Cross-border logistics package management method and system based on big data and artificial intelligence

Abstract

The present invention belongs to the field of cross-border logistics technology, and provides a cross-border logistics package management method and system based on big data and artificial intelligence. The method includes: when monitoring that the target cross-border logistics package is about to arrive at the customs clearance and transfer link, obtaining the customs clearance and transfer time consumption big data of each logistics company, and obtaining the customs clearance and transfer efficiency evaluation value of the corresponding customs clearance and transfer agency; determining the reference quantity according to the customs clearance and transfer efficiency evaluation value, and screening the first customs clearance and transfer time consumption data of other logistics companies corresponding to the reference quantity from the customs clearance and transfer time consumption big data; inputting each first customs clearance and transfer time consumption data into the customs clearance and transfer time consumption prediction model constructed based on artificial intelligence, and predicting the second customs clearance and transfer time consumption data; predicting the logistics time of the subsequent stage of the target cross-border logistics package according to the second customs clearance and transfer time consumption data, and outputting it. The present invention predicts the time consumption of the target cross-border logistics package in the customs clearance and transfer agency, and realizes the prediction of the subsequent logistics time of the package.

Description

Technical Field

[0001] The present invention relates to the field of cross-border logistics technology, and in particular to a cross-border logistics package management method and system based on big data and artificial intelligence. Background Art

[0002] Cross-border logistics refers to the process of transporting goods from one country to another country or region by sea, air, land or multimodal transport. It is of great significance in promoting international trade, supporting global supply chains, enhancing corporate market competitiveness, and meeting consumer needs.

[0003] For cross-border logistics, the timeliness management of logistics is a crucial link. With good timeliness management, more accurate information on the flow of goods can be provided to enterprises and consumers, such as the specific time when the goods are delivered to the customer. However, compared with domestic logistics, cross-border logistics needs to go through customs clearance and transshipment, and the time consumption of customs clearance and transshipment is affected by many factors and fluctuates greatly, which increases the difficulty of logistics timeliness management and makes it difficult to provide customers with accurate logistics time information. The present invention aims to improve the technical problem. Summary of the invention

[0004] In this regard, the present invention provides a cross-border logistics package management method, system, electronic device, computer storage medium and computer program product based on big data and artificial intelligence to solve the above-mentioned technical problems.

[0005] The present invention discloses a cross-border logistics package management method based on big data and artificial intelligence, and the method comprises the following steps: when monitoring that a target cross-border logistics package is about to arrive at a customs clearance and transshipment link, obtaining the customs clearance and transshipment time consumption big data of each logistics company, and obtaining the customs clearance and transshipment efficiency evaluation value of the corresponding customs clearance and transshipment agency; determining a reference quantity according to the customs clearance and transshipment efficiency evaluation value, and screening out each first customs clearance and transshipment time consumption data of other logistics companies corresponding to the reference quantity from the customs clearance and transshipment time consumption big data; inputting each first customs clearance and transshipment time consumption data into a customs clearance and transshipment time consumption prediction model constructed based on artificial intelligence, and obtaining the second customs clearance and transshipment time consumption data predicted by the customs clearance and transshipment time consumption prediction model; predicting the logistics time of the subsequent stage of the target cross-border logistics package according to the second customs clearance and transshipment time consumption data, and outputting it.

[0006] Optionally, the obtaining of the customs clearance and transshipment time big data of each logistics company includes: when a target cross-border logistics package is monitored, determining the customs clearance and transshipment agency according to the expected delivery path of the target cross-border logistics package, and obtaining the ID of each logistics company that has a customs clearance and transshipment record in the customs clearance and transshipment agency within a set period; using each logistics company ID as an index, obtaining the customs clearance and transshipment time big data of the corresponding logistics company.

[0007] Optionally, the monitoring that the target cross-border logistics package is about to arrive at the customs clearance and transfer link includes: obtaining real-time transportation positioning information of the target cross-border logistics package, and calculating the logistics time between the package and the customs clearance and transfer agency according to the real-time transportation positioning information; when the logistics time is lower than a time threshold, it is determined that the monitoring that the target cross-border logistics package is about to arrive at the customs clearance and transfer link.

