Financial product combination recommendation method and device and electronic equipment

Abstract

The invention discloses a financial product combination recommendation method and device and electronic equipment, and relates to the field of financial investment. The method comprises the following steps: obtaining product characteristics of a financial product held by a target object; determining a target template corresponding to the target object from preset N templates according to the product features; determining at least two target financial products recommended to the target object from the M to-be-combined financial products according to the target template and the product features of the financial products held by the target object; and according to the target template and the portrait information of the target object, performing configuration combination on the at least two target financial products to obtain a financial product combination and recommending the financial product combination to the target object. The technical problems that in the prior art, the financial product combination is configured based on the experience of the financial consultant, so that the configuration of the financial product combination is unreasonable, the matching accuracy with the user is low, and the recommendation success rate of the financial product combination is low are solved.

Description

Technical Field

[0001] This application relates to the field of financial investment, and more specifically, to a method, apparatus, and electronic device for recommending a portfolio of financial products. Background Technology

[0002] In the field of financial investment, the formulation of asset allocation plans is crucial for investors to preserve and grow their assets. Traditionally, this process relies primarily on the human experience of financial advisors, who manually analyze and formulate asset allocation strategies based on various factors such as the client's basic information, financial situation, investment goals, and risk tolerance. However, this manual approach has significant shortcomings. On the one hand, manual analysis is inefficient and cannot meet the needs of a large number of clients requiring rapid response. On the other hand, due to significant differences in the professional level and experience of different financial advisors, the quality of the asset allocation plans varies greatly, leading to unreasonable financial product portfolios, low accuracy in matching with users, and a low success rate in recommending financial product portfolios.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a method, apparatus, and electronic device for recommending financial product portfolios, which at least solves the technical problem in the prior art where configuring financial product portfolios based on the financial advisor's own experience leads to unreasonable configuration of financial product portfolios, low matching accuracy with users, and a low success rate of financial product portfolio recommendations.

[0005] According to one aspect of the embodiments of this application, a method for recommending a financial product portfolio is provided, comprising: obtaining product characteristics of financial products already held by a target object; determining a target template corresponding to the target object from N preset templates based on the product characteristics, wherein N is an integer greater than 1, and each of the N templates is used to provide a financial product configuration strategy; determining at least two target financial products to be recommended to the target object from M financial products to be combined based on the target template and the product characteristics of the financial products already held by the target object, wherein M is an integer greater than 1; configuring and combining the at least two target financial products based on the target template and the profile information of the target object to obtain a financial product portfolio and recommending it to the target object, wherein the configuration process of the financial product portfolio includes at least: configuring the recommended purchase amount, recommended holding period, and recommended purchase time for each target financial product.

[0006] Optionally, determining the target template corresponding to the target object from a pre-set set of N templates based on product characteristics includes: inputting product characteristics into a target model, segmenting product characteristics through multiple decision nodes of the target model, transmitting the segmented feature information obtained from each decision node to a leaf node of the target model, and determining the target template corresponding to the target object from the pre-set set of N templates based on the received feature information through the leaf node; wherein, each decision node is used to characterize a feature filtering condition set based on the product characteristics and the attribute information of the target object; the leaf node includes at least: target feature content corresponding to each of the N templates.

[0007] Optionally, the target template corresponding to the target object is determined from a set of N templates based on the feature information obtained from each decision node received by the leaf nodes. This includes: forming a feature matrix from the feature information obtained from each decision node received by the leaf nodes; determining the similarity between the feature matrix and the target feature content corresponding to each template by the leaf nodes; and determining the target template corresponding to the target object from the set of N templates based on the similarity.

[0008] Optionally, the method for recommending financial product portfolios also includes: during the prediction process of the target template, obtaining path information between the decision nodes and leaf nodes of the pathway, wherein the path information is used to characterize the process by which the target model gradually narrows down the template selection range based on product characteristics and attribute information of the target object; and generating a visualized report text based on the path information.

[0009] Optionally, based on the target template and the product characteristics of the financial products already held by the target object, at least two target financial products to be recommended to the target object are determined from the M financial products to be combined, including: obtaining historical transaction information of each financial product to be combined; and determining at least two target financial products to be recommended to the target object from the M financial products to be combined, based on the target template, the historical transaction information of each financial product to be combined, and the product characteristics of the financial products already held by the target object.

[0010] Optionally, based on the target template, the historical transaction information of each financial product to be combined, and the product characteristics of the financial products already held by the target object, at least two target financial products to be recommended to the target object are determined from the M financial products to be combined. This includes: converting the configuration ratio of the target template and the product characteristics of the financial products already held into feature vectors for model input; inputting the feature vectors into a screening model, and determining the vector similarity between the feature vectors and the product feature vectors of each financial product to be combined through the screening model; and determining at least two target financial products from the M financial products to be combined based on the vector similarity and the historical transaction information of each financial product to be combined.

