CN116934478A

CN116934478A - Method and device for configuring investment portfolio, electronic equipment and storage medium

Info

Publication number: CN116934478A
Application number: CN202310914023.2A
Authority: CN
Inventors: 王冠儒
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2023-07-24
Filing date: 2023-07-24
Publication date: 2023-10-24

Abstract

The invention discloses a configuration method and a device thereof for investment portfolios, electronic equipment and a storage medium, and relates to the technical field of big data or other related fields, wherein the configuration method comprises the following steps: responding to the investment combination configuration instruction, and acquiring historical transaction data of N financial products; extracting characteristic data in historical transaction data of each financial product respectively to obtain N characteristic sets; inputting the N feature sets into a target model, and outputting simulation investment data related to N financial products; and carrying out combined configuration on the N financial products based on the simulated investment data to obtain an investment combination configuration result, wherein the investment combination configuration result comprises the following steps: m financial products to be recommended, the weight each financial product occupies, a revenue index and a risk index. The invention solves the technical problems of low efficiency, great time and energy consumption and insufficient objective and accurate decision result of manually making investment portfolio decisions in the related technology.

Description

Method and device for configuring investment portfolio, electronic equipment and storage medium

Technical Field

The invention relates to the technical field of big data, in particular to a method and a device for configuring investment portfolios, electronic equipment and a storage medium.

Background

Portfolios refer to investors distributing their own funds to different investment targets for the purpose of risk dispersion and revenue maximization. The construction of portfolios is an important investment decision process, in which real investors often construct portfolios based on their own risk preferences and investment goals. For example, a conservative investor may tend to invest in a relatively stable bond market, while an investor with higher risk bearing capacity may invest more in a stock market.

In the related technology, the investment portfolio configuration mainly adopts a manual decision-making mode, investors manually select financial products according to own financial knowledge and investment experience and perform weight distribution, and investment portfolios are built, so that the problem that decision-making results are not objective and accurate enough due to insufficient experience or insufficient financial knowledge of the investors easily occurs; investors also need to continuously pay attention to market dynamics and continuously adjust investment portfolios after market entry, consume a lot of time and effort, and are inefficient in investment decisions.

In view of the above problems, no effective solution has been proposed at present.

Disclosure of Invention

The embodiment of the invention provides a method and a device for configuring investment portfolios, electronic equipment and a storage medium, which at least solve the technical problems that investment portfolio decision is manually made in the related technology, the efficiency is low, a great amount of time and energy are consumed, and the decision result is not objective and accurate enough.

According to an aspect of an embodiment of the present invention, there is provided a method for configuring a portfolio, including: responding to the investment combination configuration instruction, and acquiring historical transaction data of N financial products, wherein N is a positive integer; extracting characteristic data in the historical transaction data of each financial product respectively to obtain N characteristic sets; inputting the N feature sets into a target model, and outputting simulation investment data related to the N financial products; and carrying out combination configuration on N financial products based on the simulated investment data to obtain an investment combination configuration result, wherein the investment combination configuration result comprises the following steps: m financial products to be recommended, the weight occupied by each financial product, the income index and the risk index, wherein M is a positive integer less than or equal to N.

Optionally, before inputting the N feature sets into the target model, the method further includes: receiving investment preference data of a target object, wherein the investment preference data at least comprises: investment goals, income expectations, risk bearing ranges; inputting the investment preference data into the target model as a constraint condition of the target model in a market trend prediction process of the financial product.

Optionally, after acquiring the historical transaction data of the N financial products, further includes: performing data preprocessing on the historical transaction data of all the financial products, wherein the data preprocessing comprises at least one of the following: data deduplication, data deficiency, format standardization, and data simplification.

Optionally, extracting the characteristic data in the historical transaction data of the financial product includes: determining the category of financial features to be extracted according to a preset feature extraction strategy; performing feature sampling on the historical transaction data of the financial product based on the financial feature class to obtain sampling data; and performing data dimension reduction on the sampling data based on a preset standard format, and performing normalization processing on the sampling data after dimension reduction to obtain the characteristic data.

Optionally, the step of inputting the N feature sets into a target model and outputting simulated investment data includes: generating H sets of initial portfolio scenarios based on the investment preference data and the feature data in all the feature sets, wherein each set of initial portfolio scenarios includes: m financial products and the weight occupied by each financial product, wherein H is a positive integer, and M is a positive integer less than or equal to N; inputting each set of initial investment portfolio schemes into the target model, carrying out expected simulation on investment results of all financial products in the initial investment portfolio schemes by the target model, and outputting market trend prediction results of each set of initial investment portfolio schemes, wherein the market trend prediction results comprise: an expected profit index, an expected risk index, and an expected loss index; and outputting the simulated investment data based on the investment risk bearing grade of the target object and the market trend prediction result of the H sets, wherein the investment risk bearing grade is calculated according to the investment preference data of the target object.

Optionally, after performing combined configuration on the N financial products based on the simulated investment data, obtaining a result of investment portfolio configuration, the method further includes: the investment combination configuration result is sent to a display page of an object terminal used by a target object, and investment confirmation results transmitted by the object terminal are collected; when the investment confirmation result indicates passing, constructing a transaction instruction based on the investment combination configuration result, sending the transaction instruction to a transaction platform, and executing the transaction instruction by the transaction platform; and receiving an adjustment suggestion returned by the target terminal under the condition that the investment confirmation result indicates not to pass, and adjusting the investment combination configuration result based on the adjustment suggestion.

Optionally, after the transaction instruction is sent to the transaction platform and executed by the transaction platform, the method further includes: after a specified time length is set, acquiring real-time market data of M financial products in the investment portfolio configuration result, and extracting real-time characteristic data in the real-time market data to obtain a real-time characteristic data set; based on the real-time characteristic data set, adjusting the investment portfolio configuration result to obtain an adjusted investment portfolio configuration result; constructing a transaction adjustment instruction based on the adjusted investment portfolio configuration result; and sending the transaction adjustment instruction to a transaction platform, and executing the transaction adjustment instruction by the transaction platform.

