Method and system for identifying cheat price of imported commodity

Abstract

The invention belongs to the field of intelligent algorithm fraud identification, provides an imported commodity price fraud identification method and system, and aims to improve the imported commodity price fraud identification performance of a kernel extreme learning machine by improving the seagull algorithm to optimize the parameters of the kernel extreme learning machine. The method comprises the following steps: firstly, introducing a Sinsoid chaos thought into population initialization, changing a population initialization mode, and enhancing the quality of an initial individual and population diversity; secondly, the migration process of the sea gull population is simulated in a linear decreasing mode of additional variables, and the global optimization capacity is better improved; and thirdly, a Levy flight strategy is introduced to carry out disturbance variation at an optimal solution position, the capability of the algorithm for jumping out of a local space is enhanced, the problems of population diversity, slow convergence speed and easy falling into local optimum of the sea gull algorithm are finally solved, automatic selection of kernel extreme learning machine parameters is realized, and the price fraud identification precision of imported commodities is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent algorithm fraud identification, and in particular to a method and system for identifying price fraud of imported goods. Background Art

[0002] Price fraud in imported goods refers to the importer deliberately concealing the true price of goods by misreporting the quantity or price, misreporting the name of the goods, and false certificates of origin when declaring the import of goods to the customs, in order to evade or reduce the duties and other taxes payable. Customs tax fraud identification mainly faces the following difficulties: First, new formats such as cross-border e-commerce are booming, and the transaction process of these emerging service forms is hidden, which brings challenges to customs tax fraud identification; second, the declaration data of imported goods is incomplete and non-standard, and cannot meet the requirements of customs classification and price management; third, taxpayers evade taxes in a variety of ways, showing the characteristics of groupization, industry, and specialization, such as using similar product names to string tax numbers, which challenges the customs supervision fraud identification ability.

[0003] At present, the research on fraud identification is mainly focused on the fields of credit card transaction fraud identification and e-commerce fraud transaction identification, and the research on imported commodity price fraud identification is not sufficient. Most of the early imported commodity price fraud identification was based on rule-based expert systems, and the judgment rules were generally "if-then" or "if-else-then" trigger conditions. However, with the development of technology, the fraud methods and patterns are constantly changing, and the trigger rules need to be constantly adjusted, which increases the difficulty of fraud identification. Data mining mainly uses machine learning methods to automatically capture fraud patterns from historical data, characterize the probability of "potential fraud" of each transaction, and improve the accuracy of fraud transaction identification with diversity and complexity. Kernel Extreme Learning Machine (KELM) has good nonlinear learning ability and generalization performance, but it is difficult to determine the optimal regularization coefficient and kernel parameter. Based on intelligent algorithms, the parameters of machine learning methods are optimized to improve the adaptability of machine learning methods in various fields. Compared with other optimization algorithms, the Seagull Optimization Algorithm (SOA) has a simple structure, requires few parameters, and is easy to implement, which makes it possible to optimize the parameters of kernel limit learning. However, the Seagull Algorithm lacks population diversity and is prone to fall into local optimality. Summary of the invention

[0004] In order to solve the problem in the prior art that the Seagull algorithm is prone to fall into local optimality when optimizing the parameters of the kernel extreme learning machine model, which makes the kernel extreme learning machine model show large volatility in the recognition accuracy of price fraud of imported goods, affecting the stability and reliability of the model, the present invention proposes a method and system for identifying price fraud of imported goods, which solves the problems of insufficient population diversity, weak global optimization ability and easy to fall into local optimality of the Seagull algorithm, and realizes the optimal selection of parameters of the kernel extreme learning machine, obtains a stable and reliable kernel extreme learning machine, and improves the recognition accuracy of the kernel extreme learning machine for the category of price fraud of imported goods.

[0005] The specific plan is as follows:

[0006] A method for identifying price fraud of imported goods, comprising:

[0007] S1: Data acquisition: Obtain the imported commodity price fraud identification data; the staff determines whether there is price fraud based on the basic information of the imported commodity in each data and labels it; the labeled data is used as the data set for the subsequent steps; the data format in the data set is [basic information of imported commodities, imported commodity price fraud category label];

[0008] S2: Dataset balancing: The data set obtained in S1 is balanced by the SMOTE-CGAN data set balancing method to obtain a balanced data set; the SMOTE-CGAN data set balancing method is to increase the number of minority class samples in the data set by synthesizing new minority class samples;

[0009] S3: Dataset processing: Perform maximum and minimum normalization processing on the data set balanced in S2 to obtain the processed data set;

[0010] S4: Determine the training set, validation set, and test set: Divide the data set processed in S3 into a training set, a validation set, and a test set according to the set ratio;

[0011] S5: Model establishment and training: Establish an imported commodity price fraud identification model based on the improved Seagull algorithm to optimize the kernel extreme learning machine; the imported commodity price fraud identification model is a kernel extreme learning machine, the basic information of the imported commodities in the training set is used as the input of the kernel extreme learning machine, and the imported commodity price fraud category label is used as the output, and the kernel extreme learning machine parameters are initialized by training; the kernel extreme learning machine parameters include regularization coefficients and kernel parameters;

[0012] S6: Optimization model based on Seagull algorithm: Optimize the kernel extreme learning machine parameters by combining the improved Seagull algorithm to obtain the optimal kernel extreme learning machine parameters; set the initialized kernel extreme learning machine parameters to the initial position of the seagull in the Seagull algorithm based on Sinusoidal chaotic mapping, and simulate the migration process of the seagull population in a nonlinear decreasing manner; finally, introduce the Levy flight strategy to perturb and mutate the optimal seagull position, obtain the optimized seagull position as the optimized kernel extreme learning machine parameters, and evaluate the optimized imported commodity price fraud identification model;

[0013] S7: Evaluate the model based on the test set: Input the S4 test set into the imported commodity price fraud identification model optimized by S6 for prediction, and obtain the imported commodity price fraud category; and compare it with the real imported commodity price fraud category label, calculate the accuracy, recall rate, precision rate, and F1 value as model performance evaluation indicators, and evaluate it.

