Cold Chain Transportation Demand Analysis Method and System Based on Big Data Prediction

Abstract

This application provides a method and system for analyzing cold chain transportation demand based on big data prediction. First, a historical cold chain order dataset containing transportation records of temperature-sensitive goods and corresponding environmental parameters in multiple time periods in the target area is obtained. Then, a set of transportation demand characteristics is extracted from it, covering characteristics such as the correlation between the type of goods and temperature sensitivity, the balance between transportation timeliness and equipment energy consumption, and the matching between regional climate and storage conditions. Subsequently, this set of characteristics is input into a pre-trained spatio-temporal prediction model to generate multi-dimensional cold chain demand parameters for the target area within a specified future period, such as the tolerance threshold of temperature fluctuations. Finally, based on these multi-dimensional cold chain demand parameters, a dynamic cold chain transportation scheduling plan with timestamps is generated. This method can accurately analyze cold chain transportation demand by integrating multi-dimensional factors, achieve scientific and dynamic scheduling, and improve the efficiency and quality of cold chain transportation.

Description

Technical Field

[0001] This application relates to the technical field of cold chain transportation. Specifically, it relates to a method and system for analyzing cold chain transportation demand based on big data prediction. Background Art

[0002] In the development process of the cold chain transportation industry, the traditional methods for analyzing cold chain transportation demand face many limitations and are difficult to meet the growing market demand and refined management requirements.

[0003] In the early stage, cold chain transportation mainly relied on manual experience and simple statistical data to estimate transportation demand. Operators judged the transportation task volume in different periods based on past work experience and limited historical order data. However, this method lacks systematicness and scientificity and cannot accurately cope with the complex and changeable market environment and diverse cargo demands. Due to the lack of comprehensive data support, the special transportation requirements of different goods in different environments are often underestimated, resulting in problems such as improper temperature control during transportation, affecting the quality of goods and causing economic losses.

[0004] With the development of technology, some transportation platforms began to adopt relatively simple data statistical methods to analyze transportation demand. These methods usually only focus on single-dimensional data. For example, simply counting the number of orders to predict future transportation volume while ignoring many factors closely related to cold chain transportation. For example, the complex internal relationship between the type of goods and temperature sensitivity is not considered. Different temperature-sensitive goods have very different temperature requirements during transportation, and simple data statistics cannot accurately grasp the suitable transportation temperature range for each type of goods, making it difficult to ensure the quality of goods during transportation.

[0005] In terms of transportation timeliness and equipment energy consumption, traditional analysis methods have not fully recognized the balance relationship between the two. Often, in order to pursue transportation timeliness, equipment energy is over-consumed, resulting in a significant increase in operating costs; or in order to save energy, transportation timeliness is sacrificed, affecting the delivery timeliness of goods and customer satisfaction. At the same time, in considering regional climate and warehousing conditions, most previous methods regarded these two factors in isolation, without recognizing the important impact of regional climate conditions on warehousing condition settings and the key role of the matching degree between the two on cold chain transportation effects. This makes the construction and operation of warehouses lack pertinence and unable to effectively adapt to the climate characteristics of different regions, further increasing the difficulty and cost of cold chain transportation.

[0006] Existing prediction models also have obvious deficiencies. Most of them are based on simple time series analysis or conventional machine learning models, without fully considering the complex variation laws of cold chain transportation demand in the time and space dimensions. These models cannot accurately capture the dynamic differences in cold chain demand between different time periods and different regions, resulting in a large deviation between the prediction results and the actual demand, and it is difficult to guide effective transportation scheduling.

[0007] Traditional cold chain transportation scheduling schemes are usually static and are rarely adjusted according to the actual situation once formulated. This static scheduling method cannot cope with sudden demand changes during transportation, nor can it be optimized according to real-time transportation conditions and environmental factors, resulting in unreasonable resource allocation and low transportation efficiency. Summary of the Invention

[0008] In view of this, the purpose of this application is to provide a cold chain transportation demand analysis method and system based on big data prediction.

[0009] According to the first aspect of this application, a cold chain transportation demand analysis method based on big data prediction is provided. The method includes:

[0010] Obtain a historical cold chain order data set of the target area, where the historical cold chain order data set contains transportation records of temperature-sensitive goods in multiple time periods and their corresponding environmental parameters;

[0011] Extract the transportation demand feature set from the historical cold chain order data. The transportation demand feature set includes the association feature between the type of goods and temperature sensitivity, the balance feature between transportation timeliness and equipment energy consumption, and the matching feature between regional climate and storage conditions;

[0012] Input the transportation demand feature set into a pre-trained spatio-temporal prediction model to generate multi-dimensional cold chain demand parameters for the target area within a specified future period. The multi-dimensional cold chain demand parameters include the temperature fluctuation tolerance threshold, the transportation timeliness critical value, and the path node load factor;

[0013] Generate a timestamped cold chain transportation dynamic scheduling plan based on the multi-dimensional cold chain demand parameters.

[0014] According to the second aspect of this application, a cold chain logistics service system is provided. The cold chain logistics service system includes a machine-readable storage medium and a processor. The machine-readable storage medium stores machine-executable instructions. When the processor executes the machine-executable instructions, the cold chain logistics service system implements the aforementioned cold chain transportation demand analysis method based on big data prediction.

[0015] According to the third aspect of the present application, a computer-readable storage medium is provided. Computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed, the foregoing cold chain transportation demand analysis method based on big data prediction is implemented.

[0016] According to any of the above aspects, the technical effect of the present application is as follows:

[0017] In the embodiment of the present application, a historical cold chain order data set of temperature-sensitive cargo transportation records and their corresponding environmental parameters in a target area including multiple time periods is obtained, the transportation records are associated with the environmental parameters, and a set of transportation demand characteristics is defined. Among them, the association characteristics between the cargo type and the temperature sensitivity break the simple classification of the temperature requirements of the cargo in the past, deeply explore the internal connection of different cargoes in terms of temperature sensitivity, and provide a basis for more accurately controlling the transportation temperature; the balance characteristics between the transportation timeliness and the equipment energy consumption solve the long-existing problem in cold chain transportation that it is difficult to balance the timeliness and energy consumption. By analyzing the relationship between the two, a new perspective is provided for optimizing the transportation strategy; the matching characteristics between the regional climate and the storage conditions combine the external environment with the internal storage conditions, which is a key connection ignored in the past cold chain transportation demand analysis and helps to reasonably plan the storage layout and condition setting.

[0018] In the prediction stage, the set of transportation demand characteristics extracted is input into a pre-trained spatio-temporal prediction model to generate multi-dimensional cold chain demand parameters in the target area within a specified future period. The generation of multi-dimensional parameters such as the temperature fluctuation tolerance threshold, the transportation timeliness critical value, and the path node load factor can, compared with the traditional single-dimensional prediction, comprehensively and prospectively depict the cold chain transportation demand, enabling transportation enterprises to understand in advance the multi-faceted demands in temperature control, time arrangement, and resource allocation during future transportation processes.

[0019] Traditional scheduling schemes often lack comprehensive consideration of the time dimension and multi-dimensional demand parameters and are difficult to adapt to the complex and changeable cold chain transportation environment. However, this solution can, by combining timestamps and multi-dimensional parameters, scientifically schedule in real time and dynamically according to the transportation demands at different future times, improve the utilization efficiency of cold chain transportation resources, reduce transportation costs, and at the same time ensure the transportation quality of temperature-sensitive cargo to the greatest extent, and enhance the intelligence and adaptability levels of the entire cold chain transportation system. Description of the Drawings

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application and should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 shows a schematic flowchart of the cold chain transportation demand analysis method based on big data prediction provided by the embodiments of the present application;

[0022] Figure 2 shows a schematic component structure diagram of a cold chain logistics service system for implementing the above-mentioned cold chain transportation demand analysis method based on big data prediction. Detailed implementation manners

[0023] The embodiments of the present application will be described below with reference to the accompanying drawings in the present application. It should be understood that the embodiments described below in conjunction with the accompanying drawings are exemplary descriptions for explaining the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions of the embodiments of the present application.

[0024] Those skilled in the art of the present technology can understand that, unless specifically stated otherwise, the singular forms "a", "an", "the" and "said" used herein may also include the plural forms. It should be further understood that the terms "comprising" and "including" used in the embodiments of the present application mean that the corresponding features can be implemented as the presented features, information, data, steps, operations, elements and / or components, but do not exclude being implemented as other features, information, data, steps, operations, elements, components and / or their combinations supported by the art of the present technology. It should be understood that when an element is "connected" or "coupled" to another element, the one element can be directly connected or coupled to the other element, or it can mean that the one element and the other element establish a connection relationship through an intermediate element. In addition, the "connection" or "coupling" used herein may include a wireless connection or a wireless coupling, and the term "and / or" used herein indicates at least one of the items defined by the term, for example, "A and / or B" can be implemented as "A", or implemented as "B", or implemented as "A and B".

[0025] To make the objectives, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings. The technical solutions of the embodiments of the present application and the technical effects produced by the technical solutions of the present application will be described below through the description of several exemplary embodiments. It should be noted that the following embodiments can be referenced, learned from or combined with each other. For the same terms, similar features and similar implementation steps in different embodiments, they will not be described repeatedly.

[0026] Figure 1The flowchart shows the method and system for analyzing cold chain transportation demand based on big data prediction provided by the embodiments of the present application. It should be understood that in other embodiments, the order of some steps of the method for analyzing cold chain transportation demand based on big data prediction in this embodiment can be shared according to actual needs, or some of the steps can also be omitted or maintained. The detailed steps of the method for analyzing cold chain transportation demand based on big data prediction include:

[0027] Step S110, obtaining a historical cold chain order dataset of a target area, where the historical cold chain order dataset includes transportation records of temperature-sensitive goods and their corresponding environmental parameters for multiple time periods.

[0028] In this embodiment, in the fresh food scenario, taking the cold chain transportation of fruits and beef as an example. Assume that the target area is a large fruit and beef supply area, such as the main agricultural production area and livestock breeding area of a certain province. For fruits, it may include varieties such as apples, bananas, and oranges, and beef comes from major local farms. The multiple time periods can be each month or each quarter in the past year.

[0029] In terms of fruit transportation records, the transportation record of apples shows that in spring, since apples have a relatively long storage time and are just taken out of the cold storage, the temperature requirement is relatively low, and the temperature during transportation is maintained between 2-4°C. Bananas are more special. During the transportation in the summer maturity season, the temperature needs to be strictly controlled between 12-14°C because bananas are prone to rapid ripening and rotting at high temperatures, while the temperature can be appropriately reduced to 10-12°C during winter transportation. Oranges are preferably maintained at a temperature of 5-7°C during transportation. At the same time, the record also includes the origin and destination of transportation. For example, apples are transported from the orchard to the fruit wholesale market, or from the wholesale market to each supermarket.

[0030] For beef, its transportation record shows that the temperature of fresh beef needs to be maintained between -2-0°C during transportation to ensure the freshness of the meat and prevent the growth of bacteria. When the transportation distance is relatively long, such as transporting from the breeding area to a distant city, more strict temperature control and faster transportation timeliness are required.

[0031] Regarding the corresponding environmental parameters, during transportation, the external air temperature in different seasons has a great impact on cold chain transportation. In summer, the external air temperature often reaches over 30°C, which poses higher requirements for refrigeration equipment and requires more energy consumption to maintain the temperature required for the goods. In winter, especially in cold regions, the external air temperature may drop below -10°C. Although the energy consumption of the refrigeration equipment will decrease, it is also necessary to prevent the goods from being frozen. In addition, humidity is also an important environmental parameter. A high-humidity environment may cause fruits to mold and rot, and for beef, it may affect the dryness of its surface and shelf life. Road conditions are also part of the environmental parameters. For example, mountain roads are rough, and the bumps during transportation may affect the normal operation of the refrigeration equipment and also have an impact on the quality of fruits and beef.

[0032] Step S120, extract the set of transportation demand characteristics from the historical cold chain order data. The set of transportation demand characteristics includes the association characteristics between the type of goods and temperature sensitivity, the balance characteristics between transportation timeliness and equipment energy consumption, and the matching characteristics between regional climate and storage conditions.

