Investment recommendation method and device, equipment, medium and product

Abstract

The invention discloses an investment recommendation method and device, equipment, a medium and a product. Relates to the technical field of finance and artificial intelligence, and comprises the following steps: if an investment recommendation request sent by a target user is detected, determining an investment demand, candidate financial products, investment analysis data and user information data of the target user, and preprocessing the investment analysis data and the user information data; determining a risk tolerance category and a financial product proportion condition of the target user, and performing feature extraction processing on the preprocessed investment analysis data to obtain corresponding analysis features; and inputting the analysis features into a preset price prediction model to obtain prediction information of each candidate financial product, and determining a target financial product based on a preset optimization algorithm according to the prediction information, the investment demand, the financial product proportion condition and the risk tolerance category to perform investment recommendation on the target user. According to the method, personalized investment recommendation can be performed for the user, and the investment decision-making efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of finance and artificial intelligence technology, and in particular to an investment recommendation method, device, equipment, medium and product. Background Art

[0002] In the current financial investment field, traditional bank investment services face many challenges. On the one hand, it is difficult to quickly and accurately process massive amounts of financial data when conducting market analysis and investment decisions manually, resulting in low investment decision-making efficiency and prone to errors. On the other hand, when customizing investment plans for customers, it is often impossible to accurately match the risk tolerance of customers, resulting in uneven investment results.

[0003] Therefore, how to combine the price prediction model to conduct a comprehensive analysis of the investment analysis data, obtain accurate prediction information, further consider the user's risk tolerance, provide personalized investment recommendations for users, and improve investment decision-making efficiency is an urgent problem to be solved. Summary of the invention

[0004] The present invention provides an investment recommendation method, device, equipment, medium and product to make personalized investment recommendations for users and improve investment decision-making efficiency.

[0005] According to one aspect of the present invention, there is provided an investment recommendation method, comprising:

[0006] If an investment recommendation request sent by a target user is detected, the target user's investment needs, candidate financial products, investment analysis data and user information data are determined, and the investment analysis data and user information data are pre-processed;

[0007] Determine the risk tolerance category and proportion of financial products of the target user, and perform feature extraction processing on the pre-processed investment analysis data to obtain corresponding analysis features; the analysis features include at least one of the following: price trend features, volatility features, indicator features, and quantitative features;

[0008] The analysis features are input into the preset price prediction model to obtain the prediction information of each candidate financial product. Based on the prediction information, investment demand, proportion of financial products and risk tolerance category, the target financial product is determined based on the preset optimization algorithm to make investment recommendations to the target users.

[0009] According to another aspect of the present invention, there is provided an investment recommendation device, comprising:

[0010] A preprocessing module, for determining the investment needs, candidate financial products, investment analysis data and user information data of the target user if an investment recommendation request sent by the target user is detected, and preprocessing the investment analysis data and user information data;

[0011] An extraction processing module is used to determine the risk tolerance category and financial product proportion of the target user, and perform feature extraction processing on the pre-processed investment analysis data to obtain corresponding analysis features; the analysis features include at least one of the following: price trend features, volatility features, indicator features, and quantitative features;

[0012] The recommendation module is used to input the analysis features into the preset price prediction model to obtain the prediction information of each candidate financial product, and determine the target financial product based on the preset optimization algorithm according to the prediction information, investment demand, proportion of financial products and risk tolerance category, so as to make investment recommendations to the target users.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the investment recommendation method described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the investment recommendation method described in any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the investment recommendation method of any embodiment of the present invention is implemented.

[0019] The technical solution of the embodiment of the present invention, if an investment recommendation request sent by a target user is detected, the investment needs, candidate financial products, investment analysis data and user information data of the target user are determined, and the investment analysis data and user information data are preprocessed; the risk tolerance category and the proportion of financial products of the target user are determined, and the preprocessed investment analysis data is subjected to feature extraction processing to obtain corresponding analysis features; the analysis features are input into a preset price prediction model to obtain prediction information of each candidate financial product, and the target financial product is determined based on the prediction information, investment needs, proportion of financial products and risk tolerance category, based on a preset optimization algorithm, to make investment recommendations to the target user. The present invention can improve the accuracy of the prediction results by performing comprehensive feature extraction on the investment analysis data, considering price trend characteristics, fluctuation characteristics, indicator characteristics and quantitative characteristics for prediction, and further, by combining the user's risk tolerance for investment recommendations, the user's investment needs can be fully considered to improve the efficiency of investment decision-making.

