Medical product logistics transportation state intelligent supervision system and method based on cloud computing

Abstract

The invention discloses a medical product logistics transportation state intelligent supervision system and method based on cloud computing, and relates to the field of transportation state supervision. According to the invention, the acquisition frequency of temperature data of a current medical product is adjusted so as to ensure that the acquired temperature data is not missed; the acquisition frequency is ensured to be in a reasonable range; then the acquisition frequency of the parameters influencing the temperature of the medicine product is adjusted based on the transportation data in the actual process, so that the accuracy of the basis source for adjusting the acquisition frequency of the temperature data of the current medicine product is further ensured, namely, the acquired temperature data is further ensured not to be missed; a plurality of constant coefficients of the initial medical product temperature monitoring frequency mapping equation are iteratively optimized for multiple times by adopting a king butterfly optimization algorithm, the mapping accuracy of the initial medical product temperature monitoring frequency mapping equation is higher and higher along with iteration, and finally the mapping requirement is met.

Description

Technical Field

[0001] The present invention belongs to the field of transportation status supervision, and in particular, relates to a cloud computing-based intelligent supervision system and method for the logistics transportation status of pharmaceutical products. Background Art

[0002] During the transportation of pharmaceutical products, temperature monitoring is an essential part of the transportation process due to their sensitivity to temperature. However, some temperature monitoring equipment relies on periodic recording (such as once every 15 minutes), that is, the monitoring frequency is fixed. If a fixed monitoring frequency is always used during transportation, short-term temperature anomalies (such as instantaneous temperature rise caused by opening the cold storage door) may be missed, thus affecting the pharmaceutical products. Summary of the invention

[0003] In view of the problems in the related technologies, the present invention proposes a cloud computing-based intelligent supervision system and method for the logistics and transportation status of pharmaceutical products to overcome the above-mentioned technical problems existing in the existing related technologies.

[0004] To solve the above technical problems, the present invention is achieved through the following technical solutions: The present invention is a method for intelligently supervising the logistics and transportation status of pharmaceutical products based on cloud computing, comprising the following steps: S1. Obtaining real-time temperature impact parameter data corresponding to the transportation of the current pharmaceutical product to be regulated, and obtaining the current real-time pharmaceutical product temperature impact parameter set; S2, collecting the temperature monitoring frequency data of several groups of pharmaceutical products in the transportation process and the corresponding temperature influencing parameter data of the pharmaceutical products in history and constructing the final pharmaceutical product temperature monitoring frequency mapping equation; S3. Use the final pharmaceutical product temperature monitoring frequency mapping equation to map the current real-time pharmaceutical product temperature influence parameter set to obtain the current real-time pharmaceutical product temperature monitoring frequency data; collect the frequency data of the pharmaceutical product temperature influence parameter data collected during the current transportation of pharmaceutical products and the pharmaceutical product deterioration rate data after the corresponding transportation is completed to construct a pharmaceutical product deterioration rate mapping model; adjust the frequency of collecting the pharmaceutical product temperature influence parameter data during the transportation of the current pharmaceutical products to be regulated in accordance with the current real-time pharmaceutical product temperature monitoring frequency data and the pharmaceutical product deterioration rate mapping model to obtain the current final pharmaceutical product temperature influence parameter collection frequency; In this solution, the frequency of collecting temperature data of the current pharmaceutical products is first adjusted to ensure that the collected temperature data will not be missed, and the collection frequency is ensured to be within a reasonable range; then, based on the transportation data in the actual process, the frequency of collecting parameters that affect the temperature of the pharmaceutical products is adjusted, further ensuring the accuracy of the basis for adjusting the frequency of collecting temperature data of the current pharmaceutical products, that is, further ensuring that the collected temperature data will not be missed.

[0005] Preferably, the S1 comprises the following steps: S11, setting several types of medical product temperature monitoring frequencies to obtain a medical product temperature monitoring frequency type set; and then setting several types of parameters that have an impact on the temperature of the medical product to obtain a medical product temperature impact parameter type set; S12, setting the current pharmaceutical product to be regulated; according to the pharmaceutical product temperature impact parameter type set, obtaining the real-time temperature impact parameter data corresponding to the transportation of the current pharmaceutical product to be regulated, and obtaining the current real-time pharmaceutical product temperature impact parameter set , a i Indicates the first i types of real-time temperature-affected parameter data, Indicates the total number of the set pharmaceutical product temperature-affecting parameter types; Since pharmaceutical products are greatly affected by temperature, they need to be monitored in a timely manner during transportation so as to promptly learn of any abnormal temperature conditions and take appropriate measures to deal with them. By setting a pharmaceutical product temperature monitoring frequency type set and a pharmaceutical product temperature influencing parameter type set, the pharmaceutical product temperature monitoring frequency can be dynamically adjusted according to the current real-time transportation environment, thereby ensuring the rationality of the monitoring frequency and preventing the monitoring frequency from being too high, thereby preventing the monitoring cost from being too high. At the same time, all temperature data of the pharmaceutical products can be monitored, and the monitoring of abnormal temperature data within the monitoring frequency will not be missed.

[0006] Preferably, S2 comprises the following steps: S21, setting a threshold value for drug deterioration rate; in conjunction with the pharmaceutical product temperature monitoring frequency type set and the pharmaceutical product temperature influencing parameter type set, collecting pharmaceutical product temperature monitoring frequency data and corresponding pharmaceutical product temperature influencing parameter data corresponding to the result that the deterioration rate of several groups of pharmaceutical products after transportation is less than the pharmaceutical deterioration rate threshold in history, and obtaining a historical pharmaceutical product temperature monitoring frequency data set And the temperature impact parameter matrix of historical pharmaceutical products ; Indicates the collected j The temperature monitoring frequency data corresponding to the transportation process of pharmaceutical products in history is collected. Indicates the total number of groups of transportation processes of medical products collected in history; as follows, ; in, Indicates the collected j The transportation process of pharmaceutical products in the history of the group corresponds to the i Types of real-time temperature-affected parameter data; S22, constructing a final pharmaceutical product temperature monitoring frequency mapping equation using the historical pharmaceutical product temperature monitoring frequency data set and the historical pharmaceutical product temperature influence parameter matrix; By collecting the temperature monitoring frequency data of pharmaceutical products during transportation and the corresponding pharmaceutical product temperature influencing parameter data corresponding to the results of several groups of pharmaceutical products in history whose deterioration rates after transportation were less than the pharmaceutical deterioration rate threshold, data support is provided for the subsequent construction of the final pharmaceutical product temperature monitoring frequency mapping equation; wherein, by setting the pharmaceutical deterioration rate threshold, a standard for collecting historical pharmaceutical product transportation data is constructed; by collecting the data of pharmaceutical product transportation that meets the requirements in history, the correctness of the source of the collected data is guaranteed, thereby ensuring the correctness of the final pharmaceutical product temperature monitoring frequency mapping equation constructed subsequently.

