Big data visualization digital system for freight management

By combining customer manual input and automatic identification technology in the freight management system, using image processing and three-dimensional reconstruction to identify cargo information, and combining big data analysis and machine learning to generate shipping orders, the problem of cumbersome and inaccurate entry of cargo information is solved, and the problem of cumbersome and inaccurate entry of cargo information is achieved. Efficient and accurate logistics management reduces transportation costs and risks.

CN118917674AInactive Publication Date: 2024-11-08YIJIU TECHNOLOGY (TIANJIN) CO LTD

Patent Information

Application Number
CN202411409125.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-10
Publication Date
2024-11-08
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing cargo information entry process is cumbersome and takes a long time, and it is easy to cause inaccurate information due to manual errors, which affects the interests of transportation companies and customers.

Method used

A big data visual digital system for freight management is designed, which uses a combination of customer manual input and automatic identification to collect cargo information, cargo identification is carried out through image processing and three-dimensional reconstruction technology, and a transportation order is generated by combining big data analysis and machine learning. Real-time monitoring and management during transportation.

Benefits of technology

It greatly improves the speed of cargo information entry and processing, reduces human error, improves the efficiency and accuracy of the logistics process, reduces transportation costs, and enhances operational safety and customer satisfaction.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118917674A_ABST
    Figure CN118917674A_ABST
Patent Text Reader

Abstract

The invention relates to the field of data management, in particular to a big data visualization digital system for freight management. According to the technical scheme, the big data visualization digital system for freight management comprises a cargo information acquisition module, an order information generation module, a risk management module, a packaging management module, a transportation monitoring module and an information management module; according to the invention, an automatic identification technology based on image processing and analysis is adopted, and a three-dimensional reconstruction technology is combined, so that the cargo type, the measured weight and the calculated volume can be rapidly identified; compared with traditional manual and weighing equipment, the method has the advantages that the order processing speed and the cargo processing speed are greatly increased, the waiting time is shortened, more accurate information is provided, and personal errors are avoided; meanwhile, the automation technology reduces labor dependence and labor cost, so that enterprises can manage transportation and storage resources more accurately, and resource waste and cost increase are avoided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of data management, and in particular to a big data visualization digital system for freight management. Background Art

[0002] The freight management system is a software system used to manage and optimize the logistics transportation process; it is based on the highway network information management system and uses a variety of technical means such as the global positioning system (GPS), geographic information system (GIS), communication technology, network technology, etc. to provide drivers, traffic management personnel, cargo owners and other personnel with necessary and real-time information, thereby realizing the positioning and tracking of vehicles and goods, cargo loading, vehicle scheduling, safety monitoring and other functions.

[0003] In the process of cargo transportation, it is first necessary to count and enter the cargo information, and check the accuracy and correctness of the cargo information. In the existing cargo information entry process, manual operation methods and cargo information entry and identification equipment with weighing equipment and large machinery are used to enter cargo information. The operation process of these two information entry methods is relatively cumbersome and time-consuming. In addition, due to staff errors or other reasons, the entered cargo information may not be consistent with the actual cargo information, affecting the interests of customers and transportation companies. Summary of the invention

[0004] In order to overcome the existing cargo information entry process, manual operation methods and cargo information entry and identification equipment using weighing equipment and large machinery are used to enter cargo information. These two information entry methods have complicated operation procedures and take a long time to complete. In addition, due to staff errors or other reasons, the entered cargo information may not be consistent with the actual cargo information.

[0005] The technical solution of the present invention is: a big data visualization digital system for freight management, including: The cargo information collection module is used to identify and collect cargo information through manual input by customers and automatic identification, wherein the collected cargo information includes the type of cargo, the quantity of cargo, the weight of cargo, the shipping address of cargo, the receiving address of cargo, the sender information of cargo and the recipient information of cargo; The order information generation module is used to generate a cargo delivery order based on the cargo information collected by the cargo information collection module and using big data analysis technology; The risk management module is used to conduct risk prediction and risk management based on cargo information and cargo delivery order information; The packaging management module is used to monitor and manage the packaging of goods after the goods delivery order is established; The transportation monitoring module is used to monitor and record the transportation process of goods during the transportation of goods; The information management module is used to build a communication network to realize the sharing of information generated by the cargo information collection module, order information generation module, risk management module, packaging management module and transportation monitoring module.

[0006] Preferably, the cargo information collection module includes a client software end and an information collection end. The client software end is installed on the customer's smart terminal device and is used for data access to the information entered by the customer. The information collection end is installed on a device that has passed system security verification and has an image collection function. The information collection end is used for staff to collect images of the cargo.

[0007] Preferably, when the cargo information collection module identifies and collects cargo information through manual input by customers and automatic identification, it includes the following steps: S11: The customer inputs partial cargo information of the cargo to be transported through the client software installed on the smart terminal device, wherein the partial cargo information includes the type of cargo, the quantity of cargo, the weight of cargo, the sender information of the cargo, and the receiver information of the cargo; S12: The cargo information collection module sends the cargo information entered by the customer to the order generation module. The order generation module determines the rationality of the order. When the rationality verification of the order passes, it enters the next stage. If the rationality verification of the order fails, the verification result is fed back to the customer's smart terminal device through the cargo information collection module. S13: The cargo information collection module generates a work plan and displays it on the information collection terminal. The staff uses the information collection terminal to collect images of the cargo according to the work plan; S14: The cargo information collection module processes and recognizes the collected cargo images, wherein the recognized information includes the real type of cargo, the real volume of cargo, the weight range of cargo, the quantity range of cargo and the integrity of cargo; S15: The identification results are sent to the client software end and the information collection end respectively for three-party verification and modification. After the customer and the staff confirm the correctness of the cargo information, the cargo information is archived.

[0008] Preferably, the cargo information collection module includes the following steps when processing and identifying the collected cargo images: S1401: The staff uses the information collection terminal to collect images of the goods from multiple angles and positions to obtain complete image information of the goods; S1402: performing image preprocessing and image feature extraction, wherein the extracted image features include shape, color and texture features; S1403: Use the Faster R-CNN object recognition algorithm to classify and identify the extracted image features and identify the type of goods; S1404: using the collected multi-view images, restoring a three-dimensional model of the cargo through a three-dimensional reconstruction technology, wherein the three-dimensional reconstruction technology used includes an SFM technology and an MVS technology; S1405: Calculate the volume of the three-dimensional model through volume integration operation to obtain the total volume of the cargo; S1406: Classify the goods, divide the goods into different types according to their types, and retrieve historical data to determine the density information of the goods; S1407: Calculate the estimated weight of the cargo according to the density information of each type of cargo, and calculate the total weight of the cargo.