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

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

[0022] Figure 1 is a flow chart of an investment recommendation method provided by Embodiment 1 of the present invention;

[0023] Figure 2 is a flow chart of an investment recommendation method provided by Embodiment 2 of the present invention;

[0024] Figure 3 is a structural block diagram of an investment recommendation device provided by Embodiment 3 of the present invention;

[0025] Figure 4 It is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0026] 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.

[0027] It should be noted that the terms "first", "second", "target", "candidate", "alternative", 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 interchangeable 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. The acquisition, storage, use, processing, etc. of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0028] It should be noted that the user information collected in the present invention is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or reject automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered.

[0029] Embodiment 1

[0030] Figure 1 1 is a flow chart of an investment recommendation method provided in the first embodiment of the present invention; this embodiment can be applied to the situation where a banking business system predicts the trend of financial products and makes investment recommendations in combination with the risk-bearing capacity of users. The method can be executed by an investment recommendation device, which can be implemented in the form of hardware and / or software. The investment recommendation device can be configured in an electronic device, such as a bank's business system, such as Figure 1 As shown, the investment recommendation method includes:

[0031] S101. If an investment recommendation request sent by a target user is detected, the investment needs, candidate financial products, investment analysis data and user information data of the target user are determined, and the investment analysis data and user information data are pre-processed.

[0032] Among them, the target user may be a customer of the banking system service. The investment recommendation request refers to a request for investment recommendation issued by the target user on the banking system. The investment demand refers to the demand of the target user for the corresponding investment period, and the investment demand may specifically be a short investment period and a long investment period. The candidate financial product refers to the financial product that the target user can choose in the banking system. The investment analysis data may include at least one of the following: financial product price data (such as stock, bond and fund prices), market transaction data (such as trading volume and turnover rate, etc.), macroeconomic indicator data (such as GDP growth rate, inflation rate and interest rate, etc.) and financial news data. The user information data may include personal information data and investment history data, and may specifically include at least one of the following information of the target user: age, income, asset size, investment goals and risk preference.

[0033] Optionally, if an investment recommendation request sent by a target user is detected, the investment recommendation request can be parsed to determine the target user's investment needs, and matched in the bank's internal customer information database based on the target user's identification information to obtain user information data, and obtain the latest investment analysis data and candidate financial products from the preset database.

[0034] Optionally, the banking system may periodically collect data through real-time data interfaces of financial markets, authoritative financial news websites and third-party financial data suppliers to obtain the latest investment analysis data and store it in a preset database.

[0035] Optionally, the investment analysis data and user information data are preprocessed, including: using a preset anomaly detection method to identify and eliminate anomalies in the investment analysis data, and interacting with a preset verification system to verify and adjust the user information data based on the interaction results; according to the data category of the investment analysis data, determining the corresponding standardization method to standardize the financial product price data and macroeconomic indicator data in the investment analysis data, respectively.

[0036] The preset anomaly detection method may be a method based on statistical distribution (such as the 3-sigma principle) or an anomaly detection algorithm based on the isolation forest algorithm. The preset verification system may be an identity authentication system and / or a credit reporting system. The interaction result may characterize whether the user information data of the target user is erroneous or incomplete. The data category may be financial product price data, market transaction data, macroeconomic indicator data, or financial news data.

[0037] For example, for the price data of financial products in the investment analysis data, an abnormal situation may occur, such as a sudden and large fluctuation in stock prices due to a trading system failure or an individual abnormal transaction. Accordingly, the outliers can be identified and eliminated by combining statistical distribution-based methods (such as the 3-sigma principle) with anomaly detection algorithms in machine learning (such as the isolation forest algorithm).

