Quantitative transaction method and system fusing multi-source information data

Abstract

The invention discloses a quantitative transaction method and system fusing multi-source information data, and the method comprises the following steps: receiving the multi-source information data in a quantitative transaction strategy, the multi-source information data at least comprising structured data (such as opening price, transaction volume and the like) and unstructured data (such as economic indexes, news texts and the like); performing data preprocessing, feature extraction and feature fusion on the multi-source information data, and generating a quantitative transaction strategy model; historical multi-source information data is acquired, the quantitative transaction strategy model is used for back test evaluation, and a back test result is generated; and judging whether to execute a strategy transaction according to a back test result, obtaining real-time multi-source information data to simulate an actual transaction or an actual transaction, and generating a transaction result. According to the invention, an integrated system of collection and processing of multi-source information data, strategy construction, back testing and transaction is realized, and the accuracy of a prediction model and the execution efficiency of the system are improved.

Description

Technical Field

[0001] The present invention relates to the fields of artificial intelligence and computer software, and in particular to a quantitative trading method and system that integrates multi-source information data. Background Art

[0002] Financial markets widely consider technical analysis variables as core features of stock price forecasting. These variables provide important support for the prediction of future price trends by analyzing historical price and volume data. Technical analysis methods are widely used in stock market forecasting models, such as those based on the Wave Principle, Dow Theory, and Chaos Theory. These methods analyze the changing patterns of prices and volumes, identify trend reversals and support and resistance levels, and provide a basis for investment decisions. At the same time, technical indicators such as momentum and relative strength index (RSI) provide effective reference for price forecasting by quantifying key changes in historical data.

[0003] Fundamental analysis also plays an important role in value assessment. By analyzing financial statements, macroeconomic indicators and industry dynamics, investors can evaluate the intrinsic value of assets and use tools such as the capital asset pricing model (CAPM) to weigh risks and expected returns and formulate strategies. In recent years, the development of deep learning has promoted the combination of technical analysis with other data sources, such as financial news, social media information and online search behavior. Although these external variables enrich the data dimensions, research shows that a high prediction accuracy can be achieved using technical analysis data alone, and the introduction of additional data variables has not significantly improved the accuracy, which highlights the core role and advantages of technical analysis data in building efficient prediction models.

[0004] The core innovation of this invention lies in the fusion of multi-source information data, proposing a quantitative trading method that combines sentiment analysis and technical analysis, and effectively integrating it into the quantitative trading system. Unlike the traditional method of processing technical analysis and sentiment analysis separately, this invention adopts feature fusion technology to combine sentiment features based on unstructured data with technical indicator trading signals based on structured data to construct a comprehensive prediction model. This fusion method not only overcomes the limitations of single data source analysis methods in capturing multi-dimensional market information, but also significantly improves prediction accuracy and the reliability of investment decisions.

[0005] Through systematic multi-source information data fusion, the present invention further enhances the model's ability to process complex market data, thereby optimizing the execution efficiency of trading strategies. Experimental results show that compared with traditional single data source analysis methods, the prediction model based on multi-source information fusion can more accurately capture market trends and significantly improve the feasibility and trading benefits in practical applications. Summary of the invention

[0006] The present invention provides a quantitative trading method that integrates multi-source information data to improve the accuracy of quantitative trading systems in strategy prediction and the performance of returns in actual transactions. The method includes: receiving multi-source information data in a quantitative trading strategy, wherein the multi-source information data at least includes: structured data (such as opening price, trading volume, etc.) and unstructured data (such as economic indicators, news text, etc.); performing data preprocessing, feature extraction and feature fusion on the multi-source information data, and generating a quantitative trading strategy model; obtaining historical multi-source information data, using the quantitative trading strategy model for backtesting evaluation, and generating backtesting results; judging whether to execute strategy trading based on the backtesting results, obtaining real-time multi-source information data to simulate actual trading or actual trading, and generating trading results.

[0007] In the process of receiving multi-source information data of the quantitative trading method, the present invention provides a variety of data interfaces to support the acquisition of structured and unstructured data from multiple data sources. Real-time data such as structured data (such as opening price, trading volume, etc.) is obtained through the exchange interface; unstructured data (such as news text, economic indicators, etc.) is obtained through the data packet interface. Historical data can be downloaded through the data interface or uploaded directly by the user. All collected or uploaded data are finally stored in the system database to ensure the integrity and availability of the data.

