Whole-course tracking management method and system for cold-chain logistics and medium

Abstract

The invention discloses a cold-chain logistics whole-course tracking management method and system and a medium, and relates to the technical field of logistics management, and the method comprises the steps: analyzing the influence of a logistics whole cycle on cold-chain articles, obtaining cold-chain correlation parameters of cycle nodes, and building a data collection architecture which comprises nodes, correlation parameters and interfaces; acquiring cold chain article information, analyzing constraint conditions, and determining cold chain constraint information; performing data accumulation operation through the acquisition architecture to obtain a temperature-time data mapping relation; evaluating the mapping relation according to the constraint information to obtain cold chain evaluation information; and performing parameter optimization on the nodes according to the evaluation information to generate a logistics management strategy. The technical problem that dynamic monitoring and optimal control of whole-course temperature and time are lacked in cold-chain logistics management is solved, and the technical effects that cold-chain logistics parameter optimization is achieved through whole-course tracking and real-time data analysis, the article quality is ensured, and the cold-chain transportation efficiency is improved are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics management, and particularly to a method, system and medium for full-process tracking management of cold chain logistics. Background Art

[0002] Cold chain logistics refers to the need to control factors such as temperature and humidity throughout the process during transportation, warehousing and distribution to ensure that the quality of goods is not affected by the external environment. Especially for goods sensitive to temperature and time, such as food and medicine. Traditional cold chain logistics management faces the problems of information silos and inability to transmit data in real time, resulting in the inability to grasp the status of cold chain goods in real time, affecting the quality and safety of goods. Especially during transportation, factors such as transitions and transfers at different cycle nodes often become important links affecting the quality of cold chain logistics. Problems such as temperature fluctuations, time delays and equipment failures in these links will reduce the reliability of cold chain logistics and bring potential cargo damage risks to goods. Existing cold chain logistics management systems usually lack comprehensive consideration and full-process tracking of these influencing factors, resulting in the inability to effectively respond to various emergencies generated during the logistics process. Therefore, there is an urgent need to establish an intelligent tracking management system throughout the logistics life cycle, and through data fusion and intelligent analysis technologies, achieve full-process and refined control of temperature-sensitive goods, ensuring that the cold chain is unbroken and the quality is traceable. Summary of the Invention

[0003] The present invention provides a method, system and medium for full-process tracking management of cold chain logistics to solve the technical problem of lack of dynamic monitoring and optimal control of the whole-process temperature and time in cold chain logistics management, and achieve the technical effect of optimizing cold chain logistics parameters, ensuring the quality of goods and improving the cold chain transportation efficiency through full-process tracking and real-time data analysis.

[0004] In a first aspect, the present invention provides a method for full-process tracking management of cold chain logistics, wherein the method for full-process tracking management of cold chain logistics includes: Analyze the influence relationship of the logistics life cycle on cold chain goods, obtain the cold chain correlation parameters of each cycle node, and build a full-process data acquisition architecture, including cycle nodes, correlation parameters and their data acquisition interfaces; obtain the goods information of cold chain logistics, analyze the cold chain logistics constraint conditions of the goods information, and determine the cold chain constraint information of the goods, including the constraint relationship between temperature and time; through the full-process data acquisition architecture, perform a full-process time-series cumulative operation on the collected data of the correlation parameters to obtain a temperature-time data mapping relationship; according to the cold chain constraint information of the goods, perform a cold chain constraint evaluation on the temperature-time data mapping relationship to obtain cold chain evaluation information; according to the cold chain evaluation information, optimize the cold chain logistics parameters of the cycle node to generate a logistics management strategy, including temperature regulation, transfer control of cycle nodes, and optimization control of logistics paths.

[0005] Second aspect, the present invention further provides a whole-process tracking and management system for cold chain logistics. Among them, the whole-process tracking and management system for cold chain logistics includes: Data acquisition architecture building module: Analyze the influence relationship of the cold chain items in the whole logistics cycle, obtain the cold chain correlation parameters of each cycle node, and build a whole-process data acquisition architecture, including cycle nodes, correlation parameters and their data acquisition interfaces; Constraint condition analysis module: Obtain the item information of cold chain logistics, analyze the cold chain logistics constraint conditions of the item information, and determine the cold chain constraint information of the item, including the constraint relationship between temperature and time; Time series cumulative operation module: Through the whole-process data acquisition architecture, perform the whole-process time series cumulative operation on the collected data of the correlation parameters to obtain the temperature-time data mapping relationship; Cold chain constraint evaluation module: According to the cold chain constraint information of the item, perform cold chain constraint evaluation on the temperature-time data mapping relationship to obtain cold chain evaluation information; Logistics parameter optimization module: Optimize the cold chain logistics parameters of the cycle nodes according to the cold chain evaluation information, and generate logistics management strategies, including temperature control, transfer control of cycle nodes, and optimization control of logistics paths.

[0006] Third aspect, the present invention further provides a computer-readable storage medium storing a computer program, which when executed by a processor, implements the whole-process tracking and management method for cold chain logistics provided by the present invention.

