Financial transaction analogue simulation method and system based on VR

Abstract

The invention discloses a financial transaction simulation method and system based on VR, and relates to the technical field of financial transaction simulation. A financial transaction simulation system based on VR comprises a virtual transaction environment module, a data acquisition and processing module, a market analysis and transaction suggestion module, a physiological feedback monitoring and psychological regulation module, a multi-dimensional market data visualization module, a social transaction and collaborative decision module and a dynamic market situation simulation and transaction strategy optimization module. The virtual trader is combined with the artificial intelligence technology, personalized market analysis reports and transaction suggestions are provided for the user, the suggestions are dynamically adjusted according to historical transaction data, risk preferences and real-time market changes of the user, and personalized support and real-time reaction capacity are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of financial transaction simulation, and in particular to a VR-based financial transaction simulation method and system. Background Art

[0002] With the increasing complexity of financial markets and the development of high-frequency trading, investors have put forward higher requirements for the optimization of trading strategies, the analysis of market data, and the management of trading psychology. Financial trading simulation systems play a key role in the training of traders, the testing and optimization of trading strategies. At present, financial trading simulation mainly relies on traditional two-dimensional interfaces, such as computer software and mobile applications. These systems usually provide historical data backtesting, simulated trading execution, and basic market analysis functions. However, traditional trading simulation systems have many limitations in terms of traders' immersion, interactivity, real-time and intelligence, making it difficult to comprehensively improve traders' market adaptability and trading decision-making level.

[0003] In recent years, the rapid development of virtual reality (VR) technology has provided new possibilities for financial trading simulation. VR technology can build a highly immersive virtual trading environment, allowing traders to perceive market dynamics in a more intuitive and interactive way. However, the current application of VR in the field of financial trading is still in its infancy, mainly focusing on the visualization of market data, and lacks solutions that are deeply integrated with trading strategies, market analysis, psychological adjustment, social trading, etc. Therefore, how to deeply combine VR technology with financial trading simulation and improve its intelligence, interactivity and practicality has become an important research direction in this field.

[0004] Although the existing financial trading simulation system can help traders practice trading and optimize strategies to a certain extent, it still has the following shortcomings: lack of immersive trading experience, single testing and optimization methods for trading strategies, insufficient intelligence level of market analysis, ignoring traders' psychological factors, limited market data visualization methods, insufficient social and collaborative trading capabilities, low adaptability of market scenario simulation, and delayed feedback on trading strategy optimization. Summary of the invention

[0005] A VR-based financial transaction simulation method comprises the following steps: Step S1, the user enters the virtual trading environment: the user wears a VR device and enters the virtual trading environment through gesture control or voice interaction, selects a trading product and sets a trading strategy; Step S2, generating personalized trading suggestions: Based on the user's historical trading data, risk preferences and market analysis reports, the virtual trader provides personalized trading suggestions through artificial intelligence analysis, and interacts with the user in real time to provide market analysis, strategy optimization suggestions and risk assessment; Step S3, physiological feedback monitoring and psychological adjustment: real-time collection of the user's physiological parameters, analysis of the user's emotional state, and automatic adjustment of the virtual environment or provision of psychological intervention suggestions when negative emotions are detected; the negative emotions are initially set to anxiety and tension, and the adjustment of the virtual environment includes sound effects, light and market fluctuation speed; Step S4, multi-dimensional market data visualization: based on multi-dimensional data, three-dimensional visualization technology is used to present market trends in a virtual environment, supporting users to conduct data analysis and market insights in an interactive manner; the multi-dimensional data includes market depth, capital flow and transaction volume; Step S5, socialized trading and collaborative decision-making: users communicate with other traders in real time in a virtual environment, share trading strategies, discuss market sentiment, and conduct collaborative trading simulations to optimize personal trading strategies through group decision-making; Step S6, dynamic market scenario simulation: Generate dynamic and adaptive market scenarios based on real-time market data and external events to simulate dynamic market changes and provide feedback and optimization suggestions for user response strategies; Step S7, trading strategy optimization and feedback: Users adjust trading strategies based on real-time feedback in the virtual environment and test the optimization in simulation. The system provides instant evaluation and improvement suggestions based on user operations to improve the effectiveness and stability of the strategy.

[0006] As a preferred technical solution of the present invention, the virtual trader includes the following functions: Market analysis function: analyze market trends, technical indicators and related economic factors, and generate real-time market analysis reports; Trading suggestion function: Provide personalized trading suggestions and trading execution strategies based on the user's historical trading data, risk preferences and market analysis reports; the trading execution strategies include entry timing, exit timing, stop loss and take profit strategies; adjust trading suggestions in real time according to the user's trading behavior, and update the trading execution strategy; adjust the risk preference for the user based on the evaluation and feedback records of the trading execution strategy; The market analysis function and trading suggestion function of the virtual trader are realized by a market analysis model, which uses artificial intelligence technology to process and analyze data to generate real-time market analysis reports, trading suggestions and trading execution strategies.

[0007] As a preferred technical solution of the present invention, the structure of the market analysis model includes: Data input layer: receiving market data, user transaction history data and risk preference data; Data preprocessing layer: Format, denoise, and standardize the input data, and perform feature extraction and quantitative analysis on the unstructured data in the input data; the denoising process uses the wavelet transform method, the standardization process uses the Z-score standardization method, and the quantitative analysis uses a self-trained natural language processing model for emotion recognition and scoring; Feature extraction layer: Extract key features from market data based on principal component analysis and long short-term memory network, including trend features, momentum features, volatility features, trading volume features, and capital flow features, and extract behavioral features and risk preference features from user transaction history data; Market analysis layer: Based on convolutional neural networks, it conducts in-depth analysis of market trends, technical indicators and external economic factors to generate market analysis reports; Trading suggestion generation layer: Based on deep reinforcement learning combined with decision trees, market analysis reports and user trading behavior characteristics are calculated to generate personalized trading suggestions and trading execution strategies, including entry timing, exit timing, stop loss and take profit strategies; Strategy optimization layer: Use genetic algorithms to optimize and adjust trading execution strategies, and based on reinforcement learning algorithms combined with historical trading performance, adjust the execution results and feedback of trading strategies to optimize trading suggestions and risk control parameters; Interactive feedback layer: Provides the generated market analysis reports, trading suggestions and optimization results to virtual traders, and interacts with users through natural language processing models to provide real-time trading analysis, decision-making suggestions and strategy optimization guidance.