[0009] Preferably, when the order information generating module generates a cargo delivery order based on the cargo information collected by the cargo information collecting module and adopts big data analysis technology, the principle steps include: S21: selecting a plurality of transport nodes between the cargo delivery location and the cargo receiving location, wherein the transport nodes include a transshipment warehouse, a temporary truck stop, and a ferry; S22: Generate multiple transportation route plans based on the selected transportation nodes, and obtain transportation restriction conditions of all transportation route plans through network channels, where the network channels include third-party service providers, social media, and government transportation departments, and the transportation restriction conditions include weather conditions, traffic flow, road conditions, and traffic restriction policies; S23: determining cargo transportation restrictions according to cargo information, screening and eliminating multiple generated transportation route plans, and eliminating transportation route plans that do not meet cargo transportation restrictions, wherein cargo transportation restrictions include cargo type, cargo transportation time requirements, and cargo quantity requirements; S24: Determine the special conditions for cargo transportation according to the cargo type, determine the type of transportation tools required for cargo transportation, retrieve historical order data, and determine the number of transportation tools required for cargo transportation through machine learning and automation technologies; S25: Generate a specific cargo transportation order plan based on the types and quantities of transportation vehicles required for cargo transportation.

[0010] Preferably, when the risk management module performs risk prediction and risk management based on the cargo information and cargo delivery order information, the principle steps of risk prediction include: S31: Collect data, including historical transportation records, cargo types, transportation routes, weather impacts, transportation department data, and third-party logistics data; S32: determining multiple risk factor variables of cargo transportation according to the cargo information, wherein the multiple risk factor variables of cargo transportation include weather conditions, air temperature, transportation time, type of transportation tool, number of transportation tools and road conditions; S33: Calculate the weight factors of different risk factors through big data analysis technology, calculate the risk score based on the weight factors, and then determine the risk level based on the risk score.

[0011] As a preferred embodiment, when the risk management module performs risk prediction and risk management based on the cargo information and cargo delivery order information, the principle steps of risk management are as follows: S41: Estimating the value of goods; S42: Loss estimation is performed based on the cargo value and cargo risk score, where the principle formula for loss estimation is: ; Among them, L is the estimated loss value, price is the value of the goods, Summarize the average value of the same type of goods for historical data; S43: Take out insurance with different insured amounts based on the estimated loss value.

[0012] Preferably, the packaging management module includes a modeling simulation module, which is used to perform modeling simulation on the packaging and generate a cargo packaging plan, wherein the modeling simulation module includes the following steps when working: S51: reading multiple cargo item models obtained by three-dimensional reconstruction technology in step S1404; S52: Inputting weight parameters and compression resistance parameters into the cargo item model; S53: According to the total volume of the cargo calculated in step S1405, containers of different specifications and sizes are selected, and container models of corresponding sizes are retrieved; S54: Using a space segmentation algorithm to gradually fill the container space with the cargo item model according to the cargo shape, size and weight; S55: Calculate cargo load-bearing capacity and confirm the rationality of the loading plan.

[0013] As a preferred embodiment, after completing the cabinet loading scheme design, the modeling simulation module then designs the cabinet loading process scheme, wherein the principle steps are as follows: S61: Read the cargo and container model after loading; S62: Using an A*-based path planning algorithm to perform cargo unloading simulation and obtain a cargo unloading plan; S63: reverse deduction is performed based on the cargo unloading plan to obtain a loading process plan; S64: After each piece of cargo is unloaded, a dynamic programming algorithm is used to calculate the stability of the remaining cargo; S65: When the stability of the goods is low, a suitable reinforcement scheme is selected, and the selected reinforcement scheme is added to the container loading process plan to obtain a final container loading process plan.

[0014] Preferably, after the cargo delivery order is established, the packaging management module adopts a method of collecting video images of the cargo packaging site and tracking the dynamic path of the cargo using image recognition algorithm and image tracking algorithm when monitoring and managing the cargo packaging, thereby monitoring and managing the cargo packaging.

[0015] Preferably, the transport monitoring module includes a real-time communication module, a positioning module and a container monitoring module. The positioning module is used to obtain real-time positioning data of the container, the container monitoring module is used to monitor the status of the container and the items inside the container in real time, and the real-time communication module is used to send the data collected by the positioning module and the container monitoring module to the information management module.

[0016] As a preferred embodiment, when the positioning module obtains the real-time positioning data of the container, the principle steps are as follows: S71: Obtaining real-time positioning data of the container through satellite positioning technology; S72: judging the satellite positioning signal strength, and using a density-based anomaly detection method to judge and identify the positioning data of the container, identifying anomalies in the positioning data, and judging the positioning anomaly when the proportion of abnormal data in the positioning data exceeds a set threshold; S73: Obtain relevant data from the Internet, such as location information shared on social media, query records of online maps, etc.; S74: Integrate data from different data sources to form a location data set, and verify and filter the acquired data to resolve data conflicts and redundancies; S75: Format, standardize and normalize the data; S76: Analyze and identify the location data, the movement patterns of the corresponding users, the plant locations and the dwell time information using statistical methods and machine learning algorithms; S77: Filling the positioning data in the position data set into the acquired real-time positioning data; S78: identifying and analyzing data conflicts in the filled real-time positioning data by a machine learning algorithm to obtain optimized positioning data; S79: Use the analysis results in step S76 to detect, correct and fill in the optimized positioning data to obtain accurate positioning data.

[0017] Preferably, the container monitoring module includes a monitoring camera, a data storage terminal and a door monitoring structure. The monitoring camera is arranged inside the container. The monitoring camera is used to accurately identify the internal image of the container. The door monitoring structure is used to monitor the opening and closing of the container door in real time. The data storage terminal is used to back up the data results of the monitoring camera and the door monitoring structure, wherein the data storage terminal is connected to the monitoring camera and the door monitoring structure signal through a unidirectional gateway.

[0018] Preferably, the door monitoring structure includes a sensing module and an analysis module. The sensing modules are arranged in two groups. The two groups of sensing modules are respectively arranged on the inner walls of the two groups of container doors. The two groups of sensing modules communicate with each other through NFC communication technology, the two groups of sensing modules and the analysis module communicate with each other through Bluetooth communication technology, and the analysis module is connected with the positioning module by signal.

