A pharmaceutical logistics and shipping management cloud platform

Abstract

The present invention discloses a pharmaceutical logistics and dispatching management cloud platform, which relates to the field of logistics technology. The present invention will establish a multi-level temperature warning, and provide different warning levels and processing solutions for the situations that the temperature approaches a threshold, exceeds the standard for a short time, and exceeds the standard for a long time respectively; when the warning is triggered, the system automatically analyzes and provides processing solution suggestions, including adjusting the temperature control equipment and changing the transportation route; according to the characteristics of different medicines, including sensitive temperature range and humidity requirements, personalized transportation and storage solutions are customized; smart labels are adopted, and each medicine is equipped with a smart label RFID, and the label records the characteristics of the medicine and real-time environmental data, so as to facilitate logistics personnel to adjust the transportation conditions; the problem that the existing technology only issues an alarm when the temperature exceeds the standard, the reaction speed is slow, and a specific processing solution cannot be provided, and transportation guarantee cannot be provided according to the specific needs of different medicines, resulting in that some medicines cannot be optimally protected during transportation is solved.

Description

Technical Field

[0001] The present invention relates to the field of logistics technology, and in particular to a pharmaceutical logistics delivery management cloud platform. Background Art

[0002] The so-called pharmaceutical logistics relies on logistics equipment, technology and logistics management information systems, integrates upstream and downstream resources of marketing channels, and optimizes the acceptance, storage, sorting, distribution and other operations in the supply and distribution of drugs to improve order processing capabilities, reduce cargo sorting errors, shorten inventory and delivery time, reduce logistics costs, and improve service levels and capital utilization efficiency, thereby achieving automation, informatization and efficiency.

[0003] For example, the patent with publication number CN114188764A discloses an electronic device system and a charging device thereof; wherein the charging device comprises: a housing, a circuit board, an elastic probe and a probe protection mechanism; the housing forms a containing space, and an opening is provided on one side of the housing; the circuit board is arranged in the containing space; the elastic probe comprises a connecting end and a contact end arranged oppositely; the connecting end is connected to the circuit board, and the contact end protrudes from the housing through the opening to charge the electronic device to be charged by contact connection; the probe protection mechanism at least covers the contact end of the elastic probe, the probe protection mechanism is elastically connected to the housing or the circuit board, and can be elastically moved under the action of external force to shield or expose the contact end of the elastic probe; the charging device can shield and protect the contact end of the elastic probe by designing a probe protection mechanism, effectively preventing the short circuit of the charging device and the corrosion and physical damage of the contact end of the elastic probe; it has the characteristics of simple structure and convenient operation;

[0004] However, in traditional pharmaceutical logistics and shipping management cloud platforms, the early warning mechanism for the pharmaceutical transportation process only issues an alarm when the temperature exceeds the standard, the response speed is slow, and no specific treatment plan can be provided. In addition, pharmaceutical cold chain transportation mostly adopts a unified standard, and cannot provide transportation guarantees according to the specific needs of different drugs, resulting in some drugs not being optimally protected during transportation. Therefore, there is an urgent need for a pharmaceutical logistics and shipping management cloud platform that provides different transportation plans for different drugs to solve such problems. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a pharmaceutical logistics and shipping management cloud platform to solve the problem that the early warning mechanism of the pharmaceutical transportation process in the prior art only issues an alarm when the temperature exceeds the standard, the response speed is slow, and no specific processing solution can be provided; in addition, pharmaceutical cold chain transportation mostly adopts a unified standard, and cannot provide transportation guarantees according to the specific needs of different drugs, resulting in some drugs not being optimally protected during transportation.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0007] The present invention provides a pharmaceutical logistics delivery management cloud platform, including:

[0008] Pharmaceutical transportation data collection and monitoring module, including:

[0009] Environmental data acquisition unit, used to monitor the drug transportation environment in real time, equipped with temperature sensors, humidity sensors, vibration sensors and light sensors.

