Smart logistics platform management system and method based on multi-source data

Abstract

The present invention relates to the field of data processing technology, and in particular to a smart logistics platform management system and method based on multi-source data. The method comprises the following steps: obtaining cold chain logistics order data; processing the temperature control requirements of multiple types of goods on the cold chain logistics order data to generate cargo temperature control demand data; performing multi-node temperature control task decomposition on the cold chain logistics order data through the cargo temperature control demand data to generate multi-node fine temperature control task data; performing cold chain abnormality feature analysis based on the multi-node fine temperature control task data to generate abnormal temperature control processing solution data; performing transport-handover point temperature control correction based on the abnormal temperature control processing solution data, and performing cold chain quality weighted scoring to generate logistics quality scoring data. The present invention realizes intelligent cold chain logistics management through the coordination of cold chain task decomposition and multiple transport nodes, thereby improving the temperature control management efficiency and cargo quality assurance of cold chain logistics.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a smart logistics platform management system and method based on multi-source data. Background Art

[0002] Cold chain logistics refers to a specialized transportation method that requires low temperatures to ensure the quality of goods during transportation, warehousing, loading and unloading. It is primarily used for temperature-sensitive goods such as food, pharmaceuticals, and chemical products. Current cold chain logistics management models still exhibit significant fragmentation between warehousing, distribution, and transportation, resulting in insufficient coordination between these links. This is particularly true during multi-node transfers, where temperature control information is often not transmitted and executed in a timely and accurate manner, leading to temperature loss and temperature control chain failures. This temperature control chain failure is particularly prone to occurring at critical nodes such as the intersection of transportation and warehousing, or between different transportation links. For example, when goods are transferred from warehouses to distribution vehicles or from one transportation node to another, temperature monitoring data is often not transmitted and shared in real time. Alternatively, due to inadequate sensor monitoring systems, temperature anomalies may not be detected and addressed promptly, leading to quality degradation or even damage. However, traditional cold chain logistics platform management methods typically rely on single-point temperature monitoring and manual inspections, failing to achieve real-time, comprehensive monitoring of the entire logistics chain. Temperature monitoring is mainly concentrated in a single transportation link or storage facility, lacking the ability to interconnect temperature control data throughout the entire supply chain, and unable to effectively deal with the temperature control instability caused by multi-link and multi-node handovers. Summary of the Invention

[0003] Based on this, the present invention provides a smart logistics platform management system and method based on multi-source data to solve at least one of the above technical problems.

[0004] To achieve the above objectives, a smart logistics platform management method based on multi-source data includes the following steps:

[0005] Step S1: Acquire cold chain logistics order data; analyze the order characteristics of the cold chain logistics order data, process the temperature control requirements of multiple types of goods, and generate temperature control requirement data for the goods;

[0006] Step S2: Build a temperature and humidity sensor monitoring network based on the cargo temperature control demand data; decompose the cold chain logistics order data into multi-node temperature control tasks based on the cargo temperature control demand data to generate multi-node refined temperature control task data; conduct real-time logistics cold chain multi-source monitoring based on the temperature and humidity sensor monitoring network to generate real-time cargo multi-source monitoring data; analyze the cold chain abnormality characteristics of the real-time cargo multi-source monitoring data based on the multi-node refined temperature control task data, set a processing plan, and generate abnormal temperature control processing plan data;

[0007] Step S3: Correct the temperature control at the transport-handover point based on the abnormal temperature control processing plan data, execute the real-time temperature control adjustment instruction, and generate corrected cold chain temperature control data;

[0008] Step S4: Integrate the corrected cold chain temperature control data and the multi-node fine temperature control task data into cold chain transportation data to generate cargo cold chain transportation process data; perform cold chain quality weighted scoring based on the cargo cold chain transportation process data to generate logistics quality scoring data.

[0009] The present invention achieves full-chain coverage of the temperature and humidity monitoring system by constructing a temperature and humidity sensor monitoring network, so that each logistics node and transportation link has real-time monitoring capabilities. This networked monitoring mode significantly improves the timeliness and accuracy of data collection. Through task decomposition and multi-node collaboration, the temperature control demand tasks for each logistics node are accurately formulated, making the temperature monitoring of the entire cold chain logistics process more systematic and coordinated. The multi-source integration of real-time monitoring data, combined with abnormal feature analysis technology, can not only quickly discover temperature control anomalies, but also make targeted corrections based on the generated processing plan, significantly reducing the risk of temperature control chain breaks. The temperature control correction function of transportation and handover points effectively ensures the temperature control stability of key nodes by making real-time adjustments to abnormal temperature control, overcoming the problem that traditional manual inspection methods cannot respond in a timely manner, thereby significantly improving the temperature control reliability of the logistics chain. Through the integration of cold chain transportation data and the introduction of cold chain quality scoring models, the quantification and feedback of the quality of the entire logistics process are achieved, which facilitates the platform to optimize management decisions in real time. This data interconnection and interoperability capability throughout the entire cold chain logistics supply chain not only improves the efficiency of temperature control management, but also provides reliable technical support for collaborative optimization between different links, comprehensively improves the overall quality of cold chain logistics services, reduces the risk of damage to goods due to improper temperature control, and ultimately achieves the goal of intelligent, full-chain cold chain logistics management. Therefore, the present invention's intelligent logistics platform management method based on multi-source data collects temperature control demand data of goods in real time by deploying temperature and humidity sensors at various nodes of cold chain logistics, and monitors temperature control throughout the entire logistics process. For different types of goods, it can automatically analyze their temperature control requirements, generate corresponding temperature control tasks, and adjust temperature control according to environmental changes when multiple nodes are handed over, to ensure that temperature control will not be broken in any link. In the event of temperature abnormalities, timely warnings are issued and temperature control correction measures are implemented to maximize the quality of goods.

[0010] Preferably, step S1 includes the following steps:

[0011] Step S11: Obtain cold chain logistics order data;

[0012] Step S12: performing order characteristic analysis on the cold chain logistics order data to generate cold chain logistics order characteristic data;

[0013] Step S13: performing cargo information retrieval and matching on the cold chain logistics order feature data through a preset cargo information database to generate cold chain cargo matching data;

[0014] Step S14: Evaluate the transportation time based on the cold chain logistics order feature data and generate logistics time requirement data;

[0015] Step S15: Extract the temperature and humidity adaptability ranges of multiple types of goods based on the cold chain goods matching data and the logistics timeliness requirement data, perform temperature control demand processing, and generate goods temperature control demand data.

[0016] By acquiring and parsing cold chain logistics order data, the present invention can accurately extract order features and provide efficient data support for further matching of cargo information. Subsequently, through matching and searching the cargo information database, it ensures that the characteristics of the cold chain cargo accurately correspond to the order information, avoiding the problems of logistics link disorder or cargo temperature control errors caused by data mismatch. At the same time, the evaluation of transportation time provides clear timeliness requirements for logistics planning, effectively avoiding the risk of cargo quality degradation caused by transportation delays. Finally, by integrating cargo characteristics and timeliness requirements, extracting the temperature and humidity adaptation range of the cargo and generating specific temperature control requirements, it not only ensures the environmental adaptability of different types of cargo during transportation, but also improves the scientific and refined management level of the entire cold chain logistics chain.

[0017] Preferably, step S15 includes the following steps:

[0018] Step S151: Perform cargo cluster analysis on the cold chain cargo matching data to generate cargo classification label data;

[0019] Step S152: extracting cold chain logistics and transportation impact features from the cold chain goods matching data based on the goods classification label data to generate goods transportation sensitive feature data;

[0020] Step S153: Calculating temperature and humidity sensitivity based on the cargo transportation sensitive characteristic data to generate cargo temperature and humidity sensitivity data;

[0021] Step S154: Processing the cargo transportation sensitive characteristic data based on the temperature and humidity adaptability ranges of multiple types of cargoes using the cargo temperature and humidity sensitivity data to obtain cargo temperature and humidity range requirement data;

[0022] Step S155: Use the logistics timeliness requirement data to associate the cargo temperature and humidity range requirement data with the transportation distance, and perform temperature and humidity distance control range correction to obtain cargo temperature control requirement data.

[0023] The present invention generates cargo classification label data by clustering analysis on cold chain cargo matching data, so that the system can distinguish different types of cargo, avoid the "one size fits all" extensive management method, extract cargo transportation sensitive features based on cargo classification label data, and perform temperature and humidity sensitivity calculations, so that the system can more accurately grasp the temperature and humidity sensitivity characteristics of different types of cargo. For example, for biological products that are extremely sensitive to temperature changes, the system will identify them as highly sensitive cargo and formulate more stringent temperature control strategies; while for certain daily necessities with strong tolerance, a relatively loose temperature control scheme can be adopted, thereby reducing energy consumption and costs while ensuring the safety of the cargo. By associating logistics timeliness requirement data with cargo temperature and humidity range requirement data, and correcting the temperature and humidity distance control range, dynamic adjustment of the temperature control scheme is achieved. This means that even for the same type of cargo, under different transportation distances and timeliness requirements, the system will formulate different temperature control schemes to ensure that the cargo is always in the best temperature and humidity environment throughout the transportation process. For example, for goods transported over long distances, the system will take into account factors such as changes in ambient temperature during transportation and the goods' own respiration, and make more precise adjustments to the temperature control range to prevent the goods from deteriorating or being damaged.

[0024] Preferably, step S2 includes the following steps:

[0025] Step S21: Screening vehicle-mounted temperature control equipment based on cargo temperature control demand data, matching cold chain transport vehicles with cold chain logistics order data, and generating order cold chain transport equipment data;

[0026] Step S22: Deploy a warehouse monitoring sensor array based on the order cold chain transportation equipment data, and perform wireless Internet of Things processing to obtain a temperature and humidity sensor monitoring network;

[0027] Step S23: Decomposing the cold chain logistics order data into multi-node temperature control tasks based on the cargo temperature control demand data to generate multi-node refined temperature control task data;

[0028] Step S24: Perform real-time logistics cold chain multi-source monitoring based on the temperature and humidity sensor monitoring network to generate real-time cargo multi-source monitoring data; perform cold chain abnormality feature analysis on the real-time cargo multi-source monitoring data through multi-node fine temperature control task data, set a processing plan, and generate abnormal temperature control processing plan data.

