Investment risk analysis method and system based on fund user portrait analysis

Abstract

The invention relates to an investment risk analysis method and system based on fund user portrait analysis. The method comprises the steps of determining investment preference data and investment fluctuation data of a user based on historical investment data of the user; and performing matching based on the investment preference data and the investment fluctuation data to obtain a plurality of project subjects, obtaining operation information of the project subjects, generating project subject dynamic portraits based on the operation information, and determining investment suggestions and risk information based on the project subject dynamic portraits. According to the method, logic calculation can be better carried out according to basic information of an enterprise, business prosperity of the industry and support of related policies, investment suggestions about investment, investment scale, investment cycle and the like of the enterprise are given, and related fund managers are better assisted to make investment decisions.

Description

Technical Field

[0001] The present invention relates to the technical field of financial data processing, and in particular to an investment risk analysis and system based on fund user portrait analysis. Background Art

[0002] When fund managers make fund investments and decisions, they hope to receive more support. Through the basic information of the invested enterprises, the industries they belong to, regional policies and other related information, as well as the current investment preferences of the fund managers, auxiliary decision-making can be provided, which can better help fund managers analyze whether the enterprises are worth investing in, the investment cycle and returns, etc.

[0003] At present, when making investment decisions, fund managers use web crawling technology to obtain basic information about relevant companies, their industries, and regional policies, and conduct data mining based on the user's investment preferences. The collected data is summarized through classification algorithms and regression algorithms to draw conclusions to assist in decision-making. Existing data mining technology mainly classifies and summarizes data, but cannot perform intelligent analysis based on existing data. The auxiliary decisions given are relatively rigid, and cannot analyze and predict future trends based on historical data. Summary of the invention

[0004] In view of this, it is necessary to provide an investment risk analysis and system based on fund user portrait analysis to solve the defects of the existing technology that it is impossible to conduct intelligent analysis based on existing data, the auxiliary decisions given are relatively rigid, and it is impossible to analyze and predict future trends based on historical data.

[0005] In order to solve the above problems, in a first aspect, an embodiment of the present invention provides an investment risk analysis method based on fund user profile analysis, comprising: Determine the user's investment preference data and investment volatility data based on the user's historical investment data; Based on the matching of the investment preference data and the investment volatility data, multiple project entities are obtained, the operating information of the project entities is acquired, a dynamic portrait of the project entity is generated based on the operating information, and investment advice and risk information are determined based on the dynamic portrait of the project entity.

[0006] Preferably, the business information includes basic enterprise information, business dynamics information and financial report information. The basic enterprise information includes registered address, registered capital, establishment time, business scope, enterprise team, shareholders and shareholding ratio; the business dynamics information includes policy support information, market activity information, sales data, customer satisfaction, cooperation network, market layout and major events.

[0007] Preferably, the determining of the user's investment preference data and investment volatility data based on the user's historical investment data specifically includes: Obtaining the user's historical investment data based on at least one of the following methods: investment platform data interface, cooperation with third-party data service providers, data crawlers, data mining, and user self-upload; the historical investment data includes transaction time, transaction type, transaction amount, and profit and loss situation; Clean the historical investment data to remove duplicate, erroneous and invalid data; and standardize the cleaned data; Cluster analysis is performed on the historical investment data to determine the user's investment preference data and investment volatility data, wherein the investment preference data includes investment areas, investment types, investment cycles and return expectations; the investment volatility data includes position changes, transaction frequency, risk tolerance index, and return volatility index.

[0008] Preferably, generating a dynamic portrait of the project subject based on the business information specifically includes: Based on the pre-trained large language model (LLM) model, text analysis is performed on the business information to identify key features in advance, and a dynamic portrait of the project entity is generated based on the key features. The key features include investment status sub-features, market positioning and competition sub-features, financial sub-features, technological innovation sub-features, risk sub-features, growth potential sub-features and investor relations sub-features.