[0008] When processing multi-source information data, the present invention constructs a quantitative trading strategy model through data preprocessing, feature extraction and feature fusion. Structured data analyzes market trends through technical indicators, while unstructured data performs sentiment analysis by calling a large model interface to extract market sentiment features. Through feature fusion methods such as splicing, addition and multiplication, the system can effectively integrate structured and unstructured data, improve the prediction accuracy of the strategy model, and thus optimize the decision-making process of quantitative trading.

[0009] The present invention also provides a quantitative trading system integrating multi-source information data, aiming to improve the prediction accuracy and trading profit efficiency of the quantitative trading system. The system includes:

[0010] The core engine includes the main engine and the event engine. The main engine is responsible for coordinating and managing the overall process of the system, supporting the initialization and operation of different modules such as data management, backtesting, and trading; the event engine monitors events in the system in real time and triggers corresponding operations through event priority queues and loop processing mechanisms, and combines data flow and event-driven logic to achieve efficient closed-loop management of strategy signal generation, data update, and transaction instruction execution, ensuring the real-time and reliability of system response.

[0011] The service module includes business module, core module and interface module. The business module integrates modules such as data management, strategy generation, backtesting and transaction execution, and supports the whole process of quantitative trading strategy; the core module is the core execution unit of the system, responsible for performing specific operations according to the requirements of the functional module; the interface module contains multiple sub-modules: the exchange interface realizes the interaction with external exchanges, supports efficient market data reception, transaction instruction transmission and status feedback; the data packet interface connects multiple data providers through standardized APIs to download historical market data, financial reports and news data; the large model interface can efficiently convert text data into structured data, and realize efficient integration and management of diversified data.

[0012] Display visual settings interface: This interface provides an interactive bridge between users and the system. Users can input configuration information through the interface, and the system will intuitively feedback the results on the interface. The main interface supports connecting different exchange interfaces and data packet interfaces to realize buying and selling operations and real-time market data acquisition; the data packet interface also supports receiving unstructured data such as market data, financial report data and news data. The backtesting interface can set multi-source data and backtesting parameters, support historical verification of strategies, and intuitively present backtesting results; the strategy interface allows users to configure data sources and strategy running time, select actual transactions or simulated transactions, and provide real-time feedback on execution results.

[0013] The present invention expands the functions that quantitative trading should have in the business module of the quantitative trading system to improve the prediction accuracy and trading profit efficiency of the quantitative trading system. The functional module includes: a data management module for receiving, storing and processing multi-source information from different data sources to ensure the validity and timeliness of the data; a strategy module for building a prediction model based on defined data features, generating trading signals and implementing trading risk management; a backtesting module for backtesting quantitative trading strategies using historical multi-source information data to evaluate the performance and effect of the strategy; a trading module for performing simulated trading or actual trading operations based on the backtesting results using real-time multi-source information data, and updating the trading status in real time.

[0014] This invention successfully improves the construction and execution efficiency of quantitative trading strategies through the deep integration of multi-source information data and the application of feature engineering. By introducing event-driven mechanisms and efficient backtesting algorithms, it not only lowers the technical threshold, but also significantly improves the prediction accuracy of the strategy and the benefits of actual transactions. Ultimately, while processing complex market information, the system achieves more accurate predictions, has broad application potential, and can provide strong support for investors in the financial market. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0016] Figure 1 It is a business process diagram of a quantitative trading method and system that integrates multi-source information data;

[0017] Figure 2 It is a brief flowchart of the quantitative trading method that integrates multi-source information data;

[0018] Figure 3 It is a model construction flow chart of the quantitative trading method that integrates multi-source information data;

[0019] Figure 4 It is a diagram of the architecture of a quantitative trading system that integrates multi-source information data;

[0020] Figure 5 It is a schematic diagram of a quantitative trading system that integrates multi-source information data;

[0021] Figure 6 A schematic diagram of the main interface of a quantitative trading system provided in an embodiment of the present invention;

[0022] Figure 7 A schematic diagram of a backtesting interface of a quantitative trading system provided in an embodiment of the present invention;

[0023] Figure 8 A schematic diagram of a strategy interface of a quantitative trading system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0024] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0025] The embodiment of the present invention provides a quantitative trading method integrating multi-source information data, such as Figure 1As shown. The system receives and parses data through the data packet interface and the exchange interface. Structured data includes opening price, lowest price, highest price, trading volume, historical volatility, etc.; unstructured data includes news text, social media sentiment, etc. The system uses feature engineering to fuse the above data, generate high-dimensional feature vectors for strategy prediction, and build trading logic based on historical data and real-time data. According to the quantitative trading strategy, perform backtesting operations to obtain backtesting results; determine whether to perform simulated trading based on the backtesting results. If you want to perform simulated trading, set the simulation running time, control the quantitative trading strategy to perform simulated trading operations, and obtain simulated trading results; determine whether to perform actual trading based on the backtesting results. If you want to perform actual trading, control the quantitative trading strategy to perform actual trading operations and obtain actual trading results.