[0010] Smart labeling unit, equipped with smart labels for each batch of drugs, recording drug characteristics and real-time environmental data;

[0011] Edge computing unit, deploy edge computing nodes on transport vehicles to perform data preprocessing and preliminary analysis;

[0012] Pharmaceutical logistics data processing module, including:

[0013] Cleaning and analysis unit;

[0014] The machine learning unit trains historical data based on the machine learning algorithm RNN to establish a prediction model; based on real-time data and the prediction model, it predicts the trend of temperature environment parameters;

[0015] Early warning response module, including:

[0016] Multi-level warning unit, which sets multi-level temperature thresholds according to the characteristics of drugs and triggers different levels of warning notifications;

[0017] Automated emergency response unit, which automatically executes emergency response plans through smart contracts;

[0018] Personalized medicine management module, including:

[0019] Drug characteristics management unit to generate personalized transportation plans;

[0020] Dynamic adjustment unit, dynamically adjust the transportation plan;

[0021] Medical data storage module, including:

[0022] Blockchain storage unit;

[0023] Data traceability unit, traces back every link from production to use.

[0024] The present invention is further configured to establish a multi-level temperature warning in the multi-level warning unit:

[0025] Monitor temperature data in real time during drug transportation and perform temperature data analysis, triggering early warnings based on temperature data analysis;

[0026] Define temperature thresholds and warning levels, and set the allowable temperature range for drugs during transportation;

[0027] The warning levels are:

[0028] Approaching threshold: The temperature is close to but not beyond the allowable range, triggering warning level 1;

[0029] Temporary over-limit: The temperature temporarily exceeds the allowable range, but the time is short, triggering the second warning level;

[0030] Long-term over-limit: The temperature exceeds the allowable range for a long time, triggering the warning level 3;

[0031] The present invention is further configured that the temperature data analysis method is:

[0032] Clean and format data in edge computing node units to remove outliers and noise data;

[0033] Use machine learning algorithm RNN to analyze and predict temperature data in real time;

[0034] According to the set temperature threshold and analysis results, the corresponding level of warning notification is triggered;

[0035] Warning notifications include:

[0036] When the threshold is approached, the warning level 1 is triggered: remind relevant personnel to pay attention to temperature changes; check the temperature control equipment;

[0037] When the temperature exceeds the limit for a short period of time, the warning level 2 is triggered: notify relevant personnel by phone; check and adjust the temperature control equipment settings, and record abnormal temperature events on the cloud platform;

[0038] If the temperature exceeds the standard for a long time, the warning level 3 will be triggered: notify all relevant parties by phone and monitor the processing process in real time; adjust the working status of the cold chain equipment or replace the spare cold chain equipment; at the same time, change the transportation route as needed to avoid further increase in temperature

[0039] The present invention is further configured such that the early warning notification triggering mode is specifically:

[0040] Define temperature threshold range: set normal temperature range as Tmin, Tmax, Where Tmin is the lowest temperature allowed for the drug, Tmax is the highest temperature allowed for the drug, Ti is the ith temperature data point, and n represents the total number of data points;

[0041] The three-times standard deviation method was used to eliminate outliers. Where μT represents the mean of temperature data, and σT represents the standard deviation of temperature data;

[0042] Normalize the temperature data: Where Tnmld,i represents the i-th standardized temperature data;

[0043] Use recurrent neural network (RNN) to analyze and predict temperature data in real time, and take the cleaned temperature data sequence as input: X = {Tnmld,1, Tnmld,2,...Tnmld,n};

[0044] Hidden layer: ht = tanh(Wxhxt + Whhht-1 + bh), where ht is the hidden layer state at time t, Wxh represents the weight matrix input to the hidden layer, Whh is the weight matrix from hidden layer to hidden layer, xt represents the input data at time t, and bh is the bias of the hidden layer;

[0045] Output layer: in represents the predicted temperature value at the future time t+1, Who is the weight matrix from the hidden layer to the output layer, and bo represents the bias of the output layer;

[0046] According to the set temperature threshold and analysis results, the corresponding level of warning notification is triggered;

