Cross-border logistics cargo source intelligent matching method and system

Abstract

The present application relates to the technical field of logistics management, and more particularly to a cross-border logistics cargo source intelligent matching method and system, the steps of the method comprising: obtaining cargo attribute data of a to-be-transported cargo source and corresponding packaging material attribute data, obtaining transportation environment data of a planned route, and obtaining cargo quality requirement data; based on the packaging material attribute data and in combination with the transportation environment data of the planned route, analyzing performance degradation of the packaging material in the transportation process and determining packaging protection failure risk under the influence of timing environment; based on the cargo attribute data, analyzing cargo co-loading compatibility and in combination with the packaging protection failure risk, predicting cargo arrival quality state; and based on the cargo arrival quality state prediction result and in combination with the cargo quality requirement data, performing cargo source matching and outputting a cargo source matching result. The present application quantifies packaging protection performance under the influence of timing environment and cargo co-loading compatibility, effectively improving the accuracy and reliability of cargo source matching.

Description

Technical Field

[0001] This invention relates to the field of logistics management technology, and in particular to a method and system for intelligent matching of cross-border logistics cargo sources. Background Technology

[0002] With the rapid development of global trade, the demand for cross-border logistics and transportation is increasing, and long-distance maritime transport has become the main mode of cross-border circulation of bulk goods. During ship transportation, cargo must undergo a long transportation cycle and complex and variable environmental conditions, such as temperature and humidity fluctuations, sea salt spray corrosion, wind and wave impact, and loading and unloading vibrations. These environmental factors can cause varying degrees of damage to the cargo and its packaging materials, thus affecting the overall quality of the cargo upon arrival at the port. For perishable, fragile, or high-value-added goods, the risk of damage during transportation is particularly prominent, directly affecting the performance of transactions and economic losses for both the supplier and the buyer.

[0003] Packaging materials play a crucial protective role during maritime transport, but traditional logistics management systems typically focus only on the properties of the goods themselves, neglecting the performance degradation patterns of packaging materials and their adaptability to the transportation environment. Current technologies, when assessing the protective performance of packaging materials, generally treat the effects of different transportation environmental factors as additive or linear superposition effects, assuming that the cumulative damage from environmental risks such as high temperature and humidity, vibration and impact, and salt spray corrosion is independent of their order of occurrence. However, in actual transportation, the fatigue and aging of packaging materials is often a non-linear process related to historical data. Current technologies ignore the non-linear impact of the temporal differences in environmental effects on packaging failure, leading to significant discrepancies between damage predictions and actual conditions.

[0004] Meanwhile, in the process of cross-border logistics and transportation, the same ship often carries multiple different types of goods, and there are interactions between different goods. For example, there is a risk of cross-contamination when chemicals and food are carried together, and there is a risk of coordinated damage due to vibration transmission when large machinery and fragile goods are carried together. The existing cargo matching method ignores the risks of group coordination and is difficult to fully reflect the complex risks in the actual transportation scenario.

[0005] In summary, existing cross-border logistics cargo matching methods lack comprehensive consideration of dynamic changes in the transportation environment, the degradation of packaging protection performance, and the compatibility of cargo sharing, making it difficult to accurately assess the true quality status of cargo upon arrival at the port, resulting in discrepancies between the cargo matching results and actual needs. Therefore, this invention proposes a novel intelligent cross-border logistics cargo matching method to achieve comprehensive prediction based on the transportation environment, packaging performance, and cargo group effects, thereby improving the accuracy and reliability of cargo matching. Summary of the Invention

[0006] To overcome the defects and shortcomings of existing technologies, this invention provides a cross-border logistics cargo intelligent matching method and system. By quantifying the packaging protection performance and cargo co-loading compatibility under the influence of time-series environment, it improves the prediction accuracy of cargo arrival quality status, effectively enhancing the scientific nature and practicality of intelligent cargo matching.

[0007] To achieve the above objectives, the present invention adopts the following technical solution:

[0008] In a first aspect, the present invention provides a method for intelligent matching of cross-border logistics cargo sources, comprising:

[0009] Obtain cargo attribute data and corresponding packaging material attribute data of the goods to be transported, obtain transportation environment data of the planned route, and obtain cargo quality requirement data;

[0010] Based on packaging material property data and combined with transportation environment data of planned routes, we analyze the performance degradation of packaging materials during transportation and determine the risk of packaging protection failure under the influence of time-series environment.