[0029] The present invention screens on-board temperature control equipment and matches cold chain transport vehicles based on cargo temperature control demand data, ensuring a precise match between transport equipment and cargo temperature control requirements, avoiding the risk of temperature control failure due to improper equipment selection, and ensuring cargo quality from the source. Based on order cold chain transport equipment data, a warehouse monitoring sensor array is deployed, and combined with wireless Internet of Things technology, a temperature and humidity sensor monitoring network covering the entire warehouse is constructed. This enables the system to collect temperature and humidity data at various locations in the warehouse in real time, achieving comprehensive monitoring of the temperature and humidity status of the cargo, and more timely detection of potential temperature control risks compared to traditional single-point monitoring methods. By decomposing multi-node temperature control tasks for cold chain logistics orders, multi-node fine temperature control task data is generated. This means that the system can not only monitor the temperature and humidity changes throughout the entire transportation process, but also carry out fine management of the temperature control tasks of each key node, such as loading, unloading, transshipment and other links, thereby effectively avoiding the temperature control chain break problem that is prone to occur in these links. By combining multi-source monitoring data collected in real time through a temperature and humidity sensor monitoring network with data from multi-node precision temperature control tasks, the system analyzes cold chain anomaly characteristics and establishes corresponding treatment plans, enabling rapid response and effective handling of temperature control anomalies. Once the system detects that the temperature or humidity exceeds a preset range, it immediately triggers an early warning mechanism and takes appropriate measures based on the pre-set treatment plan, such as automatically adjusting temperature control equipment parameters or notifying relevant personnel for manual intervention, thereby minimizing temperature control risks.

[0030] Preferably, step S23 includes the following steps:

[0031] Step S231: extracting the shipping location and receiving location from the cold chain logistics order data to generate order logistics address data;

[0032] Step S232: Preliminary order transportation route planning is performed on the order logistics address data using a preset logistics transportation network to generate preliminary order transportation route data;

[0033] Step S233: Evaluate the capacity of the temperature control facilities at the nodes based on the preliminary order transportation route data, screen available temperature control nodes for transportation, and generate temperature control facility capacity data for the transportation nodes;

[0034] Step S234: Using the transport node temperature control facility capacity data as a path planning constraint, and performing intelligent transport path selection on the preliminary order transport route data, to generate intelligent cold chain transport path data;

[0035] Step S235: extracting cargo handover tasks from the intelligent cold chain transport route data to generate cargo handover point task data;

[0036] Step S236: Decompose the cargo transfer point task data into multi-node temperature control tasks based on the cargo temperature control demand data to generate multi-node refined temperature control task data.

[0037] This invention implements intelligent transportation route selection by performing preliminary route planning based on order logistics address data, combined with a pre-defined logistics transportation network and node temperature control facility capacity assessment. This not only shortens transportation time and reduces transportation costs, but also ensures that the selected transportation route is capable of meeting the cargo's temperature control requirements, thereby avoiding the risk of temperature control failure due to improper route selection. During the route planning process, the solution uses the temperature control facility capacity data of transportation nodes as a constraint and performs intelligent transportation route selection, effectively avoiding the transportation of goods to nodes lacking or substandard temperature control facilities, thereby ensuring temperature control safety throughout the entire transportation process. The intelligent cold chain transportation route data is used to extract cargo handover tasks and, based on the cargo temperature control requirement data, multi-node temperature control task decomposition is performed to generate multi-node refined temperature control task data. This enables the system to fine-tune temperature control tasks for each cargo handover point, such as handover time, temperature control requirements, and responsible personnel, effectively avoiding the problem of temperature control chain interruption that can easily occur during the handover process. By assessing and screening the capacity of node temperature control facilities, the solution also helps optimize resource allocation and improve the utilization rate of temperature control facilities. For example, the system can prioritize goods with higher temperature control requirements for transit to nodes with more complete temperature control facilities based on the temperature control facility capabilities of different nodes, thereby ensuring the quality of the goods to the greatest extent.

[0038] Preferably, step S236 includes the following steps:

[0039] Through the cargo temperature control demand data, the upper and lower limits of the temperature control demand of the cargo handover point task data are accurately analyzed to obtain the fine temperature control demand data of the handover point;

[0040] Calculate the dynamic thermal attenuation index of cargo based on the precise temperature control demand data at the handover point and generate the cargo thermal attenuation index;

[0041] The cargo thermal attenuation index is used to calculate the task temperature fluctuation risk value of the cargo handover task data, and the temperature fluctuation risk tasks are divided based on the preset temperature fluctuation risk threshold to obtain high-risk cargo handover task data and low-risk cargo handover task data respectively;

[0042] Determine the temperature control redundancy level of the transport section for high-risk cargo delivery task data, perform multiple redundant temperature control processing, and generate high-risk temperature control task parameters;

[0043] Calculate the optimal energy-saving temperature range for low-risk cargo delivery task data, perform dynamic energy-saving temperature control processing, and generate low-risk temperature control task parameters;

[0044] The intelligent cold chain transport path data is decomposed into temperature control tasks in the transport section through high-risk temperature control task parameters and low-risk temperature control task parameters, and the temperature control parameter execution task is encapsulated to generate multi-node fine temperature control task data.

[0045] This invention calculates the cargo's dynamic thermal attenuation index and the task's temperature fluctuation risk value, and categorizes cargo handover tasks into high-risk and low-risk categories, enabling differentiated management of tasks with different risk levels. This risk-based management strategy allows for more efficient resource allocation, focusing limited resources on temperature control for high-risk tasks, thereby minimizing the risk of cargo damage. For high-risk cargo handover tasks, the solution determines temperature control redundancy levels for transport segments and implements multiple redundant temperature control processes. This ensures that redundant temperature control measures can safeguard cargo quality even in the event of an unforeseen event. For example, the system can simultaneously activate backup refrigeration equipment and increase insulation materials to improve temperature control reliability. For low-risk cargo handover tasks, the solution calculates the optimal energy-saving temperature range and implements dynamic energy-saving temperature control. This minimizes energy consumption while ensuring cargo safety, thereby saving costs and improving economic efficiency. For example, the system can dynamically adjust the operating parameters of refrigeration equipment based on changes in ambient temperature to avoid energy waste caused by over-cooling.

[0046] Preferably, step S24 includes the following steps:

[0047] Step S241: Distribute remote temperature control tasks based on multi-node refined temperature control task data to generate remote temperature control task data;

[0048] Step S242: Acquire real-time transportation equipment communication quality data; utilize the real-time transportation equipment communication quality data to adaptively adjust the monitoring frequency of the temperature and humidity sensor monitoring network to obtain an adaptive monitoring frequency strategy;

[0049] Step S243: Execute the warehouse temperature control task according to the remote temperature control task data, and use the temperature and humidity sensor monitoring network to perform multi-point timing data collection based on the adaptive monitoring frequency strategy to obtain real-time cargo multi-source monitoring data;

[0050] Step S244: performing data analysis preprocessing on the real-time cargo multi-source monitoring data, and performing multi-source monitoring data fusion to generate standard cargo temperature monitoring data;

[0051] Step S245: Intelligent temperature control trend prediction is performed on the standard cargo temperature monitoring data, and cold chain abnormality features are extracted based on the multi-node fine temperature control task data to generate temperature control abnormal deviation feature data;

[0052] Step S246: Based on the preset transportation-handover cold chain case database, intelligent matching of historical cases is performed using temperature control abnormal deviation feature data to generate historical related case data;

[0053] Step S247: Setting a processing plan based on the historical related case data, and performing temperature control adjustment parameter processing to generate abnormal temperature control processing plan data.

[0054] This invention enables remote control and management of temperature control equipment through remote temperature control task distribution, improving the efficiency and convenience of temperature control operations. The monitoring frequency of the temperature and humidity sensor monitoring network is adaptively adjusted based on real-time transport equipment communication quality data, enabling dynamic allocation of monitoring resources. When communication quality is good, the system reduces the monitoring frequency to conserve energy and bandwidth resources; when communication quality is poor, the system increases the monitoring frequency to ensure real-time data integrity and thus better protect cargo quality. Intelligent temperature control trend prediction based on standard cargo temperature monitoring data and cold chain anomaly feature extraction combined with multi-node refined temperature control task data provide early warning of potential temperature control risks. This enables the system to take preventative measures before temperature anomalies occur, preventing temperature runaway and minimizing the risk of cargo damage. Based on a pre-set transportation-handover cold chain case database, intelligent matching of historical related cases, setting of handling plans, and processing of temperature control adjustment parameters enable rapid response and precise control of abnormal temperature control handling. This avoids the delays and misjudgments associated with manual handling of anomalies, improving the efficiency and accuracy of anomaly handling.

[0055] Preferably, step S245 includes the following steps:

[0056] Perform temperature and humidity time series processing on standard cargo temperature monitoring data to generate time series cargo temperature monitoring data;

[0057] Based on the time-series cargo temperature monitoring data, the monitoring fluctuation characteristics statistics are performed to obtain the cold chain monitoring fluctuation characteristic data;

[0058] The temperature and humidity prediction model is constructed using the preset time series model, and the cold chain monitoring fluctuation characteristic data is used for transfer learning to obtain the temperature and humidity prediction model;

[0059] Use the temperature and humidity prediction model to perform intelligent temperature control trend prediction on the time-series cargo temperature monitoring data and generate intelligent temperature control trend prediction data;

[0060] Use multi-node precise temperature control task data to match transportation task nodes with intelligent temperature control trend forecast data, calculate ideal temperature control deviation values, and generate cold chain temperature control deviation data;

[0061] Based on the cold chain temperature control deviation data, the cold chain temperature control deviation anomaly analysis is performed, and the operating status of the temperature control equipment is obtained to generate temperature control abnormal deviation characteristic data.