[0008] Among them, the method for determining the duration threshold is as follows: determine the first urgency data of the receiving customer and the second urgency data of the shipping customer of the target cross-border logistics package, and obtain an urgency assessment value by fusing and calculating the first urgency data and the second urgency data; determine the duration threshold based on the urgency assessment value, specifically, the duration threshold is positively correlated with the urgency assessment value.

[0009] Optionally, obtaining the customs clearance and transit efficiency evaluation value of the corresponding customs clearance and transit agency, and determining the reference quantity based on the customs clearance and transit efficiency evaluation value, includes: obtaining customs clearance and transit efficiency data corresponding to the customs clearance and transit agency, the customs clearance and transit efficiency data including a number of average transit times of the customs clearance and transit agency, each of the average transit time consumption corresponds to a different statistical period; calculating the transit time variance based on each of the average transit time consumption, determining the transit time variance as the customs clearance and transit efficiency evaluation value, and determining the reference quantity based on the customs clearance and transit efficiency evaluation value and the corresponding positive correlation.

[0010] Optionally, the step of inputting each of the first customs clearance and transshipment time consumption data into a customs clearance and transshipment time consumption prediction model constructed based on artificial intelligence to obtain second customs clearance and transshipment time consumption data predicted by the customs clearance and transshipment time consumption prediction model includes: determining a usage ratio of online customs clearance declaration tools of each other logistics company, associating the usage ratio with the corresponding first customs clearance and transshipment time consumption data to form an input data; and inputting each of the input data into the customs clearance and transshipment time consumption prediction model constructed based on artificial intelligence to obtain the second customs clearance and transshipment time consumption data predicted by the customs clearance and transshipment time consumption prediction model.

[0011] Optionally, the customs clearance and transit time prediction model is built based on Transformer, or is obtained by fine-tuning and training an existing artificial intelligence model using small sample data.

[0012] The present invention also provides a cross-border logistics package management system based on big data and artificial intelligence, the system comprising an acquisition module, a screening module, a first prediction module, and a second prediction module: the acquisition module is used to monitor that when a target cross-border logistics package is about to arrive at the customs clearance and transshipment link, obtain the customs clearance and transshipment time consumption big data of each logistics company, and obtain the customs clearance and transshipment efficiency evaluation value of the corresponding customs clearance and transshipment agency; the screening module is used to determine a reference quantity according to the customs clearance and transshipment efficiency evaluation value, and filter out the first customs clearance and transshipment time consumption data of other logistics companies corresponding to the reference quantity from the customs clearance and transshipment time consumption big data; the first prediction module is used to input the first customs clearance and transshipment time consumption data into a customs clearance and transshipment time consumption prediction model constructed based on artificial intelligence, and obtain the second customs clearance and transshipment time consumption data predicted by the customs clearance and transshipment time consumption prediction model; the second prediction module is used to predict the logistics time of the subsequent stage of the target cross-border logistics package according to the second customs clearance and transshipment time consumption data, and output it.

[0013] The present invention also provides an electronic device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the computer program implements the method described in any of the preceding items when executed by the processor.

[0014] The present invention also provides a computer storage medium storing a computer program executable by a processor to implement any of the methods described above.

[0015] The present invention also provides a computer program product, which includes a computer program that can be executed by a processor to implement any of the methods described above.

[0016] The solution of the present invention predicts and analyzes the time consumption data of the target cross-border logistics package to be analyzed in the customs clearance and transit agency by referring to the time consumption data of other logistics companies in the customs clearance and transit agency, thereby realizing the prediction of the subsequent logistics time of the target cross-border logistics package, so that customers can obtain more accurate subsequent logistics time, which is conducive to improving customers' logistics experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1It is a flow chart of a cross-border logistics package management method based on big data and artificial intelligence disclosed in an embodiment of the present invention.

[0019] Figure 2 It is a schematic diagram of a reference quantity determination process disclosed in an embodiment of the present invention.