[0019] As a preferred embodiment, when the door monitoring structure performs real-time monitoring on the opening and closing of the container door, the working principle is as follows: S81: The two sets of sensing modules are connected via NFC technology and mutually authenticated via a heartbeat mechanism; S82: When any one of the two groups of sensing modules fails in verification, an alarm message is sent to the analysis module, and the analysis module records the alarm message and transmits the alarm message to the data storage terminal; S83: The analysis module retrieves the positioning data in the positioning module to check whether the container is at the checkpoint; S84: If the container is not at the inspection point, the inspection result is recorded and sent to the data storage end for backup.

[0020] Preferably, the information management module includes a blockchain network, which is composed of multiple nodes. The multiple nodes are responsible for data storage, verification and transmission. The client software end, information collection end, packaging management module, real-time communication module, positioning module and analysis module are all nodes in the blockchain network. The client software end, information collection end, packaging management module, real-time communication module, positioning module and analysis module interact with data through the blockchain network. Smart contracts are deployed in the blockchain network, wherein the order number is used as the key to encrypt data in the blockchain network, and the blockchain network records the access permission information of each data item through the distributed ledger technology of the blockchain.

[0021] Beneficial effects of the present invention: 1. By adopting the automatic intelligent recognition technology based on image processing and analysis, and cooperating with a variety of modern technologies such as three-dimensional reconstruction technology, it is possible to quickly identify the type, measure the weight and calculate the volume of goods. Compared with the traditional manual operation and the operation of identifying and entering cargo information with weighing equipment and large-scale mechanical cargo information input identification equipment, it greatly improves the speed of order processing and cargo processing, making the logistics process more efficient, reducing waiting time, and being able to obtain relevant information of goods more accurately, avoiding errors and data errors caused by human factors. At the same time, the application of automatic recognition technology reduces dependence on manual labor and reduces the investment of enterprises in manpower. It can also more accurately understand the type, weight and volume of goods, so as to more reasonably arrange resources in transportation, warehousing and other links, avoiding waste of resources and rising costs; 2. When assessing cargo transportation risks, introducing the potential loss scale and its corresponding weight factors can comprehensively consider the far-reaching impact of risk events once they are triggered, significantly improving the precision and reliability of risk assessment. This approach not only deepens the cargo transporter's understanding of potential risks and losses, but also prompts them to implement a two-way dynamic assessment strategy based on the actual value of the cargo and the specific risk level during transportation. Based on this, the cargo transporter can tailor insurance plans and reasonably set insurance amounts at different levels, thereby effectively buffering the economic losses caused by accidents to cargo transportation and enhancing the safety and resilience of overall operations; 3. When transporting goods, loading the goods into the container is an important step, which affects the overall efficiency and safety of the transportation. When loading goods, the space utilization rate and loading efficiency of the goods are the most important influencing factors. The present invention is set to obtain the size, shape and weight information of the goods when entering the goods information, and then obtain a three-dimensional model of the goods, and use a variety of technologies to simulate the loading of goods on the obtained three-dimensional model to obtain an efficient solution for cargo loading, and use an A*-based path planning algorithm to simulate unloading, and obtain a process solution for cargo loading after reverse operation, and at the same time perform cargo stability identification to help generate a cargo reinforcement solution, thereby increasing the efficiency of cargo loading, improving the space utilization rate of the container, reducing transportation costs, improving transportation efficiency, and increasing the safety of cargo transportation, reducing the risk of loss of the transporter, and increasing customer satisfaction; 4. In the process of transporting goods, when they are in the state of sea transportation, it is often necessary to entrust other transport parties to transport the goods. If there is no special supervisor, the safety of the goods is difficult to guarantee, and the goods are prone to loss. By setting up a sensing module based on NFC technology and a heartbeat mechanism to monitor the opening and closing status of the container, the special communication effective range of NFC technology within ten centimeters can be used to establish an implicit monitoring chain. When the door is opened, the distance between the two sets of sensing modules exceeds the effective distance of NFC communication, and the connection is disconnected, the opening of the container can be detected, and there is no mechanical structure locking and connection, which is not easy to be destroyed, thereby preventing the goods from being stolen, tampered with or damaged, and ensuring the safety of cargo transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 What is shown is a schematic diagram of the structure of the big data visualization digital system for freight management of the present invention; Figure 2 The diagram shows the workflow of the cargo information collection module in the big data visualization digital system for cargo management of the present invention; Figure 3 What is shown is a schematic diagram of the workflow of the risk management module in the big data visualization digital system for freight management of the present invention; Figure 4 Shown is a partial workflow diagram of the packaging management module in the big data visualization digital system for freight management of the present invention; Figure 5 Shown is a partial workflow diagram of the packaging management module in the big data visualization digital system for freight management of the present invention; Figure 6 Shown is a schematic diagram of the structure of the transport monitoring module in the big data visualization digital system for freight management of the present invention. DETAILED DESCRIPTION

[0023] The present invention provides a new industry full-link multi-link collaborative operation mode, intelligently optimizes the supply chain process, and greatly improves operational efficiency. In the order generation module, risk management module, and packaging management module of this solution, all are automated operations. The automated operation of the full chain and multiple links solves the problem: helping freight forwarding companies to quickly respond to customer needs, improve service quality and satisfaction, achieve efficient resource integration and collaboration, and reduce costs and risks. The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0024] Embodiment 1 See also Figure 1 The present invention provides an embodiment: a big data visualization digital system for freight management, comprising: The cargo information collection module is used to identify and collect cargo information through manual input by customers and automatic identification, wherein the collected cargo information includes the type of cargo, the quantity of cargo, the weight of cargo, the shipping address of cargo, the receiving address of cargo, the sender information of cargo and the recipient information of cargo; The order information generation module is used to generate a cargo delivery order based on the cargo information collected by the cargo information collection module and using big data analysis technology; The risk management module is used to conduct risk prediction and risk management based on cargo information and cargo delivery order information; The packaging management module is used to monitor and manage the packaging of goods after the goods delivery order is established; The transportation monitoring module is used to monitor and record the transportation process of goods during the transportation of goods; The information management module is used to build a communication network to realize the sharing of information generated by the cargo information collection module, order information generation module, risk management module, packaging management module and transportation monitoring module.

[0025] Among them, the order information generation module, risk management module and information management module are all deployed on the server side of the freight management party.