[0062] This invention performs time-series temperature and humidity processing on standard cargo temperature monitoring data, converting discrete temperature data into continuous time-series data. By analyzing the fluctuation characteristics of the time-series cargo temperature monitoring data, cold chain monitoring fluctuation characteristic data is extracted. This provides an important reference for understanding the patterns and characteristics of temperature fluctuations and helps more accurately predict future temperature trends. A temperature and humidity prediction model is constructed using a preset time-series model and transfer learning combined with cold chain monitoring fluctuation characteristic data. The application of transfer learning enables the model to better adapt to the temperature and humidity characteristics of different cargoes and transportation environments, improving prediction accuracy and reliability. The temperature and humidity prediction model uses time-series cargo temperature monitoring data to perform intelligent temperature control trend prediction and, combined with multi-node refined temperature control task data, calculates ideal temperature control deviation values. This allows for early prediction of future temperature deviations and timely preventative measures. For example, if the temperature at a node is predicted to exceed a preset range, the system can provide an early warning and automatically adjust the operating parameters of the temperature control equipment to prevent temperature runaway. By performing anomaly analysis on cold chain temperature control deviation data and combining it with temperature control equipment operating status information, the cause of temperature control anomalies can be more accurately determined, providing more precise guidance for subsequent anomaly handling. For example, if the temperature deviation is found to be too large and the temperature control equipment is in normal operation, there is a problem with the insulation material and it needs to be replaced or repaired in time.

[0063] Preferably, step S4 includes the following steps:

[0064] Step S41: When the cold chain logistics order data completes logistics transportation, the corrected cold chain temperature control data and the multi-node fine temperature control task data are integrated into the cold chain transportation data to generate the cargo cold chain transportation process data;

[0065] Step S42: Evaluate the temperature control effect of the transport section based on the cargo cold chain transport process data to generate temperature control effect data of the transport section;

[0066] Step S43: Evaluate the status of key handover links based on the cargo cold chain transportation process data to generate handover link evaluation data;

[0067] Step S44: Calculating cargo quality change indicators based on cargo cold chain transportation process data to generate cargo transportation quality indicator data;

[0068] Step S45: Perform a weighted cold chain quality score based on the temperature control effect data of the transportation section, the handover link evaluation data, and the cargo transportation quality index data to generate logistics quality score data.

[0069] After a cold chain logistics order is completed, the present invention integrates the revised cold chain temperature control data and multi-node fine temperature control task data to generate complete cargo cold chain transportation process data. The system then evaluates the temperature control effect of the transportation section, the status of key handover links, and the cargo quality change indicators, generating corresponding evaluation data. These three aspects of the evaluation cover the key links of cold chain logistics and can comprehensively reflect the quality level of cold chain logistics services. For example, the evaluation of the temperature control effect of the transportation section can reflect the operating status and temperature control effect of the temperature control equipment; the evaluation of the handover link status can reflect the operational standardization and efficiency of the handover process; and the calculation of the cargo quality change index can reflect the impact of cold chain logistics services on cargo quality. Based on these three aspects of the evaluation data, a weighted cold chain quality score is performed to generate the final logistics quality score data. The weighted scoring method can assign different weights to different links according to their importance, thereby more objectively reflecting the overall quality of cold chain logistics services. For example, based on the characteristics of the goods and the requirements for temperature control, a higher weight can be assigned to the cargo quality change indicator, thereby more effectively ensuring the quality of the goods. The generated logistics quality scoring data can not only be used as a performance evaluation indicator within cold chain logistics companies, but also as an important reference for customers to select cold chain logistics service providers.

[0070] The present invention also provides a smart logistics platform management system based on multi-source data, which implements the smart logistics platform management method based on multi-source data as described above. The smart logistics platform management system based on multi-source data includes:

[0071] The order demand analysis module is used to obtain cold chain logistics order data; analyze the order characteristics of cold chain logistics order data, process the temperature control requirements of multiple types of goods, and generate cargo temperature control demand data;

[0072] The temperature control anomaly prediction module is used to build a temperature and humidity sensor monitoring network based on cargo temperature control demand data. It uses the cargo temperature control demand data to decompose cold chain logistics order data into multi-node temperature control tasks, generating multi-node refined temperature control task data. It also conducts real-time logistics cold chain multi-source monitoring based on the temperature and humidity sensor monitoring network, generating real-time cargo multi-source monitoring data. It uses the multi-node refined temperature control task data to analyze cold chain anomaly characteristics in real-time cargo multi-source monitoring data, sets processing solutions, and generates abnormal temperature control processing solution data.

[0073] The temperature control adjustment execution module is used to make temperature control corrections at the transport-handover point based on the abnormal temperature control processing plan data, execute real-time temperature control adjustment instructions, and generate corrected cold chain temperature control data;

[0074] The logistics quality assessment module is used to integrate the corrected cold chain temperature control data and multi-node fine temperature control task data into cold chain transportation data to generate cargo cold chain transportation process data; and to perform cold chain quality weighted scoring based on the cargo cold chain transportation process data to generate logistics quality scoring data. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 This is a flowchart of the steps of the smart logistics platform management method based on multi-source data of the present invention;

[0076] Figure 2 for Figure 1 Detailed implementation steps of step S1 in FIG.

[0077] Figure 3 for Figure 1 Detailed implementation steps of step S4 in FIG.

[0078] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0079] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0080] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0081] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0082] To achieve this, please refer to Figures 1 to 3The present invention provides a smart logistics platform management method based on multi-source data, comprising the following steps:

[0083] Step S1: Acquire cold chain logistics order data; analyze the order characteristics of the cold chain logistics order data, process the temperature control requirements of multiple types of goods, and generate temperature control requirement data for the goods;

[0084] Step S2: Build a temperature and humidity sensor monitoring network based on the cargo temperature control demand data; decompose the cold chain logistics order data into multi-node temperature control tasks based on the cargo temperature control demand data to generate multi-node refined temperature control task data; conduct real-time logistics cold chain multi-source monitoring based on the temperature and humidity sensor monitoring network to generate real-time cargo multi-source monitoring data; analyze the cold chain abnormality characteristics of the real-time cargo multi-source monitoring data based on the multi-node refined temperature control task data, set a processing plan, and generate abnormal temperature control processing plan data;

[0085] Step S3: Correct the temperature control at the transport-handover point based on the abnormal temperature control processing plan data, execute the real-time temperature control adjustment instruction, and generate corrected cold chain temperature control data;

[0086] Step S4: Integrate the corrected cold chain temperature control data and the multi-node fine temperature control task data into cold chain transportation data to generate cargo cold chain transportation process data; perform cold chain quality weighted scoring based on the cargo cold chain transportation process data to generate logistics quality scoring data.

[0087] In the embodiment of the present invention, reference Figure 1 FIG. 1 is a flow chart of a method for managing a smart logistics platform based on multi-source data according to the present invention. In this embodiment, the method for managing a smart logistics platform based on multi-source data includes the following steps:

[0088] Step S1: Acquire cold chain logistics order data; analyze the order characteristics of the cold chain logistics order data, process the temperature control requirements of multiple types of goods, and generate temperature control requirement data for the goods;

[0089] In an embodiment of the present invention, for example, a fresh produce e-commerce platform needs to deliver a batch of frozen seafood (-18°C), refrigerated fruit (0-4°C), and room-temperature vegetables (10-25°C) from Shanghai to Beijing. First, the platform's order management system automatically obtains the order data, including order number, customer information, product type, quantity, specifications, origin, destination, and estimated delivery time. The system then analyzes the order data based on its characteristics. Using a pre-set cargo database, the system identifies "frozen seafood," "refrigerated fruit," and "room-temperature vegetables" as belonging to different temperature-controlled categories and automatically extracts their corresponding ideal storage temperature ranges. The system also analyzes other order information, such as climatic conditions at the origin and destination, transportation distance, mode of transportation (e.g., road, rail, or air), and estimated transportation time. This information is used to inform subsequent temperature control strategy development. For example, the cargo temperature control requirements for this order include: frozen seafood: -18±2°C, full temperature and humidity monitoring, and a real-time alarm mechanism. Refrigerated fruits: 0-4℃, need to maintain a certain humidity and avoid large temperature fluctuations. Room temperature vegetables: 10-25℃, need good ventilation and avoid direct sunlight.

[0090] Step S2: Build a temperature and humidity sensor monitoring network based on the cargo temperature control demand data; decompose the cold chain logistics order data into multi-node temperature control tasks based on the cargo temperature control demand data to generate multi-node refined temperature control task data; conduct real-time logistics cold chain multi-source monitoring based on the temperature and humidity sensor monitoring network to generate real-time cargo multi-source monitoring data; analyze the cold chain abnormality characteristics of the real-time cargo multi-source monitoring data based on the multi-node refined temperature control task data, set a processing plan, and generate abnormal temperature control processing plan data;

[0091] In this embodiment of the present invention, based on the cargo temperature control demand data generated in the previous step, the system deploys temperature and humidity sensors in refrigerated trucks, cold storage facilities, and other locations, establishing a temperature and humidity sensor monitoring network. For example, multiple temperature sensors are installed at different locations within a refrigerated truck compartment to ensure comprehensive monitoring of the temperature distribution within the compartment. These sensors are also connected to an Internet of Things (IoT) platform for real-time data collection and transmission. Based on cargo temperature control demand data and order information, the system breaks down the entire cold chain logistics process into multiple nodes, such as warehousing, loading, transportation, unloading, and distribution, and assigns specific temperature control tasks to each node. For example, at the "loading" node, the system sets temperature ranges and loading time limits for the loading area based on the temperature control requirements of different cargoes. At the "transportation" node, the system dynamically adjusts the temperature setpoints for the refrigerated truck based on factors such as the transportation route and weather conditions. This detailed temperature control task data guides operations at each stage, ensuring accurate and effective temperature control. Through this deployed temperature and humidity sensor monitoring network, the system collects real-time data from multiple sources throughout the cold chain logistics process, including temperature, humidity, GPS location, vehicle vibration, and door opening times. This data is transmitted to the cloud platform via a wireless network, generating real-time multi-source cargo monitoring data. The system compares this real-time multi-source cargo monitoring data with multi-node precision temperature control task data to analyze whether there are any cold chain anomalies, such as abnormal temperature, humidity, position deviation, and excessive vibration. For example, if the system detects that the temperature of a refrigerated truck exceeds a preset threshold during transportation, it immediately triggers an alarm and pushes the alarm information to the relevant personnel. Simultaneously, the system automatically generates abnormal temperature control solution data based on preset solutions. For example, the system recommends immediately lowering the refrigerated truck's temperature setpoint or contacting the nearest repair station for inspection.