[0009] Preferably, the investment status sub-feature includes the current investment stage and financing history of the enterprise, the investment stage includes the start-up stage, the growth stage, and the mature stage, and the financing history includes the number of financings, the financing amount, and the investor background; The market positioning and competition sub-characteristics include market positioning, market size and potential, and competition landscape; the market positioning includes the position of the enterprise in the market, including target customer groups and market segments; the market size and potential include the size, growth rate and potential market opportunities of the market in which the enterprise is located; the competition landscape includes the market competition situation of the enterprise, including major competitors and market share distribution; The financial sub-characteristics include financial statements, return on investment and valuation pricing; the financial statements include revenue, profit and cash flow; the valuation pricing includes the market valuation, price-earnings ratio and price-to-book ratio of the enterprise; The technological innovation sub-characteristics include core technological indicators, innovation achievements, and R&D team size; Risk sub-characteristics include market risk indicators, financial risk indicators, and legal and compliance risk indicators; The growth potential sub-characteristics include growth potential indicators, strategic planning indicators, and expansion plan indicators; The investor relations sub-characteristics include shareholder structure, shareholding ratio, and information disclosure status.

[0010] Preferably, determining investment advice and risk information based on the dynamic portrait of the project subject includes: Performing data type conversion on key features of the project subject dynamic portrait, converting text data into numerical data, wherein the numerical data includes word vectors, TF-IDF and distributed vectors; The converted data is standardized or normalized to extract key information, which is then input into a pre-trained investment risk analysis model to determine the investment potential score and risk level.

[0011] Preferably, the extracting key information includes: The key information includes statistical feature information, text feature information, image feature information and time series feature information.

[0012] In a second aspect, an embodiment of the present invention provides an investment risk analysis system based on fund user profile analysis, comprising: A user analysis module, which determines the user's investment preference data and investment fluctuation data based on the user's historical investment data; The enterprise analysis module obtains multiple project entities based on the matching of the investment preference data and the investment volatility data, obtains the operating information of the project entities, generates a dynamic portrait of the project entity based on the operating information, and determines investment recommendations and risk information based on the dynamic portrait of the project entity.

[0013] In a third aspect, the present invention provides an electronic device, comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the investment risk analysis method based on fund user portrait analysis described in the first aspect above.

[0014] In a third aspect, the present invention provides a computer-readable storage medium for storing computer-readable programs or instructions, which, when executed by a processor, can implement the steps of the investment risk analysis method based on fund user portrait analysis described in the first aspect above.

[0015] The present invention provides an investment risk analysis method and system based on fund user portrait analysis, which obtains invested enterprises from the user investment database, analyzes user investment preferences, and generates investment volatility data based on the user's investment amount and income information. Through the LLM large language model, the data such as the company's disclosed financial statements are analyzed, and AI deep learning is performed in combination with information such as the company, industry, policy, investment preference, and investment volatility. All information is integrated to generate investment advice and risk information, which can better perform logical calculations based on the company's basic information, the industry's prosperity, and the support of relevant policies, and give investment advice on whether to invest, investment scale, investment cycle, etc. to the company, so as to better assist relevant fund managers in making investment decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flowchart of the investment risk analysis method based on fund user portrait analysis provided by the present invention; Figure 2 Schematic diagram of an investment risk analysis system based on fund user profile analysis according to an embodiment of the present invention; Figure 3 Schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0018] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0019] When fund managers make fund investments and decisions, they hope to get more support. By providing auxiliary decision-making information such as the basic information of the invested enterprises, the industries they belong to, regional policies, and the current investment preferences of fund managers, they can better help fund managers analyze whether the enterprises are worth investing in, the investment cycle, and the return. At present, when making investment decisions, fund managers use network crawling technology to obtain the basic information of relevant enterprises, the industries they belong to, and regional policies, and conduct data mining based on the user's investment preferences. The collected data is summarized and concluded through classification algorithms and regression algorithms to draw conclusions for auxiliary decision-making. Existing data mining technology mainly classifies and summarizes data, and cannot intelligently analyze based on existing data. The auxiliary decisions given are relatively rigid, and it is impossible to analyze and predict future trends based on historical data.

[0020] The present invention aims to solve the problem of investment risk analysis for fund users. The problem of investment risk analysis for fund users is solved by the following steps: based on the user's historical investment data, the user's investment preference data and investment volatility data are determined. The investment preference data and investment volatility data can reflect the user's investment habits and risk tolerance. Based on the investment preference data and investment volatility data, multiple project entities are matched and the operating information of these project entities is obtained. The operating information includes the basic information, operating dynamics information and financial report information of the enterprise. Based on the acquired operating information, a dynamic portrait of the project entity is generated. The dynamic portrait can comprehensively reflect the operating status and development potential of the project entity. Based on the dynamic portrait of the project entity, investment advice and risk information are determined to provide users with personalized investment advice and risk assessment. Through the above steps, the technical solution can intelligently generate investment advice and risk information based on the user's historical investment data and the operating information of the project entity, so as to help users make better investment decisions. The following will be explained and introduced through multiple embodiments.

