Product recommendation method and device, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides a product recommendation method and device, electronic equipment, a storage medium and a program product, and is applied to the technical field of big data, and the specific method comprises the following steps: obtaining investment feature information of a target customer from a customer management system, and vectorizing the investment feature information of the target customer to obtain an investment feature vector; determining a similar customer group of the target customer from the candidate customer group according to the investment feature vector of the target customer and the investment feature vector of the candidate customer in the candidate customer group; determining a template customer group from the similar customer groups according to the product investment incomes of the similar customers in the similar customer groups; matching a reference customer from the template customer group based on the predicted investment limit of the target customer; and based on the product investment portfolio condition of the reference customer, generating investment recommendation information for the target customer, and pushing the investment recommendation information to the terminal. According to the embodiment of the invention, comprehensiveness and diversification of recommendation can be ensured, and current market conditions and customer requirements can be better met.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of big data technology, and in particular, to a product recommendation method, device, electronic device, storage medium, and program product. Background Art

[0002] Purchasing financial products is a common investment behavior. Different amounts of funds usually correspond to different investment opportunities. Customers may not know about better investment opportunities due to lack of information channels. Therefore, it is necessary to make investment recommendations for financial products to customers.

[0003] Currently, some models are used to make investment recommendations for financial products. For example, a machine learning algorithm based on the gradient boosting framework (Light Gradient Boosting Machine, Light GBM) model is used to select multiple specific features (such as product features, transaction features, behavioral features, etc.), and a Deep Factorization Machine (Deep FM) algorithm is used to calculate the probability of a customer purchasing a certain financial product, and product recommendations are made based on probability. Features are reselected for model training every month, and customer feedback on the recommendation results is collected.

[0004] When using models to make financial product recommendations, the models and algorithms may rely too much on historical data and existing features, and lack dynamic adjustment to current market conditions and actual customer needs, resulting in the recommendation system often being out of touch with actual investment needs and market environment; and the algorithms often push specific products based on customers' historical behavior and preferences, over-emphasizing the recommendation of specific products without considering the diversity of customer needs and the comprehensiveness of recommendations. Summary of the invention

[0005] The embodiments of the present invention provide a product recommendation method, device, electronic device, storage medium and program product, which can ensure the comprehensiveness and diversity of recommendations and better adapt to current market conditions and customer needs.

[0006] In a first aspect, a product recommendation method provided by an embodiment of the present invention includes:

[0007] Acquire the investment characteristic information of the target customer from the customer management system, and vectorize the investment characteristic information of the target customer to obtain an investment characteristic vector;

[0008] Determine a customer group similar to the target customer from the candidate customer group according to the investment feature vector of the target customer and the investment feature vectors of the candidate customers in the candidate customer group;

[0009] Determine a template customer group from similar customer groups based on the product investment returns of similar customers in the similar customer groups;

[0010] Match reference customers from the template customer base based on the target customer's predicted investment amount;

[0011] Generate investment recommendation information for target customers based on the product investment portfolio of reference customers, and push the investment recommendation information to the terminal.

[0012] In a second aspect, an embodiment of the present invention provides a product recommendation device, including:

[0013] A vectorization module is used to obtain the investment characteristic information of the target customer from the customer management system, and vectorize the investment characteristic information of the target customer to obtain an investment characteristic vector;

[0014] A similar customer determination module is used to determine a similar customer group of the target customer from the candidate customer group based on the investment feature vector of the target customer and the investment feature vectors of the candidate customers in the candidate customer group;

[0015] A template customer determination module is used to determine a template customer group from a similar customer group based on product investment returns of similar customers in the similar customer group;

[0016] A matching module is used to match reference customers from the template customer group based on the predicted investment amount of the target customer;

[0017] The generation module is used to generate investment recommendation information for target customers based on the product investment portfolio of the reference customer, and push the investment recommendation information to the terminal.

[0018] In a third aspect, an electronic device provided by an embodiment of the present invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the program, a product recommendation method as in any embodiment of the present invention is implemented.

[0019] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, a product recommendation method as in any embodiment of the present invention is implemented.

[0020] In a fifth aspect, a computer program product provided by an embodiment of the present invention includes a computer program, and when the computer program is executed by a processor, the product recommendation method as described in any embodiment of the present invention is implemented.