[0092] Step S3: Correct the temperature control at the transport-handover point based on the abnormal temperature control processing plan data, execute the real-time temperature control adjustment instruction, and generate corrected cold chain temperature control data;

[0093] In this embodiment of the present invention, in step S2, the system has generated temperature control solution data for specific abnormal situations. This step then performs actual temperature control corrections based on this data. For example, if the system detects that the temperature in the refrigerated compartment is too high, the abnormal temperature control solution data recommends lowering the refrigerated truck's temperature setpoint. The system will automatically send a command to the refrigerated truck's temperature control system to lower the setpoint. Simultaneously, the system can also send an alert to the driver, reminding him to pay attention to temperature fluctuations and take necessary measures. At the transport-handover point, such as when goods are unloaded from a refrigerated truck to a cold storage facility, the system will control the temperature and humidity in the handover area according to the preset temperature control solution, shorten the handover time, and minimize the time the goods are exposed to non-ideal temperature environments. For example, the system can pre-cool the cold storage unloading platform to maintain a temperature similar to that in the refrigerated compartment, thereby reducing the impact of temperature differences on the goods. The system will also monitor the temperature changes of the goods during the handover process in real time and record the data to generate corrected cold chain temperature control data. This data includes the corrected temperature setpoint, the actual temperature change curve, and the handover time.

[0094] Step S4: Integrate the corrected cold chain temperature control data and the multi-node fine temperature control task data into cold chain transportation data to generate cargo cold chain transportation process data; perform cold chain quality weighted scoring based on the cargo cold chain transportation process data to generate logistics quality scoring data.

[0095] In this embodiment of the present invention, the system integrates the revised cold chain temperature control data generated in step S3 with the multi-node refined temperature control task data generated in step S2 to generate complete cold chain transportation process data. This data covers every aspect of the cold chain logistics process, including: order information: cargo type, quantity, origin, destination, etc.; temperature control requirements: ideal temperature range and humidity requirements for different cargoes; multi-node temperature control tasks: specific temperature control targets and operating specifications for each node; real-time monitoring data: real-time data such as temperature, humidity, location, and vibration; exception handling records: the time of occurrence of the exception, the handling plan, and the results; and revised temperature control data: revised temperature setpoints, actual temperature change curves, etc. Based on this complete cold chain transportation process data, the system can comprehensively evaluate the quality of cold chain logistics. The system scores the temperature control performance of each link according to pre-set weighted scoring rules. For example, the temperature fluctuation amplitude, duration, and number of exceptions will all influence the final score. The weights assigned to different links will also vary; for example, the "transportation" link will generally be weighted higher than the "loading" link. Ultimately, the system generates a comprehensive logistics quality score, such as 95 points (excellent), 80 points (good), 60 points (passing), etc. This score can be used to evaluate the service quality of carriers and as a basis for improving cold chain logistics management.

[0096] As an example of the present invention, refer to Figure 2 As shown, Figure 1 Detailed implementation steps of step S1 are shown in the flowchart. In this example, step S1 includes:

[0097] Step S11: Obtain cold chain logistics order data;

[0098] In an embodiment of the present invention, consumers place orders on the platform to purchase frozen seafood, refrigerated fruits and room temperature vegetables. After the order is generated, the platform's order management system will automatically generate order data and transmit the data to the smart logistics platform in real time through a preset API interface. The acquired order data includes order number, customer information (delivery address, contact information, etc.), cargo information (product name, quantity, specifications, packaging method, etc.), origin warehouse number, destination distribution center number, expected delivery time, etc. The system will store these data in a distributed database and perform data cleaning and preprocessing, such as removing duplicate data, processing missing values, verifying data format, etc., to ensure the accuracy and integrity of the data. In order to ensure data security, the system will encrypt the data transmission process, such as using the HTTPS protocol, and perform access control management on the database, such as setting user permissions, data encryption storage, etc. In addition, the system will also record the timestamp of data acquisition to facilitate subsequent tracking of the entire life cycle of the order and data analysis, such as counting order volume, analyzing order trends, etc.

[0099] Step S12: performing order characteristic analysis on the cold chain logistics order data to generate cold chain logistics order characteristic data;

[0100] In this embodiment of the present invention, the system analyzes and parses the order data obtained in step S11, extracts key feature information, and generates cold chain logistics order feature data. For example, the system uses a map API to calculate the transportation distance based on the order's origin warehouse number and destination distribution center number, and estimates the required average transportation speed based on the expected delivery time. The system also calculates the required transportation space and load based on the type, quantity, and packaging method of the goods, so as to select the appropriate transportation vehicle (e.g., refrigerated truck, insulated truck) and arrange the optimal transportation route. In addition, the system uses a weather API to obtain real-time weather data for the origin, destination, and route, as well as weather forecasts for the next few days, such as temperature, humidity, rainfall, and the presence of extreme weather, to provide a reference for the subsequent temperature control strategy formulation. The order feature data also includes special transportation requirements, such as whether full GPS tracking is required, whether real-time temperature and humidity monitoring is required, and whether specific packaging materials (e.g., insulated boxes, ice packs) are required. This feature data is stored in a database in a structured format, such as JSON, for efficient access and use in subsequent steps.

[0101] Step S13: performing cargo information retrieval and matching on the cold chain logistics order feature data through a preset cargo information database to generate cold chain cargo matching data;

[0102] In this embodiment of the present invention, the system pre-sets a cargo information database containing detailed information on various common fresh produce products, such as various fish, meats, fruits, and vegetables. Each cargo's information includes: name, type, optimal storage temperature range, humidity requirements, shelf life, sensitivity to light and vibration, and optimal packaging method. The system then matches the cargo name (e.g., salmon, apple, spinach) in the cold chain logistics order feature data generated in step S12 with the cargo information database. For example, if an order contains "salmon," the system searches the database for "salmon" and extracts information such as the product's optimal storage temperature range (e.g., -18°C to -20°C), optimal humidity requirements, sensitivity to light (e.g., avoid light), and shelf life. The matching results generate cold chain cargo matching data, which contains detailed information on each cargo in the order. If an order contains multiple cargoes, the system performs a matching search for each cargo. If the system cannot find matching cargo information in the database, an alarm is issued, prompting manual intervention, and the unmatched cargo information is manually added to the database for subsequent order processing.

[0103] Step S14: Evaluate the transportation time based on the cold chain logistics order feature data and generate logistics time requirement data;

[0104] In this embodiment of the present invention, the system estimates the required transportation time based on the cold chain logistics order feature data generated in step S12, particularly the transportation distance, transportation mode (e.g., road transportation), origin warehouse, destination distribution center, and real-time traffic information along the route. The system can call a map API to obtain real-time traffic information, such as traffic congestion, road construction, and traffic accidents, and analyze it in combination with historical traffic data and prediction models to predict the transportation time. For example, assuming a transportation distance of 1,300 kilometers and an average transportation speed of 80 kilometers per hour, the initial estimated transportation time is 16.25 hours. To account for factors such as rest stops, loading and unloading, traffic congestion, and weather changes, the system will add a certain buffer time based on preset algorithms and rules, such as an additional 3.75 hours, resulting in a final logistics time requirement of 20 hours. In addition, the system will adjust based on the customer's desired delivery time. For example, if the customer requests delivery the next morning, the system will reverse-calculate the transportation time based on the delivery time and use this as the logistics time requirement data. The system then optimizes the transportation route and arranges the transportation plan based on this time requirement data.

[0105] Step S15: Extract the temperature and humidity adaptability ranges of multiple types of goods based on the cold chain goods matching data and the logistics timeliness requirement data, perform temperature control demand processing, and generate goods temperature control demand data.

[0106] In an embodiment of the present invention, the system combines the cold chain cargo matching data generated in step S13 (for example, the optimal storage temperature of salmon is -18°C 4°C, the optimal storage temperature of spinach is 10°C-17°C, and it is required to maintain low humidity throughout the process to prevent frost and bacterial growth. For apples, the system will set the temperature control range to 1°C 23°C and require ventilation to prevent rotting and deterioration. The final generated cargo temperature control demand data will include the specific temperature control range, humidity control requirements, and other special requirements for each cargo, such as light protection, shockproof, ventilation, etc. These data will serve as an important reference for the subsequent cold chain logistics execution process, guiding the setting and operation of temperature control equipment, such as setting the temperature of refrigerated trucks, controlling the humidity of cold storage, etc., to ensure that the goods maintain the best quality during transportation, reduce losses, and improve customer satisfaction.

[0107] Preferably, step S15 includes the following steps:

[0108] Step S151: Perform cargo cluster analysis on the cold chain cargo matching data to generate cargo classification label data;

[0109] Step S152: extracting cold chain logistics and transportation impact features from the cold chain goods matching data based on the goods classification label data to generate goods transportation sensitive feature data;

[0110] Step S153: Calculating temperature and humidity sensitivity based on the cargo transportation sensitive characteristic data to generate cargo temperature and humidity sensitivity data;

[0111] Step S154: Processing the cargo transportation sensitive characteristic data based on the temperature and humidity adaptability ranges of multiple types of cargoes using the cargo temperature and humidity sensitivity data to obtain cargo temperature and humidity range requirement data;

[0112] Step S155: Use the logistics timeliness requirement data to associate the cargo temperature and humidity range requirement data with the transportation distance, and perform temperature and humidity distance control range correction to obtain cargo temperature control requirement data.

