User investment strategy recommendation method and device, electronic equipment and storage medium

Abstract

The invention provides a user investment strategy recommendation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining user data and investment mechanism data, analyzing the user data, generating user parameters, processing the investment mechanism data, generating channel information, and building a user portrait based on the user parameters and the channel information, and recommending an investment strategy to the user based on the user portrait. Therefore, the user data and the investment institution data are processed, the user portrait is established, and then the investment strategy is recommended for the user, so that the problem that the private investment signals are often difficult to capture when the user uses private, irony or inverse words to express the investment intention on platforms such as social media, news, forum and the like can be fundamentally solved. And especially in a financial market shaking period, missing of key information may cause serious deviation of investment suggestions and cannot meet requirements of investors for accurate investment suggestions.

Description

Technical Field

[0001] The present application relates to the field of big data, and in particular to a method, device, electronic device and storage medium for recommending user investment strategies. Background Art

[0002] With the rapid development of technology, users' behaviors in the investment field are becoming increasingly diversified. At the same time, information about investment is exploding, and this information is scattered across major social media, news, forums and other platforms. When faced with a huge amount of information, how investors can filter out valuable content and accurately understand the investment intentions and emotional tendencies behind it has become a severe challenge.

[0003] Traditional financial analysis mainly relies on company financial report disclosure and is conducted through financial structure and investment software financial report analysis. However, this method is too professional and it is difficult for ordinary investors to conduct in-depth analysis. The analysis results are often limited by the disclosure content and time of the company's financial report. In addition, different investors have different investment preferences and risk tolerance. Therefore, a more intelligent and comprehensive investment strategy recommendation method is needed to recommend investment strategies for users.

[0004] In the related technologies, the existing recommendation of user investment strategies uses traditional recognition models (such as BiLSTM, CRF) to capture and analyze investment signals. However, these models often have difficulty capturing these obscure investment signals when users use obscure, sarcastic or ironic language to express their investment intentions on social media, news, forums and other platforms. Especially during periods of financial market turmoil, missing key information may lead to serious deviations in investment advice and fail to meet investors' demand for accurate investment advice. Summary of the invention

[0005] The purpose of the embodiments of the present application is to provide a method, device, electronic device and storage medium for recommending user investment strategies, so as to solve the problem that it is often difficult to capture these obscure investment signals when users use obscure, sarcastic or ironic language to express their investment intentions on social media, news, forums and other platforms, especially during periods of financial market turmoil. Missing key information may lead to serious deviations in investment advice and fail to meet investors' needs for accurate investment advice. The specific technical solution is as follows:

[0006] In a first aspect of an embodiment of the present application, a method for recommending a user investment strategy is first proposed, the method comprising:

[0007] Obtain user data and investment institution data;

[0008] Analyze the user data to generate user parameters;

[0009] Processing the investment institution data to generate channel information;

[0010] Creating a user profile based on the user parameters and the channel information;

[0011] Based on the user portrait, an investment strategy is recommended to the user.

[0012] In an optional implementation manner, analyzing the user data to generate user parameters includes:

[0013] The user data includes interaction data and transaction data;

[0014] Analyze the interaction data using natural language processing technology to obtain intention information;

[0015] Analyze the transaction data using big data analysis technology to obtain transaction information;

[0016] The intention information and the transaction information are integrated to generate the user parameters.

[0017] In an optional implementation, the using of natural language processing technology to analyze the interaction data to obtain the intention information includes:

[0018] The intention information includes emotional tendency;

[0019] The emotional tendency is obtained by performing sentiment analysis on the interaction data through a natural language processing algorithm.

[0020] In an optional implementation manner, the processing of the investment institution data to generate channel information includes:

[0021] Preprocessing the investment institution data to obtain key information;

[0022] Classifying the key information to obtain classified key information;

[0023] Integrating the classified key information to obtain integrated information;

[0024] The integrated information is deduplicated to obtain the channel information.

[0025] In an optional implementation, the establishing of a user profile based on the user parameters and the channel information includes:

[0026] Merging the user parameters and the channel information to obtain target information;

[0027] The target information is analyzed using natural language processing technology to establish the user portrait.

[0028] In an optional implementation, the recommending an investment strategy to the user based on the user portrait includes:

[0029] Performing sentiment analysis on the sentiment tendency through a pre-trained variant model and a domain-specific dictionary to obtain user sentiment data;

[0030] Analyze the user portrait and the user sentiment data in combination with a machine learning algorithm to generate a target investment strategy;

[0031] The target investment strategy is recommended to the user.

