Electronic equipment intelligent transfer container management system and method based on Internet of Things and AI

Abstract

The invention relates to an electronic equipment intelligent transfer container management system based on the Internet of Things and Al, and the system achieves the real-time monitoring, risk prediction and automatic adjustment in a transportation process through integrating edge calculation, a federal learning framework, a risk prediction algorithm and a block chain evidence storage technology. The system adopts various sensors to monitor data such as temperature and humidity, vibration, air pressure, inclination angle and the like in the container, and carries out real-time processing through the edge calculation unit, so that the environment in the transportation process meets equipment requirements. Meanwhile, an LSTM and a random forest algorithm are used for predicting the equipment damage probability, and a transportation scheme is dynamically adjusted according to a risk assessment result. In addition, the block chain technology is used for recording key events and uploading the data to an alliance chain, so that the non-tampering and traceability of the data are ensured. The intelligent management system provided by the invention not only improves the safety and transparency of the equipment transportation process, but also optimizes the transportation path and reduces the energy consumption.

Description

Technical Field

[0001] The present invention relates to the technical fields of water resource management and remote sensing technology applications, and particularly to an intelligent transfer container management system and method for electronic devices based on the Internet of Things and AI. Background Art

[0002] With the rapid development of global trade and cross-border logistics, especially the growing demand for the transportation of high-value and precision equipment (such as electronic devices, chips, medical devices, etc.), traditional transportation management systems can no longer meet the strict requirements for environmental monitoring, transportation safety, and transparency during the transportation of these devices. Traditional container transportation management methods usually rely on manual operations or simple monitoring devices, lack real-time intelligent decision-making support, and various risks, temperature and humidity changes, vibrations, and tilts during transportation cannot be effectively predicted and responded to in real time, resulting in a significant increase in the risk of equipment damage.

[0003] Most current transportation management systems mainly rely on simple temperature and humidity monitoring and manual operations, lacking comprehensive monitoring of multiple environmental factors such as vibrations and tilts. These systems usually cannot obtain the detailed information of the equipment status inside the container and the transportation environment in real time.

[0004] Traditional container monitoring devices are usually static and cannot respond in a timely manner to changes during transportation. Even if some systems support environmental data collection, they often cannot perform intelligent prediction and dynamic adjustment of transportation risks.

[0005] Traditional transportation management systems lack the functions of recording and storing evidence for various key events during transportation (such as opening the container, exceeding the temperature and humidity standards, equipment collision, etc.). The important information during transportation fails to be effectively saved and cannot be traced later. If equipment damage or environmental out-of-control occurs, it is difficult to accurately identify the cause of the problem, and it is even impossible to prove whether the transportation process is compliant.

[0006] Although some transportation companies may use data recorders for monitoring, the data of these devices may not comprehensively present various situations during transportation, and most lack data protection and anti-tampering mechanisms, making it difficult to ensure the authenticity and credibility of the data.

[0007] Existing transportation management systems cannot predict potential risks during transportation in advance, such as equipment may be damaged due to vibrations or temperature and humidity changes. Many systems do not take into account factors such as weather, road conditions, transportation routes, etc., and also lack an assessment mechanism for possible risks.

[0008] Even when risks occur, traditional systems often rely on manual intervention to take countermeasures. This method is both time-consuming and prone to omissions, and cannot achieve real-time and automated risk response.

[0009] In traditional containers, once protective structures such as sealing strips are damaged, the equipment is often vulnerable to the external environment. However, existing systems usually cannot automatically detect the damage of the sealing strips and repair them automatically, resulting in an increased risk of the equipment being exposed to harsh environments.

[0010] Although there are some devices with environmental monitoring and self-repair functions on the market, these technologies have not been widely applied to transportation container management systems. Especially during the transportation of high-value equipment such as electronic devices and medical devices, they have not been widely promoted.