[0033] Regarding the association characteristics between the type of goods and temperature sensitivity, still taking fruits and beef as examples. Bananas among fruits are goods with extremely high temperature sensitivity. As mentioned before, even a slight fluctuation in temperature may affect their ripening speed and quality. When the temperature is higher than 14°C, bananas may start to turn yellow and black quickly during transportation, affecting sales. Apples are relatively less temperature-sensitive, but if the temperature is too high, it will also cause water loss and a worse taste. Beef, as a meat product, also has a high sensitivity to temperature. The temperature range of -2 - 0°C is crucial to ensure its freshness. If the temperature rises, the bacteria reproduction speed will accelerate, resulting in the spoilage of beef.

[0034] Regarding the balance characteristics between transportation timeliness and equipment energy consumption, consider the transportation of fruits and beef. Suppose a batch of fresh bananas is transported from the origin to a big city far away, with a long distance. If the bananas are to reach the destination in the best quality state, a faster transportation timeliness is required. This means that the transportation vehicle needs to maintain a high speed, and at the same time, the refrigeration equipment needs to operate continuously and stably, consuming a large amount of energy. However, if the transportation timeliness is too long, even if the refrigeration equipment operates normally, the bananas may deteriorate due to their own physiological characteristics. For beef, to ensure the freshness of the meat, transportation timeliness is equally important. If a slower transportation method is adopted, although the energy consumption of the refrigeration equipment will decrease, the beef may exceed its shelf life during transportation. For example, when transporting beef from the breeding area to a far-away processing enterprise, if the transportation time exceeds a certain limit, even if the temperature is kept at -2 - 0°C all the time, the freshness of the beef will be affected, the color may become darker, and the microbial indicators may exceed the standard.

[0035] The matching characteristics of regional climate and warehousing conditions are also crucial. In the hot and humid southern regions, the warehousing conditions for fruits and beef require stronger refrigeration capacity and dehumidification functions. For example, in southern cities during summer, fruit warehouses need to maintain lower temperatures and humidity to prevent fruits from mildewing and rotting. For beef warehouses, not only the temperature needs to be controlled, but also air circulation should be ensured to prevent the generation of odors. In the cold and dry northern regions, the warehousing conditions need to consider the problem of preventing goods from being frostbitten. For example, in winter in the north, fruit warehouses need appropriate insulation measures to avoid fruits being frozen, and beef warehouses also need to adjust the temperature control range to prevent beef from being overly frozen and affecting its taste.

[0036] Step S130: Input the set of transportation demand characteristics into a pre-trained spatio-temporal prediction model to generate multi-dimensional cold chain demand parameters for the target region within a specified future period. The multi-dimensional cold chain demand parameters include a temperature fluctuation tolerance threshold, a transportation time limit critical value, and a path node load factor.

[0037] Taking the cold chain transportation of fruits and beef as an example, within a specified future period (such as the upcoming summer), input the set of previously extracted transportation demand characteristics into the spatio-temporal prediction model.

[0038] Regarding the temperature fluctuation tolerance threshold, due to the relatively high temperature in summer, the temperature fluctuation tolerance threshold for bananas among fruits may be very small. For example, it can only fluctuate within ±0.5°C between 12 - 14°C because bananas are easily spoiled at high temperatures. The temperature fluctuation tolerance threshold for apples may be relatively larger, fluctuating within ±1°C between 2 - 4°C. The temperature fluctuation tolerance threshold for beef fluctuates within ±0.3°C between -2 - 0°C because beef is sensitive to even minor temperature changes.

[0039] In terms of the transportation time limit critical value, during the peak fruit harvest season in summer, the transportation time limit critical value for fruits is shorter. For example, for bananas transported from the production area to the market, if they cannot arrive within 3 days, they may lose their best selling quality due to temperature and their own physiological changes. The transportation time limit critical value for apples may be around 5 days. For beef transported from the farm to the processing enterprise or the sales market, the transportation time limit critical value may be even shorter, such as 2 days, because freshness is crucial for the quality and sales of beef.

[0040] Regarding the load factor of path nodes, assume that there are multiple transportation nodes for fruits and beef in the target area, such as the collection centers in the production areas, transfer stations during transportation, and wholesale markets at the destinations. In summer, due to the large transportation volume of fruits and beef, the load factors of these nodes will increase accordingly. For example, a collection center in a fruit production area may have to handle a large number of fruit transportation tasks during the peak fruit harvest season in summer, and its load factor may reach 0.8, indicating a nearly saturated state. While in winter, the load factor may only be 0.3. For the nodes for beef transportation, such as the collection points near the farms, the load factor will also increase during the peak demand periods such as holidays, approaching the full-load state.

[0041] Step S140, generate a dynamic cold-chain transportation scheduling plan with timestamps based on the multi-dimensional cold-chain demand parameters.

[0042] Based on the multi-dimensional cold-chain demand parameters obtained previously, formulate a dynamic cold-chain transportation scheduling plan for fruits and beef.

[0043] For fruit transportation, taking bananas as an example, since their temperature fluctuation tolerance threshold is small and the transportation time limit critical value is short. During transportation, it is necessary to precisely arrange the transportation time and route. Assume that bananas are transported from production area A to the fruit market in city B. According to the temperature fluctuation tolerance threshold, select a transportation vehicle with good refrigeration effect and precise temperature control. In summer, the transportation time must be strictly controlled within 3 days. In the transportation route planning, avoid high-temperature sections or traffic congestion sections to reduce the transportation time. For the departure time, choose to depart in the early morning when the temperature is relatively low, and during transportation, dynamically adjust the power of the refrigeration equipment according to the real-time temperature data. For example, when passing through a high-temperature area, increase the refrigeration power in advance to ensure that the temperature inside the vehicle always remains between 12 - 14°C.

[0044] For beef transportation, because its temperature fluctuation tolerance threshold is small and the transportation time limit critical value is short. When transporting from farm C to the processing enterprise in city D, the transportation vehicle should have good heat preservation and refrigeration capabilities. The departure time should ensure that the beef reaches the destination in the shortest time. For example, depart at night when the external temperature is relatively low, which helps to reduce the energy consumption of the refrigeration equipment. The transportation route should choose roads with better road conditions and shorter distances, and during transportation, check the temperature inside the vehicle and the state of the beef at regular intervals. If it is found that the temperature has an upward trend approaching the temperature fluctuation tolerance threshold, adjust the refrigeration equipment in time.

[0045] In terms of the load of path nodes, for each node in the transportation of fruits and beef, such as the collection center, transfer station, etc., the incoming and outgoing of goods are arranged according to the load factor. During the peak harvest season of fruits in summer, if the load factor of the collection center is close to saturation, the transportation of perishable fruits such as bananas is given priority to ensure that they can leave the collection center as soon as possible and reduce the residence time. For the nodes in beef transportation, during the peak demand period, the loading and unloading order of vehicles is reasonably arranged to improve the turnover efficiency of the nodes. At the same time, according to the demand and node load conditions in different time periods, a specific timestamp is assigned to each transportation task to accurately arrange the start time, arrival time of transportation, and the residence time at each node, ensuring that the quality of fruits and beef is not affected during the entire cold chain transportation process.

[0046] Based on the above steps, the embodiment of the present application obtains a historical cold chain order dataset including transportation records of temperature-sensitive goods and their corresponding environmental parameters in a target area for multiple time periods, associates the transportation records with the environmental parameters, and defines a set of transportation demand characteristics. Among them, the association characteristics between the types of goods and temperature sensitivity break the simple classification of the temperature requirements for goods in the past, deeply explore the internal relationship of different goods in terms of temperature sensitivity, and provide a basis for more accurately controlling the transportation temperature; the balance characteristics between transportation timeliness and equipment energy consumption solve the long-existing problem in cold chain transportation that it is difficult to balance timeliness and energy consumption. By analyzing the relationship between the two, a new perspective is provided for optimizing transportation strategies; the matching characteristics between regional climate and warehousing conditions combine the external environment with internal warehousing conditions, which is a key connection ignored in the past cold chain transportation demand analysis and helps to reasonably plan the warehousing layout and condition setting.

[0047] In the prediction stage, the set of transportation demand characteristics extracted is input into a pre-trained spatio-temporal prediction model to generate multi-dimensional cold chain demand parameters for the target area within a specified future period. The generation of multi-dimensional parameters such as the temperature fluctuation tolerance threshold, transportation timeliness critical value, and path node load factor can, compared with traditional single-dimensional prediction, comprehensively and prospectively depict the cold chain transportation demand, enabling transportation enterprises to understand in advance the multi-faceted requirements in temperature control, time arrangement, and resource allocation during future transportation processes.

[0048] Traditional scheduling schemes often lack comprehensive consideration of the time dimension and multi-dimensional demand parameters and are difficult to adapt to the complex and changeable cold chain transportation environment. However, this scheme can, by combining timestamps and multi-dimensional parameters, scientifically schedule in real time and dynamically according to the transportation demands at different future moments, improve the utilization efficiency of cold chain transportation resources, reduce transportation costs, and at the same time ensure the transportation quality of temperature-sensitive goods to the greatest extent, enhancing the intelligence and adaptability levels of the entire cold chain transportation system.

[0049] In a possible implementation manner, step S140 includes

[0050] Step S141: Optimize and generate a cold chain transportation path topology based on the multi-dimensional cold chain demand parameters. Each transportation node in the cold chain transportation path topology is associated with a dynamic resource allocation weight, and the dynamic resource allocation weight is negatively correlated with the historical failure rate, real-time temperature control ability, and adjacent node connectivity efficiency of the corresponding node.

[0051] In this embodiment, the process is elaborated in detail taking the cold chain transportation of fruits and beef as an example. For the transportation of bananas among fruits, consider the transportation link from the banana plantation to the fruit market in a distant city. The nodes on the transportation path include the collection center near the plantation, the transfer station during transportation, and the wholesale warehouse in the destination city, etc. If the historical failure rate of the collection center is relatively high, for example, there have been multiple refrigeration equipment failures due to equipment aging in the past year, resulting in large temperature fluctuations of bananas during the collection process and affecting the quality, then its dynamic resource allocation weight will be relatively low. The real-time temperature control ability is also an important factor. If the current refrigeration equipment of the collection center can only control the temperature within 13 - 15°C, while the optimal transportation temperature of bananas is 12 - 14°C, exceeding the suitable temperature range, this indicates insufficient temperature control ability and will also reduce the dynamic resource allocation weight. In terms of the adjacent node connectivity efficiency, if the road condition between the collection center and the next transfer station is poor, with frequent traffic jams, resulting in an extended transportation time and low connectivity efficiency, this will also reduce the dynamic resource allocation weight of the collection center.

[0052] For the transportation of beef, on the path from the farm to the processing enterprise or sales market, if the collection point near the farm has had multiple refrigeration equipment failures due to unstable power supply in the past, affecting the preservation of beef, its dynamic resource allocation weight will be reduced. If the real-time temperature control ability of the collection point can only maintain the beef temperature within -1 - 1°C, while the ideal temperature is -2 - 0°C, which will affect the freshness of the beef, it will also reduce its dynamic resource allocation weight. In terms of the adjacent node connectivity efficiency, if the transportation route between the collection point and the next transportation node is often affected by the weather, such as being prone to snow and ice in winter, affecting the transportation speed and the safety of goods, this will reduce its dynamic resource allocation weight. Based on these factors, a cold chain transportation path topology is generated through an optimization algorithm, preferentially selecting a combination of nodes with higher dynamic resource allocation weights to form a transportation path to ensure the quality and efficiency of fruits and beef during transportation.

[0053] Step S142: Dynamically adjust the matching relationship between the transportation time limit critical value and the temperature fluctuation tolerance threshold according to the real-time operation status data of each node in the cold chain transportation path topology, and generate a set of abnormal event response strategies. The set of abnormal event response strategies includes the activation conditions of backup refrigeration equipment, the path switching priority rules, and the emergency storage capacity allocation plan.

[0054] Continue to illustrate with the cold chain transportation of fruits and beef. In the transportation of fruits, for example, when bananas are on the way from the collection center to the transfer station, it is detected in real time that there is a minor fault in the refrigeration equipment of the transport vehicle, resulting in the temperature inside the vehicle rising from the normal range of 12-14°C to 14-15°C, approaching the upper limit of the temperature fluctuation tolerance threshold of bananas. At this time, according to the real-time operation status data of each node in the transportation path topology, since the refrigeration equipment failure affects the temperature control during transportation, it is necessary to dynamically adjust the matching relationship between the transportation time limit critical value and the temperature fluctuation tolerance threshold. Originally, the transportation time limit critical value for bananas from the collection center to the transfer station was 1 day, but due to the temperature rise, in order to ensure the quality of bananas, the transportation time limit critical value may be shortened to half a day. At the same time, the condition for activating the standby refrigeration equipment is set to start the standby refrigeration equipment immediately when the temperature rises to 15°C to lower the temperature inside the vehicle.