[0011] Optionally, based on vector similarity and historical transaction information of each financial product to be combined, at least two target financial products are determined from the M financial products to be combined, including: determining the risk-return ratio of each financial product to be combined based on historical transaction information of each financial product to be combined; and determining at least two target financial products from the M financial products to be combined based on vector similarity and the risk-return ratio of each financial product to be combined.

[0012] According to another aspect of the embodiments of this application, a financial product portfolio recommendation device is also provided, comprising: a first acquisition unit, configured to acquire product characteristics of financial products already held by a target object; a first determination unit, configured to determine a target template corresponding to the target object from N preset templates based on the product characteristics, wherein N is an integer greater than 1, and each of the N templates is used to provide a financial product configuration strategy; a second determination unit, configured to determine at least two target financial products to be recommended to the target object from M financial products to be combined, based on the target template and the product characteristics of the financial products already held by the target object, wherein M is an integer greater than 1; and a combination unit, configured to combine at least two target financial products based on the target template and the profile information of the target object to obtain a financial product portfolio and recommend it to the target object, wherein the configuration process of the financial product portfolio includes at least: configuring the recommended purchase amount, recommended holding period, and recommended purchase time for each target financial product.

[0013] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, which stores a computer program, wherein when the computer program is executed, it causes the device on which the computer-readable storage medium is located to perform the recommended method for the above-mentioned financial product combination.

[0014] According to another aspect of the embodiments of this application, an electronic device is also provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to perform the recommended method of the above-described financial product portfolio.

[0015] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program or instructions that, when executed by a processor, implement the recommended method for the above-described financial product portfolio.

[0016] As described above, this application obtains the product characteristics of the financial products already held by the target object; determines the target template corresponding to the target object from N preset templates based on the product characteristics, where N is an integer greater than 1, and each of the N templates is used to provide a financial product allocation strategy; based on the target template and the product characteristics of the financial products already held by the target object, determines at least two target financial products to be recommended to the target object from M financial products to be combined, where M is an integer greater than 1; and configures and combines the at least two target financial products based on the target template and the profile information of the target object to obtain a financial product combination and recommend it to the target object. The configuration process of the financial product combination includes at least: configuring the recommended purchase amount, recommended holding period, and recommended purchase time for each target financial product.

[0017] In this embodiment, a target template is determined based on the product characteristics of the financial products already held by the target object. Then, a recommended target financial product is selected from multiple financial products to be combined based on the target template and product characteristics. By combining the target template and the target object's profile information to configure and combine the target financial products, the goal of providing a personalized and accurately matched financial product combination for each target object is achieved. This improves the technical effect of increasing the success rate of financial product combination recommendations and solves the technical problem in the prior art where configuring financial product combinations based on the financial advisor's own experience leads to unreasonable configuration of financial product combinations, low matching accuracy with users, and a low success rate of financial product combination recommendations. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0019] Figure 1 This is a flowchart of an optional method for recommending a portfolio of financial products according to an embodiment of this application;

[0020] Figure 2 This is an architecture diagram of an optional method for recommending a portfolio of financial products according to an embodiment of this application;

[0021] Figure 3 This is a schematic diagram of an optional financial product portfolio recommendation device according to an embodiment of this application. Detailed Implementation

[0022] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application 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 this application 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.

[0024] It should also be noted that the information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, and displayed data) collected in this application are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with the relevant laws, regulations, and standards of the relevant regions, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding operation entry points are provided for users to choose to authorize or refuse. For example, this system has interfaces with relevant users or organizations. Before obtaining relevant information, a request to obtain the information needs to be sent to the aforementioned user or organization through the interface, and the relevant information is obtained only after receiving consent from the aforementioned user or organization.

[0025] According to an embodiment of this application, an embodiment of a method for recommending a portfolio of financial products is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0026] Optionally, according to the embodiments of this application, a financial product portfolio recommendation system (hereinafter referred to as the system) is provided as the execution subject of the financial product portfolio recommendation method of the embodiments of this application. The system can be a software system or an embedded system combining software and hardware. Of course, the method execution subject in the embodiments of this application can also be other forms of execution subject, such as devices, equipment, etc. It should be known by those skilled in the art that this application does not particularly limit the specific form of the method execution subject.

[0027] Figure 1 This is a flowchart of an optional method for recommending a portfolio of financial products according to an embodiment of this application, such as... Figure 1 As shown, the method includes the following steps:

[0028] Step S101: Obtain the product characteristics of the financial products already held by the target object.