[0021] Figure 1 This is a schematic diagram of an investment risk analysis method based on fund user profile analysis provided by the present invention. Figure 1 As shown, including: S1. Determine the user's investment preference data and investment volatility data based on the user's historical investment data; S2. Obtain multiple project entities based on the matching of the investment preference data and the investment volatility data, obtain the operating information of the project entities, generate dynamic portraits of the project entities based on the operating information, and determine investment recommendations and risk information based on the dynamic portraits of the project entities.

[0022] It should be noted that the project entities include fund parties (fund managers, fund custodians, fund unit holders), fund market service agencies (fund sales agencies, fund registration and filing agencies, law firms and accounting firms, etc.) and industry regulatory self-regulatory organizations (fund regulatory agencies, fund self-regulatory agencies, etc.).

[0023] Compared with the existing technology, this application generates personalized investment advice and risk assessment by intelligently analyzing the user's historical investment data and the project subject's operating information, overcoming the limitations of the existing technology of rigid decision-making assistance and the inability to analyze and predict future trends based on historical data. By introducing large language models and data type conversion technology, this application can more accurately analyze and assess investment risks and help fund managers make better investment decisions.

[0024] In the process of solving the problem of investment risk analysis for fund users, this application plays an important role through the following steps: First, by analyzing the user's historical investment data, the user's investment preference data and investment volatility data are determined to reflect the user's investment habits and risk tolerance. Then, based on these data, multiple project entities are matched and the operating information of these project entities is obtained. Based on the acquired operating information, a dynamic portrait of the project entity is generated to fully reflect the operating conditions and development potential of the project entity. Finally, based on the dynamic portrait of the project entity, investment advice and risk information are determined to provide users with personalized investment advice and risk assessment. Through these steps, this application can intelligently generate investment advice and risk information to help users make better investment decisions.

[0025] On the basis of the above embodiments, as a preferred implementation mode, the business information includes basic enterprise information, business dynamics information and financial report information. The basic enterprise information includes registered address, registered capital, establishment time, business scope, enterprise team, shareholders and shareholding ratio; the business dynamics information includes policy support information, market activity information, sales data, customer satisfaction, cooperation network, market layout and major events.

[0026] Basic information of an enterprise is used to assess the basic status and stability of the enterprise, including registered address, registered capital, establishment time, business scope, enterprise team, shareholders and shareholding ratio, etc. This information can be obtained from channels such as enterprise industrial and commercial registration information and public information. For example, registered capital can reflect the scale and strength of an enterprise, and shareholders and shareholding ratio can reflect the control structure and stability of an enterprise.

[0027] Establishment Date: The specific date when the company was established helps to understand the company's history and development stage.

[0028] Business scope: The main business or industry field in which the enterprise is engaged, reflecting the enterprise's market positioning and development direction.

[0029] Marketing activities: Activities such as marketing promotion, brand publicity, product launch, etc. in which an enterprise participates, which reflect the enterprise's market strategy and brand influence.

[0030] Sales data: a company’s sales revenue, sales volume, sales channels, etc., which reflect the company’s market share and sales performance.

[0031] Customer satisfaction: Customer satisfaction evaluation of a company's products or services reflects the company's service quality and customer satisfaction.

[0032] Partners: An enterprise’s partners, suppliers, distributors, etc., reflecting the enterprise’s supply chain and cooperation network.

[0033] Market layout: The company's layout and strategy in different regions or markets reflects the company's market expansion and degree of internationalization.

[0034] Major events: Major events that occur in an enterprise, such as mergers and acquisitions, reorganizations, and listings, reflect the enterprise's strategic adjustments and development direction.

[0035] Business dynamics information is used to evaluate the market performance and dynamic changes of enterprises, including policy support information, market activity information, sales data, customer satisfaction, cooperation network, market layout and major events. This information can be obtained from public news reports, industry reports, corporate official websites and other channels. For example, sales data can reflect the market competitiveness and profitability of enterprises, and customer satisfaction can reflect the brand image and service quality of enterprises.