[0007] Preferably, the S22 comprises the following steps: S221, constructing an initial pharmaceutical product temperature monitoring frequency mapping equation in conjunction with the pharmaceutical product temperature monitoring frequency type set and the pharmaceutical product temperature influencing parameter type set; as follows, ; in, b 1 is the dependent variable of the initial pharmaceutical product temperature monitoring frequency mapping equation, representing the pharmaceutical product temperature monitoring frequency data; b 2 is a mapping relationship of the initial pharmaceutical product temperature monitoring frequency mapping equation, which represents the quantitative relationship between each independent variable and the dependent variable in the initial pharmaceutical product temperature monitoring frequency mapping equation; b 3i is the first part of the initial pharmaceutical product temperature monitoring frequency mapping equation i The independent variable represents i Types of temperature-affected parameter data; S222, substituting each row of data in the historical pharmaceutical product temperature influence parameter matrix into the initial pharmaceutical product temperature monitoring frequency mapping equation for mapping, to obtain a historical pharmaceutical product temperature monitoring frequency mapping data set , Indicates that the temperature impact parameter matrix of historical pharmaceutical products j Substitute the row data into the initial medical product temperature monitoring frequency mapping equation to map the resulting data; S223, setting a pharmaceutical product temperature monitoring frequency mapping error threshold; calculating the error data between the historical pharmaceutical product temperature monitoring frequency mapping data set and the historical pharmaceutical product temperature monitoring frequency data set, and obtaining the historical temperature monitoring frequency mapping error data. ;as follows, ; When the historical temperature monitoring frequency mapping error data is greater than or equal to the pharmaceutical product temperature monitoring frequency mapping error threshold, the initial pharmaceutical product temperature monitoring frequency mapping equation is adjusted until the historical temperature monitoring frequency mapping error data is less than the pharmaceutical product temperature monitoring frequency mapping error threshold; otherwise, there is no need to adjust the initial pharmaceutical product temperature monitoring frequency mapping equation, and the initial pharmaceutical product temperature monitoring frequency mapping equation is used as the final pharmaceutical product temperature monitoring frequency mapping equation; Several types of pharmaceutical product temperature influencing parameters are set as independent variables of the initial pharmaceutical product temperature monitoring frequency mapping equation, and the pharmaceutical product temperature monitoring frequency is used as the dependent variable of the initial pharmaceutical product temperature monitoring frequency mapping equation to achieve direct mapping of pharmaceutical product temperature influencing parameters to pharmaceutical product temperature monitoring frequency, which provides an evaluation method for the effect of subsequent adjustment of the real-time temperature monitoring frequency during the transportation of current pharmaceutical products; the mapping accuracy of the initial pharmaceutical product temperature monitoring frequency mapping equation is detected by substituting the collected historical data into the initial pharmaceutical product temperature monitoring frequency mapping equation for mapping, thereby ensuring that the mapping accuracy of the final pharmaceutical product temperature monitoring frequency mapping equation constructed meets the requirements.

[0008] Preferably, adjusting the initial pharmaceutical product temperature monitoring frequency mapping equation in S223 includes the following steps: S2231, setting the value intervals of each constant coefficient in the initial pharmaceutical product temperature monitoring frequency mapping equation, and obtaining a set of value intervals of the temperature monitoring frequency mapping constant coefficients. ;as follows, ; in, , Respectively represent the first i The lower and upper limits of the constant coefficients, c represents the total number of constant coefficients in the initial pharmaceutical product temperature monitoring frequency mapping equation; Construct a temperature monitoring frequency map for pharmaceutical products to adjust the monarch butterfly population; set the maximum number of iterations of the temperature monitoring frequency map for pharmaceutical products to adjust the monarch butterfly population to And the current number of iterations is , respectively recorded as the maximum number of iterations of frequency adjustment and the current number of iterations of frequency adjustment; the temperature monitoring frequency mapping of pharmaceutical products adjusts the search space dimension of the monarch butterfly population and c same; S2232: Setting the temperature monitoring frequency mapping of pharmaceutical products according to the temperature monitoring frequency mapping constant coefficient value interval set, adjusting the initial position of each monarch butterfly in the monarch butterfly population, and obtaining a first initial position matrix ;as follows, ; in, Indicates that the pharmaceutical product temperature monitoring frequency mapping adjusts the monarch butterfly population j The initial position of the monarch butterfly is the first in the initial pharmaceutical product temperature monitoring frequency mapping equation. i The position component in the dimension of constant coefficients, Indicates that the pharmaceutical product temperature monitoring frequency mapping adjusts the size of the monarch butterfly population; The generation formula is as follows: ; In the formula, rand 1ji Indicates for Generate a random number between 0 and 1; S2233: Constructing the fitness function of the temperature monitoring frequency mapping of the pharmaceutical product to adjust the monarch butterfly population d 1; as follows, ; In the formula, It means that a set of constant coefficients obtained in each round of iteration is substituted into the initial pharmaceutical product temperature monitoring frequency mapping equation, and then each row of data in the historical pharmaceutical product temperature influence parameter matrix is ​​substituted into the initial pharmaceutical product temperature monitoring frequency mapping equation to map and obtain the error between the data and the actual data; S2234, start iteration, before iteration, set the frequency adjustment current iteration number to 1; in the first round of iteration, use the pharmaceutical product temperature monitoring frequency mapping to adjust the fitness function of the monarch butterfly population d1. Calculate the fitness value of each monarch butterfly's initial position in the first initial position matrix to obtain a first fitness value set; use the maximum fitness value in the first fitness value set and the initial position of the corresponding monarch butterfly as the first global optimal fitness and the first global optimal position respectively; update the initial position of each monarch butterfly in the first initial position matrix according to the first global optimal fitness and the first global optimal position; after the update is completed, add 1 to the current iteration number of the frequency adjustment and enter the next iteration; In each other iteration, the temperature monitoring frequency mapping of the pharmaceutical product is used to adjust the fitness function of the monarch butterfly population. d 1. Calculate the fitness value of each monarch butterfly position in the monarch butterfly population adjusted by the temperature monitoring frequency mapping of pharmaceutical products updated in the previous iteration process to obtain a second fitness value set; take the maximum fitness value in the second fitness value set and the corresponding monarch butterfly position as the second global optimal fitness and the second global optimal position respectively; update the monarch butterfly population adjusted by the temperature monitoring frequency mapping of pharmaceutical products updated in the previous iteration process at each monarch butterfly position according to the second global optimal fitness and the second global optimal position; after the update is completed, add 1 to the current iteration number of the frequency adjustment and enter the next iteration; S2235, when When , stop the iteration and get the first final global best position and the first final global best fitness; otherwise, continue to iterate until until the time; The first final global optimal fitness is used as the optimized historical temperature monitoring frequency mapping error data. When the optimized historical temperature monitoring frequency mapping error data is less than the pharmaceutical product temperature monitoring frequency mapping error threshold, each position component of the first final global optimal position is substituted into the pharmaceutical product temperature monitoring frequency mapping equation to obtain the final pharmaceutical product temperature monitoring frequency mapping equation; otherwise, return to S2234 to continue iterating until the optimized historical temperature monitoring frequency mapping error data is less than the pharmaceutical product temperature monitoring frequency mapping error threshold; The monarch butterfly optimization algorithm simulates the migration and adaptation behavior of monarch butterflies. The algorithm can conduct extensive searches in the search space, thereby having a greater probability of finding the global optimal solution. It also has good adaptability and robustness to different types of optimization problems and can maintain good performance in a variety of complex environments. Based on the above advantages, the monarch butterfly optimization algorithm is used in this scheme to perform multiple iterative optimizations on multiple constant coefficients of the initial pharmaceutical product temperature monitoring frequency mapping equation, and the mapping accuracy of the initial pharmaceutical product temperature monitoring frequency mapping equation is used as the fitness function. Therefore, as the iteration proceeds, the mapping accuracy of the initial pharmaceutical product temperature monitoring frequency mapping equation becomes higher and higher, and finally meets the mapping requirements.