[0026] Embodiment 2 See also Figure 2 In the big data visualization digital system for freight management based on the first embodiment, the cargo information collection module includes a client software end and an information collection end. The client software end is software or a small program application installed on the customer's smart terminal device such as a smart phone, a computer, etc. The client software end is used to enter and verify the customer's identity authority information, so that the order application and order information entered by the customer through the software and the small program application are bound to the customer's identity authority. The information collection end is a data collection device that has been verified and granted access authority. The information collection end can be a dedicated device or other smart device that has been modified by the system. The information collection end is held by the staff. After receiving the work task notification, the staff carries the device equipped with the information collection end to the cargo delivery location to collect and proofread the cargo information.

[0027] The cargo information collection module includes the following steps when identifying and collecting cargo information through manual input by customers and automatic identification: S11: The customer inputs partial cargo information of the cargo to be transported through the client software installed on the smart terminal device, wherein the partial cargo information includes the type of cargo, the quantity of cargo, the weight of cargo, the sender information of the cargo, and the receiver information of the cargo; S12: The cargo information collection module sends the cargo information entered by the customer to the order generation module. The order generation module determines the rationality of the order. When the rationality verification of the order passes, it enters the next stage. If the rationality verification of the order fails, the verification result is fed back to the customer's smart terminal device through the cargo information collection module. S13: The cargo information collection module generates a work plan and displays it on the information collection terminal. The staff uses the information collection terminal to collect images of the cargo according to the work plan; S14: The cargo information collection module processes and recognizes the collected cargo images, wherein the recognized information includes the real type of cargo, the real volume of cargo, the weight range of cargo, the quantity range of cargo and the integrity of cargo; S15: The identification results are sent to the client software end and the information collection end respectively for three-party verification and modification. After the customer and the staff confirm the correctness of the cargo information, the cargo information is archived.

[0028] Preferably, the order generation module includes the following steps when judging the rationality of the order: S1201: Checking the basic information of the order, including checking the integrity of the information of the sender, the receiver, the goods, and the rationality of the special transportation requirements of the goods. By checking the integrity of the information of the sender, receiver, and goods, and the rationality of the special transportation requirements, the basic information of the order is ensured to be correct, which provides a solid foundation for the subsequent logistics transportation. The accuracy of the information is directly related to the efficiency and accuracy of the logistics service, avoiding transportation delays or wrong delivery caused by incomplete or incorrect information. S1202: Estimate the transportation time based on the information of the sender and the receiver of the goods, and determine the validity period of the goods based on the type of goods. Finally, further determine whether the validity period of the goods meets the transportation time requirements. By estimating the transportation time and determining whether the validity period of the goods meets the time requirements, the timeliness of the goods is effectively guaranteed. This is especially important for fresh food, medicine and other goods that require strict control of the shelf life. It can reduce the damage or expiration of goods caused by long transportation time, thereby protecting the rights and interests of consumers and the reputation of merchants. S1203: Compliance check, including checking whether the transported items are items permitted to be transported under the national laws of the corresponding countries and checking the completeness of the compliance documents of the transported items, ensuring that the transported items comply with the requirements of national laws and regulations and that the relevant compliance documents are complete, which helps enterprises comply with laws and regulations and avoid legal risks and economic losses caused by illegal transportation; S1204: Search the historical order records of the corresponding customers to determine whether the customer's credit status is good; by searching the customer's historical order records and evaluating their credit status, it is helpful for the enterprise to identify and manage potential risky customers. For customers with good credit, better services and more flexible payment and transportation conditions can be provided; and for customers with poor credit, corresponding risk control measures can be taken, such as strengthening audits, increasing margin requirements, etc., so as to protect the interests of the enterprise from being harmed.

[0029] Specifically, the order generation module automatically judges the rationality of the order through multiple verification operations such as checking order information, checking the timeliness of goods, checking compliance and legality, and checking customer credibility. While improving the accuracy of order processing, it can also improve the efficiency of order processing, optimize resource allocation, and reduce the labor and time costs of order processing. In addition, the results of rationality judgment can also provide data support for order data processing, analysis and decision-making.

[0030] Preferably, the cargo information collection module includes the following steps when processing and identifying the collected cargo images: S1401: The staff uses the information collection terminal to collect images of the goods from multiple angles and positions to obtain complete image information of the goods; S1402: performing image preprocessing and image feature extraction, wherein the extracted image features include shape, color and texture features, which will be used for subsequent cargo classification and volume and weight estimation, wherein the collected images are subjected to preprocessing operations such as denoising, contrast enhancement, edge detection, etc., to improve image quality and extract useful features; S1403: using the Faster R-CNN object recognition algorithm to classify and recognize the extracted image features to identify the type of goods, wherein the Faster R-CNN object recognition algorithm is trained using an existing goods image dataset; S1404: using the collected multi-view images, restoring a three-dimensional model of the cargo through a three-dimensional reconstruction technology, wherein the three-dimensional reconstruction technology used includes an SFM technology and an MVS technology; S1405: Calculate the volume of the three-dimensional model through volume integration operation to obtain the total volume of the cargo; S1406: Classify the goods, divide the goods into different types according to their types, and retrieve historical data to determine the density information of the goods; S1407: Calculate the estimated weight of the cargo according to the density information of each type of cargo, and calculate the total weight of the cargo.

[0031] Specifically, by adopting automated intelligent recognition technology based on image processing and analysis, and coordinating it with a variety of modern technologies such as three-dimensional reconstruction technology, it is possible to quickly identify the type, measure the weight and calculate the volume of goods. Compared with traditional manual operations and operations that use weighing equipment and large-scale machinery to enter cargo information, it greatly improves the speed of order processing and cargo processing, making the logistics process more efficient, reducing waiting time, and being able to more accurately obtain relevant information about the goods, avoiding errors and data errors caused by human factors. At the same time, the application of automated recognition technology reduces dependence on manual labor and reduces the company's investment in manpower. It can also more accurately understand the type, weight, volume and other information of goods, thereby more reasonably arranging resources in transportation, warehousing and other links, avoiding waste of resources and rising costs.