[0029] Optionally, the system can collect information on the target entity's transaction status, investment objectives, and risk tolerance through a data acquisition module. Investment objectives include, but are not limited to, short-term profit, long-term asset appreciation, retirement savings, and children's education savings; risk tolerance information can be obtained through risk assessment questionnaires and analysis of historical investment behavior. This information collectively constitutes the product characteristics of the financial products already held by the target entity.

[0030] Optionally, the data collection module processes the target's personal information using encrypted transmission and storage technologies, complying with relevant regulations to ensure that the data is used solely for asset allocation analysis and is not disclosed to third parties without authorization. Furthermore, the system can anonymize the target's personal information using anonymization technology to ensure that the data cannot be linked to any specific individual. Additionally, the target can view the purpose of data use in real time through the authorization interface and has the right to withdraw authorization or delete data at any time. Upon withdrawal of authorization, the system will terminate the relevant data processing within 24 hours.

[0031] Optionally, the system will also clean the collected target data through a data preprocessing module, removing duplicate, erroneous, or missing data to ensure data integrity and accuracy. Subsequently, the data will be standardized, converting different types of data into a unified format and scale for subsequent analysis and processing. Furthermore, the data preprocessing module can classify and label the data based on its characteristics and patterns. Simultaneously, the system will acquire various financial market data in real time through a market data acquisition module, including stock market index trends, individual stock prices, and trading volumes; bond market bond yields and price fluctuations; fund market fund net asset values ​​and performance; and macroeconomic data such as interest rates, inflation rates, and GDP growth rates. The market data acquisition module connects to multiple financial data providers and has a real-time verification mechanism that automatically triggers manual review processes for abnormal data, thereby ensuring the reliability of the input data.

[0032] Step S102: Determine the target template corresponding to the target object from the preset N templates based on the product characteristics.

[0033] In step S102, N is an integer greater than 1, and each of the N templates is used to provide a financial product allocation strategy.

[0034] Optionally, the system can complete the above process through the asset configuration model module and the scheme generation and optimization module.

[0035] Optionally, the asset allocation model module utilizes machine learning algorithms (such as neural networks and decision trees) to conduct in-depth analysis of market data (i.e., historical transaction information of each financial product to be combined) and the product characteristics of the financial products already held by the target entity, predicting the future returns and risks of various assets and dynamically adjusting the parameters of the asset allocation model. The asset allocation model module can also meet the personalized needs of the target entity by setting multiple asset allocation strategy templates (i.e., N preset templates), such as conservative, balanced, and aggressive strategies. Each template provides a specific financial product allocation strategy suitable for clients with different risk appetites and investment objectives.

[0036] Specifically, the asset allocation model module analyzes the characteristics of the financial products already held by the target entity, and combines the target entity's risk tolerance and investment objectives to select the most suitable template from the preset templates as the target template.

[0037] Optionally, the scheme generation and optimization module generates a preliminary asset allocation scheme based on the target template determined by the asset allocation model, performs sensitivity analysis and optimization adjustments, determines the target template, and finally presents the generated scheme to the target object in a visual manner.

[0038] Optionally, the market data acquisition module acquires market data in real time, such as stock market index trends and bond market yield changes. The asset allocation model module can then dynamically adjust the parameters in the preset template based on this data. For example, if market interest rates rise, the asset allocation model module can automatically adjust the proportion of bond allocation.

[0039] Optionally, the asset allocation model module can dynamically adjust the preset template based on the target's actual investment behavior and feedback. If the target frequently adjusts the allocation of a certain type of asset, the asset allocation model module can use this behavior as feedback to optimize the allocation strategy in the preset template.

[0040] Optionally, the asset allocation model module can further refine the target audience's personal information, including their age, occupation, income level, and investment experience, to generate more personalized templates. For example, for young, high-income clients, the asset allocation model module can recommend more high-risk, high-return asset allocation strategies.

[0041] Optionally, the asset allocation model module can generate customized preset templates based on the specific investment objectives of the target (such as short-term profit, long-term asset appreciation, retirement savings, etc.). For example, for a target with retirement savings as its goal, the asset allocation model module can recommend more conservative asset allocation strategies.

[0042] Step S103: Based on the target template and the product characteristics of the financial products already held by the target object, determine at least two target financial products to recommend to the target object from the M financial products to be combined.

[0043] In step S103, M is an integer greater than 1.

[0044] Optionally, the scheme generation and optimization module can generate a preliminary asset allocation scheme based on the calculation results of the asset allocation model, and specify the investment ratio of various assets and specific investment product recommendations (i.e., select the most suitable product for the target from multiple financial products to be combined).