[0047] The present invention is further configured to automatically analyze and provide treatment plan suggestions when an early warning is triggered, specifically:

[0048] Build an intelligent decision support system to provide processing suggestions based on historical data and rule base;

[0049] Dynamically adjust treatment plans based on real-time data and forecast results;

[0050] Use smart contracts to automatically execute preset emergency response plans;

[0051] Dynamically adjust cold chain equipment and transportation routes based on real-time data and forecast results;

[0052] The present invention is further configured to collect and pre-process historical transportation data and real-time environmental data in the personalized medicine management module;

[0053] Define processing rules, use Bayesian decision networks and dynamic adjustment modules, combine real-time data and prediction results, and provide processing solutions;

[0054] Use smart contracts to automatically execute treatment plans based on warning levels;

[0055] Adjust temperature control equipment and transportation routes based on real-time data;

[0056] The present invention is further configured that the intelligent decision support system is constructed in the following manner:

[0057] Collect historical transportation data, including temperature, humidity, light environment parameters, and corresponding treatment measures and results, and perform data preprocessing;

[0058] Build a rule base:

[0059] When the temperature approaches the threshold, remind relevant personnel to pay attention to temperature changes and check the temperature control equipment;

[0060] When the temperature exceeds the limit briefly, notify relevant personnel by phone and check and adjust the temperature control equipment settings;

[0061] When the temperature exceeds the standard for a long time, adjust the working status of the cold chain equipment or replace the spare cold chain equipment, and change the transportation route;

[0062] Use logical rules to represent processing rules, calculate the posterior probabilities of different processing solutions based on historical data and real-time data, and select the optimal solution: Here P(AB) represents the posterior probability of event A under condition B, P(BA) represents the probability of B when event A occurs, P(A) is the prior probability of event A, and P(B) is the prior probability of condition B;

[0063] The present invention is further configured such that the dynamic adjustment unit receives and processes environmental sensor data in real time: Here Tt is the temperature at time t,

[0064] Ht is the humidity at time t, Lt is the light intensity at time t, and k represents the total number of time steps;

[0065] Adjust the set value of the temperature control device according to the real-time data, Tset = Tcurrent + α (Ttarget - Tcurrent), where Tset is the new set value of the temperature control device, Tcurrent is the current temperature, Ttarget represents the target temperature, and α is the adjustment coefficient;

[0066] Re-plan the transportation route using the shortest path algorithm, Here d(vi,vi+1) represents the distance between the i-th and i+1-th nodes in the path, and n is the total number of nodes in the path;

[0067] The present invention is further configured such that a database containing all drug information is established in the drug characteristic management unit, the temperature range, humidity requirements, and light condition characteristics of each drug are recorded, and the characteristic information of each drug is input:

[0068] Use RFID smart tags to record and transmit drug characteristics and real-time environmental data;

[0069] Equip each drug with a smart label, in which drug characteristic information is preset;

[0070] Install temperature, humidity, and light sensors in cold chain transport containers to collect environmental data in real time;

[0071] Transmit sensor data to edge computing nodes and cloud platforms in real time through IoT technology;

[0072] Smart tags record environmental data in real time and synchronize with the cloud platform;

[0073] The cloud platform performs data cleaning, analysis and storage;

[0074] The present invention is further configured such that the overall process of the platform includes:

[0075] Step 1. When the drugs are shipped out of the warehouse, the platform generates a personalized transportation plan based on the drug characteristics database and equips each batch of drugs with a smart label;

[0076] Step 2. Real-time monitoring: During transportation, IoT sensors and smart tags monitor environmental data in real time, and edge computing devices perform preliminary processing before uploading it to the cloud platform.

[0077] Step 3. Data processing and analysis: data cleaning, analysis and prediction are performed on the cloud platform to identify potential problems;

[0078] Step 4. Abnormal warning: the multi-level warning unit triggers different levels of warning notifications based on real-time data and prediction models, and provides processing suggestions;

[0079] Step 5. Dynamically adjust the transportation plan based on real-time data and drug characteristics;

[0080] Step 6. Data storage and traceability: All transportation data is stored through blockchain to ensure data immutability and traceability; users can view the detailed transportation process of each batch of drugs through the platform.