[0038] Optionally, the user information data of the target user can be sent to a preset verification system, i.e., an identity verification system and a credit reporting system, to respectively verify the identity of the user and to inquire whether the user's credit meets the investment recommendation conditions. If so, it is further determined whether the user's identity information is erroneous or incomplete. If so, the user's identity information is supplemented and improved through the preset verification system, that is, the preset verification system is interacted with to verify and adjust the user information data according to the interaction results.

[0039] Optionally, for financial product price data, the minimum-maximum standardization method can be used to map the price data to a specific interval for subsequent processing. For macroeconomic indicator data, the Z-score standardization method can be used to make the mean 0 and the standard deviation 1 according to its economic significance and data distribution characteristics to complete the standardization process.

[0040] It should be noted that the above-mentioned embodiment of the present invention provides an implementable method for preprocessing investment analysis data and user information data, which can help improve the accuracy of subsequent feature extraction.

[0041] S102: Determine the risk tolerance category and financial product proportion of the target user, and perform feature extraction processing on the pre-processed investment analysis data to obtain corresponding analysis features.

[0042] Among them, the risk tolerance category can represent the risk tolerance level of the target user, and the risk tolerance category can include conservative, stable, balanced and aggressive. The proportion of financial products can include the proportion of low-risk financial products, high-risk financial products, high-liquidity financial products and low-liquidity financial products respectively. The analysis characteristics include at least one of the following: price trend characteristics, volatility characteristics, indicator characteristics and quantitative characteristics.

[0043] Optionally, determining the risk tolerance category and proportion of financial products of the target user includes: evaluating the risk tolerance level of the target user based on the pre-processed user information data to obtain the risk tolerance category; determining the proportion of low-risk financial products and high-risk financial products based on the risk tolerance category of the target user, and determining the proportion of high-liquidity financial products and low-liquidity financial products based on the investment needs of the target user to obtain the proportion of financial products. Among them, the risk tolerance category is conservative, stable, balanced or aggressive.

[0044] Optionally, the user's age, income stability, asset size and behavior patterns can be determined based on user information data to assess the target user's risk tolerance level and obtain a risk tolerance category, where the behavior pattern can be, for example, the customer's trading frequency in the face of market fluctuations, whether there is any rising and falling behavior, and the tolerance of different types of risks (such as market risk, credit risk, liquidity risk, etc.).

[0045] Optionally, if the risk tolerance category is conservative, the proportion of low-risk financial products can be determined as a preset high proportion, i.e. 70%-80%; if the risk tolerance category is aggressive, the proportion of high-risk financial products can be determined as a preset higher proportion, i.e. 60%-70%.

[0046] Optionally, the investment period can be determined based on the investment needs of the target users to determine the proportion of high-liquidity financial products and low-liquidity financial products respectively. Specifically, it can be determined based on the investment needs whether the target investment period of the target users is short-term investment or long-term investment. If it is a short-term investment, high-liquidity financial products can be determined as the preset high proportion. If it is a long-term investment, low-liquidity financial products can be determined as the preset high proportion.

[0047] It should be noted that by evaluating user information data, the target users' risk tolerance categories are divided into four categories, and the proportion of different financial products is further adjusted according to different categories. This can more comprehensively evaluate the user's risk-bearing capacity and adjust the proportion of different financial products accordingly, thereby better recommending products to users.

[0048] Optionally, feature extraction processing is performed on the financial product price data in the investment analysis data to obtain price trend features, volatility features and indicator features; and macroeconomic indicator data and financial news data in the investment analysis data are quantified to determine corresponding quantitative features.

[0049] Among them, price trend characteristics can be short-term, medium-term and long-term price trends determined by methods such as moving average and exponential smoothing. Volatility characteristics can be characteristics obtained by calculating the standard deviation and coefficient of variation of prices. Indicator characteristics can be relative strength index (RSI) and stochastic indicator (KDJ) characteristics. Quantitative characteristics refer to characteristics obtained by quantitative processing of macroeconomic indicator data and financial news data.