[0009] Preferably, S3 comprises the following steps: S31, substituting the current real-time pharmaceutical product temperature influence parameter set into the final pharmaceutical product temperature monitoring frequency mapping equation for mapping, to obtain the current real-time pharmaceutical product temperature monitoring frequency data; S32, monitoring the temperature of the current pharmaceutical product to be regulated during transportation according to the current real-time pharmaceutical product temperature monitoring frequency data; after the current pharmaceutical product to be regulated is transported, collecting the deterioration rate data of the current pharmaceutical product to be regulated to obtain the current deterioration rate data; When the current deterioration rate data is greater than or equal to the drug deterioration rate threshold, the frequency of collecting the temperature impact parameter data of the current pharmaceutical product to be regulated during transportation is adjusted to obtain the current final pharmaceutical product temperature impact parameter collection frequency; otherwise, no adjustment is required; By substituting the current real-time pharmaceutical product temperature influencing parameter set into the final pharmaceutical product temperature monitoring frequency mapping equation for mapping, the optimal collection frequency for the current pharmaceutical product temperature data is determined, which not only ensures that the collected temperature data will not be missed, but also ensures that the collection frequency is within a reasonable range, thereby reducing the collection cost.

[0010] Preferably, adjusting the frequency of collecting the temperature-affecting parameter data of the pharmaceutical product during the transportation of the current pharmaceutical product to be regulated in S32 includes the following steps: S321, collecting frequency data of the temperature-affecting parameter data of the pharmaceutical products during the current transportation of the pharmaceutical products and the deterioration rate data of the pharmaceutical products after the corresponding transportation is completed, and obtaining the current pharmaceutical product temperature-affecting parameter collection frequency data set and the current pharmaceutical product deterioration rate dataset , , Respectively represent the collected i The frequency data of collecting the temperature-affecting parameter data of the pharmaceutical products during the transportation of the pharmaceutical products and the deterioration rate data of the pharmaceutical products after the transportation is completed. Indicates the total number of times the pharmaceutical products are currently transported; S322, constructing a pharmaceutical product deterioration rate mapping model using the current pharmaceutical product temperature influencing parameter acquisition frequency data set and the current pharmaceutical product deterioration rate data set; S323, adjusting the frequency of collecting the temperature influence parameter data of the pharmaceutical product during the transportation of the current pharmaceutical product to be regulated in cooperation with the pharmaceutical product deterioration rate mapping model, until the current deterioration rate data is less than the pharmaceutical deterioration rate threshold; By adjusting the frequency of collecting data on temperature influencing parameters of pharmaceutical products during the transportation of the current pharmaceutical products to be regulated, it is further ensured from the frequency perspective of collecting temperature influencing parameters that the collected data on pharmaceutical products will not be missed, thereby improving the integrity of data collection; wherein, by collecting the current pharmaceutical product temperature influencing parameter collection frequency data set and the current pharmaceutical product deterioration rate data set, data support is provided for the subsequent construction of a pharmaceutical product deterioration rate mapping model; by constructing a pharmaceutical product deterioration rate mapping model, it is used to obtain the corresponding adjustment effect in the process of adjusting the frequency of collecting temperature influencing parameters, thereby ensuring the efficiency of the adjustment.

[0011] Preferably, the S322 includes the following steps: S3221, constructing an initial SVM model and setting a training data ratio; dividing the current pharmaceutical product temperature influence parameter acquisition frequency data set and the current pharmaceutical product deterioration rate data set according to the training data ratio to obtain a current pharmaceutical product temperature influence parameter acquisition frequency training data set, a current pharmaceutical product deterioration rate training data set, a current pharmaceutical product temperature influence parameter acquisition frequency test data set, and a current pharmaceutical product deterioration rate test data set; S3222, setting a training error threshold; inputting the current pharmaceutical product temperature influence parameter acquisition frequency training data set and the current pharmaceutical product deterioration rate training data set as training data and training labels into the initial SVM model for training; during the training process, when the training error is less than the training error threshold, stopping the training to obtain a trained SVM model; otherwise, continuing the training until the training error is less than the training error threshold; S3223, set a test accuracy threshold; input the current pharmaceutical product temperature impact parameter acquisition frequency test data set and the current pharmaceutical product deterioration rate test data set as test data and test labels respectively into the trained SVM model for testing; after the test is completed, obtain the test accuracy data; when the test accuracy data is greater than or equal to the test accuracy threshold, use the trained SVM model as the pharmaceutical product deterioration rate mapping model; otherwise, return to S3222 to continue training the trained SVM model until the test accuracy data is greater than or equal to the test accuracy threshold; The SVM model performs well on small sample data sets, can make full use of limited data for modeling and prediction, and has good adaptability to situations with small amounts of data; it has a certain tolerance for noise and outliers, and can still maintain good prediction performance when there is noise or outliers in the data; it has strict mathematical theory support, and its decision boundary is determined by maximizing the interval, so it has strong interpretability and can intuitively understand the classification or regression principles of the model; during the training process, it will automatically select the most important features for the classification or regression task, thereby simplifying the feature engineering process; based on the above advantages, the SVM model is used in this scheme to construct a mapping model between the collection frequency of the temperature-influencing parameters of pharmaceutical products and the deterioration rate data of pharmaceutical products after transportation, thereby ensuring the mapping accuracy.