[0081] Compared with the prior art, the present invention has the following beneficial effects:

[0082] This application sets up multi-level temperature warnings, providing different warning levels and treatment plans for situations where the temperature approaches the threshold, exceeds the standard for a short time, and exceeds the standard for a long time. When the warning is triggered, the system automatically analyzes and provides treatment plan suggestions, including adjusting the temperature control equipment and changing the transportation route.

[0083] This application customizes personalized transportation and storage solutions based on the characteristics of different drugs, including sensitive temperature range and humidity requirements; uses smart labels, equips each drug with a smart label RFID, and the label records the characteristics of the drug and real-time environmental data, making it easier for logistics personnel to adjust transportation conditions;

[0084] The solution solves the problem that the early warning mechanism of the pharmaceutical transportation process in the prior art only issues an alarm when the temperature exceeds the standard, has a slow response speed, and cannot provide a specific treatment plan; in addition, pharmaceutical cold chain transportation mostly adopts a unified standard, and cannot provide transportation guarantees according to the specific needs of different drugs, resulting in some drugs not being optimally protected during transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] Figure 1 This is a framework diagram of the pharmaceutical logistics and shipping management cloud platform of the present invention. DETAILED DESCRIPTION

[0086] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0087] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0088] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0089] Example 1

[0090] See also Figure 1 The present invention provides a pharmaceutical logistics and shipping management cloud platform, including:

[0091] Pharmaceutical transportation data collection and monitoring module, including:

[0092] Environmental data acquisition unit, used to monitor the drug transportation environment in real time, equipped with temperature sensors, humidity sensors, vibration sensors and light sensors.

[0093] Smart labeling unit, equipped with smart labels for each batch of drugs, recording drug characteristics and real-time environmental data;

[0094] Edge computing unit, deploy edge computing nodes on transport vehicles to perform data preprocessing and preliminary analysis;

[0095] Pharmaceutical logistics data processing module, including:

[0096] Cleaning and analysis unit to verify the integrity and accuracy of collected data;

[0097] The machine learning unit uses the machine learning algorithm RNN to train historical data and establish a prediction model. Based on real-time data and the prediction model, it predicts the trend of temperature environment parameters and detects problems in advance.

[0098] Early warning response module, including:

[0099] Multi-level warning unit, which sets multi-level temperature thresholds according to the characteristics of drugs and triggers different levels of warning notifications;

[0100] Automated emergency response unit, which automatically executes emergency response plans through smart contracts;

[0101] Multi-level temperature warning is set up in the multi-level warning unit:

[0102] Monitor temperature data in real time during drug transportation and perform temperature data analysis, triggering early warnings based on temperature data analysis;

[0103] Define temperature thresholds and warning levels, and set the allowable temperature range for drugs during transportation;

[0104] The warning levels are:

[0105] Approaching threshold: The temperature is close to but not beyond the allowable range, triggering warning level 1;

[0106] Temporary over-limit: The temperature temporarily exceeds the allowable range, but the time is short, triggering the second warning level;

[0107] Long-term over-limit: The temperature exceeds the allowable range for a long time, triggering the warning level 3;

[0108] The temperature data analysis method is:

[0109] Clean and format data in edge computing node units to remove outliers and noise data;

[0110] Use machine learning algorithm RNN to analyze and predict temperature data in real time;

[0111] According to the set temperature threshold and analysis results, the corresponding level of warning notification is triggered;

[0112] Warning notifications include:

[0113] When the threshold is approached, the warning level 1 is triggered: remind relevant personnel to pay attention to temperature changes; check the temperature control equipment;

[0114] When the temperature exceeds the limit for a short period of time, the warning level 2 is triggered: notify relevant personnel by phone; check and adjust the temperature control equipment settings, and record abnormal temperature events on the cloud platform;