Optionally, the characteristic data includes at least one of: portfolio feature data, market feature data, risk-benefit feature data, the portfolio feature data comprising: investment category, asset weight, investment deadline, correlation coefficient, the market characteristics data comprising: historical price, market index, interest rate index, the risk-benefit characteristic data comprising: historical yield, historical volatility, historical risk index.

According to another aspect of the embodiment of the present invention, there is also provided an apparatus for configuring a portfolio, including: the response unit is used for responding to the investment combination configuration instruction and acquiring historical transaction data of N financial products, wherein N is a positive integer; the extraction unit is used for respectively extracting the characteristic data in the historical transaction data of each financial product to obtain N characteristic sets; the output unit is used for inputting the N characteristic sets into a target model and outputting simulation investment data related to the N financial products; the configuration unit is used for carrying out combination configuration on the N financial products based on the simulated investment data to obtain an investment combination configuration result, wherein the investment combination configuration result comprises the following steps: m financial products to be recommended, the weight occupied by each financial product, the income index and the risk index, wherein M is a positive integer less than or equal to N.

Optionally, the apparatus for configuring a portfolio further includes: the first receiving module is used for receiving investment preference data of the target object, and the investment preference data at least comprises the following components: investment goals, income expectations, risk bearing ranges; and the first input module is used for inputting the investment preference data into the target model to serve as constraint conditions of the target model in the market trend prediction process of the financial product.

Optionally, the apparatus for configuring a portfolio further includes: the preprocessing module is used for preprocessing the historical transaction data of all the financial products, wherein the data preprocessing comprises at least one of the following steps: data deduplication, data deficiency, format standardization, and data simplification.

Optionally, the extracting unit includes: the determining module is used for determining financial feature categories to be extracted according to a preset feature extraction strategy; the sampling module is used for carrying out feature sampling on the historical transaction data of the financial product based on the financial feature class to obtain sampling data; and the dimension reduction module is used for carrying out data dimension reduction on the sampling data based on a preset standard format, and carrying out normalization processing on the sampling data after dimension reduction to obtain the characteristic data.

Optionally, the output unit includes: a generating module, configured to generate H sets of initial portfolio scenarios based on investment preference data and the feature data in all the feature sets, where each set of initial portfolio scenarios includes: m financial products and the weight occupied by each financial product, wherein H is a positive integer, and M is a positive integer less than or equal to N; the second input module is used for inputting each set of initial investment portfolio scheme into the target model, carrying out expected simulation on investment results of all financial products in the initial investment portfolio scheme by the target model, and outputting market trend prediction results of each set of initial investment portfolio scheme, wherein the market trend prediction results comprise: an expected profit index, an expected risk index, and an expected loss index; and the output module is used for outputting the simulated investment data based on the investment risk bearing grade of the target object and the market trend prediction result of the H sets, wherein the investment risk bearing grade is calculated according to the investment preference data of the target object.

Optionally, the apparatus for configuring a portfolio further includes: the first sending module is used for sending the investment portfolio configuration result to a display page of an object terminal used by a target object and collecting an investment confirmation result transmitted by the object terminal; the first construction module is used for constructing a transaction instruction based on the investment combination configuration result and sending the transaction instruction to a transaction platform, and the transaction platform executes the transaction instruction under the condition that the investment confirmation result indicates passing; and the second receiving module is used for receiving an adjustment suggestion returned by the target terminal under the condition that the investment confirmation result indicates not to pass, and adjusting the investment portfolio configuration result based on the adjustment suggestion.

Optionally, the apparatus for configuring a portfolio further includes: the acquisition module is used for acquiring real-time market data of M financial products in the investment portfolio configuration result after the specified time length is set, and extracting real-time characteristic data in the real-time market data to obtain a real-time characteristic data set; the adjustment module is used for adjusting the investment portfolio configuration result based on the real-time characteristic data set to obtain the adjusted investment portfolio configuration result; the second construction module is used for constructing transaction adjustment instructions based on the adjusted investment portfolio configuration results; and the second sending module is used for sending the transaction adjustment instruction to a transaction platform, and executing the transaction adjustment instruction by the transaction platform.

According to another aspect of the embodiment of the present invention, there is also provided a computer readable storage medium, where the computer readable storage medium includes a stored computer program, where when the computer program runs, the device in which the computer readable storage medium is controlled to execute the configuration method of any one of the investment portfolios described above.

According to another aspect of the embodiments of the present invention, there is also provided an electronic device including one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method for configuring any one of the above-mentioned portfolios.

In the present disclosure, a method for configuring an investment portfolio is provided, wherein, first, a portfolio configuration instruction is responded, historical transaction data of N financial products is obtained, N is a positive integer, feature data in the historical transaction data of each financial product is extracted to obtain N feature sets, then all feature sets are input into a target model, simulated investment data of associated N financial products is output, and finally, all financial products are configured in a combined manner based on the simulated investment data to obtain an investment portfolio configuration result, wherein the investment portfolio configuration result comprises: m financial products to be recommended, the weight occupied by each financial product, the income index and the risk index, wherein M is a positive integer less than or equal to N.

In the method, the historical transaction data of the financial products are collected, the characteristic data in the historical transaction data are extracted and the characteristic set is input into the target model, the target model is utilized to analyze market environment trends in the historical transaction data, the target model is enabled to output simulated investment data related to all the financial products, the simulated investment data are used as basis to configure investment combinations capable of being put into the market, an intelligent investment combination distribution system is provided by an algorithm in the target model after the market environment factors are more fully considered by utilizing the target model, investment objects can be assisted to make more objective and accurate investment decisions, meanwhile, decision efficiency is greatly improved, time and energy of the investment objects are saved, and further the technical problems that investment combination decisions are manually made in related technologies, efficiency is low, a great amount of time and energy are consumed, and decision results are not objective and accurate are solved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:

FIG. 1 is a flow chart of an alternative portfolio configuration method in accordance with an embodiment of the present invention;

FIG. 2 is a schematic diagram of an alternative intelligent portfolio allocation system based on artificial intelligence and data mining techniques in accordance with an embodiment of the present invention;

FIG. 3 is a data modeling flow diagram of an alternative intelligent portfolio allocation system in accordance with an embodiment of the present invention;

FIG. 4 is a schematic illustration of an alternative portfolio configuration arrangement in accordance with an embodiment of the present invention;

fig. 5 is a block diagram of a hardware structure of an electronic device (or mobile device) for a method of configuring a portfolio according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

To facilitate an understanding of the invention by those skilled in the art, some terms or nouns involved in the various embodiments of the invention are explained below:

portfolios, which are composed of a plurality of different investment assets (such as stocks, bonds, funds, etc.), are aimed at achieving investors' investment goals and risk preferences.

