Medical logistics dynamic demand response scheduling method

Abstract

The invention discloses a medical logistics dynamic demand response scheduling method, which belongs to the field of logistics optimization, and comprises the following steps: carrying out matching analysis according to a medical logistics target and real-time sensor data to obtain a response synchronous evaluation result; positioning a demand deviation, wherein the demand deviation has an asynchronous timestamp; based on the asynchronous timestamp, time window analysis is carried out according to the demand deviation, a deviation time window is determined, logistics scheduling compensation is carried out, and scheduling compensation characteristics are obtained; scheduling response variables are obtained, wherein the scheduling response variables comprise path adjustment parameters and vehicle scheduling parameters; and with demand deviation minimization as a target, matching evaluation is carried out by using the scheduling compensation characteristics and the scheduling response variables, an optimal scheduling strategy is searched, the optimal scheduling strategy is used as a scheduling response strategy, and the scheduling response strategy is used for scheduling control of medical logistics. By dynamically responding to the medical logistics demand deviation, the scheduling strategy is optimized in real time, and the technical effects of improving the medical logistics scheduling efficiency and guaranteeing the medicine transportation quality are achieved.

Description

Technical Field

[0001] The present invention relates to the field of logistics optimization, and in particular to a dynamic demand response scheduling method for pharmaceutical logistics. Background Art

[0002] Pharmaceutical logistics plays an important role in ensuring that drugs are delivered to medical institutions and patients in a timely and safe manner. However, in the actual transportation process, pharmaceutical logistics is affected by many uncertain factors, such as traffic conditions, weather changes, temperature fluctuations, etc. These factors cause deviations between actual transportation demand and preset plans, thereby affecting the transportation timeliness and quality of drugs. In the existing technology, pharmaceutical logistics scheduling mainly relies on pre-established static scheduling plans, lacking the ability to respond to dynamic demand changes in real time. Once deviations from expectations occur, such as vehicle delays, temperature abnormalities, etc., it is difficult to adjust in time, resulting in reduced transportation efficiency and even possible endangerment of drug safety. Summary of the invention

[0003] This application provides a dynamic demand response scheduling method for pharmaceutical logistics, aiming to solve the technical problems in the prior art that pharmaceutical logistics scheduling is not timely and difficult to adapt to dynamic demand changes.

[0004] The dynamic demand response scheduling method for pharmaceutical logistics disclosed in the present application includes: matching and analyzing pharmaceutical logistics targets with real-time sensor data to obtain response synchronization evaluation results; locating demand deviations according to the response synchronization evaluation results, wherein the demand deviations have asynchronous timestamps; performing time window analysis based on the demand deviations to determine the deviation time windows based on the asynchronous timestamps; performing logistics scheduling compensation according to the deviation time windows to obtain scheduling compensation characteristics; obtaining scheduling response variables, wherein the scheduling response variables include path adjustment parameters and vehicle scheduling parameters; and searching for optimal scheduling strategies by matching and evaluating scheduling compensation characteristics with scheduling response variables with the goal of minimizing demand deviations, and using the optimal scheduling strategies as scheduling response strategies, wherein the scheduling response strategies are used for scheduling control of pharmaceutical logistics.

[0005] One or more technical solutions provided in this application have at least the following technical effects or advantages: The method adopts the matching analysis between the pharmaceutical logistics target and the real-time sensor data to obtain the response synchronization evaluation result, evaluate the synchronization degree between the actual transportation status and the target, and lay the foundation for the subsequent demand deviation positioning; locate the demand deviation according to the response synchronization evaluation result, and the demand deviation has an asynchronous timestamp to realize the accurate record of the time point when the deviation occurs; based on the asynchronous timestamp, the time window is parsed according to the demand deviation to determine the deviation time window, and provide a basis for the subsequent scheduling compensation; the logistics scheduling compensation is carried out according to the deviation time window, and the scheduling compensation characteristics are obtained to guide the optimization of scheduling decisions; the scheduling response variables are obtained, and the scheduling response variables include path adjustment parameters and vehicle scheduling parameters, which provide decision space for the subsequent search for the optimal scheduling strategy; with the goal of minimizing the demand deviation, the scheduling compensation characteristics are used to match and evaluate the scheduling response variables, search for the optimal scheduling strategy, and use the optimal scheduling strategy as the scheduling response strategy. The scheduling response strategy is used for scheduling control of pharmaceutical logistics, and the technical solution for guiding the dynamic scheduling control of pharmaceutical logistics solves the technical problems of the untimely response of pharmaceutical logistics scheduling and the difficulty in adapting to dynamic demand changes in the prior art. By dynamically responding to the pharmaceutical logistics demand deviation, the scheduling strategy is optimized in real time, and the technical effect of improving the scheduling efficiency of pharmaceutical logistics and ensuring the quality of drug transportation is achieved.

[0006] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 A flow chart of a method for dynamic demand response scheduling of pharmaceutical logistics is provided for the embodiment of the present application; Figure 2 A flow chart of obtaining scheduling compensation characteristics in a dynamic demand response scheduling method for pharmaceutical logistics is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0008] The overall idea of ​​the technical solution provided by this application is as follows: The embodiment of the present application provides a dynamic demand response scheduling method for pharmaceutical logistics. By real-time monitoring of various parameter indicators in the pharmaceutical logistics process, it dynamically identifies the demand deviation that occurs, and performs precise time positioning and intelligent scheduling compensation based on this, so as to minimize the impact of the deviation, improve the efficiency of pharmaceutical logistics scheduling, and ensure the quality of drug transportation.