[0026] Based on the same inventive concept, an embodiment of the present invention proposes a quantitative trading method combining multi-source information data processing. Figure 2 The flowchart of the method is shown, and the specific steps are as follows:

[0027] S201, receiving multi-source information data in a quantitative trading strategy, wherein the multi-source information data at least includes: structured data (such as opening price, trading volume, etc.) and unstructured data (such as economic indicators, news text, etc.).

[0028] Data collection is carried out through user-friendly visualization tools. Users can obtain historical data from the system data package interface or upload data to the system's data management module. Historical data backtesting is based on historical market data provided from the data package interface; simulated real-time trading and real-time trading use real-time market data, where structured data is obtained through the exchange interface and unstructured data is obtained through the data package interface.

[0029] Since unstructured data includes but is not limited to economic indicators, industry analysis reports, macroeconomic data, company financial reports, news texts, etc. Therefore, in an optional embodiment, the data packet interface provided by the embodiment of the present invention may also include: Tushare, Jukuan, IB Yingtou, Wind, etc. All collected or user-uploaded data is ultimately stored in the SQLite database for unified management and quick call.

[0030] S202, performing data preprocessing, feature extraction and feature fusion on the multi-source information data, and generating a quantitative trading strategy model.

[0031] Specifically, structured data analyzes future price trends through technical indicators. Data can be obtained by downloading historical market data from the data provider API interface, or by directly uploading data to the system's SQLite database, and obtaining other structured data features through technical indicator formulas. The most commonly used technical indicators in the market are MACD, KDJ and Bollinger Bands (BOLL).

[0032] Unstructured data uses large models and prompt words called within the system to extract text sentiment for evaluating market signals.

[0033] The above prompt is: Forget all your previous instructions. Assume that you are a financial expert with experience in stock recommendations. Based on the following text, is this text good or bad for the stock price of company name in the short term? If it is good news, answer "yes"; if it is bad news, answer "no"; if the first line is uncertain, answer "unknown".

[0034] In the process of sentiment analysis of unstructured data, the system inputs the text into the model API, calls the big model, and extracts the sentiment features that affect the stock price through the model. The specific operation is as follows: Assume that the model analyzes the input text, generates a forecast result for the target company's stock price, and determines the impact of the text on the short-term stock price. The system outputs "yes" for positive impact, recorded as the number 2; "no" for negative impact, recorded as the number 1; "unknown" for uncertainty, recorded as the number 0.

[0035] Based on the feature sequences generated from structured and unstructured data, the embodiments of the present invention provide several feature fusion methods: splicing: directly splicing different features together to form a new fused feature; adding: adding multiple feature maps element by element to obtain the feature average value, thereby reducing the impact of noise; multiplying: multiplying multiple feature maps element by element to enhance the semantic information of the feature and retain the details.

[0036] In order to further refine the construction process of the strategy model, the specific process is as follows Figure 3 As shown:

[0037] Obtain unstructured data, such as economic indicators, news texts and other text data, and use the big model to perform sentiment polarity analysis by calling the big model API interface deployed in the system to obtain the sentiment feature sequence; at the same time, the obtained structured data (such as closing price, opening price, trading volume, etc.) is used to calculate the corresponding feature sequence by calling the corresponding technical indicator module; then, the sentiment feature sequence and the technical indicator feature sequence are spliced ​​to construct new feature data; finally, the integrated feature sequence is analyzed to build a stock price prediction model.

[0038] In addition, due to the variety of unstructured and structured data, users need to select the required data in the specified strategy interface to ensure the normal call of data and the smooth progress of subsequent model building operations.

[0039] S203, obtain historical multi-source information data, use the quantitative trading strategy model to perform backtest evaluation, and generate backtest results. The specific steps include: according to the set backtest time period, obtain the corresponding market data from the SQLite database, input it into the quantitative trading strategy model in S202 through the message queue one by one, and finally obtain the backtest results.