Risk preference refers to the preference of the investor for how well the risk is sustained in the investment decisions.

It should be noted that, the method and the device for configuring a portfolio in the present disclosure may be used in the big data field when configuring a portfolio of a financial product, and may also be used in any field other than the big data field when configuring a portfolio of a financial product.

It should be noted that, the relevant information (including user equipment information, user personal information, etc.) and data (including data for analysis, stored data, collected data, presented data, etc.) related to the present disclosure are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the relevant data need to comply with relevant laws and regulations and standards of relevant countries and regions, and provide corresponding operation entries for the user to select authorization or rejection. For example, an interface is provided between the system and the relevant user or institution, before acquiring the relevant information, the system needs to send an acquisition request to the user or institution through the interface, and acquire the relevant information after receiving the consent information fed back by the user or institution.

The embodiments of the invention can be applied to various systems/applications/equipment which need to carry out investment combination configuration on financial products, can collect historical transaction data of the financial products, extract characteristic data of the historical transaction data, input the characteristic data into a target model for simulated investment, output simulated investment data related to all the financial products, further configure investment combination which can be put into the market, greatly improve decision-making efficiency and enable decision-making results to be more objective and accurate.

The present invention will be described in detail with reference to the following examples.

Example 1

In accordance with an embodiment of the present invention, there is provided an embodiment of a method of configuring a portfolio, it being noted that the steps shown in the flowchart of the figures may be performed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be performed in an order other than that shown.

FIG. 1 is a flow chart of an alternative portfolio configuration method, as shown in FIG. 1, according to an embodiment of the present invention, the method comprising the steps of:

step S101, responding to the investment combination configuration instruction, acquiring historical transaction data of N financial products, wherein N is a positive integer.

Step S102, extracting characteristic data in historical transaction data of each financial product respectively to obtain N characteristic sets.

Step S103, inputting the N feature sets into the target model, and outputting simulation investment data related to the N financial products.

Step S104, carrying out combination configuration on N financial products based on the simulated investment data to obtain an investment combination configuration result, wherein the investment combination configuration result comprises the following steps: m financial products to be recommended, the weight occupied by each financial product, the income index and the risk index, wherein M is a positive integer less than or equal to N.

Through the steps, the historical transaction data of N financial products can be obtained in response to the investment portfolio configuration instruction, N is a positive integer, the characteristic data in the historical transaction data of each financial product are respectively extracted to obtain N characteristic sets, then all the characteristic sets are input into the target model, the simulated investment data of the associated N financial products are output, finally all the financial products are subjected to combined configuration based on the simulated investment data to obtain an investment portfolio configuration result, and the investment portfolio configuration result comprises: m financial products to be recommended, the weight occupied by each financial product, the income index and the risk index, wherein M is a positive integer less than or equal to N.

In the embodiment of the invention, the historical transaction data of the financial products are collected, the characteristic data in the historical transaction data are extracted, the characteristic set is input into the target model, the target model is utilized to analyze the market environment trend in the historical transaction data, so that the target model outputs the simulated investment data related to all the financial products, the simulated investment data are used as the basis to configure the investment combination which can be put into the market, the algorithm in the target model provides an intelligent investment combination distribution system by utilizing the target model to fully consider the market environment factors, the investment object is assisted to make a more objective and accurate investment decision, the target model is utilized to analyze the market data, the investment decision efficiency is greatly improved, the time and energy of investors are saved, and the technical problems of low efficiency, great time and energy consumption and insufficient objective and accurate decision result of investment combination decision making in the related technology are solved.

Embodiments of the present invention will be described in detail with reference to the following steps.

The implementation subject of the embodiments of the present invention is an intelligent portfolio configuration system or a background server of a financial institution. In the embodiment of the invention, the system can automatically allocate investment combinations and optimize in real time according to factors such as investment targets, risk preferences, asset conditions, market environments and the like of investors (the investors can be individuals, enterprises and the like).

It should be noted that, the historical transaction data of the financial product includes, but is not limited to: transaction date and time, price for transaction, amount for transaction, direction of transaction (buy or sell), type of transaction (e.g., market price transaction, limit price transaction, loss prevention transaction, etc.), transaction commission, manner of transaction (e.g., telephone transaction, online transaction, over-the-counter transaction, etc.), result of transaction (refer to profit, loss, or flat).

It should be noted that, in the embodiment of the present invention, the channel for acquiring the historical transaction data of the financial product includes: the financial institution transaction system and database, the public information platform of the exchange, the third party data provider, the financial data analysis platform, the open data interface provided by the financial supervision institution and the like, the data acquisition channels are public free channels or payment channels, and the information and data disclosed in the platform are information and data authorized by the user or fully authorized by all parties.

Optionally, after acquiring the historical transaction data of the N financial products, further includes: performing data preprocessing on historical transaction data of all financial products, wherein the data preprocessing comprises at least one of the following: data deduplication, data deficiency, format standardization, and data simplification.

It should be noted that, the data preprocessing further includes: the method comprises the steps of data denoising, data segmentation, feature construction, anomaly detection and the like, and the aim of preprocessing historical transaction data of financial products is to reduce noise interference and redundant information in original data, convert the data into a uniform format, enable the preprocessed data to better adapt to requirements of a model algorithm and requirements of feature engineering, and further improve stability, accuracy and generalization capability of a target model.

Optionally, the feature data includes at least one of: portfolio feature data, market feature data, risk-benefit feature data, the portfolio feature data comprising: investment category, asset weight, investment deadline, correlation coefficient, market characteristics data including: historical price, market index, interest rate index, risk-benefit characteristic data includes: historical yield, historical volatility, historical risk index.