[0032] In an optional embodiment, the method further comprises:

[0033] Collecting user feedback data, wherein the user feedback data includes the user's acceptance of the recommended investment strategy and feedback on investment results;

[0034] Analyze the user feedback data using machine learning algorithms and statistical analysis methods to obtain analysis results;

[0035] Based on the analysis results, the recommendation method for the user investment strategy is optimized.

[0036] In a second aspect of the embodiment of the present application, a device for recommending user investment strategies is also provided, the device comprising:

[0037] Acquisition module, to obtain user data and investment institution data;

[0038] A first processing module analyzes the user data to generate user parameters;

[0039] The second processing module processes the investment institution data to generate channel information;

[0040] A third processing module, based on the user parameters and the channel information, establishes a user portrait;

[0041] The recommendation module recommends investment strategies to users based on the user portrait.

[0042] In a third aspect of the embodiments of the present application, there is further provided an electronic device, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0043] Memory, used to store computer programs;

[0044] The processor is used to implement the method for recommending user investment strategies as described in any one of the first aspects above when executing the program stored in the memory.

[0045] In a fourth aspect of an embodiment of the present application, a computer-readable storage medium is further provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the method for recommending user investment strategies described in any one of the first aspects above is implemented.

[0046] In a fifth aspect of the embodiments of the present application, there is also provided a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the method for recommending user investment strategies as described in any one of the first aspects above.

[0047] The above technical solution provided in the embodiment of the present application obtains user data and investment institution data, analyzes the user data, generates user parameters, processes the investment institution data, generates channel information, establishes a user portrait based on the user parameters and channel information, and recommends investment strategies to users based on the user portrait. In this way, by processing the user data and investment institution data, establishing a user portrait, and then recommending investment strategies to users, it can fundamentally solve the problem that when users use obscure, sarcastic or ironic language on social media, news, forums and other platforms to express their investment intentions, it is often difficult to capture these obscure investment signals. Especially in periods of financial market turmoil, missing key information may lead to serious deviations in investment advice and fail to meet investors' needs for accurate investment advice. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0050] Figure 1 A schematic diagram of an implementation flow of a method for recommending a user investment strategy provided in an embodiment of the present application;

[0051] Figure 2 A schematic diagram of an implementation flow of another method for recommending user investment strategies provided in an embodiment of the present application;

[0052] Figure 3 A schematic diagram of an implementation flow of user data analysis provided in an embodiment of the present application;

[0053] Figure 4 A schematic diagram of an implementation process of establishing a user portrait provided in an embodiment of the present application;

[0054] Figure 5 A schematic diagram of an implementation process of a recommended investment strategy provided in an embodiment of the present application;

[0055] Figure 6 A schematic diagram of the structure of a device for recommending user investment strategies provided in an embodiment of the present application;

[0056] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0058] To facilitate understanding of the embodiments of the present application, further explanation will be given below with reference to specific embodiments in conjunction with the accompanying drawings. The embodiments do not constitute a limitation on the embodiments of the present application.

[0059] like Figure 1 FIG. 1 is a schematic diagram of an implementation flow of a method for recommending a user investment strategy provided by an embodiment of the present application. The method may specifically include the following steps:

[0060] S101, obtaining user data and investment institution data.

[0061] In the embodiments of the present application, user data can be obtained from platforms such as social media and investment forums, where the user data may include user comments, likes, forwarding, browsing, searching, transaction records, etc. on these platforms. Investment institution data can be obtained from cooperative investment institutions, where the investment institution data may include investment projects participated by the investment institution, investment amount, investment profit, and industry research reports and market trend analysis published by the investment institution, etc., which are not limited in the embodiments of the present application.

[0062] For example, user 1 likes information about real estate on social media, and the real estate information liked by user 1 is used as user data. Cooperating investment institution 1 publishes market trend analysis, and the market trend analysis data is used as investment institution data.

[0063] S102: Analyze user data and generate user parameters.

[0064] In the embodiment of the present application, the user data is analyzed to generate user parameters. The analysis of the user data may include analyzing the user's behavior, emotion, transaction records, etc.

[0065] For example, the user data obtained is that user 1 likes real estate information. By analyzing the user data, it can be obtained that the user parameter is that user 1 may be interested in the real estate.