[0009] First, by matching and analyzing real-time sensor data with preset logistics targets, the synchronization between the transportation process and the plan is evaluated, and demand deviations are discovered in a timely manner. Then, asynchronous timestamps are used to accurately locate the deviations and divide the time windows to provide a basis for subsequent compensation. Then, based on the deviation time window and scheduling response variables, intelligent scheduling strategy search and optimization are performed to generate the optimal scheduling response strategy. This strategy is then applied to actual logistics scheduling control to dynamically guide real-time adjustments to the transportation process to ensure that drugs are delivered to their destinations safely and efficiently.

[0010] Through the dynamic demand response scheduling method of pharmaceutical logistics, we can actively adapt to various dynamic changes in the pharmaceutical logistics process, compensate for demand deviations in a timely manner, and improve the timeliness and accuracy of scheduling decisions, thereby effectively improving the efficiency of pharmaceutical logistics and ensuring the safety of drug transportation.

[0011] After introducing the basic principles of the present application, the non-limiting implementation methods of the present application will be specifically introduced below in conjunction with the drawings in the specification.

[0012] like Figure 1 As shown, the embodiment of the present application provides a dynamic demand response scheduling method for pharmaceutical logistics, the method comprising: S1: Match and analyze pharmaceutical logistics goals with real-time sensor data to obtain response synchronization evaluation results.

[0013] Specifically, first, obtain the pharmaceutical logistics goals, such as the drug storage temperature range, expected delivery time, etc., as a reference standard for evaluating whether the logistics process meets the requirements. At the same time, by connecting the sensor equipment, obtain data reflecting the logistics status in real time, such as the drug storage temperature data fed back by the temperature sensor, the logistics vehicle location data fed back by the GPS positioning device, etc. After obtaining the pharmaceutical logistics goals and real-time sensor data, perform matching analysis, for example, compare the real-time temperature with the target temperature range to determine whether it deviates; predict the arrival time based on the real-time location combined with the road conditions to determine whether it meets the expected timeliness, etc. The results of the matching analysis reflect the degree to which the current logistics status meets the pharmaceutical logistics goals, forming a response synchronization evaluation result.

[0014] By obtaining the response synchronization evaluation results, possible deviations in the logistics process can be discovered in a timely manner, providing a decision-making basis for subsequent scheduling responses and a foundation for achieving dynamic scheduling.

[0015] S2: Locate the demand deviation according to the response synchronization evaluation result, where the demand deviation has an asynchronous timestamp.

[0016] Specifically, after completing the matching analysis of the pharmaceutical logistics target and the real-time sensor data, if the response synchronization evaluation result shows that the two are not synchronized, it means that there is a demand deviation, that is, the actual logistics status deviates from the expected target. At this time, the specific demand item with the deviation is further located according to the response synchronization evaluation result. For example, if the response synchronization evaluation result shows that the temperature does not meet the requirements, it is located as a temperature deviation; if the response synchronization evaluation result shows that the estimated arrival time is delayed, it is located as a timeliness deviation, etc. Locating the demand deviation helps to carry out targeted scheduling compensation later. At the same time, since the logistics process is dynamically changing, the time of occurrence of demand deviation varies. In order to accurately record the time when the demand deviation occurs, an asynchronous timestamp is added to each located demand deviation. The asynchronous timestamp records the specific time when the deviation occurs and is a reference for the subsequent deviation time window analysis. For example, the timestamp of the temperature deviation is a certain moment in the logistics process, while the timestamp of the timeliness deviation is the difference between the estimated arrival time and the required time limit. Through the asynchronous timestamp, the time when each demand deviation occurs is associated and distinguished.

[0017] By locating demand deviations, specific problems in the logistics process can be clearly identified, and the time when the problem occurred can be recorded through a timestamp, providing data support for subsequent time window analysis and scheduling decisions, laying the foundation for dynamic response deviations.

[0018] S3: Based on the asynchronous timestamp, perform time window analysis according to the demand deviation to determine the deviation time window.

[0019] Specifically, asynchronous timestamps are used to further analyze the demand deviation in the time dimension. First, a deviation time window is introduced to represent the time range in which the demand deviation occurs as a time window. By analyzing the asynchronous timestamp of the demand deviation, the starting and ending boundaries of the deviation time window are determined. For example, for temperature deviation, the starting time of the deviation is identified according to the asynchronous timestamp, and then the end time of the deviation is determined in combination with the preset temperature recovery time threshold, thereby obtaining the deviation time window of the temperature deviation; for example, for time deviation, the asynchronous timestamp records the estimated delay time, then the starting point of the deviation time window is the current time, and the end point is the estimated arrival time.

[0020] By determining the deviation time window, more specific time constraints and goals can be provided for subsequent scheduling decisions. The time range of the impact of demand deviation can be clarified, which helps to evaluate the severity of the deviation, lays a time foundation for achieving accurate dynamic scheduling, and formulates targeted scheduling strategies.

[0021] S4: Perform logistics scheduling compensation according to the deviation time window to obtain scheduling compensation characteristics.

