Novel community order following transaction system and method based on intelligent screening and combination

Abstract

The invention discloses a novel community order following transaction method based on intelligent screening and combination. The method comprises the following steps: obtaining all available transaction signals from a target transaction platform; classifying and screening the transaction signals according to the multi-dimensional evaluation indexes, and constructing different types of transaction signal combination strategies; scoring the screened transaction signals based on a comprehensive scoring model, screening out the transaction signals with scores higher than a preset value according to a scoring result, and rejecting the transaction signals with scores lower than the preset value; based on a personalized demand recommendation model, recommending a corresponding transaction signal combination to the user, and providing personalized transaction signal combination suggestions; after the user selects a transaction signal combination, order following operations including generation, order placing, adjustment and leveling are automatically executed; risks in a transaction process are monitored in real time, and signal combination and position are automatically adjusted by using strategies of dynamic loss stop, interference stop and position adjustment, so that continuous profit is realized on the basis of ensuring fund safety of a user.

Description

Technical Field

[0001] The present invention relates to the technical field of copy trading, and in particular to a novel community copy trading system and method based on intelligent screening and combination. Background Art

[0002] With the rapid development of the Internet and financial technology, community copy trading systems have been widely used in the field of financial investment. The traditional community copy trading system allows investors to directly copy the trading operations of other successful traders in order to obtain similar investment returns. This model lowers the threshold for novice investors to enter the market, allowing them to participate in investment without having professional financial knowledge and trading experience.

[0003] However, the existing copy trading system has the following defects:

[0004] The current system usually relies on investors to manually select traders to follow, mainly based on limited indicators such as historical performance. This method cannot comprehensively assess the risk level, trading style and market adaptability of traders, resulting in investors following traders that are not suitable for their risk preferences and investment goals; the existing system usually only supports the strategy of following a single trader, lacks the combination and optimization of multiple trading strategies, which limits the possibility of investors reducing risks and increasing returns through diversification; the current system lacks personalization in strategy recommendation and matching, and cannot provide customized suggestions based on investors' historical trading behavior, risk tolerance and investment preferences, which makes it difficult for investors to find the trading strategy that best suits them; although it is a community copy, many platforms have limited social functions and lack effective communication and learning mechanisms, and cannot give full play to the advantages of the community; the existing system provides limited trading data and analysis tools, which cannot help investors fully understand traders' performance indicators, such as maximum drawdown, Sharpe ratio and other key risk indicators.

[0005] Therefore, there is an urgent need for a new community copy trading system and method based on intelligent screening and combination. Summary of the invention

[0006] The present invention provides a novel community copy trading system and method based on intelligent screening and combination to solve the above-mentioned problems existing in the prior art.

[0007] In order to achieve the above object, the present invention provides the following technical solutions:

[0008] A new community copy trading system based on intelligent screening and combination, including:

[0009] A trading signal acquisition unit, used for acquiring all available trading signals from a target trading platform;

[0010] Intelligent screening unit, used to classify and screen trading signals according to multi-dimensional evaluation indicators, and build different types of trading signal combination strategies;

[0011] A comprehensive scoring unit is used to score the filtered trading signals based on the comprehensive scoring model, and according to the scoring results, filter out the trading signals with scores higher than the preset value, and exclude the trading signals with scores lower than the preset value;

[0012] A personalized recommendation unit is used to recommend corresponding trading signal combinations to users based on a personalized demand recommendation model, and provide personalized trading signal combination suggestions;

[0013] The copy execution unit is used to automatically execute copy operations after the user selects a trading signal combination, including generating, placing orders, adjusting and closing positions;

[0014] The real-time risk monitoring unit is used to monitor the risks in the transaction process in real time, and use dynamic stop loss, take profit, and position adjustment strategies to automatically adjust signal combinations and positions to ensure that users can achieve continuous profits on the basis of capital security.

[0015] Among them, the intelligent screening unit includes:

[0016] The evaluation module is used to analyze trading signals based on multi-dimensional evaluation indicators, including the stability, accuracy, potential rate of return, risk level and market adaptability of trading signals. The multi-dimensional evaluation indicators are quantitatively calculated through a preset algorithm model;

[0017] The classification module is used to classify trading signals according to preset classification standards based on the analysis results of multi-dimensional evaluation indicators and obtain classification results. The classification standards include different risk levels and strategy types. The strategy types include trend tracking strategy, mean reversion strategy and momentum strategy.

[0018] The screening module is used to screen different types of trading signal combination strategies based on the classification results and the user's preset trading strategy preferences, and identify the trading signal combination strategies that match the user's preferences.

[0019] The comprehensive scoring units include:

[0020] A scoring module, used to score the selected trading signals based on a comprehensive scoring model. The comprehensive scoring model includes multiple scoring dimensions. The scoring dimensions include at least profitability, risk management, and market adaptability. The scoring module comprehensively scores each selected trading signal based on the scores of each dimension.

[0021] The screening module is used to screen out trading signals with scores higher than a preset threshold based on the comprehensive scoring results, and to exclude trading signals with scores lower than the preset threshold.

[0022] Among them, the corresponding trading signal combination is recommended to users, including:

[0023] Build a personalized demand recommendation model based on transaction signals;

[0024] The personalized demand recommendation model is used to analyze the user's historical trading style and the signal characteristics of community transactions to generate matching trading signal combination recommendations;

[0025] Determine whether the signal characteristics of community transactions match the user's trading style, including:

[0026] Analyze the user's short-term trading frequency to determine whether the user is a short-term trader or a long-term trader;

[0027] Analyze the user's risk tolerance and determine whether the user prefers high risk and high return or low risk and stable return;

[0028] According to the short-term trading frequency of users, select the trading signal combination with excellent short-term trading performance from community transactions;

[0029] According to the user's risk tolerance, select signal combinations with volatility that meet the user's preferences from community transactions;

[0030] When the selected trading signal combination matches the user's trading style, a corresponding personalized trading signal combination recommendation is generated;

[0031] Output the trading signal combination recommendation to the client terminal logged in to the user account transmitting the trading data;

[0032] Users can directly view the recommended signal combinations and gain a deeper understanding of the recommended strategy combinations through the system’s visual analysis charts;

[0033] Visual analysis charts show the average holding time of trading signal combinations and profit curve data to help users make choices;

[0034] After the user reviews and selects the recommended trading signal combination, the system records the user's selection and feedback.

[0035] Among them, the automatic execution of copy trading operations includes:

[0036] Generate trading instructions based on the current trading signal combination selected by the user;

[0037] Place orders based on the generated trading instructions, track strategy changes within the trading community in real time, and obtain information on changes in each strategy within the community;

[0038] Determine whether the strategy change information triggers the adjustment conditions for the current position. If the adjustment conditions are triggered, automatically generate the position adjustment instruction, and execute the position adjustment instruction to automatically adjust the current position;

[0039] Determine whether the strategy change information triggers the closing conditions. If the closing conditions are triggered, a closing instruction is automatically generated and executed to close the relevant positions;

[0040] Users can view the system's automatic copy execution details, which include the current position status, order time, and executed strategy adjustment information;

[0041] The user sets the manual intervention conditions, including the conditions for early closing of positions when the preset profit target is reached. The system determines whether to generate and execute manual intervention instructions based on the manual intervention conditions set by the user;

[0042] If the manual intervention condition is triggered, the system will automatically generate a manual intervention instruction and execute the manual intervention instruction to control the current position;

[0043] Track strategy changes within the trading community in real time, including:

[0044] Obtain several currently active trading strategies in the community and their corresponding change signals;

[0045] It is determined in turn whether the change signal of each trading strategy is associated with the trading signal combination selected by the user. If there is a correlation, the strategy corresponding to the change signal is marked as a strategy that needs to be adjusted;

[0046] For strategies marked as requiring adjustment, corresponding position adjustment instructions are generated, and the user's current position status is adjusted according to the position adjustment instructions.