[0011] Based on cargo attribute data analysis, the compatibility of cargo co-loading is analyzed, and combined with the risk of packaging protection failure, the quality status of cargo arriving at the port is predicted.

[0012] Based on the predicted quality status of cargo arriving at the port and combined with cargo quality demand data, cargo matching is performed and the cargo matching results are output.

[0013] Furthermore, the determination of the packaging protection failure risk under the influence of temporal environmental factors includes:

[0014] The planned route is divided into continuous transport segments, and environmental feature sequences of each transport segment are extracted based on transport environment data.

[0015] A dynamic model of performance degradation of packaging materials was constructed, and the basic damage factor of packaging for each transportation segment was determined by combining the environmental characteristic sequence.

[0016] Determine the temporal environmental coupling damage increment factor between adjacent transport segments based on the environmental feature sequence of adjacent transport segments;

[0017] The total damage factor is obtained by summing the basic packaging damage factor and the temporal environmental coupled damage increment factor for each transport segment. And determine the remaining protective strength of the packaging. ,in, The initial protective strength of the packaging material;

[0018] Based on the remaining protective strength of the packaging Compared with the preset packaging protection strength threshold The difference is used to perform a logistic mapping to obtain the packaging protection failure risk coefficient:

[0019] ;

[0020] in, This is the steepness coefficient of the logistic mapping, used to adjust the sensitivity of the risk curve. The larger the steepness coefficient, the more sensitive the risk of packaging protection failure is to the decrease in the remaining protective strength of the packaging. This is the bias term for the logistic mapping, used to correct for baseline risk of packaging protection failure.

[0021] Furthermore, determining the temporal environmental coupling damage increment factor between adjacent transport segments includes:

[0022] Get the Packaging basic damage factor for each transport segment And determine the first The first transport segment and the first Environmental coupling effect function of each transport segment To reflect the impact of continuous environmental conditions on the damage resistance of packaging materials;

[0023] Determining the time-series environmental coupling damage increment factor based on the cumulative damage factor and the environmental coupling effect function: ,in, The time-series environment coupling sensitivity coefficient, This represents the historical damage weighting coefficient.

[0024] Furthermore, the analysis of cargo co-cargo compatibility includes:

[0025] Based on cargo attribute data, physical, chemical and biological risk attributes of cargo are extracted and normalized risk feature vectors are generated.

[0026] The risk attribute similarity between any two goods is determined based on the risk feature vector, wherein the risk attribute similarity is determined by the cosine similarity of the risk feature vectors.

[0027] The ratio of the risk attribute similarity between any two goods to the mean risk attribute similarity among all goods is used as the cargo co-loading compatibility coefficient.

[0028] Furthermore, the predicted quality status of the cargo upon arrival at the port includes:

[0029] Determine the synergistic risk coefficient between any two goods based on the cargo co-cargo compatibility coefficient and the packaging protection failure risk coefficient: ,in, For goods The risk factor of packaging protection failure, For goods The risk factor of packaging protection failure, For goods With goods The compatibility coefficient of cargo co-loading between them;

[0030] The average of the collaborative risk coefficients among all goods is taken as the group collaborative risk coefficient of the cargo source, reflecting the damage risk of different goods when they are co-loaded;

[0031] A cargo arrival quality status prediction model is constructed based on the group collaborative risk coefficient, which analyzes the quality status of the cargo upon arrival and outputs the corresponding cargo arrival quality status prediction results.

[0032] Furthermore, the step of performing source matching and outputting source matching results includes:

[0033] The predicted quality status of cargo arriving at the port is quantified into a quality parameter vector, and the cargo quality demand data is transformed into a demand threshold vector.

[0034] Compare the quality parameter vector with the demand threshold vector and calculate the satisfaction level of each quality parameter;

[0035] The matching degree of the goods is obtained by weighted fusion based on the satisfaction of each quality parameter, and the goods corresponding to the maximum matching degree are output as the goods matching result.

