User determination method of white shark optimization algorithm based on elite reverse learning and medium

Abstract

The invention discloses a user determination method of a white shark optimization algorithm based on elite reverse learning and a medium. The method comprises the following steps: acquiring current user description information in real time and generating a current fitness evaluation value according to the current user description information; through a Chebyshev chaotic mapping method, a random population position sample obtained based on a white shark optimization algorithm is initialized to obtain a random population position mapping sample; performing position updating processing on each position in the random population position mapping sample to obtain each target updating position; obtaining an updated reverse solution position of each target through an elite reverse learning algorithm; and in combination with the current fitness evaluation value, evaluation parameter calculation is performed on each pair of target update position and target update reverse solution position, and a target final position and a target user are determined and fed back. The problem that screening and recommendation determination of customers are inaccurate in a manual mode is solved, the accuracy of determining the target user is improved, and the property safety is guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a user determination method and medium of a White Shark optimization algorithm based on elite reverse learning. Background Art

[0002] Farmer loans refer to various RMB loans issued by banks to farmers in their service areas, whose loan conditions have been reviewed, for use in operations, consumption, and other purposes. These loans primarily include loans for crop production, livestock farming, and other businesses. Banks' management of farmer loans should be tailored to the dispersed economic operations of their households. The loan purpose, amount, term, and terms should be tailored to local conditions and flexibly managed to meet the working capital needs of individual agricultural operators. To promote agricultural modernization, credit support for agricultural enterprises is encouraged.

[0003] While developing this invention, the inventors discovered the following drawbacks in the existing technology: Currently, banks use certain criteria to determine whether a client has loan potential when screening for farmer loans. Generally, banks assess a client's creditworthiness based on a comprehensive assessment of financial assets, personal liabilities, and settlements. However, manual client screening and recommendation processes are subject to inaccuracies, can easily lead to financial losses, and present a high risk. Summary of the Invention

[0004] The present invention provides a user determination method and medium based on the White Shark optimization algorithm of elite reverse learning, so as to improve the accuracy of target user determination and ensure the safety of property.

[0005] According to one aspect of the present invention, a user determination method of a White Shark optimization algorithm based on elite reverse learning is provided, which includes:

[0006] Acquire current user description information in real time, and generate a current fitness evaluation value based on the current user description information;

[0007] The random population position samples obtained by the White Shark optimization algorithm are initialized by using the pre-optimized Chebyshev chaotic mapping method to obtain random population position mapping samples.

[0008] Using the White Shark optimization algorithm, each position in the random population position mapping sample is updated to obtain an updated position of each target;

[0009] Through the pre-set elite reverse learning algorithm, the reverse solution calculation is performed on each target update position to obtain the target update reverse solution position; wherein, each target update position corresponds to a target update reverse solution position;

[0010] Combined with the current fitness evaluation value, the evaluation parameters are calculated for each pair of target update position and target update reverse solution position, and the target final position is determined based on the calculated evaluation parameters. The target user is then determined based on the target final position and feedback is provided.

[0011] According to another aspect of the present invention, a user determination device based on the White Shark optimization algorithm of elite reverse learning is provided, which includes:

[0012] A current fitness evaluation value generation module is used to obtain current user description information in real time and generate a current fitness evaluation value based on the current user description information;

[0013] The random population position mapping sample determination module is used to initialize the random population position samples obtained based on the White Shark optimization algorithm through the pre-optimized Chebyshev chaotic mapping method to obtain random population position mapping samples;

[0014] A target update position determination module is used to perform position update processing on each position in the random population position mapping sample using the White Shark optimization algorithm to obtain each target update position;

[0015] The target update reverse solution position determination module is used to perform reverse solution calculations on each target update position using a pre-set elite reverse learning algorithm to obtain each target update reverse solution position; wherein each target update position corresponds to a target update reverse solution position;

[0016] The target user determination module is used to calculate the evaluation parameters for each pair of target update position and target update reverse solution position in combination with the current fitness evaluation value, and determine the target final position according to the calculated evaluation parameters, and determine the target user according to the target final position and provide feedback.

[0017] According to another aspect of the present invention, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the user determination method of the White Shark optimization algorithm based on elite reverse learning as described in any embodiment of the present invention is implemented.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the user determination method of the White Shark optimization algorithm based on elite reverse learning described in any embodiment of the present invention when executed.