[0055] Regarding the path switching priority rule, if there is severe traffic congestion on the current transportation route, resulting in a significant extension of the transportation time and threatening the quality of bananas, then the standby transportation path is given priority. In terms of the emergency storage capacity allocation plan, if it is found that some bananas have shown slight signs of deterioration due to temperature fluctuations when the bananas arrive at the transfer station, then according to the emergency storage capacity allocation plan, the bananas with a higher risk of deterioration are preferentially allocated to the emergency storage area, where the temperature and humidity conditions are more suitable for temporarily storing and inspecting and processing this part of the bananas to prevent the deterioration situation from worsening further.

[0056] In the transportation of beef, assume that when beef is on the way from the collection point at the farm to the processing enterprise, it is detected in real time that the external temperature suddenly rises. Although the refrigeration equipment is operating normally, the temperature inside the vehicle rises from the normal range of -2-0°C to -1-0.5°C, approaching the upper limit of the temperature fluctuation tolerance threshold of beef. At this time, the transportation time limit critical value is shortened. The original transportation time limit of 2 days may be adjusted to 1.5 days. The condition for activating the standby refrigeration equipment is set to start when the temperature rises to 0.5°C. If there are force majeure factors such as natural disasters on the transportation route, resulting in the road being impassable, according to the path switching priority rule, the standby path with better road conditions, relatively shorter distance and capable of ensuring the temperature requirements of beef is preferentially selected. When the beef arrives at the storage point near the processing enterprise, if it is found that the color and smell of some beef are abnormal, according to the emergency storage capacity allocation plan, this part of the beef is stored separately in the emergency storage area, where the temperature and ventilation conditions are more conducive to further inspection and processing of the beef to prevent the deteriorated beef from affecting other normal beef.

[0057] Step S143: Perform spatio-temporal alignment processing on the set of abnormal event response strategies and the real-time meteorological data stream to generate a dynamic cold-chain transportation scheduling plan with timestamps. The dynamic cold-chain transportation scheduling plan includes the equipment pre-start time window, the threshold for the interval between transportation batches, and the trigger conditions for cross-regional collaborative transportation.

[0058] When performing spatio-temporal alignment processing with the real-time meteorological data stream, take the transportation of bananas as an example. If the meteorological data predicts high-temperature weather on the transportation route in the next few hours, then according to the set of abnormal event response strategies, the equipment pre-start time window will be opened earlier. For example, under normal circumstances, the refrigeration equipment starts 15 minutes before loading. Now, due to the prediction of high-temperature weather, the pre-start time window is advanced to 30 minutes before loading to ensure that the temperature inside the vehicle is within the suitable transportation temperature range of 12 - 14 °C for bananas at the time of loading. Regarding the threshold for the interval between transportation batches, if the meteorological data shows that the weather conditions on the transportation route are unstable during a certain period, in order to avoid the mutual influence of different batches of bananas during transportation. For example, high-temperature weather may cause an increased burden on the refrigeration equipment, and if the batch interval is too small, it may affect the refrigeration effect. Then, the threshold for the interval between transportation batches is increased. Originally, a batch of goods was dispatched every 2 hours, and now it is adjusted to every 3 hours.

[0059] When it comes to the trigger conditions for cross-regional collaborative transportation, if the banana production in a certain area suddenly increases significantly, while the local market digestion capacity is limited, and at the same time the meteorological data shows that there are suitable meteorological conditions for banana transportation in the surrounding areas, and there is a demand for bananas in the surrounding area markets, then cross-regional collaborative transportation is triggered. For example, the banana production in the area where the local banana plantation is located has increased greatly, while there is a demand in the urban fruit markets in the surrounding areas, and the meteorological data shows good weather on the transportation route. At this time, cross-regional collaborative transportation is initiated to transport bananas to the surrounding areas, which not only solves the sales problem of local bananas but also meets the market demand in the surrounding areas.

[0060] For beef transportation, meteorological data predicts that low-temperature weather will occur during transportation, which may cause the beef to be frostbitten. According to the set of abnormal event response strategies, adjust the pre-start time window of the equipment, and preheat the insulation equipment of the transportation vehicle in advance to ensure that the temperature inside the vehicle is within the appropriate range of -2 to 0 °C when loading. Regarding the threshold of the transportation batch interval, if the meteorological data shows that severe weather such as heavy snow may occur on the transportation route during a certain period, in order to avoid the impact on different batches of beef during transportation, increase the threshold of the transportation batch interval. For example, originally a batch of goods was dispatched every 1.5 hours, and now it is adjusted to every 2.5 hours. Regarding the trigger condition for cross-regional collaborative transportation, if the beef production in a certain farm is excessive, while the processing capacity of local processing enterprises is limited, and at the same time the meteorological data shows that there are suitable transportation and processing conditions in other regions and there is a demand for beef, then trigger cross-regional collaborative transportation, transport the beef to other regions for processing or sales, and achieve the effective allocation of resources. In this way, a cold-chain transportation dynamic scheduling plan with a timestamp is generated to accurately arrange all links in the cold-chain transportation of fruits and beef, ensuring the quality of the goods and the transportation efficiency.

[0061] In a possible implementation manner, step S120 includes:

[0062] Step S121, identify the correspondence between the cargo category code and the temperature monitoring curve in the historical cold-chain order data, and generate a temperature sensitivity distribution map.

[0063] In this embodiment, taking the cold-chain transportation of fruits and beef as an example, in the historical cold-chain order data, for bananas among fruits, their cargo category codes correspond to specific temperature monitoring curves. The cargo category code of bananas is a specific identifier, such as "F-001", which uniquely identifies bananas in the entire cold-chain transportation data system. Regarding the temperature monitoring curve, starting from the picking of bananas, during the storage link, the temperature is strictly controlled at about 13 - 14 °C, and this temperature range can delay the ripening process of bananas to the greatest extent. When bananas are loaded into the transportation vehicle, the temperature monitoring equipment starts to continuously record the temperature change. If the transportation distance is long, the temperature may rise slightly at the beginning of transportation, for example, from 13.5 °C to 14 °C, because of the heat exchange during vehicle startup and cargo loading. With the stable operation of the refrigeration equipment, the temperature will gradually stabilize between 13 - 14 °C. Before arriving at the destination, due to the vehicle approaching the urban area and the slightly higher external temperature, the temperature will fluctuate slightly again.

[0064] For apples, the goods category code is "F-002", and its temperature monitoring curve is different from that of bananas. When storing apples, the temperature can be within the range of 2-4°C. After being picked and entering the warehouse, the temperature is maintained within this range. During transportation, the temperature fluctuation is relatively small, basically staying within 2-3°C. This is because apples are slightly less sensitive to temperature than bananas. The goods category code for beef is "M-001", and its temperature monitoring curve shows that after slaughter, beef is quickly cooled to -2-0°C. During transportation, this temperature range must be strictly maintained. During the transportation from the farm to the processing plant or the sales market, the temperature curve recorded by the temperature monitoring equipment fluctuates very little. Once the temperature exceeds the range of -2-0°C, the freshness of beef will be affected, and the risk of bacterial growth will increase significantly. By identifying the corresponding relationships between these different goods category codes and temperature monitoring curves, a temperature sensitivity distribution map is generated. This temperature sensitivity distribution map intuitively shows the temperature sensitivity characteristics of different goods during cold chain transportation, providing an important basis for subsequent cold chain transportation scheduling.

[0065] Step S122: Analyze the correlation pattern between the transportation timeliness record and the refrigeration equipment energy consumption log, and establish a timeliness-energy consumption balance coefficient matrix.

[0066] Taking banana transportation as an example, when the transportation distance is 500 kilometers and the transportation timeliness requirement is to reach the destination within 3 days, the refrigeration equipment needs to operate continuously to maintain a temperature of 13-14°C. The refrigeration equipment energy consumption log shows that during this transportation process, the energy consumption of the refrigeration equipment shows a certain change pattern over time. In the initial stage of transportation, since the vehicle needs to reduce the temperature from the external environmental temperature to the suitable transportation temperature for bananas, the refrigeration equipment needs to operate at a high power, resulting in high energy consumption. When the temperature stabilizes, the energy consumption will decrease, but still needs to continuously consume energy to maintain the temperature. If the transportation timeliness is shortened to 2 days, in order to ensure the quality of bananas, the vehicle needs to increase the driving speed, which may cause the refrigeration equipment to be subjected to more vibrations and external environmental interferences, and the refrigeration equipment needs to adjust the refrigeration power more frequently, resulting in an increase in energy consumption.

[0067] For apple transportation, assume the transportation distance is 800 kilometers and the transportation time limit is 5 days. After the refrigeration equipment reduces the temperature to 2 - 4°C at the beginning of transportation, since the temperature sensitivity of apples is relatively lower than that of bananas, the refrigeration equipment does not need to frequently adjust the power, and the energy consumption is relatively stable. However, if the transportation time limit is shortened to 3 days, in order to meet the faster transportation speed, the refrigeration equipment may need to more flexibly adjust the refrigeration power during the acceleration and deceleration of the vehicle to cope with the impact of external environmental changes on the temperature in the carriage, which will also lead to an increase in energy consumption. In beef transportation, the transportation distance is 300 kilometers and the transportation time limit is 2 days. Since beef has strict temperature requirements, the temperature range of -2 - 0°C must be maintained at all times. The energy consumption of the refrigeration equipment is relatively stable during transportation. However, if the transportation time limit is shortened to 1.5 days and the vehicle driving speed increases, the refrigeration equipment needs to more precisely control the temperature to prevent the temperature of beef from fluctuating, which may require a higher refrigeration power, thus increasing the energy consumption. By analyzing the energy consumption of the refrigeration equipment for these different goods under different transportation time limits, an aging - energy consumption balance coefficient matrix is established. The elements in this matrix represent the quantitative relationship of the energy consumption of the refrigeration equipment required to maintain the temperature of the goods under different transportation time limits, providing key data for cost control and efficiency optimization of cold chain transportation.

[0068] Step S123, detect the matching degree between the regional climate data and the storage temperature maintenance ability, and calculate the climate adaptability index.

[0069] Taking the storage of bananas as an example, in the tropical and subtropical regions in the south, the climate is hot and humid, and the summer temperature often reaches over 30°C, and the humidity is also very high. The storage facilities for bananas need to have strong refrigeration and dehumidification capabilities. If the storage temperature maintenance ability is insufficient, for example, the refrigeration equipment can only reduce the temperature to 15 - 16°C and cannot reach the optimal temperature of 13 - 14°C for banana storage, then the storage quality of bananas will be affected, and the bananas may ripen and rot too quickly. At this time, the matching degree between the regional climate data and the storage temperature maintenance ability is relatively low.

[0070] For apple storage, in the northern temperate regions, winters are cold with temperatures potentially dropping below -10°C, and summers are relatively mild. Apple storage facilities need to prevent apples from being frostbitten in winter and maintain suitable temperatures in summer. If the storage temperature maintenance ability can be flexibly adjusted according to seasonal changes, for example, reducing refrigeration appropriately in winter and stably maintaining a temperature of 2 - 4°C in summer, then the matching degree between regional climate data and the storage temperature maintenance ability is relatively high. In the case of beef storage, whether in the cold north or the hot south, a temperature of -2 - 0°C needs to be strictly maintained. In the hot and humid southern regions, storage facilities require better heat insulation and refrigeration capabilities to combat the external climate. If the storage temperature maintenance ability can effectively respond to the external climate and ensure the freshness of beef, then the matching degree between regional climate data and the storage temperature maintenance ability is relatively high. By detecting the different regional climate data and the storage temperature maintenance ability, the climate adaptability index is calculated. This index quantifies the matching relationship between regional climate and the storage temperature maintenance ability, providing an important reference for storage site selection and facility configuration during the cold chain transportation process.

[0071] Step S124, fuse the temperature sensitivity distribution map, the time - energy consumption balance coefficient matrix, and the climate adaptability index to generate a three - dimensional feature vector space as the transportation demand feature set.

[0072] For example, the temperature sensitivity distribution map describes the temperature sensitivity characteristics of goods such as bananas, apples, and beef during transportation, which is one of the core requirements of cold chain transportation. The time - energy consumption balance coefficient matrix reflects the energy consumption relationship of refrigeration equipment required to ensure the temperature of goods under different transportation times, which is related to the cost and efficiency of cold chain transportation. The climate adaptability index quantifies the matching relationship between regional climate and the storage temperature maintenance ability, which is of great significance for the storage link of cold chain transportation.