[0021] In an embodiment of the present invention, by quantifying the investment characteristics of target customers and candidate customers and analyzing the investment returns of products of similar customer groups in real time, it is possible to better reflect the current market conditions and the actual needs of customers, and adjust the recommendation strategy by using dynamic data and real-time return information, so that the recommendation information is closer to the actual investment scenario; match reference customers from the template customer group based on the predicted investment amount of the target customer, and ensure that the recommended product portfolio is more suitable for the actual situation of the target customer; generate recommendation information based on the overall investment returns of similar customers and the investment portfolio of the template customer, consider the diversity of customer needs, provide comprehensive investment advice, rather than just the recommendation of a single product, and ensure the diversification and rationality of the investment portfolio; by analyzing the overall investment returns of similar customer groups and reference customers, the recommendation information provided can better balance returns and risks, and based on the actual investment situation of the reference customers, a more reasonable and risk-controlled investment portfolio can be recommended. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solution of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 is a flowchart of a product recommendation method provided by an embodiment of the present invention;

[0024] Figure 2 is another flowchart of the product recommendation method provided by an embodiment of the present invention;

[0025] Figure 3 is an example diagram of a reference client determination method provided by an embodiment of the present invention;

[0026] Figure 4 is a structural schematic diagram of a product recommendation device provided by an embodiment of the present invention;

[0027] Figure 5 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Figure 1 It is a flowchart of the product recommendation method provided by the embodiment of the present invention. The product recommendation method provided by the embodiment of the present invention can be applied to the scenario of recommending investment in financial products to customers. The product recommendation method can be executed by the product recommendation device provided by the embodiment of the present invention, and the device can be implemented in software and / or hardware. In a specific embodiment, the device can be integrated into an electronic device, and the electronic device can be a computer, a server, etc. The following embodiment is described by taking the example of integrating the product recommendation device into an electronic device. Figure 1 The product recommendation method of this embodiment may include the following steps:

[0031] Step 110, obtaining the investment characteristic information of the target customer from the customer management system, and vectorizing the investment characteristic information of the target customer to obtain an investment characteristic vector.

[0032] The customer management system is a system used to manage customer information. Target customers are customer groups or individuals that you want to study or serve. In the financial product recommendation system, target customers can be those who are using or intend to use the system to invest or manage their finances. Investment characteristic information is specific data and information about the customer's investment behavior and financial status. For example, investment characteristic information may include age, monthly income, monthly expenditure, total assets, investment frequency, single investment amount, various financial products invested and investment amount, investment ratio, etc.

[0033] Vectorization is the process of converting qualitative or quantitative data into vectors. Vectorization helps algorithms process and analyze these data in high-dimensional space. The vectorization process may involve data preprocessing steps such as standardization and normalization. Vectorization makes data more comparable and processable. An investment feature vector is a vector composed of investment feature information. This vector numerically represents each feature in turn. Through this representation, operations such as calculation, comparison, clustering and prediction can be easily performed.

[0034] Various investment-related characteristic information of target customers can be collected, and then these characteristics can be quantified, that is, put into the form of vectors. Such vectors can be used for further data analysis to better understand customers' investment behaviors and preferences and make accurate financial product recommendations.

[0035] Step 120: determining a customer group similar to the target customer from the candidate customer group based on the investment feature vector of the target customer and the investment feature vectors of the candidate customers in the candidate customer group.

[0036] The candidate customer group refers to a set of all potential customers. The present invention aims to determine customers with similar characteristics to the target customers from the candidate customer group. The investment feature vector of the candidate customer is the investment feature data vector of each customer in the candidate customer group. These vectors have the same format as the investment feature vector of the target customer and are used for comparison and matching. The similar customer group refers to a group of customers selected from the candidate customer group that are similar to the target customer in characteristics. This group of customers is closest to the target customer in terms of the measurement of the investment feature vector.

[0037] Specifically, appropriate measurement methods (such as Euclidean distance, cosine similarity or Mahalanobis distance) can be used to calculate the similarity between the target customer and the investment feature vector of each customer in the candidate customer group. Based on the calculated similarity, the candidate customers closest to the target customer feature vector are selected to form a similar customer group. By quantifying the investment feature vectors of the target customer and the candidate customer and using the similarity measurement method, other customers with similar characteristics to the target customer can be effectively identified and classified. This not only helps to better understand the behavior patterns of the target customers, but also provides customers with more accurate personalized recommendations or services.

[0038] Step 130 , determining a template customer group from the similar customer group based on the product investment returns of similar customers in the similar customer group.