[0115] When the temperature exceeds the standard for a long time, the warning level 3 is triggered: notify all relevant parties by phone and monitor the processing process in real time; adjust the working status of the cold chain equipment or replace the spare cold chain equipment; at the same time, change the transportation route as needed to avoid further increase in temperature;

[0116] The specific triggering methods of early warning notification are:

[0117] Define temperature threshold range: set normal temperature range as Tmin, Tmax, Where Tmin is the lowest temperature allowed for the drug, Tmax is the highest temperature allowed for the drug, Ti is the ith temperature data point, and n represents the total number of data points;

[0118] The three-times standard deviation method was used to eliminate outliers. Where μT represents the mean of temperature data, and σT represents the standard deviation of temperature data;

[0119] Normalize the temperature data: Where Tnmld,i represents the i-th standardized temperature data;

[0120] Use recurrent neural network (RNN) to analyze and predict temperature data in real time, and take the cleaned temperature data sequence as input: X = {Tnmld,1, Tnmld,2,...Tnmld,n};

[0121] Hidden layer: ht = tanh(Wxhxt + Whhht-1 + bh), where ht is the hidden layer state at time t, Wxh represents the weight matrix input to the hidden layer, Whh is the weight matrix from hidden layer to hidden layer, xt represents the input data at time t, and bh is the bias of the hidden layer;

[0122] Output layer: in represents the predicted temperature value at the future time t+1, Who is the weight matrix from the hidden layer to the output layer, and bo represents the bias of the output layer;

[0123] According to the set temperature threshold and analysis results, the corresponding level of warning notification is triggered:

[0124] Personalized medicine management module, including:

[0125] Drug characteristics management unit, which records the environmental requirements of each drug, including temperature, humidity, light, and transportation plan; and generates personalized transportation plans;

[0126] Dynamic adjustment unit, dynamically adjust the transportation plan;

[0127] When an early warning is triggered, it automatically analyzes and provides treatment plan suggestions, specifically:

[0128] Build an intelligent decision support system to provide processing suggestions based on historical data and rule base;

[0129] Dynamically adjust treatment plans based on real-time data and forecast results;

[0130] Use smart contracts to automatically execute preset emergency response plans;

[0131] Dynamically adjust cold chain equipment and transportation routes based on real-time data and forecast results;

[0132] In the personalized medicine management module, historical transportation data and real-time environmental data are collected and preprocessed;

[0133] Define processing rules, use Bayesian decision networks and dynamic adjustment modules, combine real-time data and prediction results, and provide processing solutions;

[0134] Use smart contracts to automatically execute treatment plans based on warning levels;

[0135] Adjust temperature control equipment and transportation routes based on real-time data;

[0136] The intelligent decision support system is constructed in the following ways:

[0137] Collect historical transportation data, including temperature environment parameters, humidity environment parameters and light environment parameters, as well as corresponding treatment measures and results, and perform data preprocessing;

[0138] Build a rule base:

[0139] When the temperature approaches the threshold, remind relevant personnel to pay attention to temperature changes and check the temperature control equipment;

[0140] When the temperature exceeds the limit briefly, notify relevant personnel by phone and check and adjust the temperature control equipment settings;

[0141] When the temperature exceeds the standard for a long time, adjust the working status of the cold chain equipment or replace the spare cold chain equipment, and change the transportation route; use logical rules to express the processing rules, calculate the posterior probabilities of different processing solutions based on historical data and real-time data, and select the optimal solution: Here P(AB) represents the posterior probability of event A under condition B, P(BA) represents the probability of B when event A occurs, P(A) is the prior probability of event A, and P(B) is the prior probability of condition B;

[0142] The dynamic adjustment unit receives and processes environmental sensor data in real time: Here Tt is the temperature at time t,

[0143] Ht is the humidity at time t, Lt is the light intensity at time t, and k represents the total number of time steps;

[0144] Adjust the set value of the temperature control device according to the real-time data, Tset = Tcurrent + α (Ttarget - Tcurrent), where Tset is the new set value of the temperature control device, Tcurrent is the current temperature, Ttarget represents the target temperature, and α is the adjustment coefficient;

