for each dimension based on the characteristics of the emergency scenario and the attributes of the materials, and w_U+w_I+w_R=1. For each three-dimensional matrix M, the corresponding comprehensive score S_total is calculated, and S_total=w_U·Surgency+w_I·S_inventory+w_R·S_reliabilit. For each demand point, all combinations are summarized, and the combination with the largest comprehensive score S_total is selected as the optimal candidate solution for this demand point. If multiple combinations have the same comprehensive score S_total, they are further filtered according to the following priority: the combination with the shortest predicted travel time T_total is selected first; if the predicted travel time is still the same, the combination with the highest inventory authenticity score is selected. The optimal candidate solutions for all demand points are summarized, and it is verified whether the inventory of the candidate warehouses meets the total application amount of all demand points. If there is an inventory conflict, for the demand points involved in the conflict, the second highest-scoring optimal candidate solution in the corresponding combination is selected for re-verification until the inventory of all warehouses meets the demand. The set of solutions without conflict after verification is the final optimal allocation solution.

[0024] In this embodiment, for the three-dimensional matrix M, based on the characteristics of the emergency scenario and the attributes of the materials, the dynamic weights w_U, w_I, and w_R of each dimension are obtained, and w_U+w_I+w_R=1; the specific analysis process is as follows: Set an initial weight vector (w_U0, w_I0, w_R0) (e.g., w_U0=0.4, w_I0=0.3, w_R0=0.3), corresponding to the dimensions of demand urgency, inventory authenticity, and transportation reliability, respectively; Introduce a scenario urgency coefficient x1 (assuming a value range of [1, 1.5], determined by relevant personnel based on actual circumstances according to event level classification, such as 1.5 for particularly serious events), and adjust the urgency weight of the demand: w_U = w_U0·x1 / (x1 + 0.5); where 0.5 represents the standardized adjustment parameter; Material attribute correction: Introduce material sensitivity coefficient x2 (assuming a value range of [1, 1.5], which is divided according to the characteristics of the material and obtained by relevant personnel based on the actual situation, such as 1.5 for cold chain materials), and correct the inventory authenticity weight: w_I=w_I0·x2 / (x2+0.5); Transportation reliability weight allocation: The remaining weights are allocated to the transportation reliability dimension: w_R=1-w_U-w_I.

[0025] A data analysis-based pharmaceutical supply chain data management system includes: a demand urgency assessment module, an inventory authenticity verification module, a transportation route reliability assessment module, and an optimal allocation scheme screening module. The urgency assessment module collects medical resource data and material consumption data for each demand point. The medical resource data includes the occupancy rate of key resources of medical institutions in the area where the demand point is located, and the material consumption data includes the consumption rate of emergency medical supplies within a specified time period. Based on the medical resource data and material consumption data of each demand point, a corresponding demand urgency score is obtained. The inventory authenticity verification module uses material consumption data from each demand point to determine the types of materials required by the demand point, thereby filtering out warehouses with the corresponding material storage capacity; for each warehouse, it retrieves the corresponding inventory data, analyzes the inventory data to determine the authenticity of the warehouse inventory data, and generates an inventory authenticity assessment result. The transportation route reliability assessment module selects candidate warehouses based on the inventory authenticity assessment results and extracts the transportation routes from the candidate warehouses to the corresponding demand points; it acquires real-time traffic data and real-time trajectory data of transportation vehicles for each transportation route, constructs a transportation time prediction model, and evaluates the reliability of each transportation route based on the transportation time prediction model. The optimal allocation scheme selection module constructs a three-dimensional matrix based on the urgency score of demand, the inventory authenticity assessment results, and the reliability assessment results of transportation routes. According to the characteristics of the emergency scenario and the attributes of materials, it analyzes the dynamic weights of each dimension of the three-dimensional matrix, and performs a comprehensive score on all combinations of demand points, candidate warehouses, and transportation routes through matrix weighted operations, and selects the combination with the highest score as the optimal allocation scheme.