[0113] In this embodiment of the present invention, an order placed on a fresh produce e-commerce platform includes a variety of goods, such as salmon, tuna, beef, apples, bananas, spinach, and potatoes. The system uses the K-Means clustering algorithm to perform cluster analysis on cold chain goods matching data (including information such as the goods' optimal storage temperature, humidity, and shelf life). Based on their similarities, these goods are divided into different categories, such as frozen seafood, chilled meat, chilled fruit, and room-temperature vegetables. The system assigns each category a unique label, such as A, B, C, or D, and generates goods classification label data, recording the category label to which each good belongs. Based on the goods classification label data generated in step S151, the system extracts different transport-sensitive features for different goods categories. For example, for frozen seafood (label A), the system focuses on the impact of temperature fluctuations and storage time on product freshness, extracting features such as the temperature sensitivity coefficient and time sensitivity coefficient. For chilled fruit (label C), the system focuses on the impact of humidity changes on product quality, extracting features such as the humidity sensitivity coefficient and ethylene release rate. Ultimately, cargo transport-sensitive feature data is generated, containing the specific sensitive features and corresponding values ​​for each good. Based on the cargo transportation sensitive feature data extracted in step S152, the system calculates the temperature and humidity sensitivity of each type of cargo. For example, for frozen aquatic products, the quality changes of this type of cargo under different temperature fluctuations and storage times are calculated based on the temperature sensitivity coefficient and time sensitivity coefficient, and quantified as a temperature and humidity sensitivity score. The higher the score, the more sensitive the cargo is to temperature and humidity changes. Based on the cargo temperature and humidity sensitivity data calculated in step S153, the system processes the temperature and humidity adaptability ranges of different types of cargo. For example, for highly sensitive frozen aquatic products, the system will narrow their temperature and humidity adaptability ranges, such as reducing the optimal storage temperature range from -18°C to 19.5°C, to reduce the impact of temperature fluctuations on product quality. Finally, the cargo temperature and humidity range requirement data is obtained, and the system associates the cargo temperature and humidity range requirement data obtained in step S154 with the logistics time requirement data (for example, a transportation time of 20 hours). Considering that the longer the transportation distance, the more difficult it is to control temperature and humidity, the system will modify the temperature and humidity range requirement data based on the transportation distance. For example, for frozen seafood shipped over long distances, the system will further narrow the temperature control range and increase the frequency of humidity monitoring to ensure that the product maintains optimal quality during long-distance transportation. Ultimately, the system generates cargo temperature control demand data, including the temperature and humidity control requirements for each type of cargo over a specific transportation distance and time.

[0114] Preferably, step S2 includes the following steps:

[0115] Step S21: Screening vehicle-mounted temperature control equipment based on cargo temperature control demand data, matching cold chain transport vehicles with cold chain logistics order data, and generating order cold chain transport equipment data;

[0116] Step S22: Deploy a warehouse monitoring sensor array based on the order cold chain transportation equipment data, and perform wireless Internet of Things processing to obtain a temperature and humidity sensor monitoring network;

[0117] Step S23: Decomposing the cold chain logistics order data into multi-node temperature control tasks based on the cargo temperature control demand data to generate multi-node refined temperature control task data;

[0118] Step S24: Perform real-time logistics cold chain multi-source monitoring based on the temperature and humidity sensor monitoring network to generate real-time cargo multi-source monitoring data; perform cold chain abnormality feature analysis on the real-time cargo multi-source monitoring data through multi-node fine temperature control task data, set a processing plan, and generate abnormal temperature control processing plan data.

[0119] In an embodiment of the present invention, for example, a fresh produce order may include fish that needs to be frozen at -18°C, fruit that needs to be refrigerated at 0°C, and vegetables that need to be stored at 10-25°C. Based on the cargo temperature control requirement data, the system selects on-board temperature control equipment with multi-temperature zone control capabilities, such as refrigerated trucks with independent temperature control units. Then, based on information such as the total amount of goods in the order, the number of temperature control zones required, and the transportation distance, the system matches a suitable refrigerated vehicle from the available vehicle database, such as a large refrigerated truck with three independent temperature control units. Ultimately, the order's cold chain transport equipment data is generated, which includes information about the selected vehicle and the configuration parameters of the on-board temperature control equipment. Based on the refrigerated truck and temperature control equipment determined in S21, an array of temperature and humidity sensors is deployed in different temperature zones of the vehicle compartment, for example, multiple sensors are placed in the freezer, refrigerated, and ambient temperature zones, ensuring that the temperature and humidity in each temperature zone are monitored in real time. Each sensor has a unique identifier and uploads data in real time to a cloud platform via a wireless network (e.g., 4G / 5G, NB-IoT). The system integrates data from all sensors to build a comprehensive temperature and humidity sensor monitoring network, achieving comprehensive coverage and real-time monitoring of vehicle compartment temperature and humidity data. The transportation process of a fresh produce order involves multiple nodes: loading at the warehouse, in-transit, unloading at the distribution center, and last-mile delivery. Based on the cargo temperature control requirements (e.g., fish -18°C, fruit 0°C, vegetables 10-25°C), the system refines temperature control tasks for each node. For example, during the warehouse loading phase, cargo must be loaded within a specified timeframe and the vehicle compartment must be pre-cooled to the target temperature. During transportation, temperature must be monitored in real time, with temperature control parameters dynamically adjusted based on real-time road and weather conditions. During unloading at the distribution center, cargo must be unloaded quickly and the temperature maintained stable. This ultimately generates multi-node, granular temperature control task data, including specific temperature control requirements, operating procedures, and time limits for each node. The temperature and humidity sensor monitoring network collects real-time temperature and humidity data from each temperature zone within the vehicle compartment, as well as information such as vehicle location, vibration, and door status, and uploads it to the cloud platform to generate real-time, multi-source cargo monitoring data. The system compares and analyzes this data with the multi-node fine-grained temperature control task data generated by S23. For example, if the temperature in the freezer exceeds -16°C, the system will identify it as a temperature anomaly and generate abnormal temperature control solution data based on pre-set rules. For example, it will immediately issue an alarm to notify relevant personnel, automatically adjust the cooling power of the refrigeration unit, and record the abnormal situation in a database for subsequent analysis and improvement. The system also provides different treatment solutions based on the type and severity of the anomaly and the current node. For example, if the anomaly occurs during transportation and the temperature deviation is large, it is recommended to find a nearby maintenance point for inspection.

[0120] Preferably, step S23 includes the following steps:

[0121] Step S231: extracting the shipping location and receiving location from the cold chain logistics order data to generate order logistics address data;

[0122] Step S232: Preliminary order transportation route planning is performed on the order logistics address data using a preset logistics transportation network to generate preliminary order transportation route data;

[0123] Step S233: Evaluate the capacity of the temperature control facilities at the nodes based on the preliminary order transportation route data, screen available temperature control nodes for transportation, and generate temperature control facility capacity data for the transportation nodes;

[0124] Step S234: Using the transport node temperature control facility capacity data as a path planning constraint, and performing intelligent transport path selection on the preliminary order transport route data, to generate intelligent cold chain transport path data;

[0125] Step S235: extracting cargo handover tasks from the intelligent cold chain transport route data to generate cargo handover point task data;

[0126] Step S236: Decompose the cargo transfer point task data into multi-node temperature control tasks based on the cargo temperature control demand data to generate multi-node refined temperature control task data.

[0127] In an embodiment of the present invention, information such as the shipping warehouse address and the receiving customer address is extracted from cold chain logistics order data obtained from a fresh produce e-commerce platform. The system standardizes the address information, for example, converting text addresses into longitude and latitude coordinates, and generates order logistics address data. The order logistics address data includes information such as the order ID, the shipping location's longitude and latitude, and the receiving location's longitude and latitude. The system pre-defines a logistics network that includes various transportation modes (e.g., road, rail, and air) and nodes (e.g., warehouses, distribution centers, and transfer stations). Based on the shipping and receiving location information in the order logistics address data, the system uses a path planning algorithm (e.g., Dijkstra's algorithm or A* algorithm) to search for transportation routes within the logistics network and generate multiple preliminary order transportation route data. Each preliminary route data set includes a series of node and route segment information, such as the warehouses, distribution centers, and transfer stations passed through, as well as the distances between them and the estimated transportation time. Based on the information at each node in the preliminary order transportation route data, the system evaluates the temperature control facility capabilities of the node. For example, the database is queried to obtain information such as the cold storage capacity, temperature control equipment type, and temperature range for each warehouse, distribution center, and transfer station. If an order includes goods requiring a -18°C freezer temperature, but a transfer station only has refrigeration capacity between 0°C and 4°C, the node will be marked as non-compliant. The system then selects nodes that meet the temperature control requirements for the ordered goods and generates data on the temperature control facility capabilities of the transport nodes. Using the temperature control facility capacity data generated in step S233 as constraints, the system filters and optimizes the preliminary order transportation route data generated in step S232. For example, routes containing nodes that lack the required temperature control capabilities may be excluded. The system also considers other factors, such as transportation cost, transportation time, and transportation risk, and uses a multi-objective optimization algorithm to select the optimal intelligent cold chain transportation route from the remaining routes. The resulting intelligent cold chain transportation route data contains detailed information on the selected transportation route, such as the nodes and road sections passed through, the estimated transportation time, and transportation cost. Based on the intelligent cold chain transportation route data, the cargo handover tasks between different nodes are extracted. For example, goods need to be transported from the origin warehouse to a transfer station, and then from the transfer station to the destination distribution center. The system will generate corresponding cargo handover point task data for each handover task, which includes information such as the handover location, handover time, handover cargo information, and the transportation tools involved in the handover. The system decomposes and refines the temperature control tasks of each handover point based on the cargo temperature control requirement data (for example: fish -18℃, fruit 0℃, vegetables 10-25℃) and cargo handover point task data. For example, in the warehouse loading process, different loading areas and loading sequences need to be set according to the temperature control requirements of different goods, and the temperature and humidity of the loading area need to be controlled. In the handover process at the transfer station, the temperature of the handover area needs to be controlled and the handover time needs to be shortened as much as possible to reduce the risk of goods being exposed to an undesirable environment.Finally, multi-node fine temperature control task data is generated, including specific temperature control requirements, operating specifications, time limits and other information for each handover point.