[0145] Re-plan the transportation route using the shortest path algorithm, Here d(vi,vi+1) represents the distance between the i-th and i+1-th nodes in the path, and n is the total number of nodes in the path;

[0146] Medical data storage module, including:

[0147] A blockchain storage unit for storing shipping data;

[0148] Data traceability unit, every link from production to use can be traced and viewed;

[0149] A database containing all drug information is established in the drug property management unit, recording the temperature range, humidity requirements, and light condition characteristics of each drug, and inputting the characteristic information of each drug:

[0150] Use RFID smart tags to record and transmit drug characteristics and real-time environmental data;

[0151] Equip each drug with a smart label, in which drug characteristic information is preset;

[0152] Install temperature, humidity, and light sensors in cold chain transport containers to collect environmental data in real time;

[0153] Transmit sensor data to edge computing nodes and cloud platforms in real time through IoT technology;

[0154] Smart tags record environmental data in real time and synchronize with the cloud platform;

[0155] The cloud platform performs data cleaning, analysis and storage;

[0156] The overall process of the pharmaceutical logistics delivery management cloud platform provided by the present invention includes:

[0157] Step 1. When the drugs are shipped out of the warehouse, the platform generates a personalized transportation plan based on the drug characteristics database and equips each batch of drugs with a smart label;

[0158] Step 2. Real-time monitoring: During transportation, IoT sensors and smart tags monitor environmental data in real time, and edge computing devices perform preliminary processing before uploading it to the cloud platform.

[0159] Step 3. Data processing and analysis: data cleaning, analysis and prediction are performed on the cloud platform to identify potential problems;

[0160] Step 4. Abnormal warning: the multi-level warning unit triggers different levels of warning notifications based on real-time data and prediction models, and provides processing suggestions;

[0161] Step 5. Dynamically adjust the transportation plan based on real-time data and drug characteristics;

[0162] Step 6. Data storage and traceability: All transportation data is stored through blockchain to ensure data immutability and traceability; users can view the detailed transportation process of each batch of drugs through the platform.

[0163] The present invention provides real-time drug transportation environment monitoring. Each batch of drugs is equipped with a smart label, which not only records the characteristic information of the drugs, but also collects and transmits environmental data in real time. The edge computing unit is deployed on the transport vehicle to pre-process and preliminarily analyze the data and synchronize it with the cloud platform.

[0164] In the data processing module, the RNN algorithm is used to train historical data and establish a prediction model; the trend of temperature environment parameters is predicted based on real-time data, potential problems are discovered in advance, and corresponding warnings are triggered;

[0165] The early warning response module is equipped with a multi-level early warning unit. It sets multi-level temperature thresholds according to the characteristics of the drug, and triggers early warning notifications of different levels in combination with real-time data and prediction results. The early warning levels include approaching the threshold, short-term exceeding the standard, and long-term exceeding the standard. After the early warning is triggered, the system will automatically analyze and provide treatment plan suggestions. When approaching the threshold, the system reminds relevant personnel to pay attention to temperature changes and check the temperature control equipment. When the standard is exceeded for a short time, the relevant personnel will be notified by phone to check and adjust the temperature control equipment settings, and the abnormal temperature events will be recorded on the cloud platform. When the standard is exceeded for a long time, the system will notify all relevant parties and monitor the treatment process in real time.

[0166] The intelligent decision support system provides processing suggestions based on historical data and rule bases, dynamically adjusts processing solutions based on real-time data and prediction results, calculates the posterior probabilities of different processing solutions through the Bayesian decision network, and selects the optimal solution. In addition, the platform uses smart contracts to automatically execute preset emergency processing solutions; adjust temperature control equipment and transportation routes based on real-time data;

[0167] The data storage and traceability module uses blockchain technology to store all transportation data; users can view the detailed transportation process of each batch of drugs through the platform and realize traceability management throughout the entire life cycle.