[0011] The energy efficiency of existing container systems is low. Many traditional containers require external energy to maintain temperature and humidity control, vibration monitoring, and other environmental protection measures, resulting in higher transportation costs and energy consumption.

[0012] At the same time, traditional containers usually use non-recyclable materials. With the increasing demand for environmental protection in modern logistics, it is required that containers not only improve transportation efficiency but also reduce the environmental burden.

[0013] Lack of real-time performance and accuracy: Although there are some sensors and data recording devices in existing systems, they often cannot achieve high-precision real-time monitoring and risk prediction. Once the environment changes suddenly (such as severe vibration, sudden weather changes, etc.), the transportation plan cannot be adjusted immediately, easily leading to equipment damage.

[0014] Lack of intelligent control: Most existing systems lack the ability to make intelligent decisions such as risk prediction and environmental adjustment through artificial intelligence algorithms. Existing technologies are often static monitoring devices and cannot be dynamically adjusted and optimized based on real-time data.

[0015] Data security and compliance: Since various key events and data during transportation have not been effectively archived, the transportation process lacks transparency and traceability, which cannot provide guarantees for customers and cannot meet the high standards of data protection required by some industries (such as medical equipment, military equipment, etc.).

[0016] The system cannot cope with complex environmental changes: During transportation, the changes of multiple factors such as temperature and humidity, vibration, and tilt are intertwined. Existing systems often cannot effectively analyze these multiple complex environmental changes and provide real-time and accurate countermeasures.

[0017] In summary, the existing technologies cannot meet the complex requirements of modern high-value equipment during transportation. Especially in transportation tasks that require refined environmental control and high security, the deficiencies of traditional container management systems have become increasingly prominent. Therefore, an intelligent transfer management system that can integrate cutting-edge technologies such as the Internet of Things, artificial intelligence, and blockchain is needed to address the deficiencies in the existing technologies and improve the safety, transparency, intelligence level, and environmental friendliness of equipment transportation.

[0018] For this reason, we urgently need to design an intelligent transfer container management system for electronic equipment based on the Internet of Things and Al to solve these problems mentioned above. Summary of the Invention

[0019] An intelligent transfer container management system for electronic equipment based on the Internet of Things and Al, the system includes an edge computing unit c edge , a federated learning framework c FL , a risk prediction algorithm module c Risk and a blockchain evidence storage module c Chain ;

[0020] The edge computing unit C edge is used to analyze multi-dimensional data from sensors in real time. The multi-dimensional data includes vibration V, temperature and humidity T, humidity H, air pressure P, tilt angle and make preliminary decisions locally;

[0021] The federated learning framework c FL optimizes the global risk model M global by aggregating the historical data of multiple containers, and improves the accuracy of risk prediction;

[0022] The risk prediction algorithm module C Risk adopts an adaptive algorithm. The adaptive algorithm includes LSTM and random forest algorithms, and evaluates the equipment safety risk R risk during transportation in real time, and dynamically adjusts the transportation plan;

[0023] The blockchain evidence storage module C Chain is used to record key events. The key events include opening the cabinet E open , temperature and humidity exceeding the limit E temp_exceed , severe impact E impact , and uploads the data to the consortium blockchain for evidence storage and traceability.

[0024] As a preferred technical solution of the present invention: the risk prediction algorithm module c Risk combines a long short-term memory network and a random forest model, specifically including: the input layer contains terrain data D, weather prediction data W, and historical accident records H of the transportation route, and its value is the data matrix X = [D, W, H];

[0025] Predict the temperature and humidity change trend in the next 2 hours through the LSTM neural network model, where the predicted value of the temperature and humidity change trend is Y LSTM = f LSTM (X);

[0026] Use the random forest model to evaluate the equipment damage probability, and the damage probability is P damage = f RF (X), where f RF is the decision function of the random forest model.

[0027] As a preferred technical solution of the present invention: The prediction formula of the LSTM neural network model is:

[0028] Y LSTM = f LSTM (X) = LSTM(W, X) + b

[0029] Among them, X is the input data, W is the weight of the LSTM model, b is the bias term, and f LSTM represents the prediction function of the LSTM network.