[0007] The present invention discloses a whole-process tracking and management method, system and medium for cold chain logistics, including: Analyze the influence relationship of the cold chain items in the whole logistics cycle, obtain the cold chain correlation parameters of each cycle node, and build a whole-process data acquisition architecture, including cycle nodes, correlation parameters and their data acquisition interfaces; Obtain the item information of cold chain logistics, analyze the cold chain logistics constraint conditions of the item information, and determine the cold chain constraint information of the item, including the constraint relationship between temperature and time; Through the whole-process data acquisition architecture, perform the whole-process time series cumulative operation on the collected data of the correlation parameters to obtain the temperature-time data mapping relationship; According to the cold chain constraint information of the item, perform cold chain constraint evaluation on the temperature-time data mapping relationship to obtain cold chain evaluation information; Optimize the cold chain logistics parameters of the cycle nodes according to the cold chain evaluation information, and generate logistics management strategies, including temperature control, transfer control of cycle nodes, and optimization control of logistics paths. The whole-process tracking and management method, system and medium for cold chain logistics disclosed by the present invention solve the technical problem of the lack of dynamic monitoring and optimization control of the whole-process temperature and time in cold chain logistics management, and achieve the technical effect of optimizing cold chain logistics parameters, ensuring the quality of items and improving the cold chain transportation efficiency through whole-process tracking and real-time data analysis. Description of the Drawings

[0008] Figure 1 It is a flow chart of the whole-process tracking and management method for cold chain logistics of the present invention.

[0009] Figure 2 This is a schematic structural diagram of the whole-process tracking and management system for the cold chain logistics of the present invention.

[0010] Explanation of reference numerals in the drawings: Data acquisition architecture construction module 11, constraint condition analysis module 12, time-series cumulative operation module 13, cold chain constraint evaluation module 14, logistics parameter optimization module 15. Specific implementation manners

[0011] The above technical solutions will be described in detail below in conjunction with the drawings in the specification and specific implementation manners to better understand the above technical solutions. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments for explaining the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention. In addition, it should be noted that for the sake of description, only parts related to the present invention are shown in the drawings rather than all.

[0012] Embodiment 1, as Figure 1 This is a flowchart of the whole-process tracking and management method for the cold chain logistics of the present invention. Among them, the whole-process tracking and management method for the cold chain logistics includes: Analyze the influence relationship of the entire logistics cycle on cold chain items, obtain the cold chain correlation parameters of each cycle node, and construct a whole-process data acquisition architecture, including cycle nodes, correlation parameters, and their data acquisition interfaces.

[0013] Specifically, the influence relationship of the entire logistics cycle on cold chain items refers to the parameters that have a greater impact on each link during the entire process from the start of transportation of cold chain items to the destination. For example, temperature, thermal resistance, etc. during the production pre-cooling cycle. For each cycle node of cold chain items, such as production, warehousing, transportation, transfer, etc., the analysis of the environmental temperature influence parameters is carried out to determine the cold chain correlation parameters of each cycle node. These parameters will have a greater impact on the temperature of cold chain items, thereby affecting the quality of cold chain items. In order to effectively monitor cold chain items, a comprehensive data acquisition architecture needs to be constructed. This architecture needs to cover all cycle nodes and be able to capture various correlation parameters (such as temperature, humidity, etc.) related to the state of cold chain items through data acquisition interfaces. Among them, the data acquisition interfaces can be connected to sensors, logistics management systems, equipment on transportation vehicles, etc., to ensure that the environmental conditions of cold chain items are monitored and recorded in real time at each node of cold chain logistics, providing an important basis for subsequent cold chain logistics management and optimization decisions.

[0014] In some embodiments, analyzing the influence relationship of the entire logistics cycle on cold chain items includes: From the initial production stage of cold-chain items to the completion stage of logistics distribution, cycle nodes are divided according to the environmental change nodes of cold-chain items to obtain full-cycle nodes; the environmental temperature impact parameters of the full-cycle nodes are analyzed to determine the temperature impact relationship on cold-chain items, and the cold-chain correlation parameters of each cycle node are extracted from the temperature impact relationship.

[0015] Specifically, in the process of cold-chain logistics, from the initial production stage of cold-chain items to the completion stage of logistics distribution, the entire cold-chain logistics process will be divided into multiple cycle nodes according to the environmental change nodes of cold-chain items (determined according to domain knowledge and business requirements), forming full-cycle nodes. These nodes represent the environmental changes experienced by cold-chain items at different transportation stages, usually including production pre-cooling, warehousing, trunk transportation, transfer loading and unloading, and last-mile delivery. Each node has different environmental conditions and cold-chain factors affecting the items. Subsequently, the environmental temperature impact parameters of these cycle nodes are analyzed, and the temperature changes in different nodes are analyzed through on-site simulation and domain expert decision-making methods. The environmental parameters that will affect the temperature of cold-chain items are found and these parameters are extracted as the cold-chain correlation parameters of each cycle node. These parameters reflect the changes in the cold-chain state of items under specific environmental conditions. For example, the initial temperature, pre-cooling rate, and packaging thermal resistance value in the production pre-cooling stage will all affect the temperature of cold-chain items, and these parameters can be obtained through an infrared thermal imager connected to the data acquisition interface; the temperature and humidity gradient, temperature inside the stack, and door opening frequency in the warehousing stage will all affect the temperature of cold-chain items, and these parameters can be obtained through a multi-point temperature and humidity sensor connected to the data acquisition interface; the temperature uniformity in the carriage, vibration intensity, and number of door openings in the trunk transportation stage will all affect the temperature of cold-chain items, and these parameters can be obtained through an in-vehicle IoT terminal and thermometer connected to the data acquisition interface; the exposure time, environmental temperature difference, and refrigeration efficiency of loading and unloading equipment in transfer loading and unloading will all affect the temperature of cold-chain items, and these parameters can be obtained through a handheld temperature recorder and log connected to the data acquisition interface; the decay curve of the temperature in the insulated box and the customer signature delay in the last-mile delivery stage will all affect the temperature of cold-chain items, and these parameters can be obtained through a Bluetooth temperature tag connected to the data acquisition interface. Through the above process, it is possible to comprehensively understand the temperature impact of each cycle node on cold-chain items and extract key cold-chain parameters from them, providing data support and decision-making basis for subsequent cold-chain logistics management and optimization.