[0045] Optionally, the real-time nature of the market data acquisition module and the dynamic adjustment function of the asset allocation model module can ensure that the recommended financial products can adapt to changes in the market and customer needs.

[0046] Optionally, when selecting target financial products, the solution generation and optimization module not only considers the return potential of the financial products but also assesses their risk level to ensure that the recommended financial products match the risk tolerance of the target audience. For example, for target audiences with low risk appetite, the solution generation and optimization module will prioritize recommending stable financial products.

[0047] Optionally, the solution generation and optimization module also considers the liquidity of financial products to ensure that the target can be easily converted into cash when needed. For example, for targets with short-term investment goals, the solution generation and optimization module will recommend financial products with good liquidity.

[0048] Optionally, the solution generation and optimization module can further optimize the selection of target financial products based on the target's past investment behavior and preferences. For example, if the target has invested in technology stocks multiple times in the past, the solution generation and optimization module will prioritize the technology sector when recommending stocks.

[0049] Step S104: Based on the target template and the profile information of the target object, configure and combine at least two target financial products to obtain a financial product combination and recommend it to the target object.

[0050] In step S104, the configuration process of the financial product portfolio includes at least: configuring the recommended purchase amount, recommended holding period, and recommended purchase time for each target financial product.

[0051] Optionally, the system will generate a detailed asset allocation plan based on the target template and target object profile information through the plan generation and optimization module. This plan includes the recommended purchase amount, recommended holding period, and recommended purchase time for the target financial product.

[0052] Optionally, the scheme generation and optimization module can present the generated asset allocation scheme to clients in a visual manner, such as through charts and reports, intuitively displaying key information like the allocation ratio, expected return, and risk level of various assets, and providing detailed investment advice and operational guidelines. Additionally, the scheme generation and optimization module can provide an interactive interface, allowing target clients to adjust the allocation scheme according to their needs, such as adjusting investment amounts and holding periods, and displaying the adjusted expected return and risk level in real time.

[0053] Optionally, the system can perform sensitivity analysis on the generated preliminary plans through the plan generation and optimization module to assess the impact of factors such as market volatility and interest rate changes on the plans, and optimize and adjust the plans based on the analysis results to improve the risk adaptability of the plans. In addition, the plan generation and optimization module can set a risk warning mechanism to periodically reassess the client's risk preferences and set market volatility thresholds. When there are significant changes in the market or the target's asset allocation deviates from the target, the system can promptly remind the target to adjust the allocation strategy.

[0054] It should be noted that the asset allocation plans generated by the plan generation and optimization module are reference suggestions based on data analysis. The target entities should make their own judgments and decisions. Financial institutions are not responsible for actual investment returns or losses.

[0055] As described above, this application uses the product characteristics of the financial products already held by the target object to determine the target template, and then selects the recommended target financial product from multiple financial products to be combined based on the target template and product characteristics. By combining the target template and the target object's profile information to configure and combine the target financial products, the application achieves the goal of providing a personalized and accurately matched financial product combination for each target object. This improves the technical effect of increasing the success rate of financial product combination recommendations and solves the technical problem in the prior art where configuring financial product combinations based on the financial advisor's own experience leads to unreasonable configuration of financial product combinations, low matching accuracy with users, and a low success rate of financial product combination recommendations.

[0056] Optionally, Figure 2 This is an architecture diagram of an optional financial product portfolio recommendation method according to an embodiment of this application, such as... Figure 2 As shown, the target audience first fills out personal information, investment goals, and risk assessment questionnaires through the financial institution's online platform or offline channels. Subsequently, the system transmits the collected raw data to the data preprocessing module for cleaning and standardization to ensure its quality and consistency. Simultaneously, the market data acquisition module obtains real-time financial market and macroeconomic data through interfaces with financial data providers and updates the data periodically based on market activity and the target audience's needs. For example, stock market data is typically updated in real-time, while macroeconomic data can be updated quarterly or annually.

[0057] After data preprocessing, the asset allocation model module utilizes modern portfolio theory and machine learning algorithms, combining the preprocessed target data with the latest market data, to calculate asset allocation. Following this calculation, the scheme generation and optimization module generates a preliminary asset allocation plan based on the model's results. Next, this module performs a sensitivity analysis on the preliminary plan to assess the potential impact of market volatility, interest rate changes, and other factors. For example, if a decline in bond prices or a potential shock to the stock market is predicted, the system will adjust the plan accordingly. Adjustments may include moderately reducing the bond allocation while increasing the allocation to defensive sectors within the stock market, thereby enhancing the plan's risk resilience.