[0008] As a preferred technical solution of the present invention, the training of the market analysis model includes the following steps: Data collection and preprocessing: Collecting market data , user transaction history data and risk appetite data , get the training data set , and split the training data set into training set, test set and validation set according to the set ratio; Format the market data and use wavelet transform to denoise it: ,in represents the wavelet transform function; The formatted market data is standardized using Z-score standardization: ,in μ represents the mean of market data, is the standard deviation of the market data; Extract sentiment scores using natural language processing models on unstructured data: ,in represents a natural language model, For unstructured data; Feature extraction and dimensionality reduction: Extracting features of market data using principal component analysis , using long short-term memory networks to extract features from transaction history data , combined with market characteristics , User transaction characteristics and risk appetite Form the final input feature matrix: ; Market analysis layer training: Use convolutional neural network to extract market trend features, and train the market analysis layer by minimizing the loss function: ,in The actual market trend data is obtained through real-time collection. The output predicted by the convolutional neural network; Trading suggestion generation layer training: Deep reinforcement learning combined with decision trees is used to generate trading suggestions, and the reward function is defined as: ,in is the current price of the trading asset, is the price at the previous time step, For transaction costs; Using Q-learning for reinforcement learning update: ,in Indicates the cumulative reward value, Indicates the current state. Indicates taking action, Indicates the expected cumulative reward value after taking a certain action in the current state; represents the learning rate, Indicates execution of an action The immediate reward after Represents the discount factor, which is used to control the weight of subsequent reward values; Indicates that in the next state Next, all actions The maximum reward value in is used to predict the maximum reward in the next state; Strategy optimization layer training: Use genetic algorithms to optimize trading execution strategies, define fitness functions, and iteratively optimize trading strategies through selection, crossover, and mutation operations; Model evaluation and adjustment: Using mean square error to evaluate market analysis models: ,in n Indicates the total number of output targets of the model, Indicates i training goals, Indicates i The model predicts the results; Cumulative rate of return Evaluating trading strategies: ,in is the return rate for each time step, t represents the current time step, T represents the total number of time steps; After the training is completed, the market analysis model is used for market analysis and trading suggestion generation.

[0009] As a preferred technical solution of the present invention, the physiological feedback monitoring and psychological adjustment include: Physiological data collection: The physiological parameters of the user are collected in real time through physiological sensing equipment, including heart rate, heart rate variability, skin electrical activity and brain waves. The collected physiological parameters are expressed as: ,in tp represents the time step of collecting physiological parameters, Indicates heart rate, represents the heart rate variability, Indicates skin electrical activity, Indicates brain waves; Physiological data preprocessing: Use a bandpass filter to remove artifact noise in the EEG signal, smooth the heart rate signal, and calculate the short-term mean; Emotional state recognition: Using the support vector machine classification model, the user's emotional state is recognized based on preprocessed physiological data, including four categories: anxiety, tension, calmness, and pleasure; Mental state adjustment: automatically adjust the virtual environment when it detects that the user is in an anxious or nervous state, including sound effect adjustment, visual environment adjustment and guiding feedback; User feedback and adaptive optimization: record the user's emotional changes and trading performance, associate the user's physiological feedback data with the trading results, and build an adaptive psychological adjustment matrix. The psychological adjustment matrix uses regression analysis to establish the relationship between physiological signals and trading performance, and continuously optimizes the psychological adjustment strategy; Psychological intervention suggestions: When the system detects that the user is anxious or nervous during multiple consecutive trading cycles, it provides proactive intervention.

[0010] As a preferred technical solution of the present invention, the multi-dimensional market data visualization includes the following contents: Market Depth Visualization: Displays the market depth in a three-dimensional graphic in a virtual environment, including the number of buy and sell orders at different prices; Visualization of capital flow: Use dynamic flow charts to display capital flows, including the inflow and outflow of large amounts of capital; Trading volume visualization: Display the changes in trading volume in different time periods through bar charts, heat maps or 3D surface charts; Market trend visualization: Combined with the immersive environment of VR, K-line charts, moving averages, and trend lines are used to display market trends, and users are supported to call up different technical indicators for analysis through gesture interaction or voice commands; Real-time data interaction: Provides interactive data query function. Users can select specific market areas or trading products through gestures or voice input. The system will instantly display relevant data and support comparative analysis of multi-dimensional data. Visualization of market hotspots: highlighting active market trading areas in a three-dimensional market environment, and using colors or dynamic effects to identify market areas where funds are currently flowing in or out. Multi-market comparative analysis: supports displaying the market depth, trends and trading status of multiple markets in a virtual environment at the same time; Personalized data layout: Users can customize the visualization interface, adjust the display mode, color, and transparency of different market data, and set a personalized market analysis perspective.

[0011] As a preferred technical solution of the present invention, the socialized transaction and collaborative decision-making includes the following contents: Multi-person virtual trading space: provides a virtual trading environment that supports multiple users online at the same time, in which users can interact with other traders in real time, including market analysis discussions, trading strategy sharing and collaborative trading execution; Real-time voice and text communication: integrated voice communication and text chat functions, users can discuss the market with other traders through voice commands or text input, and support automatic voice-to-text function; Trading strategy sharing and analysis: Support sharing of personal trading strategies between users, backtesting and visualization of shared strategies, and support for users to test other people's strategies in a virtual trading environment; Collaborative trading mode: provides team trading functions, supports users to form trading teams, make collective decisions in a virtual environment, negotiate trading plans, assign different roles, and jointly execute trading strategies; Market sentiment and consensus analysis: The system analyzes market sentiment and generates a market sentiment index based on the discussion content and trading behavior of user groups; Social rankings and reputation system: Establish a social reputation system for traders, provide reputation scores for traders based on factors such as user trading performance, market analysis content contributed, and effectiveness of strategy sharing, and promote the influence of high-quality traders; Virtual Tutor and Learning Mode: Support experienced traders to create virtual classrooms or live trading, accept other users to participate in learning and interaction, and follow the tutor to perform simulated trading in the simulation trading mode; Trading competition and challenge mechanism: Provide trading competition function, support users to participate in trading challenges organized by the system or community, simulate the real market environment, optimize trading strategies in the competition, and obtain feedback and improvement suggestions through competition results; Social network integration: Support users to share trading records, market analysis and trading ideas to virtual trading communities or external social platforms, promoting information exchange and cooperation among traders; Personalized collaborative environment: Customize the social trading interface, including selecting the visualization method of data display, setting interaction rules and screening co-traders.