[0020] Figure 3 It is a structural schematic diagram of a cross-border logistics package management system based on big data and artificial intelligence disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0022] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0023] like Figure 1 As shown, an embodiment of the present invention discloses a cross-border logistics package management method based on big data and artificial intelligence, and the method includes the following steps: when monitoring that a target cross-border logistics package is about to arrive at the customs clearance and transshipment link, obtaining the customs clearance and transshipment time consumption big data of each logistics company, and obtaining the customs clearance and transshipment efficiency evaluation value of the corresponding customs clearance and transshipment agency; determining a reference quantity according to the customs clearance and transshipment efficiency evaluation value, and screening out each first customs clearance and transshipment time consumption data of other logistics companies corresponding to the reference quantity from the customs clearance and transshipment time consumption big data; inputting each first customs clearance and transshipment time consumption data into a customs clearance and transshipment time consumption prediction model constructed based on artificial intelligence, and obtaining the second customs clearance and transshipment time consumption data predicted by the customs clearance and transshipment time consumption prediction model; predicting the logistics time of the subsequent stage of the target cross-border logistics package according to the second customs clearance and transshipment time consumption data, and outputting it.

[0024] In view of the problem that it is difficult to accurately predict the logistics time of cross-border logistics packages in the customs clearance and transit link in the existing method, resulting in the inability to provide customers with accurate logistics time for the subsequent stages, the present invention is set to obtain the customs clearance and transit time big data of each logistics company when monitoring that the target cross-border logistics package is about to arrive at the customs clearance and transit link, and obtain the customs clearance and transit efficiency evaluation value of the corresponding customs clearance and transit agency (i.e., each customs agency), and the reference quantity can be determined based on the customs clearance and transit efficiency evaluation value. Then, according to the reference quantity, the corresponding number of first customs clearance and transit time data of other logistics companies that have customs clearance and transit business with the customs clearance and transit agency are screened out, and the first customs clearance and transit time data are obtained from the corresponding screening of the customs clearance and transit time big data of each logistics company obtained above. Next, the obtained first customs clearance and transshipment time consumption data are input into the pre-built artificial intelligence-based customs clearance and transshipment time consumption prediction model to obtain the second customs clearance and transshipment time consumption data predicted by the model, wherein the first customs clearance and transshipment time consumption data represents the equivalent time consumption of other screened logistics companies in the customs clearance and transshipment agency (such as average value, median value, weighted mean, etc.), and the second customs clearance and transshipment time consumption data is the actual time consumption of the target cross-border logistics package in the customs clearance and transshipment agency predicted with reference to the above-mentioned equivalent time consumption of these other logistics companies.

[0025] Therefore, the solution of the present invention predicts and analyzes the time consumption data of the target cross-border logistics package to be analyzed in the customs clearance and transit agency by referring to the time consumption data of other logistics companies in the customs clearance and transit agency, thereby realizing the prediction of the subsequent logistics time of the target cross-border logistics package, so that customers can obtain more accurate subsequent logistics time, which is conducive to improving customers' logistics experience.

[0026] It should be noted that after determining the time spent by the target cross-border logistics package in the corresponding customs clearance and transfer agency, the logistics time of the subsequent stages of the target cross-border logistics package can be predicted in a conventional manner, such as the arrival time of the provincial transit node, the arrival time of the municipal transit node, etc. The specific prediction method adopts the existing technology, and the present invention will not go into details.

[0027] Optionally, the obtaining of the customs clearance and transshipment time big data of each logistics company includes: when a target cross-border logistics package is monitored, determining the customs clearance and transshipment agency according to the expected delivery path of the target cross-border logistics package, and obtaining the ID of each logistics company that has a customs clearance and transshipment record in the customs clearance and transshipment agency within a set period; using each logistics company ID as an index, obtaining the customs clearance and transshipment time big data of the corresponding logistics company.

[0028] In this embodiment, after the target cross-border logistics package is collected and shipped, it can be monitored on the website of the corresponding logistics company, and the expected delivery route of the target cross-border logistics package can be known, and the expected delivery route will include the customs clearance and transit agencies that will be passed through. Next, obtain the IDs of each logistics company that has a customs clearance and transit record at the customs clearance and transit agency within the set period, that is, determine which logistics companies have performed customs clearance and transit operations at the customs clearance and transit agency. Finally, using these logistics company IDs as indexes, it is possible to obtain the customs clearance and transit time big data of the corresponding logistics companies. Among them, the customs clearance and transit time big data refers to the customs clearance time record of the logistics company at the corresponding customs clearance and transit agency, that is, the customs clearance and transit time experienced by each cross-border logistics order, which can be limited to a time, such as one month, three months, or half a year.

[0029] It should be noted that the set period can be manually preset, such as 1 year, 2 years, etc., without specific limitation.