[0032] Embodiment 3 In the big data visualization digital system for freight management based on the first embodiment, when the order information generation module generates a freight delivery order based on the freight information collected by the freight information collection module and using big data analysis technology, the principle steps include: S21: Select multiple transport nodes between the place where the goods are shipped and the place where the goods are received. The transport nodes are places where the transport equipment needs to be replaced, temporarily stored, inspected and maintained during the transportation of goods, including transshipment warehouses, temporary truck stops and ferry crossings; S22: According to the selected transport nodes and the conditions of the selected transport nodes, one of multiple path planning algorithms such as A* algorithm, Dijkstra algorithm, ant colony algorithm, genetic algorithm, etc. is selected to perform path planning, generate multiple transport path plans, and obtain multiple transport restriction conditions in different transport path plans including but not limited to weather conditions, traffic flow, road conditions, and traffic restriction policies through multiple network channels such as third-party service providers, social media, and government transportation departments; S23: determining the cargo type, cargo transportation time requirement, and cargo quantity requirement according to the cargo information, screening and eliminating the generated multiple transportation path plans, and eliminating the transportation path plans that do not meet the cargo transportation restrictions; S24: Determine the special conditions for cargo transportation according to the type of cargo, determine the type of transportation tools that need to be dispatched for cargo transportation, retrieve historical order data, and determine the number of transportation tools that need to be dispatched for cargo transportation through machine learning and automation technology, that is, select different models and quantities of container transportation equipment based on multiple requirements such as cargo weight requirements, special cargo storage requirements, and cargo volume requirements; S25: Generate a specific cargo transportation order plan based on the types and quantities of transportation vehicles required for cargo transportation, and when there are multiple cargo transportation order plans that meet the requirements, send all of the multiple cargo transportation order plans to the customer for selection.

[0033] Among them, the order management module also has the following functions: A11: When generating a freight transport order plan, retrieve historical data and use AI-based big data analysis technology to estimate the cost of each link in the freight transport process. Based on the estimated cost of each link in the freight transport process, generate a total freight transport quotation and send it to the customer together with the freight transport order plan. A12: Read the customer's transaction account information, and automatically settle the payment based on the customer's transaction account information and the payee's account change information after the order is completed; A13: After the order is completed, an invoice will be issued based on the transaction information and the preset template.

[0034] Embodiment 4 See also Figure 3 In this embodiment, when the risk management module performs risk prediction and risk management based on the cargo information and cargo delivery order information, the principle steps of risk prediction include: S31: Collect data, including historical transportation records, cargo types, transportation routes, weather impacts, transportation department data, and third-party logistics data; S32: determining multiple risk factor variables of cargo transportation according to the cargo information, wherein the multiple risk factor variables of cargo transportation include weather conditions, air temperature, transportation time, type of transportation tool, number of transportation tools and road conditions; S33: Calculate the weight factors of different risk factors through big data analysis technology, that is, analyze and model historical data through Bayesian algorithm, decision tree algorithm, neural network algorithm and other data mining technologies, obtain the impact of different risk factors on cargo transportation, and calculate the risk score according to the weight factor, and then judge the risk level according to the risk score. The calculation principle formula of the risk score is: ,in, is the weight factor of the nth risk factor variable, is the occurrence probability of the nth risk factor variable, is a constant, It is the ratio of the estimated loss caused by the occurrence of the nth risk factor variable to the total value of the goods.

[0035] Furthermore, when the risk management module performs risk prediction and risk management based on the cargo information and cargo delivery order information, the principle steps of risk management are as follows: S41: Estimating the value of goods; S42: Loss estimation is performed based on the cargo value and cargo risk score, where the principle formula for loss estimation is: ; Among them, L is the estimated loss value, price is the value of the goods, Summarize the average value of the same type of goods for historical data; S43: Take out insurance with different insured amounts based on the estimated loss value.

[0036] Specifically, when assessing cargo transportation risks, the introduction of potential loss scale and its corresponding weight factors can comprehensively consider the far-reaching impact of risk events once they are triggered, significantly improving the precision and reliability of risk assessment. This approach not only deepens the cargo transporter's understanding of potential risks and losses, but also prompts them to implement a two-way dynamic assessment strategy based on the actual value of the cargo and the specific risk level during transportation; based on this, the cargo transporter can tailor insurance plans and reasonably set insurance amounts at different levels, thereby effectively buffering the economic losses caused by accidents to cargo transportation and enhancing the safety and resilience of overall operations.

[0037] Embodiment 5 See also Figure 4-Figure 5 In this embodiment, the packaging management module includes a modeling simulation module, which is used to model and simulate the packaging to generate a cargo packaging plan. When the modeling simulation module is working, it includes the following steps: S51: reading multiple cargo item models obtained by three-dimensional reconstruction technology in step S1404; S52: Inputting weight parameters and compression resistance parameters into the cargo item model; S53: According to the total volume of the cargo calculated in step S1405, containers of different specifications and sizes are selected, and container models of corresponding sizes are retrieved; S54: Based on the shape, size and weight of the goods, the space segmentation algorithm is used to gradually fill the container space with the goods model. That is, when a piece of goods is placed in the container, it is divided into three spaces: front, right and top. The filling continues until no more goods can be added. At the same time, the multi-packing simulation algorithm and software on the market can be used to generate the packing plan; S55: Calculate cargo load-bearing capacity and confirm the rationality of the loading plan.

[0038] Furthermore, after completing the design of the loading scheme, the modeling simulation module will then design the loading process scheme, wherein the principle steps are as follows: S61: Read the cargo and container model after loading; S62: Using an A*-based path planning algorithm to perform cargo unloading simulation and obtain a cargo unloading plan; S63: reverse deduction is performed based on the cargo unloading plan to obtain a loading process plan; S64: After each piece of cargo is unloaded, a dynamic programming algorithm is used to calculate the stability of the remaining cargo; S65: When the stability of the goods is low, a suitable reinforcement scheme is selected, and the selected reinforcement scheme is added to the container loading process plan to obtain a final container loading process plan.

[0039] Specifically, when transporting goods, loading the goods into the container is an important step, which affects the overall efficiency and safety of the transportation. When loading goods, the space utilization rate and loading efficiency of the goods are the most important influencing factors. The present invention is arranged to obtain the size, shape and weight information of the goods when entering the goods information, and then obtain a three-dimensional model of the goods, and simulate the loading of the goods with the obtained three-dimensional model through multiple technologies to obtain an efficient solution for cargo loading, and perform unloading simulation through an A*-based path planning algorithm, and obtain a process solution for cargo loading after reverse operation, and simultaneously perform cargo stability identification to help generate a cargo reinforcement solution, thereby improving the efficiency of cargo loading, and improving the space utilization rate of the container, reducing transportation costs, improving transportation efficiency, and increasing the safety of cargo transportation, reducing the risk of loss of the transporter and increasing customer satisfaction.

[0040] Furthermore, after the cargo delivery order is established, the packaging management module uses a method of collecting video images of the cargo packaging site and tracking the dynamic path of the cargo using image recognition algorithm and image tracking algorithm when monitoring and managing the cargo packaging, thereby monitoring and managing the cargo packaging.