[0050] Optionally, a preset feature extraction model can be used to determine the short-term, medium-term and long-term price trends by moving average, exponential smoothing and other methods to obtain price trend characteristics, and further calculate the standard deviation and coefficient of variation based on the financial product price data to obtain volatility characteristics. Finally, according to the preset relative strength index (RSI) and stochastic indicator (KDJ) feature calculation rules, the relative strength index (RSI) and stochastic indicator (KDJ) characteristics are calculated as indicator features.

[0051] Optionally, natural language processing technology can be used to quantify macroeconomic indicator data and financial news data to convert text data into vector data.

[0052] It should be noted that the present invention can effectively improve the prediction accuracy of subsequent prediction information by performing comprehensive feature extraction on investment analysis data and taking into account price trend characteristics, fluctuation characteristics, indicator characteristics and quantitative characteristics for prediction.

[0053] Optionally, the macroeconomic indicator data and financial news data in the investment analysis data are quantitatively processed to determine the corresponding quantitative features, including: determining the indicator category corresponding to the macroeconomic indicator data in the investment analysis data based on a preset classification strategy, and determining the quantitative features corresponding to the macroeconomic data according to the indicator category; dividing the financial news data into at least one industry dynamic text according to the candidate financial products involved in the financial news data in the investment analysis data, and associating each industry dynamic text with each candidate financial product to obtain the quantitative features corresponding to the financial news data. Among them, the indicator category is positive, negative or neutral.

[0054] Optionally, after associating the industry dynamic texts with the candidate financial products, corresponding weight features may be assigned to the industry dynamic texts to obtain quantitative features corresponding to the financial news data.

[0055] It should be noted that, by providing an implementation method for quantifying the features of macroeconomic indicator data and financial news data, macroeconomic indicator data and financial news data can be converted into quantitative features that can be processed by the model, so that the information of indicator data and news data can be taken into account during prediction, making the obtained prediction information more accurate and reasonable.

[0056] S103. Input the analysis features into a preset price prediction model to obtain prediction information of each candidate financial product, and determine the target financial product based on the preset optimization algorithm according to the prediction information, investment demand, proportion of financial products and risk tolerance category, so as to make investment recommendations to the target user.

[0057] The preset price prediction model may be a pre-trained model that can be used to predict the price data of each candidate financial product in the future time period. The prediction information may specifically include data information of the prices of different candidate financial products in the short term (such as hours, days), medium term (such as weeks, months) and long term (such as quarters, years). The target financial product refers to the financial product selected from the candidate financial products for recommendation to the target user.

[0058] The preset optimization algorithm can be a mean-variance optimization algorithm or an optimization algorithm based on a risk parity model. The mean-variance optimization algorithm constructs a mathematical model of the expected return and risk (measured by variance) of the investment portfolio, and solves the asset allocation ratio that maximizes the expected return of the investment portfolio given the risk preference of the customer. The risk parity model starts from the perspective of risk contribution, making each asset class in the investment portfolio contribute equally to the overall risk, thereby achieving a balanced distribution of risk among different assets. During the optimization process, other constraints of the investment portfolio will also be considered, such as the customer's investment period, liquidity requirements, etc.

[0059] For example, when predicting stock market trends, a preset price prediction model can be used to comprehensively consider macroeconomic factors (such as the relationship between GDP growth rate and the overall valuation of the stock market, the impact of inflation rate on stocks in different industries, etc.), industry factors (the life cycle stage of the industry, changes in the industry's competitive landscape, etc.), company factors (financial statement data, management decisions, etc.), and market sentiment factors (obtained through financial news sentiment analysis and social media opinion monitoring), thereby predicting information for each candidate financial product.

[0060] Optionally, an objective function that considers forecast information, investment demand, and the proportion of financial products can be constructed based on the mean-variance optimization algorithm according to the risk tolerance category of the target user, so as to determine the optimal target financial product from the candidate financial products.