[0016] Obtain the item information of cold-chain logistics, analyze the cold-chain logistics constraint conditions of the item information, and determine the cold-chain constraint information of the item, including the constraint relationship between temperature and time.

[0017] Specifically, in cold chain logistics, item information of cold chain items is obtained, such as the type, characteristics, packaging method, storage requirements, and types of cargo damage of cold chain items. This information helps to understand the environmental requirements of cold chain items and the requirements that need to be complied with during transportation. Once the item information of cold chain items is obtained, an analysis of cold chain logistics constraint conditions is carried out on this information. The core of this analysis is to determine the maximum temperature and maximum time that cold chain items can withstand throughout the logistics process based on the types of cargo damage of cold chain items, and thereby determine the item cold chain constraint information for each type of cold chain item, that is, the constraint relationship between temperature and time. Within this constraint information, cold chain items can maintain the best quality and safety. If this constraint information is exceeded, the quality of cold chain items may be affected, and even spoilage or failure may occur. Through the analysis of this step, the temperature and time limits of different items can be clarified, providing a scientific basis for subsequent cold chain management strategies and control means to ensure the safety and quality of cold chain items throughout the logistics process.

[0018] In some embodiments, an analysis of cold chain logistics constraint conditions is carried out on the item information to determine the item cold chain constraint information, including: Analyzing and classifying according to the types of cargo damage of the item information to obtain the cold chain item cargo damage categories, including failure types and spoilage types; obtaining the standard temperature, temperature tolerance, and maximum exposure time of the failure type, fitting the failure relationship according to the temperature tolerance and maximum exposure time to determine the item cold chain constraint information; obtaining the respiratory heat load, spoilage temperature, and its time threshold of the spoilage type, fitting the spoilage relationship according to the respiratory heat load, spoilage temperature, and time threshold to determine the item cold chain constraint information.

[0019] Specifically, in cold chain logistics, the types of cargo damage of cold chain items directly affect the transportation and storage requirements of the items. Therefore, the types of cargo damage of cold chain items are extracted from the item information of cold chain items and classified according to the types of cargo damage to obtain the cold chain item cargo damage categories, including failure types and spoilage types. Among them, the failure type is usually related to the loss of item function or property change caused by too high or too low temperature. For example, chemical substances such as drugs and vaccines may undergo chemical reactions at high or low temperatures, thus losing their efficacy; the spoilage type is mainly related to the spoilage and deterioration of biological items (such as food) due to factors such as temperature and humidity. For cold chain items of the failure type, refer to the product data of the cold chain item to obtain the standard temperature, temperature tolerance, and maximum exposure time of the cold chain item. Among them, the standard temperature is the normal temperature range of the cold chain item, and exceeding this temperature range may cause the item to fail. For example, some drugs are best stored in the range of 2-8°C. When the temperature exceeds or is lower than this temperature, the efficacy will weaken or completely fail; the temperature tolerance refers to the temperature change range that the item can tolerate. For example, some drugs may allow a fluctuation of up to 10°C for a short time, but exposure to this temperature for a long time will cause failure; the maximum exposure time refers to the maximum time that the item can be exposed to the external environment. Exceeding this time will cause failure even if the temperature change is within the allowable range. After obtaining the standard temperature, temperature tolerance, and maximum exposure time, these data will be fitted, that is, these data will be fitted into a space (the x-axis represents the standard temperature, the y-axis represents the temperature tolerance, and the z-axis represents the maximum exposure time), and this space will be used as the item cold chain constraint information of the cold chain item of the failure type. For cold chain items of the spoilage type, obtain the respiratory heat load, spoilage temperature, and spoilage time threshold in the same way. Among them, the respiratory heat load refers to the heat generated by the item during storage due to biological activities (such as respiration). Usually, biological items (such as fruits and vegetables) will accelerate their respiration at inappropriate temperatures, thus causing the temperature to rise and then leading to spoilage; the spoilage temperature is the critical temperature at which the item begins to spoil. When the item temperature is higher than this temperature, the spoilage process will accelerate; the spoilage time threshold is the maximum allowable time for the item after the temperature exceeds the spoilage temperature. Exceeding this time, the spoilage process will develop rapidly and the risk of item deterioration will increase. By fitting the respiratory heat load, spoilage temperature, and spoilage time threshold into a space, the item cold chain constraint information of the cold chain item of the spoilage type is obtained. Through these item cold chain constraint information, the specific requirements of each cold chain item can be understood, which helps to take effective control measures during cold chain transportation and storage to ensure that the item maintains the best state throughout the cold chain logistics link and avoid quality losses caused by environmental changes.

[0020] In some embodiments, after determining the item cold chain constraint information, it further includes: Construct a cargo damage evaluation model based on the failure relationship or spoilage relationship; quantify the cargo damage through the cargo damage evaluation model to obtain a cargo damage evaluation coefficient.

