Data processing method and device, electronic equipment and storage medium

Abstract

The invention discloses a data processing method and device, electronic equipment and a storage medium. According to the scheme, at least one to-be-selected item corresponding to a target user is obtained; determining a plurality of target functions corresponding to the at least one item to be selected, wherein the plurality of target functions at least comprise a first target function corresponding to an item return attribute, a second target function corresponding to an item risk attribute and a third target function corresponding to an item resource flow attribute; optimizing the plurality of objective functions according to a multi-objective particle swarm optimization algorithm to determine at least one type of target project configuration information when a constraint condition is satisfied, the target project configuration information comprising target project weight information corresponding to at least one to-be-selected project; and based on the at least one type of target item configuration information, generating item selection reference information for the target user. Accurate item selection reference information is provided, the method can adapt to complex market environment changes, and the item selection requirement of the target user is met.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a data processing method, apparatus, electronic device, and storage medium. Background Technology

[0002] With economic development and the diversification of user needs, existing project configuration solutions are unable to meet diverse user requirements.

[0003] Currently, project configuration solutions are primarily provided to users through the mean-variance model, based on resource portfolio theory. However, this approach has limitations. The mean-variance model only addresses a single need and cannot simultaneously satisfy other needs. Furthermore, this model provides resource configuration solutions based on hypothetical scenarios using historical data, making it difficult to cope with future dynamic changes and introducing certain project selection risks. Summary of the Invention

[0004] This invention provides a data processing method, apparatus, electronic device, and storage medium, which provides accurate project selection reference information, can adapt to complex market environment changes, and meet the project selection needs of target users.

[0005] According to one aspect of the present invention, a data processing method is provided, the method comprising:

[0006] Obtain at least one selectable item corresponding to the target user;

[0007] Determine multiple objective functions corresponding to at least one candidate project, wherein the multiple objective functions include at least: a first objective function corresponding to the project return attribute, a second objective function corresponding to the project risk attribute, and a third objective function corresponding to the project resource flow attribute;

[0008] The multi-objective particle swarm optimization algorithm is used to optimize multiple objective functions in order to determine at least one objective item configuration information when the constraints are met. The objective item configuration information includes: objective item weight information corresponding to at least one candidate item.

[0009] Based on at least one target project configuration information, generate project selection reference information for the target user.

[0010] According to another aspect of the present invention, a data processing apparatus is provided, the apparatus comprising:

[0011] The project acquisition module is used to acquire at least one selectable project corresponding to the target user;

[0012] The objective function determination module is used to determine multiple objective functions corresponding to at least one candidate project, wherein the multiple objective functions include at least: a first objective function corresponding to the project return attribute, a second objective function corresponding to the project risk attribute, and a third objective function corresponding to the project resource flow attribute;

[0013] The project configuration information determination module is used to optimize multiple objective functions based on the multi-objective particle swarm optimization algorithm, so as to determine at least one target project configuration information when the constraints are met. The target project configuration information includes: target project weight information corresponding to at least one candidate project.

[0014] The reference information generation module is used to generate project selection reference information for target users based on at least one target project configuration information.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory that is communicatively connected to at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the data processing method of any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided that stores computer instructions for causing a processor to execute and implement the data processing method of any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, characterized in that the computer program, when executed by a processor, implements a data processing method as described in any embodiment of the present invention.

[0021] The technical solution of this invention provides data support for subsequent function optimization by acquiring at least one selectable item corresponding to a target user and determining multiple objective functions corresponding to the at least one selectable item. Multiple objective functions are optimized using a multi-objective particle swarm optimization algorithm to determine at least one target item configuration information while satisfying constraints. Through the multi-objective particle swarm optimization algorithm and constraints, conflicts between multiple objectives can be effectively handled, ensuring a balance between the relationships between objectives during optimization and achieving a more ideal optimization effect. Based on the configuration information of at least one target item, reference information for project selection for the target user is generated, providing the target user with an optimal project selection scheme, allowing the target user to select suitable projects according to actual needs. This invention solves the problem that existing technologies, which provide resource allocation schemes based on hypothetical scenarios using historical data, have certain limitations, making it difficult to cope with future dynamic changes and posing certain project selection risks. By balancing the relationships between multiple objectives through the multi-objective particle swarm optimization algorithm, accurate project selection reference information is provided, which can adapt to complex market environment changes, meeting the project selection needs of the target user while controlling and reducing project selection risks.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of a data processing method provided in an embodiment of the present invention;

[0025] Figure 2 This is a flowchart of a data processing method provided in an embodiment of the present invention;

[0026] Figure 3 This is an example diagram illustrating the dominance of solution S1 over solution S2 provided in an embodiment of the present invention;

[0027] Figure 4 This is an example diagram showing that solutions S1 and S2 are mutually exclusive, provided in an embodiment of the present invention.

[0028] Figure 5 This is a schematic diagram of the structure of a data processing device provided in an embodiment of the present invention;

[0029] Figure 6 This is a schematic diagram of the structure of an electronic device that implements the data processing method of the present invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] Example 1

[0033] Figure 1 This is a flowchart of a data processing method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where project selection reference information is determined for a target user using a multi-objective particle swarm optimization algorithm. This method can be executed by a data processing device, which can be implemented in hardware and / or software, and can be configured in electronic devices such as mobile phones, computers, or servers. Figure 1 As shown, the method includes:

[0034] S110. Obtain at least one selectable item corresponding to the target user.