[0022] Specifically, according to the start and end time boundaries of the deviation time window, the time period for which scheduling compensation is required is determined. During this time period, the impact of the deviation is reduced or even eliminated by adjusting the logistics scheduling strategy. There are many ways to compensate for logistics scheduling, and flexible decisions can be made based on the type of deviation and actual conditions. For example, for temperature deviation, the refrigeration equipment parameters of the transport vehicle are adjusted within the deviation time window, or a spare vehicle with better temperature conditions is selected; for timeliness deviation, the path planning is optimized within the deviation time window to avoid congested sections, or additional fast-response capacity is dispatched. By implementing scheduling compensation within the deviation time window, the impact of deviations on logistics quality and timeliness can be effectively reduced, and the responsiveness and resilience of the supply chain can be improved. The results of scheduling compensation are characterized by a set of parameters to form scheduling compensation characteristics, including multiple dimensions such as the type, intensity, and duration of compensation measures, which quantitatively describe the key attributes of the compensation strategy and provide important input for subsequent scheduling optimization.

[0023] By formulating and implementing scheduling compensation measures for deviation time windows and actively adjusting strategies, we can dynamically adapt to changes in demand and ensure logistics quality and efficiency.

[0024] S5: Obtaining dispatch response variables, where the dispatch response variables include path adjustment parameters and vehicle dispatch parameters.

[0025] Specifically, first, obtain the dispatch response variables, which reflect the flexibility and adjustable space of logistics in terms of path planning and capacity scheduling. By obtaining and analyzing the dispatch response variables, the ability to cope with deviations and dynamically optimize scheduling can be better evaluated. The dispatch response variables include path adjustment parameters and vehicle dispatch parameters. Among them, the path adjustment parameters are related to the optimization of the distribution route, including a series of parameters such as the number of alternative paths, expected travel time, and adjustment cost. By analyzing the path adjustment parameters, it can be determined whether the selection of alternative paths is feasible and how much benefit can be brought. The vehicle dispatch parameters reflect the flexibility of capacity scheduling, including the number and type of available vehicles, the current location and status of the vehicle, the dispatch time and mileage cost, etc. By analyzing the vehicle dispatch parameters, it can be evaluated whether it is feasible to increase capacity or change vehicle models, and what benefits can be brought.

[0026] Through various channels such as on-board equipment and dispatching systems, dispatch response variables are obtained in real time, providing a detailed basis for optimizing dispatching decisions. By comprehensively considering path adjustment parameters and vehicle dispatching parameters, the dynamic response capability of logistics can be fully evaluated. On this basis, the optimal dispatching strategy combination is selected to minimize dispatching costs and maximize logistics efficiency while meeting the deviation time window constraints.

[0027] S6: With the goal of minimizing the demand deviation, the scheduling compensation characteristics are used to match and evaluate the scheduling response variables to search for the optimal scheduling strategy, and the optimal scheduling strategy is used as the scheduling response strategy. The scheduling response strategy is used to perform scheduling control on pharmaceutical logistics.

[0028] Specifically, the scheduling compensation characteristics and scheduling response variables are matched and evaluated to find the optimal scheduling strategy combination. The matching evaluation process takes the minimization of demand deviation as the optimization goal. By quantitatively analyzing the relationship between scheduling compensation characteristics and scheduling response variables, the expected effects of different scheduling strategy combinations are evaluated, and the optimal strategy that can minimize the impact of deviation is found. For example, heuristic search, genetic algorithm, reinforcement learning, etc. are used to continuously iterate and optimize in the strategy search space, and the deviation mitigation effects of different strategies are compared through simulation, evaluation, etc. until the optimal solution that meets the demand is found. The optimal scheduling strategy obtained by the search can effectively compensate for the deviation that has occurred and can also deal with possible deviation risks. Subsequently, the optimal scheduling strategy is used as the scheduling response strategy to guide the actual pharmaceutical logistics scheduling execution process. By dynamically responding to changes in demand and continuously optimizing scheduling decisions, the quality and efficiency of pharmaceutical logistics can be significantly improved, and the risk of drug supply can be reduced.

[0029] Through the intelligent matching optimization of scheduling compensation characteristics and scheduling response variables, the optimal scheduling strategy searched can minimize demand deviation, improve the efficiency of pharmaceutical logistics scheduling, and ensure the quality of drug transportation.

[0030] Furthermore, the embodiment of the present application also includes: Performing logistics demand analysis according to the pharmaceutical logistics target to obtain pharmaceutical logistics constraint conditions, wherein the constraint conditions have a constraint strength coefficient; Connecting to the sensor device channel to obtain sensor data, the sensor data includes drug storage temperature data and logistics location tracking data; According to the sensor data, the logistics parameters are parsed according to the data type to obtain the logistics status parameters; Performing matching analysis on the logistics state parameters using the constraint conditions to determine constraint matching coefficients; Taking the constraint strength coefficient as a target, a response evaluation is performed on the constraint matching coefficient to obtain the response synchronization evaluation result.