[0128] Preferably, step S236 includes the following steps:

[0129] Through the cargo temperature control demand data, the upper and lower limits of the temperature control demand of the cargo handover point task data are accurately analyzed to obtain the fine temperature control demand data of the handover point;

[0130] Calculate the dynamic thermal attenuation index of cargo based on the precise temperature control demand data at the handover point and generate the cargo thermal attenuation index;

[0131] The cargo thermal attenuation index is used to calculate the task temperature fluctuation risk value of the cargo handover task data, and the temperature fluctuation risk tasks are divided based on the preset temperature fluctuation risk threshold to obtain high-risk cargo handover task data and low-risk cargo handover task data respectively;

[0132] Determine the temperature control redundancy level of the transport section for high-risk cargo delivery task data, perform multiple redundant temperature control processing, and generate high-risk temperature control task parameters;

[0133] Calculate the optimal energy-saving temperature range for low-risk cargo delivery task data, perform dynamic energy-saving temperature control processing, and generate low-risk temperature control task parameters;

[0134] The intelligent cold chain transport path data is decomposed into temperature control tasks in the transport section through high-risk temperature control task parameters and low-risk temperature control task parameters, and the temperature control parameter execution task is encapsulated to generate multi-node fine temperature control task data.

[0135] In an embodiment of the present invention, a batch of frozen seafood (-18±2°C) and refrigerated fruit (0-4°C) is taken as an example and handed over at a transfer station. The system analyzes the temperature fluctuation range allowed during the handover process based on the cargo temperature control requirement data. Taking into account the influence of loading and unloading operations and ambient temperature, the system will refine the temperature control requirements. For example, the temperature control range of frozen seafood is set to -19°C to -16°C, and the temperature control range of refrigerated fruit is set to 1-3°C, generating more stringent handover point fine temperature control requirement data to ensure that the cargo temperature remains within a safe range during the handover process. Based on the fine temperature control requirement data of the handover point, as well as the physical properties of the cargo (such as specific heat capacity, thermal conductivity, etc.) and the thermal insulation performance of the packaging material, the thermal attenuation index of the cargo at different ambient temperatures is calculated. For example, for salmon, based on its specific heat capacity, the thermal insulation performance of the packaging material, and the fine temperature control requirement data (-1-5°C) at the transfer station, its thermal attenuation index at different ambient temperatures (such as 10°C, 20°C, and 30°C) is calculated. The thermal decay index reflects the rate at which cargo temperature changes over time and is used to assess the risk of temperature fluctuations during cargo transfer. The temperature fluctuation risk value for each transfer task is calculated based on the cargo thermal decay index, the ambient temperature at the transfer point, and the transfer duration. For example, the temperature fluctuation risk value for a transfer task is calculated based on the thermal decay index of salmon, the ambient temperature at the transfer station (e.g., 25°C), and the expected transfer duration (e.g., 30 minutes). A preset temperature fluctuation risk threshold, such as 0.8, is used. Tasks with risk values ​​above the threshold are classified as high-risk cargo transfer tasks, while tasks with risk values ​​below the threshold are classified as low-risk cargo transfer tasks. For high-risk cargo transfer tasks, such as frozen seafood transfers at transfer stations in summer, the system increases the temperature control redundancy level. For example, backup refrigeration units may be activated, insulation materials may be added, and transfer time may be shortened. Based on the risk level and the preset redundancy strategy, the system generates high-risk temperature control task parameters, such as the set temperatures for the primary and backup refrigeration units, transfer time limits, and the type and quantity of insulation materials. For low-risk cargo handover tasks, such as the handover of refrigerated fruits to distribution centers in spring and autumn, the system will give priority to energy conservation. The system will calculate the optimal energy-saving temperature range based on the temperature control requirements of the goods and the ambient temperature, and dynamically adjust the operating parameters of the temperature control equipment within this range, such as reducing the power of the refrigeration unit to reduce energy consumption. Ultimately, low-risk temperature control task parameters are generated, such as: the power setting range of the refrigeration unit, the temperature adjustment frequency, etc. Based on the intelligent cold chain transportation route data, the entire transportation process is broken down into multiple transportation segments, such as: warehouse to transfer station, transfer station to distribution center. The system applies corresponding high-risk temperature control task parameters or low-risk temperature control task parameters based on the risk level of the handover task contained in each transportation segment.For example, for high-risk transport segments involving frozen seafood transfers at summer transit stations, high-risk temperature control task parameters are applied, activating backup refrigeration units. For low-risk transport segments involving only refrigerated fruit transfers at spring and autumn distribution centers, low-risk temperature control task parameters are applied for energy-saving temperature control. The system encapsulates the temperature control parameters and execution tasks for each transport segment, generating multi-node, granular temperature control task data.

[0136] Preferably, step S24 includes the following steps:

[0137] Step S241: Distribute remote temperature control tasks based on multi-node refined temperature control task data to generate remote temperature control task data;

[0138] Step S242: Acquire real-time transportation equipment communication quality data; utilize the real-time transportation equipment communication quality data to adaptively adjust the monitoring frequency of the temperature and humidity sensor monitoring network to obtain an adaptive monitoring frequency strategy;

[0139] Step S243: Execute the warehouse temperature control task according to the remote temperature control task data, and use the temperature and humidity sensor monitoring network to perform multi-point timing data collection based on the adaptive monitoring frequency strategy to obtain real-time cargo multi-source monitoring data;

[0140] Step S244: performing data analysis preprocessing on the real-time cargo multi-source monitoring data, and performing multi-source monitoring data fusion to generate standard cargo temperature monitoring data;

[0141] Step S245: Intelligent temperature control trend prediction is performed on the standard cargo temperature monitoring data, and cold chain abnormality features are extracted based on the multi-node fine temperature control task data to generate temperature control abnormal deviation feature data;

[0142] Step S246: Based on the preset transportation-handover cold chain case database, intelligent matching of historical cases is performed using temperature control abnormal deviation feature data to generate historical related case data;

[0143] Step S247: Setting a processing plan based on the historical related case data, and performing temperature control adjustment parameter processing to generate abnormal temperature control processing plan data.

[0144] In this embodiment of the present invention, the system transmits multi-node precise temperature control task data, such as temperature setpoints, humidity setpoints, and cooling modes for different transport segments, to the temperature control systems of corresponding cold chain transport vehicles via a wireless communication network, generating remote temperature control task data. For example, the temperature control parameters for the "warehouse-transfer station" transport segment, {-18°C (steak), 0-4°C (salmon), 5-15°C (crayfish)}, are transmitted to the onboard temperature control system of the refrigerated truck responsible for that transport segment. Remote temperature control task data ensures that transport vehicles adhere to the predetermined temperature control plan at each node. The system acquires real-time data such as communication signal strength and latency from transport vehicles to assess communication quality. The monitoring frequency of temperature and humidity sensors is dynamically adjusted based on communication quality. For example, when communication quality is good, the monitoring frequency is maintained at a normal level, such as collecting data every minute. When communication quality is poor, the monitoring frequency is reduced, such as collecting data every five minutes, to reduce data transmission volume and ensure reliable transmission of critical data. The resulting adaptive monitoring frequency strategy is: {"Signal strength > 80%": "Collect every minute", "Signal strength < 50%": "Collect every 5 minutes"}. After receiving remote temperature control task data, the onboard temperature control terminal performs the corresponding temperature control operation, such as adjusting the temperature in the refrigerated compartment. Simultaneously, temperature and humidity sensors, based on the adaptive monitoring frequency strategy, periodically collect temperature and humidity data from multiple locations within the compartment and upload the data to the cloud platform via wireless network. The system also collects information such as vehicle position, vibration, and door status, integrating all this data to generate real-time multi-source cargo monitoring data. The system parses and preprocesses this real-time multi-source cargo monitoring data, such as removing outliers, filling in missing values, and converting data formats. The system then fuses temperature data from different sensors, for example, using a weighted average algorithm, to generate more accurate and reliable standard cargo temperature monitoring data. The system uses time series analysis and other methods to predict trends in standard cargo temperature monitoring data, such as predicting cargo temperature changes over a period of time. At the same time, the system compares the predicted results with the preset temperature range in the multi-node fine temperature control task data. If the predicted temperature exceeds the preset range, it is judged as a potential temperature control anomaly. The system extracts the deviation characteristics of the temperature control anomaly, such as the magnitude and duration of the temperature exceeding the standard, and generates temperature control anomaly deviation feature data. The system presets a database containing various transportation-handover cold chain cases, each of which contains information such as abnormal feature descriptions and processing solutions. Based on the temperature control anomaly deviation feature data, the system performs intelligent matching in the case database, such as using a similarity calculation method to find historical cases similar to the current abnormal situation and generate historical associated case data. The system sets the corresponding temperature control adjustment parameters based on the recommended processing solutions in the historical associated case data.For example, if the matched historical case recommends increasing the power of the refrigeration unit, the system will calculate the appropriate power adjustment value based on the current situation and generate abnormal temperature control processing plan data.

[0145] Preferably, step S245 includes the following steps:

[0146] Perform temperature and humidity time series processing on standard cargo temperature monitoring data to generate time series cargo temperature monitoring data;

[0147] Based on the time-series cargo temperature monitoring data, the monitoring fluctuation characteristics statistics are performed to obtain the cold chain monitoring fluctuation characteristic data;

[0148] The temperature and humidity prediction model is constructed using the preset time series model, and the cold chain monitoring fluctuation characteristic data is used for transfer learning to obtain the temperature and humidity prediction model;

[0149] Use the temperature and humidity prediction model to perform intelligent temperature control trend prediction on the time-series cargo temperature monitoring data and generate intelligent temperature control trend prediction data;

[0150] Use multi-node precise temperature control task data to match transportation task nodes with intelligent temperature control trend forecast data, calculate ideal temperature control deviation values, and generate cold chain temperature control deviation data;

[0151] Based on the cold chain temperature control deviation data, the cold chain temperature control deviation anomaly analysis is performed, and the operating status of the temperature control equipment is obtained to generate temperature control abnormal deviation characteristic data.