[0058] Finally, the optimized asset allocation plan will be presented to the target audience in the form of a visual report. The report will clearly show key information such as the allocation ratio of various assets, expected returns, and risk levels, and provide detailed investment advice and operational guidelines to help the target audience better understand the investment recommendations and the expected returns and risks.

[0059] In one optional embodiment, determining the target template corresponding to the target object from a preset set of N templates based on product characteristics includes: inputting product characteristics into a target model; segmenting product characteristics through multiple decision nodes of the target model; transmitting the segmented feature information obtained by each decision node to a leaf node of the target model; and determining the target template corresponding to the target object from the preset set of N templates based on the received feature information through the leaf node; wherein each decision node is used to characterize a feature filtering condition set based on the product characteristics and the attribute information of the target object; and the leaf node includes at least the target feature content corresponding to each of the N templates.

[0060] Optionally, the target model can refer to a decision tree model, which segments the input product features through multiple decision nodes and finally outputs the results at the leaf nodes. The system can use a data preprocessing module to clean the collected target object data and remove duplicate, erroneous, or missing data before inputting the product features into the target model.

[0061] Optionally, the product features are segmented through decision nodes in the target model. This involves the data preprocessing module classifying and labeling the data based on its characteristics and patterns. Leaf nodes then select the most suitable template for the target object from pre-set templates based on the received feature information. This is achieved by the asset allocation model module automatically matching the optimal template based on the target object data. Each decision node sets feature filtering conditions based on the product features and the target object's attribute information; that is, the system extracts key features by analyzing the target object data.

[0062] In one optional embodiment, the target template corresponding to the target object is determined from a preset set of N templates based on the feature information obtained from each decision node received by the leaf nodes. This includes: forming a feature matrix from the feature information obtained from each decision node received by the leaf nodes; determining the similarity between the feature matrix and the target feature content corresponding to each template by the leaf nodes; and determining the target template corresponding to the target object from the preset set of N templates based on the similarity.

[0063] Optionally, the leaf nodes can form a feature matrix by segmenting the feature information received from each decision node. In other words, the system can classify and label the data through the data preprocessing module, thereby better extracting and utilizing the key information in the data.

[0064] Optionally, the similarity between the feature matrix and the target feature content corresponding to each template is determined through leaf nodes. In other words, the asset allocation model module uses machine learning algorithms for feature analysis and matching. The asset allocation model module can then select the template that best matches the target object as the target template by calculating the similarity.

[0065] Optionally, the asset allocation model module can comprehensively consider similarity across multiple dimensions, such as risk appetite, investment objectives, and financial status, to more comprehensively assess the match between the target and the preset template. For example, the system can calculate the similarity between the target's risk appetite and the risk appetite of the preset template, as well as the similarity between the target's investment objectives and the investment objectives of the preset template, and finally combine these similarities to select the most suitable template.

[0066] Optionally, the asset allocation model module can dynamically adjust the weights of similarity across different dimensions based on market conditions and the needs of the target group. For example, during periods of high market volatility, the weight of risk preference similarity can be increased to ensure the robustness of the asset allocation plan.

[0067] Optionally, the system can acquire market data in real time through the market data acquisition module and integrate this data into the feature matrix to more accurately assess the matching degree between the target object and the preset template. For example, if market interest rates rise, the system can adjust the relevant features in the feature matrix through the asset allocation model module to reflect the impact of market changes on asset allocation.

[0068] In an optional embodiment, the method for recommending financial product portfolios further includes: during the prediction process of the target template, obtaining path information between the decision nodes and leaf nodes of the pathway, wherein the path information is used to characterize the process by which the target model gradually narrows the range of template selection based on product characteristics and attribute information of the target object; and generating a visualized report text based on the path information.

[0069] Optionally, the target model gradually narrows down the template selection range based on product characteristics and target object attribute information. That is, the system uses machine learning algorithms to perform feature analysis and matching, and through gradual screening and matching, finally determines the most suitable template.

[0070] Optionally, generating a visual report based on the path information can demonstrate the generation process and basis of the asset allocation plan to the target audience, thereby improving the transparency of the decision-making process. Specifically, the system can use the plan generation and optimization module to display in detail the screening conditions and decision-making logic of each decision node, allowing the target audience to clearly understand how the system progressively narrows down the template selection range. For example, the system can display the feature screening conditions for each decision node, as well as the specific impact of each condition on template selection.

[0071] Optionally, the system can dynamically adjust the logic of decision nodes and leaf nodes in the asset allocation model module based on changes in market data, and update path information in real time. For example, if market interest rates rise, the system can adjust the screening criteria of decision nodes to reflect the impact of market changes on asset allocation.

