Artificial Intelligence-Based Supply Chain Logistics Information Management System

Abstract

The present invention discloses a supply chain logistics information management system based on artificial intelligence, specifically related to the field of artificial intelligence technology, including a linear fitting module, a non-linear fitting module, a dual-mode construction module, a distribution verification module, and a management intervention module. The linear fitting module obtains linear conventional coefficients according to linear scenario information, the non-linear fitting module obtains non-linear special coefficients according to non-linear scenario information, the dual-mode construction module constructs a dual-mode management model based on the linear conventional coefficients and non-linear special coefficients and outputs a time cost delay index, the distribution verification module classifies the delay status in the supply chain logistics information management process, and the management intervention module conducts intervention management according to the classification results. This application predicts the time cost of the most time-consuming and laborious customs declaration and tax payment links in the supply chain logistics information management process, improving the management effectiveness and real-time performance of the entire logistics information management chain.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence. More specifically, the present invention is a supply chain logistics information management system based on artificial intelligence. Background Art

[0002] A supply chain logistics information management system based on artificial intelligence is a supply chain logistics management solution integrating artificial intelligence technology. Through intelligent algorithms and big data analysis, it conducts real-time monitoring, optimization, and management of the supply chain logistics process, improves logistics efficiency, reduces costs, and realizes intelligent management of the supply chain.

[0003] Existing supply chain logistics information management systems based on artificial intelligence usually build scenarios based on continuous linear data. However, there may be non-linear complex relationships in logistics information data, and simple linear models cannot meet the management requirements in non-linear scenarios. There are great differences in the logistics declaration and tax payment links, which in turn affect the subsequent ground distribution preparation links. Therefore, it has become an urgent problem to construct a prediction model based on artificial intelligence technology that can meet both linear and non-linear scenarios, predict the time cost of the declaration and tax payment links, and then verify the real-time conditions of ground distribution.

[0004] To solve the above defects, a technical solution is now proposed. Summary of the Invention

[0005] The purpose of the present invention is to provide a supply chain logistics information management system based on artificial intelligence to solve the deficiencies in the background art.

[0006] To achieve the above purpose, the present invention provides the following technical solution: A supply chain logistics information management system based on artificial intelligence, including a linear fitting module, a non-linear fitting module, a dual-mode construction module, a distribution verification module, and a management intervention module;

[0007] The linear fitting module is used to collect linear scenario information of the supply chain logistics information management system, obtain linear conventional coefficients according to the linear scenario information, and transmit the linear conventional coefficients to the dual-mode construction module;

[0008] The non-linear fitting module is used to collect non-linear scenario information of the supply chain logistics information management system, obtain non-linear special coefficients according to the non-linear scenario information, and transmit the non-linear special coefficients to the dual-mode construction module;

[0009] The dual-mode construction module is used to construct a dual-mode management model according to the linear conventional coefficients and non-linear special coefficients, evaluate the delay status of declaration and tax payment in the supply chain logistics information management process, and output a time cost delay index;

[0010] The delivery verification module is used to compare the time-cost delay index with a preset time-cost delay threshold to classify the delay status in the supply chain logistics information management process;

[0011] The management intervention module is used to perform intervention management according to the classification results.

[0012] Preferably, the linear scenario information and the non-linear scenario information are extracted from the collected data. The collected data includes the type of goods, the status of customs policies, the regional number, the seasonal status, the quantity of goods, and the value of goods. The goods are classified into different types according to their properties, and the type of goods is converted into a numerical form by one-hot encoding. The status of customs policies includes policy changes, policy unchanged, and sampling ratio, and the status of customs policies is converted into a numerical form by one-hot encoding. The seasonal status is represented by a date and converted into time series data.

[0013] Preferably, the method for obtaining the linear scenario information is as follows:

[0014] Obtain the interaction fluctuation coefficient of the supply chain logistics information management system within the cycle time T, and integrate the interaction fluctuation coefficients of the supply chain logistics information management system within several cycle times T into a data set, and mark the data set as XX = {xx p}, where p = {1, 2, 3,..., o}, and o is a positive integer, and xx p represents the interaction fluctuation coefficient of the supply chain logistics information management system within the p-th cycle time T. The calculation expression of the interaction fluctuation coefficient is Among them, X1 represents the type of goods, X1 is a categorical variable, and is converted into a numerical value {X 1，1 , X 1，2 ,..., X 1，i} by one-hot encoding, where i is the numerical serial number of the one-hot encoding and i is a positive integer, and X2 represents the seasonal status and represents the date.