In the portfolio feature data, the investment category refers to different item categories included in the portfolio, such as stocks, bonds, real estate, commodities, and the like; asset weight refers to the proportion of each investment item in a portfolio that is used to measure the distribution of an investor's assets throughout the portfolio.

The correlation coefficient is a statistic that measures the degree of correlation between investment projects, ranging from-1 to 1. If the value of the correlation coefficient is closer to 0, the correlation degree between investment projects is weak, namely, the return rate or the return rate change is independent; if the value of the correlation coefficient is closer to-1 or 1, the correlation degree between the investment projects is strong, and the correlation coefficient is positive, positive correlation exists between the investment projects, namely, the trend change of the yield rate or the return rate is similar; the correlation coefficient is negative, there is a negative correlation between investment projects, i.e., the trend of the return rate or return rate is opposite.

The investment portfolio characteristic data further includes: skewness and kurtosis, maximum withdrawal, wherein skewness and kurtosis refer to skewness and kurtosis of the yield distribution of the portfolio, for evaluating non-normal and risk characteristics of the yield distribution; maximum withdrawal refers to the maximum magnitude of loss of a portfolio over a period of time, used to evaluate the risk tolerance of the portfolio.

It should be noted that, in the market feature data, the market index is an index for measuring the performance of a portfolio in a specific market, and is typically a weighted index composed of stocks, bonds and other financial products representing the market, and by comparing the market indexes, an investor can determine whether the performance of the portfolio is better than the average level of the market.

Common market indexes include: standard 500, constant life index, etc.

In the risk-benefit characteristic data, the historical fluctuation ratio indicates the fluctuation degree of the benefit of the investment portfolio in the past period, and the higher the fluctuation ratio, the larger the fluctuation of the benefit representing the investment portfolio, and the higher the risk level, and the investor usually considers the balance between the fluctuation ratio of the investment portfolio and the expected benefit when configuring the investment portfolio, so as to achieve the optimal combination of the risk and the benefit.

In the risk-benefit characteristic data, the historical risk indicators include: standard deviation, beta coefficient, vaR, sharp ratio, etc., wherein a Beta coefficient measures the volatility of the portfolio relative to the market overall, a Beta coefficient greater than 1 indicates that the volatility of the portfolio is above market average, a Beta coefficient less than 1 indicates that the volatility is below market average; vaR (Value at Risk) is a measure of the maximum possible loss of a portfolio at a given confidence level, e.g., vaR 5% represents the maximum possible loss of a portfolio at a confidence level of 95%; the Sharp ratio is a trade-off indicator for measuring excess returns and volatility of a portfolio, and the higher the Sharp ratio, the higher the excess returns obtained by the portfolio at unit risk, and the better the returns after risk adjustment.

Optionally, extracting the characteristic data in the historical transaction data of the financial product includes: determining the category of financial features to be extracted according to a preset feature extraction strategy; performing feature sampling on historical transaction data of the financial products based on the financial feature categories to obtain sampling data; and carrying out data dimension reduction on the sampling data based on a preset standard format, and carrying out normalization processing on the sampling data after dimension reduction to obtain characteristic data.

It should be noted that, the preset extraction policy is used for indicating the financial feature category of the feature data to be extracted in the historical transaction data, and the purpose of adjusting the sampling data to the preset standard format is to improve the readability and the analyzability of the data, so that the data can be stored and processed more conveniently, and errors and confusion possibly occurring in the data processing process are reduced.

It should be noted that, the algorithm in the target model in the embodiment of the present invention may be a machine learning algorithm (e.g., decision tree, neural network algorithm, logistic regression algorithm, etc.), or may be a deep learning algorithm (e.g., convolutional neural network, cyclic neural network), where market data and user data are analyzed by the target model, and then a corresponding prediction result or suggestion result is generated for the configuration investment combination according to the analysis result.

Optionally, before inputting the N feature sets into the target model, the method further includes: receiving investment preference data of a target object, wherein the investment preference data at least comprises: investment goals, income expectations, risk bearing ranges; the investment preference data is input into a target model to serve as constraint conditions of the target model in the market trend prediction process of the financial products.

Optionally, the step of inputting the N feature sets into the target model and outputting simulated investment data includes: generating H sets of initial portfolio scenarios based on the investment preference data and the feature data in all feature sets, wherein each set of initial portfolio scenarios includes: m financial products and the weight occupied by each financial product, wherein H is a positive integer, and M is a positive integer less than or equal to N; inputting each set of initial investment portfolio scheme into a target model, carrying out expected simulation on investment results of all financial products in the initial investment portfolio scheme by the target model, and outputting market trend prediction results of each set of initial investment portfolio scheme, wherein the market trend prediction results comprise: an expected profit index, an expected risk index, and an expected loss index; and outputting simulated investment data based on the investment risk bearing grade of the target object and the H sets of market trend prediction results, wherein the investment risk bearing grade is calculated according to the investment preference data of the target object.

It should be noted that, the investment preference data of the target object is the asset ratio limitation condition when the target model generates the initial investment portfolio scheme, the feature data in the feature set can reflect the market dynamic factors of all financial products, the target model in the embodiment of the invention comprehensively considers the market dynamic factors of all financial products and the asset ratio limitation of the target object to output the H sets of initial investment portfolio scheme, and performs simulated investment to generate the market trend prediction result, observes the performances of the schemes in the market environment, and helps investors to know the potential benefits and risks of different schemes before actual investment.

Optionally, after step S104, the method further includes: the investment combination configuration result is sent to a display page of an object terminal used by a target object, and investment confirmation results transmitted by the object terminal are collected; under the condition that the investment confirmation result indicates passing, constructing a transaction instruction based on the investment combination configuration result, sending the transaction instruction to a transaction platform, and executing the transaction instruction by the transaction platform; and receiving an adjustment suggestion returned by the target terminal in the case that the investment confirmation result indicates not to pass, and adjusting the investment combination configuration result based on the adjustment suggestion.