[0019] The technical solution of the embodiment of the present invention obtains current user description information in real time and generates a current fitness evaluation value based on the current user description information; initializes the random population position samples obtained based on the White Shark optimization algorithm using a pre-optimized Chebyshev chaotic mapping method to obtain random population position mapping samples; updates each position in the random population position mapping samples using the White Shark optimization algorithm to obtain each target update position; performs reverse solution calculation on each target update position using a pre-set elite reverse learning algorithm to obtain each target update reverse solution position; each target update position corresponds to a target update reverse solution position; calculates evaluation parameters for each pair of target update positions and target update reverse solution positions based on the current fitness evaluation value, determines the target final position based on the calculated evaluation parameters, and determines the target user based on the target final position and provides feedback. This solves the problem of inaccurate customer screening and recommendation through manual methods, improves the accuracy of target user determination, and ensures property safety.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 This is a flowchart of a user determination method of a White Shark optimization algorithm based on elite reverse learning provided in accordance with the first embodiment of the present invention;

[0023] Figure 2 is a detailed flow chart of a user determination method of a White Shark optimization algorithm based on elite reverse learning according to a second embodiment of the present invention;

[0024] Figure 3 2 is a schematic structural diagram of a user determination device based on the White Shark optimization algorithm of elite reverse learning according to the third embodiment of the present invention;

[0025] Figure 4 It is a structural diagram of an electronic device provided according to the fourth embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "target", "current", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] Example 1

[0029] Figure 1 A flowchart of a user determination method based on the White Shark optimization algorithm of elite reverse learning is provided for the first embodiment of the present invention. This embodiment is applicable to the situation of determining target users in the bank credit process. The method can be executed by a user determination device based on the White Shark optimization algorithm of elite reverse learning. The user determination device based on the White Shark optimization algorithm of elite reverse learning can be implemented in the form of hardware and / or software.

[0030] Correspondingly, such as Figure 1 As shown, the method includes:

[0031] S110 , obtaining current user description information in real time, and generating a current fitness evaluation value according to the current user description information.

[0032] The current user description information may be information describing the user in various dimensions, and the current fitness evaluation value may be a parameter value for evaluating the user.

[0033] Optionally, the current user description information includes personal factor description information and environmental factor description information; wherein, the personal factor description information includes personal user identity code, personal residential ownership information, personal account flow information, personal vehicle ownership information, personal marital status information, personal debt status information and personal credit description information; wherein, the environmental factor description information includes industry field description information, crop variety description information, precipitation information of the region, altitude information of the region and season description information of the region.

[0034] Specifically, information about personal residential ownership can include whether one has a home or not (whether fully paid or mortgaged). Information about personal account transactions can include whether the total transaction amount is high or low. Information about personal vehicle ownership can include whether one has a vehicle or not (whether fully paid or mortgaged). Information about personal marital status can include whether one is married or single. Information about personal debt status can include whether one has debt or not. Information about personal creditworthiness can include whether one has met the credit standard or not.

[0035] In addition, industry description information includes agriculture, animal husbandry, forestry, fishery, or sideline industries. Crop variety description information is used to describe the specific crop varieties planted by the user. Regional precipitation information can be used to describe the local precipitation level. Regional altitude information can be used to describe the local altitude. Regional season description information can be used to describe the local season.

[0036] Optionally, generating a current fitness evaluation value according to the current user description information includes: calculating the fitness evaluation value H=Max(α.η) according to the current user description information by a preset fitness evaluation value calculation method H=Max(α.η e (t i ,u i )+β.η p (u i ,a i )) to generate the current fitness evaluation value H; where α and β are the weight factors of environmental factors and personal factors respectively; η e (t i ,u i ) is the evaluation function of environmental factors; η p (u i ,a i ) is the evaluation function of personal factors; t i Application time; i Encodes the identity of the individual user; a i It is the user's personal factor description information; i is the individual number parameter variable, which is a natural number.

[0037] In this embodiment, the evaluation function of the environmental factor and the evaluation function of the personal factor can be generated respectively according to the personal factor description information and the environmental factor description information. Among them, the application time can be obtained from the current user description information.

[0038] The weighting factors α and β can be selected based on the importance of personal factors and environmental factors. For example, α can be selected as 0.3 and β can be selected as 0.7. There is no specific restriction here.

[0039] The advantage of this setting is that by calculating the user's current fitness evaluation value, the White Shark optimization algorithm can be better combined to determine high-quality customers.

[0040] S120. Initialize the random population position samples obtained based on the White Shark optimization algorithm using a pre-optimized Chebyshev chaos mapping method to obtain random population position mapping samples.

[0041] The Chebyshev chaos mapping method can be used to uniformly map samples in the search space. The random population position mapping samples can be samples obtained by mapping the random population position samples. The random population position samples can be random samples generated based on the White Shark optimization algorithm.