[0066] S103, processing the investment institution data to generate channel information.

[0067] In an embodiment of the present application, processing the institutional data may include preprocessing the investment data to generate channel information, wherein the preprocessing may include operations such as data cleaning and deduplication.

[0068] For example, investment institution data is market trend analysis data, which includes information such as housing price trends, hot-selling properties, and investment returns in multiple cities. The market trend analysis data is deduplicated to ensure that the data for each city and each property only appears once, while removing invalid or erroneous data.

[0069] S104: Create a user profile based on user parameters and channel information.

[0070] In an embodiment of the present application, a user image is established based on user parameters and channel information, wherein the user portrait may include features such as user preferences and user needs. The user portrait may be a collection of representative user features, which is not limited in the present application example.

[0071] For example, user parameters show that user 1 may be interested in real estate, especially high-end residential properties in first-tier cities, and channel information indicates that the high-end residential market in first-tier cities has a high return on investment. Based on user parameters and channel information, the user profile that can be established is that user 1 is an investor interested in the real estate market, and is particularly interested in the high-end residential market in first-tier cities. According to channel information, user 1 may invest in the high-end residential market in first-tier cities under the current market environment.

[0072] S105, recommend investment strategies to users based on user portraits.

[0073] In an embodiment of the present application, an investment strategy is recommended to a user based on a user portrait. By establishing a user portrait based on user parameters and channel information, a user investment strategy is generated and recommended to the user.

[0074] For example, the user portrait of User 1 is that of an investor who focuses on the high-end residential market in first-tier cities. Based on the user portrait of User 1, an investment strategy can be recommended to User 1: "In the current market, the high-end residential market in first-tier cities has a high investment value. It is recommended that User 1 focus on the hot-selling properties in the market and invest at the right time. Alternatively, it is recommended that User 1 focus on related financial products and services, such as real estate mortgage loans and real estate investment funds." The above investment strategy can be recommended to the user.

[0075] Through the above description of the technical solution provided in the embodiment of the present application, user data and investment institution data are obtained, user data are analyzed, user parameters are generated, investment institution data are processed, channel information is generated, user portraits are established based on user parameters and channel information, and investment strategies are recommended to users based on user portraits. In this way, by processing user data and investment institution data, establishing user portraits, and then recommending investment strategies to users, it is possible to fundamentally solve the problem that when users use obscure, sarcastic or ironic language on social media, news, forums and other platforms to express their investment intentions, it is often difficult to capture these obscure investment signals, especially in periods of financial market turmoil. Missing key information may lead to serious deviations in investment advice and fail to meet investors' needs for accurate investment advice.

[0076] like Figure 2 FIG. 1 is a schematic diagram of an implementation flow of another method for recommending user investment strategies provided in an embodiment of the present application. The method may specifically include the following steps:

[0077] S201, obtaining user data and investment institution data.

[0078] In the embodiment of the present application, this step is similar to the above-mentioned step S101, and the embodiment of the present application will not be described one by one here.

[0079] S202, analyzing the user data to generate user parameters;

[0080] In the embodiment of the present application, the user data is analyzed to generate user parameters, wherein the user data may include interaction data and transaction data. The user data may be analyzed by analyzing the interaction data contained in the user data and analyzing the transaction data contained in the user data to generate the user parameters, which is not limited in the example of the present application.

[0081] For example, by analyzing the interaction data of user 1 and the transaction data of user 1, user parameters of user 1 are generated.

[0082] Specifically, the user data is analyzed to generate user parameters. The interaction data and transaction data can be analyzed to generate user parameters, such as Figure 3As shown, a schematic diagram of an implementation process of user data analysis provided in an embodiment of the present application may include the following steps:

[0083] S301, using natural language processing technology to analyze the interaction data to obtain intention information.

[0084] In the embodiment of the present application, natural language processing technology is used to analyze the interaction data to obtain intention information, wherein the interaction data includes the user's comments, likes, shares, and forwarding data on social media. In addition, the interaction data can also be analyzed by recurrent neural networks, long short-term memory networks, and other technologies, which are not limited in the present application example.

[0085] For example, user 1 likes multiple pieces of information about real estate on social media. Then, the real estate information liked by user 1 is used as interaction data. By analyzing the interaction data through a natural language processing algorithm, we can obtain information about user 1's possible interest in real estate topics.