[0015] Preferably, the method for obtaining the linear conventional coefficient according to the linear scenario information is as follows:

[0016] Calculate the standard deviation of the interaction fluctuation coefficients of the supply chain logistics information management system within several cycle times T. The calculation expression is In the formula, xxa is the average value of the interaction fluctuation coefficients of the supply chain logistics information management system within several cycle times T. The calculation expression is

[0017] Calibrate the customs policy status as C ps and the regional number as A c and the quantity of goods as G q and the value of goods as G v, then the expression of the linear regression model is In the formula, L nc is the linear conventional coefficient, and β1, β2, and β3 are the weight coefficients of I fc , (G q +G v ), respectively, and β1, β2, and β3 are all positive numbers. ∈ is a very small positive number representing the error term.

[0018] Preferably, the method for obtaining non-linear scenario information is as follows:

[0019] Obtain the non-linear composite coefficient of the supply chain logistics information management system within the cycle time T, and integrate the non-linear composite coefficients of the supply chain logistics information management system within several cycle times T into a data set, and label the data set as Non = {non u}, where u = {1, 2, 3,..., y}, and y is a positive integer. non u represents the non-linear composite coefficient of the supply chain logistics information management system within the u-th cycle time T. The calculation expression of the non-linear composite coefficient is In the formula, X2 is the seasonal state converted into a time series form, and P c is the number of changes in customs policies, and P c is a non-negative number.

[0020] Preferably, the method for obtaining the non-linear special coefficient according to the non-linear scenario information is as follows:

[0021] Calculate the standard deviation of the non-linear composite coefficients of the supply chain logistics information management system within several cycle times T. The calculation expression is In the formula, nona is the average value of the non-linear composite coefficients of the supply chain logistics information management system within several cycle times T. The calculation expression is

[0022] Construct a random forest model, and train each tree T r in the random forest respectively to generate prediction values, average the prediction values of all trees and output the average prediction value. The mathematical model for calculating the average prediction value is In the formula, N sp is the non-linear special coefficient, T r (A) is the prediction value of the r-th tree in the random forest, r is the tree number and r is a positive integer, w is the total number of trees, and A is the input feature vector. The input features include the type of goods, the status of customs policies, the region number, the seasonal state, the quantity of goods, and the value of goods.

[0023] Preferably, the construction logic of the dual-mode management model is as follows:

[0024] Define a dual-mode management model by combining weighted average and rule setting. When a specific condition is triggered, use rule setting to select the model; when the specific condition is not triggered, use the weighted average model. The expression of the dual-mode management model is In the formula, T cd is the time cost delay index, ωω1 and ω2 are the weight coefficients of the linear conventional coefficient and the non-linear special coefficient respectively, and both ω1 and ω2 are positive numbers. If Rule(S) = False, then output the weighted average result of linear regression and non-linear fitting. If Rule(S) = True, then output the result of non-linear fitting, where Rule(S) is a logical rule defined according to the input feature S, and In the formula, when the goods type is dangerous goods or precision instruments, or the seasonal status is a holiday, S ty takes the value of 1, otherwise, S ty takes the value of 0.

[0025] Preferably, the logic for grading the delay status in the supply chain logistics information management process is as follows:

[0026] The preset time cost delay threshold is T th , compare the calculated time cost delay index T cd with the time cost delay threshold T th . When the time cost delay index T cd is greater than or equal to the time cost delay threshold T th , mark the process as delayed and define the delay status as the diffusion level;

[0027] When the time cost delay index T cd is less than the time cost delay threshold T th , mark the process as not delayed and define the delay status as the contraction level.

[0028] Preferably, the logic for intervention management according to the grading result is as follows:

[0029] When the delay status is the diffusion level, inform the management staff that the ground delivery is postponed for waiting; when the delay status is the contraction level, inform the management staff that the ground delivery departs on time.