[0030] Optionally, the monitoring that the target cross-border logistics package is about to arrive at the customs clearance and transfer link includes: obtaining real-time transportation positioning information of the target cross-border logistics package, and calculating the logistics time between the package and the customs clearance and transfer agency according to the real-time transportation positioning information; when the logistics time is lower than a time threshold, it is determined that the monitoring that the target cross-border logistics package is about to arrive at the customs clearance and transfer link.

[0031] Among them, the method for determining the duration threshold is as follows: determine the first urgency data of the receiving customer and the second urgency data of the shipping customer of the target cross-border logistics package, and obtain an urgency assessment value by fusing and calculating the first urgency data and the second urgency data; determine the duration threshold based on the urgency assessment value, specifically, the duration threshold is positively correlated with the urgency assessment value.

[0032] In this embodiment, the acquisition of customs clearance and transit time big data of other logistics companies requires the response and approval of the corresponding logistics companies. This process also takes a certain amount of time (for example, half an hour, 1 hour), so it is necessary to execute the solution of the present invention in advance before reaching the customs clearance and transit link. Therefore, the real-time transportation positioning information of the target cross-border logistics package is monitored in real time. According to the real-time transportation positioning information and the location information of the customs clearance and transit agency, the logistics time (distance divided by driving speed) between the customs clearance and transit agency can be calculated, that is, the driving time of the transport vehicle / ship / aircraft. When the logistics time is lower than the time threshold, it can be determined that the target cross-border logistics package is about to arrive at the customs clearance and transit link.

[0033] Among them, the duration threshold in the present invention is dynamically set. Specifically, the urgency data of the receiving customer and the shipping customer of the target cross-border logistics package are obtained. The second urgency data of the shipping customer can be extracted from the logistics type selected by the shipping customer and / or the logistics order note data. For example, the logistics type is "Express" or "Ordinary Express", and the note data is "Important customers, please expedite delivery", etc. From these data, the shipping customer's requirements for the logistics time update speed and accuracy of the target cross-border logistics package can be extracted. Obviously, the more anxious the shipping customer is to deliver, the higher the corresponding second urgency data, and vice versa. The first urgency data of the receiving customer can be the number of logistics inquiries initiated by the customer to the logistics company after the package is sent. The higher the number of logistics inquiries, the higher the requirements of the receiving customer for the logistics time update speed and accuracy of the target cross-border logistics package, and vice versa. On this basis, the first urgency data and the second urgency data are fused and calculated by weighted averaging to obtain the urgency evaluation value. Of course, the weight of the first urgency data may be set higher than the weight of the second urgency data, that is, the urgency of receiving the goods from the customer is considered more important.

[0034] Finally, when the urgency assessment value of the target cross-border logistics package is higher, it is necessary to execute the solution of the present invention earlier (that is, the time threshold is larger), which is conducive to faster and more timely prediction of the above-mentioned second customs clearance and transit time data, which is conducive to providing logistics time for customers later. In contrast, when the urgency assessment value of the target cross-border logistics package is lower, the solution of the present invention can be executed later (that is, the time threshold is smaller), because the response and approval time of different logistics companies are different, and the first customs clearance and transit time data obtained first may have insufficient data volume, too much error data, etc., and it is not appropriate to use it to predict the second customs clearance and transit time data. By executing the solution of the present invention later, it is possible to screen from the first customs clearance and transit time data received from more other logistics companies, and then predict the second customs clearance and transit time data based on the more suitable first customs clearance and transit time data of other logistics companies.

[0035] Alternatively, if Figure 2 As shown, the obtaining of the customs clearance and transit efficiency evaluation value of the corresponding customs clearance and transit agency, and determining the reference quantity based on the customs clearance and transit efficiency evaluation value, include: obtaining the customs clearance and transit efficiency data corresponding to the customs clearance and transit agency, the customs clearance and transit efficiency data including a number of average transit times of the customs clearance and transit agency, each of the average transit time corresponding to a different statistical period; calculating the transit time variance based on each of the average transit time, determining the transit time variance as the customs clearance and transit efficiency evaluation value, and determining the reference quantity based on the customs clearance and transit efficiency evaluation value and the corresponding positive correlation.