[0047] Among them, real-time monitoring of risks in the transaction process includes:

[0048] Obtain the dynamic position risk level of each risk monitoring zone;

[0049] Determine the position partition that needs to be adjusted based on the position risk level and risk point data of each risk monitoring partition, where the position partition includes the position status of one or more user accounts;

[0050] Determine the target position strategy for each risk monitoring zone;

[0051] If the position risk level of a position partition is higher than the preset risk control target, the position partition will be automatically adjusted or suggestions will be provided to reduce the overall transaction risk;

[0052] Obtain the real-time risk level of each trading unit in the user's position;

[0053] Determine the high-risk trading unit in the position partition according to the risk level of the trading unit and the risk point data triggered by market fluctuations, where the high-risk trading unit includes one or more trading products;

[0054] According to the target position strategy of the position partition, determine the target position of each trading unit in the position partition;

[0055] If the real-time risk level of a trading unit exceeds the preset stop loss or take profit point, the trading unit will be automatically adjusted or suggestions will be provided based on the target position to ensure the safety of the user's position.

[0056] Among them, the trading signal combination strategy that matches the user's preferences is identified, including:

[0057] Perform feature extraction on the first transaction signal to obtain a first feature value set, where:

[0058] Based on a preset first feature extraction template, feature extraction is performed on the signal characteristics of the first transaction signal;

[0059] Signal characteristics include: multi-dimensional evaluation indicators of yield, risk level, volatility, holding time and trading volume;

[0060] Get the preset trading signal matching library, which includes:

[0061] A plurality of one-to-one corresponding second feature value sets and trading strategy types;

[0062] Trading strategy types include: low-risk arbitrage strategy, swing trading strategy and medium- and long-term steady growth strategy;

[0063] The first feature value set is matched with each second feature value set in the trading signal matching library to obtain a matching value, wherein:

[0064] Using a similarity algorithm to calculate the matching degree between the first feature value set and the second feature value set;

[0065] The matching value indicates the degree of fit between the trading signal and the preset strategy type;

[0066] According to the matching value, the trading signals are classified into:

[0067] If the matching value is greater than or equal to the preset matching value threshold, the corresponding trading signal is classified as a matching trading strategy type;

[0068] Group trading signals according to matching strategy types to form a preliminary trading signal set;

[0069] Filter the classified trading signals to obtain trading signals of different levels, including:

[0070] Based on the preset screening conditions, the evaluation indicators of each trading signal are further screened;

[0071] The trading signals are divided into three levels: high, medium and low according to their importance and reliability;

[0072] According to the level and strategy type of trading signals, different trading signal combination strategies are formed.

[0073] Among them, the screened trading signals are scored based on the comprehensive scoring model, including:

[0074] Construct a comprehensive scoring model based on multiple scoring dimensions of trading signals, where the scoring dimensions include at least profitability, risk management, and market adaptability;

[0075] The profitability scoring dimensions include parameters of historical earnings and earnings volatility;

[0076] The risk management scoring dimensions include parameters such as maximum drawdown and holding time;

[0077] The market adaptability scoring dimensions include the winning rate of trading signals in different market environments and the parameters of volatility adaptation;

[0078] The scoring module scores each screened trading signal in turn based on the constructed comprehensive scoring model;

[0079] The scoring module performs a weighted comprehensive score on each signal based on the scores of each scoring dimension to generate the final comprehensive score result.

[0080] Among them, users can view the comprehensive scoring details of each trading signal on the interface, including the score of each scoring dimension. Users can adjust the weight of each scoring dimension in the comprehensive scoring model and optimize the scoring criteria based on actual conditions and personal preferences.

[0081] Among them, the trading instructions are generated according to the trading signal combination currently selected by the user, including:

[0082] According to each signal element of the trading signal combination, the corresponding trading strategy is obtained, and the initial trading instruction is generated according to the trading strategy;

[0083] Obtain market information in real time, match the market information with the initial trading instructions, and generate final trading instructions if the market information meets the trading conditions in the initial trading instructions;

[0084] Place orders according to the final transaction instructions and record the order time and related transaction details.

[0085] Among them, the new community copy trading method based on intelligent screening and combination includes:

[0086] S101: Obtain all available trading signals from the target trading platform;

[0087] S102: Classify and screen trading signals according to multi-dimensional evaluation indicators, and build different types of trading signal combination strategies;

[0088] S103: Scoring the filtered trading signals based on the comprehensive scoring model, and filtering out trading signals with scores higher than a preset value and eliminating trading signals with scores lower than the preset value according to the scoring results;

[0089] S104: Based on the personalized demand recommendation model, recommend corresponding trading signal combinations to the user and provide personalized trading signal combination suggestions;

[0090] S105: After the user selects a trading signal combination, the copy order operation is automatically executed, including generating, placing orders, adjusting and closing positions;

[0091] S106: Real-time monitoring of risks in the transaction process, using dynamic stop loss, take profit, and position adjustment strategies to automatically adjust signal combinations and positions to ensure that users can achieve continuous profits on the basis of capital security.

[0092] Compared with the prior art, the present invention has the following advantages:

[0093] The new community copy trading system based on intelligent screening and combination includes: a trading signal acquisition unit, which is used to obtain all available trading signals from the target trading platform; an intelligent screening unit, which is used to classify and screen trading signals according to multi-dimensional evaluation indicators, and build different types of trading signal combination strategies; a comprehensive scoring unit, which is used to score the screened trading signals based on the comprehensive scoring model, and screen out trading signals with scores higher than the preset value according to the scoring results, and eliminate trading signals with scores lower than the preset value; a personalized recommendation unit, which is used to recommend corresponding trading signal combinations to users based on personalized demand recommendation models, and provide personalized trading signal combination suggestions; a copy execution unit, which is used to automatically execute copy operations after the user selects a trading signal combination, including generation, order placement, adjustment and closing positions; a real-time risk monitoring unit, which is used to monitor the risks in the trading process in real time, and automatically adjust the signal combination and position using dynamic stop loss, stop profit and position adjustment strategies to ensure that users achieve continuous profits on the basis of capital security. It is suitable for users who do not have time to watch the market, and can also avoid trading errors caused by human emotional fluctuations.

[0094] Other features and advantages of the present invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the present invention.

[0095] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0096] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0097] Figure 1 This is a structural diagram of a new community copy trading system based on intelligent screening and combination in an embodiment of the present invention;

[0098] Figure 2 This is a structural diagram of an intelligent screening unit in an embodiment of the present invention;

[0099] Figure 3 4 is a structural diagram of a comprehensive scoring unit in an embodiment of the present invention. DETAILED DESCRIPTION

[0100] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0101] The embodiment of the present invention provides a novel community copy trading system based on intelligent screening and combination, including: a trading signal acquisition unit, used to acquire all available trading signals from a target trading platform;

[0102] Intelligent screening unit, used to classify and screen trading signals according to multi-dimensional evaluation indicators, and build different types of trading signal combination strategies;

[0103] A comprehensive scoring unit is used to score the filtered trading signals based on the comprehensive scoring model, and according to the scoring results, filter out the trading signals with scores higher than the preset value, and exclude the trading signals with scores lower than the preset value;

[0104] A personalized recommendation unit is used to recommend corresponding trading signal combinations to users based on a personalized demand recommendation model, and provide personalized trading signal combination suggestions;

[0105] The copy execution unit is used to automatically execute copy operations after the user selects a trading signal combination, including generating, placing orders, adjusting and closing positions;

[0106] The real-time risk monitoring unit is used to monitor the risks in the transaction process in real time, and use dynamic stop loss, take profit, and position adjustment strategies to automatically adjust signal combinations and positions to ensure that users can achieve continuous profits on the basis of capital security.