[0026] The urgency assessment module includes a data collection unit and an urgency scoring unit; The data acquisition unit collects medical resource data and material consumption data from each demand point. The medical resource data includes the occupancy rate of key resources of medical institutions in the area where the demand point is located, and the material consumption data includes the consumption rate of emergency medical supplies within a specified time period. The urgency scoring unit obtains the corresponding urgency score based on the medical resource data and material consumption data of each demand point.

[0027] The inventory authenticity verification module includes a required material identification unit, a warehouse screening unit, and an inventory verification unit; The required materials identification unit compares the material consumption rate at the demand point with a preset threshold to identify the urgently needed material types, forming a set of required material types. The warehouse screening unit, based on the required material types set, selects warehouses whose inventory records contain all required materials and whose inventory levels meet the demand point's application quantity as candidate warehouses. The inventory verification unit evaluates the candidate warehouses' inventory data from two dimensions: the timeliness of inventory data updates and the consistency of inventory changes, generating an inventory authenticity score and evaluation result.

[0028] The transportation route reliability assessment module includes a route and traffic data acquisition unit, a travel time prediction unit, and a route reliability scoring unit. The route and traffic data acquisition unit extracts all transportation routes from candidate warehouses to demand points, and collects real-time traffic data and historical trajectory data of transportation vehicles for each route; the travel time prediction unit combines real-time traffic conditions and historical speed characteristics to predict the segment travel time and total travel time for each route; the route reliability scoring unit calculates the reliability score of the transportation route based on the fluctuation of predicted travel time and historical transportation time.

[0029] The optimal allocation scheme selection module includes a three-dimensional matrix construction unit, a comprehensive scoring calculation unit, and a scheme selection and verification unit. The three-dimensional matrix construction unit associates the urgency score of demand, the inventory authenticity assessment result, and the transportation route reliability score to construct a three-dimensional matrix of "demand-inventory-transportation" and integrates all allocation combinations. The comprehensive score calculation unit determines the dynamic weight of each dimension of the three-dimensional matrix based on the characteristics of the emergency scenario and the attributes of the materials, and calculates the comprehensive score of each allocation combination through weighted calculation. The scheme screening and verification unit selects the combination with the highest comprehensive score as the optimal candidate scheme for each demand point. After summarizing all candidate schemes, it verifies whether the warehouse inventory meets the total demand. If there is a conflict, it is dynamically adjusted, and finally outputs the optimal allocation scheme.

[0030] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0031] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A data analysis-based pharmaceutical supply chain data management method, characterized in that: The method includes the following steps: Step S100. Collect medical resource data and material consumption data for each demand point. The medical resource data includes the occupancy rate of key resources of medical institutions in the area where the demand point is located, and the material consumption data includes the consumption rate of emergency medical supplies within a specified time period. Based on the medical resource data and material consumption data of each demand point, obtain the corresponding demand urgency score. Step S200. Based on the material consumption data of each demand point, obtain the types of materials required by the demand point, and then select warehouses with corresponding material storage capacity; for each warehouse, retrieve the corresponding inventory data, analyze the inventory data to determine the authenticity of the warehouse inventory data, and generate an inventory authenticity assessment result. Step S300. Based on the inventory authenticity assessment results, candidate warehouses are selected and transportation routes from the candidate warehouses to the corresponding demand points are extracted; real-time traffic data and real-time trajectory data of transportation vehicles for each transportation route are obtained, a transportation time prediction model is constructed, and the reliability of each transportation route is evaluated based on the transportation time prediction model. Step S400. Construct a three-dimensional matrix based on the urgency score, inventory authenticity assessment results, and transportation route reliability assessment results; analyze the dynamic weights of each dimension of the three-dimensional matrix according to the characteristics of the emergency scenario and the attributes of the materials, and comprehensively score all combinations of demand points, candidate warehouses, and transportation routes through matrix weighted operations, and select the combination with the highest score as the optimal allocation plan.