[0012] As a preferred technical solution of the present invention, the dynamic market scenario simulation includes the following steps: Market data collection and real-time update: collect real-time market data , including market trend data, transaction volume data, capital flow data and external economic factor data, and updated at fixed time intervals; Classify market scenarios through pre-trained support vector machines; Construct the corresponding virtual market scenario according to the market status and define the market volatility model: ,in and Adjust parameters for market volatility, is a random market shock variable, used to simulate the impact of unexpected events on the market; Emergency simulation: Combine external news data and economic events to generate market emergency scenarios and use text analysis models to calculate event impact factors , the volatility update formula of the market after being affected by an unexpected event: ,in is the event impact factor; User decision simulation and market feedback: Users adjust their trading strategies in a virtual environment, and the system automatically adjusts feedback based on changes in market scenarios; Situational adaptability assessment: Calculate the adaptability score of user strategies in different market scenarios, record user decisions in specific market scenarios, support playback and retraining, form personalized market adaptability optimization plans, and adjust trading strategies through reinforcement learning algorithms to adapt to dynamic changes in different markets.

[0013] As a preferred technical solution of the present invention, the trading strategy optimization and feedback includes the following steps: Trading strategy execution record: record the user's trading behavior at every moment , including trading hours , Trading Assets , Trading direction , transaction price and transaction quantity , denoted as , and store for subsequent analysis; Trading strategy performance evaluation: Calculate the rate of return of the user's trading strategy and risk level ; , ,in Indicates the transaction value at the current moment, Indicates the transaction value at the previous moment, represents the historical average rate of return, For the first time in history i Record rate of return, risk level Reflect the volatility of the trading strategy; Strategy optimization method: Set the trading strategy optimization goal to maximize the Sharpe ratio, use genetic algorithms to optimize trading strategy parameters, and use reinforcement learning algorithms to adjust trading strategies; dynamically adjust trading strategies based on market conditions and trading results; Historical backtesting and simulation: Support users to backtest trading strategies in different market scenarios, calculate returns and risks based on historical data, and support users to adjust trading parameters and optimize decision-making models.

[0014] A VR-based financial transaction simulation system includes the following modules: Virtual trading environment module: used to provide an immersive virtual reality environment, where users can enter and perform market analysis and trading strategy settings by wearing VR devices. It includes the following units: User interaction unit: supports gesture control and voice interaction, allowing users to interact with market data and trading functions in a virtual environment; Trading setting unit: supports users to select trading products and set trading strategies, and define initial funds and trading parameters; Data collection and processing module: used to collect market data, user transaction history data and risk preference data in real time, and format, denoise and standardize the data. It includes the following units: Data collection unit: obtains real-time data from external data sources; Data preprocessing unit: denoises and standardizes the collected data, and performs quantitative analysis; Market analysis and trading suggestion module: used to conduct in-depth market analysis through artificial intelligence technology and generate personalized trading suggestions, including the following units: Market analysis unit: generates market analysis reports based on users' historical trading data and real-time market data; Trading suggestion generation unit: provides personalized trading suggestions based on market analysis reports and user behaviors; Physiological feedback monitoring and psychological adjustment module: used to monitor the user's physiological data, analyze their emotional state, and adjust the virtual environment or provide psychological intervention suggestions according to emotional fluctuations. It includes the following units: physiological data acquisition unit: real-time collection of physiological parameters through sensors; emotional analysis unit: judge the user's emotional state based on physiological data, and provide corresponding intervention suggestions according to emotional fluctuations; Multi-dimensional market data visualization module: used to display multi-dimensional market data through three-dimensional visualization technology, supporting users to conduct interactive analysis, including the following units: Data display unit: displays data through three-dimensional graphics and heat maps; Interactive analysis unit: supports users to interact with visualized data, view market performance in different time periods, and conduct comparative analysis; Socialized trading and collaborative decision-making module: used to provide a virtual multi-person trading space, supporting users to collaborate and make decisions with other traders, including the following units: Real-time communication unit: supports voice and text chat, and users discuss the market and trading strategies in real time; Collaborative trading unit: allows users to form trading teams, jointly analyze the market, discuss strategies and collaboratively execute transactions in a virtual environment; Dynamic market scenario simulation and trading strategy optimization module: Generates market scenarios based on real-time market data and external events, and optimizes trading strategies. It includes the following units: Market scenario simulation unit: Generates different market scenarios based on real-time data, and simulates the impact of emergencies on the market; Strategy optimization unit: Optimizes trading strategies based on users' trading performance and market scenarios, and provides real-time feedback and adjustment suggestions.

[0015] The present invention has the following advantages: The present invention provides an immersive virtual trading environment through VR technology, allowing traders to conduct market analysis and trading decisions in an immersive way; simulating the decision-making pressure and operation process in a real market environment, and improving traders' actual operation capabilities and ability to cope with market fluctuations.

[0016] The present invention simulates dynamic market scenarios based on real-time market data and external events, allowing traders to test strategies in different market environments, adjust trading strategies in real time and obtain optimization feedback, provide more comprehensive and dynamic market scenarios, and enable traders to understand the impact of different market scenarios on trading strategies, thereby improving the adaptability and effectiveness of strategies.

[0017] The present invention provides users with personalized market analysis reports and trading suggestions through virtual traders combined with artificial intelligence technology, and dynamically adjusts suggestions based on users' historical trading data, risk preferences and real-time market changes, helping traders make more targeted and efficient trading decisions, improving the deficiencies of static rules in traditional simulation systems and enhancing personalized support and real-time response capabilities.

[0018] The present invention monitors the user's heart rate, brain waves and other physiological parameters through physiological feedback equipment, analyzes their emotional state in real time, and adjusts the virtual trading environment or provides psychological adjustment suggestions according to emotional changes, effectively alleviating the psychological pressure in trading, helping traders overcome the impact of emotional fluctuations on decision-making, and improving the stability and scientific nature of trading decisions.