[0035] The target user can be any user who needs reference information for project selection. It should be noted that the technical solution provided in this embodiment of the invention can be used to determine the corresponding project selection reference information for each user; here, the current user is used as the target user for explanation. The project to be selected can be a project requiring resource investment, i.e., an investment project.

[0036] Specifically, at least one selectable item for the target user is obtained, providing data support for subsequently determining the selection weight information for each selectable item.

[0037] S120. Determine multiple objective functions corresponding to at least one candidate project, wherein the multiple objective functions include at least: a first objective function corresponding to the project return attribute, a second objective function corresponding to the project risk attribute, and a third objective function corresponding to the project resource flow attribute.

[0038] The objective function can be a mathematical function that needs to be minimized or maximized in an optimization problem. The objective function can be linear or nonlinear. The first objective function, corresponding to the project return attribute, can be a function characterizing the expected return attribute of at least one candidate project. The project return attribute can be understood as the project acquisition value of the candidate project, i.e., the rate of return. The second objective function, corresponding to the project risk attribute, can be used to characterize the risk volatility of at least one candidate project. The project risk attribute can be understood as the project risk volatility of the selected project. The third objective function, corresponding to the project resource liquidity attribute, can be used to characterize the monetization or market circulation of at least one candidate project. The project resource liquidity attribute is used to characterize the monetization or market circulation of the candidate project.

[0039] Specifically, at least one objective function is determined for the project return attribute, the second objective function for the project risk attribute, and the third objective function for the project resource flow attribute. By optimizing the first, second, and third objective functions, when the function value corresponding to the first objective function is maximized, the function value corresponding to the second objective function is minimized, and the function value corresponding to the third objective function is maximized, reference information for project selection is determined, providing data support for subsequent function optimization.

[0040] In this embodiment of the invention, the method for determining multiple objective functions corresponding to at least one candidate project may be as follows: Based on the expected return attribute corresponding to each candidate project, a first objective function associated with project weight information is determined; wherein, the expected return attribute is used to characterize the average return attribute of the candidate project within a first preset time period; the covariance value of the average return attribute of each candidate project and other candidate projects within a second preset time period is determined, and based on the covariance value, a project volatility function associated with project weight information is determined, and the project volatility function is used as the second objective function; based on the ratio of the transaction volume of each candidate project to the free trade resource information within a third preset time period, a project resource flow attribute of each candidate project is determined, and based on the project resource flow attribute, a third objective function associated with project weight information is determined.

[0041] The expected return attribute can be used to characterize the average return attribute of the projects to be selected within a first preset time period. The first preset time period can be a pre-set time length. The average return attribute can be the average project return attribute of the projects to be selected within the first preset time period. Project weight information, i.e., the resource investment weight for a project, can be used to characterize the proportion of resources invested in the projects to be selected. For example, if there are at least three projects to be selected, namely project A, project B, and project C, and the resource investment proportion for project A can be 30%, then the project weight information corresponding to project A is 30%.

[0042] Optionally, the expected return attribute of the selected projects can be determined by calculating the average return attribute over the past first preset period, or by predicting the average project return attribute over the future first preset period using time series models or factor models, or by referring to the return attribute predictions of relevant professional analysts. For example, taking the average return attribute over the first preset period as the annualized rate of return over 3 years, this can be calculated by using the annualized rate of return of the selected projects over the past 3 years and using this annualized rate of return as the expected return attribute. Alternatively, the expected return attribute can be determined by predicting the average return attribute corresponding to the future first preset period using time series models such as the Autoregressive Integrated Moving Average (ARIMA) model or Long Short-Term Memory (LSTM) networks, or the Fama-French three-factor model.

[0043] The second preset duration can be a pre-set time period. The length of the second preset duration can be the same as or different from the first preset duration. The covariance value of the average return attribute can be the covariance value between the average return attribute of each candidate project and the average return attribute of other candidate projects. For example, with a second preset duration of 3 years, the covariance value could be the daily return rate covariance over the past 3 years. The project volatility function can be a function used to characterize the risk volatility of at least one candidate project.

[0044] The third preset duration can be a pre-set time period. This third preset duration can be the same as or different from the first or second preset duration. Transaction volume represents the number of successful transactions of the selected projects within the third preset duration. Free trade resource information represents the portion of the selected projects that can be freely traded and transferred in. Project resource flow attributes represent the monetization or market circulation status of the selected projects. Optionally, the project resource flow attribute can be the reciprocal of the ratio of transaction volume to free trade resource information.

[0045] Specifically, the average return attribute of each candidate item is determined over a first preset time period, and this average return attribute is defined as the expected return attribute of the candidate item. Based on the expected return attribute of at least one candidate item, a first objective function associated with the item weight information is determined. Optionally, the first objective function can be expressed as follows:

[0046]

[0047] Among them, w i R represents the project weight information for the i-th project to be selected, which is an unknown quantity. i Let f1 represent the expected return attribute of the i-th candidate project, and f1 represent the function value of the first objective function, which characterizes the total project return attribute corresponding to all candidate projects. n represents the number of candidate projects.