[0036] Secondly, the present invention provides a cross-border logistics cargo intelligent matching system, comprising:

[0037] The data acquisition module is used to acquire cargo attribute data and corresponding packaging material attribute data of the cargo to be transported, acquire transportation environment data of the planned route, and acquire cargo quality requirement data.

[0038] The packaging protection analysis module is used to analyze the performance degradation of packaging materials during transportation and determine the risk of packaging protection failure under the influence of time-series environmental factors, based on packaging material property data and transportation environment data of planned routes.

[0039] The cargo quality prediction module is used to analyze the compatibility of cargo co-loading based on cargo attribute data and predict the quality status of cargo upon arrival at the port by combining the risk of packaging protection failure.

[0040] The cargo matching output module is used to match cargo sources based on the predicted quality status of cargo arrival at the port and the cargo quality demand data, and then output the cargo matching results.

[0041] Thirdly, the present invention provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes a cross-border logistics cargo intelligent matching method by calling the computer program stored in the memory.

[0042] Fourthly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform a cross-border logistics cargo intelligent matching method.

[0043] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0044] This invention overcomes the shortcomings of existing technologies that simply linearly superimpose different environmental risks by comprehensively considering multiple dimensions such as cargo attributes, packaging material performance degradation, and dynamic changes in the transportation environment. This makes the prediction results of packaging protection failure risk and cargo damage more consistent with reality. At the same time, the introduction of cargo co-cargo compatibility analysis and group collaborative risk assessment can accurately reflect the mutual influence between cargoes on the same ship, thereby achieving higher accuracy and reliability in the process of matching cargo sources and demand. This can effectively reduce the risk of cargo damage and transaction disputes in cross-border logistics. Attached Figure Description

[0045] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0046] Figure 1 This is a flowchart illustrating an intelligent matching method for cross-border logistics cargo sources provided in an embodiment of the present invention;

[0047] Figure 2 This is a schematic diagram of the structure of a cross-border logistics cargo intelligent matching system provided in an embodiment of the present invention;

[0048] Figure 3 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0049] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations thereof. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0050] Please see Figure 1 , Figure 1 This is a schematic diagram of the overall process of a cross-border logistics cargo intelligent matching method provided by an embodiment of the present invention, which specifically includes the following steps:

[0051] S100. Obtain cargo attribute data and corresponding packaging material attribute data for the goods to be transported, obtain transportation environment data for the planned route, and obtain cargo quality requirement data. The cargo attribute data and corresponding packaging material attribute data can be obtained through the logistics company's cargo management system, packaging testing database, and cargo instructions provided by the cargo owner. Cargo attribute data includes the cargo's weight, volume, shape, chemical stability, and humidity and heat sensitivity parameters. Packaging material attribute data includes the packaging material's compressive strength, moisture resistance, vibration resistance, and fatigue life parameters. The transportation environment data for the planned route can be obtained through route environment forecast information provided by the shipping company, historical meteorological databases, and real-time marine monitoring systems, including temperature, humidity, and salt spray concentration parameters for the transportation segment. The cargo quality requirement data is explicitly provided by the consignee in the order requirements, including permissible visual damage thresholds and chemical or biological property stability requirements.

[0052] S200. Based on the packaging material property data and combined with the transportation environment data of the planned route, analyze the performance degradation of packaging materials during transportation and determine the risk of packaging protection failure under the influence of time-series environment.