[0012] Preferably, the S323 includes the following steps: S3231, setting the frequency range of collecting the temperature-affecting parameter data of the pharmaceutical product during the transportation of the current pharmaceutical product to be regulated, and obtaining the frequency range of collecting the temperature parameters of the current pharmaceutical product transportation. , , They respectively represent the lower limit and the upper limit of the frequency of collecting the temperature-affecting parameter data of the pharmaceutical products during the transportation of the pharmaceutical products to be regulated; Construct a frequency sampling and adjustment of monarch butterfly population by temperature-affecting parameters of pharmaceutical products; set the maximum number of iterations of frequency sampling and adjustment of monarch butterfly population by temperature-affecting parameters of pharmaceutical products to be And the current number of iterations is , respectively recorded as the maximum number of iterations of sampling frequency adjustment and the current number of iterations of sampling frequency adjustment; the search space dimension of the temperature-affecting parameter sampling frequency adjustment of the monarch butterfly population of the pharmaceutical product is 1 dimension; S3232, according to the current pharmaceutical product transportation temperature parameter collection frequency interval, set the pharmaceutical product temperature influence parameter collection frequency to adjust the initial position of each monarch butterfly in the monarch butterfly population, and obtain a second initial position set , Indicates that the temperature of the pharmaceutical product affects the frequency of the adjustment of the monarch butterfly population i The initial position of the monarch butterfly, It indicates that the temperature of the pharmaceutical product affects the frequency of the parameter sampling to adjust the size of the monarch butterfly population; The generation formula is as follows: ; In the formula, rand 2i Indicates for Generate a random number between 0 and 1; S3233, constructing the fitness function of the monarch butterfly population by frequency sampling of the temperature-affecting parameter of the pharmaceutical product d 2; as follows, ; In the formula, It represents the pharmaceutical product deterioration rate data obtained by substituting the frequency of the pharmaceutical product temperature influencing parameter data obtained in each round of iteration into the pharmaceutical product deterioration rate mapping model for mapping; S3234, start iteration, before iteration, set the sampling frequency adjustment current iteration number to 1; in the first round of iteration, use the temperature influence parameter of the pharmaceutical product to sample and adjust the fitness function of the monarch butterfly population d 2. Calculate the fitness value of each monarch butterfly's initial position in the second initial position set to obtain a third fitness value set; use the maximum fitness value in the third fitness value set and the initial position of the corresponding monarch butterfly as the third global optimal fitness and the third global optimal position respectively; update the initial position of each monarch butterfly in the second initial position set according to the third global optimal fitness and the third global optimal position; after the update is completed, add 1 to the current iteration number of the sampling frequency adjustment and enter the next round of iteration; In each other iteration process, the temperature influence parameter of the pharmaceutical product is used to adjust the fitness function of the monarch butterfly population. d 2. Calculate the fitness value of each monarch butterfly position in the monarch butterfly population of the temperature influence parameter of the pharmaceutical product updated in the previous round of iterations, and obtain a fourth fitness value set; use the maximum fitness value in the fourth fitness value set and the corresponding monarch butterfly position as the fourth global optimal fitness and the fourth global optimal position respectively; update the position of each monarch butterfly in the monarch butterfly population of the temperature influence parameter of the pharmaceutical product updated in the previous round of iterations according to the fourth global optimal fitness and the fourth global optimal position; after the update is completed, add 1 to the current iteration number of the frequency adjustment and enter the next round of iterations; S3235, when When , stop the iteration and get the second final global best fitness and the second final global best position; otherwise, continue to iterate until ; taking the second final global optimal fitness as the current optimized spoilage rate data, when the current optimized spoilage rate data is less than the drug spoilage rate threshold, taking the second final global optimal position as the current final pharmaceutical product temperature influencing parameter acquisition frequency; otherwise, returning to S3234 to continue iterating until the current optimized spoilage rate data is less than the drug spoilage rate threshold; In this scheme, the monarch butterfly optimization algorithm is used to iteratively adjust the frequency of collecting temperature influencing parameter data of the current pharmaceutical products to be regulated during transportation, and the deterioration rate data of the current pharmaceutical products to be regulated after transportation is completed is used as the fitness function; therefore, as the iteration proceeds, the deterioration rate data of the current pharmaceutical products to be regulated after transportation is completed becomes smaller and smaller, thereby minimizing the loss of pharmaceutical products during transportation.

[0013] The intelligent supervision system for the logistics and transportation status of pharmaceutical products based on cloud computing includes a pharmaceutical product temperature influence parameter type setting module, a current pharmaceutical product transportation temperature influence real-time parameter collection module, a historical pharmaceutical product transportation data collection module, a pharmaceutical product temperature monitoring frequency mapping equation construction module, a current real-time temperature parameter monitoring frequency mapping module, a deterioration rate mapping model construction module and a current pharmaceutical product temperature influence parameter collection frequency adjustment module.

[0014] The present invention has the following beneficial effects: 1. In the present invention, the frequency of collecting temperature data of the current pharmaceutical product is adjusted to ensure that the collected temperature data will not be missed, and the collection frequency is ensured to be within a reasonable range; based on the transportation data in the actual process, the collection frequency of the parameters affecting the temperature of the pharmaceutical product is adjusted, and the accuracy of the basis for adjusting the frequency of collecting temperature data of the current pharmaceutical product is further ensured, that is, it is further ensured that the collected temperature data will not be missed.

[0015] 2. The present invention collects historical data on the transportation of pharmaceutical products that meet the requirements, thereby ensuring the correctness of the source of the collected data, thereby ensuring the correctness of the subsequent final pharmaceutical product temperature monitoring frequency mapping equation.

[0016] 3. In the present invention, the monarch butterfly optimization algorithm is used to perform multiple iterative optimizations on multiple constant coefficients of the initial pharmaceutical product temperature monitoring frequency mapping equation, and the mapping accuracy of the initial pharmaceutical product temperature monitoring frequency mapping equation is used as the fitness function; therefore, as the iteration proceeds, the mapping accuracy of the initial pharmaceutical product temperature monitoring frequency mapping equation becomes higher and higher, and finally the mapping requirements are met.

[0017] 4. The present invention uses the monarch butterfly optimization algorithm to iteratively adjust the frequency of collecting temperature influencing parameter data of the current pharmaceutical products to be regulated during transportation for multiple times, and uses the deterioration rate data of the current pharmaceutical products to be regulated after transportation as the fitness function; therefore, as the iteration proceeds, the deterioration rate data of the current pharmaceutical products to be regulated after transportation becomes smaller and smaller, thereby minimizing the loss of pharmaceutical products during transportation.

[0018] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 It is a flow chart of the intelligent supervision method of the logistics and transportation status of pharmaceutical products based on cloud computing of the present invention; Figure 2 A schematic diagram of a process for constructing a frequency mapping equation for temperature monitoring of a final pharmaceutical product according to the present invention; Figure 3 A schematic diagram of a flow chart of adjusting the frequency of collecting temperature-affecting parameter data of pharmaceutical products during the transportation of the currently regulated pharmaceutical products according to the present invention; Figure 4 This is a module schematic diagram of the intelligent monitoring system for the logistics and transportation status of pharmaceutical products based on cloud computing of the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the invention to clearly and completely describe the technical solutions in the embodiments of the invention. Obviously, the described embodiments are only part of the embodiments of the invention, not all of the embodiments. Based on the embodiments in the invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the invention.