It should be noted that, based on the simulated investment data of the target model, all financial products are selected, the weight of each financial product is configured, an investment portfolio which is finally put on the market is generated, the profit index and the risk index of the investment portfolio are obtained according to the simulated investment data, an investment portfolio configuration result is generated and sent to the object terminal used by the target object to request the target object to carry out investment confirmation, if the target object confirms the investment, the target terminal returns a confirmation result, if the target object does not confirm the investment, the target object is requested to return an adjustment suggestion to adjust the product type or the product weight in the current investment portfolio.

Optionally, after the transaction instruction is sent to the transaction platform and executed by the transaction platform, the method further includes: after the interval is designated for a long time, acquiring real-time market data of M financial products in the investment portfolio configuration result, and extracting real-time characteristic data in the real-time market data to obtain a real-time characteristic data set; based on the real-time characteristic data set, adjusting the investment portfolio configuration result to obtain an adjusted investment portfolio configuration result; constructing a transaction adjustment instruction based on the adjusted investment portfolio configuration result; and sending the transaction adjustment instruction to the transaction platform, and executing the transaction adjustment instruction by the transaction platform.

It should be noted that, in the embodiment of the present invention, a real-time monitoring technology is also used to track and monitor the transaction data of the investment portfolio that is put on the market in real time, and adaptively adjust the configuration of the investment portfolio, so as to ensure that the investment portfolio always maintains a reasonable and stable risk and benefit level, and accords with the expected benefit index of the investment object as much as possible.

In the embodiment of the invention, the historical transaction data of the financial products are collected, the characteristic data in the historical transaction data are extracted, the characteristic set is input into the target model, the target model is utilized to analyze the market environment trend in the historical transaction data, so that the target model outputs the simulated investment data related to all the financial products, the simulated investment data are used as the basis to configure the investment combination which can be put into the market, the algorithm in the target model provides an intelligent investment combination distribution system by utilizing the target model to fully consider the market environment factors, a more objective and accurate investment decision is made, the target model is utilized to analyze the market data and make the investment decision, the decision efficiency is greatly improved, and the time and energy of investors are saved.

In the embodiment of the invention, the data mining technology is also utilized to carry out deep analysis on the financial market, so that indexes such as market trend, risk and the like are predicted more accurately; the optimal investment combination is constructed by utilizing technologies such as constraint optimization algorithm, so that the balance between risks and benefits can be realized, and certain constraint conditions are met; the investment portfolio can be dynamically adjusted by utilizing a real-time monitoring technology, so that continuous optimization and adjustment of the investment portfolio can be realized to adapt to market changes and risk preference of investors; the method has the advantages of providing friendly user interaction interfaces, investment advice and other functions, helping investors to better understand market conditions and investment strategies, and improving the quality of investment decisions.

The invention is described below in connection with another specific embodiment.

FIG. 2 is a schematic diagram of an alternative intelligent portfolio allocation system based on artificial intelligence and data mining techniques, as shown in FIG. 2, including: a data acquisition and preprocessing module 21, a data analysis and modeling module 22, a portfolio construction module 23, a transaction execution module 24, and a user interaction module 25.

It should be noted that, artificial intelligence is an intelligent system realized by techniques such as machine learning, natural language processing, computer vision, etc., and is capable of simulating intelligent thinking and behaviors of human beings; data mining is a technique that discovers, extracts, and analyzes associations and trends between data from a large amount of data in an automated or semi-automated manner.

The following describes the functional modules in the intelligent portfolio allocation system.

The data acquisition and preprocessing module 21 acquires historical transaction data (e.g., stock collection prices, volume of exchanges, market values, etc.) of a plurality of financial products (e.g., stocks, funds, bonds, etc.) from a plurality of financial data acquisition channels by means of API interface acquisition, etc., and preprocesses all the historical transaction data for subsequent analysis and decision.

The pretreatment includes: the method has the advantages that the method comprises the steps of data de-duplication, data deficiency, format standardization, data simplification, data de-noising, data segmentation, feature construction and anomaly detection, and the preprocessed original data can better adapt to the requirements of model algorithms and the requirements of feature engineering in the subsequent analysis and decision process, so that the stability, accuracy and generalization capability of a target model are improved.

The data analysis and modeling module 22 performs feature extraction on the historical transaction data using data mining techniques to obtain feature data for all financial products, including: portfolio characteristics data, market characteristics data, risk-benefit characteristics data.

The data analysis and modeling module 22 also utilizes machine learning algorithms (e.g., decision trees, neural networks, logistic regression, etc.) to build a financial analysis model, input the characteristic data of the financial product described above into the financial analysis model, and output relevant predictions and suggestions of portfolio configurations. It should be noted that, a deep learning algorithm (for example, convolutional neural network, cyclic neural network, etc.) may also be used when building the financial analysis model.

The portfolio construction module 23 constructs an optimal portfolio based on the user's risk preferences, investment goals, and associated predictions and suggestions of portfolio configurations output by the financial analysis model, such that the risk or return of the portfolio is minimized and certain constraints (e.g., a portfolio limit) are met.

It should be noted that the techniques used by the portfolio construction module 23 include, but are not limited to:

the risk assessment and asset allocation model can be combined with factors such as investment targets, risk preferences, investment periods and the like of users to automatically construct reasonable investment portfolios. For example, asset configuration may be performed using a variety of models, such as the Markov mean variance model, the risk factor model, and the like.

Optimization algorithms, which optimize portfolios using mathematical optimization algorithms (e.g., linear programming, nonlinear programming, quadratic programming, integer programming, etc.) to achieve goals of maximizing revenue, minimizing risk.

The quantitative analysis technology is used for quantitatively analyzing market trend through historical transaction data, and predicting and analyzing market trend, industry development, asset price and other aspects by adopting methods such as data mining, machine learning, time sequence analysis and the like so as to construct reasonable investment combinations.

The real-time monitoring technology can monitor and adjust the investment portfolio in real time, and ensure that the investment portfolio always maintains reasonable and stable risk and income level. For example, the portfolio can be dynamically adjusted using machine learning and adaptive control.

It should be noted that the above techniques may be selected and combined according to practical situations to implement the functions of the portfolio construction module 23. For example, the functions of optimizing and quantitatively analyzing investment portfolios can be realized by using programming languages such as MATLAB, python, related open source tools and databases, and meanwhile, factors such as instantaneity, expandability and safety are also required to be considered, so that the module can stably run and the information safety of users is ensured.