[0168] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A pharmaceutical logistics and shipping management cloud platform, characterized in that: include: Pharmaceutical transportation data collection and monitoring module, including: Environmental data acquisition unit, used to monitor the drug transportation environment in real time, equipped with temperature sensors, humidity sensors, vibration sensors and light sensors. Smart label unit, equipped with smart labels for each batch of drugs, records drug characteristics and real-time environmental data, Edge computing unit, deploy edge computing nodes on transport vehicles to perform data preprocessing and preliminary analysis; Pharmaceutical logistics data processing module, including: Cleaning and analysis unit, The machine learning unit trains historical data based on the machine learning algorithm RNN to establish a prediction model; based on real-time data and the prediction model, it predicts the trend of temperature environment parameters; Early warning response module, including: The multi-level warning unit sets multi-level temperature thresholds according to the characteristics of the drug, triggering different levels of warning notifications. A multi-level temperature warning is set up in the multi-level warning unit. The multi-level temperature warning method is as follows: Monitor temperature data in real time during drug transportation and perform temperature data analysis, trigger warnings based on temperature data analysis, define temperature thresholds and warning levels, and set the allowable temperature range for drugs during transportation; The warning levels are: Approaching threshold: The temperature is close to but not beyond the allowable range, triggering warning level 1. Temporary over-limit: The temperature temporarily exceeds the allowable range, but the time is short, triggering the second warning level. Long-term over-limit: The temperature exceeds the allowable range for a long time, triggering the warning level 3; The temperature data analysis method is: Data cleaning and formatting are performed at the edge computing node unit to remove outliers and noise data. Use machine learning algorithm RNN to analyze and predict temperature data in real time. According to the set temperature threshold and analysis results, the corresponding level of warning notification is triggered; Warning notifications include: When the threshold is approached, the warning level 1 is triggered: remind relevant personnel to pay attention to temperature changes and check the temperature control equipment. When the temperature exceeds the limit for a short period of time, the warning level 2 is triggered: relevant personnel are notified by phone, the temperature control equipment settings are checked and adjusted, and abnormal temperature events are recorded on the cloud platform. When the standard is exceeded for a long time, the warning level 3 is triggered: all relevant parties are notified by phone, and the processing process is monitored in real time, the working status of the cold chain equipment is adjusted or the standby cold chain equipment is replaced, and the transportation route is changed as needed; The specific triggering methods of early warning notification are: Define the temperature threshold range: Set the normal temperature range as T min ,T max , T min ≤T i ≤T max , Where T min T is the lowest temperature allowed for the drug. max T is the maximum temperature allowed for the drug. i The i-th temperature data point, n represents the total number of data points, The triple standard deviation method is used to eliminate outliers, μ T -3σ T ≤T i ≤μ T +3σ T , where μ T represents the mean of temperature data, σ T represents the standard deviation of the temperature data, Normalize the temperature data: Where T nmld,i represents the i-th standardized temperature data, Use recurrent neural network RNN ​​to analyze and predict temperature data in real time, and take the cleaned temperature data sequence as input: X = {T nmld,1 ,T nmld,2 ,...T nmld,n }, Hidden layer: h t =tanh(W xh x t +W hh h t-1 +b h ), where h t is the hidden layer state at time t, W xh Represents the weight matrix input to the hidden layer, W hh is the weight matrix from hidden layer to hidden layer, x t represents the input data at time t, b h is the bias of the hidden layer, Output layer: in represents the predicted temperature value at the future time t+1, W ho is the weight matrix from the hidden layer to the output layer, b o represents the bias of the output layer, According to the set temperature threshold and analysis results, the corresponding level of warning notification is triggered; Automated emergency response unit, which automatically executes emergency response plans through smart contracts; Personalized medicine management module, including: Drug characteristics management unit generates personalized transportation plans. Dynamic adjustment unit, dynamically adjust the transportation plan; Medical data storage module, including: Blockchain storage unit, Data traceability unit, traces back every link from production to use.