[0031] In a feasible implementation, first, according to the specific needs of the pharmaceutical logistics target, a comprehensive logistics demand analysis is carried out, which not only considers the logistics requirements such as the storage conditions and delivery time limit of the medicine, but also considers the particularity of pharmaceutical logistics, such as the precise control requirements for temperature and humidity, the restrictions on environmental factors such as vibration and light during the transportation process, and the special requirements for transportation tools and packaging materials. By comprehensively analyzing the pharmaceutical logistics target, the constraints of pharmaceutical logistics are extracted. At the same time, the constraint intensity coefficient is introduced, and for each constraint condition, its critical degree of impact on the quality and safety of pharmaceutical logistics is evaluated, and the corresponding intensity coefficient is given. For example, the constraint intensity coefficient of the drug storage temperature is higher than the constraint intensity coefficient of the transportation tool type, because the former has a more direct and critical impact on the quality and effectiveness of the drug. Through the constraint intensity coefficient, the refined and differentiated characterization of logistics demand is achieved, which provides an important basis for the subsequent intelligent matching analysis. Then, the sensor device channel is connected, and by integrating various sensor devices, multi-dimensional data in the logistics process is collected in real time to obtain sensor data, which includes drug storage temperature data and logistics positioning tracking data. Among them, the drug storage temperature data is controlled at multiple points and monitored throughout the entire process to ensure its accuracy and completeness; the logistics positioning and tracking data is obtained through a variety of positioning and tracking technologies such as GPS and Beidou, reflecting the transportation trajectory and key nodes of monitored drugs.

[0032] Next, different types of sensor data are classified and preprocessed to remove noise and outliers and improve data quality. Subsequently, for each type of data, a special feature extraction and parameter calculation algorithm is designed. For example, for drug storage temperature data, the average temperature is calculated, and multiple indicators such as temperature fluctuations and the proportion of time exceeding the threshold are analyzed; for logistics positioning and tracking data, key parameters such as driving speed, path deviation, and estimated arrival time are calculated. Through intelligent data analysis, the original sensor data is converted into a series of measurable and evaluable logistics state parameters, providing rich data support for intelligent decision-making. After that, the logistics state parameters are mapped one by one with the constraints to establish a corresponding relationship between the two. After that, for each pair of constraints and logistics state parameters, a matching evaluation function is designed to quantitatively evaluate the degree to which the state parameters satisfy the constraints. For example, for temperature constraints and actual temperature parameters, the degree of deviation between the actual temperature and the target temperature range, the deviation duration, and other factors are considered to give the constraint matching coefficient of the temperature constraint; for time limit constraints and estimated arrival time parameters, the gap between the estimated time and the required time limit is evaluated to give the constraint matching coefficient of the time constraint. By introducing the constraint matching coefficient, the quantitative correlation and comparison between logistics status and demand constraints are realized, which provides an important basis for deviation analysis and scheduling optimization. Then, the constraint matching coefficients of various constraint conditions are weighted and fused with the constraint strength coefficient as the weight to obtain the response synchronization evaluation result. The response synchronization evaluation result is a comprehensive indicator that takes into account the differences in the importance of various logistics constraints and comprehensively and objectively reflects the degree of fit between the real-time status of drug logistics and the expected requirements.

[0033] Furthermore, the embodiment of the present application also includes: The demand deviation includes storage temperature deviation and logistics time tracking deviation. When the demand deviation is storage temperature deviation, the temperature threshold and time tolerance interval are obtained according to the constraint condition; Obtaining a time starting point according to the asynchronous timestamp of the demand deviation; Acquire the drug storage temperature data of the demand deviation, calculate the temperature cumulative deviation in combination with the temperature threshold, and determine the tolerance time threshold based on the time tolerance interval; The deviation time window is acquired according to the time starting point and the tolerance time threshold.

[0034] In a preferred embodiment, first, it is clarified that the demand deviation in the pharmaceutical logistics process includes storage temperature deviation and logistics time tracking deviation. Among them, the storage temperature deviation refers to the situation where the actual storage temperature of the drug deviates from the preset temperature range. For the storage temperature deviation, the temperature threshold and time tolerance interval are obtained according to the corresponding temperature constraints. Among them, the temperature threshold defines the upper and lower limits of the acceptable temperature of the drug, which is the benchmark for judging whether the temperature deviates; and the time tolerance interval specifies the maximum tolerance time for the temperature deviation threshold, which reflects the tolerance of the drug to temperature fluctuations. Secondly, for each detected temperature deviation, the time point of its occurrence is recorded to form an asynchronous timestamp, which serves as the starting point of time and identifies the starting time of the deviation. It is the key anchor point for determining the deviation time window. By capturing the asynchronous timestamp, the precise positioning of the time when the deviation occurs is achieved, laying the foundation for subsequent time window analysis.

[0035] Then, the drug storage temperature data after the temperature deviation occurs is continuously obtained and compared with the temperature threshold in real time. If the actual temperature continues to exceed the temperature threshold range, the temperature difference of the exceeding part is accumulated to obtain the cumulative temperature deviation value, which reflects the severity and duration of the temperature deviation. At the same time, the tolerance time threshold is calculated with reference to the preset time tolerance interval. If the cumulative temperature deviation value returns to the acceptable range within the tolerance time, the impact of the deviation will be considered tolerable. The setting of the tolerance time threshold can avoid excessive sensitivity to occasional and short-term temperature fluctuations and improve the rationality of deviation judgment. Subsequently, according to the obtained time starting point and tolerance time threshold of the temperature deviation, the time interval formed in the middle with the time starting point as the starting point and the tolerance time threshold as the end point constitutes the deviation time window, which accurately frames the impact period of the temperature deviation and intuitively presents the start and end boundaries of the temperature deviation. The extraction of the deviation time window enables subsequent scheduling decisions to accurately lock the key time nodes affected by the deviation and impose regulation at the most needed time point, thereby minimizing the adverse effects of the deviation to the greatest extent.