[0086] Among them, the intention information includes emotional tendencies. The interaction data is analyzed using natural speech processing technology to obtain the intention information, including:

[0087] The sentiment analysis of the interaction data is performed through natural language processing algorithms to obtain the emotional tendency.

[0088] In an embodiment of the present application, by analyzing the user's interaction data, the user's emotional attitude towards specific content or topics, such as support, opposition, neutrality, etc., can be understood, and the emotional attitude can also be accurately obtained when the user posts ironic remarks.

[0089] For example, user 1 likes multiple pieces of information about real estate on social media, and user 1's comment information shows that he is optimistic about high-end residential properties. Then, user 1 likes the real estate information and is optimistic about high-end residential properties as interaction data. The interaction data is subjected to sentiment analysis through the natural language processing algorithm to obtain the emotional tendency that user 1 may be interested in real estate and maintain a supportive attitude towards the high-end residential market.

[0090] For example, when user 1 posted on social media, "I am so smart that I chose to invest in A! Now my money is like being swallowed by a black hole, and I can't even see its shadow. This is really a good project with a 'guaranteed profit', but the profit is negative!", the statement posted by user 1 is ironic. Traditional technical means may obtain information that supports investment in A and A is profitable. However, through sentiment analysis using natural language processing algorithms, it can be obtained that investment in A is not supported and A is suffering a serious loss.

[0091] S302, using big data analysis technology to analyze transaction data to obtain transaction information.

[0092] In the embodiment of the present application, the transaction data is mined and analyzed using big data technology to obtain transaction information. Among them, the transaction data may include the user's investment transaction amount, investment product type, investment transaction time, investment transaction frequency and other data in the platform. The transaction information may include whether the user tends to trade frequently or hold for a long time, the user's investment preference, that is, which type of product is preferred, and the risk preference, that is, whether the attitude is stable and conservative or active and risky when facing market fluctuations. The embodiment of the present application does not limit this.

[0093] For example, user 1 holds stocks of high-end community A on the platform for a long time, and the volatility of stocks of high-end community A is relatively large. Through big data analysis technology, the transaction information that can be obtained shows that user 1 tends to hold stocks for a long time and has a greater risk tolerance.

[0094] S303, integrating the intention information and the transaction information to generate user parameters.

[0095] In an embodiment of the present application, when the intention information and the transaction information are fused, it is necessary to first clean and preprocess the intention information and the transaction information, and extract features from the intention information and the transaction information after cleaning and preprocessing, so that the extracted features can be fused through a data fusion algorithm to generate user parameters.

[0096] For example, user 1 is an investor who holds high-end community A stocks for a long time on the platform, and the stock fluctuation of high-end community A is relatively large. User 1's intention information indicates that user 1 may prefer to invest in the high-end real estate market, and the transaction information indicates that user 1 prefers to hold for a long time and has a high risk tolerance. After cleaning and preprocessing, the user parameters indicate that user 1 is optimistic about the high-end real estate market and has a high risk tolerance.

[0097] S203, pre-processing the investment institution data to obtain key information.

[0098] In the embodiment of the present application, the investment institution data is preprocessed to obtain key information. The investment institution data includes the investment projects, investment amounts, investment profits, and industry research reports and market trend analysis data released by the cooperating investment institutions. The preprocessing process may include data cleaning, formatting, normalization, and other operations. The embodiment of the present application does not limit this.

[0099] For example, as shown in Table 1, the data of the investment institutions obtained are cleaned. The investment amount format of Project 4 corresponding to Institution C is incorrect, so the data of Project 4 of Institution C is removed. The investment amount format of Project 2 of Institution B is incorrect and needs to be adjusted to 200,000. The investment amount can be normalized by dividing the investment amount of each project by the maximum investment amount to obtain a value between 0 and 1. The key information obtained through the above operation includes the name of the institution, participating projects, investment amount, profitability, industry research report, and market trend analysis.

[0100] Table 1

[0101]

[0102]

[0103] S204, classify the key information to obtain the classified key information.

[0104] In the embodiment of the present application, by classifying the key information, the information can be better integrated and organized, and the key information can be classified according to the type of investment institution, investment field, investment stage and other dimensions.