The trade execution module 24 converts the constructed investment portfolio into specific trade instructions, and sends the specific trade instructions to a securities exchange or a trade platform for trade execution, and meanwhile, the investment portfolio is dynamically adjusted according to the trade result so as to adapt to market change and risk preference of investors.

The user interaction module 25 provides a friendly interaction interface for investors, wherein the interaction interface comprises investment advice, risk prompt and other functions, and the investors can conveniently perform inquiry, adjustment, tracking and other operations of investment portfolios.

The specific steps performed by the data analysis and modeling module 22 are described in detail below.

FIG. 3 is a data modeling flow diagram of an alternative intelligent portfolio allocation system, as shown in FIG. 3, including the steps of:

Step S301, feature extraction and data preprocessing.

The method comprises the steps of extracting the characteristics of historical transaction data by utilizing a data mining technology to obtain the characteristic data of all financial products, and preprocessing the characteristic data, wherein the method comprises the following steps: data normalization, data sampling, feature selection, feature dimension reduction and the like.

The feature data includes:

1, portfolio characteristics.

Asset class/investment class: different types of assets (stocks, bonds, futures, etc.) are characterized to reflect the diversity of the portfolio.

Asset weight: the weight ratio of each asset in the portfolio is represented for measuring the relative size of the asset allocation.

Investment period: referring to the holding period of each asset in a portfolio, the risk and benefit of the portfolio can be impacted.

Correlation coefficient: the correlation between assets is calculated to measure their effectiveness of linkage and risk dispersion.

2, market characteristics.

Market index: consider an index of the overall market trend, such as the composite index of the stock market (e.g., the dow jones industrial average index, the standard 500 index, etc.).

The interest rate index: consider the impact of market interest level on portfolios, such as national liability, short term interest, etc.

Risk-benefit feature 3.

Historical yield: the historical profitability of each asset is calculated and used to measure the profitability and volatility of the asset.

Historical volatility: by calculating the historical volatility of an asset, the risk level of the asset may be assessed.

Historical risk index: and calculating risk indexes of the investment portfolio, such as fluctuation rate, summer ratio, maximum withdrawal and the like.

In step S302, data modeling and analysis are performed.

A financial analysis model is established using a machine learning algorithm (e.g., decision tree, neural network, logistic regression, etc.), and the relevant predictions and suggestions of portfolio configurations can be output by inputting the characteristic data of the financial products described above into the financial analysis model.

It should be noted that, a deep learning algorithm (for example, convolutional neural network, cyclic neural network, etc.) may also be used when building the financial analysis model.

Step S303, a prediction result or suggestion is generated.

The prediction results may be portfolios recommended by a financial analysis model, and in particular, through a process of data analysis and modeling, the system may generate a set of optimized portfolio suggestions based on factors such as the user's investment goals, risk preferences, and market conditions. The prediction result comprises the following contents:

1. Asset weight distribution: the system will recommend weight allocations for different asset classes based on the investment goals and risk preferences of the user to achieve the desired return and risk goals, the weight allocations may be expressed as percentages or scales, guiding the investor in the allocation of funds in the various asset classes.

2. Investment combination is formed: the outcome of the forecast will provide a specific organization of the portfolio, including the individual assets, securities, or funds selected.

3. Expected revenue and risk index: the predicted outcome will also provide an expected return and risk indicator for the generated portfolio, helping the user assess the potential return and risk level of the portfolio. Expected revenue and risk indicators include: annual rate of return, rate of fluctuation, maximum withdrawal, etc.

In step S304, the system is optimized and updated.

The data analysis and modeling module 22 also requires system optimization and updating, e.g., optimizing model parameters, updating data sets, adding new machine learning algorithms, etc., to ensure accuracy and real-time of the prediction results and recommendations of the module.

The modules in the embodiment of the invention are connected and cooperated in a data flow, control flow, information interaction and other modes, so that continuous optimization and adjustment of the investment combination are realized together, the factors such as market change and risk preference of investors are adapted, the functions such as friendly user interaction interface and investment advice are provided, the investors can be helped to better understand market conditions and investment strategies, and the quality of investment decision is improved.

The embodiment of the invention can realize the following technical effects:

1. the intelligent investment portfolio allocation is realized, a more accurate asset allocation scheme can be provided for investors, and the investment efficiency and the yield are improved.

2. And the financial market is deeply analyzed and modeled by utilizing technologies such as data mining, machine learning and the like, so that indexes such as market trend, risk and the like can be predicted more accurately.

3. And the optimal investment combination is constructed by utilizing technologies such as constraint optimization algorithm, so that the balance between risks and benefits can be realized, and certain constraint conditions are met.

4. The investment portfolio can be dynamically adjusted by utilizing a real-time monitoring technology, and continuous optimization and adjustment of the investment portfolio can be realized so as to adapt to market changes and risk preference of investors.

5. The method has the advantages of providing friendly user interaction interfaces, investment advice and other functions, helping investors to better understand market conditions and investment strategies, and improving the quality of investment decisions.

The invention is described below in connection with alternative embodiments.

Example two

The apparatus for configuring a portfolio provided in this embodiment includes a plurality of implementation units, each of which corresponds to each of the implementation steps in the first embodiment.

FIG. 4 is a schematic illustration of an alternative portfolio configuration device, as shown in FIG. 4, in accordance with an embodiment of the present invention, the portfolio configuration device may include: a response unit 41, an extraction unit 42, an output unit 43, a configuration unit 44, wherein,

a response unit 41, configured to obtain historical transaction data of N financial products in response to the investment portfolio configuration instruction, where N is a positive integer;

an extracting unit 42, configured to extract feature data in the historical transaction data of each financial product, to obtain N feature sets;

an output unit 43 for inputting the N feature sets into the target model and outputting simulated investment data associated with the N financial products;

a configuration unit 44, configured to perform a combinatorial configuration on N financial products based on the simulated investment data, to obtain an investment portfolio configuration result, where the investment portfolio configuration result includes: m financial products to be recommended, the weight occupied by each financial product, the income index and the risk index, wherein M is a positive integer less than or equal to N.