[0053] During cross-border maritime transport, the performance degradation of packaging materials depends not only on the intensity of a single environmental stress but also closely on the sequence of these stresses. For example, for goods packaged in cardboard boxes: if the goods are subjected to high temperature and humidity environments continuously during the initial stages of transport, the cardboard fiber material will soften due to moisture absorption and become brittle due to thermal stress, resulting in a significant decrease in its compressive strength. When the goods subsequently enter seas with rough seas and experience strong vibrations and impacts, the cardboard boxes, already in a low-strength state, are highly susceptible to collapse or damage, significantly increasing the risk of protective failure. Conversely, if the goods are subjected to vibrations and impacts during the initial stages of transport, although this will cause some structural fatigue in the cardboard boxes, their moisture resistance has not yet been weakened. When subsequently subjected to high temperature and humidity environments, the overall strength of the cardboard boxes decreases relatively slowly, and the cumulative damage is significantly less than in the former sequence. This demonstrates that the same combination of environmental factors, under different time sequences, can lead to drastically different packaging protection results. Similarly, for wooden packaging boxes, if they are first subjected to prolonged high humidity environments, the wood content... Increased moisture content leads to expansion and decreased structural strength. Subsequent exposure to high-intensity vibration and impact makes the enclosure more prone to cracking at joints, rapidly increasing the risk of failure. Conversely, if the sequence is reversed—vibration followed by moisture—while damage still occurs, the conditions for crack propagation are not yet established, resulting in more stable overall protection. Therefore, calculating the failure risk of packaging protection cannot rely solely on the individual intensity of various environmental factors. It must combine the sequence of environmental characteristics and their duration, utilizing a performance degradation kinetic model to capture the historical correlation between material fatigue and aging. This allows for a scientific prediction of packaging protection failure risk, determining the failure risk under the influence of temporal environmental factors, including:

[0054] The planned route is divided into continuous transport segments, and environmental feature sequences of each transport segment are extracted based on transport environment data.

[0055] A dynamic model of packaging material performance degradation is constructed, and the basic damage factor of packaging for each transport segment is determined by combining environmental feature sequences. During maritime transport, the performance degradation of packaging materials is coupled with environmental factors such as temperature, humidity, vibration, and salt spray. Therefore, it is necessary to construct a dynamic model of packaging material performance degradation based on the theory of materials mechanics and environmental fatigue. The dynamic model of performance degradation takes the key performance parameters of packaging materials (such as compressive strength, moisture resistance, vibration resistance, and fatigue life parameters) as state variables, and fits their degradation law under a single environmental stress through experiments or historical data. For example, the strength under high temperature conditions decreases exponentially with time, the stiffness under humidity conditions decreases linearly with time, and the fatigue life under vibration conditions decreases power-law with the number of cycles. At the same time, the environmental feature sequences extracted from each transport segment in the planned route are used as input parameters and substituted into the dynamic model of performance degradation to calculate the performance degradation rate of packaging materials under the corresponding environmental conditions of the transport segment. Based on this, the basic damage factor of packaging for that transport segment is obtained, which is used to reflect the degree of performance damage of packaging materials under the independent action of a single transport segment.

[0056] Determine the temporal environmental coupling damage increment factor between adjacent transport segments based on the environmental feature sequence of adjacent transport segments;

[0057] The total damage factor is obtained by summing the basic packaging damage factor and the temporal environmental coupled damage increment factor for each transport segment. And determine the remaining protective strength of the packaging. ,in, The initial protective strength of packaging materials represents the baseline strength of packaging materials when they are not subjected to environmental forces. The total damage factor has a range of values. This indicates the cumulative damage to the packaging throughout the entire shipping journey. This indicates the remaining integrity of the packaging material. The protective strength of the packaging material after transportation is obtained by multiplying its initial protective strength by its remaining integrity.

[0058] Based on the remaining protective strength of the packaging Compared with the preset packaging protection strength threshold The difference is used to perform a logistic mapping to obtain the packaging protection failure risk coefficient:

[0059] ;

[0060] in, This is the steepness coefficient of the logistic mapping, used to adjust the sensitivity of the risk curve. The larger the steepness coefficient, the more sensitive the risk of packaging protection failure is to the decrease in the remaining protective strength of the packaging. This represents the ratio of the remaining protective strength of the packaging to the preset protective strength threshold of the packaging. This indicates the percentage of protection gap. A positive number means the remaining protection strength of the packaging is below the threshold, posing a risk of protection failure. A negative number means the remaining protection strength of the packaging is above the threshold, posing a lower risk of protection failure. This is the bias term of the logistic mapping, used to adjust the baseline level of the risk curve. Since the risk coefficient of packaging protection failure is essentially a probability quantity between 0 and 1, the logistic mapping can limit the mapping result to within a certain range. The range, and at the same time, the Logistic mapping can reflect the characteristic that small differences lead to large risk changes near the threshold, which is consistent with the characteristics of packaging failure;