[0014] Preferably, the specific method of optimizing the model based on the Seagull algorithm is:

[0015] S61: Initialization of parameters of improved Seagull algorithm: Setting parameters in improved Seagull algorithm, including population size, maximum number of iterations, search dimension, upper and lower limits of optimization target parameters and spiral coefficient parameters;

[0016] S62: Initializing the initial positions of seagulls using chaotic mapping: Initializing the initial positions of seagulls using Sinusoidal chaotic mapping to obtain the initial positions of multiple seagulls;

[0017] S63: Determine the fitness value of the seagull: Input the S4 training set into the kernel extreme learning machine, and use the initial position of each seagull in S62 to represent the hyperparameters to train the kernel extreme learning machine; then input the S4 validation set into the trained kernel extreme learning machine to obtain the price fraud category of imported goods and calculate the recognition accuracy; use the recognition accuracy as the fitness of each seagull; and determine the global optimal seagull individual by comparing the fitness of all seagulls;

[0018] S64: Update the position of the seagull according to the migration operation: calculate the new position of the seagull after the seagull individual migrates to the global optimal seagull individual; adjust the position of the seagull by the nonlinear control factor A during the migration process;

[0019] S65: Update the position of the seagull according to the attack operation: Update the position of the seagull again according to the attack operation integrated into Levi's flight, and obtain the final updated position of the seagull;

[0020] S66: Find the best individual: According to the final updated position of the seagull in S65, compare the fitness values ​​between the seagull individuals again, and find the global best seagull individual;

[0021] S67: Determine the termination condition: Determine whether the termination condition is met. If so, use the global optimal seagull position as the optimal kernel extreme learning machine parameter; otherwise jump to S64; the termination condition is whether the number of iterations reaches the maximum number of iterations set in S61.

[0022] Preferably, the expression of the Sinusoidal chaotic map is as follows:

[0023]

[0024] Among them, the value range of a is [0,1], and the value range of x is [0,1].

[0025] Preferably, the nonlinear control factor A changes nonlinearly and is affected by the parameter h; the specific expression of the nonlinear control factor A is as follows:

[0026]

[0027] Where h is a random number between [0,1]; M represents the maximum number of iterations; C f represents a positive integer; t represents the number of iterations.

[0028] Preferably, the method for updating the position of the seagull according to the migration operation is:

[0029] A1: Determine the new position of the seagull to avoid collision: The nonlinear control factor A is introduced to adjust the position of the seagull to avoid collision between adjacent seagulls. The formula for determining the new position of the seagull is as follows:

[0030] C s (t) = A × P s (t) (3)

[0031] Among them, C s (t) indicates the new position of the seagull; P s (t) represents the initial position of the seagull; t represents the number of iterations;

[0032] A2: Determine the direction of movement toward the optimal seagull individual: After determining the optimal seagull individual, on the basis of avoiding collision with adjacent seagulls in A1, the seagull moves toward the direction of the optimal seagull individual. At this time, the formula for determining the direction of movement toward the optimal seagull individual is as follows:

[0033] M s (t) = C B ×(P bs (t)-P s (t)) (4)

[0034] C B=2×A 2 ×rand (5)

[0035] Among them, M s (t) represents the direction in which the seagull individual moves toward the optimal seagull individual; C B is a random number used to balance global search and local search; P bs (t) represents the best individual seagull position; where rand is a random number in the range [0,1] that follows a uniform distribution;

[0036] A3: Update the latest position of the seagull: Through the new position of the seagull determined in A1 and the moving direction to the optimal seagull individual determined in A2, the seagull individual reaches the new position during the continuous migration process. The final update formula of the new position is as follows:

[0037] D s (t) = C s (t)+M s (t)(6)

[0038] Among them, D s (t) represents the distance between the seagull and the optimal seagull.

[0039] Preferably, the updating of the seagull position again according to the attack operation integrated into Levi's flight is expressed as:

[0040] P s (t) = D s (t)×x×y×z×levy(a)+P bs (t) (7)

[0041] Among them, levy(a) is a random number vector based on Levy distribution, and x, y, z represent the coordinates of the seagull running in a spiral shape in the air during the attack operation. The specific expression is:

[0042] x=R×cos(i) (8)

[0043] y=R×sin(i) (9)

[0044] z=R×i (10)

[0045] R=u×e iv (11)

[0046] Where R is the spiral radius of the seagull; i is a random number in the range [0,2π] that follows a uniform distribution, representing the attack angle of the seagull; u and v are spiral factors; e is the base of the natural logarithm;

[0047] The Levy flight is a random method with random walk characteristics. The Levy flight can be expressed as:

[0048]

[0049] Among them, parameter α represents a random number, Γ is the Gamma function, Γ(1+a)=a!; r1 and r2 are respectively r1 and σ r2 Normally distributed random numbers.