The above-mentioned configuration device of investment portfolio can firstly respond to the configuration instruction of investment portfolio through the response unit 41 to obtain the historical transaction data of N financial products, N is a positive integer, then the extraction unit 42 extracts the characteristic data in the historical transaction data of each financial product respectively to obtain N characteristic sets, then the output unit 43 inputs all characteristic sets into the target model to output the simulated investment data of the associated N financial products, finally the configuration unit 44 performs the combination configuration on all financial products based on the simulated investment data to obtain the configuration result of the investment portfolio, wherein the configuration result of the investment portfolio includes: m financial products to be recommended, the weight occupied by each financial product, the income index and the risk index, wherein M is a positive integer less than or equal to N.

In the embodiment of the invention, the historical transaction data of the financial products are collected, the characteristic data in the historical transaction data are extracted, the characteristic set is input into the target model, the target model is utilized to analyze the market environment trend in the historical transaction data, the target model is used for outputting the simulated investment data related to all the financial products, the simulated investment data are used as the basis to configure the investment combination which can be put into the market, the algorithm in the target model provides an intelligent investment combination distribution system by utilizing the target model to fully consider the market environment factors, the investment object is assisted to make more objective and accurate investment decisions, the decision efficiency can be greatly improved while the target model is utilized to analyze the market data, the time and energy of investors are saved, and the technical problems of low efficiency, great time and energy consumption and insufficient objective and accurate decision result of investment combination decision making in the related technology are solved.

Optionally, the apparatus for configuring a portfolio further includes: the first receiving module is configured to receive investment preference data of a target object, where the investment preference data at least includes: investment goals, income expectations, risk bearing ranges; the first input module is used for inputting the investment preference data into the target model as constraint conditions of the target model in the market trend prediction process of the financial products.

Optionally, the apparatus for configuring a portfolio further includes: the preprocessing module is used for preprocessing the historical transaction data of all financial products, wherein the data preprocessing comprises at least one of the following steps: data deduplication, data deficiency, format standardization, and data simplification.

Optionally, the extraction unit includes: the determining module is used for determining financial feature categories to be extracted according to a preset feature extraction strategy; the sampling module is used for carrying out characteristic sampling on historical transaction data of the financial products based on the financial characteristic categories to obtain sampling data; the dimension reduction module is used for carrying out data dimension reduction on the sampling data based on a preset standard format, and carrying out normalization processing on the sampling data after dimension reduction to obtain characteristic data.

Optionally, the output unit includes: the generating module is used for generating H sets of initial investment combination schemes based on the investment preference data and the feature data in all feature sets, wherein each set of initial investment combination schemes comprises: m financial products and the weight occupied by each financial product, wherein H is a positive integer, and M is a positive integer less than or equal to N; the second input module is used for inputting each set of initial investment portfolio scheme into the target model, carrying out expected simulation on investment results of all financial products in the initial investment portfolio scheme by the target model, and outputting market trend prediction results of each set of initial investment portfolio scheme, wherein the market trend prediction results comprise: an expected profit index, an expected risk index, and an expected loss index; and the output module is used for outputting simulated investment data based on the investment risk bearing grade of the target object and the H sets of market trend prediction results, wherein the investment risk bearing grade is calculated according to the investment preference data of the target object.

Optionally, the apparatus for configuring a portfolio further includes: the first sending module is used for sending the investment combination configuration result to a display page of an object terminal used by a target object and collecting an investment confirmation result transmitted by the object terminal; the first construction module is used for constructing a transaction instruction based on the investment combination configuration result under the condition that the investment confirmation result indicates to pass, sending the transaction instruction to the transaction platform, and executing the transaction instruction by the transaction platform; and the second receiving module is used for receiving the adjustment advice returned by the target terminal under the condition that the investment confirmation result indicates not to pass, and adjusting the investment combination configuration result based on the adjustment advice.

Optionally, the apparatus for configuring a portfolio further includes: the acquisition module is used for acquiring real-time market data of M financial products in the investment portfolio configuration result after the interval appointed time length, and extracting real-time characteristic data in the real-time market data to obtain a real-time characteristic data set; the adjustment module is used for adjusting the investment portfolio configuration result based on the real-time characteristic data set to obtain an adjusted investment portfolio configuration result; the second construction module is used for constructing transaction adjustment instructions based on the adjusted investment portfolio configuration results; the second sending module is used for sending the transaction adjustment instruction to the transaction platform, and the transaction platform executes the transaction adjustment instruction.

The above-described apparatus for configuring a portfolio may further include a processor and a memory, and the above-described response unit 41, the extraction unit 42, the output unit 43, the configuration unit 44, and the like are stored in the memory as program units, and the processor executes the above-described program units stored in the memory to realize the corresponding functions.

The processor includes a kernel, and the kernel fetches a corresponding program unit from the memory. The kernel can be set with one or more, and the kernel parameters are adjusted to carry out combination configuration on N financial products based on the simulated investment data so as to obtain an investment combination configuration result.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), which includes at least one memory chip.

The application also provides a computer program product adapted to perform, when executed on a data processing device, a program initialized with the method steps of: responding to the investment combination configuration instruction, and acquiring historical transaction data of N financial products, wherein N is a positive integer; extracting characteristic data in historical transaction data of each financial product respectively to obtain N characteristic sets; inputting the N feature sets into a target model, and outputting simulation investment data related to N financial products; and carrying out combined configuration on the N financial products based on the simulated investment data to obtain an investment combination configuration result, wherein the investment combination configuration result comprises the following steps: m financial products to be recommended, the weight occupied by each financial product, the income index and the risk index, wherein M is a positive integer less than or equal to N.

According to another aspect of the embodiments of the present application, there is also provided a computer readable storage medium, including a stored computer program, where the computer program when executed controls a device in which the computer readable storage medium is located to perform the method of configuring a portfolio of any of the above.

According to another aspect of the embodiments of the present application, there is also provided an electronic device including one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of configuring an investment portfolio of any of the above.