[0022] Embodiment 1 See also Figure 1-3 This embodiment is a method for intelligently supervising the logistics and transportation status of pharmaceutical products based on cloud computing, comprising the following steps: S1. Obtaining real-time temperature impact parameter data corresponding to the transportation of the current pharmaceutical product to be regulated, and obtaining the current real-time pharmaceutical product temperature impact parameter set; The S1 comprises the following steps: S11. Set several types of pharmaceutical product temperature monitoring frequencies to obtain a pharmaceutical product temperature monitoring frequency type set; the pharmaceutical product temperature monitoring frequency type set includes 1 time / minute, 10 times / second (transient recording) and continuous recording, etc.; then set several types of parameters that have an impact on the pharmaceutical product temperature to obtain a pharmaceutical product temperature impact parameter type set; the pharmaceutical product temperature impact parameter type set includes the standard deviation of the pharmaceutical product temperature data in the past hour, The frequency of starting and stopping the refrigeration unit, the transportation stage, such as loading and unloading, in transit and warehousing, etc., the altitude, the outside temperature, the wind speed, Drug thermal sensitivity (which can be measured by activation energy) and historical abnormality rate, etc.; the standard deviation of pharmaceutical product temperature data can be calculated using the temperature data collected by existing temperature sensors; loading and unloading, in-transit, and warehousing during the transportation stage are represented by natural numbers; the historical abnormality rate is the number of abnormal temperatures of pharmaceutical products along the same route in the past 30 days, etc.; S12, setting the current pharmaceutical product to be regulated; according to the pharmaceutical product temperature impact parameter type set, obtaining the real-time temperature impact parameter data corresponding to the transportation of the current pharmaceutical product to be regulated, and obtaining the current real-time pharmaceutical product temperature impact parameter set , a i Indicates the first i types of real-time temperature-affected parameter data, Indicates the total number of the set pharmaceutical product temperature-affecting parameter types; S2, collecting the temperature monitoring frequency data of several groups of pharmaceutical products in the transportation process and the corresponding temperature influencing parameter data of the pharmaceutical products in history and constructing the final pharmaceutical product temperature monitoring frequency mapping equation; The S2 comprises the following steps: S21, setting a threshold value for drug deterioration rate; in conjunction with the pharmaceutical product temperature monitoring frequency type set and the pharmaceutical product temperature influencing parameter type set, collecting pharmaceutical product temperature monitoring frequency data and corresponding pharmaceutical product temperature influencing parameter data corresponding to the result that the deterioration rate of several groups of pharmaceutical products after transportation is less than the pharmaceutical deterioration rate threshold in history, and obtaining a historical pharmaceutical product temperature monitoring frequency data set And the temperature impact parameter matrix of historical pharmaceutical products ; Indicates the collected j The temperature monitoring frequency data corresponding to the transportation process of pharmaceutical products in history is collected. Indicates the total number of groups of transportation processes of medical products collected in history; as follows, ; in, Indicates the collected j The transportation process of pharmaceutical products in the history of the group corresponds to the i Types of real-time temperature-affected parameter data; S22, constructing a final pharmaceutical product temperature monitoring frequency mapping equation using the historical pharmaceutical product temperature monitoring frequency data set and the historical pharmaceutical product temperature influence parameter matrix; The S22 comprises the following steps: S221, constructing an initial pharmaceutical product temperature monitoring frequency mapping equation in conjunction with the pharmaceutical product temperature monitoring frequency type set and the pharmaceutical product temperature influencing parameter type set; as follows, ; in, b 1 is the dependent variable of the initial pharmaceutical product temperature monitoring frequency mapping equation, representing the pharmaceutical product temperature monitoring frequency data; b 2 is the mapping relationship of the initial pharmaceutical product temperature monitoring frequency mapping equation, which represents the quantitative relationship between each independent variable and the dependent variable in the initial pharmaceutical product temperature monitoring frequency mapping equation; if the standard deviation of the pharmaceutical product temperature data is positively correlated with the pharmaceutical product temperature monitoring frequency data, the larger the standard deviation of the pharmaceutical product temperature data, the larger the pharmaceutical product temperature monitoring frequency data should be; b 3i is the first part of the initial pharmaceutical product temperature monitoring frequency mapping equation i The independent variable represents i Types of temperature-affected parameter data; S222, substituting each row of data in the historical pharmaceutical product temperature influence parameter matrix into the initial pharmaceutical product temperature monitoring frequency mapping equation for mapping, to obtain a historical pharmaceutical product temperature monitoring frequency mapping data set , Indicates that the temperature impact parameter matrix of historical pharmaceutical products j Substitute the row data into the initial medical product temperature monitoring frequency mapping equation to map the resulting data; S223, setting a pharmaceutical product temperature monitoring frequency mapping error threshold; calculating the error data between the historical pharmaceutical product temperature monitoring frequency mapping data set and the historical pharmaceutical product temperature monitoring frequency data set, and obtaining the historical temperature monitoring frequency mapping error data. ;as follows, ; When the historical temperature monitoring frequency mapping error data is greater than or equal to the pharmaceutical product temperature monitoring frequency mapping error threshold, the initial pharmaceutical product temperature monitoring frequency mapping equation is adjusted until the historical temperature monitoring frequency mapping error data is less than the pharmaceutical product temperature monitoring frequency mapping error threshold; otherwise, there is no need to adjust the initial pharmaceutical product temperature monitoring frequency mapping equation, and the initial pharmaceutical product temperature monitoring frequency mapping equation is used as the final pharmaceutical product temperature monitoring frequency mapping equation; The adjustment of the initial pharmaceutical product temperature monitoring frequency mapping equation in S223 includes the following steps: S2231, setting the value intervals of each constant coefficient in the initial pharmaceutical product temperature monitoring frequency mapping equation, and obtaining a set of value intervals of the temperature monitoring frequency mapping constant coefficients. ;as follows, ; in, , Respectively represent the first i The lower and upper limits of the constant coefficients, c represents the total number of constant coefficients in the initial pharmaceutical product temperature monitoring frequency mapping equation; Construct a medicine product temperature monitoring frequency mapping to adjust the monarch butterfly population; set the maximum number of iterations of the medicine product temperature monitoring frequency mapping to adjust the monarch butterfly population to And the current iteration number is , respectively recorded as the maximum number of iterations of frequency adjustment and the current number of iterations of frequency adjustment; the temperature monitoring frequency mapping of pharmaceutical products adjusts the search space dimension of the monarch butterfly population and c same; S2232: Setting the temperature monitoring frequency mapping of pharmaceutical products according to the temperature monitoring frequency mapping constant coefficient value interval set, adjusting the initial position of each monarch butterfly in the monarch butterfly population, and obtaining a first initial position matrix ;as follows, ; in, Indicates that the pharmaceutical product temperature monitoring frequency mapping adjusts the monarch butterfly population j The initial position of the monarch butterfly is the first in the initial pharmaceutical product temperature monitoring frequency mapping equation. i The position component in the dimension of constant coefficients, Indicates that the pharmaceutical product temperature monitoring frequency mapping adjusts the size of the monarch butterfly population; The generation formula is as follows: ; In the formula, rand 1ji Indicates for Generate a random number between 0 and 1; S2233, constructing the fitness function of the temperature monitoring frequency mapping of the pharmaceutical product to adjust the monarch butterfly population d 1; as follows, ; In the formula, It means that a set of constant coefficients obtained in each round of iteration is substituted into the initial pharmaceutical product temperature monitoring frequency mapping equation, and then each row of data in the historical pharmaceutical product temperature influence parameter matrix is ​​substituted into the initial pharmaceutical product temperature monitoring frequency mapping equation to map and obtain the error between the data and the actual data; S2234, start iteration, before iteration, set the frequency adjustment current iteration number to 1; in the first round of iteration, use the pharmaceutical product temperature monitoring frequency mapping to adjust the fitness function of the monarch butterfly population d 1. Calculate the fitness value of each monarch butterfly's initial position in the first initial position matrix to obtain a first fitness value set; use the maximum fitness value in the first fitness value set and the initial position of the corresponding monarch butterfly as the first global optimal fitness and the first global optimal position respectively; update the initial position of each monarch butterfly in the first initial position matrix according to the first global optimal fitness and the first global optimal position; after the update is completed, add 1 to the current iteration number of the frequency adjustment and enter the next iteration; In each other iteration, the temperature monitoring frequency mapping of the pharmaceutical product is used to adjust the fitness function of the monarch butterfly population. d 1. Calculate the fitness value of each monarch butterfly position in the monarch butterfly population adjusted by the temperature monitoring frequency mapping of pharmaceutical products updated in the previous iteration process to obtain a second fitness value set; take the maximum fitness value in the second fitness value set and the corresponding monarch butterfly position as the second global optimal fitness and the second global optimal position respectively; update the monarch butterfly population adjusted by the temperature monitoring frequency mapping of pharmaceutical products updated in the previous iteration process at each monarch butterfly position according to the second global optimal fitness and the second global optimal position; after the update is completed, add 1 to the current iteration number of the frequency adjustment and enter the next iteration; S2235, when When , stop the iteration and get the first final global best position and the first final global best fitness; otherwise, continue to iterate until until the time; The first final global optimal fitness is used as the optimized historical temperature monitoring frequency mapping error data. When the optimized historical temperature monitoring frequency mapping error data is less than the pharmaceutical product temperature monitoring frequency mapping error threshold, each position component of the first final global optimal position is substituted into the pharmaceutical product temperature monitoring frequency mapping equation to obtain the final pharmaceutical product temperature monitoring frequency mapping equation; otherwise, return to S2234 to continue iterating until the optimized historical temperature monitoring frequency mapping error data is less than the pharmaceutical product temperature monitoring frequency mapping error threshold; S3. Use the final pharmaceutical product temperature monitoring frequency mapping equation to map the current real-time pharmaceutical product temperature influence parameter set to obtain the current real-time pharmaceutical product temperature monitoring frequency data; collect the frequency data of the pharmaceutical product temperature influence parameter data collected during the current transportation of pharmaceutical products and the pharmaceutical product deterioration rate data after the corresponding transportation is completed to construct a pharmaceutical product deterioration rate mapping model; adjust the frequency of collecting the pharmaceutical product temperature influence parameter data during the transportation of the current pharmaceutical products to be regulated in accordance with the current real-time pharmaceutical product temperature monitoring frequency data and the pharmaceutical product deterioration rate mapping model to obtain the current final pharmaceutical product temperature influence parameter collection frequency; The S3 comprises the following steps: S31, substituting the current real-time pharmaceutical product temperature influence parameter set into the final pharmaceutical product temperature monitoring frequency mapping equation for mapping, to obtain the current real-time pharmaceutical product temperature monitoring frequency data; S32, monitoring the temperature of the current pharmaceutical product to be regulated during transportation according to the current real-time pharmaceutical product temperature monitoring frequency data; after the current pharmaceutical product to be regulated is transported, collecting the deterioration rate data of the current pharmaceutical product to be regulated to obtain the current deterioration rate data; When the current deterioration rate data is greater than or equal to the drug deterioration rate threshold, the frequency of collecting the temperature impact parameter data of the current pharmaceutical product to be regulated during transportation is adjusted to obtain the current final pharmaceutical product temperature impact parameter collection frequency; otherwise, no adjustment is required; In S32, adjusting the frequency of collecting the temperature-affecting parameter data of the pharmaceutical product during the transportation of the current pharmaceutical product to be regulated includes the following steps: S321, collecting frequency data of the temperature-affecting parameter data of the pharmaceutical products during the current transportation of the pharmaceutical products and the deterioration rate data of the pharmaceutical products after the corresponding transportation is completed, and obtaining the current pharmaceutical product temperature-affecting parameter collection frequency data set and the current pharmaceutical product deterioration rate dataset , , Respectively represent the collected i The frequency data of collecting the temperature-affecting parameter data of the pharmaceutical products during the transportation of the pharmaceutical products and the deterioration rate data of the pharmaceutical products after the transportation is completed. Indicates the total number of times the pharmaceutical products are currently transported; S322, constructing a pharmaceutical product deterioration rate mapping model using the current pharmaceutical product temperature influencing parameter acquisition frequency data set and the current pharmaceutical product deterioration rate data set; The S322 includes the following steps: S3221, constructing an initial SVM model and setting a training data ratio; dividing the current pharmaceutical product temperature influence parameter acquisition frequency data set and the current pharmaceutical product deterioration rate data set according to the training data ratio to obtain a current pharmaceutical product temperature influence parameter acquisition frequency training data set, a current pharmaceutical product deterioration rate training data set, a current pharmaceutical product temperature influence parameter acquisition frequency test data set, and a current pharmaceutical product deterioration rate test data set; S3222, setting a training error threshold; inputting the current pharmaceutical product temperature influence parameter acquisition frequency training data set and the current pharmaceutical product deterioration rate training data set as training data and training labels into the initial SVM model for training; during the training process, when the training error is less than the training error threshold, stopping the training to obtain a trained SVM model; otherwise, continuing the training until the training error is less than the training error threshold; S3223, set a test accuracy threshold; input the current pharmaceutical product temperature impact parameter acquisition frequency test data set and the current pharmaceutical product deterioration rate test data set as test data and test labels respectively into the trained SVM model for testing; after the test is completed, obtain the test accuracy data; when the test accuracy data is greater than or equal to the test accuracy threshold, use the trained SVM model as the pharmaceutical product deterioration rate mapping model; otherwise, return to S3222 to continue training the trained SVM model until the test accuracy data is greater than or equal to the test accuracy threshold; S323, adjusting the frequency of collecting the temperature influence parameter data of the pharmaceutical product during the transportation of the current pharmaceutical product to be regulated in cooperation with the pharmaceutical product deterioration rate mapping model, until the current deterioration rate data is less than the pharmaceutical deterioration rate threshold; The S323 comprises the following steps: S3231, setting the frequency range of collecting the temperature-affecting parameter data of the pharmaceutical product during the transportation of the current pharmaceutical product to be regulated, and obtaining the frequency range of collecting the temperature parameters of the current pharmaceutical product transportation. , , They respectively represent the lower limit and the upper limit of the frequency of collecting the temperature-affecting parameter data of the pharmaceutical products during the transportation of the pharmaceutical products to be regulated; Construct a frequency sampling and adjustment of monarch butterfly population by temperature-affecting parameters of pharmaceutical products; set the maximum number of iterations of frequency sampling and adjustment of monarch butterfly population by temperature-affecting parameters of pharmaceutical products to be And the current iteration number is , respectively recorded as the maximum number of iterations of sampling frequency adjustment and the current number of iterations of sampling frequency adjustment; the search space dimension of the temperature-affecting parameter sampling frequency adjustment of the monarch butterfly population of the pharmaceutical product is 1 dimension; S3232, according to the current pharmaceutical product transportation temperature parameter collection frequency interval, set the pharmaceutical product temperature influence parameter collection frequency to adjust the initial position of each monarch butterfly in the monarch butterfly population, and obtain a second initial position set , Indicates that the temperature of the pharmaceutical product affects the frequency of the adjustment of the monarch butterfly population i The initial position of the monarch butterfly, It indicates that the temperature of the pharmaceutical product affects the frequency of the parameter sampling to adjust the size of the monarch butterfly population; The generation formula is as follows: ; In the formula, rand 2i Indicates for Generate a random number between 0 and 1; S3233, constructing the fitness function of the monarch butterfly population by frequency sampling of the temperature-affecting parameter of the pharmaceutical product d 2; as follows, ; In the formula, It represents the pharmaceutical product deterioration rate data obtained by substituting the frequency of the pharmaceutical product temperature influencing parameter data obtained in each round of iteration into the pharmaceutical product deterioration rate mapping model for mapping; S3234, start iteration, before iteration, set the sampling frequency adjustment current iteration number to 1; in the first round of iteration, use the temperature influence parameter of the pharmaceutical product to sample and adjust the fitness function of the monarch butterfly population d 2. Calculate the fitness value of each monarch butterfly's initial position in the second initial position set to obtain a third fitness value set; use the maximum fitness value in the third fitness value set and the initial position of the corresponding monarch butterfly as the third global optimal fitness and the third global optimal position respectively; update the initial position of each monarch butterfly in the second initial position set according to the third global optimal fitness and the third global optimal position; after the update is completed, add 1 to the current iteration number of the sampling frequency adjustment and enter the next round of iteration; In each other iteration process, the temperature influence parameter of the pharmaceutical product is used to adjust the fitness function of the monarch butterfly population. d2. Calculate the fitness value of each monarch butterfly position in the monarch butterfly population of the temperature influence parameter of the pharmaceutical product updated in the previous round of iterations, and obtain a fourth fitness value set; use the maximum fitness value in the fourth fitness value set and the corresponding monarch butterfly position as the fourth global optimal fitness and the fourth global optimal position respectively; update the position of each monarch butterfly in the monarch butterfly population of the temperature influence parameter of the pharmaceutical product updated in the previous round of iterations according to the fourth global optimal fitness and the fourth global optimal position; after the update is completed, add 1 to the current iteration number of the frequency adjustment and enter the next round of iterations; S3235, when When , stop the iteration and get the second final global best fitness and the second final global best position; otherwise, continue to iterate until until the time comes; the second final global optimal fitness is used as the current optimized spoilage rate data, and when the current optimized spoilage rate data is less than the drug spoilage rate threshold, the second final global optimal position is used as the current final pharmaceutical product temperature influencing parameter collection frequency; otherwise, return to S3234 to continue iterating until the current optimized spoilage rate data is less than the drug spoilage rate threshold; wherein, the distributed storage technology in the cloud computing technology can be used to support the process of using the monarch butterfly optimization algorithm to iteratively adjust the frequency of collecting pharmaceutical product temperature influencing parameter data during the transportation of the current pharmaceutical products to be regulated; such as Google's Bigtable, Amazon's DynamoDB, etc., to support the storage and efficient access of massive data.