[0042] Optionally, the method of initializing the random population position samples obtained based on the White Shark optimization algorithm using a pre-optimized Chebyshev chaotic mapping method to obtain the random population position mapping samples includes: determining the random population generation dimension using the evaluation parameter dimension corresponding to the current user description information; obtaining the upper limit random value and the lower limit random value corresponding to the random population generation dimension, and generating the random population position samples in combination with the White Shark optimization algorithm; and performing initialization processing on the random population position samples obtained based on the White Shark optimization algorithm using the pre-optimized Chebyshev chaotic mapping method X. q+1 =cos(kcos -1 (X q )), initialize the random population position sample to obtain the random population position mapping sample X q+1 ; Among them, X q represents a random population position sample; q represents a random parameter, and the value range of q is [0,1].

[0043] Among them, the random population generation dimension is equal to the evaluation parameter dimension. Since the evaluation parameter dimension includes personal factors and environmental factors, the evaluation parameter dimension is 2, so the random population generation dimension is also equal to 2.

[0044] In this embodiment, since no prior conditions are used, the initial distribution of random population position samples is randomly generated, which can easily cause the algorithm to fall into a local optimum prematurely. Therefore, it is necessary to use the Chebyshev chaos mapping method to make the random population position samples in the White Shark optimization algorithm evenly distributed in the search space.

[0045] The advantage of this setting is that the Chebyshev chaos mapping method can generate samples by mapping the random population position samples generated by the white shark optimization algorithm, so that the samples can be evenly distributed in the search space, thereby improving the search performance of the white shark optimization algorithm.

[0046] S130 , performing position update processing on each position in the random population position mapping sample using the White Shark optimization algorithm to obtain each target updated position.

[0047] In this embodiment, the core concept and fundamental approach of the White Shark Optimization Algorithm are inspired by the hunting behavior of great white sharks, including their exceptional hearing and sense of smell as they navigate the ocean and forage. This foraging behavior is mathematically modeled to accommodate the great white shark's optimal balance between exploration and exploitation, enabling the search agent to explore and exploit every potential region of the search space for optimization. The fitness value of each White Shark's location reflects the quality of its foraging, or the probability of obtaining food.

[0048] Optionally, the White Shark optimization algorithm is used to perform position update processing on each position in the random population position mapping sample to obtain each target update position, including: performing position update processing on each position in the random population position mapping sample by the White Shark optimization algorithm to obtain the current position and the next relative optimal individual position corresponding to each position; and calculating the target update position by a predetermined target update position calculation formula. Calculate the target update position corresponding to each position in, is the current number position; is the next relative optimal individual position; rand is the random variable obtained in advance; k is the current number of iterations; k+1 is the next number of iterations.

[0049] For location update, the process of determining the target update location is as follows:

[0050] 1) The great white shark senses the position of its prey through the waves generated by its movement, and uses this to update its own speed and obtain the shark's new position:

[0051] in, is the speed of the i-th great white shark at the k-th iteration; is the speed of the i-th great white shark at the k+1th iteration; is the position of the i-th great white shark in the population at the k-th iteration; V represents the initial value of the velocity vector; n is the population size; represents the global optimal position within the population at the kth time; At the kth iteration, at the optimal position of the kth iteration; C1 and C2 are random values ​​within [0,1]; p max is the maximum value of the intensity factor, which can be set to 1.5; p min is the minimum value of the intensity factor, which can be set to 0.5; p1 is the first intensity factor; p2 is the second intensity factor; μ is the shrinkage factor; K is the maximum number of iterations; τ is the acceleration coefficient, which can be set to τ = 4.125.

[0052] 2) Great white sharks spend most of their time searching for potential prey, where they can find the best or next-best prey, so their position must constantly change. Often, prey will inadvertently leave their scent at a certain location, attracting the white shark to that location. In this case, the white shark navigates to random locations in search of prey, much like a school of fish searching for food. Its position is updated using the following formula:

[0053] in, is the position of the i-th great white shark in the population at the k+1th iteration; u is the upper limit of the search space; l is the lower limit of the search space; is the negation operator; is a bitwise operator; sgn() is a sign-returning function; is a logical vector; f is the wave motion frequency; a0 is the first constant; a1 is the second constant; where a0=6.25; a1=100; f min is the minimum value of the wave motion frequency; f max is the maximum value of the wave motion frequency; where f can be set max =0.75; f min =0.07; a, b, and mv are all intermediate variables.

[0054] 3) Based on the position update of the optimal white shark, since white sharks are group predators, they will prioritize approaching the companion with the best position. The specific approach method is as follows:

[0055] in, For the current individual A relative position relative to the best individual in the population; r1, r2 and r3 are all random values ​​in [0,1]; is the relative distance; s sis the shark's sense of smell and hearing, which guides the shark's position update. a2 is a third constant, wherein a2 can be set to 0.0005.