[0072] Optionally, the system can generate educational visual reports to help the target audience understand the basic principles and decision-making process of asset allocation. For example, the report can explain the characteristics and applicable scenarios of different asset allocation strategy templates, helping the target audience better understand the system's recommended solutions.

[0073] Optionally, the system can incorporate profit forecast information into the path information to help target users understand the expected returns of different asset allocation schemes. For example, the system can display the expected return range for each template and adjust the profit forecast based on the path information.

[0074] In one optional embodiment, based on the target template and the product characteristics of the financial products already held by the target object, at least two target financial products to be recommended to the target object are determined from M financial products to be combined, including: obtaining historical transaction information of each financial product to be combined; and determining at least two target financial products to be recommended to the target object from M financial products to be combined based on the target template, the historical transaction information of each financial product to be combined, and the product characteristics of the financial products already held by the target object.

[0075] Optionally, the product characteristics of the financial products already held by the target individual, i.e., the target individual's personal information, and the historical transaction information of each financial product to be combined, i.e., market data, including the historical price, trading volume, and yield of the financial product, are used to assess the performance and risk of the financial product. This data is used to generate personalized asset allocation plans.

[0076] Optionally, the system can use the scheme generation and optimization module to select the most suitable product for the target object from multiple candidate financial products based on the analysis of the target template, the historical transaction information of each financial product to be combined, and the product characteristics of the financial products already held by the target object by the asset allocation model module.

[0077] In one optional embodiment, based on the target template, the historical transaction information of each financial product to be combined, and the product characteristics of the financial products already held by the target object, at least two target financial products to be recommended to the target object are determined from the M financial products to be combined. This includes: converting the configuration ratio of the target template and the product characteristics of the financial products already held into feature vectors for model input; inputting the feature vectors into a screening model, and determining the vector similarity between the feature vectors and the product feature vectors of each financial product to be combined through the screening model; and determining at least two target financial products from the M financial products to be combined based on the vector similarity and the historical transaction information of each financial product to be combined.

[0078] Optionally, the system uses a data preprocessing module to quantify and standardize the configuration ratio of the target template and the product characteristics of the financial products already held, so as to serve as input for the screening model. Through the screening model, the system can quantitatively evaluate the similarity between the feature vectors corresponding to the product characteristics of the financial products already held by the target object and the product feature vectors of the financial products to be combined, thereby providing a basis for subsequent financial product recommendations.

[0079] Optionally, based on vector similarity and combined with historical transaction information of each financial product to be combined, the system can conduct a comprehensive analysis of the financial products to be combined through the scheme generation and optimization module. This comprehensive analysis method can more comprehensively assess the potential value and risk of each financial product, thereby more accurately identifying the financial products suitable for the target.

[0080] Optionally, the system can acquire market data in real time, such as stock market index trends and bond market yield changes, and incorporate this data into the screening model. In this way, when determining target financial products, the system considers not only historical trading information and vector similarity, but also the dynamic changes in the current market. For example, if a financial product performs well in the current market environment, the system may still recommend it as a target financial product even if its historical trading information and vector similarity are not the highest.

[0081] In one optional embodiment, at least two target financial products are determined from M financial products to be combined based on vector similarity and historical transaction information of each financial product to be combined, including: determining the risk-return ratio of each financial product to be combined based on historical transaction information of each financial product to be combined; and determining at least two target financial products from M financial products to be combined based on vector similarity and the risk-return ratio of each financial product to be combined.

[0082] Optionally, the asset allocation model module can predict the risk-return ratio of the financial products to be combined using historical transaction information, thereby providing an important basis for subsequent asset allocation.

[0083] Optionally, the scheme generation and optimization module generates a preliminary asset allocation scheme and determines the target financial products based on the risk-return ratio and vector similarity obtained from the asset allocation model. When selecting target financial products, the system considers not only vector similarity but also the risk-return ratio, thereby ensuring that the recommended financial products not only match the needs of the target group but also possess reasonable risk and return characteristics.

[0084] Optionally, the solution generation and optimization module can adjust the risk-reward ratio based on the risk preferences of the target audience. For example, for target audiences with lower risk preferences, the module can increase the weight of the risk component in the risk-reward ratio, thereby recommending more stable financial products; for target audiences with higher risk preferences, the module can appropriately reduce the risk weight, recommending more promising financial products. This personalized adjustment can better meet the needs of different target audiences and improve the adaptability and satisfaction of asset allocation solutions.