[0021] Specifically, in order to quantify the cargo damage risk caused by factors such as temperature changes and exposure time during the transportation and storage of cold chain items, a cargo damage evaluation model will be constructed according to the failure relationship or spoilage relationship. Taking the failure relationship as an example, sample cumulative temperature (composed of sample temperatures), sample cumulative time, and sample cargo damage evaluation coefficients are collected. These sample data are divided to obtain training data and validation data. Subsequently, an initial cargo damage evaluation model is constructed using a long short-term memory network (LSTM), including an input layer, an LSTM layer, a fully connected layer, and an output layer. Then, the weights and biases of the initial cargo damage evaluation model are initialized using random numbers, etc., and the training data is input into the initialized initial cargo damage evaluation model for forward propagation. Through layer-by-layer transmission, the predicted cargo damage evaluation coefficient is calculated. After that, the mean squared error (MSE) loss function is used to calculate the loss value between the prediction result and the sample data, and the gradient of the loss with respect to the weights of each layer is calculated layer-by-layer through backpropagation. Then, the Adam optimizer is used to optimize the model parameters and adjust the weights to minimize the value of the loss function. Repeat the above process until the maximum number of iterations is reached. After the training is completed, the validation data is used to test the model performance, and indicators such as the accuracy of the model in calculating the cargo damage evaluation coefficient and the loss value are evaluated. If these indicators meet the preset standards, the current initial cargo damage evaluation model is output as the final cargo damage evaluation model. Otherwise, hyperparameters such as the learning rate and the number of training batches are adjusted to further improve the prediction ability of the cargo damage evaluation model. For the spoilage relationship, the sample cumulative temperature (composed of sample respiratory heat and sample temperature), sample time, and sample cargo damage evaluation coefficients are used as training data, and a cargo damage evaluation model of the spoilage type is constructed through the same steps as above. After obtaining the cargo damage evaluation model, the actually collected environmental data is input into the model, and the model will analyze these data according to the learned mapping relationship to quantify a cargo damage evaluation coefficient under the current environmental conditions, thereby helping to quickly evaluate the risks in the cold chain process, formulate corresponding countermeasures, and effectively ensure the quality and safety of cold chain items during transportation.

[0022] Through the above-mentioned full-process data acquisition architecture, perform the full-process time-series cumulative operation of the associated parameter acquisition data to obtain the temperature-time data mapping relationship.

[0023] In one embodiment, during the cold chain logistics process, cold chain items will experience various environmental changes at different transportation and storage stages. To ensure that cold chain items are always in the best storage conditions, a full-process data acquisition architecture is activated to monitor these environmental factors. The full-process data acquisition architecture will collect environmental parameters through multiple data acquisition interfaces to obtain associated parameter acquisition data, such as generating the initial temperature of the pre-cooling node, the temperature and humidity gradient of the cold storage in the warehousing node, and the temperature uniformity of the carriage in the trunk transportation node. Subsequently, time-series cumulative operations are performed on the collected temperature data. The core of this process is to aggregate the temperature data at different time points according to the cumulative time granularity to form an overall record of the temperature changing over time, that is, the temperature-time data mapping relationship. Generally speaking, this cumulative method helps to evaluate the risks in the cold chain logistics process and the overall state of cold chain items, assisting in making reasonable adjustments and optimizations to ensure that the quality of cold chain items is not damaged.

[0024] In some embodiments, through the full-process data acquisition architecture, full-process time-series cumulative operations are performed on the associated parameter acquisition data to obtain the temperature-time data mapping relationship, including: Through the full-process data acquisition architecture, the monitoring data of each cycle node is obtained, and the monitoring data is projected according to the cycle node to establish a time-series monitoring chain; based on the time-series monitoring chain, cumulative operations of the temperature measurement quantity and the time measurement quantity are performed, and cumulative quantity mapping is performed according to the corresponding relationship between the temperature measurement quantity and the time measurement quantity to obtain the temperature-time data mapping relationship.

[0025] Specifically, at each node of the cold chain logistics (such as production pre-cooling, warehousing, transportation, etc.), environmental data such as temperature and humidity are monitored in real time through the whole-process data acquisition architecture. The data at each cycle node will be collected according to different monitoring interfaces. For example, in the production pre-cooling stage, temperature data may be obtained through an infrared thermal imager, and in the transportation stage, the temperature information of the carriage is obtained through an in-vehicle IoT terminal. These monitoring data not only include temperature, but may also include other factors related to the quality of the cold chain such as humidity and vibration. These data will be collected and recorded in real time to provide a basis for subsequent analysis. Subsequently, the data at each cycle node will be projected into the time series chain of the cycle node in chronological order to form a time series monitoring chain. The purpose of the projection process is to calibrate the monitoring data of each node according to its time point and cycle, ensuring that the data of each node in the entire cold chain process can be correctly connected in time series. Exemplarily, the temperature data in the warehousing stage may be collected at different time points, such as [(8:00AM, 4℃), (9:00AM, 4.2℃), (10:00AM, 4.1℃), (11:00AM, 4.3℃)], and the same is true for the temperature data in the transportation stage, such as [(12:00PM, 3.8℃), (12:30PM, 4.0℃), (1:00PM, 4.2℃), (1:30PM, 4.1℃)]. All these data will be sorted into a time series monitoring chain, such as [(8:00AM, 4℃), (9:00AM, 4.2℃), (10:00AM, 4.1℃), (11:00AM, 4.3℃), (12:00PM, 3.8℃), (12:30PM, 4.0℃), (1:00PM, 4.2℃), (1:30PM, 4.1℃)], reflecting the change of temperature in the whole cold chain logistics process. After that, the temperature data and its corresponding time data are accumulated according to the cumulative time granularity to obtain the time cumulative amount, and then the time cumulative amount is arranged in time series to form a mapping relationship between temperature and time. This mapping relationship can help analyze the overall quality status of cold chain items under different temperature and time combinations, so as to timely discover potential risks and take measures for optimization and adjustment to ensure that the items maintain the best state during transportation and storage.

[0026] In some embodiments, temperature monitoring quantity and time monitoring quantity cumulative operations are performed based on the time series monitoring chain, including: Setting the cumulative time granularity according to the failure type, spoilage type and their cargo damage sensitivity; extracting the temperature monitoring quantity from the time series monitoring chain according to the cumulative time granularity, performing time series aggregation on the extracted time series temperature monitoring values to obtain the temperature cumulative amount and its corresponding time granularity, and performing cumulative time aggregation based on the time granularity to obtain the time cumulative amount.