[0036] Financial reporting information is used to assess the financial health of a company, including balance sheets, income statements, and cash flow statements. This information can be obtained from the company's public financial statements or professional databases. For example, the income statement can reflect the profitability of the company, and the cash flow statement can reflect the company's cash flow status.

[0037] Balance sheet: reflects the financial status of a company on a specific date, including assets, liabilities and owners' equity.

[0038] Cash flow statement: reflects the cash inflow and outflow of an enterprise over a certain period of time, including operating activities, investment activities and financing activities.

[0039] Financial analysis: In-depth analysis of the company's financial status, including profitability analysis, debt repayment ability analysis, operational efficiency analysis, etc.

[0040] Financial indicators: such as gross profit margin, net profit margin, debt-to-asset ratio, current ratio, etc., are used to evaluate the financial status and operating performance of an enterprise.

[0041] Through the comprehensive analysis of the above three types of information, a comprehensive corporate portrait can be constructed, thereby assisting fund users in making more accurate investment decisions. This method can use a variety of data analysis techniques, such as data mining and machine learning, to process and analyze the collected data, extract key information, and generate corresponding investment recommendations and risk assessment reports.

[0042] In this application, the acquisition and analysis of business information can be achieved by a variety of technical means. For example, web crawler technology can be used to automatically capture public corporate information; third-party data service providers can be cooperated to obtain more comprehensive and accurate data; natural language processing technology can also be used to analyze unstructured data (such as news reports, market analysis reports) to extract key information. In addition, historical data can be analyzed in combination with machine learning algorithms to predict future market trends and corporate development prospects.

[0043] As a preferred implementation, the present application can use a pre-trained large language model (LLM) to perform text analysis on the collected business information to extract key features, such as investment status, market competitiveness, financial status, technological innovation capabilities, risk status, and growth potential. These key features can be converted into numerical data, such as word vectors, TF-IDF, and distributed vectors, and input into a pre-trained investment risk analysis model to determine the investment potential score and risk level. The training data of the model can come from historical investment cases and market data. The output results of the model can provide fund users with more accurate investment advice and help them better assess investment risks.

[0044] This application can more effectively assist fund users in making investment decisions through a comprehensive analysis of corporate operating information. Compared with the existing technology that only simply classifies and summarizes data, this application can more deeply analyze the business conditions of enterprises and predict future development trends, thereby providing more accurate and reliable investment advice, reducing investment risks and increasing investment returns.

[0045] Based on the above embodiment, as a preferred implementation mode, determining the user's investment preference data and investment volatility data based on the user's historical investment data specifically includes: Obtaining the user's historical investment data based on at least one of the following methods: investment platform data interface, cooperation with third-party data service providers, data crawlers, data mining, and user self-upload; the historical investment data includes transaction time, transaction type, transaction amount, and profit and loss situation; Clean the historical investment data to remove duplicate, erroneous and invalid data; and standardize the cleaned data; Cluster analysis is performed on the historical investment data to determine the user's investment preference data and investment volatility data, wherein the investment preference data includes investment areas, investment types, investment cycles and return expectations; the investment volatility data includes position changes, transaction frequency, risk tolerance index, and return volatility index.

[0046] The user's historical investment data is obtained through various means, and the data is cleaned and standardized to ensure the accuracy and consistency of the data. Then, the user's investment preference data and investment volatility data are extracted through cluster analysis technology. The investment preference data includes the areas, types, cycles and expected returns that the user tends to invest in, which helps to understand the user's investment habits and expectations. The investment volatility data includes changes in user positions, transaction frequency, risk tolerance and return fluctuations, which helps to assess the user's risk tolerance and the stability of investment behavior. Through the synergy of these technical features, useful investment preference and investment volatility data can be extracted from the user's historical investment data, providing a basis for subsequent investment risk analysis.

[0047] Furthermore, the determination of the user's investment preference data and investment volatility data based on the user's historical investment data can be achieved in the following ways: first, the user's transaction data is obtained through the investment platform data interface to ensure the real-time and accuracy of the data; second, cooperate with third-party data service providers to obtain the user's investment data on different platforms to ensure the comprehensiveness of the data; third, use data crawler technology to crawl the user's investment data from public investment information to supplement the data source; finally, the user can also upload his historical investment data on his own to ensure the diversity of the data. The acquired historical investment data is cleaned to remove duplicate, erroneous and invalid data, and the cleaned data is standardized to ensure the consistency and comparability of the data. The cleaned and standardized data is analyzed through cluster analysis technology to determine the user's investment preference data and investment volatility data. Among them, the investment preference data includes the field, type, cycle and expected return that the user prefers to invest in; the investment volatility data includes the changes in the user's position, transaction frequency, risk tolerance and return volatility.