[0061] Determine the temporal environmental coupling damage increment factor between adjacent transport segments, including:

[0062] Get the Packaging basic damage factor for each transport segment And determine the first The first transport segment and the first Environmental coupling effect function of each transport segment ,in, , and The first The first transport segment and the first The first of the transport segments Class environment parameter values, The number of environmental parameters, For the first The weighting coefficients of environmental parameters reflect their sensitivity to damage to packaging materials. For the first Nonlinear sensitivity index of environmental parameters is used to reflect the nonlinear response of materials to continuous environmental changes. This indicates the magnitude of environmental changes along a continuous transport segment;

[0063] Determining the time-series environmental coupling damage increment factor based on the cumulative damage factor and the environmental coupling effect function: ,in, The temporal-environment coupling sensitivity coefficient describes the amplification ratio of material vulnerability to different environmental interactions. The larger the temporal-environment coupling sensitivity coefficient, the more sensitive the packaging material is to changes in the temporal environment. The historical damage weighting coefficient reflects the amplification effect of existing damage on the temporal environment coupling effect.

[0064] S300: Analyze cargo co-loading compatibility based on cargo attribute data and predict the quality status of cargo upon arrival at the port by combining packaging protection failure risk;

[0065] In cross-border shipping, the physical, chemical, and biological properties of different goods interact. For example, when a batch of metal materials is transported together with chemicals, if the packaging protection fails, acid leakage will directly corrode the metal materials, resulting in a decline in cargo quality. In this case, the co-cargo compatibility coefficient of the metal materials is low, and the predicted quality status upon arrival at the port often indicates a high risk of damage. Analyzing cargo co-cargo compatibility includes:

[0066] Based on cargo attribute data, physical, chemical and biological risk attributes of cargo are extracted and normalized risk feature vectors are generated.

[0067] The risk attribute similarity between any two goods is determined based on the risk feature vector, wherein the risk attribute similarity is determined by the cosine similarity of the risk feature vectors.

[0068] The ratio of the risk attribute similarity between any two goods to the mean risk attribute similarity among all goods is used as the cargo co-loading compatibility coefficient.

[0069] Predicting the quality status of goods upon arrival at port, including:

[0070] Determine the synergistic risk coefficient between any two goods based on the cargo co-cargo compatibility coefficient and the packaging protection failure risk coefficient: ,in, For goods The risk factor of packaging protection failure, For goods The risk factor of packaging protection failure, For goods With goods The compatibility coefficient of cargo co-loading between them;

[0071] The average of the collaborative risk coefficients among all goods is taken as the group collaborative risk coefficient of the cargo source, reflecting the damage risk of different goods when they are co-loaded;

[0072] A cargo arrival quality status prediction model is constructed based on the group collaborative risk coefficient. This model analyzes the quality status of cargo upon arrival and outputs corresponding prediction results. The model can utilize various existing modeling methods, including empirical formula models, statistical regression models, and machine learning models, or combine these methods to form a hybrid model. Specifically, the group collaborative risk coefficient can be used as the main input feature. Combined with the physical properties, packaging performance parameters, and transportation environment characteristics of each cargo, the model calculates the cumulative damage that cargo may suffer upon arrival using empirical formula models, statistical regression models, or machine learning models. This outputs the cargo arrival quality status and the overall quality evaluation of the entire cargo batch. The prediction results reflect the potential damage and quality changes of cargo under the influence of group collaborative risk during transportation, providing a scientific basis for subsequent cargo matching.

[0073] S400: Based on the predicted quality status of cargo arriving at the port and combined with cargo quality demand data, perform cargo matching and output cargo matching results.

[0074] By matching cargo sources based on their arrival quality status, it is possible to scientifically predict potential damage and quality changes during transportation. The prediction results are quantified into a quality parameter vector and precisely compared with the cargo source quality requirements. This allows for the calculation of the satisfaction level of each quality parameter, followed by weighted fusion to obtain a comprehensive cargo source matching degree. This reduces the risk of cargo failing to meet requirements due to damage during transportation. The cargo source matching process outputs the matching results, including:

[0075] The predicted quality status of cargo arriving at the port is quantified into a quality parameter vector, and the cargo quality demand data is transformed into a demand threshold vector.