[0039] The product investment income of similar customers refers to the investment return of each customer in the similar customer group on different financial products. The template customer group is a group of customers further screened from the similar customer group, whose investment performance on specific products (such as the highest investment return rate) is particularly outstanding or representative. The investment behavior of the template customer group can be used as a reference template for target customers, thereby optimizing the investment strategy of target customers.

[0040] By further screening customers with outstanding investment returns from similar customer groups, a template customer group can be determined. The investment behavior and returns of the template customer group can provide target customers with more valuable investment advice, helping them optimize their investment strategies and achieve higher returns.

[0041] Step 140 , matching reference customers from the template customer group based on the predicted investment amount of the target customer.

[0042] The predicted investment amount refers to the prediction of the target customer's possible future investment amount based on factors such as the target customer's historical investment behavior, financial status, and risk preference. For example, the predicted investment amount can be obtained through a machine learning model or statistical analysis method. Matching refers to finding a template customer whose characteristics are closest to the target customer based on certain criteria (such as the predicted investment amount, etc.). This process involves comparing the predicted investment amount of the target customer with the actual investment amount of each customer in the template customer base, and selecting the closest customer from them. Reference customers are customers selected from the template customer base who are most compatible with the target customer in terms of predicted investment amount. The investment behavior and return performance of reference customers can provide valuable references for target customers.

[0043] Specifically, the historical investment data of each customer in the template customer group can be collected, especially the actual investment amount of each customer in different investment products, and the predicted investment amount of the target customer can be compared with the actual investment amount of each customer in the template customer group. Use a suitable matching algorithm (such as the minimum Euclidean distance method) to find those customers whose predicted amount is closest to the target customer, and use the found customers as reference customers.

[0044] Based on the predicted investment amount of the target customer, the closest reference customer is matched from the template customer group, which can provide the target customer with valuable investment reference. This process utilizes the characteristic data of the target customer and the template customer group, and effectively finds the most suitable investment reference through the matching algorithm, thereby helping the target customer optimize its investment decision.

[0045] Step 150: Generate investment recommendation information for the target customer based on the product investment portfolio of the reference customer, and push the investment recommendation information to the terminal.

[0046] Product investment portfolio refers to the reference customer's investment allocation and combination in various financial products (such as stocks, funds, bonds, etc.), which may include information such as the investment ratio, investment strategy and specific amount of each type of product. Investment recommendation information is personalized investment advice provided to target customers based on the reference customer's investment portfolio. These suggestions may include recommended financial products, investment ratios, investment strategies, etc., to help target customers make better investment decisions. That is, by analyzing the reference customer's investment allocation and combination in various financial products, personalized investment advice suitable for target customers is generated. These suggestions will help target customers optimize their investment portfolios, increase returns or reduce risks. The terminal is the terminal used by the target customer, which can be the target customer's mobile phone, personal computer, etc. Investment recommendation information can be pushed to the target customer through e-mail, text messages, application notifications, etc.

[0047] In this embodiment, by quantifying the investment characteristics of target customers and candidate customers and analyzing the product investment returns of similar customer groups in real time, it is possible to better reflect the current market conditions and the actual needs of customers, and use dynamic data and real-time return information to adjust the recommendation strategy so that the recommendation information is closer to the actual investment scenario; based on the predicted investment amount of the target customer, a reference customer is matched from the template customer group to ensure that the recommended product portfolio is more suitable for the actual situation of the target customer; based on the overall investment returns of similar customers and the investment portfolio of the template customer, recommendation information is generated, taking into account the diversity of customer needs, and providing comprehensive investment advice rather than just the recommendation of a single product, ensuring the diversification and rationality of the investment portfolio; by analyzing the overall investment returns of similar customer groups and reference customers, the recommendation information provided can better balance returns and risks, and based on the actual investment situation of the reference customer, a more reasonable and risk-controlled investment portfolio can be recommended.

[0048] The following further illustrates the product recommendation method provided by the embodiment of the present invention. Figure 2 As shown, the method of this embodiment may include:

[0049] Step 201 , using principal component analysis to analyze the target customer's investment characteristic information, to obtain the main characteristic information that affects the target customer's investment behavior.

[0050] Principal Component Analysis (PCA) is a statistical technique for dimensionality reduction and data simplification. It reduces the dimensionality of data by converting the original data into a set of linearly unrelated variables (called principal components) while retaining the variance of the data as much as possible. PCA is often used to reveal the most important features or patterns in the data and simplify the complexity of the data. The main feature information is the data features extracted by PCA that best explain the investment behavior of the target customers. These features can have the highest explained variance in the original data and represent the most critical or relatively critical factors for the customer's investment behavior.