[0019] The present invention supports users to interact with other traders in real time, share trading strategies, and make collaborative decisions in a virtual environment. Through social trading and learning functions, traders can discuss the market with other peers, share trading experiences, and improve the diversity and effectiveness of trading strategies; it simulates various market scenarios and emergencies to help traders conduct response training under extreme market conditions, thereby enhancing traders' market adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art description are briefly introduced below. Obviously, the drawings in the following description are only schematic diagrams of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on the provided drawings without creative work. Figure 1 This is a structural diagram of a VR-based financial transaction simulation system used in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Embodiment 1, a VR-based financial transaction simulation method, comprising the following steps: Step S1, the user enters the virtual trading environment: the user wears a VR device and enters the virtual trading environment through gesture control or voice interaction, selects a trading product and sets a trading strategy; Step S2, generating personalized trading suggestions: Based on the user's historical trading data, risk preferences and market analysis reports, the virtual trader provides personalized trading suggestions through artificial intelligence analysis, and interacts with the user in real time to provide market analysis, strategy optimization suggestions and risk assessment; The virtual trader includes the following features: Market analysis function: analyze market trends, technical indicators and related economic factors, and generate real-time market analysis reports; Trading suggestion function: Provide personalized trading suggestions and trading execution strategies based on the user's historical trading data, risk preferences and market analysis reports; the trading execution strategies include entry timing, exit timing, stop loss and take profit strategies; adjust trading suggestions in real time according to the user's trading behavior, and update the trading execution strategy; adjust the risk preference for the user based on the evaluation and feedback records of the trading execution strategy; The market analysis function and trading suggestion function of the virtual trader are realized by a market analysis model, which uses artificial intelligence technology to process and analyze data to generate real-time market analysis reports, trading suggestions and trading execution strategies.

[0023] The structure of the market analysis model includes: Data input layer: receiving market data, user transaction history data and risk preference data; the market data includes but is not limited to market trend data, technical indicator data, capital flow data, transaction volume data and external economic factor data; Data preprocessing layer: Format, denoise, and standardize the input data, and perform feature extraction and quantitative analysis on the unstructured data in the input data; the denoising process uses the wavelet transform method, the standardization process uses the Z-score standardization method, and the quantitative analysis uses a self-trained natural language processing model for emotion recognition and scoring; Feature extraction layer: Extract key features from market data based on principal component analysis and long short-term memory network, including trend features, momentum features, volatility features, trading volume features, and capital flow features, and extract behavioral features and risk preference features from user transaction history data; Market analysis layer: Based on convolutional neural networks, it conducts in-depth analysis of market trends, technical indicators and external economic factors to generate market analysis reports; Trading suggestion generation layer: Based on deep reinforcement learning combined with decision trees, market analysis reports and user trading behavior characteristics are calculated to generate personalized trading suggestions and trading execution strategies, including entry timing, exit timing, stop loss and take profit strategies; Strategy optimization layer: Use genetic algorithms to optimize and adjust trading execution strategies, and based on reinforcement learning algorithms combined with historical trading performance, adjust the execution results and feedback of trading strategies to optimize trading suggestions and risk control parameters; Interactive feedback layer: Provides the generated market analysis reports, trading suggestions and optimization results to virtual traders, and interacts with users through natural language processing models to provide real-time trading analysis, decision-making suggestions and strategy optimization guidance.

[0024] The training of the market analysis model includes the following steps: Data collection and preprocessing: Collecting market data , user transaction history data and risk appetite data , get the training data set , and split the training data set into training set, test set and validation set according to the set ratio; Format the market data and use wavelet transform to denoise it: ,in represents the wavelet transform function; The formatted market data is standardized using Z-score standardization: ,in μ represents the mean of market data, is the standard deviation of the market data; Extract sentiment scores using natural language processing models on unstructured data: ,in represents a natural language model, For unstructured data; Feature extraction and dimensionality reduction: Extracting features of market data using principal component analysis , using long short-term memory networks to extract features from transaction history data , combined with market characteristics , User transaction characteristics and risk appetite Form the final input feature matrix: ; Market analysis layer training: Use convolutional neural network to extract market trend features, and train the market analysis layer by minimizing the loss function: ,in The actual market trend data is obtained through real-time collection. The output predicted by the convolutional neural network; Trading suggestion generation layer training: Deep reinforcement learning combined with decision trees is used to generate trading suggestions, and the reward function is defined as: ,in is the current price of the trading asset, is the price at the previous time step, For transaction costs; Using Q-learning for reinforcement learning update: ,in Indicates the cumulative reward value, Indicates the current state. Indicates taking action, Indicates the expected cumulative reward value after taking a certain action in the current state; represents the learning rate, Indicates execution of an action The immediate reward after Represents the discount factor, which is used to control the weight of subsequent reward values; Indicates that in the next state Next, all actions The maximum reward value in is used to predict the maximum reward in the next state; Strategy optimization layer training: Use genetic algorithms to optimize trading execution strategies, define fitness functions, and iteratively optimize trading strategies through selection, crossover, and mutation operations; Model evaluation and adjustment: Using mean square error to evaluate market analysis models: ,in n Indicates the total number of output targets of the model, Indicates i training goals, Indicates i The model predicts the results; Cumulative rate of return Evaluating trading strategies: ,in is the return rate for each time step, t represents the current time step, T represents the total number of time steps; After the training is completed, the market analysis model is used for market analysis and trading suggestion generation.

[0025] Step S3, physiological feedback monitoring and psychological adjustment: real-time collection of the user's physiological parameters, analysis of the user's emotional state, and automatic adjustment of the virtual environment or provision of psychological intervention suggestions when negative emotions are detected; the negative emotions are initially set to anxiety and tension, and the adjustment of the virtual environment includes sound effects, light and market fluctuation speed; The physiological feedback monitoring and psychological adjustment include: Physiological data collection: The physiological parameters of the user are collected in real time through physiological sensing equipment, including heart rate, heart rate variability, skin electrical activity and brain waves. The collected physiological parameters are expressed as: ,in tp represents the time step of collecting physiological parameters, Indicates heart rate, represents the heart rate variability, Indicates skin electrical activity, Indicates brain waves; Physiological data preprocessing: Use a bandpass filter to remove artifact noise in the EEG signal, smooth the heart rate signal, and calculate the short-term mean; Emotional state recognition: Using the support vector machine classification model, the user's emotional state is recognized based on preprocessed physiological data, including four categories: anxiety, tension, calmness, and pleasure; Psychological state adjustment: When the user is detected to be in an anxious or nervous state, the virtual environment is automatically adjusted, including sound effect adjustment (reducing the intensity of ambient sound or playing soothing background music), visual environment adjustment (reducing the speed of market fluctuations and reducing visual stimulation) and guiding feedback. Based on the natural language processing model, psychological adjustment suggestions are provided to the user, such as reminding the user to take a deep breath, postpone trading decisions, etc.; User feedback and adaptive optimization: record the user's emotional changes and trading performance, associate the user's physiological feedback data with the trading results, and build an adaptive psychological adjustment matrix. The psychological adjustment matrix uses regression analysis to establish the relationship between physiological signals and trading performance, and continuously optimizes the psychological adjustment strategy; Psychological intervention suggestions: When the system detects that the user is anxious or nervous during multiple consecutive trading cycles, it will provide active intervention. For example: remind the user to pause trading and take a short break; provide breathing training guidance such as 4-7-8 breathing method; adjust the trading interface to reduce interference from high-frequency market data.