[0036] In this embodiment, the scheme of the present invention is to analyze the time consumption of the target cross-border logistics package in the customs clearance and transit agency this time by referring to the customs clearance and transit time consumption data of other logistics companies, which requires determining the number of logistics companies used for reference. Specifically, several average transit times of the customs clearance and transit agency in the recent period (for example, 1 year) are obtained, and each average transit time corresponds to a different statistical period, such as every month. These average transit times can be released by the customs clearance and transit agency itself. Then, the variance of these average transit times can be calculated, and the variance can be used to characterize the fluctuation amplitude of the transit time consumption of the customs clearance and transit agency in the recent period, that is, the larger the variance, the larger the corresponding fluctuation amplitude, and vice versa. On this basis, the present invention sets the variance as the customs clearance and transit efficiency evaluation value, and the number of logistics companies used for reference is positively correlated with the variance, that is, the greater the fluctuation of the transit time consumption of the customs clearance and transit agency, the more logistics companies used for reference, which can effectively reduce the prediction deviation caused by abnormal disturbances and improve the accuracy of the second customs clearance and transit time consumption data; on the contrary, the fewer the number of logistics companies used for reference, the less data calculation can be reduced and the prediction rate can be improved.

[0037] It should be noted that the present invention does not impose any specific limitation on the calculation formula form of the positive correlation between the above-mentioned time threshold and the urgency assessment value, and the positive correlation between the reference quantity and the customs clearance and transportation efficiency assessment value.

[0038] Optionally, the step of inputting each of the first customs clearance and transshipment time consumption data into a customs clearance and transshipment time consumption prediction model constructed based on artificial intelligence to obtain second customs clearance and transshipment time consumption data predicted by the customs clearance and transshipment time consumption prediction model includes: determining a usage ratio of online customs clearance declaration tools of each other logistics company, associating the usage ratio with the corresponding first customs clearance and transshipment time consumption data to form an input data; and inputting each of the input data into the customs clearance and transshipment time consumption prediction model constructed based on artificial intelligence to obtain the second customs clearance and transshipment time consumption data predicted by the customs clearance and transshipment time consumption prediction model.

[0039] In this embodiment, customs clearance and transshipment can be performed manually on-site customs clearance or online customs clearance using online customs clearance declaration tools. The efficiency of online customs clearance is significantly higher than that of manual on-site customs clearance, so it has gradually become the mainstream method of customs clearance. Therefore, the present invention also obtains the usage ratio of the online customs clearance declaration tools of each other logistics company obtained by the above screening. The data used to calculate the usage ratio can be attached to the first customs clearance and transshipment time consumption data, or it can be obtained by sending a request information to the corresponding logistics company again. The usage ratio of each other logistics company and the first customs clearance and transshipment time consumption data are associated to form an input data. Each input data is input into the customs clearance and transshipment time consumption prediction model to obtain the second customs clearance and transshipment time consumption data predicted by the model.

[0040] When the customs clearance and transit time consumption prediction model makes the above prediction, it is mainly based on the first customs clearance and transit time consumption data of other logistics companies, that is, the customs clearance and transit time consumption prediction model can analyze the current time consumption of the target cross-border logistics package by analyzing the customs clearance and transit time consumption data of multiple other logistics companies used for reference. At the same time, the usage ratio of the online customs clearance declaration tool can be used to guide the customs clearance and transit time consumption prediction model to correct the predicted customs clearance and transit time consumption data. For example, the customs clearance and transit time consumption prediction model first predicts the preliminary second customs clearance and transit time consumption data based on the first customs clearance and transit time consumption data, and then calculates the average usage ratio based on the usage ratio of the online customs clearance declaration tools of other logistics companies, and uses the average usage ratio to match and obtain the corresponding correction coefficient, and uses the correction coefficient to correct the preliminary second customs clearance and transit time consumption data to the final second customs clearance and transit time consumption data. Among them, the corresponding relationship between the average usage ratio matching and the correction coefficient can be shown in the following table:

[0041] It should be noted that since the use of online customs clearance declaration tools has become the norm, most logistics companies are using them, and the proportion of manual on-site customs clearance is already very low. The target cross-border logistics parcels in the present invention also adopt online customs clearance methods. Therefore, when the average use ratio of the online customs clearance declaration tool is higher, it means that the reliability of the preliminary second customs clearance transit time data predicted by the target cross-border logistics parcel is higher, that is, the higher the matching degree with the target cross-border logistics parcel is, the smaller the correction coefficient is set at this time, that is, the correction of the preliminary second customs clearance transit time data is reduced; and when the average use ratio of the online customs clearance declaration tool is lower, it means that the reliability of the preliminary second customs clearance transit time data predicted by the target cross-border logistics parcel is lower, that is, the lower the matching degree with the target cross-border logistics parcel is, the larger the correction coefficient is set at this time, that is, the correction of the preliminary second customs clearance transit time data is enhanced. Such a setting can ensure the accuracy of the predicted second customs clearance transit time data and reduce the probability of inaccurate logistics time output to customers.

[0042] Optionally, the customs clearance and transit time prediction model is built based on Transformer, or is obtained by fine-tuning and training an existing artificial intelligence model using small sample data.

[0043] In this embodiment, Transformer is the basis of many artificial intelligence models, so Transformer can be used to construct the above-mentioned customs clearance and transit time prediction model, and it can be fully trained using a specially collected and constructed training data set to achieve the second customs clearance and transit time data of the target cross-border logistics package based on the first customs clearance and transit time data of other logistics companies used for reference.

[0044] However, manually building a customs clearance and transshipment time prediction model is time-consuming and laborious, and whether the model construction and initial parameter settings are appropriate will directly affect the prediction performance of the customs clearance and transshipment time prediction model. In this regard, you can also choose to use small sample data to fine-tune the existing artificial intelligence model to obtain the above customs clearance and transshipment time prediction model. The existing artificial intelligence model preferably uses the GPT series large model, or the BERT model, etc.

[0045] like Figure 3 As shown, the present invention also discloses a cross-border logistics package management system based on big data and artificial intelligence, the system comprising an acquisition module, a screening module, a first prediction module, and a second prediction module: the acquisition module is used to monitor that when a target cross-border logistics package is about to arrive at the customs clearance and transshipment link, obtain the customs clearance and transshipment time consumption big data of each logistics company, and obtain the customs clearance and transshipment efficiency evaluation value of the corresponding customs clearance and transshipment agency; the screening module is used to determine a reference quantity according to the customs clearance and transshipment efficiency evaluation value, and filter out each first customs clearance and transshipment time consumption data of other logistics companies corresponding to the reference quantity from the customs clearance and transshipment time consumption big data; the first prediction module is used to input each of the first customs clearance and transshipment time consumption data into a customs clearance and transshipment time consumption prediction model constructed based on artificial intelligence, and obtain the second customs clearance and transshipment time consumption data predicted by the customs clearance and transshipment time consumption prediction model; the second prediction module is used to predict the logistics time of the subsequent stage of the target cross-border logistics package according to the second customs clearance and transshipment time consumption data, and output it.

[0046] The present invention also discloses an electronic device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the computer program implements the method described in any of the preceding items when executed by the processor.

[0047] The present invention also discloses a computer storage medium, which stores a computer program that can be executed by a processor to implement any of the methods described in the preceding items.

[0048] The present invention also discloses a computer program product, which includes a computer program that can be executed by a processor to implement any of the methods described in the preceding items.

[0049] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0050] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or can be electrical, mechanical or other forms of connection.

[0051] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0052] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A cross-border logistics package management method based on big data and artificial intelligence, characterized by: The method comprises the following steps: when it is detected that the target cross-border logistics package is about to arrive at the customs clearance and transshipment link, obtaining the customs clearance and transshipment time consumption big data of each logistics company, including: when the target cross-border logistics package is detected, determining the customs clearance and transshipment agency according to the expected delivery path of the target cross-border logistics package, and obtaining the ID of each logistics company that has a customs clearance and transshipment record in the customs clearance and transshipment agency within a set period; using each of the logistics company IDs as an index, obtaining the customs clearance and transshipment time consumption big data of the corresponding logistics company; and obtaining a customs clearance and transshipment efficiency evaluation value of a corresponding customs clearance and transshipment agency, and determining a reference quantity according to the customs clearance and transshipment efficiency evaluation value, including: obtaining customs clearance and transshipment efficiency data corresponding to the customs clearance and transshipment agency, the customs clearance and transshipment efficiency data including a number of average transshipment times of the customs clearance and transshipment agency, each of the average transshipment times corresponding to a different statistical period; calculating a transshipment time variance according to each of the average transshipment times, determining the transshipment time variance as the customs clearance and transshipment efficiency evaluation value, and determining the reference quantity according to the customs clearance and transshipment efficiency evaluation value and the corresponding positive correlation; The first customs clearance and transshipment time consumption data of other logistics companies that have customs clearance and transshipment business with the customs clearance and transshipment agency corresponding to the reference number are screened out from the customs clearance and transshipment time consumption big data; the first customs clearance and transshipment time consumption data are input into the customs clearance and transshipment time consumption prediction model constructed based on artificial intelligence to obtain the second customs clearance and transshipment time consumption data predicted by the customs clearance and transshipment time consumption prediction model; the logistics time of the subsequent stage of the target cross-border logistics package is predicted according to the second customs clearance and transshipment time consumption data, and the result is output.