[0040] S204, judging whether to execute the strategy transaction according to the backtesting result, obtaining real-time multi-source information data to simulate actual transactions or actual transactions, and generating transaction results.

[0041] Specifically, after the backtest results meet the user's requirements, the system starts the simulated trading module and obtains market data from the exchange in real time to input quantitative trading strategies. During the simulated trading process, non-daily data (such as data from the previous two days) is used to simulate the actual trading process, but actual fund operations are not involved. The system monitors the simulated trading status according to the preset strategy running time, and automatically stops trading when the set deadline is reached, generating simulated trading results.

[0042] After the backtest results and simulated trading results meet the user's requirements, the system starts the actual trading function. Considering the randomness of market data, even if the backtest and simulated trading results meet the conditions, actual trading may still be risky. Therefore, the actual trading results will be transmitted to the visual interface in real time for users to decide whether to continue or stop trading.

[0043] As can be seen from the above, the quantitative trading method that integrates multi-source information data provided by the embodiment of the present invention can realize historical backtesting, simulated trading and actual trading of the strategy. The method can quickly verify whether the test results meet the conditions and ensure that the strategy runs normally in actual trading, thereby improving the prediction accuracy and significantly improving the rate of return of actual trading.

[0044] Based on the same inventive concept, an optional system architecture diagram of a quantitative trading system based on multi-source information data provided in an embodiment of the present invention is as follows: Figure 4 The quantitative trading system consists of three parts: front-end, strategy construction layer and strategy operation layer. The data flow is referenced as follows: Figure 4 Number in:

[0045] Step 1: The user configures parameters such as data type, feature fusion method and function selection in the front-end interface; Step 2: Send the configuration information into the system and call the API to obtain the configured multi-source information data; Step 3: Send the obtained data to the strategy construction layer, and perform feature processing on structured and unstructured data according to the configured processing method. Structured data is used to calculate the characteristics of technical indicators, and unstructured data is sent to the large model for sentiment analysis, and finally a unified data set is generated through feature fusion; Step 4: The system uses the generated data set to build a model in the strategy generation module, and designs trading logic and risk control conditions based on the model prediction value; Step 5: After the strategy is built, the strategy operation layer calls the corresponding function module in the strategy startup configuration information to perform backtesting, simulated trading or actual trading; Step 6: After the function is run, the system transmits the results to the strategy evaluation and visualization module to calculate the final results; Step 7: The final results are displayed on the front-end interface. When executing simulated trading and actual trading, the interface displays the transaction results, key indicators and detailed information on strategy operation in real time.

[0046] Based on the same inventive concept, the embodiment of the present invention provides a functional module of a quantitative trading system based on multi-source information data. The principles of each module are similar to the quantitative trading strategy execution method, so the implementation of the method can be referred to, and the repeated parts will not be repeated.

[0047] The embodiment of the present invention provides a quantitative trading system integrating multi-source information data. Figure 5 Schematic diagram of the system in an embodiment of the present invention. The system includes an event engine, a main engine and a service module.

[0048] Among them, the main engine is the core management module of the system, responsible for managing and coordinating the initialization and operation of different modules, including: Module management: responsible for managing each module in the system (such as functions, function engines, interfaces, etc.), initializing and adding different modules through methods such as add_app, add_engine and add_gateway; Event engine startup: responsible for starting the event engine and ensuring that the event engine can handle events in the system.

[0049] The event engine is based on the event loop architecture for processing, supporting scheduled tasks and asynchronous interactions to ensure real-time response and efficient processing of the system. Its core technologies include: Scheduled task processing: Generate scheduled events through timers, and asynchronously trigger these scheduled tasks through the event engine to ensure that the system can periodically execute related tasks; Asynchronous event processing: Using the event loop mechanism and asynchronous non-blocking architecture, event processing will not block other tasks of the system, and supports high concurrency and low-latency event processing; Modular event processor: Schedule corresponding modules for different types of events (such as data subscriptions, transaction instructions, and system alarms).