[0048] Determine the covariance between the average return attribute of each candidate project and the average return attribute of other candidate projects. Based on the covariance, determine the project volatility function, i.e., the second objective function, associated with the project weight information. The second objective function can be expressed as:

[0049]

[0050] Among them, w i σ represents the project weight information of the i-th candidate project, which is an unknown quantity. ij w represents the covariance of the average return attribute between the i-th and j-th candidate items. j represents the project weight information of the j-th candidate project, which is an unknown quantity. f2 represents the function value of the second objective function, used to characterize the total project fluctuation corresponding to all candidate projects, and to measure the risk of project selection. n represents the number of candidate projects.

[0051] The ratio of the transaction volume to the free trade resource information of each candidate project within a third preset time period is determined, and the reciprocal of this ratio is used as the project resource flow attribute of that candidate project. Based on the project resource flow attribute of each candidate project, a third objective function associated with the project weight information is determined. Optionally, the third objective function can be expressed as:

[0052]

[0053] Among them, w i This represents the weight information of the i-th candidate item, which is an unknown quantity. n represents the number of candidate items. L i This represents the resource flow attribute of the i-th project to be selected.

[0054] S130. Optimize multiple objective functions according to the multi-objective particle swarm optimization algorithm to determine at least one objective item configuration information when the constraints are met. The objective item configuration information includes: objective item weight information corresponding to at least one candidate item.

[0055] Multi-Objective Particle Swarm Optimization (MOPSO) is a swarm intelligence-based optimization technique, an extension of the classic Particle Swarm Optimization (PSO) algorithm, used to solve multi-objective optimization problems. PSO is an optimization algorithm that simulates the behavior of swarms in nature. In PSO, solutions are viewed as "particles," each moving in the solution space and searching for the optimal solution by updating its velocity. Particles adjust their positions based on their own historical best position (pBest) and the swarm's historical best position (gBest). Through swarm cooperation and information sharing, MOPSO finds the globally optimal solution or a near-optimal solution in the solution space. Multi-objective optimization problems involve simultaneously optimizing multiple objective functions. In this embodiment of the invention, the optimization requirements for different objective functions are different; therefore, multi-objective optimization problems need to balance these optimization requirements to optimize each objective function as much as possible.

[0056] The constraints may include: the sum of the project weight information of at least one candidate project is 1; the project weight information of each candidate project does not exceed a preset weight threshold; and the project weight information of a candidate project that belongs to the project blacklist is 0.

[0057] Optionally, the sum of the weight information of at least one candidate item being 1 can be represented as:

[0058]

[0059] Among them, w iThis represents the weight information of the i-th candidate project. n represents the number of candidate projects. The preset weight threshold can be a pre-set maximum resource allocation ratio for each candidate project. For example, the preset weight threshold could be 30%, i.e., w i ∈[0,0.3]. The project blacklist may include at least one non-compliant or high-risk project.

[0060] Target project configuration information can be used to represent the project weight information of at least one candidate project. The target project configuration information includes the target project weight information corresponding to at least one candidate project. The target project weight information can be the project weight information of the candidate projects determined after optimizing multiple objective functions.

[0061] Specifically, multiple objective functions are optimized using a multi-objective particle swarm optimization algorithm. Based on constraints such as the sum of the weights of all candidate items being 1, the weight of each candidate item not exceeding a preset weight threshold, and the weight of candidate items in the blacklist being 0, at least one target item configuration is determined. Each target item configuration includes the target item weight information for each candidate item.

[0062] S140. Based on at least one target project configuration information, generate project selection reference information for the target user.

[0063] It should be noted that the at least one type of target project configuration information obtained by optimizing multiple objective functions using a multi-objective particle swarm optimization algorithm includes the target project weight information for each of the candidate projects. Different target project configuration information emphasize different attributes. For example, given target project configuration information a, b, and c, target project configuration information a might be more advantageous in terms of project return attributes compared to the other two. Target project configuration information c might be more advantageous in terms of project risk attributes compared to the other two. Target project configuration information b might be more advantageous in terms of project resource flow attributes compared to the other two. Project selection reference information can be determined based on the attributes emphasized by each type of target project configuration information.

[0064] Specifically, based on the identified configuration information for at least one target project, the attribute information emphasized by each target project configuration is determined. Based on each target project configuration and its corresponding emphasized attribute information, project selection reference information for the target user is generated, enabling the target user to determine the appropriate resource allocation ratio (project weight information) for each candidate project that meets their actual needs.

[0065] In this embodiment of the invention, the method for generating project selection reference information for target users may be as follows: evaluating at least one type of target project configuration information to determine the attribute reference information of each type of target project configuration information in the project return attribute, project risk attribute, and project resource flow attribute; and generating project selection reference information based on the attribute reference information and the target project configuration information.

[0066] The attribute reference information is used to characterize which attribute among project return, project risk, or project resource flow attributes the target project configuration information is more advantageous. Project selection reference information can include each type of target project configuration information and the corresponding attribute reference information.

[0067] Specifically, for at least one type of target project configuration information, each type of target project configuration information is evaluated to determine attribute reference information for each type of target project configuration information in terms of project return attribute, project risk attribute, and project resource flow attribute. Based on each type of target project configuration information and the corresponding attribute reference information, project selection reference information for the target user is generated.