[0030] As a preferred technical solution of the present invention: The formula for the random forest model to evaluate the equipment damage probability is:

[0031]

[0032] Among them, w i is the weight of the i-th tree, h i (X) is the prediction output of the i-th tree, N is the number of trees in the forest, and f RF is the prediction function of the random forest model.

[0033] As a preferred technical solution of the present invention: When the system dynamically adjusts the shock absorption strategy according to the prediction result, the adjusted shock absorption intensity S damping is:

[0034] S damping = α · P damage + B · Y LSTM

[0035] Among them, α and β are the adjustment coefficients of the system, used to weight the damage probability and the temperature and humidity change trend, P damage is the equipment damage probability, and Y LSTM is the temperature and humidity prediction value.

[0036] As a preferred technical solution of the present invention: The hash value generated by the blockchain evidence storage module c Chain is used to store the key events during transportation, and its hash value generation formula is:

[0037] Hevent = Hash(T, E)

[0038] Wherein, T is the time stamp of the event, E is the event content, Hash is the hash function, and H event is the hash value of the event.

[0039] As a preferred technical solution of the present invention: the blockchain evidence storage module c Chain uploads the hash value of the event to the consortium blockchain, and the uploaded event data is represented by the following formula:

[0040] Event i = <H event , K i >

[0041] Wherein, K i is the encryption key of the i-th event, and · represents the encrypted encapsulation of the data.

[0042] As a preferred technical solution of the present invention: the system further includes a self-healing sealing structure, which triggers a polymer gel to repair the sealing strip through microcapsules, and the mathematical model of its repair process is:

[0043] R = f repair (C)

[0044] Wherein, R is the degree of repair, C is the degree of damage of the sealing strip, and f repair is the repair function, representing the self-healing process of the sealing strip.

[0045] As a preferred technical solution of the present invention: when the system optimizes the transportation path according to real-time data, the path optimization function P opt is:

[0046]

[0047] Wherein, P is the set of all possible transportation paths, α i and B i are the coefficients of path optimization, R i (P) is the risk assessment value of path P, and T i (P) is the transportation time of path P.

[0048] As a preferred technical solution of the present invention: the risk prediction algorithm module c Risk further includes a real-time monitoring and alarm function based on temperature, humidity, vibration frequency and tilt angle, and the alarm condition is:

[0049]

[0050] Wherein, T is the temperature, H is the humidity, ∈ T 、∈H is the tolerance threshold for temperature and humidity, V is the vibration frequency, is the tilt angle, ∈ V 、 is the tolerance threshold for vibration and tilt, A is the alarm signal.

[0051] The present invention provides an intelligent transfer container management method for electronic devices based on the Internet of Things and artificial intelligence. The method includes the following steps:

[0052] Real-time monitoring and data collection: Through multiple sensors installed in the container (including temperature and humidity, vibration, air pressure, tilt angle and other sensors), the environmental data during transportation is collected in real time;

[0053] Edge computing and data processing: Transmit the collected environmental data to the edge computing unit in the container for real-time processing, conduct a preliminary risk assessment and adjust the transportation parameters according to the prediction results;

[0054] Transportation risk prediction: Use the LSTM neural network and random forest algorithm to predict the safety risk of the equipment during transportation, calculate the equipment damage probability, and generate a risk assessment result;

[0055] Dynamic adjustment and route optimization: Dynamically adjust the shock absorption intensity of the container according to the prediction results, optimize the transportation route, and select the optimal transportation route to reduce the equipment damage risk;

[0056] Event recording and data certification: Use blockchain technology to generate hash values of key events during transportation (such as excessive temperature and humidity, excessive vibration, opening the container, etc.) and upload them to the consortium chain, making the data tamper-proof and facilitating subsequent traceability and auditing;

[0057] Data verification after transportation: Customers obtain the blockchain certification report by scanning the QR code, verify the compliance of the transportation process, and conduct a review and confirmation of the transportation data.