[0056] Since the white shark is chasing both the final prey and the best individual in the current population, the final update method of the individual is as follows. Specifically, through the above-mentioned white shark optimization algorithm, each position in the random population position mapping sample is updated, and the current position and the next relative best individual position corresponding to each position are obtained respectively; the target position is updated by the pre-set target position calculation formula. Calculate the target update position corresponding to each position.

[0057] S140. Perform reverse solution calculations on each target update position using a pre-set elite reverse learning algorithm to obtain the updated reverse solution position of each target.

[0058] Among them, each target update position corresponds to a target updated reverse solution position.

[0059] Reverse learning involves finding the reverse solution to a feasible solution to a problem, evaluating both the reverse solution and the feasible solution, and selecting the optimal solution as the next generation of individuals, thereby improving the algorithm's optimization efficiency. The elite reverse learning algorithm can prevent the White Shark optimization algorithm from prematurely reaching the global optimum.

[0060] Specifically, the reverse solution calculation is performed on each target update position by using a pre-set elite reverse learning algorithm to obtain the reverse solution position of each target update, including: determining the current feasible solution X corresponding to each target update position i ; Perform reverse solution calculation on each of the current feasible solutions to obtain the current reverse solution Among them, X i =(x1,x2,....,x D ), according to the formula Calculated Where D represents the dimension of the search space; x i Indicates the feasible solution corresponding to each target update position; Indicates the reverse solution of the feasible solution corresponding to each target update position; a i Represents x i The maximum value of b i Represents x i The minimum value of; through the pre-set elite reverse learning algorithm Calculate the current reverse solution corresponding to each target update position respectively to obtain the updated reverse solution position of each target in, is x i of current elite individuals; is the elite reverse solution corresponding to the current elite individual; where, in, Among them, i represents the dynamic upper bound of the search space; zb i represents the dynamic lower bound of the search space; x i best represents the optimal feasible solution corresponding to each target update position; N represents the population size; θ represents a random number uniformly distributed on [0,1].

[0061] In this embodiment, an elite reverse learning algorithm is introduced. During the great white shark hunting process, a reverse learning mechanism is used to generate corresponding reverse solutions for elite individuals. A two-way evaluation guideline is adopted to select mayfly individuals with higher fitness as the next generation population to accelerate the convergence of the algorithm.

[0062] By calculating the updated position of each target, it is necessary to calculate the reverse solution for each updated position of the target. The extreme value of the evaluation function corresponding to all individuals in the current population (that is, the individuals corresponding to each target updated position) is the elite individual, that is, Construct a reverse solution for the current elite individual, obtain the elite reverse solution, and further obtain the updated reverse solution position of each target.

[0063] The advantage of this setting is that it can increase the diversity of the population and select the optimal value from the feasible solution and the reverse solution as the optimal great white shark individual, thereby improving the convergence ability of the algorithm.

[0064] S150. Calculate evaluation parameters for each pair of target update positions and target update reverse solution positions based on the current fitness evaluation value, determine the target final position based on the calculated evaluation parameters, and determine the target user based on the target final position and provide feedback.

[0065] In this embodiment, evaluation parameters can be further calculated for each pair of target update positions and target update reverse solution positions to determine the target final position. Then, the corresponding target user can be further matched based on the target final position, and the target user can be fed back. That is, the target user is a high-quality customer screened out, and credit can be provided to the high-quality customer, thereby reducing the bank's risk and ensuring the bank's property safety.

[0066] The technical solution of the embodiment of the present invention obtains current user description information in real time and generates a current fitness evaluation value based on the current user description information; initializes the random population position samples obtained based on the White Shark optimization algorithm using a pre-optimized Chebyshev chaotic mapping method to obtain random population position mapping samples; updates each position in the random population position mapping samples using the White Shark optimization algorithm to obtain each target update position; performs reverse solution calculation on each target update position using a pre-set elite reverse learning algorithm to obtain each target update reverse solution position; each target update position corresponds to a target update reverse solution position; calculates evaluation parameters for each pair of target update positions and target update reverse solution positions based on the current fitness evaluation value, determines the target final position based on the calculated evaluation parameters, and determines the target user based on the target final position and provides feedback. This solves the problem of inaccurate customer screening and recommendation through manual methods, improves the accuracy of target user determination, and ensures property safety.

[0067] Example 2

[0068] Figure 2 A detailed flow chart of a user determination method for the White Shark optimization algorithm based on elite reverse learning is provided for the second embodiment of the present invention. This embodiment is based on the above embodiments and is refined. In this embodiment, the current fitness evaluation value is combined with the calculation of evaluation parameters for each pair of target update position and target update reverse solution position, and the target final position is determined based on the calculated evaluation parameters for further refinement.