2. The pharmaceutical supply chain data management method based on data analysis according to claim 1, characterized in that: Step S100 includes: Collect medical resource data and material consumption data for each demand point. Based on the medical resource data, obtain the key resource occupancy rate Rm of medical institutions in the corresponding demand point area, and Rm=Us_m / Um, where Us_m represents the actual usage of the m-th key resource, Um represents the total allocation of the m-th key resource, and m represents the number of key resource types in medical institutions in the corresponding demand point area. Based on the material consumption data, calculate the consumption rate Cn of each type of emergency medical supply, and Cn=An / T, where An represents the total consumption of the n-th emergency medical supply in the selected time period, T represents the selected time period, and n represents the type of emergency medical supply. For each demand point, the critical resource occupancy rate and emergency medical supply consumption rate are standardized to obtain a set of standardized medical resource values ​​SR and a set of standardized supply consumption values ​​SC; where SR = {R1, R2, ..., Rm}, R1 represents the occupancy rate of the first type of critical resource, R2 represents the occupancy rate of the second type of critical resource, and so on, with Rm representing the occupancy rate of the m-th type of critical resource; SC = {C1, C2, ..., Cn}, similarly, C1 represents the consumption rate of the first type of emergency medical supply, C2 represents the consumption rate of the second type of emergency medical supply, and Cn represents the consumption rate of the n-th type of emergency medical supply; Based on the standardized value set SR for medical resources and the standardized value set SC for material consumption, the urgency score (Surgency) for each demand point is calculated, and Surgency = ∑ i∈[1,m] αi×Ri+∑ j∈[1,n] βj×Cj, where αi represents the weight of the i-th key resource, and ∑ i∈[1,m] αi=1; βj represents the weight of the j-th type of emergency medical supplies, and ∑ j∈[1,n] βj=1.

3. The pharmaceutical supply chain data management method based on data analysis according to claim 2, characterized in that: Step S200 includes: For each demand point, the consumption rate Cn of the corresponding emergency medical supplies is obtained and compared with the preset consumption threshold C. When the consumption rate Cn of a certain emergency medical supply is ≥ C, this emergency medical supply is marked as a required supply. All required supplies are summarized to obtain the set Mt of required supply types for the corresponding demand point, and Mt = {mt1, mt2, ..., mtp}, where mt1 represents the first type of required supply, mt2 represents the second type of required supply, and so on, and mtp represents the p-th type of required supply. Based on the required material type set Mt, select warehouses with corresponding material storage capacity. Warehouses with corresponding material storage capacity must meet the following conditions: the warehouse inventory records contain all material types in the required material type set Mt; the inventory of all material types in the required material type set Mt declared by the warehouse is greater than the material application quantity of the corresponding demand point. For each warehouse with the corresponding material storage capacity, retrieve the relevant inventory data to extract the last update time T_update of the inventory data for each required material in the required material type set Mt, and then calculate the corresponding timeliness score S_timeliness, where S_timeliness=e -λΔT , where λ represents the time decay coefficient, ΔT represents the standardized value of the time interval, and (T_current-T_update) / Tmax, where T_current represents the current time, and Tmax represents the preset maximum effective time interval; obtain the most recent selected time period of the inbound and outbound records of each required material in the required material type set Mt, and calculate the theoretical inventory Qt based on the inbound and outbound records, and Qt=Q0+Q_in+Q_out; Obtain the required material inventory quantity Q1, calculate the inventory change consistency score S_consistency, and S_consistency=1-|(Q1-Qt) / Q1|; summarize the timeliness score S_timeliness and inventory change consistency score S_consistency for each required material in the required material type set Mt, calculate the overall warehouse inventory authenticity score S_inventory, and S_inventory=γ1·(1 / p)∑ k∈[1,p] Sk_timeliness+γ2·(1 / p)∑ k∈[1,p] Sk_consistency, where γ1 and γ2 represent the weight coefficients of the timeliness score S_timeliness and the inventory change consistency score S_consistency, respectively, and γ1+γ2=1; The inventory change consistency score S_consistency is compared with the authenticity threshold Tu. If S_consistency≥Tu, the inventory data of this warehouse is determined to be true and reliable, and an evaluation result of "passed verification" is generated; otherwise, an evaluation result of "to be verified" is generated.