[0107] The working principle of the above technical solution is as follows: the trading signal acquisition unit will obtain available trading signals from multiple target trading platforms (such as MetaTrader, Binance, etc.). Trading signals refer to information that recommends buying or selling a certain asset at a certain moment. For example, assuming that platform A provides 30 different signals and platform B provides 20 signals, the trading signal acquisition unit will collect these signals into a database for subsequent analysis; the intelligent screening unit uses preset multi-dimensional evaluation indicators (such as volatility, return rate, risk level, etc.) to classify and screen the acquired trading signals. Assuming there are 50 trading signals, signals with high volatility but low return rate will be identified and classified as "high risk and low return", while signals with low volatility but high return rate may be screened as "low risk and high return"; the comprehensive scoring unit will score the screened signals based on a scoring model (such as a weighted scoring algorithm). The scoring model will take into account factors such as return rate and risk control. Assuming that the return rate of trading signal X is 10% and the volatility is 5%, it will score 85 points through the scoring model; the return rate of trading signal Y is 15% and the volatility is 8% , the score is 75 points. In the end, the system will retain the signals with scores higher than the set threshold and remove the signals below the threshold; by analyzing the user's historical trading behavior and preferences, the personalized recommendation unit will recommend a suitable combination of trading signals according to the user's investment style (such as aggressive, conservative). For example, if the user likes low-risk investment, the system may recommend more low-volatility signal combinations; when the user selects a combination of trading signals, the copy execution unit will automatically place an order according to the signal. Assuming that the user selects a combination of 10 signals, the system will automatically generate the corresponding buy and sell orders, and automatically adjust or close the position when the stop loss or take profit point is reached; the real-time risk monitoring unit continuously monitors the risks that may arise during the transaction, such as drastic fluctuations in market prices. By dynamically adjusting the stop loss point, take profit point and position size, the system can ensure that the user's trading strategy is adapted to the current market risk situation. For example, if the risk of a certain trading combination is too high, the system will automatically reduce or close the position to reduce the user's potential losses.

[0108] The beneficial effects of the above technical solution are as follows: the system reduces the workload of users manually analyzing a large number of signals by automatically screening trading signals. Based on the personalized demand recommendation model, users can quickly obtain signal combinations that match their investment style, significantly improving decision-making efficiency; the dynamic stop loss, stop profit and position adjustment functions provided by the real-time risk monitoring unit ensure the safety of funds during the transaction. Even in the case of drastic market fluctuations, users can reduce risks and avoid excessive losses through the automatic adjustment function of the system; the comprehensive scoring unit screens out potential high-yield trading signal combinations based on a multi-dimensional evaluation model, which helps users seize the best investment opportunities. Especially when there are many noise signals in the market, the system helps users eliminate low-quality trading signals and increase the possibility of profit; the copy execution unit realizes fully automated operations from signal selection to order execution, and users do not need to frequently monitor the market, saving time and energy. It is especially suitable for users who do not have time to watch the market, and can also avoid trading errors caused by human emotional fluctuations.

[0109] In another embodiment, the intelligent screening unit comprises:

[0110] The evaluation module is used to analyze trading signals based on multi-dimensional evaluation indicators, including the stability, accuracy, potential rate of return, risk level and market adaptability of trading signals. The multi-dimensional evaluation indicators are quantitatively calculated through a preset algorithm model;

[0111] The classification module is used to classify trading signals according to preset classification standards based on the analysis results of multi-dimensional evaluation indicators and obtain classification results. The classification standards include different risk levels and strategy types. The strategy types include trend tracking strategy, mean reversion strategy and momentum strategy.

[0112] The screening module is used to screen different types of trading signal combination strategies based on the classification results and the user's preset trading strategy preferences, and identify the trading signal combination strategies that match the user's preferences.

[0113] Among them, the multi-dimensional evaluation indicators are quantitatively calculated through the preset algorithm model, including:

[0114] Obtain a preset algorithm model, the algorithm model including a stability calculation model, an accuracy calculation model, a potential rate of return calculation model, a risk level calculation model and a market adaptability calculation model; input the first feature into the algorithm model, and calculate a plurality of first evaluation indicators, wherein:

[0115] The stability calculation model is constructed as:

[0116]

[0117] Among them, S represents stability and σ represents the standard deviation of the return of the trading signal within the preset period.

[0118] The accuracy calculation model is constructed as:

[0119]

[0120] Among them, A represents accuracy, TP is the number of correct signals, and FP is the number of wrong signals;

[0121] The potential rate of return calculation model is constructed as follows:

[0122]

[0123] Where R represents the potential rate of return, ri is the profit of each successful transaction, and n is the total number of transactions;

[0124] The risk level calculation model is constructed as follows:

[0125]

[0126] Among them, L represents the risk level, D represents the maximum drawdown, and C represents the total capital;

[0127] The market adaptability M calculation model is constructed as follows:

[0128]

[0129] Input the first feature into the algorithm model and calculate the evaluation indicators S, A, R, L, and M;

[0130] If the evaluation indicators S, A, R, and M are all greater than or equal to the corresponding preset thresholds, and L is less than the corresponding risk level threshold, the transaction signal is used as the second transaction signal, and at the same time, the second transaction signal is associated with the corresponding evaluation indicator;

[0131] Acquire historical transaction data corresponding to the second transaction signal, and at the same time, acquire the generation time of the second transaction signal;

[0132] Determine, from the historical trading data, a plurality of third trading signals corresponding to the second trading signal and generated within a preset time period before and after the generation time;

[0133] All third trading signals are input into the preset impact analysis model to obtain the affected market index I output by the impact analysis model. At the same time, the risk level associated with the second trading signal is cumulatively calculated to obtain the risk level sum, where:

[0134] The impact analysis model is constructed as:

[0135] I=∑(i×si)

[0136] Among them, I represents the affected market index, i represents the sensitivity of the market index to the signal, and si represents the strength of each signal;

[0137] If the affected market indicator I exceeds the preset threshold and / or risk level and is greater than or equal to the preset first risk level threshold, the trading signal is rejected;

[0138] Otherwise, obtain the preset strategy importance analysis model, determine multiple trading strategies corresponding to the trading signal from the strategy library, input all trading strategies into the importance analysis model, and obtain the importance D output by the importance analysis model, where:

[0139] The importance analysis model is constructed as follows:

[0140] D=∑(wj×pj)

[0141] Among them, D represents the importance, wj represents the weight of each strategy factor, and pj represents the performance indicator of each strategy;

[0142] Obtain a second risk level threshold corresponding to the importance D;

[0143] If the risk level sum is greater than or equal to the second risk level threshold, the trading signal is rejected;

[0144] Otherwise, the trade signal is accepted.

[0145] The working principle of the above technical solution is as follows: the evaluation module is responsible for analyzing each trading signal and performing quantitative evaluation based on evaluation indicators in multiple dimensions. The multi-dimensional evaluation indicators include:

[0146] Stability: Whether the signal has performed consistently over a period of time.

[0147] Accuracy: The success rate of the signal in predicting market movements.

[0148] Potential Rate of Return: The expected return of a signal based on historical data.

[0149] Risk Level: The potential risk that a signal may bring, such as volatility.

[0150] Market adaptability: The signal's ability to adapt to different market environments.

[0151] After the evaluation module completes the multi-dimensional evaluation of the trading signals, the classification module will classify the trading signals into different categories based on the preset classification criteria. The classification criteria include:

[0152] Risk level: For example, signals are classified into high risk, medium risk and low risk.

[0153] Strategy types: such as trend following strategies, mean reversion strategies and momentum strategies.

[0154] Assuming there are 50 trading signals, the classification module will classify 20 of them as "high-risk momentum strategies", 15 as "medium-risk mean reversion strategies", and the remaining signals as "low-risk trend following strategies".

[0155] The screening module combines the user's trading preferences to select trading signal combination strategies that meet the user's preferences from the classification results. The user can set specific trading strategy preferences (such as a mean reversion strategy that tends to be low-risk), and the screening module will automatically identify and recommend signal combination strategies that meet these preferences. For example, if a user prefers a medium-risk strategy with a high potential return rate, the system will automatically select a trading signal combination that matches his or her preferences.