[0036] Furthermore, the embodiment of the present application also includes: When the demand deviation is the logistics time tracking deviation, obtaining the logistics node time constraint according to the constraint condition; According to the asynchronous timestamp of the demand deviation, obtain the deviation time starting point; Determine the vehicle speed based on the logistics location tracking data combined with the time data; Obtaining a node time deviation according to the vehicle driving speed and the logistics node time constraint; The deviation time window is obtained according to the deviation time starting point and the node time deviation, wherein the deviation time end point of the deviation time window is a time point obtained by adding the node time deviation to the deviation time starting point.

[0037] In a preferred embodiment, when the demand deviation is a logistics time tracking deviation, first, according to the constraint conditions, the expected arrival time of each key logistics node is obtained as the logistics node time constraint, wherein the logistics nodes include the shipping point, the transfer station, the destination, etc. The logistics node time constraint reflects the expected time requirements of the drug at each logistics node. By clarifying the time constraints of each logistics node, a judgment benchmark is provided for the subsequent quantitative calculation of the time deviation. Unlike the single end point time requirement, the refined control of the time of each link in the whole logistics process is realized. Subsequently, the asynchronous timestamp when the time deviation occurs is obtained as the starting point of the deviation time. However, unlike the temperature deviation, the occurrence of the time deviation is often not a certain time point, but gradually accumulated during the logistics process. Therefore, the starting point of the time deviation is selected when the expected time begins to be significantly affected, such as when delivery delays begin to occur, so as to more accurately lock the key influencing nodes of the time problem.

[0038] Next, the location tracking data and timestamp information of the logistics vehicle are used to calculate the driving speed of the vehicle in different sections in real time. Specifically, the GPS location data of the vehicle at different times is obtained, and the vehicle driving speed is obtained by the ratio of the distance difference and the time difference. By continuously tracking the changes in vehicle speed, it is possible to accurately perceive whether the vehicle is idling abnormally or delayed due to congestion, which provides an important basis for judging the timeliness deviation. Subsequently, the real-time measured vehicle speed is compared with the time constraint of the logistics node to quantitatively evaluate whether the current vehicle speed can meet the time requirements of the subsequent nodes, thereby obtaining the estimated node time deviation. Specifically, the node time deviation is equal to the actual expected arrival time minus the expected arrival time of the constraint. When the node time deviation is positive, it means that there is a risk of timeliness delay. Afterwards, the starting point of the deviation time is used as the timestamp of the occurrence of the logistics deviation, and the end point is the starting point of the deviation time plus the node time deviation, forming a forward-looking deviation time window. Compared with a simple time section, the deviation time window can perceive the timeliness deviation in advance and predict the duration of the deviation impact, so as to adjust the response strategy accordingly.

[0039] Further, such as Figure 2 As shown, the embodiment of the present application also includes: Obtaining a deviation attribute of the deviation time window, wherein the deviation attribute is a deviation parameter category determined for the storage temperature deviation and the logistics aging tracking deviation; According to the deviation attribute, obtaining the temperature deviation amount and time range, and the aging deviation amount and time range of the deviation time window; According to the temperature deviation and time range, the aging deviation and time range, the compensation parameters and the compensation requirements are extracted to obtain the scheduling compensation characteristics.

[0040] In a feasible implementation, first, the deviation attribute of each deviation time window is obtained. The deviation attribute characterizes the type of the deviation, which is divided into two categories: storage temperature deviation and logistics time tracking deviation. By identifying the attribute category of the deviation time window, the corresponding compensation strategy and parameters can be selected in a targeted manner to provide a basis for differentiated compensation schemes. Then, for different deviation attributes, the corresponding deviation quantitative indicators and time information are extracted. For storage temperature deviation, the temperature deviation amount and the time range of the deviation duration are obtained from the deviation time window; for logistics time tracking deviation, the time deviation amount (such as estimated delay time) and the time range affected by the deviation are obtained from the deviation time window. By extracting key indicators, the deviation risk reflected by the deviation time window is converted into a specific quantitative indicator, which is convenient for subsequent targeted compensation scheduling. Afterwards, according to the obtained temperature deviation amount and time range, time deviation amount and time range, the matching compensation parameters and the required compensation amount are further extracted, thereby forming a complete scheduling compensation feature. Specifically, for temperature deviation, the compensation parameter is the power of the refrigeration equipment of the drug-carrying vehicle, and the compensation demand is the refrigeration time or intensity required to restore the temperature; for time deviation, the compensation parameter is the speed increase of the dispatched vehicle, and the compensation demand is the time reduction required to make up for the delay. When designing the compensation parameters and demand, factors such as the properties of the drugs and the performance parameters of the vehicles were fully considered, and efforts were made to offset the adverse effects of the deviation to the maximum extent through compensation strategies.

[0041] Through key mapping and transformation from deviation time windows to scheduling compensation characteristics, a bridge is built between deviation analysis and compensation decision-making. By accurately extracting compensation-related parameters and quantitatively analyzing compensation needs, the scheduling optimization process is guided more efficiently and accurately, minimizing the impact of transportation deviations on drug quality and timeliness, and ensuring the safe and efficient operation of medicines.