[0105] For example, as shown in Table 1, if Project 1 and Project 3 are Internet projects, and Project 2 is a real estate project, Project 1 and Project 3 can be classified into one category, and Project 2 can be classified into another category. Alternatively, if the profitability of Project 1 and Project 3 is profitable, and the profitability of Project 2 is loss-making, then Project 1 and Project 3 can be classified into one category, and Project 2 can be classified into another category.

[0106] S205, integrating the classified key information to obtain integrated information.

[0107] In an embodiment of the present application, the classified data is integrated so that the scattered data are summarized. The integration may include eliminating duplicate data and summarizing similar data, thereby generating a comprehensive data set containing various information of the investment institution, i.e., integrated information.

[0108] For example, as shown in Table 1, we can classify by investment institution name, integrate Project 1 and Project 3 in Institution A, and summarize them together for subsequent analysis. Or after classification and integration by project field, we can get the Internet field: Institution A (participating projects: Project 1, Project 3; total investment amount: 6 million yuan; number of profitable projects: 2; number of industry research reports: 1; number of market trend analysis: 1); Real estate field Institution B (participating projects: Project 2; investment amount: 200000 yuan; number of profitable projects: 0; number of loss-making projects: 1; number of industry research reports: 1; number of market trend analysis: 1).

[0109] S206, performing deduplication processing on the integrated information to obtain channel information.

[0110] In the embodiment of the present application, deduplication processing is performed on the integrated information, including comparison and identification of identical or similar records, deletion of duplicate data, etc. Through deduplication processing, more accurate and non-redundant channel information is obtained.

[0111] For example, if the corresponding integrated information is Institution A (participating in project 1, investment amount of 1 million yuan, profitable project), Institution A (participating in project 1, investment amount of 5 million yuan, profitable project), then these two pieces of data are regarded as duplicate records, only one piece of data is retained, and the other piece of data is deleted.

[0112] S207, creating a user portrait based on user parameters and channel information.

[0113] In an embodiment of the present application, a user image is established based on user parameters and channel information, wherein the user portrait may include user preferences, user needs, etc. The user portrait is a collection of user characteristics, which is not limited in the present application example.

[0114] For example, user parameters show that user 1 may be interested in real estate, especially high-end residential properties in first-tier cities, and channel information indicates that the high-end residential market in first-tier cities has a high return on investment. Based on user parameters and channel information, the user profile that can be established is that user 1 is an investor interested in the real estate market, and is particularly interested in the high-end residential market in first-tier cities. According to channel information, user 1 may invest in the high-end residential market in first-tier cities under the current market environment.

[0115] Specifically, based on user parameters and channel information, a user profile is established, such as Figure 4 As shown, a schematic diagram of an implementation process of establishing a user portrait provided in an embodiment of the present application may include the following steps:

[0116] S401, integrating user parameters and channel information to obtain target information.

[0117] In the embodiment of the present application, the user parameters and channel information are deeply integrated. Technical means such as data matching, data cleaning, and data standardization can be used to ensure the accuracy and consistency of the user parameters and channel information during the integration process, and to associate data from different sources to generate target information.

[0118] For example, user parameters are: User 1 has a strong risk tolerance and is interested in the high-end residential market, and channel information is the trend of real estate stocks. By integrating user parameters with channel information, the target information is that User 1 may invest in the high-end residential market in first-tier cities under the current market environment, especially in high-end residential area A with great value-added potential.

[0119] S402, using natural language processing technology to analyze the target information and establish a user portrait.

[0120] In an embodiment of the present application, the target information can be parsed through natural language processing technology to obtain information such as the user's investment preferences, risk tolerance, areas of concern, etc., and a user portrait can be established based on the parsed information and user characteristics.

[0121] For example, if the target information includes information that User 1 is interested in the high-end real estate market and has a strong risk tolerance, then in the user portrait, User 1 may be portrayed as an investor who has a strong interest in the high-end real estate market and is willing to take higher risks.

[0122] S207, recommend investment strategies to users based on user portraits.

[0123] In an embodiment of the present application, an investment strategy is recommended to the user based on the user portrait.

[0124] For example, the user portrait of User 1 is that of an investor who focuses on the high-end residential market in first-tier cities. Based on the user portrait of User 1, an investment strategy can be recommended to User 1: "In the current market, the high-end residential market in first-tier cities has a high investment value. It is recommended that User 1 focus on the hot-selling properties in the market and invest at the right time. Alternatively, it is recommended that User 1 focus on related financial products and services, such as real estate mortgage loans and real estate investment funds."