[0058] Beneficial effects:

[0059] Through the integration of the Internet of Things, edge computing and artificial intelligence algorithms, this technical solution can realize real-time monitoring and analysis of various environmental factors during transportation (such as vibration, temperature and humidity, air pressure, tilt angle, etc.). The edge computing unit processes the sensor data immediately, which not only improves the real-time performance of data processing, but also can automatically adjust the shock absorption intensity of the container according to the predicted transportation risk (such as the equipment damage probability), ensuring the safety of the equipment during transportation. This intelligent and automated risk management greatly reduces the risk of equipment damage.

[0060] By introducing blockchain technology, the present invention realizes the recording and certification of key events during transportation (such as opening the container, exceeding temperature and humidity standards, severe impact, etc.). All important transportation data is uploaded to the consortium blockchain through hash encryption, making the data tamper-proof and traceable. This not only improves the transparency of the transportation process but also meets the high standards of customers for transportation safety and compliance, and is particularly suitable for the transportation of high-value and sensitive products such as electronic devices and medical devices.

[0061] This technical solution also pays attention to environmental protection and energy efficiency. It uses recyclable materials to manufacture the container and optimizes the energy consumption during transportation through an intelligent control system, reducing energy waste during transportation. At the same time, through an adaptive shock absorption and temperature and humidity control strategy, it reduces the dependence on external energy, further reducing costs and carbon emissions. Compared with the traditional solution, this system can significantly improve transportation efficiency and reduce energy consumption and logistics costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0063] Figure 1 It is a system block diagram of an intelligent transfer container management system for electronic devices based on the Internet of Things and AI. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0064] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention in conjunction with the drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0065] The following will Figure 1 describe the specific implementation manners of the present invention in detail in conjunction with the

[0066] An intelligent transfer container management system for electronic devices based on the Internet of Things and AI, the system includes an edge computing unit c edge and a federated learning framework c FL and a risk prediction algorithm module c Risk and a blockchain certification module c Chain ;

[0067] The edge computing unit C edgeFor real-time analysis of multi-dimensional data from sensors, the multi-dimensional data includes vibration V, temperature and humidity T, humidity H, air pressure P, and tilt angle And make a preliminary decision locally;

[0068] Federated learning framework c FL By aggregating the historical data of multiple containers, optimize the global risk model M global , improve the accuracy of risk prediction;

[0069] Risk prediction algorithm module C Risk Adopt an adaptive algorithm, the adaptive algorithm includes LSTM and random forest algorithms, and evaluate the equipment safety risk R during transportation in real time risk , dynamically adjust the transportation plan; the risk prediction algorithm module c Risk Combines a long short-term memory network and a random forest model, specifically including: the input layer contains terrain data D, weather prediction data W, and historical accident records H of the transportation route, and its value is the data matrix X = [D, W, H];

[0070] Risk prediction algorithm module c Risk Further includes real-time monitoring and alarm functions based on temperature and humidity, vibration frequency, and tilt angle. The alarm conditions are:

[0071]

[0072] Among them, T is the temperature, H is the humidity, ∈ T , ∈ H Are the tolerance thresholds of temperature and humidity, V is the vibration frequency, θ is the tilt angle, ∈ V , Are the tolerance thresholds of vibration and tilt, and A is the alarm signal.

[0073] Predict the temperature and humidity change trend in the next 2 hours through the LSTM neural network model, where the predicted value of the temperature and humidity change trend is Y LSTM = f LSTM (X); the prediction formula of the LSTM neural network model is:

[0074] Y LSTM = f LSTM (X) = LSTM(W, X) + b

[0075] Among them, X is the input data, W is the weight of the LSTM model, b is the bias term, and f LSTM Represents the prediction function of the LSTM network.