[0042] Furthermore, the embodiment of the present application also includes: According to the scheduling response variable, the response parameters of the schedulable target are obtained, the schedulable target includes a spare logistics vehicle and an adjustable path, the response parameters are the position, speed, and temperature of the spare logistics vehicle, and the adjustment distance and adjustment time of the adjustable path, wherein the response parameters correspond to the path adjustment parameters and the vehicle scheduling parameters; Fitting a relationship function between the response parameter and the scheduling compensation feature, and performing a matching evaluation between the scheduling compensation feature and the response parameter based on the relationship function to obtain a matching degree; The missing compensation coefficient is calculated according to the matching degree, and the demand deviation minimization is converted into the missing compensation coefficient minimum as the goal for iterative search until the demand deviation requirement or the number of iterations is met, and the schedulable target with the smallest current demand deviation and its response parameters are combined into the optimal scheduling strategy.

[0043] In a preferred embodiment, first, according to the scheduling response variable, the response parameters of the schedulable target are obtained, that is, the target object and its key parameters that can be currently optimized for scheduling. The schedulable targets mainly include spare logistics vehicles and adjustable paths. For spare logistics vehicles, the current position, driving speed, warehouse temperature and other state parameters of the spare logistics vehicles are obtained; for adjustable paths, the attribute parameters such as distance change and time cost of possible adjustment schemes are obtained. These parameters directly correspond to the path adjustment and vehicle scheduling variables, providing an optional decision space for subsequent scheduling optimization. After obtaining the scheduling compensation characteristics and response parameters, a mapping relationship between the two is established, and matching evaluation is carried out accordingly. First, through the data fitting method, a relationship function between the response parameters and the scheduling compensation characteristics is constructed to characterize the quantitative relationship between different response parameter combinations and the corresponding compensation effects. Then, based on the relationship function, the compensation effect of each possible scheduling decision (i.e., a set of response parameters) is evaluated to see how much compensation gap it can make up, and the matching index is calculated. The higher the matching degree, the more effectively the scheduling decision can compensate for the current deviation, and the better the scheduling effect. Through the matching degree, the advantages and disadvantages of different scheduling strategies can be evaluated and compared more accurately and efficiently. After that, based on the matching degree, the compensation missing coefficient is calculated to measure the size of the compensation gap of the scheduling strategy for the current deviation. The smaller the coefficient, the better the effect of the scheduling strategy in compensating for the deviation, and the less the remaining uncompensated deviation. Therefore, the original demand deviation minimization problem is transformed into the compensation missing coefficient minimization problem. Under this goal orientation, the intelligent optimization algorithm is used to continuously evaluate and adjust the scheduling strategy through iterative search until a set of response parameter combinations with the smallest compensation missing coefficient is found, or the preset number of iterations is reached. The optimal parameter combination is finally determined, that is, the optimal scheduling strategy with the smallest current demand deviation. Through the construction of intelligent search algorithms and objective functions, the optimal solution can be quickly locked in a large number of scheduling strategy combinations, greatly improving the efficiency and accuracy of scheduling optimization.

[0044] Furthermore, the embodiment of the present application also includes: Taking the response parameter as an independent variable and the adjustment compensation characteristic as a dependent variable, fitting the relationship function, wherein the relationship function includes a path adjustment parameter relationship function and a vehicle scheduling parameter relationship function; According to the path adjustment parameter relationship function, the adjustment distance and adjustment time of the adjustable path are converted into compensation amounts to obtain a path time-efficiency characteristic compensation amount; According to the vehicle scheduling parameter relationship function, the position, speed and temperature of the standby logistics vehicle are converted into compensation amounts to obtain a temperature deviation characteristic compensation amount; The path aging characteristic compensation amount and / or the temperature deviation characteristic compensation amount are used as the numerator, and the corresponding parameter compensation characteristic in the scheduling compensation characteristic is used as the denominator to calculate the proportion and obtain the matching degree.

[0045] In a preferred embodiment, first, a function fitting method is used to model the quantitative relationship between the response parameter and the scheduling compensation feature. Among them, the response parameter is used as the independent variable, the scheduling compensation feature is used as the dependent variable, and the mapping function of the two is constructed. Considering that the compensation scheduling is mainly achieved by two means: path adjustment and vehicle scheduling, the mapping function is also divided into two categories: path adjustment parameter relationship function and vehicle scheduling parameter relationship function. In the form of mathematical functions, the corresponding relationship between different scheduling strategies (i.e., different response parameter combinations) and their corresponding compensation effects is depicted, which lays the foundation for the model for quantitative analysis of the compensation effect. Subsequently, the response parameters are converted into corresponding compensation feature quantities using the path adjustment parameter relationship function and the vehicle scheduling parameter relationship function respectively. For path adjustment, the key parameters are the distance change and time cost of the adjustment path, which are mapped to the compensation amount of the path adjustment for the time deviation through the relationship function, that is, the path time characteristic compensation amount; for vehicle scheduling, the key parameters are the attributes such as the position, speed, and temperature of the spare vehicle, which are mapped to the compensation amount of the vehicle scheduling for the temperature deviation through the relationship function, that is, the temperature deviation characteristic compensation amount. By calculating the compensation amount, on the one hand, the adjustment range of the scheduling strategy is taken into account, and on the other hand, the sensitivity of the compensation characteristics to the deviation is also taken into account, which can objectively reflect the compensation effect of the scheduling strategy.