[0023] Embodiment 2 See also Figure 4 , this embodiment discloses a pharmaceutical product logistics transportation status intelligent supervision system based on cloud computing, the system can implement the method of the above embodiment, including a pharmaceutical product temperature influence parameter type setting module, a current pharmaceutical product transportation temperature influence real-time parameter acquisition module, a historical pharmaceutical product transportation data acquisition module, a pharmaceutical product temperature monitoring frequency mapping equation construction module, a current real-time temperature parameter monitoring frequency mapping module, a deterioration rate mapping model construction module and a current pharmaceutical product temperature influence parameter acquisition frequency adjustment module; The pharmaceutical product temperature influence parameter type setting module sets several parameter types that have an influence on the pharmaceutical product temperature to obtain a pharmaceutical product temperature influence parameter type set; The current pharmaceutical product transportation temperature impact real-time parameter acquisition module cooperates with the pharmaceutical product temperature impact parameter type set to obtain real-time temperature impact parameter data corresponding to the transportation of the current pharmaceutical product to be regulated, and obtains the current real-time pharmaceutical product temperature impact parameter set; The historical pharmaceutical product transportation data collection module cooperates with the pharmaceutical product temperature impact parameter type set to collect pharmaceutical product temperature monitoring frequency data and corresponding pharmaceutical product temperature impact parameter data of several groups of pharmaceutical products in the transportation process in history, and obtains a historical pharmaceutical product temperature monitoring frequency data set and a historical pharmaceutical product temperature impact parameter matrix; The pharmaceutical product temperature monitoring frequency mapping equation construction module uses the historical pharmaceutical product temperature monitoring frequency data set and the historical pharmaceutical product temperature impact parameter matrix to construct the final pharmaceutical product temperature monitoring frequency mapping equation; The current real-time temperature parameter monitoring frequency mapping module uses the final pharmaceutical product temperature monitoring frequency mapping equation to map the current real-time pharmaceutical product temperature influence parameter set to obtain the current real-time pharmaceutical product temperature monitoring frequency data; The deterioration rate mapping model building module builds a pharmaceutical product deterioration rate mapping model by collecting frequency data of pharmaceutical product temperature influencing parameter data collected during the current transportation of pharmaceutical products for multiple times and pharmaceutical product deterioration rate data after the corresponding transportation is completed; The current pharmaceutical product temperature influencing parameter collection frequency adjustment module cooperates with the current real-time pharmaceutical product temperature monitoring frequency data and the pharmaceutical product deterioration rate mapping model to adjust the frequency of collecting pharmaceutical product temperature influencing parameter data during the transportation of the current pharmaceutical product to be regulated, and obtains the current final pharmaceutical product temperature influencing parameter collection frequency.