Fig. 5 is a block diagram of a hardware structure of an electronic device (or mobile device) for a method of configuring a portfolio according to an embodiment of the present invention. As shown in fig. 5, the electronic device may include one or more processors 502 (shown in fig. 5 as 502a, 502b, … …,502 n) (the processor 502 may include a processing means such as a microprocessor MCU or a programmable logic device FPGA), a memory 504 for storing data. In addition, the method may further include: a display, an input/output interface (I/O interface), a Universal Serial Bus (USB) port (which may be included as one of the ports of the I/O interface), a network interface, a keyboard, a power supply, and/or a camera. It will be appreciated by those of ordinary skill in the art that the configuration shown in fig. 5 is merely illustrative and is not intended to limit the configuration of the electronic device described above. For example, the electronic device may also include more or fewer components than shown in FIG. 5, or have a different configuration than shown in FIG. 5.

The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.

In the foregoing embodiments of the present invention, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.

In the several embodiments provided in the present application, it should be understood that the disclosed technology may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and the division of units may be a logic function division, and there may be another division manner in actual implementation, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention.

Claims

1. A method of portfolio configuration, comprising:

responding to the investment combination configuration instruction, and acquiring historical transaction data of N financial products, wherein N is a positive integer;

extracting characteristic data in the historical transaction data of each financial product respectively to obtain N characteristic sets;

inputting the N feature sets into a target model, and outputting simulation investment data related to the N financial products;

and carrying out combination configuration on N financial products based on the simulated investment data to obtain an investment combination configuration result, wherein the investment combination configuration result comprises the following steps: m financial products to be recommended, the weight occupied by each financial product, the income index and the risk index, wherein M is a positive integer less than or equal to N.

2. The configuration method according to claim 1, characterized by further comprising, before inputting N of the feature sets into the object model:

receiving investment preference data of a target object, wherein the investment preference data at least comprises: investment goals, income expectations, risk bearing ranges;

inputting the investment preference data into the target model as a constraint condition of the target model in a market trend prediction process of the financial product.

3. The configuration method according to claim 1, further comprising, after acquiring the historical transaction data of the N financial products:

performing data preprocessing on the historical transaction data of all the financial products, wherein the data preprocessing comprises at least one of the following: data deduplication, data deficiency, format standardization, and data simplification.

4. The configuration method according to claim 1, characterized in that, when extracting feature data in the historical transaction data of the financial product, comprising:

determining the category of financial features to be extracted according to a preset feature extraction strategy;

performing feature sampling on the historical transaction data of the financial product based on the financial feature class to obtain sampling data;

and performing data dimension reduction on the sampling data based on a preset standard format, and performing normalization processing on the sampling data after dimension reduction to obtain the characteristic data.

5. The configuration method according to claim 1, characterized in that the step of inputting N sets of the features into a target model and outputting simulated investment data includes:

generating H sets of initial portfolio scenarios based on the investment preference data and the feature data in all the feature sets, wherein each set of initial portfolio scenarios includes: m financial products and the weight occupied by each financial product, wherein H is a positive integer, and M is a positive integer less than or equal to N;

Inputting each set of initial investment portfolio schemes into the target model, carrying out expected simulation on investment results of all financial products in the initial investment portfolio schemes by the target model, and outputting market trend prediction results of each set of initial investment portfolio schemes, wherein the market trend prediction results comprise: an expected profit index, an expected risk index, and an expected loss index;

and outputting the simulated investment data based on the investment risk bearing grade of the target object and the market trend prediction result of the H sets, wherein the investment risk bearing grade is calculated according to the investment preference data of the target object.

6. The arrangement method according to claim 1, further comprising, after the combination arrangement of N of the financial products based on the simulated investment data, after obtaining an investment portfolio arrangement result:

the investment combination configuration result is sent to a display page of an object terminal used by a target object, and investment confirmation results transmitted by the object terminal are collected;

when the investment confirmation result indicates passing, constructing a transaction instruction based on the investment combination configuration result, sending the transaction instruction to a transaction platform, and executing the transaction instruction by the transaction platform;

And receiving an adjustment suggestion returned by the target terminal under the condition that the investment confirmation result indicates not to pass, and adjusting the investment combination configuration result based on the adjustment suggestion.

7. The configuration method according to claim 6, characterized by further comprising, after the transaction instruction is transmitted to a transaction platform and executed by the transaction platform:

after a specified time length is set, acquiring real-time market data of M financial products in the investment portfolio configuration result, and extracting real-time characteristic data in the real-time market data to obtain a real-time characteristic data set;

based on the real-time characteristic data set, adjusting the investment portfolio configuration result to obtain an adjusted investment portfolio configuration result;

constructing a transaction adjustment instruction based on the adjusted investment portfolio configuration result;

and sending the transaction adjustment instruction to a transaction platform, and executing the transaction adjustment instruction by the transaction platform.

8. The configuration method according to any one of claims 1 to 7, characterized in that the feature data includes at least one of: portfolio feature data, market feature data, risk-benefit feature data, the portfolio feature data comprising: investment category, asset weight, investment deadline, correlation coefficient, the market characteristics data comprising: historical price, market index, interest rate index, the risk-benefit characteristic data comprising: historical yield, historical volatility, historical risk index.

9. A portfolio configuration apparatus, comprising:

the response unit is used for responding to the investment combination configuration instruction and acquiring historical transaction data of N financial products, wherein N is a positive integer;

the extraction unit is used for respectively extracting the characteristic data in the historical transaction data of each financial product to obtain N characteristic sets;

the output unit is used for inputting the N characteristic sets into a target model and outputting simulation investment data related to the N financial products;

the configuration unit is used for carrying out combination configuration on the N financial products based on the simulated investment data to obtain an investment combination configuration result, wherein the investment combination configuration result comprises the following steps: m financial products to be recommended, the weight occupied by each financial product, the income index and the risk index, wherein M is a positive integer less than or equal to N.

10. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored computer program, wherein the computer program, when run, controls a device in which the computer readable storage medium is located to perform the method of configuring a portfolio according to any one of claims 1 to 8.

11. An electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of configuring portfolios of any of claims 1 to 8.