[0051] Specifically, various characteristic information related to the target customer's investment behavior can be collected from the target customer's historical investment data, such as income, investment amount, risk preference, etc. The collected investment characteristic information is standardized to ensure that each feature has the same magnitude. PCA is used to analyze the standardized data set, and the eigenvectors and eigenvalues ​​are calculated to transform the original characteristic data into a new principal component space. According to the size of the eigenvalue, the first few principal components with larger explained variance are selected as the main characteristic information. For example, the target customer's investment characteristic information includes 10 characteristic information such as income, investment amount, and risk preference. The main characteristic information obtained after PCA analysis can include 2 characteristic information of income and investment amount.

[0052] By using principal component analysis to analyze the target customer's investment characteristics, we can effectively extract and identify the key characteristics that best explain and influence the customer's investment behavior. These main characteristics help to better understand the customer's investment habits and motivations, and provide a basis for further personalized investment advice and decision support. This method can not only simplify the complexity of the data, but also improve the accuracy and effectiveness of data interpretation.

[0053] Step 202, quantize the main feature information to obtain an investment feature vector.

[0054] The main feature information extracted through analysis is vectorized and converted into an investment feature vector. This vectorization process makes the feature information suitable for further calculation and analysis.

[0055] Step 203: determining a mean vector according to the investment feature vector of the target customer and the investment feature vectors of the candidate customers in the candidate customer group.

[0056] The mean vector is a vector obtained by averaging the values ​​of multiple investment feature vectors in each dimension. It represents the average performance of a customer group in each feature dimension.

[0057] Step 204, calculating the degree of center deviation of each candidate customer based on the investment feature vector and mean vector of the candidate customer.

[0058] The degree of center deviation refers to the difference or distance between the candidate customer's investment feature vector and the mean vector. Distance measurement methods (such as Mahalanobis distance and Euclidean distance) are usually used to calculate this degree of deviation, indicating the degree of deviation of the candidate customer from the average level of the group in each feature dimension. This calculation helps to identify which customers' characteristics are significantly different from the average characteristics of the group, so as to obtain better customer feature characterization and classification. The formula for measuring the degree of center deviation of candidate customers using Mahalanobis distance can be as follows:

[0059]

[0060] Among them, d represents the degree of central deviation of the candidate customer, x represents the investment feature vector of the candidate customer, μ represents the mean vector, T represents the transpose, and Σ represents the sample covariance matrix.

[0061] Step 205 , selecting candidate customers whose center deviation degree is lower than a preset deviation degree from the candidate customer group to obtain a similar customer group.

[0062] The preset deviation degree is a pre-set threshold used to determine whether the central deviation degree of the candidate customer is within an acceptable range. The similar customer group is a customer group selected from the candidate customer group. The central deviation degree of these customers is lower than the preset deviation degree, which means that they have a high similarity with the target customer in investment characteristics.

[0063] By selecting those candidate customers whose central deviation is lower than the preset deviation from the candidate customer group, customers with high similarity in investment characteristics with the target customers can be effectively identified. These selected customers form a similar customer group, and such a screening process helps to further refine customer analysis.

[0064] Step 206, calculating the sum of the investment income of similar customers in various financial products to obtain the product investment income of similar customers.

[0065] By summarizing the investment returns of similar customers on various financial products, the total investment returns of these customers on each financial product are calculated. This result reflects the collective investment performance of similar customer groups on various financial products.

[0066] Step 207, selecting similar customers whose product investment income exceeds the preset investment income from the similar customer group to obtain a template customer group.

[0067] The preset investment income is a preset income threshold. The template customer group is a customer group obtained by further screening. These customers are not only similar to the target customers in terms of feature vectors, but also their product investment income exceeds the preset investment income level.

[0068] Furthermore, the template customer group can be classified according to the mode of investment amount, that is, the customers in the template customer group are classified according to their investment amount data, wherein the classification standard is based on the mode of investment amount, that is, grouping according to the investment amount value with the highest frequency. For example, the investment amount of each customer in a certain financial product or multiple financial products can be obtained from the template customer group; the number of occurrences of each investment amount in the template customer group is counted to find the investment amount with the highest number of occurrences, that is, the mode; and the customers in the template customer group are divided into different categories according to the calculated mode of investment amount. For example, it can be divided into three categories: "higher than the mode", "equal to the mode" and "lower than the mode".