[0050] Preferably, the method for finding the optimal individual described in step S66 is: using the final updated position of each seagull as the new parameter of the kernel extreme learning machine to update the parameters of the kernel extreme learning machine; inputting the verification set into the kernel extreme learning machine after parameter update to obtain the category of price fraud of imported goods and calculate the recognition accuracy; using the obtained recognition accuracy as the new fitness of each seagull, and comparing them to determine the new global optimal seagull individual.

[0051] Preferably, the kernel extreme learning machine uses a kernel function mapping operation to replace the random mapping method used by the extreme learning machine in the hidden layer, wherein the output equation of the extreme learning machine is:

[0052]

[0053] Among them, I is the unit matrix, C is the regularization coefficient, T is the expected output, h(x) represents the output of the hidden layer, and H represents the output matrix of the hidden layer; the kernel matrix Ω is made by Mercer condition KELM Replace HH T , the kernel matrix Ω KELM It is expressed as:

[0054] Ω KELM =HH T (17)

[0055] Kernel Matrix Ω KELM The element in row i and column j is:

[0056]

[0057] Among them, K(x i ·x j ) is the kernel function. From equations (17) and (18), we can see that HH T The expression is:

[0058]

[0059] h(x)H T Using the kernel function K(x i ,x j )The expression after replacement is:

[0060]

[0061] When h(x)H in equation (16) T Expressed in formula (20), HH T Expressed as (17), the KELM model f KELM (x) The output is:

[0062]

[0063] Where K(g) represents the kernel function, Ω KELM represents the kernel function matrix, xLx N Represents the training samples of price fraud of imported goods.

[0064] Preferably, the kernel function of the kernel extreme learning machine includes:

[0065] Linear kernel function:

[0066]

[0067] Gaussian kernel function:

[0068]

[0069] Among them, ‖·‖ represents the Euclidean distance; σ is the width parameter of the kernel function;

[0070] Polynomial kernel function:

[0071]

[0072] Where b represents the constant term; d represents the degree of the polynomial;

[0073] Sigmoid kernel function:

[0074]

[0075] Wherein, tanh represents the hyperbolic tangent function; β represents the slope parameter, and γ represents the intercept parameter.

[0076] Preferably, it includes:

[0077] Data acquisition module: obtains import commodity price fraud identification data;

[0078] Data preprocessing module: normalize the data to its maximum and minimum values;

[0079] Import commodity price fraud identification module: uses the import commodity price fraud identification model to identify the imported commodity price fraud on the acquired data, and the commodity price fraud identification model is the optimal import commodity price fraud identification model.

[0080] Beneficial effects:

[0081] The present invention proposes a method and system for identifying price fraud of imported goods. By integrating the improved Seagull Optimization Algorithm (SWLSOA) with the sinusoidal chaotic initialization population, nonlinear inertia weight strategy and Levy flight strategy, the problems of poor population diversity, weak global optimization ability and easy falling into local optimum of the Seagull algorithm are solved. Secondly, the regularization coefficient and kernel parameters of the kernel extreme learning machine (KELM model) are optimized by introducing the SWLSOA algorithm. Through simulation comparison experiments, the optimal selection of the parameters of the kernel extreme learning machine is achieved, which avoids the interference of human factors and improves the accuracy of the kernel extreme learning machine in identifying price fraud of imported goods. Specifically:

[0082] (1) The present invention adopts a balancing method for import commodity price fraud identification dataset based on SMOTE-CGAN to generate samples of a small number of categories, achieve effective expansion and balancing of the import commodity price fraud dataset, and improve the accuracy of import commodity price fraud transaction identification.

[0083] (2) The present invention proposes a method for identifying price fraud of imported goods based on the improved Seagull Algorithm Optimized Kernel Extreme Learning Machine (SWLSOA-KELM). Aiming at the problem that the Seagull Algorithm has poor population diversity and is prone to falling into local optimality, firstly, the population is initialized with Sinusoidal chaos, the population initialization method is changed, and the quality of the initial individuals and the population diversity are enhanced; secondly, in the process of optimizing the update of the individual positions of the Seagulls, the additional variable A is used to simulate the migration process of the Seagull population in a linear decreasing manner, so as to better improve the global optimization ability. Finally, the Levy flight strategy is introduced to perform perturbation mutation at the optimal solution position to enhance the algorithm's ability to jump out of the local space.

[0084] (3) The present invention divides the imported commodity price fraud data set into a training set, a validation set, and a test set. The training set and the test set are used to train and optimize the kernel extreme learning machine, respectively, and the regularization coefficient and kernel parameters of the kernel extreme learning machine are updated; the performance of the kernel extreme learning machine after the updated parameters is evaluated through the validation set, and the accuracy of import commodity price fraud recognition is used as the measurement standard, and finally the kernel extreme learning machine with the highest recognition accuracy is determined as the optimal model. The test set is used to test and compare the optimal model, and compare the test results of the kernel extreme learning machine and the Seagull algorithm optimized kernel extreme learning machine (SOA-KELM), and it is found that SWLSOA-KELM has the best recognition effect.