[0073] Taking banana transportation as an example, the temperature sensitivity distribution map shows that bananas can maintain better quality within the temperature range of 13 - 14°C, and this temperature requirement occupies one dimension in the three - dimensional feature vector space. The time - energy consumption balance coefficient matrix shows the energy consumption situation of the refrigeration equipment when the transportation time is 3 days and the transportation distance is 500 kilometers, and this data occupies another dimension in the three - dimensional feature vector space. The climate adaptability index reflects the adaptability of banana storage facilities under local climate conditions. For example, in the hot and humid southern regions, this index is relatively low, and this data also becomes one dimension of the three - dimensional feature vector space.

[0074] For apples and beef, their respective temperature sensitivities, aging - energy consumption relationships, and climate adaptability data are also incorporated into this three - dimensional feature vector space. This three - dimensional feature vector space comprehensively covers the key transportation demand characteristics during the cold - chain transportation of fruits and beef. As a set of transportation demand characteristics, it provides comprehensive and accurate data input for the subsequent spatio - temporal prediction model, helping to more accurately predict the demand parameters of cold - chain transportation, thereby optimizing the scheduling and management of cold - chain transportation.

[0075] Among them, the training steps of the spatio - temporal prediction model include:

[0076] Step S101, divide the three - dimensional feature vector space into a training set and a validation set, and label the corresponding time - series tags for the training set and the validation set.

[0077] In the cold - chain transportation scenario of fruits and beef, for the generated three - dimensional feature vector space, divide it into a training set and a validation set. Assume that the three - dimensional feature vector space contains cold - chain transportation data of fruits and beef in the past year. According to a certain ratio, for example, 80% of the data is divided into the training set, and 20% of the data is divided into the validation set.

[0078] For banana transportation data, in the training set, it includes data such as temperature sensitivity, aging - energy consumption balance coefficient, and climate adaptability under different seasons, different transportation distances, and different transportation aging times. For example, a set of data for transporting bananas in spring, with a transportation distance of 300 kilometers and a transportation aging time of 2 days, its corresponding time - series tag is spring, 300 kilometers, 2 days. This tag accurately describes the time and transportation - related characteristics of this set of data. In the validation set, it also includes similar banana transportation data, but different from the data in the training set. For example, data for transporting bananas in summer, with a transportation distance of 400 kilometers and a transportation aging time of 2.5 days, its time - series tag is summer, 400 kilometers, 2.5 days.

[0079] For the apple and beef transportation data, the training set and validation set are also divided in this way, and the corresponding time series labels are marked. The apple transportation data in the training set may include data on autumn transportation, with a transportation distance of 600 kilometers and a transportation time of 4 days, and the labels are autumn, 600 kilometers, and 4 days. In the validation set, there may be data on winter transportation, with a transportation distance of 500 kilometers and a transportation time of 3.5 days, and the labels are winter, 500 kilometers, and 3.5 days. The beef transportation data in the training set may include data from a certain farm to a specific processing enterprise, with a transportation distance of 200 kilometers and a transportation time of 1.5 days, and the labels are specific time, 200 kilometers, and 1.5 days. In the validation set, there may be data from another farm to a different processing enterprise, with a transportation distance of 250 kilometers and a transportation time of 1.8 days, and the labels are specific time, 250 kilometers, and 1.8 days. In this way, the three-dimensional feature vector space is accurately divided into a training set and a validation set, and the corresponding time series labels are marked for it, providing an organized and labeled data source for the subsequent training of the spatio-temporal prediction model.

[0080] Step S102, construct a deep spatio-temporal convolutional network, which includes a climate fluctuation perception layer, a transportation path dependence layer, and a device state memory unit.

[0081] For example, the climate fluctuation perception layer is mainly responsible for dealing with the impact of regional climate data on cold chain transportation. Taking the transportation of bananas as an example, when bananas are transported from tropical regions to temperate regions, the climate fluctuation perception layer will receive the high-temperature and high-humidity climate data in tropical regions and the relatively mild climate data in temperate regions. It can analyze the impact of the climate change from tropical to temperate regions on the temperature control of banana transportation during the transportation process. For example, from a high-temperature environment to a relatively low-temperature environment, the refrigeration equipment may need to make appropriate power adjustments during transportation to prevent bananas from being affected by sudden temperature changes.

[0082] The transportation path dependence layer focuses on factors related to the transportation path. For apple transportation, from the orchard to the wholesale market, the transportation path may pass through mountainous and plain areas. The transportation path dependence layer will consider the impact of the rugged mountain roads on the transportation speed, thus affecting the transportation time, and the impact of traffic flow in the plain area on the transportation. If there are frequently congested sections on the transportation path, this layer will take them into account because congestion will lead to an extended transportation time, thereby affecting the energy consumption of the refrigeration equipment and the freshness preservation of apples.

[0083] The device status memory unit is used to record the status information of cold chain transportation equipment such as refrigeration equipment. During beef transportation, the device status memory unit will record information such as the working hours of the refrigeration equipment, the change in refrigeration efficiency, and whether there have been any failures. For example, after long-term operation, the refrigeration efficiency of the refrigeration equipment may decline. The device status memory unit will record this change and feedback it to the entire deep spatio-temporal convolutional network. When predicting the temperature control requirements during beef transportation, these device status information will be taken into consideration. By constructing a deep spatio-temporal convolutional network that includes a climate fluctuation perception layer, a transportation path dependence layer, and a device status memory unit, various factors during the cold chain transportation of fruits and beef can be comprehensively considered, thus predicting the demand parameters more accurately.

[0084] Step S103, optimize the network parameters of the deep spatio-temporal convolutional network through the backpropagation algorithm to minimize the spatio-temporal correlation loss function between the predicted output of the deep spatio-temporal convolutional network and the true demand parameters of the validation set.

[0085] For example, taking banana transportation as an example, after inputting the training set data, the deep spatio-temporal convolutional network will output predicted values of demand parameters for banana transportation, such as the temperature fluctuation tolerance threshold, the critical value of transportation timeliness, etc. Then these predicted values are compared with the true demand parameters of the validation set. Suppose there is a set of banana transportation data in the validation set, the true temperature fluctuation tolerance threshold is ±0.5°C, and the critical value of transportation timeliness is 3 days. The initial predicted values of the deep spatio-temporal convolutional network are a temperature fluctuation tolerance threshold of ±1°C and a critical value of transportation timeliness of 3.5 days.

[0086] Calculate the spatio-temporal correlation loss function, which comprehensively considers the prediction errors of the temperature fluctuation tolerance threshold and the critical value of transportation timeliness. Since there are differences between the predicted values and the true values, the value of the loss function is relatively large. Through the backpropagation algorithm, the value of the loss function is propagated backward from the output layer to each layer of the network, adjusting the network parameters, such as adjusting the weights of climate data in the climate fluctuation perception layer, adjusting the weights of path factors in the transportation path dependence layer, and adjusting the weights of device status information in the device status memory unit, etc.

[0087] The same process applies to the transportation of apples and beef. For example, in the transportation of apples, the true demand parameters of the validation set are a temperature fluctuation tolerance threshold of ±1°C, and the critical value of transportation time limit is 5 days. The initial prediction values of the network are a temperature fluctuation tolerance threshold of ±1.5°C and a critical value of transportation time limit of 5.5 days. The network parameters are adjusted through the backpropagation algorithm to gradually reduce the loss function. In the transportation of beef, assume that the true demand parameters of the validation set are a temperature fluctuation tolerance threshold of ±0.3°C and a critical value of transportation time limit of 2 days. The initial prediction values of the network are a temperature fluctuation tolerance threshold of ±0.5°C and a critical value of transportation time limit of 2.2 days. By continuously adjusting the network parameters through backpropagation, the spatio-temporal correlation loss function between the predicted output of the deep spatio-temporal convolutional network and the true demand parameters of the validation set is minimized, thereby improving the prediction accuracy of the deep spatio-temporal convolutional network for the demand parameters of fruit and beef cold chain transportation.

[0088] Step S104, when the change rate of the loss value for N consecutive training cycles is lower than a preset threshold, freeze the network parameters of the deep spatio-temporal convolutional network and export the model weights.

[0089] For example, assume that the preset threshold is 0.01 and N is 5. During training, the change rate of the loss value is calculated for each training cycle. Taking the transportation of bananas as an example, in the initial few training cycles, as the network parameters are adjusted by the backpropagation algorithm, the loss value will gradually decrease, and the change rate of the loss value is also relatively large. However, as training progresses, when the change rate of the loss value for 5 consecutive training cycles is lower than 0.01, it indicates that the deep spatio-temporal convolutional network has converged to a relatively optimal state.

[0090] The same is true for the transportation of apples and beef. For example, in the training of the deep spatio-temporal convolutional network related to apple transportation, when the change rate of the loss value for 5 consecutive training cycles is lower than 0.01, it indicates that the prediction of the network for the demand parameters of apple cold chain transportation has reached a relatively stable and accurate state. Similarly, in the training of the deep spatio-temporal convolutional network related to beef transportation, when this condition is met, it shows that the prediction ability of the network for the demand parameters of beef cold chain transportation has been optimized to a certain extent. At this time, freeze the network parameters of the deep spatio-temporal convolutional network, no longer adjust it, and then export the model weights. These model weights contain the parameter information of each layer such as the climate fluctuation perception layer, transportation path dependence layer, and device status memory unit after optimization. These weights can be used for subsequent prediction of cold chain transportation demand parameters, providing an accurate basis for the scheduling and management of cold chain transportation.

[0091] In a possible implementation manner, step S141 includes:

[0092] Step S1411, calculate the bearing margin value of each transportation section according to the path node load factor.

[0093] In this embodiment, in the cold chain transportation scenarios of fruits and beef, the transportation routes from the fruit production areas to the urban sales markets and from the beef farms to the processing enterprises or sales points are considered. The routes contain multiple nodes, such as the collection centers in the fruit production areas, the transfer stations during transportation, the distribution centers on the urban fringes, the collection points in the beef farms during transportation, the cold storage warehouses in the middle, and the processing workshops at the destinations. Taking the transportation section from the collection center to the transfer station in fruit transportation as an example, the load factor of the route node reflects the busyness degree and resource occupancy of this node. Suppose the collection center has to handle the collection and temporary storage of 100 boxes of fruits every day in a certain period, and its designed maximum handling capacity is 150 boxes, then its load factor is 100 / 150 = 0.67. The designed receiving capacity of the transfer station is 200 boxes per day, and the actual received quantity is 120 boxes, with a load factor of 120 / 200 = 0.6. For this transportation section, the bearing margin value is equal to 1 - (0.67 + 0.6) = -0.27 (this is only an example calculation, and in practice, it may be adjusted according to specific calculation logics and data, and factors such as transportation directions and node weights may need to be considered). If it is beef transportation, from the collection point in the farm to the cold storage warehouse in the middle, suppose the collection point processes the collection of 50 cows every day, with a maximum handling capacity of 80 cows, the load factor is 50 / 80 = 0.625, the cold storage warehouse receives 40 cows every day, with a maximum receiving capacity of 60 cows, and the load factor is 40 / 60 = 0.667. The bearing margin value of this transportation section is 1 - (0.625 + 0.667) = -0.292. Through such calculations, the bearing margin values of each transportation section can be obtained. This value reflects the remaining bearing capacity of the transportation section and provides basic data for constructing the cold chain transportation route topology later.

[0094] Step S1412, construct a topological relationship graph among transportation nodes based on a graph neural network, where the edge weights in the topological relationship graph are determined by the product of the bearing margin value and the transportation timeliness.

[0095] Taking the cold chain transportation of fruits and beef as an example, for nodes such as the consolidation center, transfer station, and distribution center on the fruit transportation route, as well as nodes such as the collection point, cold storage warehouse, and processing workshop on the beef transportation route, a topological relationship graph is constructed using a graph neural network. In fruit transportation, between the consolidation center and the transfer station, if the carrying margin value is -0.27 (obtained from the previous calculation), and assuming the transportation time for this transportation section is half a day (0.5 days), then the weight of the edge between them is -0.27×0.5 = -0.135. From the transfer station to the distribution center, if the load factor of the transfer station is 0.5 (assumed), the load factor of the distribution center is 0.4, the carrying margin value is 1-(0.5 + 0.4)=0.1, and the transportation time is 1 day, then the edge weight is 0.1×1 = 0.1. For beef transportation, from the collection point at the farm to the cold storage warehouse, if the carrying margin value is -0.292 and the transportation time is 1 day, the edge weight is -0.292×1 = -0.292; from the cold storage warehouse to the processing workshop, assuming the carrying margin value is 0.05 and the transportation time is 0.5 days, the edge weight is 0.05×0.5 = 0.025. The topological relationship graph constructed in this way can reflect the degree of closeness between each node. The edge weight comprehensively considers the carrying margin value and transportation time, which not only reflects the remaining carrying capacity of the transportation section but also takes into account the transportation time factor, providing a basis for finding the optimal transportation route.