[0041] Embodiment 6 See also Figure 6 In this embodiment, the transport monitoring module includes a real-time communication module, a positioning module and a container monitoring module. The positioning module is used to obtain real-time positioning data of the container. The container monitoring module is used to monitor the status of the container and the items inside the container in real time. The real-time communication module is used to send the data collected by the positioning module and the container monitoring module to the information management module.

[0042] Among them, when the positioning module obtains the real-time positioning data of the container, the principle steps are as follows: S71: Obtaining real-time positioning data of the container through satellite positioning technology; S72: judging the satellite positioning signal strength, and using a density-based anomaly detection method to judge and identify the positioning data of the container, identifying anomalies in the positioning data, and judging the positioning anomaly when the proportion of abnormal data in the positioning data exceeds a set threshold; S73: Obtain relevant data from the Internet, such as location information shared on social media, query records of online maps, etc.; S74: Integrate data from different data sources to form a location data set, and verify and filter the acquired data to resolve data conflicts and redundancies; S75: Format, standardize and normalize the data; S76: Analyze and identify the location data, the movement patterns of the corresponding users, the plant locations and the dwell time information using statistical methods and machine learning algorithms; S77: Filling the positioning data in the position data set into the acquired real-time positioning data; S78: identifying and analyzing data conflicts in the filled real-time positioning data by a machine learning algorithm to obtain optimized positioning data; S79: Use the analysis results in step S76 to detect, correct and fill in the optimized positioning data to obtain accurate positioning data.

[0043] Specifically, by utilizing a variety of automation technologies such as big data technology, statistical methods, and machine learning algorithms, the obtained container positioning data can be analyzed and processed, and erroneous data in the positioning data can be eliminated to increase the accuracy of positioning. At the same time, it can prevent the positioning of goods from being lost or erroneous due to weather or weak positioning signals in the sea area, thereby improving the reliability and accuracy of positioning, and helping the cargo transporter to better grasp the real-time location information of the cargo, thereby improving transportation efficiency and safety. At the same time, in the present invention, data collection and monitoring are real-time to ensure the timeliness and accuracy of information.

[0044] Among them, the container monitoring module includes a monitoring camera, a data storage terminal and a door monitoring structure. The monitoring camera is set inside the container. The monitoring camera is used to accurately identify the internal image of the container. The door monitoring structure is used to monitor the opening and closing of the container door in real time. The data storage terminal is used to back up the data results of the monitoring camera and the door monitoring structure. Among them, the data storage terminal is connected to the monitoring camera and the door monitoring structure signal through a unidirectional gateway.

[0045] Specifically, by setting up a one-way communication method at the data storage end, on the one hand, the risk of data loss can be reduced and the integrity and accuracy of the data can be ensured; on the other hand, by limiting the flow of data, the one-way communication system reduces the risk of external threats invading the system through the backup process, thereby improving the security of the overall network, reducing network security risks, ensuring the security of backup data, and increasing the effectiveness of monitoring goods during transportation.

[0046] Furthermore, the door monitoring structure includes a sensing module and an analysis module. The sensing modules are arranged in two groups. The two groups of sensing modules are respectively arranged on the inner walls of the two groups of container doors. The two groups of sensing modules communicate with each other through NFC communication technology, and the two groups of sensing modules and the analysis module communicate with each other through Bluetooth communication technology. The analysis module is connected with the positioning module by signal.

[0047] Furthermore, when the door monitoring structure performs real-time monitoring on the opening and closing of the container door, the working principle is as follows: S81: The two sets of sensing modules are connected via NFC technology and mutually authenticated via a heartbeat mechanism; S82: When any one of the two groups of sensing modules fails in verification, an alarm message is sent to the analysis module, and the analysis module records the alarm message and transmits the alarm message to the data storage terminal; S83: The analysis module retrieves the positioning data in the positioning module to check whether the container is at the checkpoint; S84: If the container is not at the inspection point, the inspection result is recorded and sent to the data storage end for backup.

[0048] Specifically, in the process of transporting goods, when they are in the sea transportation state, it is often necessary to entrust other transport parties to transport the goods. If there is no special supervisor, the safety of the goods is difficult to guarantee, and the goods are prone to loss. By setting up a sensing module based on NFC technology and a heartbeat mechanism to monitor the opening and closing status of the container, the special communication effective range of NFC technology within ten centimeters can be used to establish an implicit monitoring chain. When the door is opened, the distance between the two sets of sensing modules exceeds the effective distance of NFC communication, and the connection is disconnected. The opening of the container can be detected, and there is no mechanical structure locking and connection, which is not easy to be destroyed, thereby preventing the goods from being stolen, tampered with or damaged, and ensuring the safety of cargo transportation.

[0049] Embodiment 7 In the big data visualization digital system for freight management based on Example 1, the information management module includes a blockchain network, which is composed of multiple nodes. The multiple nodes are responsible for data storage, verification and transmission. The client software end, information collection end, packaging management module, real-time communication module, positioning module and analysis module are all nodes in the blockchain network. The client software end, information collection end, packaging management module, real-time communication module, positioning module and analysis module interact with data through the blockchain network. Smart contracts are deployed in the blockchain network, wherein the order number is used as the key to encrypt data in the blockchain network, and the blockchain network records the access permission information of each data item through the distributed ledger technology of the blockchain.

[0050] Among them, by using blockchain technology to establish a communication network between customers, enterprises, and transportation units, the decentralized nature of blockchain can enable all participants to access the same information, allowing customers to view their order status in real time, and enterprises can track the location and transportation status of transport vehicles, thereby improving the transparency of the entire supply chain. At the same time, through the immutability of blockchain-recorded transactions and the transparency of data, a higher level of trust can be established between customers and enterprises; once any information is recorded on the blockchain, it cannot be tampered with, thereby reducing the risk of fraud and information asymmetry.

[0051] The blockchain technology of the present invention can effectively eliminate information asymmetry, improve market transparency and resource utilization, which are the general advantages and characteristics of blockchain technology. There is no need for manual response to information, etc. Customers can see all information together through blockchain and prevent tampering. It solves the cumbersome processes and communication barriers in the traditional model and improves work efficiency.