[0027] Specifically, according to the failure type, corruption type, and cargo damage sensitivity of cold-chain items, setting the cumulative time granularity is to more precisely evaluate the impact of temperature changes on the quality of items during transportation. For temperature-sensitive items (such as drugs, vaccines, etc.), since these items are very sensitive to temperature fluctuations and any small temperature change may affect their efficacy, a finer time granularity, such as a 1-minute granularity, is required to monitor their temperature in real time. For some storable items (such as certain foods), these items are relatively less sensitive to temperature fluctuations, so a coarser time granularity, such as 5 minutes or 10 minutes, can be used to reduce the computational amount and maintain the effectiveness of monitoring. Therefore, according to the cargo damage category and cargo damage sensitivity of each item, combined with industry standards and historical experience, a suitable granularity is selected as the cumulative time granularity. Subsequently, according to the set cumulative time granularity, the temperature data corresponding to the corresponding time is extracted from the time-series monitoring chain. For example, when the cumulative time granularity is 1 minute, the temperature data per minute is extracted from the time-series monitoring chain and recorded. After that, for the extracted temperature data, these data are subjected to time-series aggregation, that is, the temperature data recorded according to the time granularity are added up to obtain the temperature cumulative amount for that time period. After aggregating the temperature data, cumulative time aggregation is also performed on the time data, that is, the times corresponding to the temperature data are added up to obtain the time cumulative amount. Then, the temperature cumulative amount and the time cumulative amount are mapped, that is, the time cumulative amount and the temperature cumulative amount at each moment are corresponded to form a temperature-time data mapping relationship, providing data support for cold-chain management and ensuring that cold-chain items always remain in the optimal temperature control environment throughout the transportation process.

[0028] According to the cold-chain constraint information of the item, a cold-chain constraint evaluation is performed on the temperature-time data mapping relationship to obtain cold-chain evaluation information.

[0029] Specifically, after obtaining the temperature-time data mapping relationship, the temperature accumulation, time accumulation, and their corresponding relationships are extracted from the temperature-time data mapping relationship. Among them, for the failure type, the corresponding relationship indicates the moment when the accumulated time is the exposure time and the temperature change at each moment; for the spoilage type, the corresponding relationship indicates the moment when the accumulated heat is the respiratory heat. Subsequently, the extracted data is compared with the corresponding cold chain constraint information of the item to determine whether the temperature accumulation and time accumulation exceed the tolerable limit of the item, such as whether the temperature exceeds the allowable temperature control range of the item and whether the exposure time exceeds the maximum exposure time. If both are within the range of the cold chain constraint information of the item, it indicates that the cold chain transportation risk is relatively small at this time, and a default loss evaluation coefficient, such as 0.1 or 0.2, is set and used as the cold chain evaluation information. Otherwise, the loss evaluation model is used for quantification to obtain the loss evaluation coefficient in the current environment as the cold chain evaluation information. If the cold chain evaluation information shows a high loss coefficient, it indicates that the temperature fluctuates too much during transportation or storage and the quality of the item may have been damaged; if the loss coefficient is low, it indicates that the cold chain management is relatively compliant and the quality of the item is within an acceptable range. Generally speaking, this process helps to evaluate the quality risk in the cold chain process, provides data support for decision-making, and ensures the quality of cold chain items during transportation.

[0030] In some embodiments, according to the cold chain constraint information of the item, a cold chain constraint evaluation is performed on the temperature-time data mapping relationship to obtain cold chain evaluation information, including: According to the temperature-time data mapping relationship, the temperature accumulation, time accumulation, and their corresponding relationships are extracted; the temperature accumulation, time accumulation, and their corresponding relationships are quantified for loss through the loss evaluation model to obtain a loss evaluation coefficient; the loss evaluation coefficient is used as the cold chain evaluation information.

[0031] Specifically, the temperature accumulation, time accumulation, and their corresponding relationships are extracted from the temperature-time data mapping relationship, and the cold chain constraint information of the item is used for judgment. When the requirements of the cold chain constraint information of the item are not met, the temperature accumulation and time accumulation are input into the loss evaluation model for quantification, so as to convert the cumulative effect of temperature and time into a loss evaluation coefficient. Finally, this loss evaluation coefficient is used as the cold chain evaluation information to help evaluate the risk in the entire cold chain process to ensure that the quality of cold chain items is not damaged.

[0032] According to the cold chain evaluation information, the cold chain logistics parameters of the cycle node are optimized to generate a logistics management strategy, including temperature control, transfer control of the cycle node, and optimization control of the logistics path.

[0033] Specifically, after obtaining the cold chain evaluation information, the cycle nodes of the cold chain logistics will be optimized according to the cold chain evaluation information. Specifically, first, according to the evaluation results of each cycle node reflected in the cold chain evaluation information, its timing relationship with the full cycle nodes will be compared, and the subsequent timing cycles that need to be optimized will be extracted. These subsequent optimized timing cycles are usually the nodes with longer exposure time or larger temperature fluctuations during the cold chain process, that is, the cycle nodes where the cargo damage evaluation coefficient is greater than or equal to the cargo damage threshold. After determining the timing cycles that need to be optimized, the optimizable parameters of these cycles will be obtained. These parameters may include temperature control parameters, transfer control parameters of cycle nodes, or logistics path adjustment parameters, etc. By analyzing these parameters, an optimization evaluation function will be constructed, and a margin calculation will be performed on the target damage threshold of the cold chain items. The purpose of this margin calculation is to measure how much risk the cold chain items can still bear under the existing conditions without affecting the final quality standard. Finally, based on the optimization evaluation function, a search for the margin will be conducted to find the optimization parameters that can meet the margin conditions and minimize the cargo damage evaluation coefficient. These optimal parameters will be used as the final logistics management strategy, including specific adjustments in aspects such as temperature control, transportation path optimization, and management control during the transfer process. Through such a process, it is possible to ensure that the temperature of the items in the cold chain logistics remains in the best state, while minimizing the quality loss during transportation to the greatest extent, and improving the overall cold chain efficiency and safety.