[0096] Step S1413, using the dynamic programming algorithm to search for the optimal path set that satisfies the temperature fluctuation tolerance threshold in the topological relationship graph.

[0097] In the cold chain transportation of fruits, taking banana transportation as an example, the temperature fluctuation tolerance threshold of bananas is ±0.5℃ between 12-14℃. Starting from the collection center of the fruit production area, passing through multiple transfer stations and finally reaching the urban sales market, the dynamic programming algorithm is used to search for paths based on the constructed topological relationship diagram. Assume that there are two paths from the collection center to the first transfer station. One path passes through the mountainous area. Although the transportation time is short, the bumpy road may affect the operation of the refrigeration equipment and cause large temperature fluctuations; the other path passes through the plains. The transportation time is slightly longer but the temperature is easier to control. The dynamic programming algorithm will comprehensively consider the node load margin value, edge weight and temperature fluctuation on each path. If the path through the mountainous area has a short transportation time, but the temperature fluctuation may exceed the temperature fluctuation tolerance threshold of bananas, then this path may not be selected. The path through the plains, although the transportation time is slightly longer, can ensure that the temperature is within the tolerance threshold, and the node load margin value and edge weight also meet the requirements, then this path will be included in the optimal path set. For beef transportation, the temperature fluctuation tolerance threshold of beef is ±0.3℃ between -2℃ and 0℃. When searching for the optimal path from the farm to the processing enterprise in the topological relationship diagram, the conditions of each node and the temperature control during transportation should also be considered. If the refrigeration equipment of the cold storage warehouse on a certain path is unstable, which may cause the temperature fluctuation to exceed the tolerance threshold, then this path does not meet the requirements, and those paths that can ensure that the temperature is within the tolerance threshold and perform well in terms of node load margin value and edge weight will be selected into the optimal path set.

[0098] Step S1414, performing a Monte Carlo simulation on each optimal path in the optimal path set, and selecting an optimal path with a failure risk lower than a preset threshold as a trunk transportation channel.

[0099] In terms of fruit transportation, for each path in the optimal path set for banana transportation, Monte Carlo simulation is carried out. Assume that the preset threshold is 10%. An optimal path may pass through multiple nodes, such as a collection center, a transfer station, a distribution center, etc. In the Monte Carlo simulation, the historical failure rates of each node are considered. The refrigeration equipment at the collection center failed 3 times in the past year, and the total number of operating days was 300 days. The failure rate was 3 / 300 = 1%; at the transfer station, the temperature fluctuated abnormally 2 times due to power supply problems in the past year, and the total number of operating days was 300 days. The failure rate was 2 / 300 ≈ 0.67%; at the distribution center, the transportation timeliness was affected 4 times due to loading and unloading equipment failures in the past year, and the total number of operating days was 300 days. The failure rate was 4 / 300 ≈ 1.33%. Considering the failure rates of each node on this path, the total failure risk is calculated as 1% + 0.67% + 1.33% = 3%, which is lower than the preset threshold of 10%. This path can be used as the main transportation channel. For the optimal path of beef transportation, Monte Carlo simulation is also carried out. For example, for an optimal path from the collection point of the farm to the processing enterprise, the historical failure rate of the collection point is 2%, the historical failure rate of the intermediate cold storage warehouse is 1.5%, and the historical failure rate of the processing workshop is 0.5%. The total failure risk is 2% + 1.5% + 0.5% = 4%, which is lower than the preset threshold of 10%. It can also be used as the main transportation channel. Selecting the optimal path with low failure risk as the main transportation channel through Monte Carlo simulation can improve the reliability of the cold chain transportation of fruits and beef.

[0100] Moreover, step S142 includes:

[0101] Step S1421, real-time collect the in-cabin temperature data stream of the transport vehicle and the external environment sensor data.

[0102] During the cold chain transportation of fruits and beef, for fruit transport vehicles, temperature sensors are installed inside the vehicle to be able to collect the in-cabin temperature data stream in real time. For example, during the transportation of bananas, the sensor records the temperature data at regular intervals (such as every 5 minutes). At the same time, environmental sensors are also installed outside the vehicle to collect data such as the external temperature, humidity, and air pressure. When transporting beef, the in-cabin temperature sensor of the transport vehicle accurately monitors the temperature of the environment where the beef is located and records the data at regular intervals as well. The external environment sensor also obtains the external environment information in real time. Taking the transportation of bananas as an example, if it is transported in summer, the external environmental temperature may be as high as over 30°C, and the humidity is relatively high, which forms a large temperature difference with the temperature of 12 - 14°C set inside the cabin to keep the bananas fresh. For beef transportation, in the cold winter, the external environmental temperature may be as low as below -10°C, while the temperature inside the cabin needs to be maintained at -2 - 0°C. These real-time collected data provide a basis for subsequent analysis and decision-making.

[0103] Step S1422: Calculate the deviation degree between the actual temperature fluctuation value of the current transportation section and the predicted tolerance threshold.

[0104] In fruit transportation, for banana transportation, if the predicted temperature fluctuation tolerance threshold is ±0.5°C within the range of 12 - 14°C, that is, 11.5 - 14.5°C. During transportation, the in-cabin temperature data collected in real-time shows that the temperature reaches a minimum of 11°C and a maximum of 15°C within a certain period. Then the actual temperature fluctuation range is 11 - 15°C. When calculating the deviation degree, first determine the range that exceeds the tolerance threshold. The lower limit exceeds 0.5°C (11 - 11.5), and the upper limit exceeds 0.5°C (15 - 14.5). The deviation degree can be calculated through a certain algorithm (such as the ratio of the sum of the temperature values outside the range to the tolerance threshold range, etc.). For beef transportation, if the predicted temperature fluctuation tolerance threshold is ±0.3°C within the range of -2 - 0°C, that is, -2.3 - 0.3°C, and the actually collected temperature data shows a minimum of -2.5°C and a maximum of 0.5°C, then the lower limit exceeds 0.2°C, and the upper limit exceeds 0.2°C. Similarly, calculate the deviation degree according to the corresponding algorithm.

[0105] Step S1423: When the deviation degree exceeds the first critical value, activate the standby refrigeration equipment and recalculate the transportation time efficiency compensation coefficient.

[0106] In banana transportation, assume the first critical value is set to 10% (this 10% is a relative value obtained according to the deviation degree calculation method). If the previously calculated deviation degree exceeds 10%, for example, reaches 15%, it indicates that the temperature fluctuation has a greater impact on the preservation of bananas. At this time, activate the standby refrigeration equipment. After the standby refrigeration equipment starts, the refrigeration power increases to quickly pull the temperature back within the tolerance threshold range. At the same time, due to the startup of the refrigeration equipment and temperature adjustment, the transportation time efficiency may be affected, and it is necessary to recalculate the transportation time efficiency compensation coefficient. The original critical value of banana transportation time efficiency is 3 days. If due to temperature fluctuation and refrigeration equipment adjustment, the critical value of transportation time efficiency may need to be shortened to 2.5 days. This requires recalculating factors such as speed and stop time during transportation to ensure that bananas reach the destination within the specified new transportation time efficiency and the quality is not affected. For beef transportation, if the deviation degree exceeds the first critical value, for example, the first critical value of beef is set to 8%, and the actually calculated deviation degree is 10%, then activate the standby refrigeration equipment and recalculate the transportation time efficiency compensation coefficient, such as adjusting the original critical value of 2-day transportation time efficiency to 1.8 days to ensure the freshness of beef.

[0107] Step S1424: When the deviation degree exceeds the second critical value, trigger the path switching mechanism and update the emergency storage allocation priority.

[0108] In banana transportation, assuming the second critical value is set at 20%, if the calculated deviation exceeds 20%, for example, reaching 25%, this indicates that the temperature control problem on the current transportation path is very serious, which may be due to refrigeration equipment failure or poor external environment and continuous impact. At this time, trigger the path switching mechanism to find an alternative path in the cold chain transportation path topology constructed previously. Meanwhile, update the emergency storage allocation priority. If there are multiple emergency storage points available, preferentially select the one closer to the current location and with better temperature control conditions, and transfer the bananas to the emergency storage point for inspection and temperature adjustment operations to prevent further deterioration of the bananas. For beef transportation, if the deviation exceeds the set second critical value (such as 15%) and reaches 18%, trigger the path switching mechanism, select other suitable transportation paths, and update the emergency storage allocation priority, and transfer the beef to the emergency storage point for processing to ensure that the quality of the beef is not affected more severely.

[0109] In a possible implementation manner, step S143 includes:

[0110] Step S1431, perform spatial matching between the meteorological prediction data and the geographical locations of the nodes in the path topology.

[0111] In this embodiment, taking the transportation path topologies of bananas and beef as examples, which contain numerous nodes, such as the origin collection center of bananas, transfer stations during transportation, fruit markets at the destination, the breeding farm collection points of beef, cold storage warehouses, processing enterprises, etc. The meteorological prediction data covers various meteorological elements such as temperature, humidity, wind speed, precipitation, etc. For example, the meteorological department provides detailed meteorological prediction data within the next 24 hours, including that there will be rainfall and temperature drop in a certain area. In the path topology, the collection center is located in a specific latitude and longitude coordinate area, and the transfer station is located in another area. Perform precise matching between the geographical location information in the meteorological prediction data and the geographical locations of the nodes in the path topology. If the meteorological prediction in the area where the collection center is located shows that rainfall will cause road flooding, which may affect the vehicle access and cargo handling efficiency, this meteorological information is associated with the collection center node. For beef transportation, if strong wind weather is predicted in the area where the cold storage warehouse is located, which may affect the power supply stability of the cold storage warehouse, this meteorological information is matched with the cold storage warehouse node. Through this spatial matching, the potential impacts of different meteorological conditions on each node of the cold chain transportation path can be clarified.

[0112] Step S1432, identify the extreme weather areas that may affect the transportation path within a preset future time period.

[0113] Continuing with the example of fruit and beef transportation, within a preset future time period (such as the next 48 hours), analysis is conducted based on meteorological prediction data. For banana transportation, if the meteorological data shows that a mountainous section of a transportation route is about to encounter heavy rain and lightning, this mountainous area is identified as an extreme weather area that may affect the transportation route. Because heavy rain may trigger landslides and muddy roads, and lightning may affect the operation of the vehicle's electronic equipment, thus threatening the safety of the banana's cold chain transportation. In terms of beef transportation, if a plain area is predicted to have heavy snow, this plain area is the extreme weather area. Heavy snow may cause road snow accumulation and icing, affecting the driving speed and safety of transportation vehicles, and may also affect the timeliness of beef transportation because beef needs to reach the processing enterprise within a specified time to ensure freshness. By analyzing the meteorological data, these extreme weather areas are accurately identified so as to take corresponding countermeasures.

[0114] Step S1433, perform priority ranking on all in-transit transportation tasks for the affected path segment, and the basis for the priority ranking includes the cargo spoilage rate, remaining transportation time, and availability of alternative paths.

[0115] In fruit transportation, for banana transportation, assume there are multiple in-transit transportation tasks on a certain transportation route. If a batch of bananas has been transported for two days and there is still one day's journey to the destination, and the spoilage rate of bananas is relatively fast. Under normal circumstances, the remaining transportation time can just ensure the freshness of the bananas, but due to the extreme weather affecting the path segment, the priority needs to be re-evaluated. At the same time, the availability of alternative paths also needs to be considered. If there is an alternative path, although it may be slightly longer, it can avoid the extreme weather area, then the priority of this task is relatively high. For another transportation task of bananas that still has two days to reach the destination and has a relatively slow spoilage rate, if there is no suitable alternative path, its priority is relatively low. In terms of beef transportation, if a batch of beef has been transported most of the way, the remaining transportation time is short, the spoilage rate of beef is fast, and there is an alternative transportation path, then the priority of this in-transit transportation task is high. And if a batch of beef still has a long remaining transportation time, a slow spoilage rate, and no alternative path, its priority is low. By comprehensively considering factors such as the cargo spoilage rate, remaining transportation time, and availability of alternative paths, a reasonable priority ranking is performed on all in-transit transportation tasks for the affected path segment.