[0069] Classifying the template customer groups by the mode of investment amount can analyze the differences in customer investment behavior in more detail. This classification method can reveal the distribution and performance differences between customers at the most typical level of investment amount (i.e., the mode) and those who invest more money, which is important for formulating more targeted financial product recommendation strategies, personalized marketing strategies, and improving customer investment results. The classification results not only reflect the concentration trend of customers in investment amount, but also distinguish customer groups at different investment amount levels, thus providing a reference for further precise analysis and services.

[0070] Step 208: predicting the target customer's income in a future preset period based on the target customer's income in a past preset period.

[0071] The preset time period in the past is, for example, the past three months, six months, or one year. The preset time period in the future is, for example, the next month.

[0072] Step 209, predicting the investment amount of the target customer in a future preset period of time based on the target customer's investment characteristic information and the income situation in a future preset period of time, and obtaining a predicted investment amount.

[0073] That is, using the target customer's investment characteristic information and his expected income in a certain period of time in the future, we can predict the possible investment amount in that future period and finally get a predicted investment amount. Investment characteristic information can be used to understand the customer's investment preferences, risk tolerance, historical investment behavior, etc. Based on the target customer's investment characteristic information and his income in the future preset period, we can predict his investment amount in the future preset period, which can help provide customized investment strategies, optimize resource allocation, and conduct effective risk management.

[0074] Specifically, the exponentially weighted moving average method can be used to predict the target customer's investment amount in the future preset period. Exponentially Weighted Moving Average (EWMA) is a time series analysis method that reflects the changing trend of data more quickly by assigning exponentially decreasing weights to past data. The formula for predicting the target customer's investment amount in the future preset period using the exponentially weighted moving average method can be as follows:

[0075]

[0076] in, represents the exponentially weighted moving average at time point K, i.e. the predicted investment amount. k-L+1 , X k-L+2 , X k-2 , X k-1 and X k Represents the actual observation sequence from k-L+1 to time point k, which represents the investment amount of the customer in the past L time periods, that is, the amount of funds in each period. L represents the number of periods used for calculation. λ is the weighting coefficient, a value between 0 and 1, which is used to determine the degree of influence of new data on the predicted value. The closer the λ value is to 1, the greater the influence of the new data, and the closer the λ value is to 0, the smaller the influence of the new data. In forecasting, λ can be used to adjust the sensitivity of the model to recent changes in the amount of funds. Initially set λ to 1, and then the λ value can be corrected by the next period's income. is an adjustment factor used to ensure that the forecast values ​​are stable in the long run and do not grow or decrease indefinitely over time.

[0077] By combining the customer's funds in the past L time periods in a weighted average, the investment amount at a future time point K is predicted. By adjusting the lambda value, the model's sensitivity to recent changes in funds can be controlled, thereby more accurately predicting future changes in investment amounts and identifying whether the current customer will invest more in financial products in the next period.

[0078] Step 210: When the predicted investment amount exceeds the current investment amount, a reference customer is matched from the template customer group based on the predicted investment amount of the target customer.

[0079] If the predicted investment amount exceeds the current investment amount, it means that the target customer may change the investment product. Therefore, we can combine big data to make some investment recommendations to the target customer in a timely manner to improve the recommendation effect. Specifically, we can collect the investment amount of each customer in the template customer group and screen out customers whose investment amount is close to the predicted investment amount within a certain range, i.e., reference customers.

[0080] By predicting the investment amount and matching it with similar reference customers, target customers can optimize their investment decisions on a relatively safe and scientific basis, increase the chances of investment success and improve overall investment performance. Figure 3 is an example diagram of a method for determining a reference customer provided by an embodiment of the present invention. It can be seen that the reference customer is determined by gradually screening a candidate customer group, a similar customer group, and a template customer group.

[0081] Step 211, based on the reference customer's investment situation in various financial products, determine the financial products recommended to the target customer and the recommended amount of each financial product.

[0082] You can refer to the investment data of customers in different financial products. For example, the investment data of the reference customer's investment portfolio may include stocks, bonds, funds, etc., and the investment proportion and amount of each financial product. According to the reference customer's investment portfolio, select financial products with higher performance and matching degree to recommend to the target customer. For example, if the reference customer has better investment performance in stocks and funds, these financial products can be recommended first. The specific investment amount of each recommended financial product can be determined based on the reference customer's investment proportion and the target customer's predicted investment amount. For example, if the reference customer invests 40% in stocks and 60% in funds, and the target customer's predicted investment amount is 15,000, then the recommended amount is stocks: 15,000*40%=6,000; funds: 15,000*60%=9,000.