[0061] For example, if the target user's risk tolerance category is conservative, the return-risk objective function focuses more on risk minimization. Under the premise of meeting a certain expected return (such as outperforming the inflation rate by 2%-3%), the internal proportion of cash and fixed-income assets is adjusted through an optimization algorithm to minimize the variance (i.e. volatility risk) of the investment portfolio. For example, bonds with high credit ratings and matching maturities are given priority to build a portfolio to reduce the risks caused by interest rate fluctuations, while ensuring that liquid assets are sufficient to cope with short-term funding needs.

[0062] For example, if the target user's risk tolerance category is conservative, the objective function can consider the balance between return and risk. Within the established asset class ratio range, the optimization algorithm is used to analyze the correlation, historical return and volatility data of different assets to find the configuration plan that maximizes the Sharpe ratio (excess return under unit risk). For example, by adjusting the ratio of stocks and bonds, when the market rises, stock assets drive the value of the portfolio, and when the market falls, bond assets are relied on to stabilize the value of the portfolio, so as to achieve long-term and stable asset growth.

[0063] For example, if the target user's risk tolerance category is aggressive, the return-risk objective function tends to maximize returns. Within the acceptable risk range (such as setting the maximum drawdown to no more than 30%), the proportion of high-growth and high-potential assets in equity assets is increased through optimization algorithms, while leveraging tools (under the premise of controllable risks and compliance) or derivatives are used for risk management and return enhancement. For example, in the expected rise period of the technology sector, increase the allocation of technology-themed stock funds or high-growth potential stocks, and use stock index futures to hedge systemic risks in order to obtain high returns.

[0064] Optionally, the banking system may make investment recommendations to target users through personalized presentation based on the determined target financial products, thereby providing feedback on investment recommendation requests sent by target users.

[0065] Optionally, after making investment recommendations to target users, the method also includes: determining whether there is a risk of market volatility based on changes in macroeconomic indicator data and financial news data in the investment analysis data; if so, determining the market volatility range based on the financial product price data and market transaction data in the investment analysis data, and adjusting the investment recommendation products for the target users when it is detected that the market volatility range is greater than a preset threshold.

[0066] For example, for the stock market, the standard deviation method can be used to calculate the historical volatility of a stock market 300 index or other representative index. Assume that the standard deviation of the daily return of a stock market 300 index in the past year is 1.5%. Generally speaking, in a milder market environment, the market volatility threshold can be set at an annualized volatility of 20%. Converted to daily volatility is approximately 1.26% (assuming there are 250 trading days in a year, the daily volatility is inferred through the annualized volatility formula). When the market volatility exceeds this threshold, for example, the average daily volatility reaches 1.5% for multiple consecutive days (such as 5 days), the portfolio adjustment mechanism may be triggered.

[0067] It should be noted that the preset threshold can be flexibly adjusted under different market environments. During periods of extreme market instability, such as during the financial crisis, the preset threshold can be appropriately relaxed, because the entire market is in a state of high volatility at this time, and frequent adjustments to the portfolio are costly and may miss subsequent rebound opportunities; while in the relatively stable bull market or the slow development stage of the bear market, the preset threshold can be relatively tightened to capture subtle changes in the market in a timely manner. For example, during a financial crisis, the market's daily volatility may soar to 3% or even higher. At this time, the threshold that triggers adjustment can be raised to 30% annualized volatility (about 1.94% daily volatility); in a relatively stable slow bull market, the threshold can be set at 15% annualized volatility (about 0.97% daily volatility).

[0068] It should be noted that when the monitoring indicators trigger adjustments, a gradual adjustment strategy should be adopted when adjusting the investment portfolio. For example, if the proportion of stock assets needs to be reduced from 60% to 50%, do not sell 10% of the stocks at one time, but trade them in multiple times (such as 5-10 times) on different trading days, and control the size of each transaction to about 1%-2% of the total stock assets. This can effectively avoid the increase in excessive transaction costs such as market impact costs and slippage costs caused by large-scale selling or buying. At the same time, after each adjustment, the investment portfolio adjustment report will be pushed to the customer in a timely manner. The report content includes the reasons for the adjustment (such as excessive market volatility, customer asset change trigger thresholds), asset allocation details before and after the adjustment, and the expected impact on future investment returns and risks, etc., so that users can fully understand the dynamic changes in the investment portfolio and enhance customers' trust and understanding of the investment management process.