[0156] The beneficial effects of the above technical solution are: through the comprehensive analysis of trading signals by multi-dimensional evaluation indicators, users can not only understand the potential rate of return of the signal, but also consider its stability, accuracy and risk level. This comprehensive analysis provides users with a more accurate basis for market judgment and reduces investment blindness; the classification module classifies signals based on preset risk levels and strategy types, so that users can more clearly understand the characteristics and potential risks of different signals. For example, users can easily choose high-risk momentum strategies or low-risk trend tracking strategies, which facilitates strategy screening and decision-making. The screening module allows users to choose a suitable signal combination according to their trading preferences, which significantly improves the personalized investment experience. Users do not have to manually select from a large number of signals, but the system automatically matches strategies that suit their personal style, saving a lot of time.

[0157] In another embodiment, the comprehensive scoring unit includes:

[0158] A scoring module, used to score the selected trading signals based on a comprehensive scoring model. The comprehensive scoring model includes multiple scoring dimensions. The scoring dimensions include at least profitability, risk management, and market adaptability. The scoring module comprehensively scores each selected trading signal based on the scores of each dimension.

[0159] The screening module is used to screen out trading signals with scores higher than a preset threshold based on the comprehensive scoring results, and to exclude trading signals with scores lower than the preset threshold.

[0160] The working principle of the above technical solution is as follows: the scoring module scores the screened trading signals through a comprehensive scoring model, which is based on multiple dimensions for quantitative evaluation, including: profitability: how profitable the signal is in historical data, risk management: the effectiveness of the signal in controlling risk, such as maximum drawdown or risk-return ratio, market adaptability: the flexibility and adaptability of the signal under different market conditions. The system will aggregate the scores of each dimension into a comprehensive score, usually by weighted average. For example, a signal scores 8 / 10 in profitability and 7 / 10 in risk management, with a comprehensive score of 7.5.

[0161] On the "New Community Copy Trading" platform, users can see the signals shared by other users. The platform evaluates these signals through a scoring module to help novice traders in the community select high-quality signals to copy. The scoring system is similar to a rating website, which scores the multi-dimensional characteristics of each signal and finally comes up with an overall score, allowing users to quickly understand the pros and cons of the signal.

[0162] Based on the comprehensive score of the scoring module, the screening module will screen out trading signals with scores higher than the preset threshold and remove signals below the threshold. For example, if a threshold is set to 6 / 10, any signal with a score higher than 6 will be retained, and signals below this value will be removed. Users can also adjust the screening threshold according to their personal preferences. Users of the new community copy trading platform can set their own copy trading standards, such as only following signals with a score of 7 or above, which can automatically filter out those signals with lower scores and higher risks, ensuring the quality of the copy trading strategy.

[0163] The beneficial effects of the above technical solution are: through the scoring module and the multi-dimensional scoring system, traders can intuitively judge the profit potential and risk level of the signal. The automated calculation of the scoring module reduces the errors of manual analysis, helps users quickly discover high-quality trading signals, and improves the accuracy of copy trading decisions; the screening module can eliminate trading signals that are below the preset scoring threshold and reduce the interference of low-quality signals.

[0164] In another embodiment, recommending a corresponding trading signal combination to a user includes:

[0165] Build a personalized demand recommendation model based on transaction signals;

[0166] The personalized demand recommendation model is used to analyze the user's historical trading style and the signal characteristics of community transactions to generate matching trading signal combination recommendations;

[0167] Determine whether the signal characteristics of community transactions match the user's trading style, including:

[0168] Analyze the user's short-term trading frequency to determine whether the user is a short-term trader or a long-term trader;

[0169] Analyze the user's risk tolerance and determine whether the user prefers high risk and high return or low risk and stable return;

[0170] According to the short-term trading frequency of users, select the trading signal combination with excellent short-term trading performance from community transactions;

[0171] According to the user's risk tolerance, select signal combinations with volatility that meet the user's preferences from community transactions;

[0172] When the selected trading signal combination matches the user's trading style, a corresponding personalized trading signal combination recommendation is generated;

[0173] Output the trading signal combination recommendation to the client terminal logged in to the user account transmitting the trading data;

[0174] Users can directly view the recommended signal combinations and gain a deeper understanding of the recommended strategy combinations through the system’s visual analysis charts;

[0175] Visual analysis charts show the average holding time of trading signal combinations and profit curve data to help users make choices;

[0176] After the user reviews and selects the recommended trading signal combination, the system records the user's selection and feedback.

[0177] The working principle of the above technical solution is: the system first builds a personalized demand recommendation model based on the user's historical trading data and trading signals in the community. This model will analyze the user's past trading behavior, including the timing of buying and selling, trading frequency, holding time, etc. Through machine learning technology, the model can automatically identify the user's trading style, such as whether the user prefers short-term or long-term trading, and high-risk or low-risk investment.

[0178] Short-term or long-term trading style analysis: The system determines the user's trading frequency by counting the time the user holds assets each time. Short-term traders usually hold assets for a shorter period of time, while long-term traders hold them for a longer period of time. Through this analysis, the system can understand the user's trading rhythm. Risk tolerance analysis: By analyzing the asset volatility and returns of the user's past trading records, the user's risk preference is determined. If the user usually chooses highly volatile assets, the system will consider the user to have a higher risk tolerance, and vice versa.

[0179] The system will filter trading signals from the community. Community trading signals are buy and sell suggestions generated by other traders or trading algorithms. The system will filter out those signals that perform well and meet the user's preferences based on the user's trading style. For example, if the user is a short-term trader, the system will give priority to signal combinations that achieve higher returns in a short period of time.

[0180] Once the system passes the user style analysis and community signal screening, it will generate a personalized trading signal combination recommendation for the user. This signal combination will be customized according to the user's trading preferences, including indicators such as average holding time and risk level. Through this recommendation, users can find the trading strategy that best matches their style. Users can directly view the recommended signal combination through the client. The system will generate a series of visual charts, including data such as average holding time, yield curve, risk volatility, etc., to help users gain an in-depth understanding of the performance of each signal combination. This visualization tool not only improves the user's understanding ability, but also helps users make decisions quickly. When the user selects and views the recommended trading signal combination, the system will record the user's selection and feedback. This feedback information will be used for future model optimization to make personalized recommendations more and more in line with the actual needs of users.

[0181] The beneficial effects of the above technical solution are: by analyzing the user's trading habits and community trading signals, the system can provide a customized trading signal combination, which can greatly improve the user's investment efficiency and reduce the time cost of the user's screening of trading strategies; the system can recommend a signal combination that matches risk and return based on the user's risk tolerance. This can not only help users with high risk preferences to obtain higher returns, but also provide more stable returns for users with low risk preferences, meeting the needs of different investors; through visual analysis tools, users can more intuitively understand the historical performance and risk characteristics of each signal combination. This process of information transparency gives users higher confidence in the recommended signal combination and reduces uncertainty in investment decisions.

[0182] In another embodiment, the copy trading operation is automatically performed, including:

[0183] Generate trading instructions based on the current trading signal combination selected by the user;

[0184] Place orders based on the generated trading instructions, track strategy changes within the trading community in real time, and obtain information on changes in each strategy within the community;

[0185] Determine whether the strategy change information triggers the adjustment conditions for the current position. If the adjustment conditions are triggered, automatically generate the position adjustment instruction, and execute the position adjustment instruction to automatically adjust the current position;

[0186] Determine whether the strategy change information triggers the closing conditions. If the closing conditions are triggered, a closing instruction is automatically generated and executed to close the relevant positions;

[0187] Users can view the system's automatic copy execution details, which include the current position status, order time, and executed strategy adjustment information;

[0188] The user sets the manual intervention conditions, including the conditions for early closing of positions when the preset profit target is reached. The system determines whether to generate and execute manual intervention instructions based on the manual intervention conditions set by the user;

[0189] If the manual intervention condition is triggered, the system will automatically generate a manual intervention instruction and execute the manual intervention instruction to control the current position;

[0190] Track strategy changes within the trading community in real time, including:

[0191] Obtain several currently active trading strategies in the community and their corresponding change signals;

[0192] It is determined in turn whether the change signal of each trading strategy is associated with the trading signal combination selected by the user. If there is a correlation, the strategy corresponding to the change signal is marked as a strategy that needs to be adjusted;

[0193] For strategies marked as requiring adjustment, corresponding position adjustment instructions are generated, and the user's current position status is adjusted based on the position adjustment instructions.