[0069] Correspondingly, such as Figure 2 As shown, the method includes:

[0070] S210 , obtaining current user description information in real time, and generating a current fitness evaluation value according to the current user description information.

[0071] S220. Initialize the random population position samples obtained based on the White Shark optimization algorithm using a pre-optimized Chebyshev chaos mapping method to obtain random population position mapping samples.

[0072] S230: Perform position update processing on each position in the random population position mapping sample using the White Shark optimization algorithm to obtain each target updated position.

[0073] S240. Perform reverse solution calculations on each target update position using a pre-set elite reverse learning algorithm to obtain the updated reverse solution position of each target.

[0074] Among them, each target update position corresponds to a target updated reverse solution position.

[0075] S250. Obtain a pair of target update positions and target update reverse solution positions in sequence, and calculate the evaluation parameters respectively in combination with the current fitness evaluation value to obtain a first fitness evaluation parameter corresponding to the target update position and a second fitness evaluation parameter corresponding to the target update reverse solution position.

[0076] The first fitness evaluation parameter can be used to describe the size of the evaluation parameter for the target update position; the second fitness evaluation parameter can be used to describe the size of the evaluation parameter for the target update reverse solution position. The larger the fitness evaluation parameter, the higher the customer evaluation score, the more suitable the customer is for credit, and the lower the risk the bank needs to bear.

[0077] S260 , determining whether the first fitness evaluation parameter is greater than or equal to the second fitness evaluation parameter; if so, executing S270 ; if not, executing S280 .

[0078] For example, assuming that the first fitness evaluation parameter corresponding to the target update position is P1 and the second fitness evaluation parameter corresponding to the target update reverse solution position is P2, it is necessary to determine the magnitude relationship between P1 and P2.

[0079] S270: Determine the target updated position as the current target final position, and execute S290.

[0080] S280: Determine the updated reverse solution position of the target as the final position of the current target, and execute S290.

[0081] Continuing with the previous example, if P1≥P2, the target updated position can be determined as the current target final position; if P1<P2, the target updated reverse solution position can be determined as the current target final position.

[0082] S290: Determine whether all target update positions and target update reverse solution positions have been traversed. If so, execute S2100; if not, return to execute S250.

[0083] S2100: Combine the determined final positions of the current targets to obtain the final target position.

[0084] S2110: Determine the target user based on the target final location and provide feedback.

[0085] The technical solution of the embodiment of the present invention obtains current user description information in real time and generates a current fitness evaluation value based on the current user description information; initializes the random population position samples obtained based on the White Shark optimization algorithm using a pre-optimized Chebyshev chaotic mapping method to obtain random population position mapping samples; updates each position in the random population position mapping samples using the White Shark optimization algorithm to obtain each target update position; performs reverse solution calculation on each target update position using a pre-set elite reverse learning algorithm to obtain each target update reverse solution position; wherein each target update position corresponds to a target update reverse solution position; and calculates evaluation parameters for each pair of target update positions and target update reverse solution positions based on the current fitness evaluation value to obtain a first fitness evaluation parameter and a second fitness evaluation parameter, thereby determining the size of the fitness evaluation parameters to determine the target final position, and then determines the target user based on the target final position and provides feedback. This improves the accuracy of target user determination, ensures property security, and reduces bank credit risks.

[0086] Example 3

[0087] Figure 3 This is a structural diagram of a user determination device based on the elite reverse learning White Shark optimization algorithm provided in the third embodiment of the present invention. The user determination device based on the elite reverse learning White Shark optimization algorithm provided in this embodiment can be implemented by software and / or hardware, and can be configured in a terminal device or server to implement a user determination method based on the elite reverse learning White Shark optimization algorithm in the embodiment of the present invention. Figure 3 As shown, the device includes: a current fitness evaluation value generation module 310, a random population position mapping sample determination module 320, a target update position determination module 330, a target update reverse solution position determination module 340 and a target user determination module 350.

[0088] The current fitness evaluation value generating module 310 is used to obtain the current user description information in real time and generate the current fitness evaluation value according to the current user description information;

[0089] The random population position mapping sample determination module 320 is used to initialize the random population position samples obtained based on the White Shark optimization algorithm using a pre-optimized Chebyshev chaotic mapping method to obtain random population position mapping samples;

[0090] The target update position determination module 330 is configured to perform position update processing on each position in the random population position mapping sample using the White Shark optimization algorithm to obtain each target update position;

[0091] The target update reverse solution position determination module 340 is used to perform reverse solution calculations on each target update position using a pre-set elite reverse learning algorithm to obtain each target update reverse solution position; wherein each target update position corresponds to a target update reverse solution position;

[0092] The target user determination module 350 is used to calculate evaluation parameters for each pair of target update position and target update reverse solution position based on the current fitness evaluation value, determine the target final position based on the calculated evaluation parameters, and determine the target user based on the target final position and provide feedback.