[0085] (4) The present invention optimizes the regularization coefficient and kernel parameters of KELM through SWLSOA, regards the optimized regularization coefficient and kernel parameters as the position of the seagull, regards the optimization process of the regularization coefficient and kernel parameters of the kernel extreme learning machine as the behavior of the seagull migrating and attacking prey in search of abundant food sources, takes the classification accuracy of the verification set as the fitness function, and judges whether the individual position is optimal through the fitness. When the algorithm ends, the optimal regularization coefficient and kernel parameters of KELM are obtained, and the optimal SWLSOA-KELM import commodity price fraud transaction identification method is constructed to achieve accurate identification of import commodity price fraud transactions. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] Figure 1 A flow chart of a method for identifying price fraud of imported goods.

[0087] Figure 2 A flowchart of the overall implementation of a method for identifying price fraud of imported goods.

[0088] Figure 3 Improved Seagull algorithm flow chart.

[0089] Figure 4 Import commodity price fraud identification model based on SWLSOA-KELM. Import commodity price fraud identification confusion matrix.

[0090] Figure 5 An architecture diagram of a system for identifying price fraud on imported goods. DETAILED DESCRIPTION

[0091] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0092] like Figure 1 As shown, the specific steps of the present invention include:

[0093] A method for identifying price fraud of imported goods, comprising:

[0094] S1: Data acquisition: Obtain the imported commodity price fraud identification data; the staff determines whether there is price fraud based on the basic information of the imported commodity in each data and labels it; the labeled data is used as the data set for the subsequent steps; the data format in the data set is [basic information of imported commodities, imported commodity price fraud category label];

[0095] S2: Dataset balancing: The data set obtained in S1 is balanced by the SMOTE-CGAN data set balancing method to obtain a balanced data set; the SMOTE-CGAN data set balancing method is to increase the number of minority class samples in the data set by synthesizing new minority class samples;

[0096] S3: Dataset processing: Perform maximum and minimum normalization processing on the data set balanced in S2 to obtain the processed data set;

[0097] S4: Determine the training set, validation set, and test set: Divide the data set processed in S3 into a training set, a validation set, and a test set according to the set ratio;

[0098] S5: Model establishment and training: Establish an imported commodity price fraud identification model based on the improved Seagull algorithm to optimize the kernel extreme learning machine; the imported commodity price fraud identification model is a kernel extreme learning machine, the basic information of the imported commodities in the training set is used as the input of the kernel extreme learning machine, and the imported commodity price fraud category label is used as the output, and the kernel extreme learning machine parameters are initialized by training; the kernel extreme learning machine parameters include regularization coefficients and kernel parameters;

[0099] S6: Optimization model based on Seagull algorithm: Optimize the kernel extreme learning machine parameters by combining the improved Seagull algorithm to obtain the optimal kernel extreme learning machine parameters; set the initialized kernel extreme learning machine parameters to the initial position of the seagull in the Seagull algorithm based on Sinusoidal chaotic mapping, and simulate the migration process of the seagull population in a nonlinear decreasing manner; finally, introduce the Levy flight strategy to perturb and mutate the optimal seagull position, obtain the optimized seagull position as the optimized kernel extreme learning machine parameters, and evaluate the optimized imported commodity price fraud identification model;

[0100] S7: Evaluate the model based on the test set: Input the S4 test set into the imported commodity price fraud identification model optimized by S6 for prediction, and obtain the imported commodity price fraud category; and compare it with the real imported commodity price fraud category label, calculate the accuracy, recall rate, precision rate, and F1 value as model performance evaluation indicators, and evaluate it.

[0101] like Figure 2 The specific contents include:

[0102] 1. Obtain the dataset for identifying price fraud of imported goods; the data format in the dataset is [basic information of imported goods, category label of price fraud of imported goods];

[0103] Specifically, the basic information of imported goods includes variables such as product number, product name, product specifications, product model, country of production and sales, transaction currency, declared unit price, declared total price, declared quantity, declared measurement unit, total transaction price and whether there is fraud.

[0104] 2. Import commodity price fraud data balance: The acquired data set is balanced by the SMOTE-CGAN data set balancing method to obtain a balanced data set;

[0105] 3. Normalization of the imported goods price fraud dataset:

[0106] The data of the import commodity price fraud index is normalized to [0,1]. The processing process is as follows:

[0107]

[0108] Among them, x(k) is the original data, x(k) min is the minimum value of the original data, x(k) max is the maximum value of the original data, and y(k) is the normalized data.

[0109] 4. Divide the data set into training set, validation set and test set in a certain ratio, and the ratio is set to 7:2:1;

[0110] 5. Use the training set and validation set of imported commodity price fraud to train the kernel extreme learning machine and obtain the optimal kernel extreme learning machine model;

[0111] Establish an import commodity price fraud identification model based on the improved Seagull algorithm to optimize the extreme learning machine, namely the core extreme learning machine; use the training set and validation set of the imported commodity price fraud to train the core extreme learning machine and obtain the optimal core extreme learning machine model;

[0112] Specifically, the basic idea of ​​identifying price fraud of imported goods based on the improved Seagull algorithm and optimized kernel extreme learning machine is to regard the regularization coefficient and kernel parameters of the extreme learning machine as the seagull individuals in the Seagull algorithm, and the optimization process of the regularization coefficient and kernel parameters of the kernel extreme learning machine is regarded as the behavior of seagulls migrating and attacking prey in search of abundant food sources.