[0048] This embodiment ensures the comprehensiveness and accuracy of the user's historical investment data through a variety of data acquisition methods. Through data cleaning and standardization processing, the consistency and comparability of the data are guaranteed. Using cluster analysis technology, the user's investment preferences and investment volatility data can be effectively extracted, providing a reliable data basis for investment risk analysis. Compared with the prior art, this embodiment can more comprehensively and accurately analyze the user's investment behavior and risk tolerance, and provide more accurate investment risk analysis results.

[0049] Based on the above embodiment, as a preferred implementation mode, generating a dynamic portrait of the project subject based on the business information specifically includes: Based on the pre-trained large language model (LLM) model, text analysis is performed on the business information to identify key features in advance, and a dynamic portrait of the project entity is generated based on the key features. The key features include investment status sub-features, market positioning and competition sub-features, financial sub-features, technological innovation sub-features, risk sub-features, growth potential sub-features and investor relations sub-features.

[0050] Use pre-trained large language models to perform text analysis on business information to extract key features such as investment status, market positioning and competition, finance, technological innovation, risk, growth potential, and investor relations. The extraction and analysis of these features can fully reflect the dynamic situation and potential risks of the project subject. By using large language models to analyze business information, it is possible to automatically extract and process large amounts of complex text data to generate a detailed dynamic portrait of the project subject. This method can improve the accuracy and efficiency of analysis and provide stronger support for investment decisions.

[0051] Furthermore, the text analysis of the business information is performed based on the pre-trained large language model (LLM) model to extract key features. Specifically, the investment status sub-feature includes the current investment stage and financing history of the enterprise. The investment stage includes the start-up stage, growth stage, and mature stage. The financing history includes the number of financings, the amount of financing, and the background of investors; the market positioning and competition sub-features include market positioning, market size and potential, and competitive landscape. Market positioning includes the position of the enterprise in the market, including target customer groups and market segments; market size and potential include the size, growth rate, and potential market opportunities of the market where the enterprise is located; the competitive landscape includes the market competition situation of the enterprise, including major competitors and market share distribution; financial sub-features include financial statements, return on investment, and valuation pricing. Financial statements include revenue, profit, and cash flow; valuation pricing includes the market valuation, price-earnings ratio, and price-to-book ratio of the enterprise; technological innovation sub-features include core technology indicators, innovation results, and R&D team size; risk sub-features include market risk indicators, financial risk indicators, and legal and compliance risk indicators; growth potential sub-features include growth potential indicators, strategic planning indicators, and expansion plan indicators; investor relations sub-features include shareholder structure, shareholding ratio, and information disclosure status.

[0052] Through the above methods, this application can use a pre-trained large-scale language model to conduct a more comprehensive and in-depth analysis of business information on the basis of existing technologies, thereby generating a more accurate and detailed dynamic portrait of the project subject. Compared with the existing technology, this application can automatically extract and process a large amount of complex text data, improve the accuracy and efficiency of analysis, and provide stronger support for investment decisions. Therefore, this application has significant advantages and innovations in solving the technical problem of generating dynamic portraits of project subjects based on business information.

[0053] Based on the above embodiment, as a preferred implementation mode, the investment status sub-feature includes the current investment stage and financing history of the enterprise, the investment stage includes the start-up stage, the growth stage, and the mature stage, and the financing history includes the number of financings, the financing amount, and the investor background; The market positioning and competition sub-characteristics include market positioning, market size and potential, and competition landscape; the market positioning includes the position of the enterprise in the market, including target customer groups and market segments; the market size and potential include the size, growth rate and potential market opportunities of the market in which the enterprise is located; the competition landscape includes the market competition situation of the enterprise, including major competitors and market share distribution; The financial sub-characteristics include financial statements, return on investment and valuation pricing; the financial statements include revenue, profit and cash flow; the valuation pricing includes the market valuation, price-earnings ratio and price-to-book ratio of the enterprise; The technological innovation sub-characteristics include core technological indicators, innovation achievements, and R&D team size; Risk sub-characteristics include market risk indicators, financial risk indicators, and legal and compliance risk indicators; The growth potential sub-characteristics include growth potential indicators, strategic planning indicators, and expansion plan indicators; The investor relations sub-characteristics include shareholder structure, shareholding ratio, and information disclosure status.