[0068] The technical solution of this embodiment obtains at least one selectable item corresponding to the target user and determines multiple objective functions corresponding to the at least one selectable item, providing data support for subsequent function optimization. Multiple objective functions are optimized using a multi-objective particle swarm optimization algorithm to determine at least one target item configuration information while satisfying constraints. Through the multi-objective particle swarm optimization algorithm and constraints, conflicts between multiple objectives can be effectively handled, ensuring a balance between the relationships between objectives during optimization and achieving a more ideal optimization effect. Based on the configuration information of at least one target item, reference information for project selection for the target user is generated, providing the target user with an optimal project selection scheme, allowing the target user to select suitable projects according to actual needs. This invention solves the problem that existing technologies, which provide resource allocation schemes based on hypothetical scenarios using historical data, have certain limitations, are difficult to cope with future dynamic changes, and have certain project selection risks. By balancing the relationships between multiple objectives through the multi-objective particle swarm optimization algorithm, accurate project selection reference information is provided, which can adapt to complex market environment changes, meeting the project selection needs of the target user while controlling and reducing project selection risks.

[0069] Example 2

[0070] Figure 2This is a flowchart of a data processing method provided in Embodiment 2 of the present invention. This embodiment refines the step of "optimizing multiple objective functions according to a multi-objective particle swarm optimization algorithm to determine at least one objective item configuration information when constraints are met" based on the above embodiments. Specific implementation details can be found in the technical solution of this embodiment. Technical terms that are the same as or corresponding to those in the above embodiments will not be repeated here. Figure 2 As shown, the method includes:

[0071] S210. Obtain at least one selectable item corresponding to the target user.

[0072] S220. Determine multiple objective functions corresponding to at least one candidate item.

[0073] Among them, the multiple objective functions include at least: a first objective function corresponding to the project return attribute, a second objective function corresponding to the project risk attribute, and a third objective function corresponding to the project resource flow attribute.

[0074] S230. Determine the initial particle position and particle velocity in the multi-objective particle swarm optimization algorithm, wherein the initial particle position corresponds to the initial project weight information of at least one project to be selected, and the particle velocity is used to characterize the update information of the project weight information.

[0075] The initial particle position corresponds to the initial item weight information of at least one item to be selected. The initial item weight information can be the initially set item weight information of the items to be selected. The particle velocity represents the update information of the item weight information.

[0076] Specifically, particle positions and velocities are initialized using a multi-objective particle swarm optimization algorithm to obtain initial particle positions and velocities. The initial particle positions correspond to the initial weight information of at least one candidate item, and the particle velocities represent the updated information of the item weights.

[0077] For example, by initializing the particle position and particle velocity using a multi-objective particle swarm optimization algorithm, the determined initial particle position can be expressed as:

[0078] x k =[w1,w2,...,w n ]

[0079] Where, x k Indicates the initial particle position, w1 represents the initial weight information of the first candidate item, w2 represents the initial weight information of the second candidate item, w n This represents the initial project weight information for the nth project to be selected.

[0080] The determined particle velocity can be expressed as:

[0081] v k =[v1,v2,...,v n ]

[0082] Among them, v k This represents the particle velocity; v1 represents the updated weight information of the first candidate item; v2 represents the updated weight information of the second candidate item; v n This represents the updated information on the project weights of the nth project to be selected.

[0083] The external archive can also be initialized to be empty. The external archive is used to store the optimal solution determined later. By optimizing the optimal solution in the external archive, the project weight information of at least one candidate project corresponding to the optimal solution is determined, and the project weight information of that project is used as the target project weight information.

[0084] S240. Based on multiple objective functions and constraint functions associated with constraints, determine the initial particle fitness corresponding to the initial project weight information of at least one candidate project.

[0085] The constraint function associated with the constraints can be a penalty function determined based on the three constraints mentioned above. The constraint function can be expressed as:

[0086]

[0087] Where Penalty represents the constraint penalty value of the constraint function, λ is a preset penalty coefficient for each objective function, and w i This represents the project weight information for the i-th candidate project. It should be noted that when determining the initial particle fitness through the constraint function, w... i This represents the initial weight information for the i-th item to be selected. n represents the number of items to be selected. 0.3 represents the preset weight threshold.

[0088] The initial particle fitness can be determined based on the fitness function defined by each objective function and constraint function, as well as the initial item weight information. Optionally, the first fitness function can be determined based on the first objective function and constraint function corresponding to the item reward attribute. The first fitness function can be expressed as:

[0089] f1' = f1 - Penalty

[0090] Where f1' represents the particle fitness corresponding to the first fitness function, f1 represents the first objective function corresponding to the project reward attribute, and Penalty represents the constraint function.

[0091] Optionally, the second fitness function can be determined based on the second objective function and constraint function corresponding to the project risk attribute. The second fitness function can be expressed as:

[0092] f2'=f2-Penalty

[0093] Where f2' represents the particle fitness corresponding to the second fitness function, f2 represents the second objective function corresponding to the project risk attribute, and Penalty represents the constraint function.