[0113] The kernel extreme learning machine replaces the random mapping method used by the extreme learning machine (ELM) in the hidden layer by using the kernel function mapping operation. This can improve the robustness of the model. In addition, this method can also make the ELM more efficient and reduce the computational overhead during training. The output equation of ELM is:

[0114]

[0115] Among them, I is the unit matrix, C is the regularization coefficient, T is the expected output, h(x) represents the output of the hidden layer, and H represents the output matrix of the hidden layer; the kernel matrix Ω is made by Mercer condition KELM Replace HH T , the kernel matrix Ω KELM It is expressed as:

[0116] Ω KELM =HH T (17)

[0117] Kernel Matrix Ω KELM The element in row i and column j is:

[0118]

[0119] Among them, K(x i ·x j ) is the kernel function. From equations (17) and (18), we can see that HH T The expression is:

[0120]

[0121] h(x)H T Using the kernel function K(x i ,x j )The expression after replacement is:

[0122]

[0123] When h(x)H in equation (16) T Expressed in formula (20), HH T Expressed as (17), the KELM model f KELM (x) The output is:

[0124]

[0125] Where K(g) represents the kernel function, Ω KELM represents the kernel function matrix, xLx N Represents the training samples of price fraud of imported goods.

[0126] For the kernel extreme learning machine, different kernel functions are selected to effectively balance the model accuracy and computational complexity. Currently, the commonly used kernel functions of extreme learning machines include linear kernel function, Gaussian kernel function, polynomial kernel function, and Sigmoid kernel function.

[0127] Linear kernel function:

[0128]

[0129] Gaussian kernel function:

[0130]

[0131] Polynomial kernel function:

[0132]

[0133] Sigmoid kernel function:

[0134]

[0135] At present, the usual practice of selecting kernel functions is to select them according to the actual application effects. The identification of price fraud in imported goods has the characteristics of multivariate, nonlinearity, and concealment. The Gaussian function has the advantages of good ability to handle nonlinearity and low computational complexity. Therefore, the Gaussian kernel function is used as the kernel function of the kernel extreme learning machine, which enables it to have good learning and generalization capabilities.

[0136] Specifically, the improved Seagull algorithm implementation process is as follows Figure 3 As shown, including:

[0137] Step 1: Initialize the relevant parameters of the Seagull optimization algorithm. Specifically, the population size is set to 20, the maximum number of iterations is set to 50, the search dimension is set to 2, and the upper and lower limits of the optimization target parameters are: lower limit: lb = [0.01, 1]; upper limit: ub = [50, 10]; spiral coefficient parameters: u and v are used to control the spiral shape, and u and v are set to 1;

[0138] According to formula (1), the population is initialized based on the Sinusoidal chaotic map;

[0139] Specifically, the seagull algorithm uses a random generation method to initialize the population, which will make the seagull population unevenly distributed and affect the subsequent iterative optimization. Chaotic mapping has the characteristics of randomness, ergodicity, and regularity, and can traverse all states without repeating within a certain range. The chaotic sequence can be used to initialize the position of individual seagulls. Sinusoidal mapping is a typical representative of chaotic mapping. The mathematical form of Sinusoidal mapping is as follows:

[0140]

[0141] Among them, the value range of a is [0,1], and the value range of x is [0,1].

[0142] Step 2: Calculate the fitness value of each seagull and mark the best individual;

[0143] Specifically, the classification accuracy of the training set is used as the fitness function, and the calculation formula is as follows (27). The improved Seagull algorithm is used to find the optimal iteration and meet the convergence condition or the maximum number of iterations. The search is terminated to obtain the optimal regularization coefficient and kernel parameter of the kernel extreme learning machine, so that the performance of the imported commodity price fraud identification model optimized by the improved Seagull algorithm and the kernel extreme learning machine is optimal.

[0144]

[0145] Among them, TP represents the number of correctly identified positive examples, FP represents the number of incorrectly classified positive examples, FN represents the number of incorrectly classified negative examples, and TN represents the number of correctly classified negative examples.

[0146] Step 3: Update the seagull migration process according to equations (2), (3), (4), (5) and (6), and calculate the new position of the seagull individual after it moves to the optimal position;

[0147] Specifically, the seagull migration model is designed by imitating the migration behavior of seagull groups. At this stage, three conditions need to be met: avoiding collisions between seagulls, approaching the best seagull individual, and updating the position through the best seagull individual.

[0148] (1) Avoid collision

[0149] In order to avoid collisions between individual seagulls, the seagull algorithm introduces a control factor A. The role of A is to adjust the position of the seagulls to avoid collisions between adjacent seagulls, which can balance the global search and local search to a certain extent. During the seagull migration behavior, if the additional control factor A simulates the migration process of the seagulls in a linear decreasing manner, the optimization ability of the seagull algorithm will be reduced. Therefore, the proposed seagull optimization algorithm with nonlinear decreasing control factors is mainly improved in two aspects: first, the proposed nonlinear additional variable control factor A can achieve a nonlinear early sudden decrease and a slow decrease in the later stage, which can accelerate the convergence ability of the algorithm, better match the actual migration process of the seagull group, and make the algorithm search accuracy more accurate; second, the value of the additional variable A is affected by h, which increases the randomness of the A value. The random index is similar to the mutation factor of the genetic algorithm, which will help maintain the diversity of the population.