[0069] It should be noted that the present invention can protect the stability of user assets and improve the effectiveness of product recommendations by detecting the amplitude of market fluctuations and adjusting investment products when it is detected that it is greater than a preset threshold.

[0070] The technical solution of the embodiment of the present invention, if an investment recommendation request sent by a target user is detected, the investment needs, candidate financial products, investment analysis data and user information data of the target user are determined, and the investment analysis data and user information data are preprocessed; the risk tolerance category and the proportion of financial products of the target user are determined, and the preprocessed investment analysis data is subjected to feature extraction processing to obtain corresponding analysis features; the analysis features are input into a preset price prediction model to obtain prediction information of each candidate financial product, and the target financial product is determined based on the prediction information, investment needs, proportion of financial products and risk tolerance category, based on a preset optimization algorithm, to make investment recommendations to the target user. The present invention can improve the accuracy of the prediction results by performing comprehensive feature extraction on the investment analysis data, considering price trend features, fluctuation features, indicator features and quantitative features for prediction, and further, by combining the user's risk tolerance for investment recommendations, the user's investment needs can be fully considered to improve the efficiency of investment decision-making.

[0071] Embodiment 2

[0072] Figure 2 is a flow chart of an investment recommendation method provided in Embodiment 2 of the present invention; based on the above embodiments, this embodiment provides a preferred example of investment recommendation based on a price prediction model, specifically, Figure 2 As shown, the method includes:

[0073] S201. If an investment recommendation request sent by a target user is detected, the investment needs, candidate financial products, investment analysis data and user information data of the target user are determined.

[0074] S202: using a preset anomaly detection method to identify and eliminate anomalies in the investment analysis data, and interacting with a preset verification system to verify and adjust the user information data according to the interaction results.

[0075] S203. Determine a corresponding standardization method according to the data category of the investment analysis data to standardize the financial product price data and macroeconomic indicator data in the investment analysis data, respectively, so as to preprocess the investment analysis data and user information data.

[0076] S204: Evaluate the risk tolerance level of the target user based on the pre-processed user information data to obtain a risk tolerance category.

[0077] S205. Determine the proportion of low-risk financial products and high-risk financial products based on the risk tolerance category of the target user, and determine the proportion of high-liquidity financial products and low-liquidity financial products based on the investment needs of the target user to obtain the proportion of financial products.

[0078] S206: Perform feature extraction processing on the financial product price data in the investment analysis data to obtain price trend features, fluctuation features, and indicator features.

[0079] S207. Quantitatively process the macroeconomic indicator data and financial news data in the investment analysis data to determine corresponding quantitative features, and determine price trend features, fluctuation features, indicator features, and quantitative features as analysis features.

[0080] S208. Input the analysis features into a preset price prediction model to obtain prediction information for each candidate financial product, and determine the target financial product based on the preset optimization algorithm according to the prediction information, investment demand, proportion of financial products and risk tolerance category, so as to make investment recommendations to the target user.

[0081] Embodiment 3

[0082] Figure 3 : is a structural block diagram of an investment recommendation device provided in the third embodiment of the present invention; this embodiment can be applied to the situation where the banking system predicts the trend of financial products and makes investment recommendations in combination with the risk-bearing capacity of the user. The investment recommendation device provided in the embodiment of the present invention can execute the investment recommendation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method; the investment recommendation device can be implemented in the form of hardware and / or software, and configured in an electronic device with an investment recommendation function, such as a banking system, such as Figure 3 As shown, the investment recommendation device specifically includes:

[0083] The preprocessing module 301 is used to determine the investment needs, candidate financial products, investment analysis data and user information data of the target user if an investment recommendation request sent by the target user is detected, and preprocess the investment analysis data and user information data;

[0084] The extraction processing module 302 is used to determine the risk tolerance category and the proportion of financial products of the target user, and perform feature extraction processing on the pre-processed investment analysis data to obtain corresponding analysis features; the analysis features include at least one of the following: price trend features, fluctuation features, indicator features, and quantitative features;

[0085] The recommendation module 303 is used to input the analysis features into a preset price prediction model to obtain prediction information of each candidate financial product, and determine the target financial product based on the preset optimization algorithm according to the prediction information, investment demand, proportion of financial products and risk tolerance category, so as to make investment recommendations to the target user.