[0085] According to another aspect of the embodiments of this application, a device for recommending financial product portfolios is also provided, wherein, Figure 3 This is a schematic diagram of an optional financial product portfolio recommendation device according to an embodiment of this application, such as... Figure 3 As shown, the financial product portfolio recommendation device includes: a first acquisition unit 301, a first determination unit 302, a second determination unit 303, and a combination unit 304.

[0086] Optionally, the first acquisition unit 301 is used to acquire the product characteristics of the financial products already held by the target object; the first determination unit 302 is used to determine the target template corresponding to the target object from N preset templates according to the product characteristics, where N is an integer greater than 1, and each of the N templates is used to provide a financial product configuration strategy; the second determination unit 303 is used to determine at least two target financial products to be recommended to the target object from M financial products to be combined, based on the target template and the product characteristics of the financial products already held by the target object, where M is an integer greater than 1; the combination unit 304 is used to configure and combine at least two target financial products according to the target template and the profile information of the target object, to obtain a financial product combination and recommend it to the target object, wherein the configuration process of the financial product combination includes at least: configuring the recommended purchase amount, recommended holding period and recommended purchase time for each target financial product.

[0087] Optionally, the first determining unit 302 includes: a first determining subunit. The first determining subunit is used to input product features into the target model, segment the product features through multiple decision nodes of the target model, and transmit the segmented feature information obtained from each decision node to a leaf node of the target model. The leaf node, based on the received feature information, determines a target template corresponding to the target object from a preset set of N templates. Each decision node represents a feature filtering condition set based on the product features and the attribute information of the target object. The leaf node includes at least: target feature content corresponding to each of the N templates.

[0088] Optionally, the first determining subunit includes: a processing module, a first determining module, and a second determining module. The processing module is used to form a feature matrix from the feature information obtained from each decision node segmentation through leaf nodes; the first determining module is used to determine the similarity between the feature matrix and the target feature content corresponding to each template through leaf nodes; and the second determining module is used to determine the target template corresponding to the target object from a preset set of N templates based on the similarity.

[0089] Optionally, the financial product portfolio recommendation device further includes: a second acquisition unit and a generation unit. The second acquisition unit is used to acquire path information between decision nodes and leaf nodes during the prediction process of the target template, wherein the path information is used to characterize the process by which the target model gradually narrows the template selection range based on product characteristics and target object attribute information; the generation unit is used to generate a visualized report text based on the path information.

[0090] Optionally, the second determining unit 303 includes: an acquisition subunit and a second determining subunit. The acquisition subunit is used to acquire historical transaction information for each financial product to be combined; the second determining subunit is used to determine at least two target financial products to recommend to the target object from the M financial products to be combined, based on the target template, the historical transaction information of each financial product to be combined, and the product characteristics of the financial products already held by the target object.

[0091] Optionally, the second determining subunit includes: a conversion module, a third determining module, and a fourth determining module. The conversion module converts the configuration ratio of the target template and the product characteristics of the held financial products into feature vectors for model input. The third determining module inputs the feature vectors into a screening model, which determines the vector similarity between the feature vectors and the product feature vectors of each financial product to be combined. The fourth determining module determines at least two target financial products from the M financial products to be combined based on the vector similarity and the historical transaction information of each financial product to be combined.

[0092] Optionally, the fourth determining module includes: a first determining submodule and a second determining submodule. The first determining submodule is used to determine the risk-return ratio of each financial product to be combined based on its historical transaction information; the second determining submodule is used to determine at least two target financial products from the M financial products to be combined based on vector similarity and the risk-return ratio of each financial product to be combined.

[0093] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, which stores a computer program, wherein when the computer program is executed, it causes the device on which the computer-readable storage medium is located to perform the recommended method for the above-mentioned financial product combination.

[0094] According to another aspect of the embodiments of this application, an electronic device is also provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to perform the recommended method of the above-described financial product portfolio.

[0095] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program or instructions that, when executed by a processor, implement the recommended method for the above-described financial product portfolio.

[0096] The above-described embodiments or examples disclosed in this application are not exhaustive, but merely illustrative of some embodiments or examples, and are not intended to limit the scope of protection of this application. Unless otherwise specified, each step in a particular embodiment or example can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment or example can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment or example can be arbitrarily interchanged. Furthermore, optional methods or examples in a particular embodiment or example can be arbitrarily combined; moreover, various embodiments or examples can be arbitrarily combined. For example, some or all steps of different embodiments or examples can be arbitrarily combined, and a particular embodiment or example can be arbitrarily combined with optional methods or examples of other embodiments or examples.