[0093] The technical solution of the embodiment of the present invention obtains current user description information in real time and generates a current fitness evaluation value based on the current user description information; initializes the random population position samples obtained based on the White Shark optimization algorithm using a pre-optimized Chebyshev chaotic mapping method to obtain random population position mapping samples; updates each position in the random population position mapping samples using the White Shark optimization algorithm to obtain each target update position; performs reverse solution calculation on each target update position using a pre-set elite reverse learning algorithm to obtain each target update reverse solution position; each target update position corresponds to a target update reverse solution position; calculates evaluation parameters for each pair of target update positions and target update reverse solution positions based on the current fitness evaluation value, determines the target final position based on the calculated evaluation parameters, and determines the target user based on the target final position and provides feedback. This solves the problem of inaccurate customer screening and recommendation through manual methods, improves the accuracy of target user determination, and ensures property safety.

[0094] Based on the above embodiments, the current user description information includes personal factor description information and environmental factor description information; wherein, the personal factor description information includes personal user identity code, personal residential ownership information, personal account flow information, personal vehicle ownership information, personal marital status information, personal debt status information and personal credit description information; wherein, the environmental factor description information includes industry field description information, crop variety description information, precipitation information of the region, altitude information of the region and season description information of the region.

[0095] On the basis of the above embodiments, the current fitness evaluation value generating module 310 can be specifically used to: calculate the fitness evaluation value H=Max(α.η) according to the current user description information through the preset fitness evaluation value calculation method H=Max(α.η e (t i ,u i )+β.η p(u i ,a i )) to generate the current fitness evaluation value H; where α and β are the weight factors of environmental factors and personal factors respectively; η e (t i ,u i ) is the evaluation function of environmental factors; η p (u i ,a i ) is the evaluation function of personal factors; t i Application time; i Encodes the identity of the individual user; a i It is the user's personal factor description information; i is the individual number parameter variable, which is a natural number.

[0096] Based on the above embodiments, the random population position mapping sample determination module 320 can be specifically used to: determine the random population generation dimension according to the evaluation parameter dimension corresponding to the current user description information; obtain the upper limit random value and the lower limit random value corresponding to the random population generation dimension, and generate random population position samples in combination with the White Shark optimization algorithm; and generate random population position samples by using the pre-optimized Chebyshev chaotic mapping method X. q+1 =cos(kcos -1 (X q )), initialize the random population position sample to obtain the random population position mapping sample X q+1 ; Among them, X q Represents a random population position sample; q represents a random parameter, and the value range of q is [0,1].

[0097] On the basis of the above embodiments, the target update position determination module 330 can be specifically used to: perform position update processing on each position in the random population position mapping sample by the white shark optimization algorithm, and obtain the current position and the next relative optimal individual position corresponding to each position; through the pre-set target update position calculation formula Calculate the target update position corresponding to each position in, is the current number position; is the next relative optimal individual position; rand is the random variable obtained in advance; k is the current number of iterations; k+1 is the next number of iterations.

[0098] On the basis of the above embodiments, the target updated reverse solution position determination module 340 can be specifically used to: determine the current feasible solution X corresponding to each target updated position. i ; Perform reverse solution calculation on each of the current feasible solutions to obtain the current reverse solution Among them, X i =(x1,x2,....,x D ), according to the formula Calculated Where D represents the dimension of the search space; x i Indicates the feasible solution corresponding to each target update position; Indicates the reverse solution of the feasible solution corresponding to each target update position; a i Represents x i The maximum value of b i Represents x i The minimum value of; through the pre-set elite reverse learning algorithm Calculate the current reverse solution corresponding to each target update position respectively to obtain the updated reverse solution position of each target in, is x i of current elite individuals; is the elite reverse solution corresponding to the current elite individual; where, in, Among them, i represents the dynamic upper bound of the search space; zb i represents the dynamic lower bound of the search space; x i best represents the optimal feasible solution corresponding to each target update position; N represents the population size; θ represents a random number uniformly distributed on [0,1].

[0099] Based on the above embodiments, the target user determination module 350 can be specifically used to: obtain a pair of target update positions and target update reverse solution positions in sequence, and calculate the evaluation parameters respectively in combination with the current fitness evaluation value to obtain a first fitness evaluation parameter corresponding to the target update position and a second fitness evaluation parameter corresponding to the target update reverse solution position; determine whether the first fitness evaluation parameter is greater than or equal to the second fitness evaluation parameter, and if so, determine the target update position as the current target final position; if not, determine the target update reverse solution position as the current target final position; return to execute the operation of obtaining a pair of target update positions and target update reverse solution positions in sequence until all target update positions and target update reverse solution positions are traversed, and combine the determined current target final positions to obtain the target final position.