[0050] At the same time, the system functions are improved through service modules, including:

[0051] Business module: The main functions of the system are completed by integrating core modules such as data management, strategy generation, backtesting and transaction execution. Including:

[0052] The data management module is responsible for receiving, storing and processing data from multiple data sources, ensuring the integrity, validity and timeliness of the data, and providing historical data and real-time market data support required for strategy execution and backtesting;

[0053] Strategy module, based on defined data features, builds prediction models, generates trading signals, and manages trading risks. This module can automatically analyze market trends, output buy and sell signals, and perform necessary risk warnings and stop-loss settings;

[0054] The backtesting module backtests quantitative trading strategies based on historical data and evaluates the performance of strategies under different market conditions. The backtesting results help optimize strategies and improve the success rate and profit performance in actual transactions;

[0055] The trading module performs simulated trading and actual trading operations based on the trading signals and backtesting results generated by the strategy module. This module can update the trading status in real time, track the execution status, and communicate with the exchange to ensure the accurate and timely delivery of trading instructions;

[0056] Core module: provides the core services of the system. According to the functions of the engine, this part is the module that provides specific functional support in the system. Core services include but are not limited to:

[0057] The order management system is responsible for issuing and managing all trading instructions to ensure that orders can respond quickly to market dynamics;

[0058] The log system provides developers and users with real-time operation status tracking, captures system errors and exceptions, and provides strong support for debugging and optimization;

[0059] Email notification module, used to promptly remind users when offline or in case of major events, improving user experience and system transparency;

[0060] Interface module: connects to external API interfaces. According to the functions of the API, this part will build communication with the outside world. It can obtain multi-source information data required by the system from exchange APIs and data providers. The exchange API also takes on the responsibility of communicating with the exchange, implementing order operations, obtaining permissions to interact with the big model from the model API, and performing text analysis on unstructured data through the big model. The callable big models include: GLM-4, Prompt, and Claude2.1, etc.

[0061] In order to lower the technical threshold, the present invention provides a visual setting interface, through which users can easily input quantitative trading parameters. Therefore, as an optional embodiment, before the above S201, the method for executing a quantitative trading strategy provided by the embodiment of the present invention also includes displaying a visual setting interface, specifically including:

[0062] In the above S201 and S202, the configuration information of executing the quantitative trading strategy input by the user through the interface can be received; in the above S203 and S204, the output results of different strategy transactions can be outputted regularly or in real time.

[0063] Figure 6 , Figure 7 and Figure 8 The main interface, backtest interface and strategy interface provided by the embodiment of the present invention. Figure 6 The main interface shown includes a functional area for switching to the other two interfaces and includes account modules connected to external interfaces (such as data packet interface accounts, simulated trading accounts, and real trading accounts) for data acquisition; Figure 7 The backtesting interface shown provides a button for quickly adjusting the strategy code. After the user configures the backtesting parameters, the backtesting can be started with one click. The results will be displayed in the result display area and the visualization display area. Figure 8 The strategy interface shown focuses on simulating actual trading and actual trading functions. Before executing the strategy, the user needs to configure the relevant parameters of the strategy, such as data selection, running time and other strategy parameters.

[0064] As the three visualization interfaces in this embodiment, they respectively assume different functions: the main interface is used for external connections; the backtesting interface supports strategy backtesting using historical data; and the strategy interface is used to execute simulated actual transactions or actual transactions.

[0065] The method and system of the embodiment of the present invention can realize strategy backtesting, simulated trading and real trading through pre-selected multi-source information data, quickly verify the feasibility of the strategy, improve the reliability of the strategy, reduce trading risks, and thus effectively improve the rate of return of real trading.

[0066] In summary, the embodiments of the present invention provide a quantitative trading method and system that integrates multi-source information data. By pre-selecting the required multi-source information data, it is possible to implement strategy backtesting, simulated trading and actual trading, quickly verify the feasibility of the strategy, improve the reliability of the strategy, and reduce trading risks. The above-described embodiments are only descriptions of the preferred embodiments of the present invention, and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solution of the present invention by ordinary technicians in this field should fall within the scope of protection determined by the claims of the present invention.

Claims

1. A quantitative trading method integrating multi-source information data, characterized by: Receiving multi-source information data in a quantitative trading strategy, wherein the multi-source information data at least includes: structured data (such as opening price, trading volume, etc.) and unstructured data (such as economic indicators, news text, etc.); Performing data preprocessing, feature extraction and feature fusion on the multi-source information data, and generating a quantitative trading strategy model; Obtain historical multi-source information data, use the quantitative trading strategy model to perform backtesting evaluation, and generate backtesting results; Determine whether to execute strategy trading based on backtesting results, obtain real-time multi-source information data to simulate actual trading or actual trading, and generate trading results.