[0030] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0031] This application optimizes the management of supply chain logistics information by separately designing a linear model applicable to the normal state and a non-linear model for special states, ensuring that in special cases, time-cost prediction is carried out for the most time-consuming and labor-intensive customs declaration and duty-paying links in the supply chain logistics information management process, improving the management effectiveness and real-time nature of the entire logistics information management chain, strengthening the accuracy and applicability of time-cost prediction, reducing the cost and accuracy of using the linear model for prediction under normal circumstances, and improving the interpretability of using the non-linear model for fitting prediction in special cases, effectively enhancing the management efficiency of supply chain logistics information. Brief Description of the Drawings

[0032] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0033] Figure 1 It is a system module diagram of the present invention. Detailed Embodiments

[0034] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0035] Embodiment 1: Please refer to Figure 1 As shown, the present invention is a supply chain logistics information management system based on artificial intelligence, including a linear fitting module, a non-linear fitting module, a dual-mode construction module, a distribution verification module, and a management intervention module;

[0036] The linear fitting module is used to collect linear scenario information of the supply chain logistics information management system, obtain linear normal coefficients according to the linear scenario information, and transmit the linear normal coefficients to the dual-mode construction module;

[0037] The non-linear fitting module is used to collect non-linear scenario information of the supply chain logistics information management system, obtain non-linear special coefficients according to the non-linear scenario information, and transmit the non-linear special coefficients to the dual-mode construction module;

[0038] The dual-mode construction module is used to construct a dual-mode management model according to the linear normal coefficients and non-linear special coefficients, evaluate the delay status of customs declaration and duty payment in the supply chain logistics information management process, and output a time-cost delay index;

[0039] The delivery verification module is used to compare the time - cost delay index with a preset time - cost delay threshold to classify the delay status in the supply - chain logistics information management process;

[0040] The management intervention module is used to perform intervention management according to the classification result.

[0041] Non - linear data refers to the situation where the relationship between variables does not conform to a simple linear pattern. The relationship between the dependent variable and the independent variable cannot be represented by a straight line, but rather shows a curve or a complex pattern. This means that the association between data is more complex, and multiple factors may act simultaneously, and the effect will change with the change of conditions. For the same type of logistics goods, the type, quantity, and value of the goods are roughly the same, the customs policy is stable, and the sampling inspection mode is regular, and the duty - paid tax rate basically does not fluctuate. Then the time for declaration and duty - payment basically increases linearly with the quantity of goods, and a simple linear regression model can be used for prediction. However, for different types of goods, for example, there are both ordinary goods with low value and low risk, and special goods with high value and high risk. The customs policy will be adjusted at different times, and sometimes special situations such as sampling inspection will be encountered. The calculation of taxes involves complex combinations of tax types, resulting in a sharp increase in the duty - payment time under certain conditions. In this complex situation, the relationship between data is no longer a linear relationship but shows non - linear characteristics, and it is difficult to accurately predict through a simple linear model;

[0042] The characteristics of non - linear data include: the change of the independent variable does not cause the dependent variable to change at a fixed rate; there are complex interactions between multiple independent variables; when a certain variable exceeds a certain threshold, the impact on the dependent variable changes sharply, while the impact is small below the threshold.

[0043] Linear - scenario information and non - linear - scenario information are extracted by collecting data. The collected data includes goods type, customs - policy status, region number, seasonal status, quantity of goods, and value of goods. The goods are classified into different types according to their nature, and the goods type is converted into a numerical form using one - hot encoding. The customs - policy status includes policy changes, policy unchanged, and sampling - inspection ratio, and the customs - policy status is converted into a numerical form using one - hot encoding. The seasonal status is represented by a date and converted into time - series data.