[0054] The investment status sub-feature helps evaluate the growth potential and financing ability of an enterprise by analyzing the investment stage and financing history of the enterprise. The market positioning and competition sub-feature helps evaluate the market opportunities and competitiveness of an enterprise by analyzing the market position, market size and potential, and competitive landscape of the enterprise. The financial sub-feature helps evaluate the financial health and investment value of an enterprise by analyzing the financial statements, return on investment, and valuation pricing of the enterprise. The technological innovation sub-feature helps evaluate the technological innovation capability of an enterprise by analyzing the core technical indicators, innovative achievements, and R&D team size of the enterprise. The risk sub-feature helps evaluate the risk status of an enterprise by analyzing market risks, financial risks, and legal and compliance risks. The growth potential sub-feature helps evaluate the future growth potential of an enterprise by analyzing growth potential indicators, strategic planning indicators, and expansion plan indicators. The investor relations sub-feature helps evaluate the shareholder relations and corporate governance level of an enterprise by analyzing the shareholder structure, shareholding ratio, and information disclosure status. Through the mutual cooperation of these technical features, the dynamic portrait of the project subject can be comprehensively analyzed, thereby solving the technical problem of analyzing investment risks and investment potential through the dynamic portrait of the project subject.

[0055] Specifically, the implementation of the investment status sub-feature may include determining the investment stage of the enterprise by collecting the financing history data of the enterprise, analyzing the number of financings, the amount of financing and the background of investors. The implementation of the market positioning and competition sub-feature may include determining the position of the enterprise in the market, the market size and potential and the competitive landscape through market research and data analysis. The implementation of the financial sub-feature may include evaluating the financial health of the enterprise by analyzing the financial statements of the enterprise, calculating the return on investment and valuation pricing. The implementation of the technological innovation sub-feature may include determining the technological innovation capability of the enterprise by evaluating the core technical indicators, innovative achievements and R&D team size of the enterprise. The implementation of the risk sub-feature may include evaluating the risk status of the enterprise by analyzing market risks, financial risks and legal and compliance risks. The implementation of the growth potential sub-feature may include determining the future growth potential of the enterprise by analyzing the growth potential indicators, strategic planning indicators and expansion plan indicators of the enterprise. The implementation of the investor relations sub-feature may include evaluating the shareholder relations and corporate governance level of the enterprise by analyzing the shareholder structure, shareholding ratio and information disclosure status.

[0056] Therefore, this application achieves a comprehensive evaluation of the dynamic portrait of the project subject through a comprehensive analysis of multiple sub-features, and solves the technical problem of analyzing investment risks and investment potential through the dynamic portrait of the project subject. Compared with the existing technology, this application can more comprehensively and accurately evaluate the investment value and risk status of the enterprise, and improve the scientificity and accuracy of investment decisions.

[0057] Based on the above embodiment, as a preferred implementation mode, determining investment advice and risk information based on the dynamic portrait of the project subject includes: Performing data type conversion on key features of the project subject dynamic portrait, converting text data into numerical data, wherein the numerical data includes word vectors, TF-IDF and distributed vectors; The converted data is standardized or normalized to extract key information, which is then input into a pre-trained investment risk analysis model to determine the investment potential score and risk level.

[0058] Data type conversion converts text data into numerical data so that the data can be processed by the model; standardization or normalization ensures data consistency; key information is extracted to obtain information that is crucial to investment risk analysis; and pre-trained investment risk analysis models are used to ultimately determine the investment potential score and risk level.

[0059] Data type conversion is the process of converting text data into numerical data, which includes word vectors, TF-IDF, and distributed vectors. Word vectors map words in the text to a high-dimensional space for calculation and analysis; TF-IDF is a statistical method used to evaluate the importance of a word in a document; distributed vectors use deep learning technology to convert text data into numerical data with semantic information. Standardization or normalization is to eliminate differences in the data so that the data can be compared and analyzed on the same scale. Extracting key information is to extract information that is crucial to investment risk analysis from the standardized or normalized data, which will be input as input data into the pre-trained investment risk analysis model.