[0100] The user determination device of the White Shark optimization algorithm based on elite reverse learning provided in an embodiment of the present invention can execute the user determination method of the White Shark optimization algorithm based on elite reverse learning provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0101] Example 4

[0102] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement the fourth embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0103] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0104] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0105] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the user determination method of the White Shark optimization algorithm based on elite reverse learning.

[0106] In some embodiments, the user determination method of the White Shark optimization algorithm based on elite reverse learning can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the user determination method of the White Shark optimization algorithm based on elite reverse learning described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the user determination method of the White Shark optimization algorithm based on elite reverse learning by any other appropriate means (for example, by means of firmware).

[0107] The method includes: obtaining current user description information in real time, and generating a current fitness evaluation value based on the current user description information; initializing a random population position sample obtained based on a white shark optimization algorithm through a pre-optimized Chebyshev chaotic mapping method to obtain a random population position mapping sample; performing position update processing on each position in the random population position mapping sample through the white shark optimization algorithm to obtain each target update position; performing reverse solution calculation on each target update position through a pre-set elite reverse learning algorithm to obtain each target update reverse solution position; wherein each target update position corresponds to a target update reverse solution position; combining the current fitness evaluation value, calculating evaluation parameters for each pair of target update positions and target update reverse solution positions, determining the target final position based on the calculated evaluation parameters, and determining the target user based on the target final position and providing feedback.

[0108] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0109] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0110] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0111] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0112] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0113] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0114] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0115] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

[0116] Example 5

[0117] Embodiment 5 of the present invention also provides a computer-readable storage medium, wherein the computer-readable instructions are used to execute a user determination method based on the White Shark optimization algorithm of elite reverse learning when executed by a computer processor, the method comprising: obtaining current user description information in real time, and generating a current fitness evaluation value based on the current user description information; initializing the random population position sample obtained based on the White Shark optimization algorithm through a pre-optimized Chebyshev chaos mapping method to obtain a random population position mapping sample; performing position update processing on each position in the random population position mapping sample through the White Shark optimization algorithm to obtain each target update position; performing reverse solution calculation on each target update position through a pre-set elite reverse learning algorithm to obtain each target update reverse solution position; wherein each target update position corresponds to a target update reverse solution position; calculating evaluation parameters for each pair of target update positions and target update reverse solution positions in combination with the current fitness evaluation value, determining the target final position based on the calculated evaluation parameters, and determining the target user based on the target final position and providing feedback.

[0118] Of course, the embodiment of the present invention provides a computer-readable storage medium, and its computer-executable instructions are not limited to the method operations described above, and can also execute related operations in user determination of the White Shark optimization algorithm based on elite reverse learning provided by any embodiment of the present invention.

[0119] Through the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented with the help of software and necessary general-purpose hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0120] It is worth noting that in the above-mentioned user-determined embodiment of the White Shark optimization algorithm based on elite reverse learning, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0121] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A user determination method based on the White Shark optimization algorithm of elite reverse learning, characterized in that: include: Acquire current user description information in real time, and generate a current fitness evaluation value based on the current user description information; The random population position samples obtained by the White Shark optimization algorithm are initialized by using the pre-optimized Chebyshev chaotic mapping method to obtain random population position mapping samples. Using the White Shark optimization algorithm, each position in the random population position mapping sample is updated to obtain an updated position of each target; Through the pre-set elite reverse learning algorithm, the reverse solution calculation is performed on each target update position to obtain the target update reverse solution position; wherein, each target update position corresponds to a target update reverse solution position; Combined with the current fitness evaluation value, the evaluation parameters are calculated for each pair of target update position and target update reverse solution position, and the target final position is determined based on the calculated evaluation parameters. The target user is determined based on the target final position and feedback is given.

2. The method according to claim 1, characterized in that The current user description information includes personal factor description information and environmental factor description information; Among them, personal factor description information includes personal user identity code, personal residence ownership information, personal account flow information, personal vehicle ownership information, personal marital status information, personal debt status information and personal credit description information; The environmental factor description information includes industry field description information, crop variety description information, precipitation information of the region, altitude information of the region and season description information of the region.