[0125] Specifically, based on user portraits, investment strategies are recommended to users, such as Figure 5 As shown, a schematic diagram of an implementation process of a recommended investment strategy provided in an embodiment of the present application may include the following steps:

[0126] S501, sentiment analysis is performed on sentiment tendency through a pre-trained variant model and a domain-specific dictionary to obtain user sentiment data.

[0127] In the embodiment of the present application, in order to more accurately capture the user's emotional tendencies, the user's interaction data can be subjected to sentiment analysis through a pre-trained variant model and a domain-specific dictionary. The variant model is a model that can dynamically adjust its parameters according to the context, and can more accurately understand the user's emotional expression in a specific context. The domain-specific dictionary contains words and phrases related to the investment field, which can help the model better identify and understand emotional expressions related to investment.

[0128] For example, a user posts a comment about the stock market on social media, such as "The stock market has been volatile recently, I hope the stocks I bought can stabilize." Through the analysis of variant models and domain-specific dictionaries, we can identify the user's concerns about stock market fluctuations and expectations for the stability of the stocks they hold, thereby obtaining the user's sentiment data.

[0129] S502, analyzing the user portrait and user sentiment data in combination with a machine learning algorithm to generate a target investment strategy.

[0130] In the embodiment of the present application, the user portrait and user sentiment data are analyzed by a machine learning algorithm to generate an investment strategy that meets the user's needs and emotional tendencies. The machine learning algorithm can extract useful features and regularities from a large amount of data, and make predictions and decisions based on these features and regularities, and can generate a target investment strategy through collaborative filtering and reinforcement learning, which is not limited in the embodiment of the present application.

[0131] For example, the user profile shows that the user is interested in the real estate market and has a strong risk tolerance. At the same time, the user sentiment data shows that the user is worried about the current stock market volatility. Based on this information, the machine learning algorithm can recommend some relatively stable real estate investment strategies to the user, such as investing in the high-end residential market in first-tier cities, or choosing some real estate company stocks with a good profit record and stable development prospects.

[0132] S503: Recommend the target investment strategy to the user.

[0133] In the embodiment of the present application, after the target investment strategy is generated, it can be recommended to the user in a suitable manner. The recommendation method may include displaying detailed information of the investment strategy on the user interface, sending a summary of the investment strategy via email or text message, etc., which is not limited in the embodiment of the present application.

[0134] For example, a dedicated investment strategy recommendation page can be provided to users, which will display investment strategies tailored for users, including detailed information such as the name of the investment strategy, expected returns, risk level, etc. Users can decide whether to adopt the investment strategy based on this information.

[0135] In addition, after implementing investment strategies for users through the above method, user feedback data can also be collected.

[0136] Among them, user feedback data includes users' acceptance of recommended investment strategies and feedback on investment results.

[0137] For example, when an investment strategy 1 is recommended to user 1, and user 1 chooses to accept investment strategy 1, then user feedback data of "acceptance" will be received. After the user has implemented the investment strategy for a period of time and has made a profit, user 1 will evaluate the investment results and give a "very satisfied" evaluation.

[0138] The user feedback data is analyzed using machine learning algorithms and statistical analysis methods to obtain analysis results.

[0139] For example, after collecting feedback data from User 1, a machine learning algorithm is used to analyze the factors that influence the user's acceptance of the investment strategy, and it is found that User 1's risk tolerance is one of the key factors that influence his acceptance of the investment strategy.

[0140] Based on the analysis results, the recommendation method for user investment strategies is optimized, by increasing the weight of factors that have a significant impact on user acceptance.

[0141] For example, for users with lower risk tolerance, more conservative investment strategies may be recommended.

[0142] At the same time, cluster analysis can be used to divide users into different groups and provide personalized investment strategy recommendations for each group, thereby improving the accuracy of investment strategy recommendations and user satisfaction.

[0143] For example, a more aggressive investment strategy may be recommended for younger users with higher risk tolerance, while a more conservative investment strategy may be recommended for older users with lower risk tolerance.

[0144] In addition, to ensure the privacy and security of users during use, user data can be anonymized and de-identified. User data can be encrypted and stored, and anonymized using hash functions, tokenization and other technologies. De-identification can be performed through data desensitization and data obfuscation technologies, replacing sensitive information in user data with information that cannot be directly associated with the user.