[0052] In the present invention, relevant technologies of digital human customers can also be introduced, and artificial intelligence can be used to realize corresponding intelligent services. Artificial intelligence can replace traditional manual work to handle the route generation, freight rate push, real-time positioning of the transportation process, warehouse reminders before arrival, collaborative communication between the shipper and the transportation end and the target end, office work, and amount transactions, invoices and other operations on the system. Specific example processes include: creating orders, foreign trade booking, loading containers, reporting data, customs declaration, bill of lading supplement (including customs clearance number application, insurance coverage, etc.), sailing, settlement (including online payment), release, and arrival at the port. The above example links are shared in real time with relevant units and individuals, such as customers, fleets, customs brokers, drivers, shipping companies, yards, etc., and the entire system is integrated, and is automatically operated and pushed through artificial intelligence, without the need for manual management. The above matters can be comprehensively and intelligently handled through the above-mentioned visual digital system.

[0053] The system establishment and training process is as follows: 1). Clarify the various steps of the transportation process and define the specific tasks and data requirements for each step. As mentioned above, the transportation process includes the following steps: Create an order; Foreign trade booking; Loading cabinets; Report data; customs clearance; Supplementary materials for bill of lading (including application for customs clearance number, insurance, etc.); sail; Settlement of fees (including online payment); Release the order; Arrived at port.

[0054] 2). Data collection and processing: Data Type: Order data: customer information, product information, quantity, price, etc.; Shipping data: vessel information, routes, space, etc.; Customs declaration data: customs declaration form, commodity details, tariff information, etc.; Financial data: expense details, payment records, invoices, etc.; Logistics tracking data: container status, transportation status, port information, etc.; Other relevant data: insurance policy number, customs clearance number, etc.; Data processing: Data cleaning: dealing with missing values, duplicate values ​​and data format consistency issues; Data conversion: convert data in different formats into a unified standard; Data storage: Use a database (such as SQL, NoSQL) to store processed data; 3). Model building and training Model Type: Prediction model: predicting transportation time, cost, etc.; Optimization model: optimize container loading and route selection, etc.; Classification model: risk warning, anomaly detection, etc. (Including but not limited to the above models, which can be added and integrated based on actual needs later) Model training: Use machine learning algorithms (such as regression, classification, clustering, etc.); Use deep learning algorithms (such as neural networks); Training based on large-scale data, using historical transportation data, external data, etc. 4). Visualization: Use charts, maps, dashboards, etc. to display data from all aspects of the transportation process; Update and monitor shipping status in real time; Provide interactive functions, users can query detailed information, perform data analysis, etc. 5). System Integration: System architecture: Front-end: Build user interfaces based on web technologies (such as React, Vue.js); Backend: Use microservice architecture to develop backend services based on Node.js, Python and other technologies; Middleware: message queues (such as RabbitMQ), caches (such as Redis), etc. Databases: relational databases (such as MySQL) and non-relational databases (such as MongoDB); Integrated digital human model: Collection and training module: use digital human models for data collection and training; Model interface: Provides a standardized API interface to facilitate front-end and back-end calls; Monitoring and maintenance: Regularly evaluate and update the model to ensure its accuracy and reliability.

[0055] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of those skilled in the art without departing from the spirit of the present invention.

Claims

1. A big data visualization digital system for freight management; characterized by: Included are: The cargo information collection module is used to identify and collect cargo information through manual input by customers and automatic identification, wherein the collected cargo information includes the type of cargo, the quantity of cargo, the weight of cargo, the shipping address of cargo, the receiving address of cargo, the sender information of cargo and the recipient information of cargo; The order information generation module is used to generate a cargo delivery order based on the cargo information collected by the cargo information collection module and using big data analysis technology; The risk management module is used to conduct risk prediction and risk management based on cargo information and cargo delivery order information; The packaging management module is used to monitor and manage the packaging of goods after the goods delivery order is established; The transportation monitoring module is used to monitor and record the transportation process of goods during the transportation of goods; The information management module is used to build a communication network to realize the sharing of information generated by the cargo information collection module, the order information generation module, the risk management module, the packaging management module and the transportation monitoring module; Among them, the cargo information collection module includes a client software end and an information collection end. The client software end is installed on the customer's smart terminal device and is used to access the information entered by the customer. The information collection end is installed on a device that has passed the system security verification and has an image collection function. The information collection end is used by the staff to collect images of the cargo.

2. The big data visualization digital system for freight management according to claim 1 is characterized by: The cargo information collection module includes the following steps when identifying and collecting cargo information through manual input by customers and automatic identification: S11: The customer inputs partial cargo information of the cargo to be transported through the client software installed on the smart terminal device, wherein the partial cargo information includes the type of cargo, the quantity of cargo, the weight of cargo, the sender information of the cargo, and the receiver information of the cargo; S12: The cargo information collection module sends the cargo information entered by the customer to the order generation module. The order generation module determines the rationality of the order. When the rationality verification of the order passes, it enters the next stage. If the rationality verification of the order fails, the verification result is fed back to the customer's smart terminal device through the cargo information collection module. S13: The cargo information collection module generates a work plan and displays it on the information collection terminal. The staff uses the information collection terminal to collect images of the cargo according to the work plan; S14: The cargo information collection module processes and recognizes the collected cargo images, wherein the recognized information includes the real type of cargo, the real volume of cargo, the weight range of cargo, the quantity range of cargo and the integrity of cargo; S15: The identification results are sent to the client software end and the information collection end respectively for three-party verification and modification. After the customer and the staff confirm the correctness of the cargo information, the cargo information is archived.

3. The big data visualization digital system for freight management according to claim 2 is characterized by: The cargo information collection module includes the following steps when processing and identifying the collected cargo images: S1401: The staff uses the information collection terminal to collect images of the goods from multiple angles and positions to obtain complete image information of the goods; S1402: performing image preprocessing and image feature extraction, wherein the extracted image features include shape, color and texture features; S1403: Use the Faster R-CNN object recognition algorithm to classify and identify the extracted image features and identify the type of goods; S1404: using the collected multi-view images, restoring a three-dimensional model of the cargo through a three-dimensional reconstruction technology, wherein the three-dimensional reconstruction technology used includes an SFM technology and an MVS technology; S1405: Calculate the volume of the three-dimensional model through volume integration operation to obtain the total volume of the cargo; S1406: Classify the goods, divide the goods into different types according to their types, and retrieve historical data to determine the density information of the goods; S1407: Calculate the estimated weight of the cargo according to the density information of each type of cargo, and calculate the total weight of the cargo.