[0076] Compare the quality parameter vector with the demand threshold vector and calculate the satisfaction level of each quality parameter. The satisfaction level of each quality parameter can be obtained by the proportional mapping method or the difference mapping method.

[0077] The matching degree of the goods is obtained by weighted fusion based on the satisfaction of each quality parameter, and the goods corresponding to the maximum matching degree are output as the goods matching result.

[0078] In this embodiment of the invention, the determination of parameters such as weighted values ​​and preset packaging protection strength thresholds can be achieved by: constructing a dataset by acquiring cargo attribute data, packaging material attribute data, transportation environment data, and cargo quality demand data; substituting these data into the dataset to calculate the packaging protection failure risk coefficient and cargo matching degree; simultaneously obtaining expert judgment results on the packaging protection failure risk and cargo matching degree; importing the calculated packaging protection failure risk coefficient, cargo matching degree, and judgment results into fitting software; and outputting the weighted values ​​that meet the maximum judgment accuracy and the preset packaging protection strength threshold.

[0079] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of a cross-border logistics cargo intelligent matching system provided in an embodiment of the present invention, including:

[0080] The data acquisition module 210 is used to acquire cargo attribute data and corresponding packaging material attribute data of the cargo to be transported, acquire transportation environment data of the planned route, and acquire cargo quality requirement data.

[0081] The packaging protection analysis module 220 is used to analyze the performance degradation of packaging materials during transportation and determine the risk of packaging protection failure under the influence of time-series environmental factors, based on packaging material property data and combined with transportation environment data of the planned route.

[0082] Cargo quality prediction module 230 is used to analyze the compatibility of cargo co-loading based on cargo attribute data and predict the quality status of cargo upon arrival at the port by combining the risk of packaging protection failure.

[0083] The cargo matching output module 240 is used to match cargo based on the predicted cargo arrival quality status and cargo quality demand data, and output the cargo matching results.

[0084] In this embodiment of the invention, the packaging protection analysis module 220 is used to analyze the performance degradation of packaging materials during transportation and determine the risk of packaging protection failure under the influence of time-series environmental factors, based on packaging material property data and combined with transportation environment data of the planned route, including:

[0085] The planned route is divided into continuous transport segments, and environmental feature sequences of each transport segment are extracted based on transport environment data.

[0086] A dynamic model of performance degradation of packaging materials was constructed, and the basic damage factor of packaging for each transportation segment was determined by combining the environmental characteristic sequence.

[0087] Determine the temporal environmental coupling damage increment factor between adjacent transport segments based on the environmental feature sequence of adjacent transport segments;

[0088] The total damage factor is obtained by summing the basic damage factor of the packaging for each transport segment and the temporal environmental coupled damage increment factor, and the remaining protection strength of the packaging is determined.

[0089] The packaging protection failure risk coefficient is obtained by performing a logistic mapping based on the difference between the remaining packaging protection strength and the preset packaging protection strength threshold.

[0090] Determine the temporal environmental coupling damage increment factor between adjacent transport segments, including:

[0091] Get the The basic damage factor of packaging for each transport segment was determined. The first transport segment and the first An environmental coupling effect function for each transport segment is used to reflect the impact of continuous environmental conditions on the damage resistance of packaging materials.

[0092] The temporal environmental coupling damage increment factor is determined based on the cumulative damage factor and the environmental coupling effect function.

[0093] In this embodiment of the invention, the cargo quality prediction module 230 is used to analyze cargo co-loading compatibility based on cargo attribute data and predict the cargo arrival quality status by combining the risk of packaging protection failure, including:

[0094] Based on cargo attribute data, physical, chemical and biological risk attributes of cargo are extracted and normalized risk feature vectors are generated.

[0095] The risk attribute similarity between any two goods is determined based on the risk feature vector, wherein the risk attribute similarity is determined by the cosine similarity of the risk feature vectors.

[0096] The ratio of the risk attribute similarity between any two goods to the mean risk attribute similarity among all goods is used as the cargo co-loading compatibility coefficient.