[0034] In some embodiments, optimizing cold chain logistics parameters for cycle nodes according to the cold chain evaluation information to generate a logistics management strategy, including: Projecting according to the evaluation cycle nodes and time relationships corresponding to the cold chain evaluation information into the full cycle node timing relationship to obtain subsequent optimized timing cycles; obtaining the optimizable parameters of the subsequent optimized timing cycles, and constructing an optimization evaluation function based on the optimizable parameters, where the optimizable parameters include one or more of temperature control parameters, transfer control parameters of cycle nodes, and logistics path adjustment parameters; performing a margin calculation on the cargo damage evaluation coefficient using the target damage threshold of the cold chain items; searching for the optimizable parameters of the subsequent optimized timing cycles for the margin according to the optimization evaluation function to obtain logistics management parameters that meet the margin and minimize the cargo damage evaluation coefficient as the logistics management strategy.

[0035] Specifically, according to the evaluation results of each cycle node in the cold chain evaluation information, project these evaluation cycle nodes and their time relationships into the time sequence relationship of the full-cycle nodes. This means judging which cycle nodes need to be optimized preferentially based on the cargo damage evaluation coefficients of the cold chain items at each cycle node, so as to determine the post-optimization time sequence cycle. The post-optimization time sequence cycle refers to those nodes with relatively high cargo damage evaluation coefficients due to large temperature fluctuations or excessive exposure time. Once the post-optimization time sequence cycle that needs to be optimized is determined, the next step is to extract the optimizable parameters of these cycles. These parameters usually include but are not limited to temperature control parameters, transfer control parameters at cycle nodes, and logistics path adjustment parameters. Among them, the temperature control parameters are the temperature set values of the cold chain items during transportation or storage, the working efficiency of the temperature control equipment, etc.; the transfer control parameters at cycle nodes are the residence time of the items during transfer, the adjustment range of the warehouse temperature control system, the temperature control during the loading and unloading operation, etc.; the logistics path adjustment parameters are the selection of the transportation path, whether to avoid high-temperature areas, etc. Subsequently, an optimization evaluation function is constructed by weighting these three parameters. The goal of this function is to minimize the cargo damage evaluation coefficient according to the adjustment effects of each optimizable parameter, so as to find the most effective adjustment plan. During the optimization process, the target damage threshold of the cold chain items is used to calculate the margin of the cargo damage evaluation coefficient. The target damage threshold is the maximum cargo damage tolerance that the items can withstand during the cold chain process. By comparing the current cargo damage evaluation coefficient with the target damage threshold, the margin is calculated. The result of the margin calculation measures how much temperature fluctuation or exposure time can still be tolerated in the current cold chain management without exceeding the quality damage limit of the items. For example, if the current cargo damage evaluation coefficient is 0.6 and the target damage threshold is 0.8, then the remaining margin is 0.2. This margin provides a basis for subsequent optimization, meaning that the temperature, path, or transfer time can still be adjusted within a certain range without exceeding the tolerance range of the items. After the margin is determined, the optimization process enters the search stage. According to the optimization evaluation function and the margin conditions, search for the optimizable parameters of the post-optimization time sequence cycle. Specifically, the search process is to find the best plan that can meet the margin conditions and minimize the cargo damage evaluation coefficient according to different combinations of parameters such as temperature control, path adjustment, and transfer control. For example, a possible optimization strategy is to adjust the transportation path to a route with better temperature control to reduce temperature fluctuations; adjust the transfer time to reduce the temperature exposure during transfer; and refine the temperature control system settings to maintain a more stable temperature environment. Through this optimization search, a set of optimal logistics management parameters that meet the minimum cargo damage evaluation coefficient will finally be obtained, thus forming a logistics management strategy. This logistics management strategy will directly guide the management and execution of the cold chain logistics to ensure that the cold chain items are minimized in loss during transportation, maintain their quality, and reduce unnecessary damage risks.

[0036] In summary, the cold chain logistics full-process tracking and management method provided by the present invention has the following technical effects: Analyze the influence relationship of the cold chain items in the whole logistics cycle, obtain the cold chain correlation parameters of each cycle node, and build a full-process data acquisition architecture, including cycle nodes, correlation parameters and their data acquisition interfaces; obtain the item information of the cold chain logistics, analyze the cold chain logistics constraint conditions of the item information, and determine the cold chain constraint information of the item, including the constraint relationship between temperature and time; through the full-process data acquisition architecture, perform the full-process time-series cumulative operation of the correlation parameter acquisition data to obtain the temperature-time data mapping relationship; according to the cold chain constraint information of the item, perform the cold chain constraint evaluation on the temperature-time data mapping relationship to obtain the cold chain evaluation information; according to the cold chain evaluation information, optimize the cold chain logistics parameters of the cycle node, and generate a logistics management strategy, including temperature control, transfer control of cycle nodes, and optimization control of logistics paths, so as to achieve the technical effect of optimizing the cold chain logistics parameters, ensuring the quality of items and improving the cold chain transportation efficiency through full-process tracking and real-time data analysis.

[0037] Embodiment 2, as Figure 2 is a schematic structural diagram of the cold chain logistics full-process tracking and management system of the present invention. For example, Figure 1 in the flow chart of the cold chain logistics full-process tracking and management method of the present invention can be implemented by a structure such as Figure 2 shown.