[0145] Corresponding to the above method embodiment, the present application embodiment also provides a device for recommending user investment strategies, such as Figure 6 As shown, the device may include an acquisition module 601, a first processing module 602, a second processing module 603, a third processing module 604, and a recommendation module 605.

[0146] Acquisition module 601, acquiring user data and investment institution data;

[0147] The first processing module 602 analyzes the user data and generates user parameters;

[0148] The second processing module 603 processes the investment institution data to generate channel information;

[0149] The third processing module 604 creates a user portrait based on user parameters and channel information;

[0150] The recommendation module 605 recommends investment strategies to users based on user portraits.

[0151] The present application also provides an electronic device, such as Figure 7 As shown, it includes a processor 701, a communication interface 702, a memory 703 and a communication bus 704, wherein the processor 701, the communication interface 702, and the memory 703 communicate with each other through the communication bus 704.

[0152] Memory 703, used for storing computer programs;

[0153] In one embodiment of the present application, the processor 701, when used to execute the program stored in the memory 703, implements the following steps:

[0154] Obtain user data and investment institution data, analyze the user data, generate user parameters, process the investment institution data, generate channel information, establish user portraits based on user parameters and channel information, and recommend investment strategies to users based on the user portraits.

[0155] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0156] The communication interface is used for communication between the above electronic device and other devices.

[0157] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0158] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0159] In another embodiment provided in the present application, a storage medium is also provided, in which instructions are stored. When the storage medium is executed on a computer, the computer executes the method for recommending user investment strategies described in any of the above embodiments.

[0160] In another embodiment provided by the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute the method for recommending user investment strategies described in any of the above embodiments.

[0161] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a storage medium, or transmitted from one storage medium to another storage medium, for example, the computer instructions may be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive Solid State Disk (SSD)), etc.

[0162] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0163] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0164] The above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application are included in the protection scope of the present application.

Claims

1. A method for recommending user investment strategies, characterized in that: The method comprises: Obtain user data and investment institution data; Analyze the user data to generate user parameters; Processing the investment institution data to generate channel information; Creating a user profile based on the user parameters and the channel information; Based on the user portrait, an investment strategy is recommended to the user.

2. The method according to claim 1, characterized in that The analyzing the user data to generate user parameters includes: The user data includes interaction data and transaction data; Analyze the interaction data using natural language processing technology to obtain intention information; Analyze the transaction data using big data analysis technology to obtain transaction information; The intention information and the transaction information are integrated to generate the user parameters.

3. The method according to claim 2, characterized in that The using of natural language processing technology to analyze the interaction data to obtain the intention information includes: The intention information includes emotional tendency; The emotional tendency is obtained by performing sentiment analysis on the interaction data through a natural language processing algorithm.

4. The method according to claim 1, characterized in that The processing of the investment institution data to generate channel information includes: Preprocessing the investment institution data to obtain key information; Classifying the key information to obtain classified key information; Integrating the classified key information to obtain integrated information; The integrated information is deduplicated to obtain the channel information.

5. The method according to claim 1, characterized in that The establishing of a user profile based on the user parameters and the channel information includes: Merging the user parameters and the channel information to obtain target information; The target information is analyzed using natural language processing technology to establish the user portrait.

6. The method according to claim 3, characterized in that The recommending investment strategies to the user based on the user portrait includes: Performing sentiment analysis on the sentiment tendency through a pre-trained variant model and a domain-specific dictionary to obtain user sentiment data; Analyze the user portrait and the user sentiment data in combination with a machine learning algorithm to generate a target investment strategy; The target investment strategy is recommended to the user.

7. The method according to claim 1, characterized in that The method further comprises: Collecting user feedback data, wherein the user feedback data includes the user's acceptance of the recommended investment strategy and feedback on investment results; Analyze the user feedback data using machine learning algorithms and statistical analysis methods to obtain analysis results; Based on the analysis results, the recommendation method for the user investment strategy is optimized.

8. A device for recommending user investment strategies, characterized in that: The device comprises: Acquisition module, to obtain user data and investment institution data; A first processing module analyzes the user data to generate user parameters; The second processing module processes the investment institution data to generate channel information; A third processing module, based on the user parameters and the channel information, establishes a user portrait; The recommendation module recommends investment strategies to users based on the user portrait.

9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, for implementing the method steps described in any one of claims 1 to 7 when executing a program stored in a memory.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps described in any one of claims 1 to 7 are implemented.

Images