[0026] The physiological feedback monitoring and psychological adjustment method adapts to the user's state in real time during the transaction process and optimizes the user's trading psychological environment.

[0027] Step S4, multi-dimensional market data visualization: based on multi-dimensional data, three-dimensional visualization technology is used to present market trends in a virtual environment, supporting users to conduct data analysis and market insights in an interactive manner; the multi-dimensional data includes market depth, capital flow and transaction volume; The multi-dimensional market data visualization includes the following contents: Market Depth Visualization: Displays market depth in a three-dimensional graphic in a virtual environment, including the number of buy and sell orders at different prices. Users can interactively adjust the viewing angle to intuitively understand the market supply and demand situation; Visualization of capital flow: Use dynamic flow charts to display capital flows, including the inflow and outflow of large amounts of capital. Users can distinguish the dynamic trends of buyer funds and seller funds through color changes; Volume visualization: Display the changes in market volume over different time periods through bar charts, heat maps or 3D surface charts. Users can freely zoom in and out of the time range to view short-term or long-term volume trends. Market trend visualization: Combined with the immersive environment of VR, K-line charts, moving averages, and trend lines are used to display market trends. Users can also use gesture interaction or voice commands to call up different technical indicators (such as MACD, RSI, Bollinger Bands, etc.) for analysis. Real-time data interaction: Provides interactive data query function. Users can select specific market areas or trading products through gestures or voice input. The system will instantly display relevant data and support comparative analysis of multi-dimensional data. Visualization of market hotspots: Highlight active market trading areas in a three-dimensional market environment, and use colors or dynamic effects to identify market intervals where funds are currently flowing in or out, helping users quickly identify trading opportunities; Multi-market comparative analysis: Supports displaying the market depth, trends and trading status of multiple markets (stocks, foreign exchange, cryptocurrencies, etc.) in a virtual environment at the same time. Users can switch between different markets or observe the interactive relationship between multiple markets in parallel; Personalized data layout: Users can customize the visualization interface, adjust the display mode, color, and transparency of different market data, and set a personalized market analysis perspective to meet the preferences and needs of different traders.

[0028] The multi-dimensional market data visualization method provides immersive and interactive data display through a VR environment, enabling users to analyze market dynamics and optimize trading decisions more intuitively and efficiently.

[0029] Step S5, socialized trading and collaborative decision-making: users communicate with other traders in real time in a virtual environment, share trading strategies, discuss market sentiment, and conduct collaborative trading simulations to optimize personal trading strategies through group decision-making; The socialized transaction and collaborative decision-making include the following contents: Multi-person virtual trading space: provides a virtual trading environment that supports multiple users online at the same time, in which users can interact with other traders in real time, including market analysis discussions, trading strategy sharing and collaborative trading execution; Real-time voice and text communication: integrated voice communication and text chat functions, users can discuss the market with other traders through voice commands or text input, and support automatic voice-to-text function, which is convenient for traders to quickly record and review the discussion content; Trading strategy sharing and analysis: Support sharing of personal trading strategies between users, backtesting and visualization of shared strategies, and support for users to test other people's strategies in a virtual trading environment; Collaborative trading mode: provides team trading functions, supports users to form trading teams, make collective decisions in a virtual environment, negotiate trading plans, assign different roles (analysts, executors, etc.), and jointly execute trading strategies; Market sentiment and consensus analysis: The system analyzes market sentiment and generates a market sentiment index based on the discussion content and trading behavior of user groups. Users can view the market trends of different trading groups to assist in decision-making; Social rankings and reputation system: Establish a social reputation system for traders, provide reputation scores for traders based on factors such as user trading performance, market analysis content contributed, and effectiveness of strategy sharing, and promote the influence of high-quality traders; Virtual tutor and learning mode: Support experienced traders to create virtual classrooms or live trading, other users can participate in learning and interaction, and follow the tutor to perform simulated trading in simulation trading mode; Trading competition and challenge mechanism: Provide trading competition function, support users to participate in trading challenges organized by the system or community, simulate the real market environment, optimize trading strategies in the competition, and obtain feedback and improvement suggestions through competition results; Social network integration: Support users to share trading records, market analysis and trading ideas to virtual trading communities or external social platforms, promoting information exchange and cooperation among traders; Personalized collaborative environment: Customize the social trading interface, including selecting the visual data display method, setting interaction rules and screening co-traders to improve the efficiency and experience of collaborative trading.

[0030] The social trading and collaborative decision-making method provides an interactive, multi-user collaborative trading environment, enabling users to share knowledge, optimize strategies, and conduct team trading simulations in a VR environment.

[0031] Step S6, dynamic market scenario simulation: Generate dynamic and adaptive market scenarios based on real-time market data and external events to simulate dynamic market changes and provide feedback and optimization suggestions for user response strategies; The dynamic market scenario simulation includes the following steps: Market data collection and real-time update: collect real-time market data , including market trend data, transaction volume data, capital flow data and external economic factor data, and updated at fixed time intervals; Market scenarios are classified through pre-trained support vector machines; scenario categories include bull market, bear market, volatile market, high volatility market, low liquidity market, etc. Construct the corresponding virtual market scenario according to the market status and define the market volatility model: ,in and Adjust parameters for market volatility, is a random market shock variable, used to simulate the impact of unexpected events on the market; Emergency simulation: Combine external news data and economic events to generate market emergency scenarios, such as policy changes, geopolitical conflicts, economic crises, etc., and use text analysis models to calculate event impact factors The text analysis model is a self-trained natural language processing model that analyzes news sentiment and quantifies the impact of events on the market. The volatility update formula for the market after being affected by an emergency is: ,in is the event impact factor; User decision simulation and market feedback: Users adjust their trading strategies in a virtual environment, and the system automatically adjusts feedback based on changes in market scenarios; Situational adaptability assessment: Calculate the adaptability score of user strategies in different market scenarios, record user decisions in specific market scenarios, support playback and retraining, form personalized market adaptability optimization plans, and adjust trading strategies through reinforcement learning algorithms to adapt to dynamic changes in different markets.