[0116] Step S1434, generate a time-sliced transportation resource reallocation instruction set, and the transportation resource reallocation instruction set specifies the speed adjustment strategy and the adjustment range of the refrigeration power for each cold chain vehicle within each time window.

[0117] Taking the cold chain transportation of fruits and beef as an example, during the transportation of bananas, according to the analysis results above, a time - segmented transportation resource re - allocation instruction set is generated. If during a certain time period, a certain transportation path segment is affected by extreme weather, such as rainy weather. For the cold chain vehicles on this path segment, within a time window (such as 2 - 3 hours) before the rain starts, due to the slippery road surface, in order to ensure safety, the transportation resource re - allocation instruction set may specify that the vehicle reduces its driving speed, for example, from the original 60 kilometers per hour to 40 kilometers per hour. At the same time, due to the reduction in vehicle speed, the heat exchange between the vehicle and the outside world decreases, and the adjustment range of the refrigeration power of the refrigeration equipment may be a 10% reduction to avoid excessive refrigeration. During the transportation of beef, when facing heavy snow weather, within a time window (such as 1 - 2 hours) before the heavy snow arrives, the transportation resource re - allocation instruction set may require the vehicle to reduce its speed in advance, from 80 kilometers per hour to 50 kilometers per hour. And due to the decrease in the external temperature, in order to maintain the temperature of - 2 - 0°C inside the vehicle, the adjustment range of the refrigeration power may be a 15% increase to prevent the beef from being frozen. As time goes by, according to the meteorological conditions and the actual situation of the transportation tasks, different time windows continuously adjust the speed control strategies and the adjustment ranges of the refrigeration power of each cold chain vehicle to ensure the quality and safety of fruits and beef during cold chain transportation.

[0118] In a possible implementation manner, the method further includes:

[0119] Step S210, dividing the target area into multiple cold - chain demand sub - areas based on the historical order distribution density.

[0120] In this embodiment, in the cold - chain transportation scenario of fruits and beef, it is considered that the target area is a large area covering multiple cities and their surrounding rural areas. The statistical data of the historical order distribution density is derived from the cold - chain transportation order records of the past many years. For example, for the transportation orders of bananas and beef, through detailed analysis, it is found that near the commercial areas in the city center, due to the presence of numerous supermarkets, restaurants, and retailers, the order density is very high. These areas have a large and stable demand for fruits and beef, and there is a large amount of goods transportation demand every day. While in some small residential areas in the suburbs of the city, the order density is relatively low, and the goods transportation demand is mainly concentrated on weekends or holidays because residents will make centralized purchases during these times. In rural areas, near fruit plantations and beef farms, the order density shows a periodic change related to the harvest season. During the fruit harvest season, such as when bananas are harvested, the transportation order volume from around the plantation to the city increases significantly, while it is less in the non - harvest season.

[0121] Based on such a historical order distribution density, the target area is divided into multiple cold chain demand sub-areas. The central business district of the city can be divided into one sub-area, marked as Sub-area A. The characteristics of the cold chain demand here are stable and large transportation volume, and extremely high requirements for the freshness and timeliness of goods, because the commercial activities in these areas rely on the continuous supply of fresh fruits and beef. The small residential areas in the suburbs of the city are divided into Sub-area B, whose cold chain demand is periodic and volatile, with a relatively small transportation volume, and the requirement for the freshness of goods depends to a certain extent on the consumption habits of residents. The areas in rural areas close to plantations and farms are further subdivided according to different crops and breeding types. For example, the area around the banana plantation is Sub-area C, and the area around the beef farm is Sub-area D. The cold chain demand in Sub-area C is strong during the banana harvest season, and bananas need to be transported out quickly to avoid spoilage caused by large piles, while the demand drops sharply during the non-harvest season. The beef transportation demand in Sub-area D is related to the breeding cycle and market demand. When the breeding is mature and the market demand is high, the cold chain transportation demand is relatively large.

[0122] Step S220, establish an independent demand fluctuation baseline for each cold chain demand sub-area, and the demand fluctuation baseline includes the daily minimum transportation volume, the typical cargo composition ratio, and the peak period characteristics.

[0123] For Sub-area A, the daily minimum transportation volume is obtained by statistical analysis of historical data. For example, at least 100 boxes of bananas and 500 kg of beef need to be transported every day to meet the basic commercial needs. In terms of the typical cargo composition ratio, since this is a commercial area, the sales ratio of fruits and beef is relatively balanced. Maybe bananas account for 40% of the total cargo transportation volume, and beef accounts for 60%. The peak period characteristics are before lunch and dinner on weekdays and throughout the weekend. During these periods, the demand for fruits and beef in supermarkets, restaurants, etc. increases significantly, and the transportation demand reaches the peak.

[0124] In Sub-area B, the daily minimum transportation volume is relatively small, maybe 20 boxes of bananas and 100 kg of beef per day. In the typical cargo composition ratio, due to the consumption habits of residents, the demand for fruits may be slightly higher than that for beef. Bananas account for 60%, and beef accounts for 40%. The peak periods are mainly concentrated in the afternoon and evening on weekends. At this time, residents have more time to shop, and the demand for fruits and beef increases.

[0125] In the banana harvest season in sub-region C, the minimum daily transportation volume may be as high as 500 boxes of bananas, and the typical cargo composition ratio is almost 100% bananas. The peak period is the concentrated transportation period after banana harvest, usually lasting for several weeks. In the non-harvest season, the minimum daily transportation volume may drop below 10 boxes, and the typical cargo composition ratio is still 100% bananas, but the transportation demand is extremely low. Around the beef farms in sub-region D, the minimum daily transportation volume depends on the breeding scale and market order situation. Assuming it is 300 kg of beef per day, the typical cargo composition ratio is 100% beef. The peak period is related to the breeding cycle, such as the concentrated slaughter period after breeding maturity and the peak period of market demand during holidays.

[0126] Step S230, when the deviation degree of the order flow in the sub-region detected in real time from the demand fluctuation baseline exceeds the preset threshold, trigger the inter-regional transport capacity balance mechanism.

[0127] In the actual cold chain transportation operation, the order flow of each sub-region is continuously tracked through a real-time monitoring system. Taking sub-region A as an example, if on a certain day, the order flow of bananas is only 50 boxes, far lower than the demand fluctuation baseline of 100 boxes per day, and the order flow of beef is 300 kg, also lower than the demand fluctuation baseline of 500 kg. Assuming the preset threshold is 30%, at this time, the deviation degree of the banana order flow is (100 - 50) / 100 = 50%, and the deviation degree of the beef order flow is (500 - 300) / 500 = 40%, both exceeding the preset threshold.

[0128] For sub-region C in the banana harvest season, if for some reason, such as a transportation vehicle breakdown or bad weather, the daily transportation volume can only reach 300 boxes, while the demand fluctuation baseline is 500 boxes, the deviation degree is (500 - 300) / 500 = 40%, exceeding the preset threshold. When this situation occurs, trigger the inter-regional transport capacity balance mechanism.

[0129] Among them, the transport capacity balance mechanism includes the cold storage resource sharing agreement of neighboring sub-regions, the dynamic scheduling rules of cross-regional transport vehicles, and the enabling strategy of temporary storage facilities.

[0130] When the order flow in sub-region A is lower than the demand fluctuation baseline, according to the cold storage resource sharing agreement of neighboring sub-regions, sub-region A can share cold storage resources with neighboring sub-region B. For example, the cold storage in sub-region B has a certain idle capacity during the non-peak period, and sub-region A can temporarily store some goods originally planned to be transported to its own cold storage in the cold storage of sub-region B to relieve its own transport capacity pressure.

[0131] Regarding the dynamic scheduling rules for cross-regional transport vehicles, if there is a shortage of transport capacity in sub-region C during the banana harvest season, and there is surplus transport capacity in the transport vehicles of sub-region A after meeting its own demands, according to the dynamic scheduling rules for cross-regional transport vehicles, some vehicles in sub-region A can be scheduled to sub-region C for banana transportation. These vehicles need to operate according to the specified time, temperature requirements, and transport routes to ensure the quality of cold-chain transportation of bananas.

[0132] The strategy for enabling temporary storage facilities may also play a role in sub-region D. If there is a tight transport capacity in sub-region D during the beef slaughter period and there are temporary storage facilities nearby, these facilities can be enabled. Part of the beef can be temporarily stored in the temporary storage facilities and wait for the scheduling of transport vehicles to avoid spoilage of the beef during the waiting for transportation.

[0133] In a possible implementation manner, the method further includes:

[0134] Step S310, calculating the transport time efficiency correlation matrix between each demand fluctuation sub-region, where the matrix elements of the transport time efficiency correlation matrix represent the maximum allowable transport time that meets the temperature requirements between two demand fluctuation sub-regions.

[0135] Taking sub-regions A, B, C, and D as examples, calculate the transport time efficiency correlation matrix between them. From sub-region A to sub-region B, due to the relatively short distance, convenient transportation, good road conditions, and the ability to ensure the temperature requirements of fruits and beef during transportation, the maximum allowable transport time may be 2 hours. From sub-region A to sub-region C, the distance is relatively far, and different climate regions may be passed through on the way, requiring more complex temperature control measures, and the maximum allowable transport time is 4 hours. From sub-region A to sub-region D, considering the temperature sensitivity of beef and the situation of the transport route, the maximum allowable transport time is 3 hours.

[0136] From sub-region B to sub-region C, due to the need to cross urban and rural areas with complex traffic conditions, the maximum allowable transport time is 3 hours. From sub-region B to sub-region D, the maximum allowable transport time is 2.5 hours. From sub-region C to sub-region D, although the distance is not far, considering the different temperature requirements of bananas and beef and their mutual influence during transportation, the maximum allowable transport time is 2 hours. These matrix elements constitute the transport time efficiency correlation matrix, providing an important basis for the planning and scheduling of cold-chain transportation.

[0137] Step S320, updating the time parameters in the transport time efficiency correlation matrix according to real-time traffic flow data.

[0138] In the actual transportation process, real-time traffic flow data is constantly changing. For example, during the morning and evening rush hours on weekdays, the roads within the city are congested, the traffic flow from sub-area A to sub-area B increases, and the road speed decreases. The original maximum allowable transportation time is 2 hours, but due to traffic congestion, this time may need to be extended to 3 hours. At night, the traffic flow is reduced and the roads are unblocked, and the transportation time from sub-area A to sub-area C may be shortened from 4 hours to 3.5 hours.

[0139] If there is a traffic accident or road construction from sub-area B to sub-area D, the traffic flow will be seriously affected and the maximum allowable transportation time may increase from 2.5 hours to 4 hours. By monitoring and analyzing real-time traffic flow data, the time parameters in the transportation time association matrix are updated in a timely manner to ensure that cold chain transportation can be reasonably arranged according to actual conditions.

[0140] Step S330: When the actual transportation time between any two demand fluctuation sub-areas exceeds the corresponding value in the transportation time efficiency association matrix, a detour route suggestion is generated and the additional energy consumption cost is evaluated.

[0141] Assume that during the transportation process, the actual transportation time from sub-area A to sub-area C exceeds the 4 hours in the transportation time association matrix. At this time, the system will generate a detour route suggestion. The original route may pass through the congested section of the city center, and now it is recommended to detour through the road outside the city. However, the detour route may be longer, requiring more fuel consumption and refrigeration equipment operation time.

[0142] For detour routes, additional energy costs need to be evaluated. If the energy cost of the original route is 1 yuan per kilometer (including refrigeration equipment energy consumption), the total distance is 100 kilometers, and the total energy cost is 100 yuan. The detour route distance becomes 120 kilometers. Due to changes in road conditions and driving speed, the energy cost per kilometer may become 1.2 yuan, and the total energy cost becomes 144 yuan, and the additional energy cost is 144-100=44 yuan.

[0143] Step S340 , performing a weighted comparison between the detour route suggestion and the economic priority of the current transportation task, and selecting a route adjustment solution with the best cost-effectiveness.

[0144] For the transportation task from sub-area A to sub-area C, if the high-value beef is transported and the current economic priority is high, the freshness and timely arrival of the goods are emphasized. Although the detour route has additional energy consumption costs, it can ensure that the beef arrives at the destination within the specified temperature and time, avoiding greater economic losses due to spoilage. Even if the cost of the detour route increases, it may still be chosen from a cost-effectiveness perspective.