[0038] Based on the same concept as the cold chain logistics full-process tracking and management method in the above embodiment, the cold chain logistics full-process tracking and management system provided by the present invention further includes: A data acquisition architecture building module 11: Analyze the influence relationship of the cold chain items in the whole logistics cycle, obtain the cold chain correlation parameters of each cycle node, and build a full-process data acquisition architecture, including cycle nodes, correlation parameters and their data acquisition interfaces; a constraint condition analysis module 12: Obtain the item information of the cold chain logistics, analyze the cold chain logistics constraint conditions of the item information, and determine the cold chain constraint information of the item, including the constraint relationship between temperature and time; a time-series cumulative operation module 13: Through the full-process data acquisition architecture, perform the full-process time-series cumulative operation of the correlation parameter acquisition data to obtain the temperature-time data mapping relationship; a cold chain constraint evaluation module 14: According to the cold chain constraint information of the item, perform the cold chain constraint evaluation on the temperature-time data mapping relationship to obtain the cold chain evaluation information; a logistics parameter optimization module 15: According to the cold chain evaluation information, optimize the cold chain logistics parameters of the cycle node, and generate a logistics management strategy, including temperature control, transfer control of cycle nodes, and optimization control of logistics paths.

[0039] In some embodiments, the data acquisition architecture building module 11 includes: From the initial production stage of cold-chain items to the completion stage of logistics distribution, cycle nodes are divided according to the environmental change nodes of cold-chain items to obtain full-cycle nodes; the environmental temperature impact parameters of the full-cycle nodes are analyzed to determine the temperature impact relationship on cold-chain items, and cold-chain correlation parameters of each cycle node are extracted from the temperature impact relationship.

[0040] In some embodiments, the constraint condition analysis module 12 includes: Analyze and classify according to the types of goods damage in the item information to obtain cold-chain item goods damage categories, including failure types and corruption types; obtain the standard temperature, temperature tolerance, and maximum exposure time of the failure type, and perform failure relationship fitting according to the temperature tolerance and maximum exposure time to determine the cold-chain constraint information of the item; obtain the respiratory heat load, corruption temperature, and its time threshold of the corruption type, and perform corruption relationship fitting according to the respiratory heat load, corruption temperature, and time threshold to determine the cold-chain constraint information of the item.

[0041] In some embodiments, the constraint condition analysis module 12 further includes: Based on the failure relationship or corruption relationship, construct a goods damage evaluation model; quantify the goods damage through the goods damage evaluation model to obtain a goods damage evaluation coefficient.

[0042] In some embodiments, the time series cumulative operation module 13 includes: Through the full-process data acquisition architecture, obtain the monitoring data of each cycle node, project the monitoring data according to the cycle nodes, and establish a time series monitoring chain; perform cumulative operations on the temperature monitoring quantity and time monitoring quantity based on the time series monitoring chain, and perform cumulative quantity mapping according to the corresponding relationship between the temperature monitoring quantity and time monitoring quantity to obtain the temperature-time data mapping relationship.

[0043] In some embodiments, the time series cumulative operation module 13 includes: Set the cumulative time granularity according to the failure type, corruption type, and their goods damage sensitivity; extract the temperature monitoring quantity from the time series monitoring chain according to the cumulative time granularity, perform time series aggregation on the extracted time series temperature monitoring values to obtain the temperature cumulative quantity and its corresponding time granularity, and perform cumulative time aggregation based on the time granularity to obtain the time cumulative quantity.

[0044] In some embodiments, the cold-chain constraint evaluation module 14 includes: According to the temperature-time data mapping relationship, extract the temperature cumulative quantity, time cumulative quantity, and their corresponding relationship; quantify the goods damage of the temperature cumulative quantity, time cumulative quantity, and their corresponding relationship through the goods damage evaluation model to obtain a goods damage evaluation coefficient; use the goods damage evaluation coefficient as the cold-chain evaluation information.

[0045] In some embodiments, the logistics parameter optimization module 15 includes: According to the evaluation cycle nodes and time relationships corresponding to the cold chain evaluation information, project them into the time sequence relationship of the full-cycle nodes to obtain the post-optimization time sequence cycle; obtain the optimizable parameters of the post-optimization time sequence cycle, and construct an optimization evaluation function based on the optimizable parameters. The optimizable parameters include one or more of temperature control parameters, transfer control parameters at cycle nodes, and logistics path adjustment parameters; use the target loss determination threshold of cold chain items to calculate the margin of the loss evaluation coefficient; search for the optimizable parameters of the post-optimization time sequence cycle based on the optimization evaluation function for the margin, and obtain the logistics management parameters that satisfy the margin and minimize the loss evaluation coefficient as the logistics management strategy.

[0046] Embodiment 3, the present invention also provides a computer-readable storage medium, which can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the cold chain logistics full-process tracking management method in the embodiments of the present invention, so as to implement the above cold chain logistics full-process tracking management method.

[0047] It should be understood that the disclosed embodiments of the present invention and the above descriptions enable those skilled in the art to implement the present invention using the present invention. At the same time, the present invention is not limited to the above-mentioned part of the embodiments. It should be understood that those of ordinary skill in the art can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A cold chain logistics full-process tracking management method, characterized in that: include: Analyze the impact of the entire logistics cycle on cold chain items, obtain the cold chain related parameters of each cycle node, and build a full-process data collection architecture, including cycle nodes, related parameters and their data collection interfaces; Obtain the item information of cold chain logistics, analyze the cold chain logistics constraints on the item information, and determine the cold chain constraint information of the item, including the constraint relationship between temperature and time; Through the full-process data acquisition architecture, a full-process time series accumulation operation of the associated parameter acquisition data is performed to obtain a temperature-time data mapping relationship; According to the cold chain constraint information of the item, a cold chain constraint evaluation is performed on the temperature-time data mapping relationship to obtain cold chain evaluation information; The cold chain logistics parameters of the cycle nodes are optimized according to the cold chain evaluation information, and a logistics management strategy is generated, including temperature control, cycle node transit control, and logistics path optimization control.