[0076] Adopt a random forest model to evaluate the equipment damage probability, and the damage probability is P damage = f RF (X), where fRF is the decision function of the random forest model. The formula for the random forest model to evaluate the equipment damage probability is:

[0077]

[0078] where w i is the weight of the i-th tree, h i (X) is the predicted output of the i-th tree, N is the number of trees in the forest, and f RF is the prediction function of the random forest model

[0079] Blockchain evidence storage module C Chain is used to record key events. The key events include cabinet opening E open , temperature and humidity exceeding the limit E temp_exceed , severe impact E impact , and upload the data to the consortium blockchain for evidence storage and traceability. The blockchain evidence storage module c Chain generates a hash value for storing key events during transportation. The formula for generating its hash value is:

[0080] H event = Hash(T, E)

[0081] where T is the timestamp of the event, E is the event content, Hash is the hash function, and H event is the hash value of the event.

[0082] The blockchain evidence storage module c Chain uploads the hash value of the event to the consortium blockchain. The uploaded event data is represented by the following formula:

[0083] Event i = <H event , K i >

[0084] where K i is the encryption key for the i-th event, and · represents the encrypted encapsulation of the data.

[0085] When the system dynamically adjusts the shock absorption strategy according to the prediction result, the adjusted shock absorption intensity S damping is:

[0086] S damping = α · P damage + B · Y LSTM

[0087] where α and β are the adjustment coefficients of the system, used to weight the damage probability and the temperature and humidity change trend, P damage is the equipment damage probability, and Y LSTM is the predicted value of temperature and humidity.

[0088] The system also includes a self-healing sealing structure, which triggers a polymer gel to repair the sealing strip through microcapsules. The mathematical model of the repair process is as follows:

[0089] R = f repair (C)

[0090] where R is the degree of repair, C is the degree of damage to the sealing strip, and f repair is the repair function, representing the self-healing process of the sealing strip.

[0091] When the system optimizes the transportation route according to real-time data, the route optimization function P opt is as follows:

[0092]

[0093] where P is the set of all possible transportation routes, α i and B i are the coefficients for route optimization, R i (P) is the risk assessment value of route P, and T i (P) is the transportation time of route P.

[0094] Example 1: An intelligent transfer container management system based on the Internet of Things and AI

[0095] Step 1: System initialization and preparation;

[0096] The user inputs device information (such as device type, size, weight, vulnerability level, etc.) through a smartphone or PC client; the system automatically generates a container partition layout plan according to the device type and specifications, calculates the optimal storage position of the device in the container to minimize vibration and tilt during transportation;

[0097] The system starts the environmental monitoring module, confirms that the temperature, humidity, air pressure and other data in the container meet the transportation requirements, and automatically adjusts the temperature and humidity of the container to the required set value if necessary.

[0098] Step 2: Sensor data collection and edge computing;

[0099] The container is equipped with a vibration sensor (V), temperature and humidity sensors (T, H), an air pressure sensor (P), and a tilt sensor The sensors collect environmental data in real time and send the data to the edge computing unit C edge of the container. This unit performs preliminary analysis to ensure the safety of the device state during transportation; the data stream is transmitted to the cloud for further processing after passing through the edge computing unit. The cloud computing module combines the data of multiple containers to optimize the global risk prediction model M globalo

[0100] Step 3: Risk Prediction and Dynamic Adjustment;

[0101] Risk Prediction Algorithm Module C Risk Use the LSTM neural network and random forest model to process the data, predict the temperature and humidity change trend Y within the next 2 hours LSTM , and evaluate the damage probability P of the equipment damage ; According to the prediction results, adjust the shock absorption strategy of the container. For example, when the equipment damage probability P damage is relatively high, the system will dynamically adjust the shock absorption intensity 5 according to the formula damping , and the formula is as follows:

[0102] S damping = α·P damage + B·Y LSTM

[0103] Step 4: Real-time Route Optimization and Alarm;

[0104] The system optimizes the transportation route based on real-time data and selects the route P with the least risk opt , avoiding areas with high vibration, high temperature and humidity. The route optimization function formula is:

[0105]

[0106] If abnormal situations such as excessive temperature and humidity, excessive vibration or too high inclination angle of the container occur during transportation, the system will automatically trigger an alarm, and the alarm condition is defined by the following formula:

[0107] The conditions are defined by the following formula:

[0108]

[0109] Among them, A is the alarm signal, and the system will notify the driver to limit the speed or adjust the route when alarming.