[0024] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0025] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.

Claims

1. A cloud computing-based intelligent supervision method for the logistics and transportation status of pharmaceutical products, characterized in that: The following steps are involved: S1. Obtaining real-time temperature impact parameter data corresponding to the transportation of the current pharmaceutical product to be regulated, and obtaining the current real-time pharmaceutical product temperature impact parameter set; S2, collecting the temperature monitoring frequency data of several groups of pharmaceutical products in the transportation process and the corresponding temperature influencing parameter data of the pharmaceutical products in history and constructing the final pharmaceutical product temperature monitoring frequency mapping equation; S3. Use the final pharmaceutical product temperature monitoring frequency mapping equation to map the current real-time pharmaceutical product temperature influencing parameter set to obtain the current real-time pharmaceutical product temperature monitoring frequency data; collect the frequency data of the pharmaceutical product temperature influencing parameter data collected during the current pharmaceutical product transportation process and the corresponding pharmaceutical product deterioration rate data after the transportation is completed to construct a pharmaceutical product deterioration rate mapping model; adjust the frequency of collecting the pharmaceutical product temperature influencing parameter data during the current transportation of the pharmaceutical product to be regulated in conjunction with the current real-time pharmaceutical product temperature monitoring frequency data and the pharmaceutical product deterioration rate mapping model to obtain the current final pharmaceutical product temperature influencing parameter collection frequency.

2. The method for intelligently supervising the logistics and transportation status of pharmaceutical products based on cloud computing according to claim 1 is characterized in that: The S1 comprises the following steps: S11, setting several types of medical product temperature monitoring frequencies to obtain a medical product temperature monitoring frequency type set; and then setting several types of parameters that have an impact on the temperature of the medical product to obtain a medical product temperature impact parameter type set; S12, setting the current pharmaceutical product to be regulated; obtaining the real-time temperature impact parameter data corresponding to the transportation of the current pharmaceutical product to be regulated according to the pharmaceutical product temperature impact parameter type set, and obtaining the current real-time pharmaceutical product temperature impact parameter set.