[0094] Optionally, the third fitness function can be determined based on the third objective function and constraint function corresponding to the project resource flow attributes. The third fitness function can be expressed as:

[0095] f3' = f3 - Penalty

[0096] Where f3' represents the particle fitness corresponding to the third fitness function, f3 represents the third objective function corresponding to the project resource flow attribute, and Penalty represents the constraint function.

[0097] Specifically, based on the constraints, constraint functions associated with the constraints are determined. Based on each objective function and constraint function, fitness functions corresponding to each objective function are determined, namely the first fitness function, the second fitness function, and the third fitness function mentioned above. The initial item weight information of at least one candidate item is substituted into the first fitness function, the second fitness function, and the third fitness function to obtain the initial particle fitness corresponding to the initial item weight information.

[0098] S250. Based on the initial particle fitness, determine the individual optimal solution and the global optimal solution corresponding to the initial project weight information.

[0099] The individual optimal solution, or individual optimal position (pBest), is the best position for each particle across all objective functions. The global optimal solution, or global best position (gBest), is the best position for all particles.

[0100] Specifically, based on the initial particle fitness, the individual optimal solution and the global optimal solution corresponding to the initial project weight information are determined.

[0101] S260. Based on the individual optimal solution and the global optimal solution, the initial particle position is updated to obtain the updated particle position, where the updated particle position corresponds to the optimized initial project weight information.

[0102] The optimized initial project weight information can be understood as the updated initial project weight information.

[0103] Specifically, based on the individual optimal solution and the global optimal solution, the initial particle position is updated to obtain the updated particle position, which corresponds to the optimized initial project weight information.

[0104] In this embodiment of the invention, the method for updating the initial particle position may be as follows: substituting the individual optimal solution, the global optimal solution, the initial particle position, and the particle velocity corresponding to the initial particle position into the particle velocity update function to obtain the updated particle velocity; and determining the updated particle position based on the updated particle velocity and the initial particle position.

[0105] The particle velocity update function can be as follows:

[0106]

[0107] in, Let represent the particle velocity of the k-th particle in the (t+1)-th iteration, i.e., the updated particle velocity. This represents the particle velocity of the k-th particle in the t-th iteration, i.e., the particle velocity corresponding to the initial particle position mentioned above. t indicates the current iteration number, where t = 1, and ω represents the dynamic inertia weight, ω = ω max -(ω max -ω min )·t / T max Where t represents the current iteration number, T max ω represents the maximum number of iterations. max ω represents the maximum inertia weight. min This represents the minimum inertia weight. Dynamic inertia weights can enhance the global search in the early stages of iteration and the local search in the later stages. c1 and c2 represent learning factors, typically set to 2.0. r1 and r2 represent random numbers in the range [0,1] used to update particles. pbest k Let represent the individual optimal solution for the k-th particle, and gbest represent the global optimal solution. This represents the position of the k-th particle in the t-th iteration, where it represents the initial particle position.

[0108] Specifically, by substituting the individual optimal solution, the global optimal solution, the initial particle position, and the particle velocity corresponding to the initial particle position into the particle velocity update function described above, the updated particle velocity can be obtained. Based on the updated particle velocity and the initial particle position, the updated particle position can be determined using the following particle position update function.

[0109]

[0110] in, This represents the position of the k-th particle in the t-th iteration, where the initial particle position is represented here. Let represent the particle velocity of the k-th particle in the (t+1)-th iteration, i.e., the updated particle velocity. This represents the position of the k-th particle in the (t+1)-th iteration, i.e., the updated particle position.

[0111] It should be noted that, in order to ensure the accuracy of particle position updates, the updated particles are normalized so that the proportion of all particles after the position update remains at 1, which corresponds to the sum of the weight information of at least one candidate item in the constraints being 1. The normalized result is taken as the final particle position after this update, that is, the updated particle position mentioned above.

[0112] Optionally, determine the fitness of the first particle corresponding to the updated particle position; determine the Pareto dominance relationship based on the fitness of the first particle and the initial particle fitness; when the Pareto dominance relationship is a preset dominance relationship, update the individual optimal solution and the global optimal solution based on the current solution corresponding to the fitness of the first particle, and update the target project configuration information based on the project configuration information corresponding to the current solution.

[0113] The first particle fitness can be determined based on the optimized initial item weight information corresponding to the updated particle position and the first fitness function, second fitness function and third fitness function determined above.

[0114] Pareto dominance is used to compare the performance of the best solution (historical best solution) at the initial particle fitness with the current solution at the first particle fitness. For example, the following illustrates Pareto dominance: If solution p is better than solution q on at least one objective function, and no worse than solution q on all other objective functions, then the Pareto dominance of solution p and solution q is said to be that solution p dominates solution q. That is, solution p is at least equal to solution q on all objective functions, and performs better on some objective functions. Figure 3 As shown. Figure 3 An example diagram illustrates that solution S1 dominates solution S2, meaning solution S1 is superior to solution S2 on some objective functions and at least not inferior to solution S2 on other objective functions. Conversely, if no such relationship exists between the two solutions—that is, solution S1 is superior to solution S2 on some objective functions, while solution S2 performs the same or better on other objective functions—the Pareto dominance relationship between solutions S1 and S2 is said to be that solutions S1 and S2 are not mutually dominant. For example... Figure 4 As shown, Figure 4This is an example diagram showing that solutions S1 and S2 are non-dominated. Since solutions S1 and S2 each have advantages on the objectives corresponding to different objective functions, they are called non-dominated solutions.