[0086] The technical solution of the embodiment of the present invention, if an investment recommendation request sent by a target user is detected, the investment needs, candidate financial products, investment analysis data and user information data of the target user are determined, and the investment analysis data and user information data are preprocessed; the risk tolerance category and the proportion of financial products of the target user are determined, and the preprocessed investment analysis data is subjected to feature extraction processing to obtain corresponding analysis features; the analysis features are input into a preset price prediction model to obtain prediction information of each candidate financial product, and the target financial product is determined based on the prediction information, investment needs, proportion of financial products and risk tolerance category, based on a preset optimization algorithm, to make investment recommendations to the target user. The present invention can improve the accuracy of the prediction results by performing comprehensive feature extraction on the investment analysis data, considering price trend features, fluctuation features, indicator features and quantitative features for prediction, and further, by combining the user's risk tolerance for investment recommendations, the user's investment needs can be fully considered to improve the efficiency of investment decision-making.

[0087] Furthermore, the preprocessing module 301 is specifically used for:

[0088] Use the preset anomaly detection method to identify and eliminate anomalies in investment analysis data, and interact with the preset verification system to verify and adjust user information data based on the interaction results;

[0089] According to the data category of the investment analysis data, the corresponding standardization method is determined to standardize the financial product price data and macroeconomic indicator data in the investment analysis data respectively.

[0090] Furthermore, the extraction processing module 302 may include:

[0091] The first extraction unit is used to perform feature extraction processing on the price data of financial products in the investment analysis data to obtain price trend features, fluctuation features and indicator features;

[0092] The second extraction unit is used to perform quantitative processing on the macroeconomic indicator data and financial news data in the investment analysis data to determine corresponding quantitative features.

[0093] Furthermore, the second extraction unit is specifically used for:

[0094] Based on a preset classification strategy, determine the indicator category corresponding to the macroeconomic indicator data in the investment analysis data, and determine the quantitative characteristics corresponding to the macroeconomic data according to the indicator category; the indicator category is positive, negative or neutral;

[0095] According to the candidate financial products involved in the financial news data in the investment analysis data, the financial news data is divided into at least one industry dynamic text, and each industry dynamic text is associated with each candidate financial product to obtain quantitative features corresponding to the financial news data.

[0096] Furthermore, the extraction processing module 302 is specifically used for:

[0097] Based on the pre-processed user information data, the risk tolerance level of the target user is evaluated to obtain the risk tolerance category; the risk tolerance category is conservative, stable, balanced or aggressive;

[0098] According to the risk tolerance category of the target users, determine the proportion of low-risk financial products and high-risk financial products, and according to the investment needs of the target users, determine the proportion of high-liquidity financial products and low-liquidity financial products to obtain the proportion of financial products.

[0099] Furthermore, the above device is also used for:

[0100] Determine whether there is market volatility risk based on changes in macroeconomic indicators and financial news data in investment analysis data;

[0101] If so, the market volatility is determined based on the financial product price data and market transaction data in the investment analysis data, and when it is detected that the market volatility is greater than a preset threshold, the investment recommendation products for the target user are adjusted.

[0102] Embodiment 4

[0103] Figure 4 It is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0104] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0105] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0106] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the investment recommendation method.

[0107] In some embodiments, the investment recommendation method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the investment recommendation method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the investment recommendation method in any other appropriate manner (e.g., by means of firmware).

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

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

[0110] In the context of the present invention, a computer readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer readable storage medium may be a machine readable signal medium. A more specific example of a machine readable storage medium may include an electrical connection based on one or more lines, 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 foregoing.