[0044] By obtaining the linear - scenario information of the supply - chain logistics information management system, the effectiveness of the linear mode of the supply - chain logistics information management system is evaluated to obtain a linear - regular coefficient, which measures the linear effectiveness degree of the supply - chain logistics information management system;

[0045] The linear fitting module is used to collect the linear - scenario information of the supply - chain logistics information management system, obtain the linear - regular coefficient according to the linear - scenario information, and transmit the linear - regular coefficient to the dual - mode construction module;

[0046] The method for obtaining linear scenario information is as follows:

[0047] Obtain the interaction fluctuation coefficient of the supply chain logistics information management system within the cycle time T, and integrate the interaction fluctuation coefficients of the supply chain logistics information management system within several cycle times T into a data set, and label the data set as XX = {xx p}, where p = {1, 2, 3,..., o}, and o is a positive integer, and xx p represents the interaction fluctuation coefficient of the supply chain logistics information management system within the p-th cycle time T. The calculation expression of the interaction fluctuation coefficient is where X1 represents the type of goods, X1 is a categorical variable, and is transformed into a numerical value {X 1，1 , X 1，2 ,..., X 1，i} through one-hot encoding. Here, i is the numerical serial number of the one-hot encoding, and i is a positive integer. X2 represents the seasonal state and represents the date;

[0048] It should be noted that the type of goods is provided by the supplier or manufacturer at the time of shipment. The customs policy status is obtained through the customs department, government statistical websites, and professional international trade data platforms. The regional number is generated based on the logistics information of the place of shipment and destination of the goods. The quantity of goods is obtained from the supplier's shipping order, and the value of the goods is obtained from the supplier's invoice or purchase contract.

[0049] The method for obtaining the linear conventional coefficient according to the linear scenario information is as follows:

[0050] Calculate the standard deviation of the interaction fluctuation coefficients of the supply chain logistics information management system within several cycle times T. The calculation expression is In the formula, xxa is the average value of the interaction fluctuation coefficients of the supply chain logistics information management system within several cycle times T. The calculation expression is

[0051] Fit a linear regression model by the least squares method, and calibrate the customs policy status as C ps , the regional number as A c , the quantity of goods as G q , and the value of the goods as G v . Then the expression of the linear regression model is In the formula, L nc is the linear conventional coefficient, and β1, β2, β3 are the weight coefficients of I fc , (G q +G v ) respectively, and β1, β2, β3 are all positive numbers. ∈ is a very small positive number representing the error term.

[0052] In the process of calculating the linear conventional coefficient, linear scenario information is obtained by interacting the goods type and the seasonal status, integrating the characteristic meanings of the goods type and the seasonal status, effectively and deeply capturing the periodic laws of different types of goods, and improving the accuracy of prediction using the linear model.

[0053] The non-linear fitting module is used to collect the non-linear scenario information of the supply chain logistics information management system, obtain the non-linear special coefficient according to the non-linear scenario information, and transmit the non-linear special coefficient to the dual-mode construction module;

[0054] The method for obtaining the non-linear scenario information is as follows:

[0055] Obtain the non-linear composite coefficient of the supply chain logistics information management system within the cycle time T, integrate the non-linear composite coefficients of the supply chain logistics information management system within several cycle times T into a data set, and mark the data set as Non = {non u}, where u = {1, 2, 3,..., y}, and y is a positive integer, non u represents the non-linear composite coefficient of the supply chain logistics information management system within the u-th cycle time T, and the calculation expression of the non-linear composite coefficient is In the formula, X2 is the seasonal status converted into a time series form, P c is the number of changes in customs policies, and p c is a non-negative number;

[0056] The method for obtaining the non-linear special coefficient according to the non-linear scenario information is as follows:

[0057] Calculate the standard deviation of the non-linear composite coefficients of the supply chain logistics information management system within several cycle times T, and the calculation expression is In the formula, nona is the average value of the non-linear composite coefficients of the supply chain logistics information management system within several cycle times T, and the calculation expression is

[0058] Construct a random forest model, and for each tree T of the random forest r train and generate prediction values respectively, average the prediction values of all trees and output the average prediction value, and the mathematical model for calculating the average prediction value is In the formula, N sp is the non-linear special coefficient, T r (A) is the prediction value of the r-th tree in the random forest, r is the tree number and r is a positive integer, w is the total number of trees, A is the input feature vector, and the input features include goods type, customs policy status, region number, seasonal status, quantity of goods, value of goods.