[0115] The pre-defined dominance relationship can be that the current solution corresponding to the fitness of the first particle dominates the optimal solution corresponding to the fitness of the initial particle, i.e., the historical optimal solution.

[0116] Specifically, based on the first fitness function, the second fitness function, the third fitness function, and the optimized initial item weight information corresponding to the updated particle position, the first particle fitness corresponding to the updated particle position is determined. The current solution corresponding to the first particle fitness is determined. Based on the current solution corresponding to the first particle fitness and the optimal solution (historical optimal solution) corresponding to the initial particle fitness, the Pareto dominance is determined. If the Pareto dominance is that the current solution corresponding to the first particle fitness dominates the optimal solution (historical optimal solution) corresponding to the initial particle fitness, then based on the current solution corresponding to the first particle fitness, the individual optimal solution and the global optimal solution are updated, and the target item configuration information is updated based on the item configuration information corresponding to the current solution.

[0117] Optionally, updating the individual optimal solution means: when the current solution dominates the optimal solution corresponding to the initial particle fitness (historical optimal solution), updating the individual optimal solution, that is, replacing the historical optimal solution with the current solution as the optimal solution. Updating the global optimal solution means: selecting particles with high crowding density from the external archive as guides (to avoid premature convergence). In other words, storing the updated non-dominated solutions in the external archive, and when the number of optimal solutions stored in the external archive exceeds the maximum number of solutions, redundant solutions are eliminated according to crowding density (neighborhood density of the target space). For example, if most of the optimal solutions in the external archive are dominant in project reward attributes, some solutions that are dominant in project reward attributes can be deleted based on the presented crowding information.

[0118] S270, Repeatedly determine the optimal solution corresponding to the project weight information and optimize the project weight information, so as to obtain at least one target project configuration information when the number of repeated executions reaches a preset threshold or the update improvement rate is lower than a preset value.

[0119] The preset threshold for the number of repetitions can be a pre-set maximum number of times the operation can be repeated. For example, the preset threshold could be 200. The preset value can be a standard value corresponding to the update improvement rate; for example, the preset value could be 1%. The update improvement rate can be used to characterize the degree of update of the project weight information after repeated execution.

[0120] Specifically, the process of determining the optimal solution for project weight information and optimizing project weight information is repeated to obtain at least one target project configuration information when the number of repetitions reaches a preset threshold or the update improvement rate is lower than a preset value.

[0121] For example, the process of determining the optimal solution for project weight information and optimizing project weight information is repeated. When the number of repetitions reaches 200 times or the update improvement rate corresponding to 10 consecutive iterations is less than 1%, the target project weight information of at least one candidate project corresponding to each non-dominated solution is determined based on the optimal solution in the external archive, i.e., at least one non-dominated solution. That is, at least one target project configuration information is obtained.

[0122] S280. Based on at least one target project configuration information, generate project selection reference information for the target user.

[0123] The technical solution of this embodiment obtains at least one selectable item corresponding to the target user and determines multiple objective functions corresponding to the at least one selectable item, providing data support for subsequent function optimization. The initial particle position and particle velocity in the multi-objective particle swarm optimization algorithm are determined. Based on the multiple objective functions and the constraint functions associated with the constraints, the initial particle fitness corresponding to the initial item weight information of at least one selectable item is determined. Based on the initial particle fitness, the individual optimal solution and the global optimal solution corresponding to the initial item weight information are determined. Based on the individual optimal solution and the global optimal solution, the initial particle position is updated to obtain the updated particle position, where the updated particle position corresponds to the optimized initial item weight information. The process of determining the optimal solution corresponding to the item weight information and optimizing the item weight information is repeated until the number of repetitions reaches a preset threshold or the update improvement rate is lower than a preset value, at least one target item configuration information is obtained. Through the multi-objective particle swarm optimization algorithm and constraints, conflicts between multiple objectives can be effectively handled, ensuring a balance between the relationships between objectives during the optimization process, achieving a more ideal optimization effect. Based on configuration information for at least one target project, this invention generates project selection reference information for target users, providing them with an optimal project selection scheme. This allows target users to choose projects that suit their actual needs. This invention addresses the limitations of existing technologies that rely on hypothetical scenarios based on historical data for resource allocation schemes, which are unable to cope with future dynamic changes and carry certain project selection risks. By using a multi-objective particle swarm optimization algorithm to balance the relationships between multiple objectives, it provides accurate project selection reference information that can adapt to complex market environment changes. While meeting the project selection needs of target users, it controls and reduces project selection risks.

[0124] Example 3

[0125] Figure 5 This is a schematic diagram of the structure of a data processing device provided in Embodiment 3 of the present invention. Figure 5 As shown, the device includes: a project acquisition module 310, an objective function determination module 320, a project configuration information determination module 330, and a reference information generation module 340.