2. According to claim 1, a cross-border logistics package management method based on big data and artificial intelligence is characterized by: Monitoring that a target cross-border logistics package is about to arrive at the customs clearance and transfer link includes: obtaining real-time transportation positioning information of the target cross-border logistics package, and calculating the logistics time between the package and the customs clearance and transfer agency according to the real-time transportation positioning information; when the logistics time is lower than a time threshold, determining that the target cross-border logistics package is about to arrive at the customs clearance and transfer link; wherein, the time threshold is determined as follows: determining first urgency data of the receiving customer and second urgency data of the shipping customer of the target cross-border logistics package, and obtaining an urgency assessment value by fusion calculation of the first urgency data and the second urgency data; determining the time threshold according to the urgency assessment value, specifically, the time threshold is positively correlated with the urgency assessment value.

3. According to claim 2, a cross-border logistics package management method based on big data and artificial intelligence is characterized by: Inputting each of the first customs clearance and transshipment time consumption data into the customs clearance and transshipment time consumption prediction model constructed based on artificial intelligence to obtain the second customs clearance and transshipment time consumption data predicted by the customs clearance and transshipment time consumption prediction model, including: determining the usage ratio of the online customs clearance declaration tools of each other logistics company, associating the usage ratio with the corresponding first customs clearance and transshipment time consumption data to constitute an input data; inputting each of the input data into the customs clearance and transshipment time consumption prediction model constructed based on artificial intelligence to obtain the second customs clearance and transshipment time consumption data predicted by the customs clearance and transshipment time consumption prediction model.

4. According to claim 1, a cross-border logistics package management method based on big data and artificial intelligence is characterized by: The customs clearance and transit time prediction model is built based on Transformer, or is obtained by fine-tuning and training an existing artificial intelligence model using small sample data.

5. A cross-border logistics package management system based on big data and artificial intelligence, the system is based on the method described in any one of claims 1 to 4, characterized in that: The system includes an acquisition module, a screening module, a first prediction module, and a second prediction module: the acquisition module is used to monitor that when a target cross-border logistics package is about to arrive at the customs clearance and transshipment link, obtain the customs clearance and transshipment time consumption big data of each logistics company, and obtain the customs clearance and transshipment efficiency evaluation value of the corresponding customs clearance and transshipment agency; the screening module is used to determine a reference quantity according to the customs clearance and transshipment efficiency evaluation value, and filter out the first customs clearance and transshipment time consumption data of other logistics companies corresponding to the reference quantity from the customs clearance and transshipment time consumption big data; the first prediction module is used to input the first customs clearance and transshipment time consumption data into a customs clearance and transshipment time consumption prediction model constructed based on artificial intelligence, and obtain the second customs clearance and transshipment time consumption data predicted by the customs clearance and transshipment time consumption prediction model; the second prediction module is used to predict the logistics time of the subsequent stage of the target cross-border logistics package according to the second customs clearance and transshipment time consumption data, and output it.

6. An electronic device, characterized in that: The electronic device comprises: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the computer program implements the method according to any one of claims 1 to 4 when executed by the processor.

7. A computer storage medium, characterized in that: The computer storage medium stores a computer program that can be executed by a processor to implement the method according to any one of claims 1 to 4.

8. A computer program product, characterized in that: The computer program product comprises a computer program executable by a processor to implement the method according to any one of claims 1 to 4.

Images