3. The method according to claim 2, characterized in that Generating a current fitness evaluation value according to the current user description information includes: According to the current user description information, the fitness evaluation value calculation method H=Max(α.η) is preset. e (t i ,u i )+β.η p (u i ,a i )) Generate the current fitness evaluation value H; Among them, α and β are the weight factors of environmental factors and personal factors respectively; η e (t i ,u i ) is the evaluation function of environmental factors; η p (u i ,a i ) is the evaluation function of personal factors; t i Application time; i Encodes the identity of the individual user; a i It is the user's personal factor description information; i is the individual number parameter variable, which is a natural number.

4. The method according to claim 3, characterized in that The random population position samples obtained based on the White Shark optimization algorithm are initialized by the pre-optimized Chebyshev chaotic mapping method to obtain random population position mapping samples, including: Determine the random population generation dimension by the evaluation parameter dimension corresponding to the current user description information; Obtaining upper and lower random value limits corresponding to the random population generation dimensions, respectively, and combining them with the White Shark optimization algorithm to generate random population position samples; Through the pre-optimized Chebyshev chaos mapping method X q+1 =cos(kcos -1 (X q )), initialize the random population position sample to obtain the random population position mapping sample X q+1 ; Among them, X q represents a random population position sample; q represents a random parameter, and the value range of q is [0,1].

5. The method according to claim 4, characterized in that The White Shark optimization algorithm is used to perform position update processing on each position in the random population position mapping sample to obtain each target update position, including: By using the White Shark optimization algorithm, each position in the random population position mapping sample is updated to obtain the current position and the next relative optimal individual position corresponding to each position; Update the position calculation formula by pre-target Calculate the target update position corresponding to each position in, is the current number position; is the next relative optimal individual position; rand is the random variable obtained in advance; k is the current number of iterations; k+1 is the next number of iterations.

6. The method according to claim 5, characterized in that The pre-set elite reverse learning algorithm is used to perform reverse solution calculations on each target update position to obtain the updated reverse solution position of each target, including: Determine the current feasible solution X corresponding to each target update position i ; Perform reverse solution calculation on each of the current feasible solutions to obtain the current reverse solution Among them, X i =(x1,x2,....,x D ), according to the formula Calculated Where D represents the dimension of the search space; x i Indicates the feasible solution corresponding to each target update position; Indicates the reverse solution of the feasible solution corresponding to each target update position; a i Represents x i The maximum value of b i Represents x i The minimum value of Through the pre-set elite reverse learning algorithm , calculate the current reverse solution corresponding to each target update position, and obtain the updated reverse solution position of each target in, is x i of current elite individuals; is the elite reverse solution corresponding to the current elite individual; where, in, Among them, i represents the dynamic upper bound of the search space; zb i represents the dynamic lower bound of the search space; x i best represents the optimal feasible solution corresponding to each target update position; N represents the population size; θ represents a random number uniformly distributed on [0,1].

7. The method according to claim 6, characterized in that The step of calculating evaluation parameters for each pair of target update positions and target update reverse solution positions in combination with the current fitness evaluation value, and determining the target final position based on the calculated evaluation parameters, includes: Obtaining a pair of target update positions and target update reverse solution positions in sequence, and calculating evaluation parameters respectively in combination with the current fitness evaluation value, to obtain a first fitness evaluation parameter corresponding to the target update position and a second fitness evaluation parameter corresponding to the target update reverse solution position; Determine whether the first fitness evaluation parameter is greater than or equal to the second fitness evaluation parameter, and if so, determine the target updated position as the current target final position; if not, determine the target updated reverse solution position as the current target final position; Return to execute the operation of sequentially obtaining a pair of target update positions and target update reverse solution positions until all target update positions and target update reverse solution positions are traversed, and combine the determined final positions of each current target to obtain the final target position.

8. A user determination device based on the White Shark optimization algorithm of elite reverse learning, characterized in that: include: A current fitness evaluation value generation module is used to obtain current user description information in real time and generate a current fitness evaluation value based on the current user description information; The random population position mapping sample determination module is used to initialize the random population position samples obtained based on the White Shark optimization algorithm through the pre-optimized Chebyshev chaotic mapping method to obtain random population position mapping samples; A target update position determination module is used to perform position update processing on each position in the random population position mapping sample using the White Shark optimization algorithm to obtain each target update position; The target update reverse solution position determination module is used to perform reverse solution calculations on each target update position using a pre-set elite reverse learning algorithm to obtain each target update reverse solution position; wherein each target update position corresponds to a target update reverse solution position; The target user determination module is used to calculate the evaluation parameters for each pair of target update position and target update reverse solution position in combination with the current fitness evaluation value, and determine the target final position according to the calculated evaluation parameters, and determine the target user according to the target final position and provide feedback.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the user determination method of the White Shark optimization algorithm based on elite reverse learning according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement a user determination method of a White Shark optimization algorithm based on elite reverse learning according to any one of claims 1 to 7 when executed.

Images