[0194] The working principle of the above technical solution is: the user selects multiple trading strategies in the community and combines them into trading signals. For example, the user selects a trend strategy based on moving average crossover and an overbought and oversold strategy based on RSI. These two strategies are combined by the system to generate a buy or sell trading instruction.

[0195] Assuming that the strategy combination selected by the user triggers a moving average crossover signal (buy signal) and an RSI pullback below 30 (oversold signal) in the BTC / USD market, the system will automatically generate a trading order to buy BTC.

[0196] The system places orders based on the generated trading instructions, and at the same time tracks the strategy changes within the trading community in real time to obtain relevant change signals. After the order is placed, the system continues to track the signal changes of the strategies within the community. For example, if a strategy recommends an increase in the stop loss price of BTC, the system will automatically update the trading plan.

[0197] The system determines whether the strategy change triggers the position adjustment conditions. If the BTC quantity or current price held by the user deviates from the strategy setting, the system will automatically generate an instruction to adjust the position. If the strategy indicates that additional positions are required after the BTC price reaches a new high, the system will automatically generate additional buy instructions and execute them.

[0198] When the strategy signal indicates that the position should be closed, the system will generate and execute the closing instruction. When the strategy change shows that BTC has reached the predetermined profit stop point, the system will automatically execute the sell operation and close the BTC position.

[0199] Users can view all automatically executed copy order details in the system, including the current position status, specific order placement time, and strategy adjustment information. For example, users can view the current number of BTC held, when the system adjusted the stop loss point according to the strategy, and the specific selling time through the interface.

[0200] Users can set specific conditions to manually intervene in the system's automatic trading behavior. For example, the user sets a position to be closed early when the profit reaches 5%. The system monitors in real time and performs manual intervention based on this setting.

[0201] The system continuously tracks multiple active strategies in the community and determines which strategies need to be adjusted based on the signal combination selected by the user. If a strategy followed by the user shows that the signal becomes bearish, the system will automatically generate an adjustment instruction and execute the corresponding sell operation.

[0202] The beneficial effects of the above technical solution are as follows: the system can automatically generate and execute trading instructions, reduce delays and errors in human decision-making, ensure the timeliness of trading operations, and users do not need to monitor market changes all the time, and can easily follow orders based on the system; by automatically tracking strategy changes within the community, the system can quickly make position adjustments to prevent users from suffering losses due to sudden market fluctuations. In addition, the system supports users to set manual intervention conditions to achieve more flexible risk control strategies; the system will automatically adjust users' positions according to changes in strategies, help users maintain ideal position allocation, and reduce unnecessary position risks. Especially in a complex market environment, this automatic adjustment mechanism is particularly critical; users can view the details of all automatically executed follow-up transactions to ensure a clear understanding of each operation. The system improves the transparency of the trading process by updating the position status and strategy adjustment information in real time; through the combination of strategy automation and manual intervention, users do not have to make frequent subjective decisions in drastic market fluctuations, which reduces the psychological burden in trading, especially for novice investors.

[0203] In another embodiment, real-time monitoring of risks during a transaction includes:

[0204] Obtain the dynamic position risk level of each risk monitoring zone;

[0205] Determine the position partition that needs to be adjusted based on the position risk level and risk point data of each risk monitoring partition, where the position partition includes the position status of one or more user accounts;

[0206] Determine the target position strategy for each risk monitoring zone;

[0207] If the position risk level of a position partition is higher than the preset risk control target, the position partition will be automatically adjusted or suggestions will be provided to reduce the overall transaction risk;

[0208] Obtain the real-time risk level of each trading unit in the user's position;

[0209] Determine the high-risk trading unit in the position partition according to the risk level of the trading unit and the risk point data triggered by market fluctuations, where the high-risk trading unit includes one or more trading products;

[0210] According to the target position strategy of the position partition, determine the target position of each trading unit in the position partition;

[0211] If the real-time risk level of a trading unit exceeds the preset stop loss or take profit point, the trading unit will be automatically adjusted or suggestions will be provided based on the target position to ensure the safety of the user's position.

[0212] The working principle of the above technical solution is: the system will monitor the risk level of multiple risk monitoring partitions (composed of one or more groups of user positions) in real time, and calculate the dynamic position risk of each partition based on market price fluctuations, trading volume, volatility and other factors. For example: the position accounts of user A and user B are assigned to the same partition, and the system will track the price changes of the stocks, futures and other assets they hold, and update the risk level of the partition in real time.

[0213] The system will analyze the risk points of each partition (such as large market fluctuations, breaking news, economic policy changes) and compare them with the current position risk level to determine which partitions have risk levels exceeding the preset risk control targets. Risk point data: refers to the market volatility trigger conditions set in advance by the system, such as price fluctuations exceeding 5% or abnormal increase in trading volume.

[0214] Each risk zone has a preset target strategy, such as maintaining a certain proportion of cash, reducing the proportion of high-volatility assets, etc. When the risk level of the zone's holdings deviates from the target, the system will trigger corresponding adjustments. Assuming that the target strategy is to limit each user's high-risk assets (such as leveraged products) to less than 20% of the total holdings, if the proportion of leveraged assets in a zone reaches 30%, the system will mark the zone as needing adjustment.

[0215] When the risk level of a position partition exceeds the threshold set by the system, the system will automatically close, reduce or increase hedging operations, or issue suggestions to users to adjust their positions. For example, if user A holds a large number of highly volatile technology stocks and the market fluctuates sharply, the system will reduce some of the technology stocks according to the preset strategy to avoid greater losses.

[0216] The system breaks down the risk of each trading unit (single trading product, such as a stock or futures contract) to ensure that the risk of each product can be more accurately controlled based on the partition monitoring. For example, if user A holds Apple stock, which fluctuates violently, the system will calculate its real-time risk level based on the price changes of the stock.

[0217] Based on market volatility and risk point data, the system determines which trading units (such as a certain stock or futures contract) are too risky and may affect the risk level of the entire partition. If a technology stock's share price drops sharply due to sudden negative news, the system will mark the stock as a high-risk trading unit and trigger further risk management measures.

[0218] The system automatically adjusts the positions of high-risk trading units according to the preset target position strategy (for example, when the market fluctuates violently, the proportion of safe assets held is not less than 30%). If the risk level of a high-risk stock exceeds the preset stop loss point, the system will automatically reduce the holding of part of the stock and adjust the position to the target level.

[0219] The beneficial effects of the above technical solution are: by dynamically monitoring the risk level of each partition and trading unit, the system can issue early warnings and take measures to prevent users' assets from suffering heavy losses under extreme market conditions; the system can automatically adjust positions according to preset target strategies, reducing the complexity of users' manual operations and ensuring timely response during market turmoil; by identifying and adjusting high-risk trading units, users can use funds more efficiently and avoid excessive exposure to high-risk assets, while maintaining stable returns using low-risk assets; the system can not only operate automatically, but also provide adjustment suggestions based on the user's specific circumstances, and users can make final decisions based on their own risk tolerance.

[0220] In another embodiment, identifying a trading signal combination strategy that matches a user's preference includes:

[0221] Perform feature extraction on the first transaction signal to obtain a first feature value set, where:

[0222] Based on a preset first feature extraction template, feature extraction is performed on the signal characteristics of the first transaction signal;

[0223] Signal characteristics include: multi-dimensional evaluation indicators of yield, risk level, volatility, holding time and trading volume;

[0224] Get the preset trading signal matching library, which includes:

[0225] A plurality of one-to-one corresponding second feature value sets and trading strategy types;

[0226] Trading strategy types include: low-risk arbitrage strategy, swing trading strategy and medium- and long-term steady growth strategy;

[0227] The first feature value set is matched with each second feature value set in the trading signal matching library to obtain a matching value, wherein:

[0228] Using a similarity algorithm to calculate the matching degree between the first feature value set and the second feature value set;

[0229] The matching value indicates the degree of fit between the trading signal and the preset strategy type;

[0230] According to the matching value, the trading signals are classified into:

[0231] If the matching value is greater than or equal to the preset matching value threshold, the corresponding trading signal is classified as a matching trading strategy type;

[0232] Group trading signals according to matching strategy types to form a preliminary trading signal set;

[0233] Filter the classified trading signals to obtain trading signals of different levels, including:

[0234] Based on the preset screening conditions, the evaluation indicators of each trading signal are further screened;

[0235] The trading signals are divided into three levels: high, medium and low according to their importance and reliability;

[0236] According to the level and strategy type of trading signals, different trading signal combination strategies are formed, including:

[0237] For trading signals classified as low-risk arbitrage strategies, a low-risk arbitrage strategy portfolio suitable for type A users is formed;

[0238] For trading signals classified as swing trading strategies, a swing trading strategy portfolio suitable for Type B users is formed;

[0239] For trading signals classified as medium- and long-term steady growth strategies, a medium- and long-term steady growth strategy portfolio suitable for type C users is formed.