[0083] Recommending financial products to target customers and determining recommended amounts based on the investment situation of reference customers can provide more accurate, personalized and professional investment advice, helping target customers optimize their investment portfolios while controlling risks, and achieving financial goals and maximizing benefits.

[0084] Step 212, verify whether the recommended amount of each financial product is higher than the investment threshold of the corresponding financial product.

[0085] The investment threshold refers to the minimum investment amount for each financial product. Customers must invest at least this amount to purchase the financial product.

[0086] Step 213, when the recommended amount of each financial product is higher than the investment threshold of the corresponding financial product, generate investment recommendation information based on the financial products recommended to the target customer and the recommended amount of each financial product, and push the investment recommendation information to the terminal.

[0087] Investment recommendation information is the actual investment advice generated based on the financial products recommended to customers and their recommended amounts. It can be checked whether the investment amount of each financial product recommended for the target customer exceeds the minimum investment requirement of the product. If the investment amount of all recommended financial products is higher than the corresponding minimum investment threshold, a detailed investment advice is generated based on these recommended financial products and their amounts. By verifying the recommended amount and generating detailed investment recommendation information, customers can invest under accurate guidance to ensure the accuracy and effectiveness of investment decisions.

[0088] In this embodiment, by quantifying the investment characteristics of target customers and candidate customers and analyzing the product investment returns of similar customer groups in real time, it is possible to better reflect the current market conditions and the actual needs of customers, and use dynamic data and real-time return information to adjust the recommendation strategy so that the recommendation information is closer to the actual investment scenario; based on the predicted investment amount of the target customer, a reference customer is matched from the template customer group to ensure that the recommended product portfolio is more suitable for the actual situation of the target customer; based on the overall investment returns of similar customers and the investment portfolio of the template customer, recommendation information is generated, taking into account the diversity of customer needs, and providing comprehensive investment advice rather than just the recommendation of a single product, ensuring the diversification and rationality of the investment portfolio; by analyzing the overall investment returns of similar customer groups and reference customers, the recommendation information provided can better balance returns and risks, and based on the actual investment situation of the reference customer, a more reasonable and risk-controlled investment portfolio can be recommended.

[0089] Figure 4 is a schematic diagram of a product recommendation device provided in an embodiment of the present invention, and the device is suitable for executing the product recommendation method provided in an embodiment of the present invention, such as Figure 4 As shown, the device may specifically include:

[0090] A vectorization module 401 is used to obtain investment characteristic information of target customers from a customer management system, and vectorize the investment characteristic information of the target customers to obtain an investment characteristic vector;

[0091] A similar customer determination module 402 is used to determine a similar customer group of the target customer from the candidate customer group based on the investment feature vector of the target customer and the investment feature vectors of the candidate customers in the candidate customer group;

[0092] The template customer determination module 403 is used to determine a template customer group from the similar customer group according to the product investment income of similar customers in the similar customer group;

[0093] A matching module 404 is used to match reference customers from the template customer group based on the predicted investment amount of the target customer;

[0094] The generating module 405 is used to generate investment recommendation information for target customers based on the product investment portfolio of the reference customer, and push the investment recommendation information to the terminal.

[0095] In one embodiment, the vectorization module 401 vectorizes the investment feature information of the target customer to obtain an investment feature vector, including:

[0096] Use principal component analysis to analyze the target customers' investment characteristics and obtain the main characteristics that affect the target customers' investment behavior;

[0097] The main feature information is vectorized to obtain the investment feature vector.

[0098] In one embodiment, the similar customer determination module 402 determines a similar customer group of the target customer from the candidate customer group according to the investment feature vector of the target customer and the investment feature vectors of the candidate customers in the candidate customer group, including:

[0099] Determine a mean vector according to the investment feature vector of the target customer and the investment feature vector of the candidate customer in the candidate customer group;

[0100] Calculate the degree of central deviation of each candidate customer based on the investment feature vector and mean vector of the candidate customer;

[0101] Select candidate customers whose center deviation degree is lower than a preset deviation degree from the candidate customer group to obtain a similar customer group.

[0102] In one embodiment, the template customer determination module 403 determines a template customer group from a similar customer group according to product investment returns of similar customers in the similar customer group, including:

[0103] Calculate the sum of investment returns of similar customers on various financial products to obtain product investment returns of similar customers;

[0104] Similar customers whose product investment income exceeds the preset investment income are selected from the similar customer groups to obtain a template customer group.