[0059] The dual - mode construction module is used to construct a dual - mode management model based on linear conventional coefficients and non - linear special coefficients, evaluate the delay status of customs declaration and duty payment in the supply chain logistics information management process, and output the time - cost delay index;

[0060] The construction logic of the dual - mode management model is as follows:

[0061] Define the dual - mode management model by combining weighted average and rule - setting methods. When a specific condition is triggered, use rule - setting to select the model; when the specific condition is not triggered, use the weighted - average model. The expression of the dual - mode management model is In the formula, T cd is the time - cost delay index, ω1 and ω2 are the weight coefficients of the linear conventional coefficient and the non - linear special coefficient respectively, and both ω1 and ω2 are positive numbers. If Rule(S) = False, then output the weighted - average result of linear regression and non - linear fitting. If Rule(S) = True, then output the result of non - linear fitting. Among them, Rule(S) is a logical rule defined according to the input feature S, and In the formula, when the cargo type is dangerous goods or precision instruments, or the seasonal status is a holiday, S ty takes the value of 1. Otherwise, S ty takes the value of 0.

[0062] The delivery verification module is used to compare the time - cost delay index with a preset time - cost delay threshold to classify the delay status in the supply chain logistics information management process;

[0063] The preset time - cost delay threshold is T th . Compare the calculated time - cost delay index T cd with the time - cost delay threshold T th . When the time - cost delay index T cd is greater than or equal to the time - cost delay threshold T th , mark the process as delayed and define the delay status as the diffusion level;

[0064] When the time - cost delay index T cd is less than the time - cost delay threshold T th , mark the process as not delayed and define the delay status as the contraction level.

[0065] The management intervention module is used to conduct intervention management according to the classification results;

[0066] When the delay status is at the diffusion level, inform the management staff that the ground delivery is postponed for waiting; when the delay status is at the contraction level, inform the management staff that the ground delivery departs on time.

[0067] This application optimizes the management of supply chain logistics information by separately designing a linear model applicable to normal states and a non-linear model for special states, ensuring that in special cases, time-cost prediction is carried out for the most time-consuming and labor-intensive customs declaration and duty payment links in the supply chain logistics information management process, improving the management effectiveness and real-time nature of the entire chain of logistics information management, strengthening the accuracy and applicability of time-cost prediction, reducing the cost and inaccuracy of using the linear model for prediction under normal circumstances, and improving the interpretability of using the non-linear model for fitting prediction in special cases, effectively enhancing the management efficiency of supply chain logistics information.

[0068] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0069] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of this application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more sets of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0070] It should be understood that in various embodiments of this application, the magnitudes of the serial numbers of the above processes do not mean the order of execution is prior or posterior. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of this application.

[0071] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0072] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working process of the system described above can refer to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0073] If the described functions are implemented in the form of software function units and sold or used as independent goods, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of software goods. This computer software good is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0074] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claimed rights.

Claims

1. An artificial intelligence-based supply chain logistics information management system, characterized in that, It includes a linear fitting module, a non - linear fitting module, a dual - mode construction module, a delivery verification module, and a management intervention module; The linear fitting module is used to collect the linear scenario information of the supply chain logistics information management system, obtain the linear conventional coefficient according to the linear scenario information, and transmit the linear conventional coefficient to the dual - mode construction module; The non - linear fitting module is used to collect the non - linear scenario information of the supply chain logistics information management system, obtain the non - linear special coefficient according to the non - linear scenario information, and transmit the non - linear special coefficient to the dual - mode construction module; The dual - mode construction module is used to construct a dual - mode management model based on the linear conventional coefficient and the non - linear special coefficient, evaluate the delay status of customs declaration and duty payment in the supply chain logistics information management process, and output the time - cost delay index; The delivery verification module is used to compare the time - cost delay index with a preset time - cost delay threshold to classify the delay status in the supply chain logistics information management process; The management intervention module is used to conduct intervention management according to the classification results; The method for obtaining the linear scenario information is as follows: Obtain the interaction fluctuation coefficient of the supply chain logistics information management system within the cycle time T, and integrate the interaction fluctuation coefficients of the supply chain logistics information management system within several cycle times T into a data set, and label the data set as , where , and is a positive integer, represents the interaction fluctuation coefficient of the supply chain logistics information management system within the -th cycle time T. The calculation expression of the interaction fluctuation coefficient is , where represents the type of goods, is a categorical variable and is transformed into a value through one-hot encoding , where is the numerical serial number of the one-hot encoding, and is a positive integer, represents the seasonal status and represents the date; The method for obtaining the non - linear scenario information is as follows: Obtain the non - linear composite coefficient of the supply chain logistics information management system within the cycle time T, and integrate the non - linear composite coefficients of the supply chain logistics information management system within several cycle times T into a data set, and label the data set as , where , and is a positive integer,[[]]END]] represents the non - linear composite coefficient of the supply chain logistics information management system within the th cycle time T. The calculation expression of the non - linear composite coefficient is . In the formula, is the seasonal state converted into a time - series form, is the number of changes in customs policies, and is a non - negative number; The construction logic of the dual - mode management model is as follows: Define a dual-mode management model by combining weighted average and rule setting. When a specific condition is triggered, use the rule setting to select the model; when the specific condition is not triggered, use the weighted average model. The expression of the dual-mode management model is , where is the time cost delay index, are the weight coefficients of the linear conventional coefficient and the nonlinear special coefficient respectively, and are all positive numbers. If , then output the weighted average result of linear regression and nonlinear fitting. If , then output the result of nonlinear fitting. Among them, is a logical rule defined according to the input feature , and , where, when the goods type is dangerous goods or precision instruments, or the seasonal status is holidays, takes the value of 1, otherwise, takes the value of 0.