[0046] After that, the matching index of the scheduling strategy is obtained by calculating the ratio of the compensation amount to the compensation feature. Specifically, for time deviation, the path time feature compensation amount is used as the numerator and the time compensation feature is used as the denominator. The ratio of the two represents the degree of compensation of the scheduling strategy for the time deviation; for temperature deviation, the temperature deviation feature compensation amount is divided by the temperature compensation feature, and the ratio represents the compensation effect of the scheduling strategy for the temperature deviation. The calculation of the matching degree fully considers the differences in compensation demands for different types of deviations. The use of independent ratio calculations can evaluate the matching degree more accurately and specifically. In practical applications, a scheduling strategy may involve both path adjustment and vehicle scheduling, so it is necessary to comprehensively consider the time matching degree and temperature matching degree. For example, the two matching degree values ​​are simply added or weighted averaged to obtain a comprehensive matching degree; or, according to the urgency of time and temperature under the current deviation, the weight coefficients of the two matching degrees are dynamically adjusted. The more serious the deviation, the greater the weight of the indicator, thereby obtaining a dynamically weighted comprehensive matching degree.

[0047] Furthermore, the embodiment of the present application also includes: Perform compensation time analysis according to the optimal scheduling strategy and construct a compensation time window; According to the compensation time window and the deviation time window, matching and fitting are performed with the end time window to determine the window fitting degree; The window fitting degree is used as a strategy verification parameter, and when the strategy verification parameter meets the fitting requirement, the optimal scheduling strategy is determined.

[0048] In a feasible implementation, first, according to the path adjustment and vehicle scheduling scheme determined by the optimal scheduling strategy, the compensation completion time of each deviation node is estimated, and a complete compensation time window is constructed. This window covers the entire time span from the current moment to the time when all deviations are compensated, and describes the process of the dynamic change of the deviation impact over time after the implementation of the scheduling strategy. The introduction of the compensation time window can organically combine the static decision-making of the scheduling strategy with the dynamic execution effect, providing a timing basis for strategy verification. Then, the compensation time window is compared and fitted with the original deviation time window. Among them, the compensation time window reflects the expected improvement and elimination process of the deviation impact under the action of the optimal scheduling strategy; the deviation time window describes the natural persistence and diffusion trend of the deviation impact. By matching the two windows at the end time and evaluating the degree of overlap, a window fitting degree is obtained. The higher the fitting degree, the better the dynamic effect of the optimal scheduling strategy on the deviation compensation, and the higher the adaptability and reliability of the optimal scheduling strategy. Subsequently, the window fitting degree is used as a quantitative strategy verification parameter, representing the dynamic adaptability of the optimal scheduling strategy. When the parameter meets the preset fitting requirements (such as being higher than a certain threshold), the current optimal scheduling strategy is considered reliable and effective and can be implemented; on the contrary, if the strategy verification parameter does not meet the standard, it means that the strategy may have risks and uncertainties during dynamic execution and needs further adjustment and optimization. By verifying the strategy parameters and setting clear judgment criteria, a closed-loop strategy optimization mechanism can be constructed to adaptively correct and improve scheduling decisions and continuously improve the dynamic performance of the strategy.

[0049] In summary, the pharmaceutical logistics dynamic demand response scheduling method provided in the embodiment of the present application has the following technical effects: According to the matching analysis of pharmaceutical logistics goals and real-time sensor data, the response synchronization evaluation results are obtained to identify changes in logistics demand, providing a basis for timely discovery of demand deviations. According to the response synchronization evaluation results, the demand deviation is located. The demand deviation has an asynchronous timestamp, which realizes the time dimension quantification of the deviation and lays the foundation for subsequent time window analysis and scheduling compensation. Based on the asynchronous timestamp, the time window is parsed according to the demand deviation, the deviation time window is determined, and the deviation impact is associated with the time dimension, providing a more fine-grained decision reference for scheduling compensation. Logistics scheduling compensation is performed according to the deviation time window, and scheduling compensation characteristics are obtained to guide subsequent scheduling optimization. The scheduling response variables are obtained. The scheduling response variables include path adjustment parameters and vehicle scheduling parameters, which provide a basis for intelligent search for the optimal scheduling strategy. With the goal of minimizing demand deviations, the scheduling compensation characteristics are used to match and evaluate the scheduling response variables, search for the optimal scheduling strategy, and use the optimal scheduling strategy as the scheduling response strategy. The scheduling response strategy is used for scheduling control of pharmaceutical logistics, forming a complete dynamic scheduling response closed loop of pharmaceutical logistics, which can effectively respond to various dynamic changes in the transportation process, improve the efficiency of pharmaceutical logistics scheduling, and ensure the quality of drug transportation.

[0050] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0051] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to multiple elements that can be selected individually or in full. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these changes and variations.

Claims

1. A dynamic demand response scheduling method for pharmaceutical logistics, characterized in that: The pharmaceutical logistics dynamic demand response scheduling method comprises: Match and analyze pharmaceutical logistics goals with real-time sensor data to obtain response synchronization evaluation results; Locating a demand deviation according to the response synchronization evaluation result, the demand deviation having an asynchronous timestamp; Based on the asynchronous timestamp, performing time window analysis according to the demand deviation to determine the deviation time window; Perform logistics scheduling compensation according to the deviation time window to obtain scheduling compensation characteristics; Obtaining a dispatch response variable, wherein the dispatch response variable includes a path adjustment parameter and a vehicle dispatch parameter; With the goal of minimizing the demand deviation, the scheduling compensation characteristics are used to match and evaluate the scheduling response variables to search for the optimal scheduling strategy, which is used as the scheduling response strategy for scheduling control of pharmaceutical logistics.