[0240] The working principle of the above technical solution is as follows: First, feature extraction is performed on the first trading signal. Trading signals usually refer to buying and selling prompts for a certain asset or financial product. These signals need to be extracted from market data through specific algorithms, such as historical stock prices, trading volumes, etc. A preset feature extraction template is used during extraction, which analyzes various characteristics of trading signals, including:

[0241] Rate of return: The potential profit percentage that a trading signal can bring.

[0242] Risk level: The degree of risk associated with a signal, which can be measured by indicators such as volatility.

[0243] Volatility: The range of fluctuations in asset prices over time. The higher the volatility, the greater the risk of the asset.

[0244] Holding time: refers to the time from when the signal is sent to when the transaction is executed and closed.

[0245] Volume: The trading volume of an asset within a specified period of time.

[0246] For example, if the trading signal of a certain stock shows that its return rate in the past week was 3%, its volatility was high, its holding time was short, and its trading volume was large, then its characteristics can be extracted as: high return, high volatility, and short term.

[0247] After extracting the features, the system compares them with the features in the preset trading signal matching library. The matching library stores multiple classified trading strategy types and corresponding feature value sets, such as:

[0248] Low-risk arbitrage strategy: matching signals with low volatility and low risk.

[0249] Swing trading strategy: Match signals with large fluctuations and short-term trading opportunities.

[0250] Medium- to long-term steady growth strategy: matching medium- to long-term investment signals with stable returns and low risks.

[0251] The similarity between the first feature value set and each second feature value set in the matching library is calculated through a similarity algorithm (such as Euclidean distance or cosine similarity). This similarity is the matching value, which indicates the degree of fit between the trading signal and a certain strategy type.

[0252] The system classifies based on the matching value. If the matching value of a trading signal is greater than or equal to the preset threshold, the signal is classified into the corresponding strategy type. For example, if a signal has low volatility, stable returns and a long holding period, the strategy type with the highest matching value may be "medium- and long-term steady growth strategy".

[0253] After completing the initial classification, the system will further screen each trading signal according to the preset screening conditions (such as risk level, yield threshold, etc.), and divide it into three categories: high, medium and low according to importance and reliability.

[0254] According to the signal level and strategy type after screening, the system will combine to form different trading strategies. For example, the combination strategy for low-risk arbitrage signals is suitable for type A users with low risk tolerance.

[0255] A signal combination for swing trading strategies, suitable for Type B users who seek short-term gains.

[0256] The signal combination for the medium- and long-term steady growth strategy is suitable for type C users who invest for the long term and pursue stable growth.

[0257] The beneficial effects of the above technical solution are: through feature extraction and matching algorithms, the system can quickly classify a large number of trading signals into different strategy types, saving users time for manual analysis; classifying different trading signals by strategy type and level, and providing corresponding trading strategy combinations according to users' risk preferences, can help users maximize returns while reducing risks. For example, conservative investors can invest according to the "low-risk arbitrage strategy" provided by the system, while aggressive investors can choose the "band trading strategy" to obtain short-term returns; the system can combine high, medium and low-level signals into different strategy combinations based on the risk level, volatility and other characteristics of each signal, so that investors can choose a suitable investment portfolio based on their own requirements for risk and return, thereby optimizing investment returns.

[0258] In another embodiment, scoring the filtered trading signals based on a comprehensive scoring model includes:

[0259] Construct a comprehensive scoring model based on multiple scoring dimensions of trading signals, where the scoring dimensions include at least profitability, risk management, and market adaptability;

[0260] The profitability scoring dimensions include parameters of historical earnings and earnings volatility;

[0261] The risk management scoring dimensions include parameters such as maximum drawdown and holding time;

[0262] The market adaptability scoring dimensions include the winning rate of trading signals in different market environments and the parameters of volatility adaptation;

[0263] The scoring module scores each screened trading signal in turn based on the constructed comprehensive scoring model;

[0264] The scoring module performs a weighted comprehensive score on each signal based on the scores of each scoring dimension to generate the final comprehensive score result;

[0265] Among them, users can view the comprehensive scoring details of each trading signal on the interface, including the score of each scoring dimension. Users can adjust the weight of each scoring dimension in the comprehensive scoring model and optimize the scoring criteria based on actual conditions and personal preferences.

[0266] The working principle of the above technical solution is as follows: according to the performance of the trading signal, the scoring dimension is divided into three main aspects: profitability, risk management and market adaptability. Each dimension contains specific parameters to quantify the performance of the signal. The profitability scoring dimension includes two parameters: historical profit and profit volatility; historical profit: quantify its profitability by calculating the cumulative profit of the signal over a period of time. Profit volatility: evaluate its stability by calculating the change in profit of each transaction. Risk management scoring dimension: includes two parameters: maximum retracement and holding time. Maximum retracement: refers to the loss amplitude of the signal from the highest point to the lowest point, reflecting the risk resistance of the signal. Holding time: measures the length of the signal holding time and evaluates its control over risk exposure. Market adaptability scoring dimension: includes the winning rate and volatility adaptation in different market environments. Winning rate in different market environments: evaluates the performance of the signal in different market environments such as volatile market, bull market or bear market. Volatility adaptation: examines whether the signal can operate stably under different market volatilities.

[0267] Score each filtered trading signal using the above scoring dimensions and parameters. The specific steps are as follows:

[0268] First, the system calculates the values ​​of each parameter in each scoring dimension based on the historical data of each trading signal. Taking trading signal A as an example, the system will calculate its cumulative return, profit volatility, maximum drawdown and win rate in the past 12 months. Then, the system assigns a specific score to each parameter. For example, the historical profit of signal A is 20%, and the signal gets 80 points in the profitability scoring dimension. Then, the system weights the scores of each scoring dimension into a comprehensive score and generates a total score. Assuming that the user selects a profitability weight of 50%, a risk management weight of 30%, and a market adaptability weight of 20%, the final comprehensive score of signal A will be calculated based on the scores and weights of these three dimensions.

[0269] In the scoring module, users can view the detailed scores of each trading signal, including the scores of each scoring dimension (for example, the profitability score of signal A is 80, the risk management score is 75, and the market adaptability score is 85). At the same time, users can adjust the weight of each scoring dimension on the interface according to their preferences. For example, if the user attaches more importance to risk management, the weight of the risk management dimension can be increased to 50%, thereby optimizing the overall scoring criteria.

[0270] The beneficial effects of the above technical solution are: by incorporating profitability, risk management, market adaptability and other dimensions into the scoring model, a more comprehensive evaluation of trading signals can be performed. Unlike the evaluation of a single dimension, this method can help users better understand the advantages and disadvantages of trading signals; users can flexibly adjust the scoring weights according to their investment preferences, thereby generating signal recommendations that better meet personal needs. For example, risk-averse users can focus more on the risk management dimension, while aggressive users can pay more attention to the profitability dimension. This flexibility enables the model to adapt to the needs of different investors and enhance the practical application value of the signal; users can view the scoring details of each trading signal and clearly know the score of each dimension and the logic behind it. This transparent design enables users to better understand the scoring process and avoid blindly relying on the scoring results; through the comprehensive scoring model, users can quickly screen out the signals that best meet their personal investment strategies from a large number of trading signals, thereby effectively improving the efficiency and accuracy of trading decisions.