4. The big data visualization digital system for freight management according to claim 3 is characterized by: When the order information generation module generates a cargo delivery order based on the cargo information collected by the cargo information collection module and using big data analysis technology, the principle steps include: S21: selecting a plurality of transport nodes between the cargo delivery location and the cargo receiving location, wherein the transport nodes include a transshipment warehouse, a temporary truck stop, and a ferry; S22: Generate multiple transportation route plans based on the selected transportation nodes, and obtain transportation restriction conditions of all transportation route plans through network channels, where the network channels include third-party service providers, social media, and government transportation departments, and the transportation restriction conditions include weather conditions, traffic flow, road conditions, and traffic restriction policies; S23: determining cargo transportation restrictions according to cargo information, screening and eliminating multiple generated transportation route plans, and eliminating transportation route plans that do not meet cargo transportation restrictions, wherein cargo transportation restrictions include cargo type, cargo transportation time requirements, and cargo quantity requirements; S24: Determine the special conditions for cargo transportation according to the cargo type, determine the type of transportation tools that need to be dispatched for cargo transportation, retrieve historical order data, and determine the number of transportation tools that need to be dispatched for cargo transportation through machine learning technology and automation technology; S25: Generate a specific cargo transportation order plan based on the types and quantities of transportation vehicles required for cargo transportation.

5. The big data visualization digital system for freight management according to claim 4 is characterized by: When the risk management module performs risk prediction and risk management based on cargo information and cargo delivery order information, the principle steps for risk prediction include: S31: Collect data, including historical transportation records, cargo types, transportation routes, weather impacts, transportation department data, and third-party logistics data; S32: determining multiple risk factor variables of cargo transportation according to the cargo information, wherein the multiple risk factor variables of cargo transportation include weather conditions, air temperature, transportation time, type of transportation tool, number of transportation tools and road conditions; S33: Calculate the weight factors of different risk factors through big data analysis technology, calculate the risk score based on the weight factors, and then determine the risk level based on the risk score.

6. A big data visualization digital system for freight management according to claim 5, characterized in that: The packaging management module includes a modeling simulation module, which is used to model and simulate the packaging and generate a cargo packaging plan. When the modeling simulation module is working, it includes the following steps: S51: reading multiple cargo item models obtained by three-dimensional reconstruction technology in step S1404; S52: Inputting weight parameters and compression resistance parameters into the cargo item model; S53: According to the total volume of the cargo calculated in step S1405, containers of different specifications and sizes are selected, and container models of corresponding sizes are retrieved; S54: Using a space segmentation algorithm to gradually fill the container space with the cargo item model according to the cargo shape, size and weight; S55: Calculate cargo load-bearing capacity and confirm the rationality of the loading plan.

7. The big data visualization digital system for freight management according to claim 6 is characterized by: After completing the loading scheme design, the modeling simulation module will then design the loading process scheme. The principle steps are as follows: S61: Read the cargo and container model after loading; S62: Using an A*-based path planning algorithm to perform cargo unloading simulation and obtain a cargo unloading plan; S63: reverse deduction is performed based on the cargo unloading plan to obtain a loading process plan; S64: After each piece of cargo is unloaded, a dynamic programming algorithm is used to calculate the stability of the remaining cargo; S65: When the stability of the goods is low, a suitable reinforcement scheme is selected, and the selected reinforcement scheme is added to the container loading process plan to obtain a final container loading process plan.

8. The big data visualization digital system for freight management according to claim 7 is characterized by: The transport monitoring module includes a real-time communication module, a positioning module and a container monitoring module. The positioning module is used to obtain real-time positioning data of the container. The container monitoring module is used to monitor the status of the container and the items inside the container in real time. The real-time communication module is used to send the data collected by the positioning module and the container monitoring module to the information management module.

9. A big data visualization digital system for freight management according to claim 8, characterized in that: When the positioning module obtains the real-time positioning data of the container, the principle steps are as follows: S71: Obtaining real-time positioning data of the container through satellite positioning technology; S72: judging the satellite positioning signal strength, and using a density-based anomaly detection method to judge and identify the positioning data of the container, identifying anomalies in the positioning data, and judging the positioning anomaly when the proportion of abnormal data in the positioning data exceeds a set threshold; S73: Obtain relevant data from the Internet, such as location information shared on social media, query records of online maps, etc.; S74: Integrate data from different data sources to form a location data set, and verify and filter the acquired data to resolve data conflicts and redundancies; S75: Format, standardize and normalize the data; S76: Analyze and identify the location data, the movement patterns of the corresponding users, the plant locations and the dwell time information using statistical methods and machine learning algorithms; S77: Filling the positioning data in the position data set into the acquired real-time positioning data; S78: identifying and analyzing data conflicts in the filled real-time positioning data by a machine learning algorithm to obtain optimized positioning data; S79: Use the analysis results in step S76 to detect, correct and fill in the optimized positioning data to obtain accurate positioning data.

10. A big data visualization digital system for freight management according to claim 9, characterized in that: The container monitoring module includes a monitoring camera, a data storage terminal and a door monitoring structure. The monitoring camera is arranged inside the container. The monitoring camera is used to accurately identify the internal image of the container. The door monitoring structure is used to monitor the opening and closing of the container door in real time. The data storage terminal is used to back up the data results of the monitoring camera and the door monitoring structure. The data storage terminal is connected to the monitoring camera and the door monitoring structure through a one-way gateway. The door monitoring structure includes a sensing module and an analysis module. The sensing module is arranged in two groups. The two groups of sensing modules are respectively arranged on the inner walls of the two groups of container doors. The two groups of sensing modules communicate with each other through NFC communication technology. The two groups of sensing modules communicate with the analysis module through Bluetooth communication technology. The analysis module is connected with the positioning module by signal. When the door monitoring structure monitors the opening and closing of the container door in real time, the working principle is as follows: S81: The two sets of sensing modules are connected via NFC technology and mutually authenticated via a heartbeat mechanism; S82: When any one of the two groups of sensing modules fails in verification, an alarm message is sent to the analysis module, and the analysis module records the alarm message and transmits the alarm message to the data storage terminal; S83: The analysis module retrieves the positioning data in the positioning module to check whether the container is at the checkpoint; S84: If the container is not at the inspection point, the inspection result is recorded and sent to the data storage end for backup.

Citation Information

Patent Citations

  • Freight transportation safety evaluation model based on man-vehicle-road-freight multi-risk source

    CN106228499A

  • Goods source automatic checking method and system based on big data analysis

    CN108734435A

  • Whole-process logistics management and control system

    CN116128392A

  • Digital twinning-based logistics distribution vehicle three-dimensional loading method and system

    CN117371737A

  • Big data logistics management system

    CN117649116A

Cited By

  • High-speed rail freight data information management system and dispatching management method thereof

    CN119721643A