[0110] Example 2: Cross-border Transportation Management of Medical Equipment;

[0111] Step 1: Equipment Information Input and Container Initialization;

[0112] The user inputs the type of medical equipment (such as MRI machine), temperature and humidity requirements (such as temperature 18 - 22 °C, humidity 45% - 50%) in the system;

[0113] The system calculates the optimal container layout according to the characteristics of the equipment and sets appropriate protection measures for each equipment, including adding isolation boards, strengthening packaging, etc.

[0114] Step 2: Real-time Monitoring and Dynamic Adjustment during Transportation;

[0115] The system monitors real-time data such as temperature, humidity, vibration, and inclination inside the container, and performs preliminary processing through the edge computing unit. If the temperature and humidity deviate from the set values, the system will automatically adjust and issue a warning;

[0116] In case of external impact, the system automatically adjusts the shock absorption intensity of the container through the shock absorption system to reduce damage to medical equipment.

[0117] Step 3: Risk assessment and alarm;

[0118] The system will conduct a risk assessment of equipment damage based on real-time sensor data, combine the LSTM model and the random forest algorithm to predict the possible damage probability of the equipment, and dynamically adjust the shock absorption strategy according to the prediction results.

[0119] Step 4: Data verification after arriving at the destination;

[0120] After the customer arrives, they can obtain the transportation log stored on the blockchain by scanning the code, making the transportation process compliant and tracing key events (such as excessive temperature and humidity, abnormal vibration, etc.) that occurred.

[0121] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An intelligent transport container management system for electronic equipment based on the Internet of Things and AI, characterized by: The system includes an edge computing unit c edge 、Federated Learning Frameworkc FL , Risk prediction algorithm module c Risk And blockchain evidence module c Chain ; Edge computing unit C edge Used to analyze multi-dimensional data from sensors in real time, including vibration V, temperature and humidity T, humidity H, air pressure P, tilt angle and make initial decisions locally; Federated Learning Frameworkc FL By aggregating historical data of multiple containers, the global risk model M is optimized. global , improve the accuracy of risk prediction; Risk prediction algorithm module C Risk Adaptive algorithms, including LSTM and random forest algorithms, are used to assess the equipment safety risk during transportation in real time. risk , dynamically adjust transportation plans; Blockchain Evidence Module C Chain Used to record key events, including opening cabinet E open 、Temperature and humidity exceed the limit E temp_exceed , severe impact E impact And upload the data to the alliance chain for storage and traceability.

2. The electronic device intelligent transport container management system based on Internet of Things and AI as claimed in claim 1, characterized in that: The risk prediction algorithm module c Risk It combines the long short-term memory network and the random forest model, specifically including: the input layer contains the terrain data D of the transportation route, the weather forecast data W, and the historical accident records H, and its value is the data matrix X = [D, W, H]; The LSTM neural network model is used to predict the temperature and humidity change trend in the next 2 hours, where the temperature and humidity change trend prediction value is Y LSTM =f LSTM (X); The random forest model is used to evaluate the probability of equipment damage, and the damage probability is P damage =f RF (X), where f RF is the decision function of the random forest model.

3. The electronic device intelligent transport container management system based on Internet of Things and AI as claimed in claim 2, characterized in that: The prediction formula of the LSTM neural network model is: Y LSTM =f LSTM (X)=LSTM(W,X)+b Among them, X is the input data, W is the weight of the LSTM model, b is the bias term, and f LSTM Represents the prediction function of the LSTM network.