2. The supply chain logistics information management system based on artificial intelligence according to claim 1, characterized in that The linear scenario information and the non - linear scenario information are extracted by collecting data. The collected data includes the type of goods, the status of customs policies, the regional number, the seasonal status, the quantity of goods, and the value of goods. The goods are classified into different types according to their nature, and the type of goods is converted into a numerical form by one - hot encoding. The status of customs policies includes policy changes, policy unchanged, and sampling ratio, and the status of customs policies is converted into a numerical form by one - hot encoding. The seasonal status is represented by a date and converted into time - series data.

3. The supply chain logistics information management system based on artificial intelligence according to claim 1, characterized in that, The method for obtaining the linear conventional coefficient according to the linear scenario information is as follows: Calculate the standard deviation of the interaction fluctuation coefficient of the supply chain logistics information management system within several cycle times T. The calculation expression is , where is the average value of the interaction fluctuation coefficient of the supply chain logistics information management system within several cycle times T. The calculation expression is ; Calibrate the customs policy status by fitting a linear regression model using the least squares method , the region number is , the quantity of goods is , the value of goods is , then the expression of the linear regression model is , where is the linear conventional coefficient, are respectively weight coefficients, and are all positive numbers, is a very small positive number representing the error term.

4. The supply chain logistics information management system based on artificial intelligence according to claim 1, characterized in that, The method for obtaining the non - linear special coefficient according to the non - linear scenario information is as follows: Calculate the standard deviation of the non - linear composite coefficient of the supply chain logistics information management system within several cycle times T. The calculation formula is , where is the average value of the non - linear composite coefficient of the supply chain logistics information management system within several cycle times T. The calculation formula is ; Build a random forest model. For each tree in the random forest Train them separately and generate prediction values. Average the prediction values of all trees and output the average prediction value. The mathematical model for calculating the average prediction value is , where is a non-linear special coefficient is the prediction value of the r-th tree in the random forest, r is the tree number and r is a positive integer, w is the total number of trees is the input feature vector. The input features include cargo type, customs policy status, region number, seasonal status, cargo quantity, and cargo value.

5. The supply chain logistics information management system based on artificial intelligence according to claim 1, characterized in that The logic for classifying the delay status in the supply chain logistics information management process is as follows: The preset time cost delay threshold is , and the calculated time cost delay index is compared with the time cost delay threshold . When the time cost delay index is greater than or equal to the time cost delay threshold , mark the process as delayed and define the delay status as the diffusion level; When the time cost delay index is less than the time cost delay threshold the marking process is not delayed, and the delay status is defined as the contraction level.

6. The supply chain logistics information management system based on artificial intelligence according to claim 5, characterized in that The logic for conducting intervention management according to the classification results is as follows: When the delay status is at the diffusion level, inform the management staff that the ground delivery is postponed for waiting; when the delay status is at the contraction level, inform the management staff that the ground delivery departs on time.

Images