[0145] If the bananas transported are relatively low in value and have a low economic priority, the requirements for transportation time are not particularly strict. After comparing the additional energy consumption cost of the detour route and the possible losses caused by the slight deterioration of the bananas, if the additional energy consumption cost is too high, it may be chosen to continue transporting along the original route, while taking some measures, such as adjusting the power of the refrigeration equipment, to minimize the risk of banana deterioration. Through such a weighted comparison, the most cost-effective route adjustment plan that best suits the current transportation task is selected, and the economic optimization of cold chain transportation is achieved while ensuring the quality of the goods.

[0146] In a possible implementation, the method further includes:

[0147] Step S410, establishing a full life cycle performance attenuation model for cold chain transportation equipment, wherein the full life cycle performance attenuation model includes a compressor working efficiency curve, an insulation material aging coefficient, and a battery capacity attenuation function.

[0148] In this embodiment, in the cold chain transportation scenario of fruits and beef, cold chain transportation equipment is essential to ensure the quality of goods. Taking the transport vehicle as an example, the refrigeration equipment in the vehicle includes a compressor, and its working efficiency changes continuously throughout the life cycle. When the equipment is newly put into use, the compressor has a high working efficiency and can quickly reduce the temperature in the car to the temperature range required for fruits (such as 12-14°C for bananas) and beef (-2-0°C). As the use time increases and the number of transportations increases, the working efficiency of the compressor gradually decreases. For example, during the first 1000 hours of operation, the compressor can reduce the temperature of the car from room temperature to the target temperature at a rate of 5°C per hour. But when the operating time reaches 5000 hours, this cooling rate may be reduced to 3°C per hour. Through long-term data collection and analysis, a compressor working efficiency curve can be drawn, which reflects the changes in the working efficiency of the compressor under different operating times.

[0149] The aging coefficient of insulation materials is also an important part of the performance attenuation model of the entire life cycle. The compartments of cold chain transport vehicles use insulation materials to reduce heat exchange. Over time, the insulation materials will gradually age. New insulation materials can effectively prevent external heat from entering the compartment during transportation, so that the energy consumption of refrigeration equipment is kept at a relatively low level. For example, in the early stage of use, bananas with a temperature of 13°C in the compartment are transported for 1 hour in an environment with an external temperature of 30°C, and the temperature rise does not exceed 0.5°C. But after several years of use, the insulation material ages, and the temperature rise may reach 1°C under the same conditions. According to the changes in the insulation performance of the insulation material under different usage times, the aging coefficient of the insulation material can be determined.

[0150] For electric cold-chain transport vehicles, the battery capacity attenuation function is a factor that must be considered. A new battery can provide sufficient power support for the refrigeration equipment and vehicle operation. As the number of charge and discharge cycles increases, the battery capacity gradually decreases. For example, a newly charged battery can support the vehicle to continuously travel 500 kilometers and maintain the normal operation of the refrigeration equipment. After the battery undergoes 500 charge and discharge cycles, its cruising range may decrease to 400 kilometers, and the operating time of the refrigeration equipment will also be correspondingly shortened. By monitoring and analyzing the capacity changes of the battery under different charge and discharge cycles, a battery capacity attenuation function is established. These compressor working efficiency curves, insulation material aging coefficients, and battery capacity attenuation functions together constitute the full-life cycle performance attenuation model of the cold-chain transport equipment, providing an important basis for the maintenance and management of the equipment.

[0151] Step S420, predict the maintainable time window of each transport vehicle according to the real-time equipment monitoring data.

[0152] During cold-chain transportation, various sensors are installed on the vehicle to monitor the operating conditions of the equipment in real time. For the refrigeration equipment, the sensors can monitor parameters such as the operating pressure, temperature, and current of the compressor. Taking the operating pressure of the compressor as an example, under normal circumstances, the operating pressure of the compressor should be maintained within a stable range, such as 2 - 3 MPa. When the real-time monitored operating pressure of the compressor gradually increases and exceeds the normal range, and this trend continues for a period of time, this may be a signal of wear of internal components of the compressor or blockage of the refrigeration system. Combining with the compressor working efficiency curve in the full-life cycle performance attenuation model, it is analyzed that when the operating pressure reaches this abnormal value, according to historical data and model prediction, the compressor may still be able to work normally for 100 hours, but serious failures may occur afterwards.

[0153] For the insulation material, the sensors can monitor the temperature difference between the inside and outside of the carriage. If it is found that the temperature difference between the inside and outside of the carriage gradually decreases under the same external environment, this indicates that the insulation performance of the insulation material is deteriorating. According to the insulation material aging coefficient model, when the temperature difference decreases to a certain extent, it is predicted that the insulation material may still be able to maintain the current state for 300 hours, and then maintenance or replacement is required.

[0154] For the battery of the electric vehicle, monitor parameters such as the battery voltage, current, and remaining power. When the battery voltage drops rapidly after charging, or the consumption rate of the remaining power is much faster than normal, combining with the battery capacity attenuation function, it is predicted that the battery may still be able to support the normal operation of the vehicle for 200 hours, which is the maintainable time window of the battery. By analyzing these real-time equipment monitoring data and combining with the full-life cycle performance attenuation model, accurately predict the maintainable time windows of different equipment of each transport vehicle.

[0155] Step S430: Embed a preventive maintenance plan in the dynamic scheduling plan. The preventive maintenance plan specifies the priority maintenance period for each vehicle and the alternative vehicle scheduling plan.

[0156] In the cold chain transportation of fruits and beef, a preventive maintenance plan is formulated based on the prediction of the maintainable time window of each transport vehicle. For a vehicle transporting bananas, according to the prediction, the compressor of its refrigeration equipment has a maintainable time window of 100 hours, the thermal insulation material has 300 hours, and the battery has 200 hours. Considering the importance of the compressor in maintaining the appropriate temperature for bananas, the priority maintenance period can be set to a low-transport-demand period within the next 100 hours. For example, during the off-season of banana transportation when the transport demand is low, the vehicle can be selected for maintenance during this time.

[0157] During the maintenance period, an alternative vehicle scheduling plan needs to be formulated. If this vehicle was originally responsible for transporting bananas from the banana plantation to the urban wholesale market, then a spare vehicle is allocated from other existing transport vehicles. This spare vehicle needs to meet the same cold chain transportation requirements as the original vehicle, including refrigeration capacity, carriage capacity, etc. During the scheduling process, the transport route and time arrangement need to be adjusted to ensure that the bananas can reach the destination at the specified temperature and time. The same principle applies to vehicles transporting beef. The priority maintenance period is determined according to the maintainable time window of different equipment, and appropriate alternative vehicles are arranged to ensure the uninterrupted cold chain transportation of beef.

[0158] Step S440: When the predicted value of the equipment failure probability exceeds the safety threshold, execute the maintenance plan in advance and recalculate the transport path topology.

[0159] During the cold chain transportation process, continue to take the vehicles transporting bananas and beef as examples. Assume that the safety threshold is set at a 10% equipment failure probability. Through the real-time analysis of the equipment operation data and the prediction of the full-life cycle performance degradation model, if the predicted value of the compressor failure probability of a certain vehicle's refrigeration equipment reaches 15%, exceeding the safety threshold. At this time, regardless of whether it is currently in the priority maintenance period, the maintenance plan needs to be executed in advance.

[0160] Since the vehicle needs to be maintained, the transport path topology originally planned based on this vehicle needs to be recalculated. For example, this vehicle was originally a key link in the transport path from the fruit production area through multiple transfer stations to the urban sales market. When recalculating the transport path topology, multi-dimensional cold chain demand parameters such as other available transport vehicles, the load factor of each node, transport timeliness, and the temperature fluctuation tolerance threshold need to be considered. The transport route may be adjusted, other vehicles may be selected, or the transport tasks of certain nodes may be increased to ensure the continuous, efficient, and safe cold chain transportation of bananas and beef.

[0161] In a possible implementation manner, the method further includes:

[0162] Step S510, constructing a multi-level cold chain resource allocation strategy, where the multi-level cold chain resource allocation strategy includes a core node resource reservation mechanism and an edge node dynamic sharing mechanism.

[0163] In the cold chain transportation network of fruits and beef, there are multiple levels of nodes. The core nodes can be large fruit consolidation centers, storage centers of beef processing enterprises, etc. These nodes play a key hub role in cold chain transportation. The edge nodes are some small transfer stations, temporary storage points at the retail end, etc.

[0164] The core node resource reservation mechanism is to ensure that in critical moments, such as the fruit harvest season or the beef sales peak season, the core nodes can meet important transportation needs. Taking the fruit consolidation center as an example, during the banana harvest season, the consolidation center needs to reserve a certain proportion of storage space, loading and unloading equipment, and transportation vehicle resources. Suppose the total storage space of the consolidation center is 1000 cubic meters. According to historical data and predicted harvest volume, 30% of the storage space, that is, 300 cubic meters, is reserved specifically to cope with the possible large-scale arrival of bananas. For the loading and unloading equipment, 20% of the equipment working time is reserved to ensure efficient loading and unloading of bananas during peak hours. For the transportation vehicles, 10% of the vehicle capacity is reserved so that bananas can be transported out in a timely manner in case of emergencies.

[0165] The edge node dynamic sharing mechanism takes into account the flexibility of edge node resources. For example, in a certain small transfer station, while its storage space and refrigeration equipment meet its own daily transportation tasks, if there is a backlog of goods at the adjacent temporary storage point at the retail end and more storage space is needed, according to the edge node dynamic sharing mechanism, a part of the idle storage space of the transfer station can be shared with the temporary storage point at the retail end. Similarly, for the refrigeration equipment, if the refrigeration equipment at the retail end fails, the transfer station can provide refrigeration support to a certain extent to ensure the quality of fruits and beef is not affected.

[0166] Step S520, calculating the resource gap amounts of each level of nodes according to the real-time demand prediction results.

[0167] In the cold chain transportation of fruits and beef, through the analysis of various data such as market demand, production, and transportation plans, the resource requirements of each level of nodes are predicted in real time. Taking beef transportation as an example, the storage center of a beef processing enterprise is a core node. According to historical order data and market trend forecasts, during the upcoming holiday period, it is expected that 1,000 kg of beef needs to be stored and transported every day. However, the maximum storage capacity of the current storage center is 800 kg, and the transportation capacity of the transport vehicles can only meet the transportation of 800 kg per day. Then, the resource gap at the core node is 200 kg in terms of storage and 200 kg in terms of transportation.

[0168] For edge nodes, such as small transfer stations, it is predicted that 50 boxes of fruits need to be transferred every day within a certain time period, but the actual transfer capacity is only 40 boxes, and the resource gap is 10 boxes. In this way, the resource gaps of each level of nodes are accurately calculated, providing a basis for resource allocation.

[0169] Step S530, when the resource gap of the core node among each level of nodes exceeds the first threshold, start the cross-regional cold storage resource allocation process.

[0170] Suppose the first threshold is set at 20% of the total resources of the core node. In fruit transportation, a large fruit consolidation center is a core node. During the fruit peak season, the storage resource gap of this center reaches 30%, exceeding the first threshold. At this time, start the cross-regional cold storage resource allocation process. If there is idle storage space in other cold storages in the surrounding areas, the excess fruits in this region can be allocated to these cold storages for storage. For example, due to insufficient storage space for bananas in the local consolidation center, some bananas can be transported to a cold storage in the adjacent region. The cold storage is 100 km away from the local consolidation center. During the transportation process, it is necessary to ensure that the cold chain transportation conditions meet the temperature requirements of bananas, and at the same time, coordinate the transportation plan and cost to avoid adverse effects on the quality and transportation efficiency of bananas.

[0171] Step S540, when the resource gap of the edge node among each level of nodes exceeds the second threshold, trigger the deployment plan of mobile temporary cold chain equipment.

[0172] Suppose the second threshold is set at 30% of the total resources of the edge node. In beef transportation, a small transfer station is an edge node. During a certain period, due to a sudden increase in transportation demand, the capacity gap of its transport vehicles reaches 40%, exceeding the second threshold. At this time, trigger the deployment plan of mobile temporary cold chain equipment. Mobile refrigerated trucks can be allocated to this transfer station to increase the transfer station's transportation capacity. These mobile refrigerated trucks have independent refrigeration systems and a certain amount of storage space, and can supplement the insufficient transportation capacity of the transfer station in a short time to ensure that the beef can be transported to the next node in a timely and safe manner.