[0150] In this method, the value of A shows a nonlinear change trend in the decreasing process, which can better improve the global optimization ability. Each iteration can avoid position conflicts between seagulls and better balance exploration and development.

[0151] The formula for updating the seagull position is as follows:

[0152]

[0153] C s (t) = A × P s (t) (3)

[0154] Among them, C s (t) indicates the new position of the seagull; P s (t) represents the initial position of the seagull; the value of A is obtained by C f Linearly regulated, its value is from C f Linearly decreases to 0, Cf The value of is usually set to 2; t represents the number of iterations; M represents the maximum number of iterations; h represents the random index, which is a random number between [0,1].

[0155] (2) Optimal position and direction

[0156] After determining the migration location, the seagull moves towards the optimal location while avoiding collisions with other individuals. The seagull movement behavior update formula is as follows:

[0157] M s (t) = C B ×(P bs (t)-P s (t)) (4)

[0158] C B =2×A 2 ×rand (5)

[0159] Among them, M s (t) indicates the direction in which the seagull individual moves toward the best seagull individual; C B is a random number used to balance global search and local search; P bs (t) represents the best individual seagull position. Where rand is a random number in the range [0,1] that follows a uniform distribution.

[0160] (3) Best location update

[0161] During the continuous migration process, individual seagulls will continue to move closer to the best position and reach a new position. The formula for updating the new position is as follows:

[0162] D s (t) = C s (t)+M s (t) (6)

[0163] Among them, D s (t) represents the distance between the seagull and the optimal seagull.

[0164] Step 4: Update the attack behavior of the seagull according to equations (7), (8), (9), (10) and (11), and calculate the final updated position of the seagull;

[0165] Specifically, during the process of continuous migration, the seagull will use its own weight and wing flapping frequency to reach the desired height, and constantly change the attack angle and speed according to the actual needs. If the seagull attacks, it will take a spiral shape in the air. At this time, the update formula of the seagull's movement behavior in three-dimensional space is as follows:

[0166] x=R×cos(i) (8)

[0167] y=R×sin(i) (9)

[0168] z=R×i (10)

[0169] R=u×e iv (11)

[0170] Among them, R represents the spiral radius of the seagull; i is a random number in the range [0,2π] that follows a uniform distribution, representing the attack angle of the seagull; u and v are spiral factors, which are usually set to 1; and e is the basis of the natural logarithm.

[0171] In order to enhance the ability of the seagull optimization algorithm to jump out of the local optimum, the Levy flight strategy is integrated into the seagull optimization algorithm. In the process of the seagull population moving to the optimal individual position, the Levy flight is introduced, so that the seagulls have the probability of random walk when they are close to the optimal individual position, which alleviates the disadvantage of the seagull optimization algorithm converging too early, effectively improves the population diversity, and enhances the ability of the algorithm to jump out of the local optimum. The part of the seagull group update position algorithm that is updated after adding the Levy flight is:

[0172] P s (t) = D s (t)×x×y×z×levy(a)+P bs (t) (7)

[0173] Where levy(a) is a random number vector based on Levy distribution.

[0174] Levy flight refers to a random method with random walk characteristics, which is often used in the optimization process of metaheuristic algorithms. In uncertain environments, the Levy flight strategy is conducive to improving the search efficiency of the algorithm. Levy flight can be expressed as:

[0175]

[0176]

[0177] Wherein, parameter α = 1.5, Γ is the Gamma function, Γ(1+a) = a!; r1 and r2 are the standard deviations σ r1 and σ r2 A normally distributed random number, σ r2 =1.

[0178] Step 5: Compare the fitness values ​​of each seagull individual again and find the global optimal seagull individual;

[0179] Step 6: Determine whether the algorithm has reached the maximum number of iterations. If so, the algorithm terminates; otherwise, loop steps 3 to 6 until the algorithm reaches the maximum number of iterations;

[0180] Step 7: Output the best position and fitness value of the seagull;

[0181] Specifically, the final parameters of the best position of Seagull are: regularization coefficient is 49.84, kernel parameter is 1.05

[0182] 6. Input the test set into the optimal kernel extreme learning machine to obtain the classification results of imported commodity price fraud identification;

[0183] 7. Evaluate the fraud recognition category of the test set: Use four statistical indicators, including accuracy, recall, precision, and F1-Score, to evaluate the fraud category results; use the evaluation results to evaluate the recognition performance of the model.

[0184] Specifically, in order to verify the recognition effect of the SWLSOA-KELM model, two models were selected to compare with the SWLSOA-KELM model. Control group 1: Import commodity price fraud recognition model based on KELM; Control group 2: Import commodity price fraud recognition model based on SOA-KELM; Control group 3: Import commodity price fraud recognition model based on SWLSOA-KELM. The collected imported commodity price fraud data set was balanced by SMOTE-CGAN, and then according to the technical solution of the imported commodity price fraud recognition method based on the improved Seagull algorithm optimization provided by the present invention, control group 1 and control group 2 were used respectively to obtain the imported commodity price fraud recognition type, and the fraud recognition type was evaluated and analyzed and compared with the actual value. The results are shown in Table 1.