2. The pharmaceutical logistics dynamic demand response scheduling method according to claim 1, characterized in that: The obtaining of the response synchronization evaluation result comprises: Performing logistics demand analysis according to the pharmaceutical logistics target to obtain pharmaceutical logistics constraint conditions, wherein the constraint conditions have a constraint strength coefficient; Connecting to the sensor device channel to obtain sensor data, the sensor data includes drug storage temperature data and logistics location tracking data; According to the sensor data, the logistics parameters are parsed according to the data type to obtain the logistics status parameters; Perform matching analysis on the logistics state parameters using the constraint conditions to determine constraint matching coefficients; Taking the constraint strength coefficient as a target, a response evaluation is performed on the constraint matching coefficient to obtain the response synchronization evaluation result.

3. The pharmaceutical logistics dynamic demand response scheduling method according to claim 2, characterized in that: Based on the asynchronous timestamp, performing time window analysis according to the demand deviation to determine the deviation time window includes: The demand deviation includes storage temperature deviation and logistics time tracking deviation. When the demand deviation is storage temperature deviation, the temperature threshold and time tolerance interval are obtained according to the constraint condition; Obtaining a time starting point according to the asynchronous timestamp of the demand deviation; Acquire the drug storage temperature data of the demand deviation, calculate the temperature cumulative deviation in combination with the temperature threshold, and determine the tolerance time threshold based on the time tolerance interval; The deviation time window is acquired according to the time starting point and the tolerance time threshold.

4. The pharmaceutical logistics dynamic demand response scheduling method according to claim 3, characterized in that: The determining of the deviation time window further includes: When the demand deviation is the logistics time tracking deviation, obtaining the logistics node time constraint according to the constraint condition; According to the asynchronous timestamp of the demand deviation, obtain the deviation time starting point; Determine the vehicle speed based on the logistics location tracking data combined with the time data; Obtaining a node time deviation according to the vehicle driving speed and the logistics node time constraint; The deviation time window is obtained according to the deviation time starting point and the node time deviation, wherein the deviation time end point of the deviation time window is a time point obtained by adding the node time deviation to the deviation time starting point.

5. The pharmaceutical logistics dynamic demand response scheduling method according to claim 4, characterized in that: Perform logistics scheduling compensation according to the deviation time window to obtain scheduling compensation characteristics, including: Obtaining a deviation attribute of the deviation time window, wherein the deviation attribute is a deviation parameter category determined for the storage temperature deviation and the logistics aging tracking deviation; According to the deviation attribute, obtaining the temperature deviation amount and time range, and the aging deviation amount and time range of the deviation time window; According to the temperature deviation and time range, the aging deviation and time range, the compensation parameters and the compensation requirements are extracted to obtain the scheduling compensation characteristics.

6. The pharmaceutical logistics dynamic demand response scheduling method according to claim 5, characterized in that: Taking the minimization of the demand deviation as the goal, the dispatch compensation characteristics are used to match and evaluate the dispatch response variables to search for the optimal dispatch strategy, including: According to the scheduling response variable, the response parameters of the schedulable target are obtained, the schedulable target includes a spare logistics vehicle and an adjustable path, the response parameters are the position, speed, and temperature of the spare logistics vehicle, and the adjustment distance and adjustment time of the adjustable path, wherein the response parameters correspond to the path adjustment parameters and the vehicle scheduling parameters; Fitting a relationship function between the response parameter and the scheduling compensation feature, and performing a matching evaluation between the scheduling compensation feature and the response parameter based on the relationship function to obtain a matching degree; The missing compensation coefficient is calculated according to the matching degree, and the demand deviation minimization is converted into the missing compensation coefficient minimum as the goal for iterative search until the demand deviation requirement or the number of iterations is met, and the schedulable target with the smallest current demand deviation and its response parameters are combined into the optimal scheduling strategy.

7. The pharmaceutical logistics dynamic demand response scheduling method according to claim 6, characterized in that: Fitting a relationship function between the response parameter and the scheduling compensation feature, and performing a matching evaluation between the scheduling compensation feature and the response parameter based on the relationship function to obtain a matching degree, including: Taking the response parameter as an independent variable and the adjustment compensation characteristic as a dependent variable, fitting the relationship function, wherein the relationship function includes a path adjustment parameter relationship function and a vehicle scheduling parameter relationship function; According to the path adjustment parameter relationship function, the adjustment distance and adjustment time of the adjustable path are converted into compensation amounts to obtain a path time-efficiency characteristic compensation amount; According to the vehicle scheduling parameter relationship function, the position, speed and temperature of the standby logistics vehicle are converted into compensation amounts to obtain a temperature deviation characteristic compensation amount; The path aging characteristic compensation amount and / or the temperature deviation characteristic compensation amount are used as the numerator, and the corresponding parameter compensation characteristic in the scheduling compensation characteristic is used as the denominator to calculate the proportion and obtain the matching degree.

8. The pharmaceutical logistics dynamic demand response scheduling method according to claim 6, characterized in that: The pharmaceutical logistics dynamic demand response scheduling method also includes: Perform compensation time analysis according to the optimal scheduling strategy and construct a compensation time window; According to the compensation time window and the deviation time window, matching and fitting are performed with the end time window to determine the window fitting degree; The window fitting degree is used as a strategy verification parameter, and when the strategy verification parameter meets the fitting requirement, the optimal scheduling strategy is determined.

Images