[0097] Predicting the quality status of goods upon arrival at port, including:

[0098] The collaborative risk coefficient between any two goods is determined based on the cargo co-carrying compatibility coefficient and the packaging protection failure risk coefficient.

[0099] The average of the collaborative risk coefficients among all goods is taken as the group collaborative risk coefficient of the cargo source, reflecting the damage risk of different goods when they are co-loaded;

[0100] A cargo arrival quality status prediction model is constructed based on the group collaborative risk coefficient, which analyzes the quality status of the cargo upon arrival and outputs the corresponding cargo arrival quality status prediction results.

[0101] In this embodiment of the invention, the cargo matching output module 240 is used to perform cargo matching based on the cargo arrival quality status prediction result and combined with cargo quality demand data, and output the cargo matching result, including:

[0102] The predicted quality status of cargo arriving at the port is quantified into a quality parameter vector, and the cargo quality demand data is transformed into a demand threshold vector.

[0103] Compare the quality parameter vector with the demand threshold vector and calculate the satisfaction level of each quality parameter;

[0104] The matching degree of the goods is obtained by weighted fusion based on the satisfaction of each quality parameter, and the goods corresponding to the maximum matching degree are output as the goods matching result.

[0105] The parameters and steps of each unit module in the intelligent matching system for cross-border logistics cargo of the present invention described above can be referred to the parameters and steps in the embodiments of the intelligent matching method for cross-border logistics cargo described above, and will not be repeated here.

[0106] Please refer to Figure 3 The present invention also provides an electronic device 300, including a memory 310, a processor 320, and a communication bus 330; the memory 310 and the processor 320 are connected via the communication bus 330. The memory 310 stores a cross-border logistics cargo intelligent matching method that can be loaded and executed by the processor 320 as provided in the above embodiments.

[0107] The memory 310 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 310 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function, and instructions for implementing the intelligent matching method for cross-border logistics cargo provided in the above embodiments, etc. The data storage area may store data involved in the intelligent matching method for cross-border logistics cargo provided in the above embodiments, etc.

[0108] Processor 320 may include one or more processing cores. Processor 320 executes instructions, programs, code sets, or instruction sets stored in memory 310, and calls data stored in memory 310 to perform various functions and process data according to the present invention. Processor 320 may be at least one of the following: Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), Central Processing Unit (CPU), Controller, Microcontroller, and Microprocessor. It is understood that, for different devices, the electronic devices used to implement the functions of processor 320 may also be other types, and the embodiments of the present invention do not specifically limit this.

[0109] The communication bus 330 may include a path for transmitting information between the aforementioned components. The communication bus 330 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 330 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 The symbol is represented by a single double arrow, but this does not mean that there is only one bus or one type of bus.

[0110] This invention provides a computer-readable storage medium storing a computer program that can be loaded by a processor and executed as described in the above embodiments, a cross-border logistics cargo intelligent matching method.

[0111] In this embodiment of the invention, the computer-readable storage medium can be a tangible device that holds and stores instructions used by an instruction execution device. The computer-readable storage medium can be, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination thereof. Specifically, the computer-readable storage medium can be a portable computer disk, a hard disk, a USB flash drive, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), lectern random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory stick, floppy disk, optical disk, magnetic disk, mechanical encoding device, or any combination thereof.

[0112] The terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0113] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to the technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions claimed in this invention.