4. The electronic device intelligent transport container management system based on the Internet of Things and AI as claimed in claim 2, characterized in that: The formula for evaluating the probability of equipment damage using the random forest model is: Among them, w i is the weight of the i-th tree, h i (X) is the predicted output of the i-th tree, N is the number of trees in the forest, and f RF is the prediction function of the random forest model.

5. The electronic device intelligent transport container management system based on Internet of Things and AI as claimed in claim 2, characterized in that: When the system dynamically adjusts the shock absorption strategy according to the prediction results, the adjusted shock absorption intensity S damping for: S damping =α·P damage +B·Y LSTM Among them, α and β are the adjustment coefficients of the system, which are used to weight the damage probability and the temperature and humidity change trend. damage is the probability of equipment damage, Y LSTM is the predicted value of temperature and humidity.

6. The electronic device intelligent transport container management system based on Internet of Things and AI as claimed in claim 1, characterized in that: The blockchain evidence module c Chain The generated hash value is used to store key events in the transportation process. The hash value generation formula is: H event =Hash(T,E) Among them, T is the timestamp of the event, E is the event content, Hash is the hash function, and H event A hash value of the event.

7. The electronic device intelligent transport container management system based on Internet of Things and AI as claimed in claim 6, characterized in that: The blockchain evidence module c Chain The hash value of the uploaded event is uploaded to the consortium chain. The uploaded event data is represented by the following formula: Event i =<H event ,K i > Among them, K i is the encryption key of the ith event, and represents the encryption encapsulation of data.

8. The electronic device intelligent transport container management system based on Internet of Things and AI as claimed in claim 1, characterized in that: The system also includes a self-repairing sealing structure, which triggers the polymer gel to repair the sealing strip through microcapsules. The mathematical model of the repair process is: R=f repair (C) Among them, R is the degree of repair, C is the degree of damage to the sealing strip, and f repair is the repair function, which represents the self-repair process of the sealing strip.

9. The electronic device intelligent transport container management system based on Internet of Things and AI as claimed in claim 1, characterized in that: When the system optimizes the transportation route according to real-time data, the route optimization function P opt for: Among them, P is the set of all possible transportation paths, α i and B i is the coefficient of path optimization, R i (P) is the risk assessment value of path P, T i (P) is the transportation time of path P; the risk prediction algorithm module c Risk It further includes real-time monitoring and alarm functions based on temperature and humidity, vibration frequency and tilt angle, and the alarm conditions are: Where T is temperature, H is humidity, ∈ T ,∈ H is the tolerance threshold of temperature and humidity, V is the vibration frequency, is the tilt angle, ∈ V , is the tolerance threshold of vibration and tilt, and A is the alarm signal.

10. An intelligent transport container management method for electronic devices based on the Internet of Things and artificial intelligence, characterized in that: The method comprises the following steps: Real-time monitoring and data collection: Multiple sensors installed in the container collect environmental data during transportation in real time; Edge computing and data processing: The collected environmental data is transmitted to the edge computing unit in the container for real-time processing, preliminary risk assessment is performed, and transportation parameters are adjusted based on the predicted results; Transportation risk prediction: Use LSTM neural network and random forest algorithm to predict the safety risk of equipment during transportation, calculate the probability of equipment damage, and generate risk assessment results; Dynamic adjustment and route optimization: Dynamically adjust the shock absorption strength of the container according to the prediction results, optimize the transportation route, and select the best transportation route to reduce the risk of equipment damage; Event recording and data storage: Use blockchain technology to generate hash values ​​for key events in the transportation process and upload them to the alliance chain, making the data tamper-proof and facilitating subsequent tracing and auditing; Data verification after transportation: Customers scan the QR code to obtain the blockchain evidence report, verify the compliance of the transportation process, and review and confirm the transportation data.

Images