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

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

[0113] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0114] In one embodiment, the embodiment of the present invention further includes a computer program product, the computer program product includes a computer program, and the computer program implements the investment recommendation method of any embodiment of the present invention when executed by a processor.

[0115] 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).

[0116] 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.

[0117] 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 can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An investment recommendation method, characterized in that: include: If an investment recommendation request sent by a target user is detected, the target user's investment needs, candidate financial products, investment analysis data and user information data are determined, and the investment analysis data and user information data are pre-processed; Determine the risk tolerance category and proportion of financial products of the target user, and perform feature extraction processing on the pre-processed investment analysis data to obtain corresponding analysis features; the analysis features include at least one of the following: price trend features, volatility features, indicator features, and quantitative features; The analysis features are input into the preset price prediction model to obtain the prediction information of each candidate financial product. Based on the prediction information, investment demand, proportion of financial products and risk tolerance category, the target financial product is determined based on the preset optimization algorithm to make investment recommendations to the target users.

2. The method according to claim 1, characterized in that Pre-process investment analysis data and user information data, including: Use the preset anomaly detection method to identify and eliminate anomalies in investment analysis data, and interact with the preset verification system to verify and adjust user information data based on the interaction results; According to the data category of the investment analysis data, the corresponding standardization method is determined to standardize the financial product price data and macroeconomic indicator data in the investment analysis data respectively.

3. The method according to claim 1, characterized in that Perform feature extraction on the preprocessed investment analysis data to obtain corresponding analysis features, including: Perform feature extraction on the price data of financial products in the investment analysis data to obtain price trend features, fluctuation features and indicator features; The macroeconomic indicator data and financial news data in the investment analysis data are quantified to determine the corresponding quantitative characteristics.

4. The method according to claim 3, characterized in that Quantitatively process the macroeconomic indicator data and financial news data in the investment analysis data to determine the corresponding quantitative features, including: Based on a preset classification strategy, determine the indicator category corresponding to the macroeconomic indicator data in the investment analysis data, and determine the quantitative characteristics corresponding to the macroeconomic data according to the indicator category; the indicator category is positive, negative or neutral; According to the candidate financial products involved in the financial news data in the investment analysis data, the financial news data is divided into at least one industry dynamic text, and each industry dynamic text is associated with each candidate financial product to obtain quantitative features corresponding to the financial news data.

5. The method according to claim 1, characterized in that Determine the target users’ risk tolerance categories and financial product proportions, including: Based on the pre-processed user information data, the risk tolerance level of the target user is evaluated to obtain the risk tolerance category; the risk tolerance category is conservative, stable, balanced or aggressive; According to the risk tolerance category of the target users, determine the proportion of low-risk financial products and high-risk financial products, and according to the investment needs of the target users, determine the proportion of high-liquidity financial products and low-liquidity financial products to obtain the proportion of financial products.

6. The method according to claim 1, characterized in that After making investment recommendations to target users, it also includes: Determine whether there is market volatility risk based on changes in macroeconomic indicators and financial news data in investment analysis data; If so, the market volatility is determined based on the financial product price data and market transaction data in the investment analysis data, and when it is detected that the market volatility is greater than a preset threshold, the investment recommendation products for the target user are adjusted.

7. An investment recommendation device, characterized in that: include: A preprocessing module, for determining the investment needs, candidate financial products, investment analysis data and user information data of the target user if an investment recommendation request sent by the target user is detected, and preprocessing the investment analysis data and user information data; An extraction processing module is used to determine the risk tolerance category and financial product proportion of the target user, and perform feature extraction processing on the pre-processed investment analysis data to obtain corresponding analysis features; the analysis features include at least one of the following: price trend features, volatility features, indicator features, and quantitative features; The recommendation module is used to input the analysis features into the preset price prediction model to obtain the prediction information of each candidate financial product, and determine the target financial product based on the preset optimization algorithm according to the prediction information, investment demand, proportion of financial products and risk tolerance category, so as to make investment recommendations to the target users.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the investment recommendation method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the investment recommendation method according to any one of claims 1 to 6 when executed.

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

Images