2. A pharmaceutical logistics delivery management cloud platform according to claim 1, characterized in that: When an early warning is triggered, it automatically analyzes and provides treatment plan suggestions, specifically: Build an intelligent decision support system to provide processing suggestions based on historical data and rule base; Dynamically adjust treatment plans based on real-time data and forecast results; Use smart contracts to automatically execute preset emergency response plans; Dynamically adjust cold chain equipment and transportation routes based on real-time data and forecast results.

3. A pharmaceutical logistics delivery management cloud platform according to claim 2, characterized in that: In the personalized medicine management module, historical transportation data and real-time environmental data are collected and preprocessed; Define processing rules, use Bayesian decision networks and dynamic adjustment modules, combine real-time data and prediction results, and provide processing solutions; Use smart contracts to automatically execute treatment plans based on warning levels; Adjust temperature control equipment and transportation routes based on real-time data.

4. A pharmaceutical logistics delivery management cloud platform according to claim 3, characterized in that: The intelligent decision support system is constructed in the following ways: Collect historical transportation data, including temperature, humidity, light environment parameters, and corresponding treatment measures and results, and perform data preprocessing; Build a rule base: When the temperature approaches the threshold, remind relevant personnel to pay attention to temperature changes and check the temperature control equipment; When the temperature exceeds the limit briefly, notify relevant personnel by phone and check and adjust the temperature control equipment settings; When the temperature exceeds the standard for a long time, adjust the working status of the cold chain equipment or replace the spare cold chain equipment, and change the transportation route; Use logical rules to represent processing rules, calculate the posterior probabilities of different processing solutions based on historical data and real-time data, and select the optimal solution: Here P(A|B) represents the posterior probability of event A under condition B, P(B|A) represents the probability of B when event A occurs, P(A) is the prior probability of event A, and P(B) is the prior probability of condition B.

5. A pharmaceutical logistics delivery management cloud platform according to claim 4, characterized in that: The dynamic adjustment unit receives and processes environmental sensor data in real time: X t ={T t ,H t ,L t }, Here T t is the temperature at time t, H t is the humidity at time t, L t is the light intensity at time t, k represents the total number of time steps; Adjust the temperature control device setting value according to real-time data, T set =T current +α(T target -T current ), where T set is the new set value of the temperature control device, T current is the current temperature, T target represents the target temperature, α is the adjustment coefficient; Re-plan the transportation route using the shortest path algorithm, Here d(v i ,v i+1 ) represents the distance between the i-th and i+1-th nodes in the path, and n is the total number of nodes in the path.

6. A pharmaceutical logistics delivery management cloud platform according to claim 5, characterized in that: A database containing all drug information is established in the drug property management unit, recording the temperature range, humidity requirements, and light condition characteristics of each drug, and inputting the characteristic information of each drug: Use RFID smart tags to record and transmit drug characteristics and real-time environmental data; Equip each drug with a smart label, in which drug characteristic information is preset; Install temperature sensors, humidity sensors, and light sensors in cold chain transport containers to collect environmental data in real time; Transmit sensor data to edge computing nodes and cloud platforms in real time through IoT technology; Smart tags record environmental data in real time and synchronize with the cloud platform; The cloud platform performs data cleaning, analysis and storage.

7. A pharmaceutical logistics delivery management cloud platform according to claim 6, characterized in that: The overall process of the platform includes: Step 1. When the drugs are shipped out of the warehouse, the platform generates a personalized transportation plan based on the drug characteristics database and equips each batch of drugs with a smart label; Step 2. Real-time monitoring: During transportation, IoT sensors and smart tags monitor environmental data in real time, and edge computing devices perform preliminary processing before uploading it to the cloud platform. Step 3. Data processing and analysis: data cleaning, analysis and prediction are performed on the cloud platform to identify potential problems; Step 4. Abnormal warning: the multi-level warning unit triggers different levels of warning notifications based on real-time data and prediction models, and provides processing suggestions; Step 5. Dynamically adjust the transportation plan based on real-time data and drug characteristics; Step 6. Data storage and traceability: All transportation data is stored through blockchain to ensure data immutability and traceability; users can view the detailed transportation process of each batch of drugs through the platform.

Images