2. The cold chain logistics full-process tracking management method according to claim 1 is characterized in that: Analyze the impact of the entire logistics cycle on cold chain items, including: From the production start stage of cold chain items to the completion stage of logistics and distribution, the cycle nodes are divided according to the environmental change nodes of cold chain items to obtain the full cycle nodes; The ambient temperature impact parameters of the full-cycle nodes are analyzed to determine the temperature impact relationship on cold chain items, and the cold chain associated parameters of each cycle node are extracted from the temperature impact relationship.

3. The cold chain logistics full-process tracking management method according to claim 1 is characterized in that: Analyze the cold chain logistics constraints of the item information and determine the cold chain constraint information of the item, including: Analyze and classify the damage types of the item information to obtain the damage categories of cold chain items, including expiration type and corruption type; Obtaining the standard temperature, temperature tolerance, and maximum exposure time of the failure type, performing failure relationship fitting according to the temperature tolerance and maximum exposure time, and determining the cold chain constraint information of the item; The respiratory heat load, corruption temperature and time threshold of the corruption type are obtained, and the corruption relationship is fitted according to the respiratory heat load, corruption temperature and time threshold to determine the cold chain constraint information of the item.

4. The cold chain logistics full-process tracking management method according to claim 3 is characterized in that: Determine the cold chain constraint information of the item, and then also include: Based on the failure relationship or corruption relationship, a cargo damage evaluation model is constructed; The cargo damage evaluation model is used to quantify the cargo damage and obtain a cargo damage evaluation coefficient.

5. The cold chain logistics full-process tracking management method according to claim 3 is characterized in that: Through the full-process data acquisition architecture, the full-process time series accumulation operation of the associated parameter acquisition data is performed to obtain the temperature-time data mapping relationship, including: Through the full-process data collection architecture, the monitoring data of each periodic node is obtained, and the monitoring data is projected according to the periodic nodes to establish a time-series monitoring chain; Based on the timing monitoring chain, the temperature monitoring quantity and the time monitoring quantity are accumulated and calculated, and the accumulated quantity is mapped according to the corresponding relationship between the temperature monitoring quantity and the time monitoring quantity to obtain the temperature-time data mapping relationship.

6. The cold chain logistics full-process tracking management method according to claim 5 is characterized in that: Based on the timing monitoring chain, the temperature monitoring amount and the time monitoring amount are accumulated and calculated, including: Set the cumulative time granularity according to the failure type, corruption type and cargo damage sensitivity; The temperature monitoring value is extracted from the time series monitoring chain according to the cumulative time granularity, the extracted time series temperature monitoring value is time-series aggregated to obtain the temperature cumulative value and its corresponding time granularity, and the cumulative time aggregation is performed based on the time granularity to obtain the time cumulative value.

7. The cold chain logistics full-process tracking management method according to claim 4 is characterized in that: According to the cold chain constraint information of the article, a cold chain constraint evaluation is performed on the temperature-time data mapping relationship to obtain cold chain evaluation information, including: According to the temperature-time data mapping relationship, extract the temperature cumulative amount, the time cumulative amount and their corresponding relationship; quantifying the cargo damage by using the cargo damage evaluation model to measure the temperature accumulation, time accumulation and their corresponding relationship, and obtaining a cargo damage evaluation coefficient; The cargo damage evaluation coefficient is used as the cold chain evaluation information.

8. The cold chain logistics full-process tracking management method according to claim 7 is characterized in that: Optimizing cold chain logistics parameters at cycle nodes according to the cold chain evaluation information and generating logistics management strategies include: According to the evaluation cycle nodes and time relationships corresponding to the cold chain evaluation information, project them into the full cycle node timing relationship to obtain the post-optimization timing cycle; Obtaining optimizable parameters of the post-optimization timing cycle, and constructing an optimization evaluation function based on the optimizable parameters, wherein the optimizable parameters include one or more of temperature control parameters, period node transit control parameters, and logistics path adjustment parameters; Calculate the margin of the cargo damage evaluation coefficient using the target damage assessment threshold of cold chain items; According to the optimization evaluation function, a search for optimizable parameters of the post-optimization timing period is performed on the surplus to obtain logistics management parameters that meet the surplus and minimize the cargo damage evaluation coefficient as the logistics management strategy.

9. The cold chain logistics tracking management system is characterized by: The cold chain logistics full-process tracking management method for implementing any one of claims 1 to 8 comprises: Data collection architecture building module: Analyze the impact of the entire logistics cycle on cold chain items, obtain the cold chain related parameters of each cycle node, and build a full-process data collection architecture, including cycle nodes, related parameters and their data collection interfaces; Constraint analysis module: obtains the item information of cold chain logistics, analyzes the cold chain logistics constraints of the item information, and determines the cold chain constraint information of the item, including the constraint relationship between temperature and time; Time series accumulation operation module: through the full-process data acquisition architecture, the full-process time series accumulation operation of the associated parameter acquisition data is performed to obtain the temperature-time data mapping relationship; A cold chain constraint evaluation module: performs a cold chain constraint evaluation on the temperature-time data mapping relationship according to the cold chain constraint information of the article to obtain cold chain evaluation information; Logistics parameter optimization module: optimizes the cold chain logistics parameters of the cycle nodes according to the cold chain evaluation information, and generates logistics management strategies, including temperature control, cycle node transit control, and logistics path optimization control.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the cold chain logistics full-process tracking and management method as described in any one of claims 1 to 8 is implemented.

Images