[0097] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0098] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0099] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0100] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0101] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0102] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0103] The above are merely preferred embodiments of this application. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for recommending a portfolio of financial products, characterized in that, include: Obtain the product characteristics of the financial products already held by the target entity; Based on the product characteristics, a target template corresponding to the target object is determined from a preset set of N templates, where N is an integer greater than 1, and each of the N templates is used to provide a financial product configuration strategy. Based on the target template and the product characteristics of the financial products already held by the target object, at least two target financial products are determined from M financial products to be combined and recommended to the target object, where M is an integer greater than 1; Based on the target template and the profile information of the target object, the at least two target financial products are configured and combined to obtain a financial product portfolio, which is then recommended to the target object. The configuration process of the financial product portfolio includes at least configuring the recommended purchase amount, recommended holding period, and recommended purchase time for each target financial product.

2. The method for recommending financial product portfolios according to claim 1, characterized in that, Based on the product characteristics, a target template corresponding to the target object is determined from a preset set of N templates, including: The product features are input into the target model. The product features are segmented by multiple decision nodes of the target model. The feature information obtained by each decision node is transmitted to the leaf node of the target model. Based on the received feature information, the leaf node determines the target template corresponding to the target object from N preset templates. Each decision node is used to characterize a feature filtering condition set based on the product features and the attribute information of the target object; the leaf node includes at least the target feature content corresponding to each of the N templates.

3. The method for recommending financial product portfolios according to claim 2, characterized in that, Based on the feature information obtained from each decision node received, the leaf node determines the target template corresponding to the target object from a preset set of N templates, including: The feature matrix is ​​formed by segmenting the feature information of each decision node received through the leaf node. The similarity between the feature matrix and the target feature content corresponding to each template is determined by the leaf nodes; Based on the similarity, a target template corresponding to the target object is determined from a preset set of N templates.

4. The method for recommending financial product portfolios according to claim 2, characterized in that, The method for recommending the financial product portfolio also includes: During the prediction process of the target template, path information between the decision nodes and leaf nodes of the path is obtained, wherein the path information is used to characterize the process by which the target model gradually narrows the template selection range based on the product characteristics and the attribute information of the target object; A visual report text is generated based on the path information.

5. The method for recommending financial product portfolios according to claim 1, characterized in that, Based on the target template and the product characteristics of the financial products already held by the target object, at least two target financial products are determined from M financial products to be combined and recommended to the target object, including: Obtain historical transaction information for each financial product to be combined; Based on the target template, the historical transaction information of each financial product to be combined, and the product characteristics of the financial products already held by the target object, at least two target financial products to be recommended to the target object are determined from the M financial products to be combined.

6. The method for recommending financial product portfolios according to claim 5, characterized in that, Based on the target template, the historical transaction information of each financial product to be combined, and the product characteristics of the financial products already held by the target object, at least two target financial products are determined from the M financial products to be combined to recommend to the target object, including: The configuration ratio of the target template and the product characteristics of the financial products already held are converted into feature vectors for model input; The feature vector is input into the screening model, and the feature vector similarity between the feature vector and the product feature vector of each financial product to be combined is determined by the screening model. Based on the vector similarity and the historical transaction information of each financial product to be combined, at least two target financial products are determined from the M financial products to be combined.

7. The method for recommending financial product portfolios according to claim 6, characterized in that, Based on the vector similarity and the historical transaction information of each financial product to be combined, at least two target financial products are determined from the M financial products to be combined, including: Based on the historical transaction information of each financial product to be combined, determine the risk-return ratio of each financial product to be combined; Based on the vector similarity and the risk-return ratio of each financial product to be combined, at least two target financial products are determined from the M financial products to be combined.

8. A device for recommending financial product portfolios, characterized in that, include: The first acquisition unit is used to acquire the product characteristics of the financial products already held by the target object; The first determining unit is used to determine a target template corresponding to the target object from a preset set of N templates based on the product characteristics, wherein N is an integer greater than 1, and each of the N templates is used to provide a financial product configuration strategy. The second determining unit is used to determine, based on the target template and the product characteristics of the financial products already held by the target object, at least two target financial products to be recommended to the target object from M financial products to be combined, where M is an integer greater than 1; The combination unit is used to configure and combine the at least two target financial products based on the target template and the profile information of the target object, to obtain a financial product combination and recommend it to the target object. The configuration process of the financial product combination includes at least configuring the recommended purchase amount, recommended holding period and recommended purchase time for each target financial product.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein, when the computer program is executed, the device on which the computer-readable storage medium is located performs the method for recommending a portfolio of financial products as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, It includes one or more processors and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to perform the method for recommending a portfolio of financial products as described in any one of claims 1 to 7.

11. A computer program product, characterized in that, Includes a computer program or instructions that, when executed by a processor, implement the recommended method for a portfolio of financial products according to any one of claims 1 to 7.

Images