[0152] In this embodiment of the present invention, the system receives standard cargo temperature monitoring data, including timestamps and temperature values. The system arranges this data chronologically, forming a time series, for example: [(t1, 2°C), (t2, 2.5°C), (t3, 2.2°C)...], where t1, t2, and t3 represent different time points. Considering the varying sensitivity of different cargoes to temperature fluctuations, the system sets different time intervals based on the cargo type. For example, for frozen seafood, the time interval is set to 1 minute, and for refrigerated fruit, the time interval is set to 5 minutes. This ultimately generates time-series cargo temperature monitoring data. The system analyzes this time-series cargo temperature monitoring data and calculates temperature fluctuation characteristics, such as maximum temperature difference, average temperature difference, fluctuation frequency, and standard deviation of temperature difference. For example, for a batch of frozen seafood, the system calculates a maximum temperature difference of 1°C, an average temperature difference of 0.5°C, and a fluctuation frequency of once every 10 minutes over the past hour. These cold chain monitoring fluctuation characteristics reflect the stability of the temperature control system and the temperature fluctuations of the cargo. The system also pre-configures a time series model, such as an LSTM neural network, to predict temperature and humidity trends. To improve model accuracy, the system utilizes cold chain monitoring fluctuation data for transfer learning. For example, the system uses temperature trends corresponding to different fluctuation characteristics in historical transportation data as training data to fine-tune the pre-set LSTM model, making it more adaptable to the current temperature variation patterns of the cargo, thereby generating a more accurate temperature and humidity prediction model. The system uses the trained temperature and humidity prediction model to predict temperature trends over the next one, three, and six hours based on time-series cargo temperature monitoring data. For example, the model predicts that the temperature of frozen seafood will gradually rise over the next hour, reaching a maximum of -17°C. This predicted data generates intelligent temperature control trend prediction data, providing early warning of potential temperature control risks. The system matches this intelligent temperature control trend prediction data with multi-node refined temperature control task data. For example, the system compares the temperature prediction data for the next hour with the specified temperature control range for the current transportation node. If the current transportation node requires frozen seafood to be maintained at -18±2°C, and the predicted maximum temperature is -17°C, the ideal temperature control deviation is calculated to be 1°C. The system compares the predicted temperature at each time point with the corresponding node temperature control requirements to generate cold chain temperature control deviation data for evaluating the temperature control effect. The system analyzes the cold chain temperature control deviation data to determine whether there is a temperature control anomaly. For example, if the cold chain temperature control deviation value continues to exceed the set threshold (for example, 2°C), it is considered that there is a temperature control anomaly. At the same time, the system obtains the operating status of the temperature control equipment, such as the power of the refrigeration unit, the fan speed, etc. Combining the temperature control deviation data and the operating status of the equipment, the system extracts the deviation characteristics of the temperature control anomaly, such as: the amplitude and duration of the temperature exceeding the standard, the operating status of the refrigeration unit, etc., and generates temperature control anomaly deviation feature data.

[0153] As an example of the present invention, refer to Figure 3As shown, Figure 1 Detailed implementation steps of step S4 are shown in the flowchart. In this example, step S4 includes:

[0154] Step S41: When the cold chain logistics order data completes logistics transportation, the corrected cold chain temperature control data and the multi-node fine temperature control task data are integrated into the cold chain transportation data to generate the cargo cold chain transportation process data;

[0155] In an embodiment of the present invention, once the order of the fresh food e-commerce platform is delivered, the system immediately integrates the relevant data of the order throughout the cold chain transportation process. The corrected cold chain temperature control data includes the actual temperature and humidity records, as well as any adjustment operations performed to maintain temperature stability, such as power adjustment of the refrigeration unit, door opening and closing records, etc. The multi-node fine temperature control task data includes the preset temperature control targets, operating specifications and time limits for each transportation node (for example: departure warehouse, transfer station, distribution center, terminal distribution). The system integrates these two parts of data with the original order information (goods type, quantity, transportation route, etc.) to generate a complete set of goods cold chain transportation process data. This data records in detail the temperature and humidity changes, temperature control operations and execution status of each node from the origin to the destination of the goods, such as the actual arrival and departure time of each node, the residence time of the goods at each node, temperature and humidity fluctuations, etc.

[0156] Step S42: Evaluate the temperature control effect of the transport section based on the cargo cold chain transport process data to generate temperature control effect data of the transport section;

[0157] In an embodiment of the present invention, the system analyzes the temperature and humidity data of each transport segment (for example, from the originating warehouse to the transfer station, from the transfer station to the distribution center) in the cargo cold chain transportation process data. Evaluation indicators include: temperature fluctuation range, average temperature deviation, humidity fluctuation range, and the degree of compliance with the preset temperature control target. For example, for the transport segment of frozen seafood, the system will focus on whether the temperature is always maintained within the range of -18±2°C, and calculate the deviation between the actual temperature and the target temperature. The system will also take into account external environmental factors, such as the impact of weather changes on temperature. Ultimately, the system will generate a temperature control effect score for each transport segment, such as a percentage system or a graded system (excellent, good, qualified, unqualified), and generate transport segment temperature control effect data, which contains specific evaluation indicators and scores for each transport segment.

[0158] Step S43: Evaluate the status of key handover links based on the cargo cold chain transportation process data to generate handover link evaluation data;

[0159] In an embodiment of the present invention, the system analyzes the data of each key handover link (for example: loading in the warehouse, changing at the transfer station, and unloading at the distribution center) in the cold chain transportation process data of the goods to evaluate the efficiency and safety of the handover link. Evaluation indicators include: handover time, temperature fluctuations, cargo integrity, etc. For example, the system will count the residence time of the goods at each handover point, analyze whether the temperature fluctuation exceeds the allowable range, and check whether there is any damage or loss of goods. The system will also evaluate the standardization of the operators, such as whether the temperature control operation is performed in accordance with the operating procedures. Finally, the system will generate an evaluation score for each handover link, such as a percentage system or a graded system, and generate handover link evaluation data, which contains specific evaluation indicators and scores for each handover link.

[0160] Step S44: Calculating cargo quality change indicators based on cargo cold chain transportation process data to generate cargo transportation quality indicator data;

[0161] In this embodiment of the present invention, the system calculates a cargo quality change indicator based on cold chain transportation data and the cargo's characteristics. For example, for temperature-sensitive fresh produce, the degree of quality loss can be assessed based on the temperature change curve and the cargo's shelf life information. For example, the quality loss rate of salmon during transportation can be calculated based on the temperature change curve of salmon and its shelf life data at different temperatures. Ultimately, this generates cargo transportation quality indicator data, for example: {"Salmon":"Quality Loss Rate: 2%"}.

[0162] Step S45: Perform a weighted cold chain quality score based on the temperature control effect data of the transportation section, the handover link evaluation data, and the cargo transportation quality index data to generate logistics quality score data.

[0163] In an embodiment of the present invention, the system performs a weighted score on the entire cold chain logistics process based on the temperature control effect data of the transportation section, the evaluation data of the handover link, and the cargo transportation quality index data. For example, the weight of the temperature compliance rate is set to 50%, the weight of the average temperature deviation is set to 20%, the weight of the temperature fluctuation in the handover link is set to 15%, and the weight of the cargo quality loss rate is set to 15%. According to the actual value and weight of each indicator, the final logistics quality score is calculated. For example, if the temperature compliance rate of an order is 95%, the average temperature deviation is 0.5°C, the temperature fluctuation in the handover link is 1°C, and the cargo quality loss rate is 1%, then the logistics quality score of the order is: 95% × 50% + (1-0.5 / 2) × 20% + (1-1 / 2) × 15% + (1-1 / 2) × 15% = 92.5 points. Finally, the logistics quality score data is generated.

[0164] The present invention also provides a smart logistics platform management system based on multi-source data, which implements the smart logistics platform management method based on multi-source data as described above. The smart logistics platform management system based on multi-source data includes:

[0165] The order demand analysis module is used to obtain cold chain logistics order data; analyze the order characteristics of cold chain logistics order data, process the temperature control requirements of multiple types of goods, and generate cargo temperature control demand data;

[0166] The temperature control anomaly prediction module is used to build a temperature and humidity sensor monitoring network based on cargo temperature control demand data. It uses the cargo temperature control demand data to decompose cold chain logistics order data into multi-node temperature control tasks, generating multi-node refined temperature control task data. It also conducts real-time logistics cold chain multi-source monitoring based on the temperature and humidity sensor monitoring network, generating real-time cargo multi-source monitoring data. It uses the multi-node refined temperature control task data to analyze cold chain anomaly characteristics in real-time cargo multi-source monitoring data, sets processing solutions, and generates abnormal temperature control processing solution data.

[0167] The temperature control adjustment execution module is used to make temperature control corrections at the transport-handover point based on the abnormal temperature control processing plan data, execute real-time temperature control adjustment instructions, and generate corrected cold chain temperature control data;

[0168] The logistics quality assessment module is used to integrate the corrected cold chain temperature control data and multi-node fine temperature control task data into cold chain transportation data to generate cargo cold chain transportation process data; and to perform cold chain quality weighted scoring based on the cargo cold chain transportation process data to generate logistics quality scoring data.

[0169] The present application is to ensure the environmental adaptability of different goods during transportation and reduce the risk of cargo loss due to improper temperature control through in-depth analysis of cold chain logistics order data and processing of temperature control requirements of multiple types of goods. The present invention realizes real-time monitoring of the entire cold chain logistics process by constructing a temperature and humidity sensor monitoring network. This networked monitoring mode significantly improves the timeliness and accuracy of data collection, so that each logistics node and transportation link has real-time monitoring capabilities. Through task decomposition and multi-node collaboration, the temperature control demand tasks for each logistics node are accurately formulated, making the temperature monitoring of the entire cold chain logistics process more systematic and coordinated. Through the multi-source integration of real-time monitoring data, not only can temperature control anomalies be quickly discovered, but the risk of temperature control chain breakage is significantly reduced. By making real-time adjustments to abnormal temperature control, the temperature control stability of key nodes is effectively guaranteed, overcoming the problem that traditional manual inspection methods cannot respond in time, thereby significantly improving the temperature control reliability of the logistics chain, realizing the quantification and feedback of the quality of the entire logistics process, and facilitating the platform to optimize management decisions in real time. This data interconnection and interoperability throughout the entire cold chain logistics supply chain not only improves the efficiency of temperature control management, but also provides reliable technical support for collaborative optimization between different links, comprehensively improving the overall quality of cold chain logistics services.