[0185] Table 1 Comparison of the accuracy of price fraud identification of imported goods by different evaluation models

[0186]

[0187]

[0188] From Table 1 and Figure 4 It can be seen that the SWLSOA-KELM model has the highest overall accuracy rate for identifying price fraud of imported goods, which is 92.50%, while the KELM model has the lowest overall accuracy rate, which is 80.50%. Compared with the standard KELM model, the overall accuracy rates of the SOA-KELM model and the SWLSOA-KELM model increased by 14.91% and 3.45% respectively, indicating that optimizing the KELM parameters through the SOA and SWLSOA algorithms can effectively improve the model's accuracy for identifying price fraud of imported goods.

[0189] In terms of training time, the training time of each model is different. Compared with the KELM model, the training time of the SOA-KELM model and the SWLSOA-KELM model for sample data increases to varying degrees, with training times of 225.73 seconds and 223.0 seconds respectively, indicating that SOA and SWLSOA increase the training time to a certain extent when optimizing KELM parameters.

[0190] A system for identifying price fraud of imported goods, such as Figure 5 As shown, including:

[0191] Data acquisition module: obtains import commodity price fraud identification data;

[0192] Data preprocessing module: normalize the data to its maximum and minimum values;

[0193] Import commodity price fraud identification module: uses the import commodity price fraud identification model to identify the imported commodity price fraud on the acquired data, and the commodity price fraud identification model is the optimal import commodity price fraud identification model.

[0194] Finally, it should be noted that the above is only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred arrangement scheme, a person skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for identifying price fraud of imported goods, characterized in that: S1: Data acquisition: Obtain the imported commodity price fraud identification data; the staff determines whether there is price fraud based on the basic information of the imported commodity in each data and labels it; the labeled data is used as the data set for the subsequent steps; the data format in the data set is [basic information of imported commodities, imported commodity price fraud category label]; S2: Dataset balancing: The data set obtained in S1 is balanced by the SMOTE-CGAN data set balancing method to obtain a balanced data set; the SMOTE-CGAN data set balancing method is to increase the number of minority class samples in the data set by synthesizing new minority class samples; S3: Dataset processing: Perform maximum and minimum normalization processing on the data set balanced in S2 to obtain the processed data set; S4: Determine the training set, validation set, and test set: Divide the data set processed in S3 into a training set, a validation set, and a test set according to the set ratio; S5: Model establishment and training: Establish an imported commodity price fraud identification model based on the improved Seagull algorithm to optimize the kernel extreme learning machine; the imported commodity price fraud identification model is a kernel extreme learning machine, the basic information of the imported commodities in the training set is used as the input of the kernel extreme learning machine, and the imported commodity price fraud category label is used as the output, and the kernel extreme learning machine parameters are initialized by training; the kernel extreme learning machine parameters include regularization coefficients and kernel parameters; S6: Optimization model based on Seagull algorithm: Optimize the kernel extreme learning machine parameters by combining the improved Seagull algorithm to obtain the optimal kernel extreme learning machine parameters; set the initialized kernel extreme learning machine parameters to the initial position of the seagull in the Seagull algorithm based on Sinusoidal chaotic mapping, and simulate the migration process of the seagull population in a nonlinear decreasing manner; finally, introduce the Levy flight strategy to perturb and mutate the optimal seagull position, obtain the optimized seagull position as the optimized kernel extreme learning machine parameters, and evaluate the optimized imported commodity price fraud identification model; S7: Evaluate the model based on the test set: Input the S4 test set into the imported commodity price fraud identification model optimized by S6 for prediction, and obtain the imported commodity price fraud category; The results were compared with the price fraud category labels of real imported goods, and the accuracy, recall, precision, and F1 value were calculated as model performance evaluation indicators and evaluated.

2. A method for identifying price fraud of imported goods based on claim 1, characterized in that: The specific method of optimizing the model based on the Seagull algorithm is: S61: Initialization of parameters of improved Seagull algorithm: Setting parameters in improved Seagull algorithm, including population size, maximum number of iterations, search dimension, upper and lower limits of optimization target parameters and spiral coefficient parameters; S62: Initializing the initial positions of seagulls using chaotic mapping: Initializing the initial positions of seagulls using Sinusoidal chaotic mapping to obtain the initial positions of multiple seagulls; S63: Determine the fitness value of the seagull: Input the S4 training set into the kernel extreme learning machine, and use the initial position of each seagull in S62 to represent the hyperparameters to train the kernel extreme learning machine; then input the S4 validation set into the trained kernel extreme learning machine to obtain the price fraud category of imported goods and calculate the recognition accuracy; use the recognition accuracy as the fitness of each seagull; and determine the global optimal seagull individual by comparing the fitness of all seagulls; S64: Update the position of the seagull according to the migration operation: calculate the new position of the seagull after the seagull individual migrates to the global optimal seagull individual; During the migration process, the position of the gulls is adjusted by the nonlinear control factor A; S65: Update the position of the seagull according to the attack operation: Update the position of the seagull again according to the attack operation integrated into Levi's flight, and obtain the final updated position of the seagull; S66: Find the best individual: According to the final updated position of the seagull in S65, compare the fitness values ​​between the seagull individuals again, and find the global best seagull individual; S67: Determine the termination condition: Determine whether the termination condition is met. If so, use the global optimal seagull position as the optimal kernel extreme learning machine parameter; otherwise jump to S64; the termination condition is whether the number of iterations reaches the maximum number of iterations set in S61.