[0271] In another embodiment, generating a trading instruction according to the trading signal combination currently selected by the user includes:

[0272] According to each signal element of the trading signal combination, the corresponding trading strategy is obtained, and the initial trading instruction is generated according to the trading strategy;

[0273] Obtain market information in real time, match the market information with the initial trading instructions, and generate final trading instructions if the market information meets the trading conditions in the initial trading instructions;

[0274] Place orders according to the final transaction instructions and record the order time and related transaction details.

[0275] The working principle of the above technical solution is: first, the system extracts each signal element from multiple trading signal combinations, and generates corresponding trading strategies based on the historical performance of these signals and the set rules.

[0276] Trading signal combination: refers to a combination of multiple trading signals, including trend signals, reversal signals, momentum signals, etc. For example, a combination may include signals such as 50-day moving average breakthrough and RSI overbought.

[0277] Trading strategy: Specific trading rules set based on trading signals, for example, buy when the price breaks through the 50-day moving average and the RSI is below 30.

[0278] The system will generate initial trading instructions based on the trading strategy, which will specify when to execute buy or sell operations.

[0279] Assume that a trading signal combination includes a trend signal (50-day moving average) and a momentum signal (RSI). The trading strategy stipulates that if the stock price breaks through the 50-day moving average and the RSI indicator is below 30, a buy order is generated. At this time, the system generates an initial trading order, which clearly states that the stock will be bought only when both conditions are met.

[0280] The system monitors market information in real time, including key data such as price, volume, volatility, etc., and matches this data with the conditions in the initial trading instructions.

[0281] Real-time market information: refers to the market data obtained in real time through the trading platform, such as real-time stock prices, technical indicators, etc.

[0282] Matching trading conditions: refers to the system comparing the current market data with the conditions in the initial trading instructions. If the conditions are met, further actions are triggered.

[0283] Assuming that the current stock price breaks through the 50-day moving average and the RSI index falls below 30, the market data matches the buy conditions of the initial trading instruction. At this time, the system will generate the final trading instruction, which is to buy the stock.

[0284] Once the market information fully matches the conditions in the initial trading instructions, the system will generate a final trading instruction. This instruction contains specific operation content, such as buy or sell, transaction volume, execution price, etc. Final trading instruction: refers to the execution instruction generated after market conditions are verified, which clarifies the specific trading operation. The system automatically places orders according to the final trading instructions and records the specific time and transaction details of the order.

[0285] If the above buying conditions are met, the system generates a final buy instruction, instructing the platform to buy 100 shares of the stock. At this time, the system automatically executes the order operation and records the transaction details such as the time, price and number of stocks purchased.

[0286] The beneficial effects of the above technical solution are: the system automatically generates trading instructions and matches them with real-time market conditions. The entire process does not require human intervention, which greatly improves the efficiency and accuracy of transactions. The automated trading system can respond quickly when the market changes rapidly, capture trading opportunities, and reduce the risk of missing opportunities; the system ensures that trading strategies are strictly executed according to preset conditions, avoiding subjective bias or emotional interference in manual execution. For example, when the market fluctuates violently, automated trading can accurately execute the take-profit or stop-loss instructions in the strategy to help users avoid risks or lock in profits; the system monitors the market in real time and generates the final trading instructions immediately when the conditions are met. Such real-time response capabilities can seize the opportunity when the market changes rapidly and ensure that trading instructions are executed at the best time; the automated trading process reduces the risks caused by human errors (such as transaction delays or wrong orders). Since the execution of trading conditions and instructions is fully automated, users do not need to worry about operational errors in high-frequency trading or short time windows.

[0287] In another embodiment, a novel community copy trading method based on intelligent screening and combination is characterized by including:

[0288] S101: Obtain all available trading signals from the target trading platform;

[0289] S102: Classify and screen trading signals according to multi-dimensional evaluation indicators, and build different types of trading signal combination strategies;

[0290] S103: Scoring the filtered trading signals based on the comprehensive scoring model, and filtering out trading signals with scores higher than a preset value and eliminating trading signals with scores lower than the preset value according to the scoring results;

[0291] S104: Based on the personalized demand recommendation model, recommend corresponding trading signal combinations to the user and provide personalized trading signal combination suggestions;

[0292] S105: After the user selects a trading signal combination, the copy order operation is automatically executed, including generating, placing orders, adjusting and closing positions;

[0293] S106: Real-time monitoring of risks in the transaction process, using dynamic stop loss, take profit, and position adjustment strategies to automatically adjust signal combinations and positions to ensure that users can achieve continuous profits on the basis of capital security.

[0294] The working principle of the above technical solution is as follows: Step S102 includes:

[0295] S1021: Analyze the trading signal according to multi-dimensional evaluation indicators, which include stability, accuracy, potential rate of return, risk level and market adaptability of the trading signal. The multi-dimensional evaluation indicators are quantitatively calculated through a preset algorithm model;

[0296] S1022: Based on the analysis results of the multi-dimensional evaluation indicators, the trading signals are classified according to preset classification standards to obtain classification results. The classification standards include different risk levels and strategy types. The strategy types include trend tracking strategies, mean reversion strategies, and momentum strategies.

[0297] S1023: Based on the classification results and the user's preset trading strategy preferences, different types of trading signal combination strategies are screened to identify the trading signal combination strategies that match the user's preferences.

[0298] Step S103 includes:

[0299] S1031: Scoring the selected trading signals based on a comprehensive scoring model, where the comprehensive scoring model includes multiple scoring dimensions, and the scoring dimensions include at least profitability, risk management, and market adaptability. The scoring module comprehensively scores each selected trading signal based on the scores of each dimension;

[0300] S1032: Filter out trading signals with scores higher than a preset threshold value based on the comprehensive scoring result, and eliminate trading signals with scores lower than the preset threshold value.

[0301] The beneficial effects of the above technical solution are: not only does it improve transaction efficiency and accuracy, but it also ensures that users can trade safely and efficiently in an automated environment through personalized recommendations and dynamic risk management. The system's automated execution and intelligent recommendations greatly reduce the user's operational burden, improve user experience and transaction returns, and reduce the risks brought by market fluctuations.

[0302] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A new community copy trading system based on intelligent screening and combination, characterized by: include: A trading signal acquisition unit, used for acquiring all available trading signals from a target trading platform; Intelligent screening unit, used to classify and screen trading signals according to multi-dimensional evaluation indicators, and build different types of trading signal combination strategies; A comprehensive scoring unit is used to score the filtered trading signals based on the comprehensive scoring model, and according to the scoring results, filter out the trading signals with scores higher than the preset value, and exclude the trading signals with scores lower than the preset value; A personalized recommendation unit is used to recommend corresponding trading signal combinations to users based on a personalized demand recommendation model, and provide personalized trading signal combination suggestions; The copy execution unit is used to automatically execute copy operations after the user selects a trading signal combination, including generating, placing orders, adjusting and closing positions; The real-time risk monitoring unit is used to monitor the risks in the transaction process in real time, and use dynamic stop loss, take profit, and position adjustment strategies to automatically adjust signal combinations and positions to ensure that users can achieve continuous profits on the basis of capital security.

2. The novel community copy trading system based on intelligent screening and combination according to claim 1 is characterized in that: The intelligent screening unit includes: The evaluation module is used to analyze trading signals based on multi-dimensional evaluation indicators, including the stability, accuracy, potential rate of return, risk level and market adaptability of trading signals. The multi-dimensional evaluation indicators are quantitatively calculated through a preset algorithm model; The classification module is used to classify trading signals according to preset classification standards based on the analysis results of multi-dimensional evaluation indicators and obtain classification results. The classification standards include different risk levels and strategy types. The strategy types include trend tracking strategy, mean reversion strategy and momentum strategy. The screening module is used to screen different types of trading signal combination strategies based on the classification results and the user's preset trading strategy preferences, and identify the trading signal combination strategies that match the user's preferences.