[0032] The dynamic market scenario simulation method constructs a virtual trading environment through real-time market data analysis, market status classification, emergency event modeling and user decision feedback mechanism, so that users can test and optimize trading strategies in different market scenarios and improve market adaptability.

[0033] Step S7, trading strategy optimization and feedback: Users adjust trading strategies based on real-time feedback in the virtual environment and test the optimization in simulation. The system provides instant evaluation and improvement suggestions based on user operations to improve the effectiveness and stability of the strategy.

[0034] The trading strategy optimization and feedback includes the following steps: Trading strategy execution record: record the user's trading behavior at every moment , including trading hours , Trading Assets , Trading direction (buy\sell), transaction price and transaction quantity , denoted as , and store for subsequent analysis; Trading strategy performance evaluation: Calculate the rate of return of the user's trading strategy and risk level ; , ,in Indicates the transaction value at the current moment, Indicates the transaction value at the previous moment, represents the historical average rate of return, For the first time in history i Record rate of return, risk level Reflect the volatility of the trading strategy; Strategy optimization method: Set the trading strategy optimization goal to maximize the Sharpe ratio, use genetic algorithms to optimize trading strategy parameters, and use reinforcement learning algorithms to adjust trading strategies; dynamically adjust trading strategies based on market conditions and trading results; Historical backtesting and simulation: Support users to backtest trading strategies in different market scenarios, calculate returns and risks based on historical data, and support users to adjust trading parameters and optimize decision-making models.

[0035] The trading strategy optimization and feedback method enables users to continuously optimize trading strategies in a virtual trading environment and improve trading stability and profitability through performance evaluation, intelligent optimization, real-time adjustment and visual feedback.

[0036] Example 2, a VR-based financial transaction simulation system, see Figure 1 As shown, it includes the following modules: Virtual trading environment module: used to provide an immersive virtual reality environment, where users can enter and perform market analysis and trading strategy settings by wearing VR devices. It includes the following units: User interaction unit: supports gesture control and voice interaction, allowing users to interact with market data and trading functions in a virtual environment; Trading setting unit: supports users to select trading products and set trading strategies, and define initial funds and trading parameters; Data collection and processing module: used to collect market data, user transaction history data and risk preference data in real time, and format, denoise and standardize the data. It includes the following units: Data collection unit: obtains real-time data from external data sources; Data preprocessing unit: denoises and standardizes the collected data, and performs quantitative analysis; Market analysis and trading suggestion module: used to conduct in-depth market analysis through artificial intelligence technology and generate personalized trading suggestions, including the following units: Market analysis unit: generates market analysis reports based on users' historical trading data and real-time market data; Trading suggestion generation unit: provides personalized trading suggestions based on market analysis reports and user behaviors; Physiological feedback monitoring and psychological adjustment module: used to monitor the user's physiological data, analyze their emotional state, and adjust the virtual environment or provide psychological intervention suggestions according to emotional fluctuations. It includes the following units: physiological data acquisition unit: real-time collection of physiological parameters through sensors; emotional analysis unit: judge the user's emotional state based on physiological data, and provide corresponding intervention suggestions according to emotional fluctuations; Multi-dimensional market data visualization module: used to display multi-dimensional market data through three-dimensional visualization technology, supporting users to conduct interactive analysis, including the following units: Data display unit: displays data through three-dimensional graphics and heat maps; Interactive analysis unit: supports users to interact with visualized data, view market performance in different time periods, and conduct comparative analysis; Socialized trading and collaborative decision-making module: used to provide a virtual multi-person trading space, supporting users to collaborate and make decisions with other traders, including the following units: Real-time communication unit: supports voice and text chat, and users discuss the market and trading strategies in real time; Collaborative trading unit: allows users to form trading teams, jointly analyze the market, discuss strategies and collaboratively execute transactions in a virtual environment; Dynamic market scenario simulation and trading strategy optimization module: Generates market scenarios based on real-time market data and external events, and optimizes trading strategies. It includes the following units: Market scenario simulation unit: Generates different market scenarios based on real-time data, and simulates the impact of emergencies on the market; Strategy optimization unit: Optimizes trading strategies based on users' trading performance and market scenarios, and provides real-time feedback and adjustment suggestions.

[0037] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A VR-based financial transaction simulation method, characterized in that: The following steps are involved: Step S1, the user enters the virtual trading environment: the user wears a VR device and enters the virtual trading environment through gesture control or voice interaction, selects a trading product and sets a trading strategy; Step S2, generating personalized trading suggestions: Based on the user's historical trading data, risk preferences and market analysis reports, the virtual trader provides personalized trading suggestions through artificial intelligence analysis, and interacts with the user in real time to provide market analysis, strategy optimization suggestions and risk assessment; Step S3, physiological feedback monitoring and psychological adjustment: real-time collection of the user's physiological parameters, analysis of the user's emotional state, and automatic adjustment of the virtual environment or provision of psychological intervention suggestions when negative emotions are detected; the negative emotions are initially set to anxiety and tension, and the adjustment of the virtual environment includes sound effects, light and market fluctuation speed; Step S4, multi-dimensional market data visualization: based on multi-dimensional data, three-dimensional visualization technology is used to present market trends in a virtual environment, supporting users to conduct data analysis and market insights in an interactive manner; the multi-dimensional data includes market depth, capital flow and transaction volume; Step S5, socialized trading and collaborative decision-making: users communicate with other traders in real time in a virtual environment, share trading strategies, discuss market sentiment, and conduct collaborative trading simulations to optimize personal trading strategies through group decision-making; Step S6, dynamic market scenario simulation: Generate dynamic and adaptive market scenarios based on real-time market data and external events to simulate dynamic market changes and provide feedback and optimization suggestions for user response strategies; Step S7, trading strategy optimization and feedback: Users adjust trading strategies based on real-time feedback in the virtual environment and test the optimization in simulation. The system provides instant evaluation and improvement suggestions based on user operations to improve the effectiveness and stability of the strategy.

2. A VR-based financial transaction simulation method according to claim 1, characterized in that: The virtual trader includes the following features: Market analysis function: analyze market trends, technical indicators and related economic factors, and generate real-time market analysis reports; Trading suggestion function: Provide personalized trading suggestions and trading execution strategies based on the user's historical trading data, risk preferences and market analysis reports; the trading execution strategies include entry timing, exit timing, stop loss and take profit strategies; adjust trading suggestions in real time according to the user's trading behavior, and update the trading execution strategy; adjust the risk preference for the user based on the evaluation and feedback records of the trading execution strategy; The market analysis function and trading suggestion function of the virtual trader are realized by a market analysis model, which uses artificial intelligence technology to process and analyze data to generate real-time market analysis reports, trading suggestions and trading execution strategies.