3. A method for identifying price fraud of imported goods according to claim 2, characterized in that: The expression of the Sinusoidal chaotic map is as follows: Among them, the value range of a is [0,1], and the value range of x is [0,1].

4. A method for identifying price fraud of imported goods according to claim 2, characterized in that: The nonlinear control factor A changes nonlinearly and is affected by the parameter h. The specific expression of the nonlinear control factor A is as follows: Where h is a random number between [0,1]; M represents the maximum number of iterations; C f represents a positive integer; t represents the number of iterations.

5. A method for identifying price fraud of imported goods according to claim 2, characterized in that: The method for updating the position of seagulls according to the migration operation is: A1: Determine the new position of the seagull to avoid collision: The nonlinear control factor A is introduced to adjust the position of the seagull to avoid collision between adjacent seagulls. The formula for determining the new position of the seagull is as follows: C s (t)=A×P s (t) (3) Among them, C s (t) indicates the new position of the seagull; P s (t) represents the initial position of the seagull; t represents the number of iterations; A2: Determine the direction of movement toward the optimal seagull individual: After determining the optimal seagull individual, on the basis of avoiding collision with adjacent seagulls in A1, the seagull moves toward the direction of the optimal seagull individual. At this time, the formula for determining the direction of movement toward the optimal seagull individual is as follows: M s (t)=C B ×(P bs (t)-P s (t)) (4) C B =2×A 2 ×rand (5) Among them, M s (t) represents the direction in which the seagull individual moves toward the optimal seagull individual; C B is a random number used to balance global search and local search; P bs (t) represents the best individual seagull position; where rand is a random number in the range [0,1] that follows a uniform distribution; A3: Update the latest position of the seagull: Through the new position of the seagull determined in A1 and the moving direction to the optimal seagull individual determined in A2, the seagull individual reaches the new position during the continuous migration process. The final update formula of the new position is as follows: D s (t)=|C s (t)+M s (t)| (6) Among them, D s (t) represents the distance between the seagull and the optimal seagull.

6. A method for identifying price fraud of imported goods according to claim 2, characterized in that: The above-mentioned updating of the position of the seagull again according to the attack operation integrated into Levi's flight is expressed as: P s (t)=D s (t)×x×y×z×levy(a)+P bs (t) (7) Among them, levy(a) is a random number vector based on Levy distribution, and x, y, z represent the coordinates of the seagull running in a spiral shape in the air during the attack operation. The specific expression is: x=R×cos(i) (8) y=R×sin(i) (9) z=R×i (10) R=u×e iv (11) Where R is the spiral radius of the seagull; i is a random number in the range [0,2π] that follows a uniform distribution, representing the attack angle of the seagull; u and v are spiral factors; e is the base of the natural logarithm; The Levy flight is a random method with random walk characteristics. The Levy flight can be expressed as: Among them, parameter α represents a random number, Γ is the Gamma function, Γ(1+a)=a!; r1 and r2 are respectively r1 and σ r2 Normally distributed random numbers.

7. A method for identifying price fraud of imported goods according to claim 2, characterized in that: The method for finding the optimal individual described in step S66 is: using the final updated position of each seagull as the new parameter of the kernel extreme learning machine to update the parameters of the kernel extreme learning machine; inputting the verification set into the kernel extreme learning machine after parameter update to obtain the price fraud category of imported goods and calculate the recognition accuracy; using the obtained recognition accuracy as the new fitness of each seagull, and comparing them to determine the new global optimal seagull individual.

8. A method for identifying price fraud of imported goods according to claim 1, characterized in that: The kernel extreme learning machine uses a kernel function mapping operation to replace the random mapping method used by the extreme learning machine in the hidden layer, wherein the output equation of the extreme learning machine is: Among them, I is the unit matrix, C is the regularization coefficient, T is the expected output, h(x) represents the output of the hidden layer, and H represents the output matrix of the hidden layer; the kernel matrix Ω is made by Mercer condition KELM Replace HH T , the kernel matrix Ω KELM It is expressed as: Oh KELM =HH T (17) Kernel Matrix Ω KELM The element in row i and column j is: Among them, K(x i ·x j ) is the kernel function. From equations (17) and (18), we can see that HH T The expression is: h(x)H T Using the kernel function K(x i ,x j )The expression after replacement is: When h(x)H in equation (16) T Expressed in formula (20), HH T Expressed as (17), the KELM model f KELM (x) The output is: Where K(g) represents the kernel function, Ω KELM represents the kernel function matrix, xL x N Represents the training samples of price fraud of imported goods.

9. A method for identifying price fraud of imported goods according to claim 8, characterized in that: The kernel function of the kernel extreme learning machine includes: Linear kernel function: Gaussian kernel function: Among them, ‖·‖ represents the Euclidean distance; σ is the width parameter of the kernel function; Polynomial kernel function: Where b represents the constant term; d represents the degree of the polynomial; Sigmoid kernel function: Wherein, tanh represents the hyperbolic tangent function; β represents the slope parameter, and γ represents the intercept parameter.

10. An imported commodity price fraud identification system formed based on any of the methods described in claims 1-9, characterized in that: include: Data acquisition module: obtains import commodity price fraud identification data; Data preprocessing module: normalize the data to its maximum and minimum values; Import commodity price fraud identification module: uses the imported commodity price fraud identification model to identify the imported commodity price fraud on the acquired data, and the commodity price fraud identification model is the optimal imported commodity price fraud identification model.

Images