4. The pharmaceutical supply chain data management method based on data analysis according to claim 3, characterized in that: Step S300 includes: Based on the inventory authenticity assessment results, warehouses that have passed verification are selected as candidate warehouses, and a candidate warehouse set W is obtained for each demand point, where W = {w1, w2, ..., wh}, where w1 represents the first candidate warehouse, w2 represents the second candidate warehouse, and so on, with wh representing the h-th candidate warehouse. For each candidate warehouse we, all transportation routes from the candidate warehouse to the corresponding demand point are obtained, forming a route set Pe. Each route includes several road segments, and the travel distance of each road segment is equal. Real-time traffic data for each transportation route in the route set Pe is obtained, and the real-time traffic data is then analyzed. Extract the number of congested road segments N1 and the number of temporary traffic control signs N2 for each transportation route; collect the average driving speed Vavg of transportation vehicles on similar historical routes; for each road segment of each route, calculate the corresponding predicted travel time tf, and tf=L / {Vavg·[1+(g1·N1+g2·N2) / N]}, where L represents the travel distance of the road segment, g1 and g2 represent the influence coefficients of congested road segments and temporary traffic control signs, respectively, and g1+g2=1; N represents the number of road segments; for each route, summarize the predicted travel time of all road segments and sum them to obtain the predicted travel time T_total for the corresponding route; For each transport route in the route set Pe, a time fluctuation coefficient B is calculated based on the historical trajectory data of the transport vehicles, and B = T_σ / T_μ, where T_σ represents the standard deviation of the historical transport time of the transport vehicles on the corresponding transport route, and T_μ represents the average historical transport time of the transport vehicles on the corresponding transport route. Combining the predicted travel time T_total and the time fluctuation coefficient B for each transport route, a transport route reliability score S_reliability is calculated, and S_reliability = d1·(1-T_total / T1) + d2·(1-B), where d1 and d2 represent weighting coefficients, and d1+d2=1; T1 represents the maximum travel time in the historical records of the corresponding transport route.

5. The pharmaceutical supply chain data management method based on data analysis according to claim 4, characterized in that: Step S400 includes: For each demand point, associate it with the corresponding set of candidate warehouses W; for each candidate warehouse we in the set of candidate warehouses W, associate it with the corresponding set of transportation routes Pe; thus obtaining the combination set G of all "demand point-candidate warehouse-transportation route"; based on each element in the combination set G, obtain the corresponding demand urgency score Surgency, warehouse overall inventory authenticity score S_inventory and transportation route reliability score S_reliabilit, thus constructing a three-dimensional matrix M; For a three-dimensional matrix M, dynamic weights w_U, w_I, and w_R are obtained for each dimension based on the characteristics of the emergency scenario and the attributes of the materials, and w_U+w_I+w_R=1. For each three-dimensional matrix M, the corresponding comprehensive score S_total is calculated, and S_total=w_U·Surgency+w_I·S_inventory+w_R·S_reliabilit. For each demand point, all combinations are summarized, and the combination with the largest comprehensive score S_total is selected as the optimal candidate solution for this demand point. If multiple combinations have the same comprehensive score S_total, they are further filtered according to the following priority: the combination with the shortest predicted travel time T_total is selected first; if the predicted travel time is still the same, the combination with the highest inventory authenticity score is selected. The optimal candidate solutions for all demand points are summarized, and it is verified whether the inventory of the candidate warehouses meets the total application amount of all demand points. If there is an inventory conflict, for the demand points involved in the conflict, the second highest-scoring optimal candidate solution in the corresponding combination is selected for re-verification until the inventory of all warehouses meets the demand. The set of solutions without conflict after verification is the final optimal allocation solution.