3. A VR-based financial transaction simulation method according to claim 2, characterized in that: The structure of the market analysis model includes: Data input layer: receiving market data, user transaction history data and risk preference data; Data preprocessing layer: Format, denoise, and standardize the input data, and perform feature extraction and quantitative analysis on the unstructured data in the input data; the denoising process uses the wavelet transform method, the standardization process uses the Z-score standardization method, and the quantitative analysis uses a self-trained natural language processing model for emotion recognition and scoring; Feature extraction layer: Extract key features from market data based on principal component analysis and long short-term memory network, including trend features, momentum features, volatility features, trading volume features, and capital flow features, and extract behavioral features and risk preference features from user transaction history data; Market analysis layer: Based on convolutional neural networks, it conducts in-depth analysis of market trends, technical indicators and external economic factors to generate market analysis reports; Trading suggestion generation layer: Based on deep reinforcement learning combined with decision trees, market analysis reports and user trading behavior characteristics are calculated to generate personalized trading suggestions and trading execution strategies, including entry timing, exit timing, stop loss and take profit strategies; Strategy optimization layer: Use genetic algorithms to optimize and adjust trading execution strategies, and based on reinforcement learning algorithms combined with historical trading performance, adjust the execution results and feedback of trading strategies to optimize trading suggestions and risk control parameters; Interactive feedback layer: Provides the generated market analysis reports, trading suggestions and optimization results to virtual traders, and interacts with users through natural language processing models to provide real-time trading analysis, decision-making suggestions and strategy optimization guidance.

4. A VR-based financial transaction simulation method according to claim 3, characterized in that: The training of the market analysis model includes the following steps: Data collection and preprocessing: Collecting market data , user transaction history data and risk appetite data , get the training data set , and split the training data set into training set, test set and validation set according to the set ratio; Format the market data and use wavelet transform to denoise it: ,in represents the wavelet transform function; The formatted market data is standardized using Z-score standardization: ,in μ represents the mean of market data, is the standard deviation of the market data; Extract sentiment scores using natural language processing models on unstructured data: ,in represents a natural language model, For unstructured data; Feature extraction and dimensionality reduction: Extracting features of market data using principal component analysis , using long short-term memory networks to extract features from transaction history data , combined with market characteristics , User transaction characteristics and risk appetite Form the final input feature matrix: ; Market analysis layer training: Use convolutional neural network to extract market trend features, and train the market analysis layer by minimizing the loss function: ,in The actual market trend data is obtained through real-time collection. The output predicted by the convolutional neural network; Trading suggestion generation layer training: Deep reinforcement learning combined with decision trees is used to generate trading suggestions, and the reward function is defined as: ,in is the current price of the trading asset, is the price at the previous time step, For transaction costs; Using Q-learning for reinforcement learning update: ,in Indicates the cumulative reward value, Indicates the current state. Indicates taking action, Indicates the expected cumulative reward value after taking a certain action in the current state; represents the learning rate, Indicates execution of an action The immediate reward after Represents the discount factor, which is used to control the weight of subsequent reward values; Indicates that in the next state Next, all actions The maximum reward value in is used to predict the maximum reward in the next state; Strategy optimization layer training: Use genetic algorithms to optimize trading execution strategies, define fitness functions, and iteratively optimize trading strategies through selection, crossover, and mutation operations; Model evaluation and adjustment: Using mean square error to evaluate market analysis models: ,in n Indicates the total number of output targets of the model, Indicates i training goals, Indicates i The model predicts the results; Cumulative rate of return Evaluating trading strategies: ,in is the return rate for each time step, t represents the current time step, T represents the total number of time steps; After the training is completed, the market analysis model is used for market analysis and trading suggestion generation.

5. The VR-based financial transaction simulation method according to claim 1, characterized in that: The physiological feedback monitoring and psychological adjustment include: Physiological data collection: The physiological parameters of the user are collected in real time through physiological sensing equipment, including heart rate, heart rate variability, skin electrical activity and brain waves. The collected physiological parameters are expressed as: ,in tp represents the time step of collecting physiological parameters, Indicates heart rate, represents the heart rate variability, Indicates skin electrical activity, Indicates brain waves; Physiological data preprocessing: Use a bandpass filter to remove artifact noise in the EEG signal, smooth the heart rate signal, and calculate the short-term mean; Emotional state recognition: Using the support vector machine classification model, the user's emotional state is recognized based on preprocessed physiological data, including four categories: anxiety, tension, calmness, and pleasure; Mental state adjustment: automatically adjust the virtual environment when it detects that the user is in an anxious or nervous state, including sound effect adjustment, visual environment adjustment and guiding feedback; User feedback and adaptive optimization: record the user's emotional changes and trading performance, associate the user's physiological feedback data with the trading results, and build an adaptive psychological adjustment matrix. The psychological adjustment matrix uses regression analysis to establish the relationship between physiological signals and trading performance, and continuously optimizes the psychological adjustment strategy; Psychological intervention suggestions: When the system detects that the user is anxious or nervous during multiple consecutive trading cycles, it provides proactive intervention.

6. The VR-based financial transaction simulation method according to claim 1, characterized in that: The multi-dimensional market data visualization includes the following contents: Market Depth Visualization: Displays the market depth in a three-dimensional graphic in a virtual environment, including the number of buy and sell orders at different prices; Visualization of capital flow: Use dynamic flow charts to display capital flows, including the inflow and outflow of large amounts of capital; Trading volume visualization: Display the changes in trading volume in different time periods through bar charts, heat maps or 3D surface charts; Market trend visualization: Combined with the immersive environment of VR, K-line charts, moving averages, and trend lines are used to display market trends, and users are supported to call up different technical indicators for analysis through gesture interaction or voice commands; Real-time data interaction: Provides interactive data query function. Users can select specific market areas or trading products through gestures or voice input. The system will instantly display relevant data and support comparative analysis of multi-dimensional data. Visualization of market hotspots: highlighting active market trading areas in a three-dimensional market environment, and using colors or dynamic effects to identify market areas where funds are currently flowing in or out. Multi-market comparative analysis: supports displaying the market depth, trends and trading status of multiple markets in a virtual environment at the same time; Personalized data layout: Users can customize the visualization interface, adjust the display mode, color, and transparency of different market data, and set a personalized market analysis perspective.