[0126] The project acquisition module 310 is used to acquire at least one candidate project corresponding to the target user; the objective function determination module 320 is used to determine multiple objective functions corresponding to the at least one candidate project, wherein the multiple objective functions include at least: a first objective function corresponding to the project return attribute, a second objective function corresponding to the project risk attribute, and a third objective function corresponding to the project resource flow attribute; the project configuration information determination module 330 is used to optimize the multiple objective functions according to the multi-objective particle swarm optimization algorithm, so as to determine at least one target project configuration information when the constraints are met, wherein the target project configuration information includes: target project weight information corresponding to at least one candidate project; and the reference information generation module 340 is used to generate project selection reference information for the target user based on the at least one target project configuration information.

[0127] The technical solution of this embodiment obtains at least one selectable item corresponding to the target user and determines multiple objective functions corresponding to the at least one selectable item, providing data support for subsequent function optimization. Multiple objective functions are optimized using a multi-objective particle swarm optimization algorithm to determine at least one target item configuration information while satisfying constraints. Through the multi-objective particle swarm optimization algorithm and constraints, conflicts between multiple objectives can be effectively handled, ensuring a balance between the relationships between objectives during optimization and achieving a more ideal optimization effect. Based on the configuration information of at least one target item, reference information for project selection for the target user is generated, providing the target user with an optimal project selection scheme, allowing the target user to select suitable projects according to actual needs. This invention solves the problem that existing technologies, which provide resource allocation schemes based on hypothetical scenarios using historical data, have certain limitations, are difficult to cope with future dynamic changes, and have certain project selection risks. By balancing the relationships between multiple objectives through the multi-objective particle swarm optimization algorithm, accurate project selection reference information is provided, which can adapt to complex market environment changes, meeting the project selection needs of the target user while controlling and reducing project selection risks.

[0128] Based on the above embodiments, optionally, the objective function determination module is used to determine a first objective function associated with project weight information according to the expected return attribute corresponding to each candidate project; wherein, the expected return attribute is used to characterize the average return attribute of the candidate project within a first preset time period; determine the covariance value of the average return attribute of each candidate project and other candidate projects within a second preset time period, and based on the covariance value, determine the project volatility function associated with project weight information, and use the project volatility function as the second objective function; determine the project resource flow attribute of each candidate project according to the ratio of the transaction volume of each candidate project to the free trade resource information within a third preset time period, and determine the third objective function associated with project weight information based on the project resource flow attribute.

[0129] Optionally, the constraints include: the sum of the project weight information of at least one candidate project is 1; the project weight information of each candidate project does not exceed a preset weight threshold; and the project weight information of a candidate project that belongs to the project blacklist is 0.

[0130] Optionally, the project configuration information determination module includes: a particle initialization unit, used to determine the initial particle position and particle velocity in the multi-objective particle swarm optimization algorithm, wherein the initial particle position corresponds to the initial project weight information of at least one candidate project, and the particle velocity is used to characterize the update information of the project weight information; a particle fitness determination unit, used to determine the initial particle fitness corresponding to the initial project weight information of at least one candidate project based on multiple objective functions and constraint functions associated with the constraint conditions; an optimal solution determination unit, used to determine the individual optimal solution and the global optimal solution corresponding to the initial project weight information based on the initial particle fitness; a particle position update unit, used to update the initial particle position based on the individual optimal solution and the global optimal solution to obtain the updated particle position, wherein the updated particle position corresponds to the optimized initial project weight information; and a target project configuration information determination unit, used to repeatedly determine the optimal solution corresponding to the project weight information and optimize the project weight information, so as to obtain at least one target project configuration information when the number of repeated executions reaches a preset threshold or the update improvement rate is lower than a preset value.

[0131] Optionally, a particle position update unit is used to substitute the individual optimal solution, the global optimal solution, the initial particle position, and the particle velocity corresponding to the initial particle position into the particle velocity update function to obtain the updated particle velocity; and to determine the updated particle position based on the updated particle velocity and the initial particle position.

[0132] Optionally, the project configuration information determination module further includes: an optimal solution update unit, used to determine the first particle fitness corresponding to the updated particle position; determine the Pareto dominance relationship based on the first particle fitness and the initial particle fitness; when the Pareto dominance relationship is a preset dominance relationship, update the individual optimal solution and the global optimal solution based on the current solution corresponding to the first particle fitness, and update the target project configuration information based on the project configuration information corresponding to the current solution.

[0133] Optionally, a reference information generation module is used to evaluate and process at least one target project configuration information to determine the attribute reference information of each target project configuration information in the project return attribute, project risk attribute, and project resource flow attribute; and to generate project selection reference information based on the attribute reference information and the target project configuration information.

[0134] The data processing apparatus provided in the embodiments of the present invention can execute the data processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0135] Example 4

[0136] Figure 6 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. The electronic device 10 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 may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, 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 illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0137] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0138] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0139] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as data processing methods.

[0140] In some embodiments, the data processing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the data processing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the data processing method by any other suitable means (e.g., by means of firmware).