6. A pharmaceutical supply chain data management system based on data analysis, applied to the pharmaceutical supply chain data management method based on data analysis as described in any one of claims 1-5, characterized in that: The system includes: a demand urgency assessment module, an inventory authenticity verification module, a transportation route reliability assessment module, and an optimal allocation scheme screening module. The urgency assessment module collects medical resource data and material consumption data for each demand point. The medical resource data includes the occupancy rate of key resources of medical institutions in the area where the demand point is located, and the material consumption data includes the consumption rate of emergency medical supplies within a specified time period. Based on the medical resource data and material consumption data of each demand point, a corresponding urgency score is obtained. The inventory authenticity verification module obtains the types of materials required by each demand point based on the material consumption data of each demand point, thereby screening out warehouses with corresponding material storage capabilities; for each warehouse, it retrieves the corresponding inventory data, analyzes the inventory data to determine the authenticity of the warehouse inventory data, and generates an inventory authenticity assessment result. The transportation route reliability assessment module selects candidate warehouses based on the inventory authenticity assessment results and extracts the transportation routes from the candidate warehouses to the corresponding demand points; it acquires real-time traffic data and real-time trajectory data of transportation vehicles for each transportation route, constructs a transportation time prediction model, and evaluates the reliability of each transportation route based on the transportation time prediction model. The optimal allocation scheme selection module constructs a three-dimensional matrix based on the urgency score of demand, the inventory authenticity assessment result, and the reliability assessment result of the transportation route. According to the characteristics of the emergency scenario and the attributes of the materials, it analyzes the dynamic weight of each dimension of the three-dimensional matrix, and performs a comprehensive score on all combinations of demand points, candidate warehouses and transportation routes through matrix weighted operations, and selects the combination with the highest score as the optimal allocation scheme.

7. A pharmaceutical supply chain data management system based on data analysis according to claim 6, characterized in that: The urgency assessment module includes a data acquisition unit and an urgency scoring unit; The data acquisition unit collects medical resource data and material consumption data for each demand point. The medical resource data includes the occupancy rate of key resources of medical institutions in the area where the demand point is located, and the material consumption data includes the consumption rate of emergency medical supplies within a specified time period. The urgency scoring unit obtains the corresponding urgency score based on the medical resource data and material consumption data of each demand point.

8. A pharmaceutical supply chain data management system based on data analysis according to claim 6, characterized in that: The inventory authenticity verification module includes a required material identification unit, a warehouse screening unit, and an inventory verification unit. The required material identification unit identifies urgently needed material types by comparing the material consumption rate of the demand point with a preset threshold, forming a set of required material types; the warehouse screening unit selects warehouses whose inventory records contain all required materials and whose inventory quantity meets the demand point's application quantity, as candidate warehouses, based on the set of required material types. The inventory verification unit evaluates the inventory data of candidate warehouses from two dimensions: the timeliness of inventory data updates and the consistency of inventory changes, and generates an inventory authenticity score and evaluation results.

9. A pharmaceutical supply chain data management system based on data analysis according to claim 6, characterized in that: The transportation route reliability assessment module includes a route and traffic data acquisition unit, a travel time prediction unit, and a route reliability scoring unit. The route and traffic data acquisition unit extracts all transportation routes from candidate warehouses to demand points, and collects real-time traffic data and historical trajectory data of transportation vehicles for each route; the travel time prediction unit combines real-time traffic conditions and historical speed characteristics to predict the segment travel time and total travel time for each route; the route reliability scoring unit calculates the reliability score of the transportation route based on the fluctuations in predicted travel time and historical transportation time.

10. A pharmaceutical supply chain data management system based on data analysis according to claim 6, characterized in that: The optimal allocation scheme screening module includes a three-dimensional matrix construction unit, a comprehensive scoring calculation unit, and a scheme screening and verification unit. The three-dimensional matrix construction unit associates the urgency score of demand, the inventory authenticity assessment result, and the transportation route reliability score to construct a "demand-inventory-transportation" three-dimensional matrix and integrates all allocation combinations. The comprehensive score calculation unit determines the dynamic weight of each dimension of the three-dimensional matrix based on the characteristics of the emergency scenario and the attributes of the materials, and calculates the comprehensive score of each allocation combination through weighted calculation. The scheme screening and verification unit selects the combination with the highest comprehensive score as the optimal candidate scheme for each demand point. After summarizing all candidate schemes, it verifies whether the warehouse inventory meets the total demand. If there is a conflict, it dynamically adjusts the inventory and finally outputs the optimal allocation scheme.

Images