[0105] In one embodiment, before matching a reference customer from the template customer group based on the predicted investment amount of the target customer, the matching module 404 is further configured to:

[0106] Predict the target customer's income in a future preset period based on the target customer's income in the past preset period;

[0107] Predicting the investment amount of the target customer in a future preset period of time based on the target customer's investment characteristic information and the income situation in a future preset period of time to obtain a predicted investment amount;

[0108] When the predicted investment amount exceeds the current investment amount, a reference customer is matched from the template customer group based on the predicted investment amount of the target customer.

[0109] In one embodiment, the product investment portfolio of the reference customer includes the investment of the reference customer in various financial products. The generating module 405 generates investment recommendation information for the target customer based on the product investment portfolio of the reference customer, including:

[0110] Determine the financial products recommended to target customers and the recommended amount of each financial product based on the reference customer's investment in each financial product;

[0111] Verify whether the recommended amount of each financial product is higher than the investment threshold of the corresponding financial product;

[0112] When the recommended amount of each financial product is higher than the investment threshold of the corresponding financial product, investment recommendation information is generated based on the financial products recommended to the target customers and the recommended amount of each financial product.

[0113] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the functional modules described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0114] The device of the embodiment of the present invention can better reflect the current market conditions and the actual needs of customers by quantifying the investment characteristics of target customers and candidate customers and analyzing the product investment returns of similar customer groups in real time, and adjust the recommendation strategy by using dynamic data and real-time return information to make the recommendation information closer to the actual investment scenario; match reference customers from the template customer group based on the predicted investment amount of the target customer to ensure that the recommended product portfolio is more suitable for the actual situation of the target customer; generate recommendation information based on the overall investment returns of similar customers and the investment portfolio of the template customer, consider the diversity of customer needs, provide comprehensive investment advice, rather than just the recommendation of a single product, to ensure the diversification and rationality of the investment portfolio; through the overall investment return analysis of similar customer groups and reference customers, the recommendation information provided can better balance returns and risks, and based on the actual investment situation of the reference customer, a more reasonable and risk-controlled investment portfolio can be recommended.

[0115] Reference below Figure 5 , which shows a schematic diagram of the structure of a computer system 500 of an electronic device suitable for implementing an embodiment of the present invention. Figure 5The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0116] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage part 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the computer system 500 are also stored. The CPU 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0117] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed, so that a computer program read therefrom is installed into the storage section 508 as needed.

[0118] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 509, and / or installed from the removable medium 511. When the computer program is executed by the central processing unit (CPU) 501, the above-mentioned functions defined in the system of the present invention are executed.

[0119] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0120] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0121] The modules and / or units involved in the embodiments of the present invention described in the embodiments may be implemented by software or hardware. The modules and / or units described may also be arranged in a processor, for example, it may be described as follows: a processor includes a vectorization module, a similar client determination module, a template client determination module, a matching module, and a generation module. The names of these modules do not, in some cases, constitute limitations on the modules themselves.

[0122] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes:

[0123] The investment characteristic information of the target customer is obtained from the customer management system, and the investment characteristic information of the target customer is vectorized to obtain the investment characteristic vector; based on the investment characteristic vector of the target customer and the investment characteristic vector of the candidate customer in the candidate customer group, a similar customer group of the target customer is determined from the candidate customer group; based on the product investment income of similar customers in the similar customer group, a template customer group is determined from the similar customer group; based on the predicted investment amount of the target customer, a reference customer is matched from the template customer group; based on the product investment portfolio of the reference customer, investment recommendation information for the target customer is generated, and the investment recommendation information is pushed to the terminal.

[0124] The technical solution of the embodiment of the present invention can better reflect the current market situation and the actual needs of customers by quantifying the investment characteristics of target customers and candidate customers and analyzing the product investment returns of similar customer groups in real time, and adjust the recommendation strategy by using dynamic data and real-time return information to make the recommendation information closer to the actual investment scenario; match reference customers from the template customer group based on the predicted investment amount of the target customer to ensure that the recommended product portfolio is more suitable for the actual situation of the target customer; generate recommendation information based on the overall investment returns of similar customers and the investment portfolio of the template customer, consider the diversity of customer needs, provide comprehensive investment advice, rather than just the recommendation of a single product, to ensure the diversification and rationality of the investment portfolio; through the analysis of the overall investment returns of similar customer groups and reference customers, the recommendation information provided can better balance returns and risks, and based on the actual investment situation of the reference customers, a more reasonable and risk-controlled investment portfolio can be recommended.