3. The method for intelligently supervising the logistics and transportation status of pharmaceutical products based on cloud computing according to claim 2 is characterized in that: The S2 comprises the following steps: S21, setting a threshold value for drug deterioration rate; in conjunction with the pharmaceutical product temperature monitoring frequency type set and the pharmaceutical product temperature influence parameter type set, collecting pharmaceutical product temperature monitoring frequency data and corresponding pharmaceutical product temperature influence parameter data corresponding to the result that the deterioration rate of several groups of pharmaceutical products after transportation is less than the pharmaceutical deterioration rate threshold in history, and obtaining a historical pharmaceutical product temperature monitoring frequency data set and a historical pharmaceutical product temperature influence parameter matrix; S22. Constructing a final pharmaceutical product temperature monitoring frequency mapping equation using the historical pharmaceutical product temperature monitoring frequency data set and the historical pharmaceutical product temperature impact parameter matrix.

4. The method for intelligently supervising the logistics and transportation status of pharmaceutical products based on cloud computing according to claim 3 is characterized in that: The S22 comprises the following steps: S221, constructing an initial pharmaceutical product temperature monitoring frequency mapping equation in conjunction with the pharmaceutical product temperature monitoring frequency type set and the pharmaceutical product temperature influencing parameter type set; S222, substituting each row of data in the historical pharmaceutical product temperature influence parameter matrix into the initial pharmaceutical product temperature monitoring frequency mapping equation for mapping, to obtain a historical pharmaceutical product temperature monitoring frequency mapping data set; S223, setting a pharmaceutical product temperature monitoring frequency mapping error threshold; calculating the error data between the historical pharmaceutical product temperature monitoring frequency mapping data set and the historical pharmaceutical product temperature monitoring frequency data set to obtain the historical temperature monitoring frequency mapping error data; When the historical temperature monitoring frequency mapping error data is greater than or equal to the pharmaceutical product temperature monitoring frequency mapping error threshold, the initial pharmaceutical product temperature monitoring frequency mapping equation is adjusted until the historical temperature monitoring frequency mapping error data is less than the pharmaceutical product temperature monitoring frequency mapping error threshold; otherwise, there is no need to adjust the initial pharmaceutical product temperature monitoring frequency mapping equation, and the initial pharmaceutical product temperature monitoring frequency mapping equation is used as the final pharmaceutical product temperature monitoring frequency mapping equation.

5. The method for intelligently supervising the logistics and transportation status of pharmaceutical products based on cloud computing according to claim 4 is characterized in that: In S223, the initial pharmaceutical product temperature monitoring frequency mapping equation is adjusted using a monarch butterfly optimization algorithm.

6. The method for intelligently supervising the logistics and transportation status of pharmaceutical products based on cloud computing according to claim 5 is characterized in that: The S3 comprises the following steps: S31, substituting the current real-time pharmaceutical product temperature influence parameter set into the final pharmaceutical product temperature monitoring frequency mapping equation for mapping, to obtain the current real-time pharmaceutical product temperature monitoring frequency data; S32, monitoring the temperature of the current pharmaceutical product to be regulated during transportation according to the current real-time pharmaceutical product temperature monitoring frequency data; after the current pharmaceutical product to be regulated is transported, collecting the deterioration rate data of the current pharmaceutical product to be regulated to obtain the current deterioration rate data; When the current deterioration rate data is greater than or equal to the drug deterioration rate threshold, the frequency of collecting the temperature impact parameter data of the current pharmaceutical product to be regulated during transportation is adjusted to obtain the current final pharmaceutical product temperature impact parameter collection frequency; otherwise, no adjustment is required.

7. The method for intelligently supervising the logistics and transportation status of pharmaceutical products based on cloud computing according to claim 6 is characterized in that: In S32, adjusting the frequency of collecting the temperature-affecting parameter data of the pharmaceutical product during the transportation of the current pharmaceutical product to be regulated includes the following steps: S321, collecting frequency data of collecting temperature-affecting parameter data of pharmaceutical products during the current transportation of pharmaceutical products and corresponding pharmaceutical product deterioration rate data after the transportation is completed, to obtain a current pharmaceutical product temperature-affecting parameter collection frequency data set and a current pharmaceutical product deterioration rate data set; S322, constructing a pharmaceutical product deterioration rate mapping model using the current pharmaceutical product temperature influencing parameter acquisition frequency data set and the current pharmaceutical product deterioration rate data set; S323. Adjust the frequency of collecting the temperature influence parameter data of the pharmaceutical products during the transportation of the current pharmaceutical products to be regulated in cooperation with the pharmaceutical product deterioration rate mapping model until the current deterioration rate data is less than the pharmaceutical deterioration rate threshold.

8. The method for intelligently supervising the logistics and transportation status of pharmaceutical products based on cloud computing according to claim 7 is characterized in that: The pharmaceutical product deterioration rate mapping model described in S322 adopts the SVM model.

9. The method for intelligently supervising the logistics and transportation status of pharmaceutical products based on cloud computing according to claim 8, characterized in that: The S323 comprises the following steps: S3231, setting the frequency range of collecting the temperature influence parameter data of the pharmaceutical product during the transportation of the current pharmaceutical product to be regulated, and obtaining the frequency range of collecting the temperature parameter of the current pharmaceutical product transportation; constructing the frequency sampling of the pharmaceutical product temperature influence parameter to adjust the monarch butterfly population; setting the maximum number of iterations of the pharmaceutical product temperature influence parameter frequency sampling to adjust the monarch butterfly population is And the current number of iterations is , respectively recorded as the maximum number of iterations of frequency sampling adjustment and the current number of iterations of frequency sampling adjustment; S3232, setting the frequency range of the temperature parameter collection of the pharmaceutical product temperature influencing parameters according to the current pharmaceutical product transportation temperature parameter collection frequency, adjusting the initial position of each monarch butterfly in the monarch butterfly population, and obtaining a second initial position set; S3233, constructing the fitness function of the monarch butterfly population by adjusting the frequency sampling of the temperature-affecting parameters of the pharmaceutical product; S3234, start iteration; in each round of iteration, use the fitness function of the frequency sampling of the temperature-influencing parameters of the pharmaceutical product to adjust the monarch butterfly population to calculate the fitness value of each monarch butterfly position in the frequency sampling of the temperature-influencing parameters of the pharmaceutical product updated in the previous round of iteration, and update each monarch butterfly position in the frequency sampling of the temperature-influencing parameters of the pharmaceutical product updated in the previous round of iteration; S3235, when When , stop the iteration and get the second final global best fitness and the second final global best position; otherwise, continue to iterate until until the time comes; use the second final global optimal fitness as the current optimized deterioration rate data; when the current optimized deterioration rate data is less than the drug deterioration rate threshold, use the second final global optimal position as the current final pharmaceutical product temperature influencing parameter acquisition frequency; otherwise, return to S3234 to continue iterating until the current optimized deterioration rate data is less than the drug deterioration rate threshold.

10. A system for implementing the method for intelligently supervising the logistics and transportation status of pharmaceutical products based on cloud computing as described in any one of claims 1 to 9.

Images