[0141] Various embodiments of the systems and techniques described above 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-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0142] Computer programs for implementing the data processing methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0143] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0144] Example 5

[0145] Embodiment 5 of the present invention also provides a computer-readable storage medium storing computer instructions for causing a processor to execute a data processing method, the method comprising:

[0146] Obtain at least one candidate project corresponding to the target user; determine multiple objective functions corresponding to the at least one candidate project, wherein the multiple objective functions include at least: a first objective function corresponding to the project return attribute, a second objective function corresponding to the project risk attribute, and a third objective function corresponding to the project resource flow attribute; optimize the multiple objective functions according to the multi-objective particle swarm optimization algorithm to determine at least one target project configuration information when the constraints are met, wherein the target project configuration information includes: target project weight information corresponding to at least one candidate project; generate project selection reference information for the target user based on the at least one target project configuration information.

[0147] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0148] 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 provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, 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 sound input, voice input, or tactile input).

[0149] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0150] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0151] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0152] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A data processing method, characterized in that, include: Obtain at least one selectable item corresponding to the target user; Determine multiple objective functions corresponding to the at least one candidate project, wherein the multiple objective functions include at least: a first objective function corresponding to the project return attribute, a second objective function corresponding to the project risk attribute, and a third objective function corresponding to the project resource flow attribute; The multiple objective functions are optimized using a multi-objective particle swarm optimization algorithm to determine at least one objective item configuration information when the constraints are met. The objective item configuration information includes: objective item weight information corresponding to the at least one candidate item. Based on the configuration information of at least one target project, project selection reference information for the target user is generated.

2. The method according to claim 1, characterized in that, The determination of multiple objective functions corresponding to the at least one candidate item includes: Based on the expected return attribute corresponding to each candidate project, a first objective function associated with the project weight information is determined; wherein, the expected return attribute is used to characterize the average return attribute of the candidate project within a first preset time period; Determine the covariance value of the average return attribute of each candidate project and other candidate projects within a second preset time period, and based on the covariance value, determine the project fluctuation function associated with the project weight information, and use the project fluctuation function as the second objective function; Based on the ratio of the transaction volume of each candidate project to the free trade resource information within a third preset time period, the project resource flow attribute of each candidate project is determined, and based on the project resource flow attribute, a third objective function associated with the project weight information is determined.

3. The method according to claim 1, characterized in that, The constraints include: The sum of the project weight information of the at least one candidate project is 1; The weight information of each item to be selected does not exceed the preset weight threshold; The project weight information for projects that are on the project blacklist is 0.

4. The method according to claim 1, characterized in that, The optimization of the multiple objective functions using a multi-objective particle swarm optimization algorithm, to determine at least one objective item configuration information while satisfying constraints, includes: Determine the initial particle position and particle velocity in a multi-objective particle swarm optimization algorithm, wherein the initial particle position corresponds to the initial project weight information of the at least one candidate project, and the particle velocity is used to characterize the update information of the project weight information; Based on the multiple objective functions and the constraint functions associated with the constraints, determine the initial particle fitness corresponding to the initial project weight information of the at least one candidate project; Based on the initial particle fitness, determine the individual optimal solution and the global optimal solution corresponding to the initial project weight information; Based on the individual optimal solution and the global optimal solution, the initial particle position is updated to obtain the updated particle position, wherein the updated particle position corresponds to the optimized initial project weight information; The process of repeatedly determining the optimal solution corresponding to the project weight information and optimizing the project weight information is carried out so that when the number of repeated executions reaches a preset threshold or the update improvement rate is lower than a preset value, at least one target project configuration information is obtained.

5. The method according to claim 4, characterized in that, The step of updating the initial particle position based on the individual optimal solution and the global optimal solution to obtain the updated particle position includes: Substitute the individual optimal solution, the global optimal solution, the initial particle position, and the particle velocity corresponding to the initial particle position into the particle velocity update function to obtain the updated particle velocity. The updated particle position is determined based on the updated particle velocity and the initial particle position.

6. The method according to claim 5, characterized in that, Also includes: Determine the fitness of the first particle corresponding to the updated particle position; The Pareto dominance relationship is determined based on the fitness of the first particle and the fitness of the initial particle; When the Pareto dominance relationship is a preset dominance relationship, the individual optimal solution and the global optimal solution are updated based on the current solution corresponding to the fitness of the first particle, and the target project configuration information is updated based on the project configuration information corresponding to the current solution.

7. The method according to claim 1, characterized in that, The step of generating project selection reference information for the target user based on the at least one target project configuration information includes: The configuration information of the at least one target project is evaluated and processed to determine the attribute reference information of each target project configuration information in the project return attribute, project risk attribute, and project resource flow attribute. Based on the attribute reference information and the target project configuration information, project selection reference information is generated.

8. A data processing apparatus, characterized in that, include: The project acquisition module is used to acquire at least one selectable project corresponding to the target user; The objective function determination module is used to determine multiple objective functions corresponding to the at least one candidate project, wherein the multiple objective functions include at least: a first objective function corresponding to the project return attribute, a second objective function corresponding to the project risk attribute, and a third objective function corresponding to the project resource flow attribute; The project configuration information determination module is used to optimize the multiple objective functions according to the multi-objective particle swarm optimization algorithm, so as to determine at least one target project configuration information when the constraints are met, wherein the target project configuration information includes: target project weight information corresponding to the at least one candidate project; The reference information generation module is used to generate reference information for project selection for the target user based on the configuration information of the at least one target project.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the data processing method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the data processing method according to any one of claims 1-7.

Images