[0173] Step S550: Real-time feedback the resource allocation result to the spatio-temporal prediction model to construct a closed-loop optimization system for demand prediction and resource allocation.

[0174] During the cold chain transportation of fruits and beef, after the cross-regional cold storage resource allocation or the deployment of mobile temporary cold chain equipment is completed, the resource allocation result is real-time feedback to the spatio-temporal prediction model. For example, data such as how many bananas are allocated from the local collection center to the adjacent regional cold storage, the working hours and transportation volume of the mobile refrigerated truck at the transfer station are feedback to the spatio-temporal prediction model. The spatio-temporal prediction model adjusts the future demand prediction based on these feedback data. If it is found that after the resource allocation, the cold chain transportation pressure in a certain area is relieved, and there are new changes in the transportation demand in another area, the resource allocation strategy can be readjusted. In this way, a closed-loop optimization system for demand prediction and resource allocation is constructed, continuously improving the efficiency and reliability of the cold chain transportation of fruits and beef.

[0175] Figure 2 Fig. shows a cold chain logistics service system 100 provided in an embodiment of the present application, including a processor 1001, a memory 1003, and program code stored on the memory 1003. The processor 1001 executes the above program code to implement the steps of the cold chain transportation demand analysis method based on big data prediction.

[0176] Figure 2 Fig. shows a cold chain logistics service system 100 provided in an embodiment of the present application, including a processor 1001, a memory 1003, and program code stored on the memory 1003. The processor 1001 executes the above program code to implement the steps of the cold chain transportation path optimization method based on AI prediction.

[0177] Figure 2 The shown cold chain logistics service system 100 includes: a processor 1001 and a memory 1003. Among them, the processor 1001 and the memory 1003 are connected, such as connected through a bus 1002. Optionally, the cold chain logistics service system 100 may further include a transceiver 1004, and the transceiver 1004 can be used for data interaction between this cold chain logistics service system and other cold chain logistics service systems, such as data sending and / or data receiving, etc. It should be noted that in actual scheduling, the transceiver 1004 is not limited to one, and the structure of this cold chain logistics service system 100 does not constitute a limitation to the embodiments of the present application.

[0178] The processor 1001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in connection with the disclosure of this application. The processor 1001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0179] The bus 1002 may include a path for transmitting information between the above components. The bus 1002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 1002 may be divided into an address bus, a data bus, a control bus, etc.

[0180] The memory 1003 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or may also be an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium that can be used to have or store program code and can be read by a computer, which is not limited herein.

[0181] The memory 1003 is used to store the program code for implementing the embodiments of this application and is controlled by the processor 1001 for execution. The processor 1001 is used to execute the program code stored in the memory 1003 to implement the steps shown in the foregoing method embodiments.

[0182] An embodiment of the present application provides a computer-readable storage medium, on which program code is stored. When the program code is executed by a processor, the steps and corresponding contents of the foregoing method embodiment can be implemented.

[0183] It should be understood that although the flowchart of the embodiment of the present application indicates each operation step by an arrow, the execution order of these steps is not limited to the order indicated by the arrow. Unless there is a clear description in this article, in some implementation scenarios of the embodiment of the present application, the implementation steps in each flowchart can be executed in other orders based on requirements. In addition, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages according to the actual implementation scenario. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage in these sub-steps or stages can also be executed at different times. In the scenario where the execution times are different, the execution order of these sub-steps or stages can be flexibly configured according to requirements, and the embodiment of the present application does not limit this.

[0184] The above are only optional implementation manners of some implementation scenarios of the present application. It should be noted that for those of ordinary skill in the art, without departing from the technical concept of the solution of the present application, using other similar implementation means based on the technical idea of the present application also belongs to the protection scope of the embodiment of the present application.

Claims

1. A cold chain transportation demand analysis method based on big data prediction, characterized in that, The method includes: Obtaining a historical cold chain order data set of a target area, where the historical cold chain order data set contains transportation records of temperature-sensitive goods and their corresponding environmental parameters for multiple time periods; Extracting a set of transportation demand features from the historical cold chain order data, where the set of transportation demand features includes the association feature between the type of goods and temperature sensitivity, the balance feature between transportation timeliness and equipment energy consumption, and the matching feature between regional climate and warehousing conditions; Inputting the set of transportation demand features into a pre-trained spatio-temporal prediction model to generate multi-dimensional cold chain demand parameters for the target area within a specified future period, where the multi-dimensional cold chain demand parameters include a temperature fluctuation tolerance threshold, a transportation timeliness critical value, and a path node load factor; Generating a timestamped dynamic cold chain transportation scheduling plan based on the multi-dimensional cold chain demand parameters; The step of generating a timestamped dynamic cold chain transportation scheduling plan based on the multi-dimensional cold chain demand parameters includes Optimizing and generating a cold chain transportation path topology based on the multi-dimensional cold chain demand parameters, where each transportation node in the cold chain transportation path topology is associated with a dynamic resource allocation weight, and the dynamic resource allocation weight is negatively correlated with the historical failure rate, real-time temperature control ability, and adjacent node connection efficiency of the corresponding node; According to the real-time operation status data of each node in the cold chain transportation path topology, dynamically adjusting the matching relationship between the transportation timeliness critical value and the temperature fluctuation tolerance threshold to generate a set of abnormal event response strategies, where the set of abnormal event response strategies includes standby refrigeration equipment activation conditions, path switching priority rules, and emergency warehousing capacity allocation plans; Performing spatio-temporal alignment processing on the set of abnormal event response strategies and the real-time meteorological data stream to generate a timestamped dynamic cold chain transportation scheduling plan, where the dynamic cold chain transportation scheduling plan includes an equipment pre-start time window, a transportation batch interval threshold, and a cross-regional collaborative transportation trigger condition.

2. The cold chain transportation demand analysis method based on big data prediction according to claim 1, characterized in that The step of extracting the set of transportation demand features from the historical cold chain order data includes: Identifying the correspondence between the goods category code and the temperature monitoring curve in the historical cold chain order data to generate a temperature sensitivity distribution map; Analyzing the association pattern between transportation timeliness records and refrigeration equipment energy consumption logs to establish a timeliness-energy consumption balance coefficient matrix; Detecting the matching degree between regional climate data and warehousing temperature maintenance ability and calculating a climate adaptability index; Fusing the temperature sensitivity distribution map, the timeliness-energy consumption balance coefficient matrix, and the climate adaptability index to generate a three-dimensional feature vector space as the set of transportation demand features; Among them, the training steps of the spatio-temporal prediction model include: Dividing the three-dimensional feature vector space into a training set and a validation set, and annotating corresponding time series labels for the training set and the validation set; Constructing a deep spatio-temporal convolutional network, where the deep spatio-temporal convolutional network includes a climate fluctuation perception layer, a transportation path dependence layer, and an equipment state memory unit; Optimize the network parameters of the deep spatio-temporal convolutional network through the backpropagation algorithm to minimize the spatio-temporal correlation loss function between the predicted output of the deep spatio-temporal convolutional network and the true demand parameters of the validation set; When the change rate of the loss value for N consecutive training epochs is lower than the preset threshold, freeze the network parameters of the deep spatio-temporal convolutional network and export the model weights.

3. The cold chain transportation demand analysis method based on big data prediction according to claim 1, characterized in that, The step of optimizing and generating the cold chain transportation path topology based on the multi-dimensional cold chain demand parameters includes: Calculate the bearing margin value of each transportation section according to the load coefficient of the path node; Construct a topological relationship graph between transportation nodes based on a graph neural network, where the edge weights in the topological relationship graph are determined by the product of the bearing margin value and the transportation timeliness; Use the dynamic programming algorithm to search for the optimal path set that meets the temperature fluctuation tolerance threshold in the topological relationship graph; Perform Monte Carlo simulation on each optimal path in the optimal path set, and select the optimal path with a failure risk lower than the preset threshold as the main transportation channel; And, the step of dynamically adjusting the matching relationship between the transportation timeliness critical value and the temperature fluctuation tolerance threshold according to the real-time operation status data of each node in the cold chain transportation path topology to generate a set of abnormal event response strategies includes: Real-time collect the in-cabin temperature data stream of the transportation vehicle and the external environment sensor data; Calculate the deviation degree between the actual temperature fluctuation value of the current transportation section and the predicted tolerance threshold; When the deviation degree exceeds the first critical value, activate the standby refrigeration equipment and recalculate the transportation timeliness compensation coefficient; When the deviation degree exceeds the second critical value, trigger the path switching mechanism and update the emergency warehouse allocation priority.

4. The cold chain transportation demand analysis method based on big data prediction according to claim 1, characterized in that The step of performing spatio-temporal alignment processing on the set of abnormal event response strategies and the real-time meteorological data stream to generate a cold chain transportation dynamic scheduling plan with timestamps includes: Perform spatial matching between the meteorological prediction data and the node geographical locations in the path topology; Identify the extreme weather areas that may affect the transportation path within a preset future time period; Sort the priorities of all in-transit transportation tasks for the affected path segments, and the basis for the priority sorting includes the cargo spoilage rate, remaining transportation time, and alternative path availability; Generate a time-sliced transportation resource reallocation instruction set, and the transportation resource reallocation instruction set specifies the speed adjustment strategy and the refrigeration power adjustment range of each cold chain vehicle within each time window.

5. The cold chain transportation demand analysis method based on big data prediction according to claim 1, wherein The method further includes: Divide the target area into multiple cold chain demand sub-areas based on the historical order distribution density; Establish an independent demand fluctuation baseline for each cold chain demand sub-area, and the demand fluctuation baseline includes the daily minimum transportation volume, typical cargo composition ratio, and peak period characteristics; When the deviation degree between the real-time monitored sub-area order flow and the demand fluctuation baseline exceeds the preset threshold, trigger the inter-regional transport capacity balance mechanism; The transport capacity balance mechanism includes the cold storage resource sharing protocol for adjacent sub-areas, the dynamic scheduling rules for cross-regional transport vehicles, and the temporary storage facility activation strategy.

6. The cold chain transportation demand analysis method based on big data prediction according to claim 5, characterized in that The method further includes: Calculate the transportation time correlation matrix among demand fluctuation sub-regions, where the matrix elements of the transportation time correlation matrix represent the maximum allowable transportation time that meets the temperature requirements between two demand fluctuation sub-regions; Update the time parameters in the transportation time correlation matrix according to the real-time traffic flow data; When the actual transportation time between any two demand fluctuation sub-regions exceeds the corresponding value in the transportation time correlation matrix, generate a detour path suggestion and evaluate the additional energy consumption cost; Compare the detour path suggestion with the economic priority of the current transportation task through weighted comparison, and select the path adjustment plan with the optimal cost-benefit; 7. The cold chain transportation demand analysis method based on big data prediction according to claim 1, wherein The method further includes: Establish a full-life cycle performance degradation model for cold chain transportation equipment, where the full-life cycle performance degradation model includes a compressor working efficiency curve, a thermal insulation material aging coefficient, and a battery capacity decay function; Predict the maintainable time window of each transport vehicle according to the real-time equipment monitoring data; Embed a preventive maintenance plan in the dynamic scheduling plan, and the preventive maintenance plan specifies the priority maintenance period of each vehicle and the alternative vehicle scheduling plan; When the predicted value of the equipment failure probability exceeds the safety threshold, execute the maintenance plan in advance and recalculate the transportation path topology; 8. The cold chain transportation demand analysis method based on big data prediction according to claim 1, characterized in that The method further includes: Construct a multi-level cold chain resource allocation strategy, where the multi-level cold chain resource allocation strategy includes a core node resource reservation mechanism and an edge node dynamic sharing mechanism; Calculate the resource gap of each level of nodes according to the real-time demand prediction result; When the resource gap of the core nodes in each level of nodes exceeds the first threshold, initiate a cross-regional cold storage resource allocation process; When the resource gap of the edge nodes in each level of nodes exceeds the second threshold, trigger a mobile temporary cold chain equipment deployment plan; Feed the resource allocation result back to the spatio-temporal prediction model in real time to construct a closed-loop optimization system for demand prediction and resource allocation; 9. A cold chain logistics service system, characterized in that, It includes a processor and a computer-readable storage medium, and the computer-readable storage medium stores machine-executable instructions, and when the machine-executable instructions are executed by the processor, the cold chain transportation demand analysis method based on big data prediction according to any one of claims 1-8 is implemented.

Images