[0125] An embodiment of the present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the product recommendation method provided in any embodiment of the present application.

[0126] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0127] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0128] It should be noted that the collection, use, storage, sharing and transfer of customer personal information involved in the technical solution of the present invention are in compliance with the provisions of relevant laws and regulations, and the customer needs to be informed and obtain the customer's consent or authorization. When applicable, the customer's personal information is de-identified and / or anonymized and / or encrypted. In addition, the corresponding operation portal is provided for customers to choose to agree or refuse the automated decision-making results; if the customer chooses to refuse, the expert decision-making process will be entered.

[0129] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A product recommendation method, characterized in that: include: Acquire the investment characteristic information of the target customer from the customer management system, and vectorize the investment characteristic information of the target customer to obtain an investment characteristic vector; Determine a customer group similar to the target customer from the candidate customer group according to the investment feature vector of the target customer and the investment feature vectors of the candidate customers in the candidate customer group; Determine a template customer group from similar customer groups based on the product investment returns of similar customers in the similar customer groups; Match reference customers from the template customer base based on the target customer's predicted investment amount; Generate investment recommendation information for target customers based on the product investment portfolio of reference customers, and push the investment recommendation information to the terminal.

2. The product recommendation method according to claim 1, characterized in that: Quantize the target customer's investment feature information to obtain an investment feature vector, including: Use principal component analysis to analyze the target customers' investment characteristics and obtain the main characteristics that affect the target customers' investment behavior; The main feature information is vectorized to obtain the investment feature vector.

3. The product recommendation method according to claim 1, characterized in that: According to the investment feature vector of the target customer and the investment feature vector of the candidate customer in the candidate customer group, a customer group similar to the target customer is determined from the candidate customer group, including: Determine a mean vector according to the investment feature vector of the target customer and the investment feature vector of the candidate customer in the candidate customer group; Calculate the degree of central deviation of each candidate customer based on the investment feature vector and mean vector of the candidate customer; Select candidate customers whose center deviation degree is lower than a preset deviation degree from the candidate customer group to obtain a similar customer group.

4. The product recommendation method according to claim 1, characterized in that: Based on the product investment returns of similar customers in the similar customer group, a template customer group is determined from the similar customer group, including: Calculate the sum of investment returns of similar customers on various financial products to obtain product investment returns of similar customers; Similar customers whose product investment income exceeds the preset investment income are selected from the similar customer groups to obtain a template customer group.

5. The product recommendation method according to claim 1, characterized in that: Before matching reference customers from the template customer base based on the predicted investment amount of the target customer, it also includes: Predict the target customer's income in a future preset period based on the target customer's income in the past preset period; Predicting the investment amount of the target customer in a future preset period of time based on the target customer's investment characteristic information and the income situation in a future preset period of time to obtain a predicted investment amount; When the predicted investment amount exceeds the current investment amount, a trigger is executed to match a reference customer from the template customer group based on the predicted investment amount of the target customer.

6. The product recommendation method according to any one of claims 1 to 5, characterized in that: The product investment portfolio of the reference customer includes the investment situation of the reference customer in various financial products, and generates investment recommendation information for the target customer based on the product investment portfolio of the reference customer, including: Determine the financial products recommended to target customers and the recommended amount of each financial product based on the reference customer's investment in each financial product; Verify whether the recommended amount of each financial product is higher than the investment threshold of the corresponding financial product; When the recommended amount of each financial product is higher than the investment threshold of the corresponding financial product, investment recommendation information is generated based on the financial products recommended to the target customers and the recommended amount of each financial product.

7. A product recommendation device, characterized in that: include: A vectorization module is used to obtain the investment characteristic information of the target customer from the customer management system, and vectorize the investment characteristic information of the target customer to obtain an investment characteristic vector; A similar customer determination module is used to determine a similar customer group of the target customer from the candidate customer group based on the investment feature vector of the target customer and the investment feature vectors of the candidate customers in the candidate customer group; A template customer determination module is used to determine a template customer group from a similar customer group based on product investment returns of similar customers in the similar customer group; A matching module is used to match reference customers from the template customer group based on the predicted investment amount of the target customer; The generation module is used to generate investment recommendation information for target customers based on the product investment portfolio of the reference customer, and push the investment recommendation information to the terminal.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the product recommendation method as described in any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the product recommendation method according to any one of claims 1 to 6 is implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the computer program implements the product recommendation method according to any one of claims 1 to 6.

Images