7. The VR-based financial transaction simulation method according to claim 1, characterized in that: The socialized transaction and collaborative decision-making include the following contents: Multi-person virtual trading space: provides a virtual trading environment that supports multiple users online at the same time, in which users can interact with other traders in real time, including market analysis discussions, trading strategy sharing and collaborative trading execution; Real-time voice and text communication: integrated voice communication and text chat functions, users can discuss the market with other traders through voice commands or text input, and support automatic voice-to-text function; Trading strategy sharing and analysis: Support sharing of personal trading strategies between users, backtesting and visualization of shared strategies, and support for users to test other people's strategies in a virtual trading environment; Collaborative trading mode: provides team trading functions, supports users to form trading teams, make collective decisions in a virtual environment, negotiate trading plans, assign different roles, and jointly execute trading strategies; Market sentiment and consensus analysis: The system analyzes market sentiment and generates a market sentiment index based on the discussion content and trading behavior of user groups; Social rankings and reputation system: Establish a social reputation system for traders, provide reputation scores for traders based on factors such as user trading performance, market analysis content contributed, and effectiveness of strategy sharing, and promote the influence of high-quality traders; Virtual Tutor and Learning Mode: Support experienced traders to create virtual classrooms or live trading, accept other users to participate in learning and interaction, and follow the tutor to perform simulated trading in the simulation trading mode; Trading competition and challenge mechanism: Provide trading competition function, support users to participate in trading challenges organized by the system or community, simulate the real market environment, optimize trading strategies in the competition, and obtain feedback and improvement suggestions through competition results; Social network integration: Support users to share trading records, market analysis and trading ideas to virtual trading communities or external social platforms, promoting information exchange and cooperation among traders; Personalized collaborative environment: Customize the social trading interface, including selecting the visualization method of data display, setting interaction rules and screening co-traders.

8. The VR-based financial transaction simulation method according to claim 1, characterized in that: The dynamic market scenario simulation includes the following steps: Market data collection and real-time update: collect real-time market data , including market trend data, transaction volume data, capital flow data and external economic factor data, and updated at fixed time intervals; Classify market scenarios through pre-trained support vector machines; Construct the corresponding virtual market scenario according to the market status and define the market volatility model: ,in and Adjust parameters for market volatility, is a random market shock variable, used to simulate the impact of unexpected events on the market; Emergency simulation: Combine external news data and economic events to generate market emergency scenarios and use text analysis models to calculate event impact factors , the volatility update formula of the market after being affected by an unexpected event: ,in is the event impact factor; User decision simulation and market feedback: Users adjust their trading strategies in a virtual environment, and the system automatically adjusts feedback based on changes in market scenarios; Situational adaptability assessment: Calculate the adaptability score of user strategies in different market scenarios, record user decisions in specific market scenarios, support playback and retraining, form personalized market adaptability optimization plans, and adjust trading strategies through reinforcement learning algorithms to adapt to dynamic changes in different markets.

9. The VR-based financial transaction simulation method according to claim 1, characterized in that: The trading strategy optimization and feedback includes the following steps: Trading strategy execution record: records the user's trading behavior at every moment, including trading time, trading assets, trading direction, trading price and trading quantity, recorded as , and store for subsequent analysis; Trading strategy performance evaluation: Calculate the rate of return of the user's trading strategy and risk level ; , ,in Indicates the transaction value at the current moment, Indicates the transaction value at the previous moment, represents the historical average rate of return, For the first time in history i Record rate of return, risk level Reflect the volatility of the trading strategy; Strategy optimization method: Set the trading strategy optimization goal to maximize the Sharpe ratio, use genetic algorithms to optimize trading strategy parameters, and use reinforcement learning algorithms to adjust trading strategies; dynamically adjust trading strategies based on market conditions and trading results; Historical backtesting and simulation: Support users to backtest trading strategies in different market scenarios, calculate returns and risks based on historical data, and support users to adjust trading parameters and optimize decision-making models.

10. A VR-based financial transaction simulation system, characterized in that: The system applies a VR-based financial transaction simulation method as described in any one of claims 1 to 9, and includes the following modules: Virtual trading environment module: used to provide an immersive virtual reality environment, where users can enter and perform market analysis and trading strategy settings by wearing VR devices. It includes the following units: User interaction unit: supports gesture control and voice interaction, allowing users to interact with market data and trading functions in a virtual environment; Trading setting unit: supports users to select trading products and set trading strategies, and define initial funds and trading parameters; Data collection and processing module: used to collect market data, user transaction history data and risk preference data in real time, and format, denoise and standardize the data, including the following units: Data collection unit: obtains real-time data from external data sources; Data preprocessing unit: denoise and standardize the collected data, and perform quantitative analysis; Market analysis and trading suggestion module: used to conduct in-depth market analysis through artificial intelligence technology and generate personalized trading suggestions, including the following units: Market analysis unit: generates market analysis reports based on users' historical trading data and real-time market data; Trading suggestion generation unit: provides personalized trading suggestions based on market analysis reports and user behaviors; Physiological feedback monitoring and psychological adjustment module: used to monitor the user's physiological data, analyze their emotional state, and adjust the virtual environment or provide psychological intervention suggestions according to emotional fluctuations. It includes the following units: physiological data acquisition unit: real-time collection of physiological parameters through sensors; emotional analysis unit: judge the user's emotional state based on physiological data, and provide corresponding intervention suggestions according to emotional fluctuations; Multi-dimensional market data visualization module: used to display multi-dimensional market data through three-dimensional visualization technology, supporting users to conduct interactive analysis, including the following units: Data display unit: displays data through three-dimensional graphics and heat maps; Interactive analysis unit: supports users to interact with visualized data, view market performance in different time periods, and conduct comparative analysis; Socialized trading and collaborative decision-making module: used to provide a virtual multi-person trading space, supporting users to collaborate and make decisions with other traders, including the following units: Real-time communication unit: supports voice and text chat, and users discuss the market and trading strategies in real time; Collaborative trading unit: allows users to form trading teams, jointly analyze the market, discuss strategies and collaboratively execute transactions in a virtual environment; Dynamic market scenario simulation and trading strategy optimization module: Generates market scenarios based on real-time market data and external events, and optimizes trading strategies. It includes the following units: Market scenario simulation unit: Generates different market scenarios based on real-time data, and simulates the impact of emergencies on the market; Strategy Optimization Unit: Optimize trading strategies based on users’ trading performance and market scenarios, and provide real-time feedback and adjustment suggestions.

Images