3. The novel community copy trading system based on intelligent screening and combination according to claim 1 is characterized in that: The comprehensive scoring units include: A scoring module, used to score the selected trading signals based on a comprehensive scoring model. The comprehensive scoring model includes multiple scoring dimensions. The scoring dimensions include at least profitability, risk management, and market adaptability. The scoring module comprehensively scores each selected trading signal based on the scores of each dimension. The screening module is used to screen out trading signals with scores higher than a preset threshold based on the comprehensive scoring results, and to exclude trading signals with scores lower than the preset threshold.

4. The novel community documentary trading system based on intelligent screening and combination according to claim 1 is characterized in that: Recommend corresponding trading signal combinations to users, including: Build a personalized demand recommendation model based on transaction signals; The personalized demand recommendation model is used to analyze the user's historical trading style and the signal characteristics of community transactions to generate matching trading signal combination recommendations; Determine whether the signal characteristics of community transactions match the user's trading style, including: Analyze the user's short-term trading frequency to determine whether the user is a short-term trader or a long-term trader; Analyze the user's risk tolerance and determine whether the user prefers high risk and high return or low risk and stable return; According to the short-term trading frequency of users, select the trading signal combination with excellent short-term trading performance from community transactions; According to the user's risk tolerance, select signal combinations with volatility that meet the user's preferences from community transactions; When the selected trading signal combination matches the user's trading style, a corresponding personalized trading signal combination recommendation is generated; Output the trading signal combination recommendation to the client terminal logged in to the user account transmitting the trading data; Users can directly view the recommended signal combinations and gain an in-depth understanding of the recommended strategy combinations through the system’s visual analysis charts; Visual analysis charts show the average holding time of trading signal combinations and profit curve data to help users make choices; After the user reviews and selects the recommended trading signal combination, the system records the user's selection and feedback.

5. The novel community documentary trading system based on intelligent screening and combination according to claim 1 is characterized in that: Automatically execute copy operations, including: Generate trading instructions based on the current trading signal combination selected by the user; Place orders based on the generated trading instructions, track strategy changes within the trading community in real time, and obtain information on changes in each strategy within the community; Determine whether the strategy change information triggers the adjustment conditions for the current position. If the adjustment conditions are triggered, automatically generate the position adjustment instruction, and execute the position adjustment instruction to automatically adjust the current position; Determine whether the strategy change information triggers the closing conditions. If the closing conditions are triggered, a closing instruction is automatically generated and executed to close the relevant positions; Users can view the system's automatic copy execution details, which include the current position status, order time, and executed strategy adjustment information; The user sets the manual intervention conditions, including the conditions for early closing of positions when the preset profit target is reached. The system determines whether to generate and execute manual intervention instructions based on the manual intervention conditions set by the user; If the manual intervention condition is triggered, the system will automatically generate a manual intervention instruction and execute the manual intervention instruction to control the current position; Track strategy changes within the trading community in real time, including: Obtain several currently active trading strategies in the community and their corresponding change signals; It is determined in turn whether the change signal of each trading strategy is associated with the trading signal combination selected by the user. If there is a correlation, the strategy corresponding to the change signal is marked as a strategy that needs to be adjusted; For strategies marked as requiring adjustment, corresponding position adjustment instructions are generated, and the user's current position status is adjusted based on the position adjustment instructions.

6. The novel community copy trading system based on intelligent screening and combination according to claim 1 is characterized in that: Real-time monitoring of risks during transactions, including: Obtain the dynamic position risk level of each risk monitoring zone; Determine the position partition that needs to be adjusted based on the position risk level and risk point data of each risk monitoring partition, where the position partition includes the position status of one or more user accounts; Determine the target position strategy for each risk monitoring zone; If the position risk level of a position partition is higher than the preset risk control target, the position partition will be automatically adjusted or suggestions will be provided to reduce the overall transaction risk; Obtain the real-time risk level of each trading unit in the user's position; Determine the high-risk trading unit in the position partition according to the risk level of the trading unit and the risk point data triggered by market fluctuations, where the high-risk trading unit includes one or more trading products; According to the target position strategy of the position partition, determine the target position of each trading unit in the position partition; If the real-time risk level of a trading unit exceeds the preset stop loss or take profit point, the trading unit will be automatically adjusted or suggestions will be provided based on the target position to ensure the safety of the user's position.

7. The novel community documentary trading system based on intelligent screening and combination according to claim 2 is characterized in that: Identify trading signal combination strategies that match user preferences, including: Perform feature extraction on the first transaction signal to obtain a first feature value set, where: Based on a preset first feature extraction template, feature extraction is performed on the signal characteristics of the first transaction signal; Signal characteristics include: multi-dimensional evaluation indicators of yield, risk level, volatility, holding time and trading volume; Get the preset trading signal matching library, which includes: A plurality of one-to-one corresponding second feature value sets and trading strategy types; Trading strategy types include: low-risk arbitrage strategy, swing trading strategy and medium- and long-term steady growth strategy; The first feature value set is matched with each second feature value set in the trading signal matching library to obtain a matching value, wherein: Using a similarity algorithm to calculate the matching degree between the first feature value set and the second feature value set; The matching value indicates the degree of fit between the trading signal and the preset strategy type; According to the matching value, the trading signals are classified into: If the matching value is greater than or equal to the preset matching value threshold, the corresponding trading signal is classified as a matching trading strategy type; Group trading signals according to matching strategy types to form a preliminary trading signal set; Filter the classified trading signals to obtain trading signals of different levels, including: Based on the preset screening conditions, the evaluation indicators of each trading signal are further screened; The trading signals are divided into three levels: high, medium and low according to their importance and reliability; According to the level and strategy type of trading signals, different trading signal combination strategies are formed.

8. The novel community documentary trading system based on intelligent screening and combination according to claim 3 is characterized in that: Scoring of screened trading signals based on a comprehensive scoring model, including: Construct a comprehensive scoring model based on multiple scoring dimensions of trading signals, where the scoring dimensions include at least profitability, risk management, and market adaptability; The profitability scoring dimensions include parameters of historical earnings and earnings volatility; The risk management scoring dimensions include parameters such as maximum drawdown and holding time; The market adaptability scoring dimensions include the winning rate of trading signals in different market environments and the parameters of volatility adaptation; The scoring module scores each screened trading signal in turn based on the constructed comprehensive scoring model; The scoring module performs a weighted comprehensive score on each signal based on the scores of each scoring dimension to generate the final comprehensive score result; Among them, users can view the comprehensive scoring details of each trading signal on the interface, including the score of each scoring dimension. Users can adjust the weight of each scoring dimension in the comprehensive scoring model and optimize the scoring criteria based on actual conditions and personal preferences.

9. The novel community documentary trading system based on intelligent screening and combination according to claim 5 is characterized in that: Generate trading instructions based on the current user-selected trading signal combination, including: According to each signal element of the trading signal combination, the corresponding trading strategy is obtained, and the initial trading instruction is generated according to the trading strategy; Obtain market information in real time, match the market information with the initial trading instructions, and generate final trading instructions if the market information meets the trading conditions in the initial trading instructions; Place orders according to the final transaction instructions and record the order time and related transaction details.

10. A new community copy trading method based on intelligent screening and combination, characterized in that: include: S101: Obtain all available trading signals from the target trading platform; S102: Classify and screen trading signals according to multi-dimensional evaluation indicators, and build different types of trading signal combination strategies; S103: Scoring the filtered trading signals based on the comprehensive scoring model, and filtering out trading signals with scores higher than a preset value and eliminating trading signals with scores lower than the preset value according to the scoring results; S104: Based on the personalized demand recommendation model, recommend corresponding trading signal combinations to the user and provide personalized trading signal combination suggestions; S105: After the user selects a trading signal combination, the copy order operation is automatically executed, including generating, placing orders, adjusting and closing positions; S106: Real-time monitoring of risks in the transaction process, using dynamic stop loss, take profit, and position adjustment strategies to automatically adjust signal combinations and positions to ensure that users can achieve continuous profits on the basis of capital security.

Images