2. In the method of claim 1, the receiving of multi-source information data is characterized by: Collect real-time market data, financial report data, news data, etc. Store real-time market data in an efficient database system, such as SQLite database; Connect to data providers through API interfaces to obtain and download historical data in real time and store it in the system database to support subsequent backtesting and execution of real-time trading strategies.

3. In the method according to claim 1, the data feature extraction and feature fusion are characterized by: According to the time period of the unstructured data application, text data (such as news, financial reports, etc.) is obtained from the database, and large model methods (such as GLM-4, prompt and Claude2.1, etc.) are called through the API interface to perform sentiment feature analysis to evaluate the sentiment trend of individual stocks; Based on the structured data (such as market data), relevant indicators are calculated through technical analysis methods to formulate timing operation strategies for quantitative trading; The structured data and the unstructured data are subjected to feature fusion (such as concatenation, addition and multiplication, etc.), and the prediction results of the two types of features are combined to make a comprehensive prediction of the future stock price trend, and a trading decision is generated based on the prediction.

4. In the method of claim 1, the backtest evaluation is characterized by: A backtesting period is defined, wherein the quantitative trading strategy is input according to the characteristic data to perform a backtesting operation and obtain a backtesting result, including: During the backtesting period, the quantitative trading strategy is applied to perform backtesting operations based on the feature data obtained after feature fusion of the multi-source information data to evaluate the performance of the strategy during the historical period.

5. In the method of claim 1, the strategic transaction is characterized by: Simulate actual transactions, wherein, when the backtest results meet the user's requirements, according to the simulated trading interface, control the quantitative trading strategy to perform simulated trading operations and obtain trading results, including: during the simulated trading process, monitor the performance of the strategy in real time, record the running time of the strategy, and automatically terminate the simulated trading when the running time reaches the preset simulated trading time, and output the simulated trading results for subsequent effect analysis and adjustment; Actual trading, wherein, when the simulated trading results meet the user's requirements, the quantitative trading strategy is controlled to execute real trading operations according to the real-time trading interface to obtain actual trading results, including: during the actual trading process, the performance of the strategy is monitored in real time. If the monitoring value exceeds the set indicator, the transaction is automatically terminated, or the user is asked to close the strategy, the transaction is terminated, and the actual trading results are output for subsequent effect analysis.

6. A quantitative trading method system integrating multi-source information data, characterized by: The core engine includes the main engine and the event engine. The main engine is responsible for the management and expansion of system functions and modules, while the event engine is responsible for event scheduling, scheduled tasks, and API interaction, so that the system can efficiently handle concurrent tasks and events. The service module includes business module, core module and interface module, which is characterized by: the engine provides basic services, the function module implements specific business, and the API provides a channel for access and interaction for external systems; Displays a visual setting interface, including a main interface, a backtesting interface and a strategy interface, characterized by: configuration information input by the user and feedback result information.

7. In the system as claimed in claim 6, the core engine is characterized by: The main engine is used to coordinate and manage the overall workflow of the system, handling core functions such as strategy execution, backtesting and trading; The event engine is used to store pending events through the event queue, use the event loop mechanism to continuously process events in the queue, and trigger corresponding operations.

8. In the system as claimed in claim 6, the service module is characterized in that: Functional modules, including but not limited to data management module, strategy module, backtesting module and trading module; Function engine, used to convert the logic of the function into specific operations; Exchange interface, used for the system to interact with external exchanges, perform buy and sell operations, and obtain real-time market data; Data packet interface, which connects different data sources through API to obtain unstructured data such as market data, financial report data, news data, etc. in real time for strategic decision-making; Big model interface, connect different big models through API and use it to analyze unstructured data.

9. In the system according to claim 7, the functional module is characterized in that: Data management module, used to receive, store and process data from different data sources to ensure the validity and timeliness of the data; Strategy module, which builds models and makes predictions based on defined data features, generates trading signals and performs risk management; Backtesting module, which uses historical data to backtest quantitative trading strategies to evaluate the performance and effectiveness of the strategies; The trading module performs simulated actual trading and actual trading operations based on the trading signals and backtesting results generated by the strategy module, and updates the trading status in real time.

10. In the system according to claim 9, the data management module is characterized in that: Data acquisition module, used to collect real-time multi-source information data; The data storage module is used to store real-time multi-source information data in a database (such as SQLite database) and ensure efficient access and timeliness of the data.

Images