[0060] Therefore, this application can more accurately determine the investment potential score and risk level by converting, standardizing or normalizing the key features of the project subject dynamic portrait, and extracting key information and inputting it into a pre-trained investment risk analysis model. Compared with the prior art, the method of this application can more intelligently analyze and predict investment risks and provide more accurate and flexible auxiliary decision support.

[0061] Based on the above embodiment, as a preferred implementation, the extracting key information includes: The key information includes statistical feature information, text feature information, image feature information and time series feature information.

[0062] By extracting various types of feature information, the dynamic image of the project subject can be fully reflected, so as to conduct investment risk analysis more accurately. Through these technical means, the problem of extracting key information for investment risk analysis can be better solved.

[0063] Among them, statistical feature information can include the company's financial data, market data, etc. Through statistical analysis of these data, key information such as the company's financial health and market performance can be obtained. Text feature information can be used to extract valuable information such as the company's strategic planning and market positioning from the company's public reports, news reports and other text data through natural language processing technology. Image feature information can be used to extract information such as the company's production capacity and technical level from the company's promotional pictures, production workshop photos and other image data through image recognition technology. Time series feature information can be used to extract information such as the company's growth trajectory and development trends from the company's historical data through time series analysis.

[0064] Therefore, this application can fully and accurately reflect the dynamic portrait of the project subject by extracting a variety of feature information. Compared with the existing technology, this comprehensive analysis method can better capture the various characteristics of the enterprise, thereby providing more powerful support in investment risk analysis. Through these technical means, this application can effectively solve the problems of rigid auxiliary decision-making and inability to intelligently analyze and predict future trends in the existing technology, and improve the accuracy and scientificity of investment decisions.

[0065] The present invention provides an investment risk analysis system based on fund user portrait analysis, based on the investment risk analysis method based on fund user portrait analysis described in the above embodiment, such as Figure 2 As shown in, including: A user analysis module 210, which determines the user's investment preference data and investment fluctuation data based on the user's historical investment data; The enterprise analysis module 220 obtains multiple project entities based on the matching of the investment preference data and the investment volatility data, acquires the operating information of the project entities, generates a dynamic portrait of the project entity based on the operating information, and determines investment recommendations and risk information based on the dynamic portrait of the project entity.

[0066] It should be noted that the investment risk analysis system based on fund user portrait analysis provided by the present invention can perform the investment risk analysis based on fund user portrait analysis described in any of the above embodiments during specific operation, which will not be elaborated in this embodiment.

[0067] Figure 3is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 3 As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330 and a communication bus 330, wherein the processor 310, the communications interface 320 and the memory 330 communicate with each other through the communication bus 330. The processor 310 may call the logic instructions in the memory 330 to execute the investment risk analysis method based on fund user profile analysis, the method comprising: Determine the user's investment preference data and investment volatility data based on the user's historical investment data; Based on the matching of the investment preference data and the investment volatility data, multiple project entities are obtained, the operating information of the project entities is acquired, a dynamic portrait of the project entity is generated based on the operating information, and investment advice and risk information are determined based on the dynamic portrait of the project entity.

[0068] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0069] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, and when the program instructions are executed by a computer, the computer can execute the investment risk analysis method based on fund user profile analysis provided in the above embodiments, the method comprising: Determine the user's investment preference data and investment volatility data based on the user's historical investment data; Based on the matching of the investment preference data and the investment volatility data, multiple project entities are obtained, the operating information of the project entities is acquired, a dynamic portrait of the project entity is generated based on the operating information, and investment advice and risk information are determined based on the dynamic portrait of the project entity.

[0070] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform the investment risk analysis method based on fund user profile analysis provided in the above embodiments, the method comprising: Determine the user's investment preference data and investment volatility data based on the user's historical investment data; Based on the matching of the investment preference data and the investment volatility data, multiple project entities are obtained, the operating information of the project entities is acquired, a dynamic portrait of the project entity is generated based on the operating information, and investment advice and risk information are determined based on the dynamic portrait of the project entity.

[0071] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0072] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0073] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An investment risk analysis method based on fund user profile analysis, characterized in that: include: Determine the user's investment preference data and investment volatility data based on the user's historical investment data; Based on the matching of the investment preference data and the investment volatility data, multiple project entities are obtained, the operating information of the project entities is acquired, a dynamic portrait of the project entity is generated based on the operating information, and investment advice and risk information are determined based on the dynamic portrait of the project entity.