[0170] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0171] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A smart logistics platform management method based on multi-source data, characterized in that: The following steps are involved: Step S1: Acquire cold chain logistics order data; analyze the order characteristics of the cold chain logistics order data, process the temperature control requirements of multiple types of goods, and generate temperature control requirement data for the goods; Step S2: Build a temperature and humidity sensor monitoring network based on the cargo temperature control demand data; decompose the cold chain logistics order data into multi-node temperature control tasks based on the cargo temperature control demand data to generate multi-node refined temperature control task data; perform real-time logistics cold chain multi-source monitoring based on the temperature and humidity sensor monitoring network to generate real-time cargo multi-source monitoring data; analyze cold chain abnormality characteristics of the real-time cargo multi-source monitoring data based on the multi-node refined temperature control task data, set a processing plan, and generate abnormal temperature control processing plan data; wherein, step S2 includes: Step S21: Screening vehicle-mounted temperature control equipment based on cargo temperature control demand data, matching cold chain transport vehicles with cold chain logistics order data, and generating order cold chain transport equipment data; Step S22: Deploy a warehouse monitoring sensor array based on the order cold chain transportation equipment data, and perform wireless Internet of Things processing to obtain a temperature and humidity sensor monitoring network; Step S23: Decomposing the cold chain logistics order data into multi-node temperature control tasks based on the cargo temperature control demand data to generate multi-node refined temperature control task data; wherein, step S23 includes: Step S231: extracting the shipping location and receiving location from the cold chain logistics order data to generate order logistics address data; Step S232: Preliminary order transportation route planning is performed on the order logistics address data using a preset logistics transportation network to generate preliminary order transportation route data; Step S233: Evaluate the capacity of the node temperature control facilities based on the preliminary order transportation route data, screen available temperature control nodes for transportation, and generate transportation node temperature control facility capacity data; Step S234: Using the transport node temperature control facility capacity data as a path planning constraint, and performing intelligent transport path selection on the preliminary order transport route data, to generate intelligent cold chain transport path data; Step S235: extracting cargo handover tasks from the intelligent cold chain transport route data to generate cargo handover point task data; Step S236: Decomposing the cargo transfer point task data into multi-node temperature control tasks based on the cargo temperature control demand data to generate multi-node refined temperature control task data; wherein, step S236 includes: Through the cargo temperature control demand data, the upper and lower limits of the temperature control demand of the cargo handover point task data are accurately analyzed to obtain the fine temperature control demand data of the handover point; Calculate the dynamic thermal attenuation index of cargo based on the precise temperature control demand data at the handover point and generate the cargo thermal attenuation index; The cargo thermal attenuation index is used to calculate the task temperature fluctuation risk value of the cargo handover task data, and the temperature fluctuation risk tasks are divided based on the preset temperature fluctuation risk threshold to obtain high-risk cargo handover task data and low-risk cargo handover task data respectively; Determine the temperature control redundancy level of the transport section for high-risk cargo delivery task data, perform multiple redundant temperature control processing, and generate high-risk temperature control task parameters; Calculate the optimal energy-saving temperature range for low-risk cargo delivery task data, perform dynamic energy-saving temperature control processing, and generate low-risk temperature control task parameters; The intelligent cold chain transport route data is decomposed into temperature control tasks for the transport section using high-risk and low-risk temperature control task parameters, and the temperature control parameter execution tasks are packaged to generate multi-node refined temperature control task data. Step S24: Real-time logistics cold chain multi-source monitoring is performed based on the temperature and humidity sensor monitoring network to generate real-time cargo multi-source monitoring data; cold chain abnormality characteristics are analyzed on the real-time cargo multi-source monitoring data using multi-node fine temperature control task data, and a processing plan is set to generate abnormal temperature control processing plan data; Step S3: Correct the temperature control at the transport-handover point based on the abnormal temperature control processing plan data, execute the real-time temperature control adjustment instruction, and generate corrected cold chain temperature control data; Step S4: Integrate the corrected cold chain temperature control data and the multi-node fine temperature control task data into cold chain transportation data to generate cargo cold chain transportation process data; perform cold chain quality weighted scoring based on the cargo cold chain transportation process data to generate logistics quality scoring data.

2. The intelligent logistics platform management method based on multi-source data according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Obtain cold chain logistics order data; Step S12: performing order characteristic analysis on the cold chain logistics order data to generate cold chain logistics order characteristic data; Step S13: performing cargo information retrieval and matching on the cold chain logistics order feature data through a preset cargo information database to generate cold chain cargo matching data; Step S14: Evaluate the transportation time based on the cold chain logistics order feature data and generate logistics time requirement data; Step S15: Extract the temperature and humidity adaptability ranges of multiple types of goods based on the cold chain goods matching data and the logistics timeliness requirement data, perform temperature control demand processing, and generate goods temperature control demand data.

3. The intelligent logistics platform management method based on multi-source data according to claim 2 is characterized in that: Step S15 includes the following steps: Step S151: Perform cargo cluster analysis on the cold chain cargo matching data to generate cargo classification label data; Step S152: extracting cold chain logistics and transportation impact features from the cold chain goods matching data based on the goods classification label data to generate goods transportation sensitive feature data; Step S153: Calculating temperature and humidity sensitivity based on the cargo transportation sensitive characteristic data to generate cargo temperature and humidity sensitivity data; Step S154: Processing the cargo transportation sensitive characteristic data based on the temperature and humidity adaptability ranges of multiple types of cargoes using the cargo temperature and humidity sensitivity data to obtain cargo temperature and humidity range requirement data; Step S155: Use the logistics timeliness requirement data to associate the cargo temperature and humidity range requirement data with the transportation distance, and perform temperature and humidity distance control range correction to obtain cargo temperature control requirement data.

4. The intelligent logistics platform management method based on multi-source data according to claim 1 is characterized in that: Step S24 includes the following steps: Step S241: Distribute remote temperature control tasks based on multi-node refined temperature control task data to generate remote temperature control task data; Step S242: Acquire real-time transportation equipment communication quality data; utilize the real-time transportation equipment communication quality data to adaptively adjust the monitoring frequency of the temperature and humidity sensor monitoring network to obtain an adaptive monitoring frequency strategy; Step S243: Execute the warehouse temperature control task according to the remote temperature control task data, and use the temperature and humidity sensor monitoring network to perform multi-point timing data collection based on the adaptive monitoring frequency strategy to obtain real-time multi-source monitoring data of the cargo; Step S244: performing data analysis preprocessing on the real-time cargo multi-source monitoring data, and performing multi-source monitoring data fusion to generate standard cargo temperature monitoring data; Step S245: Intelligent temperature control trend prediction is performed on the standard cargo temperature monitoring data, and cold chain abnormality features are extracted based on the multi-node fine temperature control task data to generate temperature control abnormal deviation feature data; Step S246: Based on the preset transportation-handover cold chain case database, intelligent matching of historical cases is performed using temperature control abnormal deviation feature data to generate historical related case data; Step S247: Setting a processing plan based on the historical related case data, and performing temperature control adjustment parameter processing to generate abnormal temperature control processing plan data.

5. The intelligent logistics platform management method based on multi-source data according to claim 4 is characterized in that: Step S245 includes the following steps: Perform temperature and humidity time series processing on standard cargo temperature monitoring data to generate time series cargo temperature monitoring data; Based on the time-series cargo temperature monitoring data, the monitoring fluctuation characteristics statistics are performed to obtain the cold chain monitoring fluctuation characteristic data; The temperature and humidity prediction model is constructed using the preset time series model, and the cold chain monitoring fluctuation characteristic data is used for transfer learning to obtain the temperature and humidity prediction model; Use the temperature and humidity prediction model to perform intelligent temperature control trend prediction on the time-series cargo temperature monitoring data and generate intelligent temperature control trend prediction data; Use multi-node precise temperature control task data to match transportation task nodes with intelligent temperature control trend forecast data, calculate ideal temperature control deviation values, and generate cold chain temperature control deviation data; Based on the cold chain temperature control deviation data, the cold chain temperature control deviation anomaly analysis is performed, and the operating status of the temperature control equipment is obtained to generate temperature control abnormal deviation characteristic data.

6. The intelligent logistics platform management method based on multi-source data according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: When the cold chain logistics order data completes logistics transportation, the corrected cold chain temperature control data and the multi-node fine temperature control task data are integrated into the cold chain transportation data to generate the cargo cold chain transportation process data; Step S42: Evaluate the temperature control effect of the transport section based on the cargo cold chain transport process data to generate temperature control effect data of the transport section; Step S43: Evaluate the status of key handover links based on the cargo cold chain transportation process data to generate handover link evaluation data; Step S44: Calculating cargo quality change indicators based on cargo cold chain transportation process data to generate cargo transportation quality indicator data; Step S45: Perform a weighted cold chain quality score based on the temperature control effect data of the transportation section, the handover link evaluation data, and the cargo transportation quality index data to generate logistics quality score data.

7. A smart logistics platform management system based on multi-source data, characterized by: For executing the smart logistics platform management method based on multi-source data according to claim 1, the smart logistics platform management system based on multi-source data comprises: The order demand analysis module is used to obtain cold chain logistics order data; analyze the order characteristics of cold chain logistics order data, process the temperature control requirements of multiple types of goods, and generate cargo temperature control demand data; The temperature control anomaly prediction module is used to build a temperature and humidity sensor monitoring network based on cargo temperature control demand data. It uses the cargo temperature control demand data to decompose cold chain logistics order data into multi-node temperature control tasks, generating multi-node refined temperature control task data. It also conducts real-time logistics cold chain multi-source monitoring based on the temperature and humidity sensor monitoring network, generating real-time cargo multi-source monitoring data. It uses the multi-node refined temperature control task data to analyze cold chain anomaly characteristics in real-time cargo multi-source monitoring data, sets processing solutions, and generates abnormal temperature control processing solution data. The temperature control adjustment execution module is used to make temperature control corrections at the transport-handover point based on the abnormal temperature control processing plan data, execute real-time temperature control adjustment instructions, and generate corrected cold chain temperature control data; The logistics quality assessment module is used to integrate the corrected cold chain temperature control data and multi-node fine temperature control task data into cold chain transportation data to generate cargo cold chain transportation process data; and to perform cold chain quality weighted scoring based on the cargo cold chain transportation process data to generate logistics quality scoring data.

Images