Claims

1. A method for intelligent matching of cross-border logistics cargo sources, characterized in that, include: Obtain cargo attribute data and corresponding packaging material attribute data of the goods to be transported, obtain transportation environment data of the planned route, and obtain cargo quality requirement data; Based on packaging material property data and combined with transportation environment data of planned routes, we analyze the performance degradation of packaging materials during transportation and determine the risk of packaging protection failure under the influence of time-series environment. Based on cargo attribute data analysis, the compatibility of cargo co-loading is analyzed, and combined with the risk of packaging protection failure, the quality status of cargo arriving at the port is predicted. Based on the predicted quality status of cargo arriving at the port and combined with cargo quality demand data, cargo matching is performed and the cargo matching results are output. The determination of packaging protection failure risks under the influence of temporal environmental factors includes: The planned route is divided into continuous transport segments, and environmental feature sequences of each transport segment are extracted based on transport environment data. A dynamic model of performance degradation of packaging materials was constructed, and the basic damage factor of packaging for each transportation segment was determined by combining the environmental characteristic sequence. Determine the temporal environmental coupling damage increment factor between adjacent transport segments based on the environmental feature sequence of adjacent transport segments; The total damage factor is obtained by summing the basic damage factor of the packaging for each transport segment and the temporal environmental coupled damage increment factor, and the remaining protection strength of the packaging is determined. The packaging protection failure risk coefficient is obtained by performing a logistic mapping based on the difference between the remaining packaging protection strength and the preset packaging protection strength threshold. The analysis of cargo co-cargo compatibility includes: Based on cargo attribute data, physical, chemical and biological risk attributes of cargo are extracted and normalized risk feature vectors are generated. The risk attribute similarity between any two goods is determined based on the risk feature vector, wherein the risk attribute similarity is determined by the cosine similarity of the risk feature vectors. The ratio of the risk attribute similarity between any two goods to the mean risk attribute similarity among all goods is used as the cargo co-loading compatibility coefficient.

2. The intelligent matching method for cross-border logistics cargo sources according to claim 1, characterized in that, The determination of the temporal environmental coupling damage increment factor between adjacent transport segments includes: Get the Packaging basic damage factor for each transport segment And determine the first The first transport segment and the first Environmental coupling effect function of each transport segment To reflect the impact of continuous environmental conditions on the damage resistance of packaging materials; Determining the time-series environmental coupling damage increment factor based on the cumulative damage factor and the environmental coupling effect function: ,in, For temporal environment coupling sensitivity coefficient, This represents the historical damage weighting coefficient.

3. The intelligent matching method for cross-border logistics cargo sources according to claim 1, characterized in that, The predicted quality status of the cargo upon arrival at the port includes: Determine the synergistic risk coefficient between any two goods based on the cargo co-cargo compatibility coefficient and the packaging protection failure risk coefficient: ,in, For goods The risk factor of packaging protection failure, For goods The risk factor of packaging protection failure, For goods With goods The compatibility coefficient of cargo co-loading between them; The average of the collaborative risk coefficients among all goods is taken as the group collaborative risk coefficient of the cargo source, reflecting the damage risk of different goods when they are co-loaded; A cargo arrival quality status prediction model is constructed based on the group collaborative risk coefficient, which analyzes the quality status of the cargo upon arrival and outputs the corresponding cargo arrival quality status prediction results.

4. The intelligent matching method for cross-border logistics cargo sources according to claim 1, characterized in that, The process of matching goods and outputting the matching results includes: The predicted quality status of cargo arriving at the port is quantified into a quality parameter vector, and the cargo quality demand data is transformed into a demand threshold vector. Compare the quality parameter vector with the demand threshold vector and calculate the satisfaction level of each quality parameter; The matching degree of the goods is obtained by weighted fusion based on the satisfaction of each quality parameter, and the goods corresponding to the maximum matching degree are output as the goods matching result.

5. A cross-border logistics cargo intelligent matching system, used to implement the cross-border logistics cargo intelligent matching method according to any one of claims 1-4, characterized in that, The system includes: The data acquisition module is used to acquire cargo attribute data and corresponding packaging material attribute data of the cargo to be transported, acquire transportation environment data of the planned route, and acquire cargo quality requirement data. The packaging protection analysis module is used to analyze the performance degradation of packaging materials during transportation and determine the risk of packaging protection failure under the influence of time-series environmental factors, based on packaging material property data and transportation environment data of planned routes. The cargo quality prediction module is used to analyze the compatibility of cargo co-loading based on cargo attribute data and predict the quality status of cargo upon arrival at the port by combining the risk of packaging protection failure. The cargo matching output module is used to match cargo sources based on the predicted quality status of cargo arrival at the port and the cargo quality demand data, and then output the cargo matching results.

6. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes a cross-border logistics cargo intelligent matching method as described in any one of claims 1-4 by calling the computer program stored in the memory.

7. A computer-readable storage medium, characterized in that, The system stores instructions that, when executed on a computer, cause the computer to perform a cross-border logistics cargo intelligent matching method as described in any one of claims 1-4.

Images