2. The investment risk analysis method based on fund user profile analysis according to claim 1 is characterized in that: The business information includes basic enterprise information, business dynamics information and financial report information. The basic enterprise information includes registered address, registered capital, establishment time, business scope, corporate team, shareholders and shareholding ratio; the business dynamics information includes policy support information, market activity information, sales data, customer satisfaction, cooperation network, market layout and major events.

3. The investment risk analysis method based on fund user profile analysis according to claim 1 is characterized in that: The determining of the user's investment preference data and investment volatility data based on the user's historical investment data specifically includes: Obtaining the user's historical investment data based on at least one of the following methods: investment platform data interface, cooperation with third-party data service providers, data crawlers, data mining, and user self-upload; the historical investment data includes transaction time, transaction type, transaction amount, and profit and loss situation; Clean the historical investment data to remove duplicate, erroneous and invalid data; and standardize the cleaned data; Cluster analysis is performed on the historical investment data to determine the user's investment preference data and investment volatility data, wherein the investment preference data includes investment areas, investment types, investment cycles and return expectations; the investment volatility data includes position changes, transaction frequency, risk tolerance index, and return volatility index.

4. The investment risk analysis method based on fund user profile analysis according to claim 1 is characterized in that: Generate a dynamic portrait of the project subject based on the business information, specifically including: Based on the pre-trained large language model (LLM) model, text analysis is performed on the business information to identify key features in advance, and a dynamic portrait of the project entity is generated based on the key features. The key features include investment status sub-features, market positioning and competition sub-features, financial sub-features, technological innovation sub-features, risk sub-features, growth potential sub-features and investor relations sub-features.

5. The investment risk analysis method based on fund user profile analysis according to claim 4 is characterized in that: The investment status sub-characteristic includes the current investment stage and financing history of the enterprise, the investment stage includes the start-up stage, growth stage, and mature stage, and the financing history includes the number of financings, the financing amount, and the investor background; The market positioning and competition sub-characteristics include market positioning, market size and potential, and competition landscape; the market positioning includes the position of the enterprise in the market, including target customer groups and market segments; the market size and potential include the size, growth rate and potential market opportunities of the market in which the enterprise is located; the competition landscape includes the market competition situation of the enterprise, including major competitors and market share distribution; The financial sub-characteristics include financial statements, return on investment and valuation pricing; the financial statements include revenue, profit and cash flow; the valuation pricing includes the market valuation, price-earnings ratio and price-to-book ratio of the enterprise; The technological innovation sub-characteristics include core technological indicators, innovation achievements, and R&D team size; Risk sub-characteristics include market risk indicators, financial risk indicators, and legal and compliance risk indicators; The growth potential sub-characteristics include growth potential indicators, strategic planning indicators, and expansion plan indicators; The investor relations sub-characteristics include shareholder structure, shareholding ratio, and information disclosure status.

6. The investment risk analysis method based on fund user profile analysis according to claim 5 is characterized in that: Determine investment advice and risk information based on the dynamic profile of the project subject, including: Performing data type conversion on key features of the project subject dynamic portrait, converting text data into numerical data, wherein the numerical data includes word vectors, TF-IDF and distributed vectors; The converted data is standardized or normalized to extract key information, which is then input into a pre-trained investment risk analysis model to determine the investment potential score and risk level.

7. The investment risk analysis method based on fund user profile analysis according to claim 6 is characterized in that: The extracting of key information includes: The key information includes statistical feature information, text feature information, image feature information and time series feature information.

8. An investment risk analysis system based on fund user profile analysis, characterized in that: include: A user analysis module, which determines the user's investment preference data and investment fluctuation data based on the user's historical investment data; The enterprise analysis module obtains multiple project entities based on the matching of the investment preference data and the investment volatility data, obtains the operating information of the project entities, generates a dynamic portrait of the project entity based on the operating information, and determines investment recommendations and risk information based on the dynamic portrait of the project entity.

9. An electronic device, It is characterized in that comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the investment risk analysis method based on fund user portrait analysis as described in any one of claims 1 to 7 above.

10. A computer-readable storage medium, characterized in that: Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the investment risk analysis method based on fund user portrait analysis as described in any one of claims 1 to 7 above.

Images